Optical glass stress detection system method
Through the optical glass stress detection system with real-time dynamic monitoring and high-speed image processing, the problems of complex operation, unstable accuracy and inability to monitor stress changes in real-time in the prior art are solved, and fast and accurate detection and real-time dynamic monitoring of the stress distribution of optical glass are achieved.
Patent Information
- Application Number
- CN202411671290.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-21
- Publication Date
- 2025-03-14
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing optical glass stress detection methods are complex in operation and require professional operation. The time is long and the accuracy is affected by environmental factors, so it is impossible to monitor stress changes dynamically in real time.
The optical glass stress detection system is adopted with real-time dynamic monitoring and high-speed image processing, and through high-speed image acquisition, real-time image processing and data analysis technology, the rapid, accurate and non-destructive detection of the stress distribution of optical glass is achieved.
It realizes rapid and accurate detection of stress distribution of optical glass, can monitor stress changes dynamically in real time, and improves the efficiency of product quality control and production process optimization.
Smart Images
Figure CN119618436A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of optical stress analysis, and in particular to an optical glass stress detection system method. Background Art
[0002] With the continuous development of science and technology, the application field of optical glass is also expanding, and the quality and performance requirements of optical glass are getting higher and higher. During the production, processing and use of optical glass, its internal stress distribution state has a vital impact on product quality and performance. The optical glass stress detection system is an advanced equipment specially used to detect the internal stress distribution of optical glass. It combines image processing, data analysis and optical principles, and can obtain the stress information inside the optical glass in real time and accurately.
[0003] However, the current traditional optical glass stress detection methods usually require complex operation processes, professional operators, and a long operation time, which is not conducive to real-time and rapid detection needs. Moreover, the detection accuracy is often affected by environmental factors, resulting in unstable test results and difficulty in accurately reflecting the stress conditions of the optical glass. In addition, these methods can usually only provide static stress distribution information and cannot dynamically monitor stress changes in real time.
[0004] Therefore, how to develop an optical glass stress detection system method that can use advanced image processing and data analysis technology to realize real-time dynamic monitoring of optical glass stress distribution is still an urgent problem to be solved in the development of the current optical glass stress detection system. Therefore, developing an optical glass stress detection system method that can acquire and analyze stress data in real time is of great significance to improving product quality, preventing potential risks and optimizing the production process. Summary of the invention
[0005] Aiming at the shortcomings of existing optical glass stress detection methods, the present invention proposes an optical glass stress detection system method based on real-time dynamic monitoring and high-speed image processing. This method realizes fast, accurate and non-destructive detection of optical glass stress distribution by integrating high-speed image acquisition, real-time image processing and data analysis technology, providing strong technical support for product quality control and production process optimization.
[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a real-time monitoring and detection system, characterized in that the system comprises the following components:
[0007] Real-time image acquisition module: Use the set light source to illuminate the optical glass, start the high-speed image acquisition device, capture the stress distribution image inside the optical glass in real time, and transmit the captured image data to the high-speed image processing unit in real time;
[0008] High-speed image processing module: After receiving the image data, the image processing unit performs image enhancement processing through the Gaussian filtering algorithm to improve the contrast and clarity of the image, performs denoising processing on the enhanced image to eliminate noise interference in the image, performs feature extraction, and extracts the key features of stress distribution from the processed image;
[0009] Data analysis and early warning module: Use linear mapping and moving average algorithm to analyze the received stress distribution characteristic data in real time, calculate the specific value and change trend of stress distribution, display the analysis results to the user in real time, and make judgments based on preset thresholds. When the real-time monitored stress data exceeds the preset threshold, the system automatically issues an alarm to remind users to deal with potential problems in a timely manner;
[0010] Production process optimization module: According to the real-time monitoring stress data and early warning information, the parameters and conditions in the production process are adjusted, and the production parameters and conditions are continuously optimized through machine learning algorithms to improve the quality and stability of optical glass. The stress data changes in the production process are recorded and analyzed to provide a reference for subsequent process improvements and quality improvements.
