Method, system, device and medium for safety detection of transparent structure of high-pressure gas cabin

Abstract

The application discloses a kind of high-pressure gas cabin transparent structure safety detection method, system, equipment and medium, the method includes: obtaining the relevant data of organic glass, relevant data includes microscopic image, ultrasonic feature and environmental parameter;Microscopic image and ultrasonic feature are preprocessed;Surface feature and internal depth feature of silver line are extracted, and three-dimensional defect model of silver line is constructed by multi-source data fusion;Based on silver line three-dimensional defect model and environmental parameter, the expansion trend of silver line is predicted, and residual life is calculated;Grade determination is carried out on silver line defect using machine learning model, and defect grade, residual life and repair feasibility score are output;Based on repair feasibility score, defect geometric parameter and historical repair data, repair success probability is calculated, and repair decision suggestion is generated;Silver line three-dimensional defect image, residual life, repair decision suggestion and detection report are output.The application can improve the safety and operation reliability of high-pressure gas cabin equipment.

Description

Technical Field

[0001] This invention relates to a method, system, equipment, and medium for safety testing of the transparent structure of a high-pressure gas chamber, belonging to the field of high-pressure gas equipment safety testing technology. Background Technology

[0002] Currently, hyperbaric gas chambers are increasingly used in clinical applications, and plexiglass is widely used as both the chamber material and the observation window material. However, under long-term pressure increase / depression and environmental influences, plexiglass is prone to developing silvering defects. According to current standards, the discovery of silvering defects necessitates component replacement, leading to significant resource waste. Existing detection methods largely rely on manual observation or single optical inspection, making it difficult to accurately assess the depth and spread trend of silvering defects, and they lack remaining life prediction capabilities. Therefore, there is an urgent need for an efficient, accurate, and predictable lifespan detection method and system. Summary of the Invention

[0003] In view of this, the present invention provides a method, system, computer equipment and storage medium for safety inspection of transparent structures in high-pressure gas chambers, which can realize comprehensive inspection of internal and surface defects of transparent structural components, and assess the defect expansion trend and remaining service life, thereby improving the safety and operational reliability of high-pressure gas chamber equipment.

[0004] The first objective of this invention is to provide a safety inspection method for the transparent structure of a high-pressure gas chamber.

[0005] The second objective of this invention is to provide a safety inspection system for a transparent structure of a high-pressure gas chamber.

[0006] A third objective of this invention is to provide a computer device.

[0007] A fourth objective of this invention is to provide a computer-readable storage medium.

[0008] The first objective of this invention can be achieved by adopting the following technical solution:

[0009] A safety inspection method for a transparent structure of a high-pressure gas chamber, the method comprising:

[0010] Acquire relevant data about plexiglass, including microscopic images, ultrasonic features, and environmental parameters;

[0011] Microscopic images and ultrasonic features are preprocessed, and various data are mapped to a unified spatial coordinate system;

[0012] The surface features and internal depth features of the silver ripples are extracted from the preprocessed data, and a three-dimensional defect model of the silver ripples is constructed by multi-source data fusion.

[0013] Based on the three-dimensional defect model of crazing and environmental parameters, the propagation trend of crazing is predicted and the remaining lifetime is calculated.

[0014] A machine learning model is used to determine the level of silver streaks and output the defect level, remaining lifetime, and repair feasibility score.

[0015] Based on the repair feasibility score, defect geometric parameters and historical repair data, the probability of repair success is calculated and repair decision recommendations are generated.

[0016] Outputs 3D images of silver streaks, remaining lifespan, repair decision recommendations, and inspection reports.

[0017] Furthermore, the preprocessing of the microscopic images and ultrasound features includes:

[0018] Distortion correction, scale calibration, and image enhancement are performed on the microscopic images, and sound velocity calibration and noise reduction are performed on the ultrasonic features.

[0019] Furthermore, the step of extracting surface features and internal depth features of the silver crazing from the preprocessed data, and constructing a three-dimensional defect model of the silver crazing through multi-source data fusion, includes:

[0020] By processing the microscopic images, the length, width, density, orientation angle, and planar position of the silver crazing are obtained as surface features;

[0021] The depth and uncertainty of silver cratering are obtained using ultrasonic features, which serve as internal depth features.

