CHNSpec Technology （Zhejiang）Co.,Ltd Company News

With the extensive application of plastic products in numerous fields such as automobiles, electronics, and medical care, plastic welding technology, as a key means for connecting plastic products, its welding quality directly affects product performance and service life. Traditional methods for evaluating plastic welding quality, such as visual inspection and destructive tests, have limitations including strong subjectivity, inability to comprehensively reflect internal quality, and potential damage to the products. The emergence of laser transmittance meters has provided a brand-new, efficient, and accurate solution for evaluating plastic welding quality.   I. Working Principle of Laser Transmittance Meter The laser transmittance meter operates based on the principle of light transmission. When a laser beam of a specific wavelength is irradiated onto a plastic sample, some of the light is absorbed, some is scattered, and the remaining light passes through the plastic. The instrument precisely measures the incident light intensity and the transmitted light intensity through a high-precision light detector. For the assessment of plastic welding quality, the laser transmittance meter can sensitively detect the difference in transmittance between the welded and non-welded areas. Welding defects, such as bubbles, inclusions, and incomplete penetration, can alter the microstructure within the plastic and subsequently affect the laser transmittance. For instance, the presence of bubbles will increase light scattering, resulting in a decrease in transmittance; inclusions and foreign substances will change the light propagation path, leading to abnormal transmittance. By analyzing the changes in transmittance, the welding quality can be accurately evaluated.   II. Characteristics and Advantages of the Color Spectrum Laser Transmittance Meter TH-20   The Color Spectrum Laser Transmittance Meter TH - 200 demonstrates outstanding performance in the assessment of plastic welding quality. It features a high-precision optical detection system that enables precise measurement of laser transmittance, with a measurement accuracy of ±0.1%. This high-precision characteristic enables it to sensitively capture minute changes during plastic welding, providing a solid foundation for accurate assessment of welding quality. TH - 200 has a wide spectral measurement range, covering various commonly used laser wavelengths, and is adaptable to the needs of different plastic materials and welding processes. Whether it is used for common polypropylene (PP) plastic welding in automotive manufacturing or polycarbonate (PC) plastic welding in the electronics industry, TH - 200 can accurately measure its laser transmittance.   This instrument is easy to operate and is equipped with an intuitive user interface and automated measurement software. Operators only need to place the plastic sample at the designated position, start the measurement program, and the instrument can quickly complete the measurement and generate detailed data reports. This greatly improves the detection efficiency and is suitable for large-scale detection on production lines. In addition, TH - 200 has good stability and reliability, can operate stably in industrial production environments for a long time, reduces the frequency of equipment maintenance and calibration, and lowers the usage cost.   III. Innovative Application Methods of Laser Transmittance Meter in Plastic Welding Quality Assessment   1.Material screening and evaluation before welding   Before plastic welding, the laser transmittance of different batches of plastic raw materials is tested by using the Color Spectrum Laser Transmittance Tester TH-200. By analyzing the test data, the batches of materials whose laser transmittance meets the requirements of the welding process can be selected, ensuring the consistency and stability of the raw materials. Meanwhile, for cases where different types of plastics need to be welded, TH-200 can assist engineers in choosing plastic material combinations with matching laser transmittance, optimizing the welding process and improving the welding quality. For example, in the welding of automotive interior parts, through the testing by TH-200, selecting appropriate plastic material combinations can effectively reduce welding defects and improve the aesthetics and durability of the interior parts.   2. Real-time Monitoring of Welding Process   Integrate TH - 200 into the plastic welding equipment and monitor the real-time changes of the laser transmittance in the welding area during the welding process. When the welding process parameters fluctuate, such as unstable laser power or changes in welding speed, it will cause abnormal melting and solidification states of the plastic in the welding area, thereby leading to changes in the laser transmittance. TH - 200 can promptly capture these changes and feed back the data to the welding control system. The control system automatically adjusts the welding process parameters based on the feedback data to achieve closed-loop control of the welding process and ensure the stability of the welding quality. For example, on the welding production line of electronic device casings, by monitoring the laser transmittance in real time and adjusting the welding parameters promptly, it can effectively reduce the scrap rate and improve production efficiency.   3. Comprehensive quality inspection after welding   After the welding is completed, the laser transmittance of the welded joint is detected using TH - 200. By comparing the data with the standard data before welding and the real-time data during the welding process, it is possible to determine whether there are defects in the welded joint, such as incomplete penetration, false welding, and pores. For the quality problems detected, the causes can be further analyzed and corresponding improvement measures can be taken. In addition, TH - 200 can also indirectly evaluate the strength of the welded joint. Research shows that there is a certain correlation between the laser transmittance of the welded joint and the welding strength. By establishing a mathematical model of laser transmittance and welding strength, and using the laser transmittance data measured by TH - 200, the strength of the welded joint can be predicted, providing a more comprehensive basis for product quality assessment.   The innovative application of the color spectrum laser transmittance instrument TH - 200 in the quality assessment of plastic welding brings a new quality control method to the plastic welding industry. Through material screening before welding, real-time monitoring during the welding process, and quality detection and assessment after welding, TH - 200 can effectively improve the quality of plastic welding, reduce production costs, and enhance production efficiency. With the continuous improvement of product quality requirements in the manufacturing industry, the application prospects of laser transmittance instruments in the plastic welding field will be even broader. It will continue to promote the development of plastic welding technology and provide strong support for product innovation and quality improvement in various industries.