[0011] Furthermore, the real-time image acquisition module specifically comprises the following steps:
[0012] (1) Image acquisition: Use the set light source to illuminate the optical glass, start the high-speed image acquisition device, and capture the stress distribution image inside the optical glass in real time;
[0013] (2) Data transmission: The captured image data is transmitted to the high-speed image processing unit in real time.
[0014] Furthermore, the high-speed image processing module specifically comprises the following steps:
[0015] (1) Data processing: After receiving the image data, the high-speed image processing unit performs image enhancement processing to improve the contrast and clarity of the image, and performs denoising processing on the enhanced image to eliminate noise interference in the image;
[0016] (2) Feature extraction: The key features of stress distribution are extracted from the processed image and transmitted to the data analysis unit.
[0017] Furthermore, the data analysis and early warning module includes the following specific steps:
[0018] (1) Data analysis: Use the preset stress analysis algorithm and model to analyze the stress distribution data in real time and calculate the specific value and change trend of the stress distribution;
[0019] (2) Result judgment: The analysis results are displayed to the user in real time and the analysis results are judged according to the preset threshold;
[0020] (3) Early warning reminder: When the real-time monitored stress data exceeds the preset threshold, the system automatically issues an alarm to remind the user to deal with potential problems in a timely manner.
[0021] Furthermore, the production process optimization module includes the following specific steps:
[0022] (1) Parameter adjustment: Adjust the parameters and conditions in the production process based on real-time monitoring stress data and early warning information. Improve the quality and stability of optical glass by continuously optimizing production parameters and conditions.
[0023] (2) Process optimization: Record and analyze stress data changes during the production process to provide a reference for subsequent process improvement and quality improvement.
[0024] Furthermore, the high-speed image processing module calculates the weighted average value of each pixel through Gaussian filtering to reduce image noise and details and smooth the image. The mathematical formula of Gaussian filtering can be accurately expressed in the form of convolution. Given an image f(x, y) and a Gaussian kernel G(x, y) of size (2k+1)×(2k+1), the value of the Gaussian filtered image g(x, y) at each pixel point (i, j) can be calculated by the following convolution formula: Here, f(i+m, j+n) is the pixel value of the original image f(x, y) at position (i+m, j+n), and G(m, n) is the weight value of the Gaussian kernel at position (m, n). The convolution operation involves aligning the center of the Gaussian kernel with the current pixel point (i, j) in the image, then multiplying each element in the kernel with the image pixel value it covers, and adding all the products. In practical applications, the Gaussian kernel G(x, y) is calculated by the Gaussian function, and its formula is: Among them, (x, y) is the coordinate relative to the center of the Gaussian kernel, and σ is the standard deviation of the Gaussian function, which determines the width of the Gaussian function and thus affects the blurriness of the image.
[0025] Furthermore, the data analysis and early warning module performs real-time analysis on the stress distribution data by linear mapping and calculating the moving average, and calculates the specific value and change trend of the stress distribution. The formula of linear mapping is stress = a × feature + b, where stress is the calculated stress value, feature is the feature extracted from the image (such as pixel intensity), and a and b are coefficients determined by experimental data or physical models. In this way, the module can convert the feature information in the image into a measurable stress value. After completing the stress quantification, the data analysis and early warning module further uses the algorithm formula of trend analysis to predict the change trend of the stress value. For simple statistics, the module will calculate the mean and standard deviation, using the following formula: These statistics help to understand the overall distribution and fluctuation of stress values. For time series analysis, the module may use a moving average algorithm to smooth the data and predict future trends. The moving average formula is as follows: By calculating the moving average, the module can predict the stress change trend over a period of time in the future.