[0022] The surface features and internal depth features are fused together, and interpolation and fitting are used to construct a three-dimensional defect model of silver ripples, and the defect area and volume are calculated.

[0023] Furthermore, the prediction of the expansion trend of crazing based on the three-dimensional defect model and environmental parameters, and the calculation of the remaining lifetime, includes:

[0024] According to fracture mechanics theory, when the stress intensity factor at the crack tip reaches the fracture toughness of the material, the crack is considered to have reached the critical propagation state, and the critical crack depth is calculated.

[0025] The theoretical remaining lifetime is obtained by predicting the remaining number of cycles required for crack propagation to the critical crack depth through numerical integration.

[0026] The cumulative damage ratio is calculated using a crack-fatigue superposition model. The theoretical remaining life is then corrected using the cumulative damage ratio, and the remaining life is calculated accordingly.

[0027] Furthermore, the method of using a machine learning model to determine the level of silver streaks and outputting the defect level, remaining lifetime, and repair feasibility score includes:

[0028] Convolutional neural networks are used to extract deep features from microscopic images, which are then combined with ultrasound features and input into a fusion network.

[0029] The network outputs defect level, remaining lifetime, and repair feasibility score, and optimizes the results using cross-entropy and regression loss functions, outputting the confidence interval of the prediction results.

[0030] Furthermore, the training process of the fusion network is as follows:

[0031] Based on the input data, the defect level, remaining lifetime, and repair feasibility score are obtained through forward propagation.

[0032] The error is calculated based on the cross-entropy and the regression loss function;

[0033] Update network parameters using the backpropagation algorithm;

[0034] Training stops when the loss function converges or the preset number of training rounds is reached.

[0035] Furthermore, the relevant data also includes laser speckle images and infrared thermal images;

[0036] The extraction of surface features of silver crazing also includes:

[0037] Feature parameters of strain concentration regions are extracted using laser speckle images;

[0038] Thermal anomaly characteristic parameters are extracted using infrared thermal images.

[0039] The second objective of this invention can be achieved by adopting the following technical solution:

[0040] A safety inspection system for a transparent structure of a high-pressure gas chamber, the system comprising:

[0041] The acquisition module is used to acquire relevant data of plexiglass, including microscopic images, ultrasonic features, and environmental parameters.

[0042] The preprocessing module is used to preprocess microscopic images and ultrasound features, and map various types of data to a unified spatial coordinate system;

[0043] The module is used to extract the surface features and internal depth features of the silver ripples from the preprocessed data, and to construct a three-dimensional defect model of the silver ripples through multi-source data fusion.

[0044] The prediction module is used to predict the expansion trend of crater based on the 3D defect model of crater and environmental parameters, and to calculate the remaining lifetime.

[0045] The judgment module is used to use a machine learning model to determine the level of silver streaks and output the defect type, defect severity level and repair feasibility score.

[0046] The calculation module is used to calculate the probability of successful repair and generate repair decision recommendations based on the repair feasibility score, defect geometric parameters and historical repair data.

[0047] The output module is used to output three-dimensional images of silver streaks, remaining lifespan, repair decision recommendations, and inspection reports.

[0048] The third objective of this invention can be achieved by adopting the following technical solution:

[0049] A computer device includes a processor and a memory for storing processor-executable programs, wherein when the processor executes the program stored in the memory, it implements the above-described safety detection method for the transparent structure of a high-pressure gas chamber.

[0050] The fourth objective of this invention can be achieved by adopting the following technical solution:

[0051] A computer-readable storage medium storing a program that, when executed by a processor, implements the above-described safety detection method for the transparent structure of a high-pressure gas chamber.