In the modern field of plastic processing, plastic welding, as a crucial connection technology, is widely applied in numerous industries such as automobile manufacturing, electronic equipment, and medical devices. During the plastic welding process, the measurement of light transmittance is gradually becoming an important aspect that cannot be ignored. What are the scientific basis and practical significance behind this?   The principle of plastic welding is to utilize energy sources such as heat, pressure or ultrasonic waves to make the connection parts of plastic components reach a molten state, thereby achieving molecular fusion. Among various welding methods, laser welding is favored due to its high precision, low heat-affected zone and good sealing performance. When welding plastics with laser, a laser beam needs to pass through the upper layer of plastic, which is absorbed by the lower layer and converted into heat energy, thus achieving the welding. At this time, the light transmittance becomes a key factor affecting the welding quality.   Schematic diagram of plastic welding process   Transmittance directly affects the transmission efficiency of laser energy in plastic materials. If the transmittance of the upper layer plastic is too low, the laser energy cannot effectively penetrate and reach the lower layer plastic, making it difficult to generate sufficient heat to achieve good welding. Conversely, if the transmittance is too high, it may cause the lower layer plastic to absorb insufficient energy, which also affects the welding strength. An appropriate transmittance can ensure the precise distribution of laser energy in plastic materials and achieve high-quality welding results. For example, in the welding of automotive interior parts, the requirements for welding strength and appearance quality are extremely high. Only by precisely controlling the transmittance can the welding parts be firmly and beautifully bonded, avoiding defects such as false welding and detachment. So, how can the transmittance of plastic be accurately measured? This is where the new product of Color Spectrum, the laser transmittance meter, comes into play. This instrument is specifically designed for the transmittance measurement requirements in the field of plastic welding and has many outstanding features. It uses advanced laser light sources and highly sensitive detectors to quickly and accurately measure the transmittance of various plastic materials under specific wavelength lasers. Its measurement accuracy is extremely high, capable of precisely measuring to several decimal places, greatly improving the reliability of the measurement results.   Actual measurement software interface   The Color Spectrum Laser Transmittance Meter is easy to operate and can be mastered by non-professionals. The instrument is equipped with an intuitive operation interface and a clear display screen, making the measurement data immediately understandable. Moreover, it has powerful data storage and analysis functions, capable of conducting statistical analysis on multiple measurement data, providing strong data support for the optimization of plastic welding processes. In practical applications, operators only need to place the sample to be measured on the measurement platform of the instrument and press the measurement button. Instantly, accurate transmittance data can be obtained. This convenience greatly enhances production efficiency and reduces time waste caused by cumbersome measurements.   In the plastic welding process, by using the Chroma Spectra Laser Transmittance Meter to precisely measure the transmittance, enterprises can screen and optimize plastic materials based on the measurement results. For plastics with transmittance not meeting the welding requirements, improvements can be made by adjusting the formula, adding additives, or changing the processing technology. Meanwhile, during the welding process, monitoring the changes in transmittance in real time can promptly identify potential welding problems, such as material batch differences, equipment failures, etc., and take timely measures for adjustment to ensure the stability and consistency of welding quality.   In conclusion, measuring transmittance in plastic welding is of crucial significance. It is not only a key factor in ensuring welding quality but also an important means to promote the continuous optimization and innovation of plastic welding processes. The Chroma Spectra Laser Transmittance Meter, with its advanced technology, outstanding performance, and convenient operation, provides a reliable solution for transmittance measurement in the plastic welding industry, helping enterprises improve product quality and production efficiency in the fierce market competition, and creating greater value.

In the research and production practice of coal industry, it is very important to obtain accurate information of various characteristics of coal for optimizing coal utilization and improving product quality. Hyperspectral image technology, as a powerful means of analysis, can provide abundant information of coal internal structure and composition, and its application is based on efficient and accurate coal sample hyperspectral image acquisition and processing methods. Hyperspectral imaging technology is an advanced technology integrating optics, electronics, computer science and other disciplines. Its working principle is based on the differences in the absorption, reflection and scattering properties of different substances to different wavelengths of light. Through hyperspectral imaging equipment, we can obtain the reflectance information of coal in the continuous spectral range, which is like the "fingerprint" of coal, containing rich material composition and structure information. Compared with traditional imaging technology, hyperspectral imaging technology has higher spectral resolution and can be accurate to the wavelength difference at the nanometer level, which can capture the spectral characteristics of various components in coal in more detail. In this paper, a 900-1700nm hyperspectral camera is used, and FS-15, a product of Color Spectrum Technology (Zhejiang) Co., LTD., can be used for related research. Short-wave near-infrared hyperspectral camera, the acquisition speed of the full spectrum up to 200FPS, is widely used in the composition identification, substance identification, machine vision, agricultural product quality, screen detection and other fields. The application of hyperspectral imaging technology in coal calorific value detection is relatively simple and efficient. First, hyperspectral image data is obtained by scanning coal samples with hyperspectral imaging equipment.The application of hyperspectral imaging technology in coal calorific value detection is relatively simple and efficient. First, hyperspectral image data is obtained by scanning coal samples with hyperspectral imaging equipment.   Hyperspectral image acquisition interface   These data contain information about the reflectivity of coal at different wavelengths. Then, professional data processing software is used to preprocess the acquired image data, remove noise, correct spectrum, etc., in order to improve the quality of data. (a) The original image                                 (b) Area of interest Selection of regions of interest in coal hyperspectral images   Region of interest mean spectral curve   Seven point SG smooth filtering   Due to the characteristics of the instrument itself and the influence of environmental factors, the collected spectrum may have some problems such as wavelength drift and intensity deviation. The purpose of spectral correction is to correct these deviations so that they can accurately reflect the real spectral characteristics of coal samples. Common spectral calibration methods include wavelength calibration and radiation calibration. Wavelength calibration Calibrates the wavelength accuracy of the imaging spectrometer by using standard materials with known spectral characteristics, such as mercury lamps and neon lamps, to ensure that the wavelength value corresponding to each pixel is accurate. Radiometric calibration is to convert the gray value of the image into the actual reflectance value by measuring the standard whiteboard with known reflectance, thus eliminating the influence of factors such as instrument response and uneven illumination on the spectral intensity. The results of multivariate scattering correction are shown in the figure. Multivariate scattering correction results   Standard normal transformation Standard normal transformation result   The acquisition and processing of hyperspectral images of coal samples is a complicated and critical process. By selecting suitable acquisition equipment, optimizing the acquisition process and using advanced image processing methods, abundant and accurate coal information can be extracted from hyperspectral images, which provides strong technical support for the research, production and quality control of coal industry. With the continuous development of technology, the application prospect of hyperspectral image technology in the coal field will be broader, and it is expected to bring new breakthroughs for the development of the coal industry.