[0026] Furthermore, the production process optimization module achieves precise adjustment and optimization of the production process by applying statistical analysis algorithms, machine learning algorithms and optimization algorithms to improve the quality and stability of optical glass. The statistical analysis algorithm is mainly used to perform descriptive statistics and anomaly detection on the real-time monitored stress data. The mean reflects the average level of stress data, and its calculation formula is: The standard deviation is used to measure the dispersion of stress data. The calculation formula is: These statistics can help identify stability issues in the production process and whether there are abnormal stress values. The calculation formula for anomaly detection is When the stress value exceeds the preset threshold, it is considered abnormal. The machine learning algorithm is used to establish a prediction model, predict the stress value based on historical data, and adjust the production parameters according to the prediction results. The linear regression equation is used to establish the linear relationship between the production parameters and the stress value. The calculation formula is y=β0+β1x1+β2x2+…+β n x n ,The prediction model can predict possible future stress values based on real-time ,monitored stress data, and adjust the production parameters accordingly. ,The optimization algorithm is used to automatically adjust the production parameters to minimize the stress values or ,stress fluctuations based on the stress data and prediction results. ,The genetic algorithm can search for the optimal solution in the parameter space by simulating natural ,selection and genetic mechanisms. ,These optimization algorithms can automatically adjust the production parameters based on real-time feedback and ,achieve automatic optimization of the production process.
[0027] Furthermore, the method comprises the following specific steps:
[0028] (1) System preparation and setup
[0029] Turn on the optical glass stress detection system to ensure that all modules are in normal working condition;
[0030] Through the user interface of the system control module, set the parameters of the image acquisition module to adapt to different detection requirements and environmental conditions;
[0031] According to the size and shape of the optical glass to be inspected, the position and angle of the image acquisition device are adjusted to ensure that the image of the optical glass can be fully and clearly acquired.
[0032] (2) Real-time image acquisition
[0033] Start the image acquisition module, and the system automatically adjusts the light source brightness and camera parameters to ensure the quality and clarity of the image;
[0034] The real-time acquisition of the image of the optical glass begins, and the image acquisition device continuously photographs the surface of the optical glass at a preset sampling frequency.
[0035] (3) Image processing and feature extraction
[0036] Preprocess the collected images to improve image quality;
[0037] Through image processing algorithms, characteristic information related to stress distribution is extracted, which will be used for subsequent stress analysis.
[0038] (4) Stress analysis and calculation
[0039] Based on the extracted feature information, combined with the material properties, geometric shape and environmental conditions of the optical glass, the stress distribution of the optical glass is calculated using a stress analysis algorithm;
[0040] The system achieves high-precision stress detection and generates stress distribution results through the constructed mathematical models and algorithms.
[0041] (5) Result display and early warning
[0042] The stress distribution results and alarm module are displayed in real time on the display device, so the operator can intuitively understand the stress distribution of the optical glass;
[0043] The system sets a stress threshold. When it detects that the stress exceeds the preset threshold, the alarm mechanism is automatically triggered to remind the operator to take timely treatment measures.
[0044] (6) Production process optimization
[0045] Based on the real-time stress monitoring results, the production process optimization module analyzes the stress variation patterns and influencing factors of optical glass during the production process;
[0046] Combined with production process parameters and working environment factors, the system puts forward optimization suggestions to reduce the stress level of optical glass during the production process and improve product quality and production efficiency.
[0047] Compared with the prior art, the optical glass stress detection system method has the following beneficial effects:
[0048] 1. The present invention effectively suppresses the noise interference in the image due to the influence of environmental and equipment factors through the Gaussian filtering algorithm of the high-speed image processing module, improves the signal-to-noise ratio of the image, and makes the subsequent feature extraction and stress analysis more accurate. While smoothing the image, the Gaussian filter can better retain the edge information of the image. The system can more accurately identify and analyze the stress distribution. At the same time, by adjusting the standard deviation σ of the Gaussian function, the blurring degree of the Gaussian filter can be controlled, which enables the system to flexibly adapt to stress analysis needs of different scales.
[0049] 2. The present invention performs real-time analysis on stress distribution data through linear mapping and calculation of moving average values of the data analysis and early warning module. The module can convert the feature information extracted from the image into measurable stress values, thereby ensuring the accuracy of stress value calculation. This quantification method helps to eliminate subjective errors and makes stress detection results more objective and reliable. By using the moving average algorithm, the module can also predict the stress change trend in the future in real time. The moving average value can smooth out short-term fluctuations in the data and highlight long-term trends, thereby helping operators to understand stress changes in a timely manner.
[0050] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0052] Figure 1 This is the operation flow chart of the optical glass stress detection system method.