[0052] The present invention has the following advantages over the prior art:

[0053] This invention targets medical hyperbaric oxygen chambers, hydrogen medical chambers, high-pressure experimental chambers, and other high-pressure gas environment equipment. It enables multimodal joint detection of surface and internal defects of silver crazing; by extracting surface features and internal depth features of silver crazing, a three-dimensional silver crazing defect model is constructed, and the detection results are intuitive and visual; it introduces lifespan prediction and repair assessment to improve resource utilization; it has artificial intelligence learning capabilities, and the detection accuracy improves with data accumulation; it can realize remote data transmission and expert diagnosis, improving inspection efficiency. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0055] Figure 1 This is a flowchart of the safety testing method for the transparent structure of the high-pressure gas chamber according to Embodiment 1 of the present invention.

[0056] Figure 2 This is a structural block diagram of the high-pressure gas chamber transparent structure safety detection system according to Embodiment 2 of the present invention.

[0057] Figure 3This is a practical application diagram of the high-pressure gas chamber transparent structure safety detection system of Embodiment 3 of the present invention.

[0058] Figure 4 This is a structural block diagram of the computer device according to Embodiment 4 of the present invention. Detailed Implementation

[0059] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are some embodiments of the present invention, but not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0060] Example 1:

[0061] like Figure 1 As shown, this embodiment provides a safety inspection method for the transparent structure of a high-pressure gas chamber, which includes the following steps:

[0062] S101. Obtain relevant data on plexiglass.

[0063] The relevant data in this embodiment include microscopic images, ultrasonic features, and environmental parameters. Specifically, microscopic images of the plexiglass are acquired using a microscope, and ultrasonic features of the plexiglass are acquired using an ultrasonic probe. Temperature, humidity, pressure, loading frequency, and cumulative pressurization times can be acquired using monitoring equipment. Contact medium information, mainly the media in operation such as oxygen, hydrogen, and impurities, can be obtained through equipment operation records, gas supply system records, or manual input. Cleaning solvent information, mainly the solvents used in the disinfection and cleaning process of the chamber, can be obtained through maintenance records, cleaning operation records, or manual input. Among these, temperature, humidity, pressure, loading frequency, cumulative pressurization times, contact medium information, and cleaning solvent information are considered as environmental parameters.

[0064] Optionally, the relevant data in this embodiment may also include laser speckle images and infrared thermographic images, specifically obtained through laser speckle imaging and infrared thermographic detection, to achieve potential microcrack identification. The laser speckle images and infrared thermographic images serve as new data sources, and the strain concentration area features and thermal anomaly features extracted from them are respectively involved in the defect feature extraction in step S103, the crack propagation trend prediction in step S104, and the machine learning fusion diagnosis in step S105, thereby improving the accuracy of potential microcrack identification and the accuracy of life prediction.

[0065] S102. Preprocess the microscopic images and ultrasound features, and map all types of data to a unified spatial coordinate system.

[0066] This embodiment performs distortion correction, scale calibration, and image enhancement processing on microscopic images, and performs sound velocity calibration and noise reduction processing on ultrasonic features. The image enhancement processing can be CLAHE processing of the image, and the noise reduction processing can be wavelet noise reduction of the ultrasound. All types of data are mapped to a unified spatial coordinate system.

[0067] S103. Extract the surface features and internal depth features of the silver ripples from the preprocessed data, and construct a three-dimensional defect model of the silver ripples through multi-source data fusion.

[0068] This embodiment obtains parameters such as the length, width, density, orientation angle, and planar position of the silver crater by processing the microscopic image, which are used as surface features; and obtains the depth and uncertainty of the silver crater by using ultrasonic features, which are used as internal depth features.

[0069] If the collected data also includes laser speckle images and infrared thermographic images, the extraction of surface features of silver crazing also includes: extracting characteristic parameters of strain concentration areas using laser speckle images, including speckle contrast, speckle change rate, and abnormal area; and extracting thermal anomaly characteristic parameters using infrared thermographic images, including temperature rise amplitude, temperature gradient, and hot spot area.

[0070] Furthermore, surface features and internal depth features are fused together, and interpolation and fitting are used to construct a three-dimensional defect model of silver ripples, and the defect area and volume are calculated.

[0071] S104. Based on the three-dimensional defect model of crazing and environmental parameters, predict the expansion trend of crazing and calculate the remaining lifetime.