In the textile industry, goose down and duck down have become high-quality raw materials for making high-grade thermal products because of their excellent thermal properties. However, there is a big difference in the market price between goose down and duck down. Some bad merchants often mix duck down into goose down for the pursuit of high profits, which not only damages the interests of consumers, but also disrupts the market order. Therefore, accurate and efficient quantitative detection of goose and duck mixed velvet is particularly important. In recent years, the development of hyperspectral camera technology has provided an innovative solution to this detection challenge. 一、Sample preparation: Collect a large number of pure goose down and duck down samples to ensure that their sources are reliable and representative. Use high-precision electronic scales to accurately weigh goose down and duck down according to different proportions, and configure a series of goose and duck mixed velvet samples with known mixing proportions, such as setting 5%, 10%, 15%... Samples of different proportions such as 95% duck down were mixed, and multiple repeated samples were set for each proportion to improve the accuracy and reliability of the experiment. The configured mixed wool sample is evenly laid on the special sample table to ensure uniform sample distribution without overlap and vacancy, and to ensure that the hyperspectral camera can obtain comprehensive and accurate spectral information. 二、Hyperspectral image acquisition: This paper uses a 400-1000nm hyperspectral camera, which can be used for related research FS13, the product of Hangzhou Color Spectrum Technology Co., LTD. The spectral range is 400-1000nm, the wavelength resolution is better than 2.5nm, and up to 1200 spectral channels can be reached. The acquisition speed can reach 128FPS in the full spectrum, and the maximum after band selection is 3300Hz (support multi-region band selection). Each mixed wool sample is photographed multiple times to obtain images from different angles to reduce detection errors caused by local feature differences of the sample. After each shooting, the acquired hyperspectral image data is transferred to the computer for storage in time to avoid data loss. 三、Data preprocessing: The use of professional data processing software to pre-process the hyperspectral image data collected. First of all, the radiation correction is carried out to eliminate the radiation error caused by the performance difference of the camera itself and environmental factors, so that the spectral data between different images are comparable. Geometric correction is then performed to correct the image distortion caused by the camera Angle, sample placement, etc., to ensure that the position of each pixel in the image is accurate. The image is denoised, and the noise interference in the image is removed by filtering algorithm to improve the quality and clarity of the image, so as to extract the spectral features more accurately. 四、Spectral feature extraction: Specific algorithms and software tools are used to extract the spectral features of goose down and duck down regions respectively based on the pre-processed hyperspectral images. Through the analysis and comparison of a large number of image data, it is determined that the specific wavelength range of goose down and duck down can be distinguished significantly in the visible light to near infrared spectrum. At these key wavelengths, the reflectance values of goose down and duck down are carefully measured and recorded to form their own unique spectral feature data sets. For example, after many experimental analyses, it has been found that there are obvious differences in the reflectance curves of goose down and duck down in the wavelength range of 700nm-800nm, which can be used as an important basis for identifying the two. 五、Model establishment and verification: Based on the extracted spectral characteristic data of goose down and duck down, the spectral model for quantitative analysis of goose and duck mixed down was established by using machine learning or statistical methods. Common modeling methods include support vector machine, partial least square method and so on. In the process of modeling, a part of sample data with known mixing ratio is used as a training set to train the model, so that it can learn the internal relationship between the spectral characteristics of goose down and duck down and the mixing ratio. Another part of the sample data that did not participate in the training was used as the verification set to verify the established model. The hyperspectral image data of the validation set samples were input into the model, and the predicted mixing ratio of goose down and duck down was calculated by the model, and compared with the actual known mixing ratio. The accuracy and reliability of the model are evaluated by calculating the error between the predicted value and the true value, such as the root-mean-square error and the average absolute error. According to the verification results, the model is adjusted and optimized, such as adjusting model parameters, adding or reducing feature variables, etc., to improve the performance of the model. 6. Analysis and evaluation of results: The test results of all mixed wool samples were summarized and statistically analyzed. Statistical indexes such as mean value and standard difference of test results under different mixing ratio were calculated to evaluate the stability and repeatability of the test method. The results of hyperspectral camera detection were compared with those of traditional detection methods (such as chemical analysis) to further verify the accuracy of the hyperspectral camera detection method. Through the analysis of a large number of experimental data, the error range, detection accuracy and other key performance indexes of the hyperspectral camera in quantitative detection of goose and duck mixed velvet are obtained. The experimental results show that the method can quickly and accurately detect the precise proportion of goose down and duck down in mixed velvet in a short time, and the detection error can be effectively controlled in a very small range, which fully demonstrates its high reliability and practicability. The application of hyperspectral camera technology greatly improves the accuracy and efficiency of quantitative detection of goose and duck mixed velvet. For production enterprises, it can ensure product quality and maintain brand reputation; For the regulatory authorities, it provides strong technical support for cracking down on counterfeit and shoddy products in the market, which helps to purify the market environment and protect the legitimate rights and interests of consumers. With the continuous development and improvement of technology, it is believed that the application of hyperspectral cameras in the quantitative detection of goose and duck mixed velvet and other related fields will be more extensive and in-depth, and inject new vitality into the healthy development of the industry.