[0053] Figure 2 The figure is a flow chart of the optical glass stress detection system method. DETAILED DESCRIPTION
[0054] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0055] Example 1
[0056] Optical glass stress detection system method, the system includes the following components:
[0057] Real-time image acquisition module: Use the set light source to illuminate the optical glass, start the high-speed image acquisition device, capture the stress distribution image inside the optical glass in real time, and transmit the captured image data to the high-speed image processing unit in real time;
[0058] High-speed image processing module: After receiving the image data, the image processing unit performs image enhancement processing to improve the contrast and clarity of the image. De-noising is performed on the enhanced image to eliminate noise interference in the image. Feature extraction is performed to extract the key features of stress distribution from the processed image;
[0059] Data analysis and early warning module: Use the preset stress analysis algorithm and model to perform real-time analysis on the received stress distribution characteristic data, calculate the specific value and change trend of the stress distribution, display the analysis results to the user in real time, and make judgments based on the preset threshold. When the real-time monitored stress data exceeds the preset threshold, the system automatically issues an alarm to remind the user to deal with potential problems in a timely manner;
[0060] Production process optimization module: According to the real-time monitoring stress data and early warning information, the parameters and conditions in the production process are adjusted. By continuously optimizing the production parameters and conditions, the quality and stability of the optical glass are improved. The stress data changes in the production process are recorded and analyzed to provide a reference for subsequent process improvements and quality improvements.
[0061] The high-speed image processing module calculates the weighted average value of each pixel through Gaussian filtering to reduce image noise and details and smooth the image. The mathematical formula of Gaussian filtering can be accurately expressed in the form of convolution. Given an image f(x, y) and a Gaussian kernel G(x, y) of size (2k+1)×(2k+1), the value of the Gaussian filtered image g(x, y) at each pixel (i, j) can be calculated by the following convolution formula: Here, f(i+m, j+n) is the pixel value of the original image f(x, y) at position (i+m, j+n), and G(m, n) is the weight value of the Gaussian kernel at position (m, n). The convolution operation involves aligning the center of the Gaussian kernel with the current pixel point (i, j) in the image, then multiplying each element in the kernel with the image pixel value it covers, and adding all the products. In practical applications, the Gaussian kernel G(x, y) is calculated by the Gaussian function, and its formula is: Among them, (x, y) is the coordinate relative to the center of the Gaussian kernel, and σ is the standard deviation of the Gaussian function, which determines the width of the Gaussian function and thus affects the blurriness of the image.
[0062] The Gaussian filtering algorithm of the high-speed image processing module can effectively suppress the noise interference in the image due to the influence of environmental and equipment factors, improve the signal-to-noise ratio of the image, and make the subsequent feature extraction and stress analysis more accurate. While smoothing the image, the Gaussian filter can better retain the edge information of the image. The system can more accurately identify and analyze the stress distribution. At the same time, by adjusting the standard deviation σ of the Gaussian function, the blur degree of the Gaussian filter can be controlled, which enables the system to flexibly adapt to stress analysis needs of different scales.
[0063] Example 2
[0064] Optical glass stress detection system method, the system includes the following components:
[0065] Real-time image acquisition module: Use the set light source to illuminate the optical glass, start the high-speed image acquisition device, capture the stress distribution image inside the optical glass in real time, and transmit the captured image data to the high-speed image processing unit in real time;
[0066] High-speed image processing module: After receiving the image data, the image processing unit performs image enhancement processing to improve the contrast and clarity of the image. De-noising is performed on the enhanced image to eliminate noise interference in the image. Feature extraction is performed to extract the key features of stress distribution from the processed image;
[0067] Data analysis and early warning module: Use the preset stress analysis algorithm and model to perform real-time analysis on the received stress distribution characteristic data, calculate the specific value and change trend of the stress distribution, display the analysis results to the user in real time, and make judgments based on the preset threshold. When the real-time monitored stress data exceeds the preset threshold, the system automatically issues an alarm to remind the user to deal with potential problems in a timely manner;
[0068] Production process optimization module: According to the real-time monitoring stress data and early warning information, the parameters and conditions in the production process are adjusted. By continuously optimizing the production parameters and conditions, the quality and stability of the optical glass are improved. The stress data changes in the production process are recorded and analyzed to provide a reference for subsequent process improvements and quality improvements.