[0072] According to fracture mechanics theory, when the stress intensity factor at the crack tip reaches the fracture toughness of the material, the crack is considered to have reached the critical propagation state, and the critical crack depth is... Calculate using the following formula:

[0073] ;

[0074] in, The critical crack depth; Y represents the fracture toughness of the acrylic glass; Y is the geometric factor. Equivalent stress; This is a correction factor, typically taken as 0.7 to 0.9.

[0075] Predicting crack propagation to critical crack depth 'a' using numerical integration. c The remaining number of loops N rem , thus obtaining the theoretical remaining lifespan.

[0076] For cracking, a crack-fatigue superposition model (Miner linear cumulative loss model) is adopted: initially, the Paris rule is used to predict crack growth; in the middle and later stages, if the ductile zone is reached, the failure criterion needs to be switched (such as J-integral or fracture toughness K). IC The cumulative damage ratio is calculated as follows:

[0077] ;

[0078] Where: D is the cumulative fatigue damage value; n i : represents the actual number of loading cycles under the i-th operating condition, where N represents the actual number of pressurization-depressurization cycles; fi Let be the number of fatigue life cycles under the i-th working condition.

[0079] The Paris predicted lifetime was corrected using the Miner linear cumulative loss model:

[0080] N * rem =(1-D)·N rem ;

[0081] Final remaining useful life:

[0082] ;

[0083] in, This represents the average annual loading frequency.

[0084] S105. Use a machine learning model to determine the level of silver streaks and output the defect level, remaining lifespan, and repair feasibility score.

[0085] This embodiment utilizes a convolutional neural network to extract deep features from microscopic images, which are then combined with ultrasonic features and input into a fusion network. The fusion network serves as the input processing system. If the collected data also includes laser speckle images and infrared thermographic images, the input data may also include laser speckle features and infrared thermographic features. The fusion network outputs the defect level, remaining lifespan, and repair feasibility score, and uses cross-entropy and regression loss functions for joint optimization, outputting the confidence interval of the prediction results.

[0086] To achieve defect level identification, remaining lifetime prediction, and repair feasibility assessment, this embodiment employs a multi-task learning approach to train the fusion network. The fusion network simultaneously includes classification and regression tasks; wherein:

[0087] The classification task outputs: defect type, defect level, and crack state.

[0088] The regression task outputs: remaining lifetime and repair feasibility score.

[0089] (1) Classification loss function

[0090] For defect level classification tasks, the cross-entropy loss function is used:

[0091] ;

[0092] in: For classification loss; The true label for the i-th category; is the predicted value for the i-th category; N is the number of defect categories.

[0093] This loss function is used to measure the difference between the model's predicted results and the actual defect level.

[0094] (2) Regression loss function

[0095] For remaining useful life prediction and repair feasibility score prediction, the mean squared error loss function is used:

[0096] ;

[0097] in: For regression loss; The true regression value is n; n is the sample size. To predict regression values.

[0098] This loss function is used to measure the error between the predicted lifetime and the actual lifetime.

[0099] (3) Joint loss function

[0100] To optimize both classification and regression tasks simultaneously, this embodiment employs a weighted joint loss function:

[0101] ;

[0102] Where: L is the total loss; For classification loss weights; For the regression loss weight; satisfying

[0103] (4) Network optimization process

[0104] The Adam optimization algorithm is used to iteratively update the parameters of the fusion network during training.

[0105] (4.1) Input microscopic images, ultrasonic features, laser speckle features, infrared thermographic features, and environmental parameters;

[0106] (4.2) Obtain the defect level, remaining lifetime, and repair feasibility score through forward propagation;

[0107] (4.3) Calculate the error based on the joint loss function;

[0108] (4.4) Update network parameters using the backpropagation algorithm;

[0109] (4.5) Stop training when the loss function converges or reaches the preset number of training rounds.

[0110] S106. Based on the repair feasibility score, defect geometric parameters, and historical repair data, calculate the probability of successful repair and generate repair decision recommendations.

[0111] S107 Outputs a 3D image of silver streaks, remaining lifespan, repair decision recommendations, and an inspection report.

[0112] The remaining lifetime in this embodiment includes the number of cycles and the remaining years. The test report includes result visualization, confidence level, and comparison with historical data.