Walnut is an important nut fruit tree and woody oil tree species in China. With its unique flavor and rich nutritional value, walnut ranks first among the four dried fruits in the world. Fruit expansion stage is the first stage of the development of walnut fruit, such as insufficient nutrition in this stage will directly affect the quality and yield of the later fruit. Therefore, the monitoring and diagnosis of nitrogen content of walnut fruit in the expanding stage is of great significance for controlling tree growth and adjusting fine management plan in time. In this study, a 400-1000nm hyperspectral camera was applied, and FS60, a product of Hangzhou Color Spectrum Technology Co., LTD., could be used for related research. The spectral range is 400-1000nm, the wavelength resolution is better than 2.5nm, and up to 1200 spectral channels can be reached. The acquisition speed can reach 128FPS in the full spectrum, and the maximum after band selection is 3300Hz (support multi-region band selection). 一、Preliminary preparation In order to estimate the nitrogen content of walnut canopy by UAV hyperspectral camera, data collection is needed first. Select the appropriate UAV platform equipped with hyperspectral camera, and carry out flight operations in accordance with the predetermined route and height over the Walnut Garden. During the flight, the hyperspectral camera imgrams the walnut canopy at a certain time interval or space interval to obtain a large amount of hyperspectral image data. At the same time, in order to ensure the accuracy and reliability of the data, it is also necessary to collect some reference data simultaneously on the ground, such as the nitrogen content of walnut leaves and canopy structure parameters determined by traditional methods. 二、Results and analysis Canopy range determination, canopy spectrum extraction and accuracy verification As shown in Figure 2, walnut, soil and shadow overlap to a certain extent in the whole band range of the 5-year old walnut forest remote sensing image. In the band range of 520~600nm, the spectral reflectance of the shadows is less than 0.10: the difference of spectral reflectance of walnut and soil is obviously not overlapping, and the spectral reflectance of both is greater than 0.10 in this range. In the range of 750-1000nm, the spectral reflectance of walnut, soil and shadow is significantly different. The spectral reflectance of walnut is greater than 0.7 in the range of 740-900nm, and the spectral reflectance of other non-target vegetation is less than 0.7. Since the spectral reflectance of walnut can be distinguished from other non-target vegetation in green light and near infrared band, but not in one or some bands, it cannot be calculated in ENVI5.3 software. Therefore, in order to facilitate the smooth extraction process of walnut canopy range, the maximum spectral reflectance of walnut canopy in green light and near infrared band is selected in this study Bw(550.7) and B(779.4) were classified and identified to determine the canopy range. Walnut tree, soil and shadow are defined in ENVI5.3 software, that is, when the spectral reflectance at B(550.7) is less than or equal to 0.10 and the spectral reflectance at B(779.4) is less than or equal to 0.20, the shadow is identified and eliminated. When the spectral reflectance at B(550.7) is greater than 0.10 and B; When the spectral reflectance at (779.4) is less than or equal to 0.70, it is identified as soil and removed; When the spectral reflectance at B(550.7) is greater than that at.0.10, the spectral reflectance at B(779.4) is greater than 0.70, walnut tree is identified as the target vegetation. In addition, a support vector machine with good generalization and classification accuracy was used to extract the canopy range, and the accuracy of the canopy range extraction based on spectral features was compared. First of all, in ENVI5.3 software, the ground objects in remote sensing images are divided into walnut tree and other two types (Figure 4), in which the red area is the walnut canopy, and the green area is the other. The separability between the two types of samples was 1.998, and then SVM classifier was selected for supervised classification to obtain the original classification results (FIG. 5a). However, there were often some small patches in the classification results, and its accuracy was difficult to achieve the purpose of final application. Therefore, the Majority small patch processing method was adopted to process the preliminary classification results, and the classification results meeting the actual requirements were obtained (Figure 5b). The accuracy of the classification results was verified, and the Kappa coefficient was 0.997, and the mapping accuracy of the target vegetation walnut was 99.65%. Finally, Matab2014b software was used to overlap the canopy range determined based on spectral features in this study with the canopy range pixels identified by support vector machine method. There were 4257 overlapping pixels in the canopy range, and the number of canopy range pixels selected based on spectral features accounted for 96.77% of the number of pixels in the support vector machine, with a mapping accuracy of 96.43 %, high precision, overlapping results are shown in Figure 6 At present, the application of UAV hyperspectral camera in estimating nitrogen content of walnut canopy is still in the stage of continuous development and improvement. In the future, with the continuous progress of technology, the performance of hyperspectral cameras will be further improved, the spectral resolution and imaging quality will be higher, and the data processing and analysis methods will be more intelligent and automated. At the same time, the development of multi-source data fusion technology, such as the combination of hyperspectral data with lidar data and thermal infrared data, will be able to obtain more comprehensive and accurate growth information of walnut trees, and further improve the accuracy and reliability of nitrogen content estimation. In addition, with the in-depth promotion of the concept of precision agriculture, UAV hyperspectral camera technology is expected to be more widely used in the field of walnut planting, providing strong technical support for the sustainable development of the walnut industry. In summary, UAV hyperspectral camera, as an advanced remote sensing monitoring technology, has a broad prospect and great potential in the application of walnut canopy nitrogen content estimation. Accurate and rapid estimation of walnut canopy nitrogen content can provide scientific basis for walnut growers to make fertilization decisions, achieve accurate fertilization, improve fertilizer utilization, reduce resource waste and environmental pollution, and promote the high-quality development of walnut industry.