[0069] The data analysis and early warning module performs real-time analysis on stress distribution data through linear mapping and calculation of moving average values, and calculates the specific value and change trend of stress distribution. The linear mapping formula is stress = a × feature + b, where stress is the calculated stress value, feature is the feature extracted from the image (such as pixel intensity), and a and b are coefficients determined by experimental data or physical models. In this way, the module can convert the feature information in the image into a measurable stress value. After completing the stress quantification, the data analysis and early warning module further uses the algorithm formula of trend analysis to predict the change trend of stress values. For simple statistics, the module will calculate the mean and standard deviation, using the following formula: These statistics help to understand the overall distribution and fluctuation of stress values. For time series analysis, the module may use a moving average algorithm to smooth the data and predict future trends. The moving average formula is as follows: By calculating the moving average, the module can predict the stress change trend over a period of time in the future.
[0070] The stress distribution data is analyzed in real time through linear mapping and calculation of moving average values in the data analysis and early warning module. The module can convert the feature information extracted from the image into measurable stress values, thereby ensuring the accuracy of stress value calculation. This quantification method helps to eliminate subjective errors and make stress detection results more objective and reliable. Using the moving average algorithm, the module can predict the stress change trend in the future in real time. The moving average can smooth short-term fluctuations in the data and highlight long-term trends, thereby helping operators to understand stress changes in a timely manner. The linear mapping and moving average algorithms can be adjusted and optimized according to actual conditions. This flexibility enables the system to adapt to a variety of application scenarios and improve the accuracy and reliability of detection.
[0071] Example 3
[0072] The steps of the system based on Example 1 and Example 2 are as follows:
[0073] (1) System preparation and setup
[0074] Turn on the optical glass stress detection system to ensure that all modules are in normal working condition;
[0075] Through the user interface of the system control module, set the parameters of the image acquisition module to adapt to different detection requirements and environmental conditions;
[0076] According to the size and shape of the optical glass to be inspected, the position and angle of the image acquisition device are adjusted to ensure that the image of the optical glass can be fully and clearly acquired.
[0077] (2) Real-time image acquisition
[0078] Start the image acquisition module, and the system automatically adjusts the light source brightness and camera parameters to ensure the quality and clarity of the image;
[0079] The real-time acquisition of the image of the optical glass begins, and the image acquisition device continuously photographs the surface of the optical glass at a preset sampling frequency.
[0080] (3) Image processing and feature extraction
[0081] Preprocess the collected images to improve image quality;
[0082] Through image processing algorithms, characteristic information related to stress distribution is extracted, which will be used for subsequent stress analysis.
[0083] (4) Stress analysis and calculation
[0084] Based on the extracted feature information, combined with the material properties, geometric shape and environmental conditions of the optical glass, the stress distribution of the optical glass is calculated using a stress analysis algorithm.
[0085] The system achieves high-precision stress detection and generates stress distribution results through the constructed mathematical models and algorithms.
[0086] (5) Result display and early warning
[0087] The stress distribution results and alarm module are displayed in real time on the display device, so that the operator can intuitively understand the stress distribution of the optical glass.
[0088] The system sets a stress threshold. When it detects that the stress exceeds the preset threshold, the alarm mechanism is automatically triggered to remind the operator to take timely treatment measures.
[0089] (6) Production process optimization
[0090] Based on the real-time stress monitoring results, the production process optimization module analyzes the stress variation patterns and influencing factors of optical glass during the production process.
[0091] Combined with production process parameters and working environment factors, the system puts forward optimization suggestions to reduce the stress level of optical glass during the production process and improve product quality and production efficiency.
[0092] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.