[0113] It should be noted that although the above-described method operations are depicted in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all of the illustrated operations must be performed to achieve the desired result. On the contrary, the order of execution of the depicted steps can be changed. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0114] Example 2:

[0115] like Figure 2 As shown, this embodiment provides a safety inspection system for the transparent structure of a high-pressure gas chamber. The system includes an acquisition module 201, a preprocessing module 202, a construction module 203, a prediction module 204, a judgment module 205, a calculation module 206, and an output module 207. The specific functions of each module are as follows:

[0116] The acquisition module 201 is used to acquire relevant data of plexiglass, including microscopic images, ultrasonic features, and environmental parameters.

[0117] Preprocessing module 202 is used to preprocess microscopic images and ultrasound features, and map various types of data to a unified spatial coordinate system;

[0118] Module 203 is used to extract the surface features and internal depth features of the silver ripples from the preprocessed data, and to construct a three-dimensional defect model of the silver ripples through multi-source data fusion.

[0119] The prediction module 204 is used to predict the expansion trend of crater based on the 3D defect model of crater and environmental parameters, and to calculate the remaining lifetime.

[0120] The judgment module 205 is used to use a machine learning model to judge the level of silver streaks and output the defect type, defect severity level and repair feasibility score.

[0121] Calculation module 206 is used to calculate the probability of successful repair and generate repair decision suggestions based on repair feasibility score, defect geometric parameters and historical repair data;

[0122] Output module 207 is used to output three-dimensional images of silver streaks, remaining lifespan, repair decision recommendations, and inspection reports.

[0123] The specific implementation of each module in this embodiment can be found in Embodiment 1 above, and will not be repeated here. It should be noted that the system provided in this embodiment is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional units as needed, that is, the internal structure can be divided into different functional units to complete all or part of the functions described above.

[0124] Example 3:

[0125] This embodiment illustrates a specific application of the safety inspection system for the transparent structure of a high-pressure gas chamber, such as... Figure 3 As shown, it includes an acrylic glass sample 1, a microscope 2, a silver ripple gripping system 3, a data acquisition card 4, an ultrasonic probe 5, an ultrasonic detection system 6, a data acquisition card 7, and a computer processing system 8, as detailed below:

[0126] Microscope 2 is used to magnify silver streaks.

[0127] The silver ripple grasping system 3 is used to grasp the silver ripple in its magnified state under a microscope and to locate the X and Y positions of the silver ripple.

[0128] Data acquisition card 4: Used to input the acquired data into the computer processing system 8.

[0129] Ultrasonic probe 5 is used to detect silver streaks in plexiglass samples.

[0130] 6. Ultrasonic detection system is used to detect the length and depth of the silver lines; 2) to locate the X and Y positions of the silver lines;

[0131] Data acquisition card 7 is used to input the acquired data into computer processing system 8.

[0132] Computer processing system 8 has the following functions:

[0133] 1) Information Processing: a) Collect the density, length, and planar position of the silver ripples acquired by the silver ripple capture system 3; b) Collect the length, depth, and planar position of the silver ripples detected by the ultrasonic detection system 6; c) Simulate a three-dimensional graphic of the silver ripple defect; 2) Manual Input: Input parameters such as pressure, temperature, and loading frequency, and calculate according to the built-in judgment formula; 3) Output: a) Predict the development trend of silver ripples; b) Predict the service life; c) Produce images; d) Generate reports; 4) Other Functions: Store data on SD card or USB for export.

[0134] Example 4:

[0135] This embodiment provides a computer device, such as... Figure 4 As shown, it includes a processor 402, a memory, an input device 403, a display device 404, and a network interface 405 connected via a device bus 401. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium 706 and internal memory 407. The non-volatile storage medium 406 stores operating devices, computer programs, and a database. The internal memory 407 provides an environment for the operation of the operating devices and computer programs in the non-volatile storage medium. When the processor 402 executes the computer program stored in the memory, it implements the high-pressure gas chamber transparent structure safety detection method of Embodiment 1 described above, as follows:

[0136] Acquire relevant data for plexiglass, including microscopic images, ultrasonic features, and environmental parameters; preprocess the microscopic images and ultrasonic features, and map all types of data to a unified spatial coordinate system; extract surface features and internal depth features of silver ripples from the preprocessed data, and construct a three-dimensional defect model of silver ripples through multi-source data fusion; predict the expansion trend of silver ripples and calculate the remaining lifetime based on the three-dimensional defect model of silver ripples and environmental parameters; use a machine learning model to determine the level of silver ripple defects, and output the defect level, remaining lifetime, and repair feasibility score; calculate the probability of successful repair based on the repair feasibility score, defect geometric parameters, and historical repair data, and generate repair decision suggestions; output the three-dimensional defect image of silver ripples, remaining lifetime, repair decision suggestions, and inspection report.

[0137] Example 5:

[0138] This embodiment provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it implements the safety detection method for the transparent structure of a high-pressure gas chamber described in Embodiment 1 above, as follows:

[0139] Acquire relevant data for plexiglass, including microscopic images, ultrasonic features, and environmental parameters; preprocess the microscopic images and ultrasonic features, and map all types of data to a unified spatial coordinate system; extract surface features and internal depth features of silver ripples from the preprocessed data, and construct a three-dimensional defect model of silver ripples through multi-source data fusion; predict the expansion trend of silver ripples and calculate the remaining lifetime based on the three-dimensional defect model of silver ripples and environmental parameters; use a machine learning model to determine the level of silver ripple defects, and output the defect level, remaining lifetime, and repair feasibility score; calculate the probability of successful repair based on the repair feasibility score, defect geometric parameters, and historical repair data, and generate repair decision suggestions; output the three-dimensional defect image of silver ripples, remaining lifetime, repair decision suggestions, and inspection report.

[0140] It should be noted that the computer-readable storage medium in this embodiment can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0141] In this embodiment, the computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in connection with an instruction execution system, apparatus, or device. In this embodiment, the computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable storage medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0142] The computer-readable storage medium described above can be used to write computer programs for executing this embodiment in one or more programming languages ​​or combinations thereof. These programming languages ​​include object-oriented programming languages—such as Java, Python, and C++—and conventional procedural programming languages—such as C or similar programming languages. The program can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0143] In summary, this invention targets medical hyperbaric oxygen chambers, hydrogen medical chambers, high-pressure experimental chambers, and other high-pressure gas environment equipment. It enables multimodal joint detection of surface and internal defects in silver crazing; by extracting surface and internal depth features of the silver crazing, a three-dimensional silver crazing defect model is constructed, providing intuitive and visual detection results; it incorporates lifetime prediction and repair assessment to improve resource utilization; it possesses artificial intelligence learning capabilities, with detection accuracy improving with data accumulation; and it enables remote data transmission and expert diagnosis, enhancing inspection efficiency.

[0144] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any changes, modifications, substitutions, combinations, or simplifications made without departing from the spirit and principle of the present invention shall be considered equivalent substitutions and shall be included within the protection scope of the present invention.

Claims

1. A safety inspection method for a transparent structure of a high-pressure gas chamber, characterized in that, The method includes: Acquire relevant data about plexiglass, including microscopic images, ultrasonic features, and environmental parameters; Microscopic images and ultrasonic features are preprocessed, and various data are mapped to a unified spatial coordinate system; The surface features and internal depth features of the silver ripples are extracted from the preprocessed data, and a three-dimensional defect model of the silver ripples is constructed by multi-source data fusion. Based on the three-dimensional defect model of crazing and environmental parameters, the propagation trend of crazing is predicted and the remaining lifetime is calculated. A machine learning model is used to determine the level of silver streaks and output the defect level, remaining lifetime, and repair feasibility score. Based on the repair feasibility score, defect geometric parameters and historical repair data, the probability of repair success is calculated and repair decision recommendations are generated. Outputs 3D images of silver streaks, remaining lifespan, repair decision recommendations, and inspection reports.

2. The safety inspection method for the transparent structure of a high-pressure gas chamber according to claim 1, characterized in that, The preprocessing of the microscopic images and ultrasound features includes: Distortion correction, scale calibration, and image enhancement are performed on the microscopic images, and sound velocity calibration and noise reduction are performed on the ultrasonic features.