Orange peel has good economic value and medicinal value, but the phenomenon of fake and shoddy in the market is serious. In particular, as an important index to measure the quality of orange peel, the accuracy and efficiency of manual detection methods are low. In this paper, hyperspectral imaging technology combined with deep learning method was used to establish a fast and non-destructive identification method for the aging year of orange peel. 一、Materials and methods The purchased orange peel samples were divided into 1 year, 5 years, 10 years and 15 years according to the aging years. As shown in Figure 1, 120 orange peel samples were collected for each year, and a total of 480 orange peel samples were collected. The orange peel samples of each year were randomly divided in a ratio of 7:3, in which 84 samples entered the training set and 36 samples entered the test set. In this paper, a 900-1700nm hyperspectral camera is used, and FS-15, a product of Color Spectrum Technology (Zhejiang) Co., LTD., can be used for related research. Short-wave near-infrared hyperspectral camera, the acquisition speed of the full spectrum up to 200FPS, is widely used in the composition identification, substance identification, machine vision, agricultural product quality, screen detection and other fields. 二、Results and analysis The spectral curves of orange peel samples in different years are shown in Figure 3. The original spectral curves shown in Figure 3 can obviously find that there are absorption peaks near 1200m and 1450nm. The absorption peak at 1200nm is mainly caused by the spectral absorption of bond pairs, and the absorption peak at 1450nm is mainly caused by the spectral absorption of water. The bands of the NIR spectra of all kinds of samples overlapped closely, the overall trend was close to the same, and the absorption peak was almost in the same position, with no obvious difference. It was difficult to distinguish the four kinds of orange peel samples by naked eye. 三、Spectral pretreatment method The pretreatment of hyperspectral data of orange peel includes several steps, which are image segmentation, spectrum averaging and spectrum preprocessing. The original average spectrum of orange peel samples in different years and the average spectral curves after SG+D1 pretreatment are shown in Figure 4. It can be seen from FIG. 4(a) and FIG. 4(b) that the SG+D1 combined pretreatment method can effectively eliminate the influence of spectral baseline drift and smooth the spectral curve, thus improving the accuracy of orange peel year identification. Rapid identification of orange peel year by hyperspectral camera has broad application prospect in Chinese medicine industry. On the one hand, it can help Chinese medicine manufacturers and dealers accurately control the quality and year of orange peel, and avoid economic losses and reputation risks caused by misjudgment of year. On the other hand, in terms of market supervision, relevant departments can use the technology to carry out rapid sampling of orange peel products on the market, crack down on shoddy and other behaviors, and maintain the normal order of the market. In addition, with the continuous improvement and popularization of the technology, it will also provide strong support for the scientific research and quality evaluation of orange peel, and promote the development of orange peel industry in a more standardized, standardized and scientific direction.

In the evaluation of dairy nutrition, the protein content is the most important indicator that milk is an essential source of protein absorption in People's Daily life. In recent years, the health of consumers and the development of the dairy industry are closely related to the quality of milk. Therefore, the detection of milk protein content is a very important link. Traditional detection methods consume a long time, waste a lot of human resources, and lead to environmental deterioration. Therefore, it is of great significance to find a faster and more accurate method for detecting milk protein content. Therefore, this paper uses machine learning combined with hyperspectral imaging technology to quantitatively evaluate milk protein content, providing a feasible scheme for milk protein content detection on the market. Specific research work and conclusions are as follows:   一、Experimental materials We bought seven different brands of pure milk, including Mengniu, New Hope, Yili and Guangming, and stored them in the refrigerator. Protein content is shown in Table 1. 二、Experimental equipment In this paper, a 400-1000nm hyperspectral camera is used. FS13, a product of Hangzhou Color Spectrum Technology Co., LTD., can be used for related research. The spectral range is 400-1000nm, the wavelength resolution is better than 2.5nm, and up to 1200 spectral channels can be reached. The acquisition speed can reach 128FPS in the full spectrum, and the maximum after band selection is 3300Hz (support multi-region band selection). 三、Experimental setting method The hyperspectral images of milk samples were collected by using the hyperspectral spectrometer. Samples were collected three times for each type of milk, and then a clear image was selected from ENVI5.3. The collected spectral image had a resolution of 777x1004 pixels. The exposure time of the hyperspectral imager was 10ms, the pixel mixing times were 6, the resolution was 4.8nm, the average interval was 0.8nm, the vertical distance was 30cm, and the acquisition condition was room temperature (23~25°C). The imaging spectrometer and scanning head are installed together during the shooting, and the average spectral data of the milk is derived from the hyperspectral image using the ENVI software." 四、Extraction and preprocessing of hyperspectral data Extracting hyperspectral reflectance data from hyperspectral images is the basis of traditional machine learning modeling. Generally, the spectral reflectance data of samples is obtained by extracting the average spectral reflectance of all pixels in the region of interest (ROD). In this paper, ENVI software was used to open the corrected hyperspectral image of milk sample, and the pixel near the center of each hyperspectral image was selected as the ROI with the rectangle tool. A total of 30 ROI and 7 hyperspectral images were selected, and 210 ROI were selected. The average spectral reflectance of all pixels in ROI was calculated as the spectral data of the sample, a total of 210 spectral data. The spectral data is saved in ASCI format. The following figure shows the process of extracting ROI. In this paper, hyperspectral imaging technology combined with machine learning was used to predict milk protein content in order to improve the accuracy of milk protein content prediction. Hyperspectral imaging system was built, hyperspectral images of 7 kinds of milk brands on the market were collected, spectral data were extracted by ENVI software, milk hyperspectral data set was established, and 210 hyperspectral data were extracted finally. Hyperspectral imaging technology has shown great potential in the field of milk protein content detection, although there are some challenges at this stage, but with the integration of interdisciplinary technology innovation, it will gradually revolutionize the traditional milk detection mode. Through continuous optimization of the technical system and solving practical application problems, hyperspectral imaging will become an indispensable and powerful tool for dairy quality control, help improve the economic and social benefits of the milk industry, and meet the growing demand of consumers for high-quality dairy products.