Claims
1. An optical glass stress detection system method, characterized in that: The system consists of the following components: Real-time image acquisition module: Use the set light source to illuminate the optical glass, start the high-speed image acquisition device, capture the stress distribution image inside the optical glass in real time, and transmit the captured image data to the high-speed image processing unit in real time; High-speed image processing module: After receiving the image data, the image processing unit performs image enhancement processing through the Gaussian filtering algorithm to improve the contrast and clarity of the image, performs denoising processing on the enhanced image to eliminate noise interference in the image, performs feature extraction, and extracts the key features of stress distribution from the processed image; Data analysis and early warning module: Use linear mapping and moving average algorithm to analyze the received stress distribution characteristic data in real time, calculate the specific value and change trend of stress distribution, display the analysis results to the user in real time, and make judgments based on preset thresholds. When the real-time monitored stress data exceeds the preset threshold, the system automatically issues an alarm to remind users to deal with potential problems in a timely manner; Production process optimization module: According to the real-time monitoring stress data and early warning information, the parameters and conditions in the production process are adjusted, and the production parameters and conditions are continuously optimized through machine learning algorithms to improve the quality and stability of optical glass. The stress data changes in the production process are recorded and analyzed to provide a reference for subsequent process improvements and quality improvements.
2. The optical glass stress detection system method according to claim 1, characterized in that: The specific steps of the real-time image acquisition module are as follows: (1) Image acquisition: Use the set light source to illuminate the optical glass, start the high-speed image acquisition device, and capture the stress distribution image inside the optical glass in real time; (2) Data transmission: The captured image data is transmitted to the high-speed image processing unit in real time.
3. The optical glass stress detection system method according to claim 1, characterized in that: The high-speed image processing module has the following specific steps: (1) Data processing: After receiving the image data, the high-speed image processing unit uses Gaussian filtering to perform image enhancement processing to improve the contrast and clarity of the image, and performs denoising processing on the enhanced image to eliminate noise interference in the image; (2) Feature extraction: The key features of stress distribution are extracted from the processed image and transmitted to the data analysis unit.
4. The optical glass stress detection system method according to claim 1, characterized in that: The specific steps of the data analysis and early warning module are as follows: (1) Data analysis: Use linear mapping and average value algorithm to analyze stress distribution data in real time and calculate the specific value and change trend of stress distribution; (2) Result judgment: Compare the analysis result with the preset threshold to determine whether it exceeds the preset threshold; (3) Early warning reminder: When the real-time monitored stress data exceeds the preset threshold, the system automatically issues an alarm to remind the user to deal with potential problems in a timely manner.
5. The optical glass stress detection system method according to claim 1, characterized in that: The specific steps of the production process optimization module are as follows: (1) Parameter adjustment: According to the real-time monitoring stress data and early warning information, the parameters and conditions in the production process are adjusted, and the quality and stability of optical glass are improved by continuously optimizing the production parameters and conditions. (2) Process optimization: Record and analyze stress data changes during the production process to provide a reference for subsequent process improvement and quality improvement.
6. The optical glass stress detection system method according to claim 4, characterized in that: The high-speed image processing module calculates the weighted average value of each pixel through Gaussian filtering to reduce image noise and details and smooth the image. The mathematical formula of Gaussian filtering can be accurately expressed in the form of convolution. Given an image f(x, y) and a Gaussian kernel G(x, y) of size (2k+1)×(2k+1), the value of the Gaussian filtered image g(x, y) at each pixel (i, j) can be calculated by the convolution formula: is the original image, f(x, y) is the pixel value at position (i+m, j+n), G(m, n) is the weight value of the Gaussian kernel at position (m, n), and the convolution operation involves aligning the center of the Gaussian kernel with the current pixel point (i, j) in the image, then multiplying each element in the kernel with the image pixel value it covers, and adding all the products. In practical applications, the Gaussian kernel G(x, y) is calculated by the Gaussian function, and its formula is: Among them, (x, y) is the coordinate relative to the center of the Gaussian kernel, and σ is the standard deviation of the Gaussian function, which determines the width of the Gaussian function and thus affects the blurriness of the image.