3. The safety inspection method for the transparent structure of a high-pressure gas chamber according to claim 1, characterized in that, The process of extracting surface and internal depth features of silver crazing from preprocessed data and constructing a three-dimensional defect model of silver crazing through multi-source data fusion includes: By processing the microscopic images, the length, width, density, orientation angle, and planar position of the silver crazing are obtained as surface features; The depth and uncertainty of silver cratering are obtained using ultrasonic features, which serve as internal depth features. The surface features and internal depth features are fused together, and interpolation and fitting are used to construct a three-dimensional defect model of silver ripples, and the defect area and volume are calculated.

4. The safety inspection method for the transparent structure of a high-pressure gas chamber according to claim 1, characterized in that, The method for predicting the propagation trend of crests and calculating the remaining lifetime based on a three-dimensional defect model of crests and environmental parameters includes: According to fracture mechanics theory, when the stress intensity factor at the crack tip reaches the fracture toughness of the material, the crack is considered to have reached the critical propagation state, and the critical crack depth is calculated. The theoretical remaining lifetime is obtained by predicting the remaining number of cycles required for crack propagation to the critical crack depth through numerical integration. The cumulative damage ratio is calculated using a crack-fatigue superposition model. The theoretical remaining life is then corrected using the cumulative damage ratio, and the remaining life is calculated accordingly.

5. The safety inspection method for the transparent structure of a high-pressure gas chamber according to claim 1, characterized in that, The method utilizes a machine learning model to determine the level of silver streaks, outputting the defect level, remaining lifetime, and repair feasibility score, including: Convolutional neural networks are used to extract deep features from microscopic images, which are then combined with ultrasound features and input into a fusion network. The network outputs defect level, remaining lifetime, and repair feasibility score, and optimizes the results using cross-entropy and regression loss functions, outputting the confidence interval of the prediction results.

6. The safety inspection method for the transparent structure of a high-pressure gas chamber according to claim 5, characterized in that, The training process of the fusion network is as follows: Based on the input data, the defect level, remaining lifetime, and repair feasibility score are obtained through forward propagation. The error is calculated based on the cross-entropy and the regression loss function; Update network parameters using the backpropagation algorithm; Training stops when the loss function converges or the preset number of training rounds is reached.

7. The safety inspection method for the transparent structure of a high-pressure gas chamber according to any one of claims 1-6, characterized in that, The relevant data also includes laser speckle images and infrared thermal images; The extraction of surface features of silver crazing also includes: Feature parameters of strain concentration regions are extracted using laser speckle images; Thermal anomaly characteristic parameters are extracted using infrared thermal images.

8. A safety inspection system for a transparent structure of a high-pressure gas chamber, characterized in that, The system includes: The acquisition module is used to acquire relevant data of plexiglass, including microscopic images, ultrasonic features, and environmental parameters. The preprocessing module is used to preprocess microscopic images and ultrasound features, and map various types of data to a unified spatial coordinate system; The module is used to extract the surface features and internal depth features of the silver ripples from the preprocessed data, and to construct a three-dimensional defect model of the silver ripples through multi-source data fusion. The prediction module is used to predict the expansion trend of crater based on the 3D defect model of crater and environmental parameters, and to calculate the remaining lifetime. The judgment module is used to use a machine learning model to determine the level of silver streaks and output the defect type, defect severity level and repair feasibility score. The calculation module is used to calculate the probability of successful repair and generate repair decision recommendations based on the repair feasibility score, defect geometric parameters and historical repair data. The output module is used to output three-dimensional images of silver streaks, remaining lifespan, repair decision recommendations, and inspection reports.

9. A computer device comprising a processor and a memory for storing a processor-executable program, characterized in that, When the processor executes the program stored in the memory, it implements the safety detection method for the transparent structure of the high-pressure gas chamber as described in any one of claims 1-7.

10. A computer-readable storage medium storing a program, characterized in that, When the program is executed by the processor, it implements the safety testing method for the transparent structure of the high-pressure gas chamber as described in any one of claims 1-7.

Images