With the improvement of living standards, people have higher and higher requirements for the taste and nutrition of lotus seeds. Lotus seed as a medicine is also a kind of tonic, its amylose content directly affects the quality and taste of lotus seed. The amylose content of lotus seeds varies greatly among different varieties, so the determination of amylose content of lotus seeds is of great significance for subsequent processing. The traditional amylose detection is generally using iodine colorimetry, iodine affinity titration and cross-cutting infection method, these methods are time-consuming and laborious, and easy to be affected by experimental conditions! Hyperspectral imaging technology is a non-destructive testing technology that can obtain rich spectrum and image information. Compared with chemical detection methods, it has the advantages of saving time, labor and environmental protection. In this paper, hyperspectral imaging technology was used to detect amylose of fresh lotus. 一、Materials and methods   1.1 Test materials The samples were from Fujian province, and the varieties of Xuanlian, Guangchanglian, Jianxuan 36, Mantianxing, Space lotus and Xianglian were selected. After picking at maturity, the fresh lotus seed was stored in liquid nitrogen and transported to the laboratory, where it was refrigerated at 4 ° C for 12 hours. 1.2 Hyperspectral image acquisition and correction The main components of hyperspectral imaging system include hyperspectral imager, light source, stage, black box and hyperspectral data acquisition software. The whole system can use the color spectrum hyperspectral camera fs-13, which can collect the spectral range of 400nm~1000nm, and the spectral resolution is 2.5nm. The hyperspectral imaging system is shown in Figure 1. The moving speed of the payload platform is set to 3.5mm/s and the exposure time is 30ms. The lens is 40cm away from the moving platform and straight down. Adjust the focal length of the camera of the spectrometer for black and white correction of the system. 1.3 Data Processing Analysis software was used to extract the average spectrum of the region of interest (ROI) from the spectral image of lotus seeds. In order to eliminate the influence of noise and external stray light, the modeling effect of pre-processing methods such as first derivative, second derivative, SG smoothing, multiple scattering correction (MSC) standard normal variable conversion was compared, and the best pretreatment method was selected. 二、Results and analysis   2.1 Average spectrum of the region of interest In this paper, the spectral curve of each pixel in the region of interest of a single sample is used for subsequent processing. The average spectral diagram after removing the head and tail noise (400nm~971nm) is shown in Figure 2. It can be seen from the figure that the variation trend of spectral values of different samples is consistent. The band has an obvious upward shift between 460nm and 570nm, which may be caused by the shift in the water band. The band has a relatively obvious absorption between 500nm and 920nm. It may be related to quaternary frequency doubling, O-H secondary frequency doubling and O-H primary frequency doubling of C-H group in amylose molecule. 2.2 Amylose content of lotus seeds The results of correction set and prediction set of amylose content divided by SPXY method are shown in Table 1. It can be seen from the table that the amylose content of fresh lotus seeds varies greatly. The maximum value of amylose content of corrected lotus seeds is 227.90 mg/g, the minimum value is 100.82 mg/g, and the standard deviation is 44.73mg/g. The amylose content of the predicted sample is within the range of the correction set sample, so the sample division is reasonable. 三、Conclusion In this paper, hyperspectral imaging technology was used to rapidly detect amylose content. The results show that the modeling effect is the best after using first derivative and multiple scattering correction MSC). Then SPA was used to extract 9 feature bands. The corrected set correlation coefficient (R) of the PLSR prediction model was 0.835, the corrected set root mean square error (RMSEC) was 1.802, the predicted set correlation coefficient (R) was 0.856, and the predicted set root mean square error (RMSEP) was 1.752. The relative analysis error (RPD) was 1.944. The correlation coefficient of prediction set of PLSR prediction model established by RC method (R. The prediction set root mean square error (RMSEP) was 1.897. The relative analysis error (RPD) was 1.761. This study provided a thought for further developing an on-line detection instrument for amylose content, and laid a good foundation.

As an important cash crop, pumpkin seed vitality is directly related to the emergence rate, seedling growth potential and final yield after sowing. The traditional methods of seed vitality detection, such as germination test, are time-consuming and laborious, and can not meet the needs of rapid and large-scale seed quality detection in modern agriculture. Hyperspectral imaging technology combines the advantages of spectroscopy and imaging, and can obtain the spectral information and spatial information of samples at the same time, which shows great potential in the field of seed viability nondestructive testing. 一、Preparation of experimental materials Divide the pumpkin seeds into 4 groups of 100 seeds and place them in a nylon mesh bag, as shown in Figure 3-2. Put a group of pumpkin seeds in the dryer every other day. The specific procedure is as follows: take out 3 groups of samples, put the first group of samples in the dryer, put the second group of samples in the dryer 24 hours later, put the third group of samples in the dryer 24 hours later, and take out all the samples with aging time of 1 to 3 days respectively after 3 days (the first group is the samples with aging time of 3 days). Group 2 is for samples aged for 2 days, and Group 3 is for samples aged for 1 day). The remaining 1 of the 4 groups was not subjected to aging treatment and was placed at room temperature for 3 days during the aging group experiment. 二、Hyperspectral data acquisition Seeds with different aging days were collected by a color spectrum hyperspectral camera, and hyperspectral images of 400-1000nm were taken for all samples. After the spectral data were extracted, a total of 400 spectral curves were obtained, as shown in the figure. Observe the growth every day, and pour the right amount of water to ensure the water needed for germination. The germination was recorded once on the third and fifth days respectively. The following is the pre-germination test diagram of pumpkin seeds. According to the vitality level of each seed, the average spectral data of each seed was classified, and the overall spectral curve of each grade was shown in the figure below. 三、Spectral data processing The original hyperspectral image is susceptible to noise and uneven illumination. Median filter is adopted to remove salt and pepper noise, and the illumination difference is eliminated based on the reflectivity correction of the standard whiteboard. The region of interest (ROI) is extracted from the corrected image, focusing on the seed embryo and endosperm to ensure the accuracy of subsequent feature extraction. Dimensionality reduction methods such as principal component analysis (PCA) are used to compress data initially, retain key information and reduce computation. 四、Conclusion and Prospect In this study, a pumpkin seed vitality detection model based on hyperspectral imaging technology was successfully constructed to realize rapid, non-destructive and high-precision vitality identification, and provide an efficient technical solution for the quality control of pumpkin seed industry. Follow-up research can be extended to more crop seeds, and multi-modal data (such as fluorescence spectrum, thermal imaging, etc.) can be integrated to further improve the detection accuracy in complex environments. Combined with Internet of Things technology, an online monitoring system for seed vitality can be built to help real-time control and accurate screening of seed quality in smart agriculture.