7. The optical glass stress detection system method according to claim 5, characterized in that: The data analysis and early warning module performs real-time analysis on stress distribution data by linear mapping and calculating moving average values, and calculates specific values and change trends of stress distribution. The linear mapping formula is stress=a×feature+b, where stress is the calculated stress value, feature is the feature extracted from the image (such as pixel intensity), and a and b are coefficients determined by experimental data or physical models. In this way, the module can convert feature information in the image into measurable stress values. After completing stress quantification, the data analysis and early warning module further uses the algorithm formula of trend analysis to predict the change trend of stress values. For simple statistics, the module will calculate the mean and standard deviation, using the formula: These statistics help to understand the overall distribution and fluctuation of stress values. For time series analysis, the module may use a moving average algorithm to smooth the data and predict future trends. The formula for moving average is as follows: By calculating the moving average, the module can predict the stress change trend over a period of time in the future.
8. The optical glass stress detection system method according to claim 5, characterized in that: The production process optimization module achieves precise adjustment and optimization of the production process by applying statistical analysis algorithms, machine learning algorithms and optimization algorithms to improve the quality and stability of optical glass. The statistical analysis algorithm is mainly used to perform descriptive statistics and anomaly detection on real-time monitored stress data. The mean reflects the average level of stress data, and its calculation formula is: The standard deviation is used to measure the dispersion of stress data. The calculation formula is: These statistics can help identify stability issues in the production process and whether there are abnormal stress values. The calculation formula for anomaly detection is When the stress value exceeds the preset threshold, it is considered abnormal. The machine learning algorithm is used to establish a prediction model, predict the stress value based on historical data, and adjust the production parameters according to the prediction results. The linear regression equation is used to establish the linear relationship between the production parameters and the stress value. The calculation formula is y=β0+β1x1+β2x2+…+β n x n ,The prediction model can predict possible future stress values based on real-time ,monitored stress data, and adjust the production parameters accordingly. ,The optimization algorithm is used to automatically adjust the production parameters to minimize the stress values or ,stress fluctuations based on the stress data and prediction results. ,The genetic algorithm can search for the optimal solution in the parameter space by simulating natural ,selection and genetic mechanisms. ,These optimization algorithms can automatically adjust the production parameters based on real-time feedback and ,achieve automatic optimization of the production process.
9. The optical glass stress detection system method according to claim 1, characterized in that: The real-time image acquisition module also includes a light source control part to ensure that the optical glass is evenly and appropriately illuminated during the acquisition process.
10. The method for detecting stress in optical glass according to claim 1, characterized in that: The specific steps of the method are: (1) System preparation and setup Turn on the optical glass stress detection system to ensure that all modules are in normal working condition; Through the user interface of the system control module, set the parameters of the image acquisition module to adapt to different detection requirements and environmental conditions; According to the size and shape of the optical glass to be inspected, the position and angle of the image acquisition device are adjusted to ensure that the image of the optical glass can be fully and clearly acquired. (2) Real-time image acquisition Start the image acquisition module, and the system automatically adjusts the light source brightness and camera parameters to ensure the quality and clarity of the image; The real-time acquisition of the image of the optical glass begins, and the image acquisition device continuously photographs the surface of the optical glass at a preset sampling frequency. (3) Image processing and feature extraction Preprocess the collected images to improve image quality; Through image processing algorithms, characteristic information related to stress distribution is extracted, which will be used for subsequent stress analysis. (4) Stress analysis and calculation Based on the extracted feature information, combined with the material properties, geometric shape and environmental conditions of the optical glass, the stress distribution of the optical glass is calculated using a stress analysis algorithm; The system achieves high-precision stress detection and generates stress distribution results through the constructed mathematical models and algorithms. (5) Result display and early warning The stress distribution results and alarm module are displayed in real time on the display device, so the operator can intuitively understand the stress distribution of the optical glass; The system sets a stress threshold. When it detects that the stress exceeds the preset threshold, the alarm mechanism is automatically triggered to remind the operator to take timely treatment measures. (6) Production process optimization Based on the real-time stress monitoring results, the production process optimization module analyzes the stress variation patterns and influencing factors of optical glass during the production process; Combined with production process parameters and working environment factors, the system puts forward optimization suggestions to reduce the stress level of optical glass during the production process and improve product quality and production efficiency.