Tea inchworm is one of the common pests in tea gardens, which seriously affects the yield and quality of tea. The traditional method of monitoring the damage degree of tea inchworm mainly relies on manual investigation, which has some problems such as low efficiency, strong subjectivity and difficult to realize real-time monitoring in large area. Hyperspectral remote sensing technology has the characteristics of high spectral resolution and rich spectral information, which provides a new way for rapid and accurate monitoring of the harm degree of tea inchworm. 一、Environmental conditions The spectral reflectance of tea canopy was measured from 10:00 to 14:00 on a sunny day with no wind, no cloud and good solar visibility. In this study, a 400-1000nm hyperspectral camera was applied, and FS13, a product of Hangzhou Color Spectrum Technology Co., LTD., could be used for related research. During the observation, the field of view Angle was 25, and the height between the detection head of the hyperspectral camera and the top of the tea canopy was about 0.5m. The diameter of the observation range was about 0.22m. In order to reduce the experimental error, the measurements were repeated three times in each sample area, and the average value was taken as the spectral reflection value.   二、 Data processing and analysis 1. Comparison of leaf surface appearance between normal tea and tea inchworms. In this experiment, a series of tea leaves harmed by tea inchworms to different degrees were collected as research subjects, and their spectral data, leaf area index and the number of tea inchworms per mu of tea ruler were respectively collected. The comparison between tea leaves without insect pests and those harmed by tea inchworms was shown in Figure 1: The leaves were intact, the leaves were crowded together, and the leaves of the insect-damaged tea were bitten into irregular shapes, their external color became dark yellow, and the structure of the leaves also changed accordingly. 2. Comparison of leaf area index between normal tea and tea inchworm. As can be seen from FIG. 2, the leaf area index was greatly affected by the degree of harm caused by tea geometrid. The more tea ruler there were, the more tea leaves were eaten, and the smaller the leaf area index would be. 3. The influence of tea inchworms on the reflectance spectral characteristics of tea canopy. The influence of insect infestation on tea leaves will lead to some changes in the physical and chemical properties of tea leaves, including the color, structure, water content, chlorophyll content and nutritional status of the leaves. The change of these physical and chemical properties will cause some changes in the value of its spectral characteristic parameters, such as spectral reflectivity, transmittance, absorptivity, red peak and its wavelength position and blue peak and its wavelength position. Therefore, to grasp the normal tea spectral characteristics and related information is the premise and basis of studying the damage of tea by other diseases and pests. 三、Research significance and prospect Research significance: This study provides a new technical means for the rapid and accurate monitoring of the harm degree of tea inchworms, helps to timely grasp the occurrence of tea inchworms in tea gardens, provides scientific basis for the accurate prevention and control of diseases and pests in tea gardens, reduces the use of pesticides, and improves the yield and quality of tea. Research prospects: Future studies can further optimize hyperspectral remote sensing models and improve the accuracy and stability of the models. At the same time, it can be combined with UAV remote sensing, satellite remote sensing and other technologies to achieve a larger range of tea inchworm harm degree monitoring. In addition, the relationship between the harm of tea inchworms and the physiological and ecological changes of tea trees can be deeply studied, and the mechanism of hyperspectral remote sensing monitoring can be revealed from a deeper level.

Wood moisture content is an important attribute of wood quality, which has an important impact on wood processing, use and storage. Although the traditional methods of measuring wood moisture content such as weighing method and resistance method have certain accuracy, they have some disadvantages such as cumbersome operation, long measurement time and damage to wood. Hyperspectral imaging provides a fast, non-destructive and efficient method for measuring wood moisture content. 一、hyperspectral camera test principle Hyperspectral cameras can obtain spectral information of the wood surface, which includes the reflectivity or transmission of the wood at different wavelengths. Since the moisture content of wood will affect its spectral characteristics, the moisture content can be deduced by analyzing the spectral information of wood. Specifically, the spectral data of wood can be collected by hyperspectral imaging technology, and the prediction model between wood moisture content and spectral information can be established by pre-processing, feature extraction and modeling, so as to realize the rapid test of wood moisture content. 二、Application examples Instrument: Color spectrum built-in push sweep FS-17 near infrared high spectrometer Auxiliary equipment: Constant spectral light source - for indoor modeling Light source: linear halogen light source Experimental materials: A number of wood samples with different moisture content are used as experimental materials, and these wood blocks are cyclically dried to obtain different moisture content states. Data acquisition: Spectral image acquisition of wood samples was carried out using hyperspectral imaging system. In the acquisition process, it is necessary to ensure that the lighting conditions are stable to avoid the impact of light changes on the spectral information. At the same time, in order to obtain more accurate results, spectral image acquisition can be carried out at multiple locations of the wood sample, and the average value is taken as the final spectral data. Data processing: Pre-processing the collected spectral data, such as removing noise, correcting spectrum, etc. Then feature selection algorithm is used to extract the characteristic wavelength related to wood moisture content to simplify the model and improve the prediction accuracy. Model building: Based on the extracted characteristic wavelength, the prediction model between wood moisture content and spectral information was established. Common modeling methods include Gaussian process regression (GPR), partial least squares regression (PLSR) and so on. These models can quickly predict the moisture content of wood based on its spectral information. Model validation: The established model is validated using an independent validation set to assess its predictive performance and accuracy. Common evaluation indexes include correlation coefficient (R²) and root mean square error (RMSE). 三、Application advantages Fast test: The hyperspectral camera can obtain the spectral information of the wood surface in a short time, so as to realize the rapid test of the wood moisture content. Non-destructive testing: Compared with traditional testing methods, hyperspectral imaging technology does not cause damage to the wood, so it is more suitable for testing valuable wood or wood that needs to be maintained in integrity. High accuracy: By establishing an accurate prediction model, hyperspectral cameras can achieve high-precision testing of wood moisture content, meeting the stringent quality control requirements of the wood processing industry. 四、Application prospect With the continuous development and improvement of hyperspectral imaging technology, its application prospects in wood moisture content testing will be more broad. In the future, we can look forward to the emergence of hyperspectral cameras with higher precision, faster speed and easier operation to meet the needs of the wood processing industry for quality control and intelligent production. At the same time, combined with advanced technologies such as machine learning and deep learning, the accuracy and intelligence level of wood moisture content testing can be further improved. In summary, hyperspectral cameras have significant advantages in testing wood moisture content, providing an efficient, accurate and non-destructive inspection method for the wood processing industry.

In today's era of rapid development of science and technology, color measurement has a vital position in many fields, from product quality control, artistic creation to scientific research. As an advanced optical device, hyperspectral camera brings a new, more accurate and comprehensive solution for color measurement. 一、the basic principle of hyperspectral camera The working principle of hyperspectral cameras is based on the fine capture of spectral information. Unlike traditional cameras, which can only record the color information of the three channels of red, green and blue, hyperspectral cameras can divide the spectrum into many narrow bands in a wide spectral range such as visible light to near infrared, usually up to hundreds or even more. For example, it can divide the spectral range of 400-1000nm into bands with very small intervals, such as 1nm or smaller intervals. When light shines on the surface of the measured object, the reflection, absorption and transmission characteristics of the object to different wavelengths of light are different. Through its special optical system and detector, the hyperspectral camera collects the intensity of the light signal of each band in turn, so as to construct the spectral reflectance curve of the object. This curve records in detail the reflectivity of objects at various wavelengths and is the basic data source for color measurement.   二、the specific process of color measurement (1) Calibration Calibration is a critical step before using a hyperspectral camera for color measurement. The purpose of calibration is to establish an accurate correspondence between the spectral data captured by the camera and the true color values. Standard whiteboards with known spectral properties are often used as calibration references. Standard whiteboards have stable and precisely known reflectance at various wavelengths. The hyperspectral camera takes pictures of the standard whiteboard, records its optical signal intensity in each band, and calculates the response function of the camera according to the known spectral reflectance data of the standard whiteboard, so as to correct the possible spectral deviation, dark current noise and other error factors of the camera, and ensure the accuracy and reliability of the subsequent measurement data.   (2) Image collection After the calibration is completed, the image of the target object can be acquired. When a hyperspectral camera takes pictures of an object, it obtains the intensity information of the light reflected by the object band by band according to the preset spectral band range and resolution. For example, for each pixel in an image, its reflected light data across multiple spectral bands is recorded. If the camera divides the spectral range into 200 bands, then each pixel will have 200 corresponding spectral reflectance values. Together, these data form a three-dimensional data cube, where the two-dimensional plane represents the spatial position information of the image (x, y coordinates), and the third dimension represents the spectral band information (λ). In this way, the hyperspectral camera not only records the color and appearance information of the object, but also contains its spectral characteristics information, which provides more abundant data than traditional cameras.   (3) Data processing and color calculation The massive spectral data collected need to go through complex data processing to get the final color measurement results. First of all, the data should be preprocessed, including removing noise, correcting spectral distortion and other operations. Then, the color is calculated according to a specific color model and algorithm. In the field of color science, the commonly used color models are CIE XYZ, CIELAB, etc. Taking the CIELAB color model as an example, it represents color as three coordinate values based on the human eye's perception characteristics of color: L represents the brightness, a represents the red-green degree component, and b * represents the yellow-blue degree component. By combining the spectral reflectance data collected by the hyperspectral camera with the spectral power distribution of the standard illumination body (such as the D65 standard light source), and integrating according to the color matching function, the coordinate value of the object in the CIELAB color space can be calculated, so as to accurately describe the color attribute of the object. Such as color depth, tone and saturation. In addition, color difference can also be calculated by comparing the color coordinate values of different objects or different parts of the same object, which is used to evaluate the consistency or degree of change of color. 三、the advantages of hyperspectral camera color measurement (1) High precision and high resolution Hyperspectral cameras provide extremely high spectral resolution, which allows them to capture extremely fine color differences in color measurements. For example, in some industries that require very high color accuracy, such as high-end printing, cosmetics production, etc., it can accurately distinguish color changes that are difficult for the human eye to detect, ensuring the consistency of product color and high quality standards. Its high-precision measurement results help to improve the quality control level of products and reduce the rate of defective products caused by color deviation.   (2) Rich spectral information In addition to the tristimulus value information of the color, the spectral reflectance curve obtained by the hyperspectral camera contains detailed information about the object over the entire measured spectral range. This has unique advantages for the color analysis of some special materials or objects. For example, in the field of cultural relics restoration and protection, by analyzing the spectral characteristics of pigments on the surface of cultural relics, we can understand their composition and age information, which provides an important basis for restoration work. In the field of agriculture, the growth status, nutrient content and disease and insect pests of plants can be monitored according to the changes in the spectral reflectance of plant leaves, because the absorption and reflection characteristics of different wavelengths of light will change in different growth stages and health states of plants.   (3) Non-contact measurement Hyperspectral cameras do not need to make direct contact with the object being measured, which is important in many cases. For some fragile, precious or difficult to reach objects, such as art, cultural relics, biological samples, etc., non-contact measurement can avoid damage or pollution to the object. At the same time, it can also achieve fast, large area color measurement, improve the measurement efficiency. For example, in the color detection of large-scale mural paintings, the color information of the entire mural can be quickly obtained, providing comprehensive data support for protection and restoration work.   四、Experimental test of hyperspectral camera in color measurement 1. Experimental purpose Test the Lab value of the sample below 2. List of experimental testing instruments Device name Model number Configuration details Remark CHNSpec hyperspectral camera FS-13 Spectral range: 400-1000nm; Spectral resolution: 2.5nm Spectral band: 1200       3. Experimental content The reflectance curve was obtained by external push scan detection of 400-1000nm hyperspectral camera The experimental measurement process is shown in the figure below: 4. Conclusion The hyperspectral camera FS-13 was used to shoot the customer's samples, and the Lab value of each sample was obtained from the hyperspectral image analysis, which could be used to replace the color difference meter, and the test stability was good, the sampling position of the test sample was flexible, and multi-point measurement could be made to realize automatic detection.