Explosion-proof Performance Evaluation Method and System for Explosion-proof Equipment

Abstract

The present application relates to the technical field of explosion-proof performance detection, and discloses an explosion-proof performance evaluation method and system for explosion-proof equipment. The method includes: establishing a geometric model of the explosion-proof equipment, obtaining the stress distribution on the surface of the shell during the test of the explosion-proof equipment by using the finite element analysis method, respectively constructing a finite element reduced-order model and a stress distribution surrogate model based on the finite element analysis results, and fusing the two models to construct an optimization model. Inputting the data-level fusion result of multi-source heterogeneous data into the optimization model to predict the stress distribution of the explosion-proof equipment shell. Inputting the measured data and the calculated data into the multi-modal fusion evaluation model to obtain the safety level of the explosion-proof equipment. Finally, a three-dimensional visualization modeling method is used to realize the visual display of the explosion-proof equipment performance detection test in the digital twin system. The present application improves the comprehensiveness and reliability of the performance evaluation of explosion-proof equipment.

Description

Technical Field

[0001] This application relates to the technical field of explosion-proof performance detection, and particularly to an explosion-proof performance evaluation method and system for explosion-proof equipment. Background Art

[0002] The explosion-proof performance test is a test to evaluate the safety performance of products in a potentially explosive environment. In many industrial fields, such as petroleum, chemical, and coal, equipment or systems may generate explosive gases or dust during operation. To ensure the safe operation of these equipment or systems in a potentially explosive environment, the explosion-proof performance test is particularly important.

[0003] Currently, the explosion-proof performance test only verifies the anti-explosion performance and flameproof ability of equipment through a single pressure data, and cannot accurately evaluate the influence of various physical parameters during the explosion process on the performance of explosion-proof equipment. The traditional pressure detection test needs to be carried out in a closed flameproof tank, and the test process is not visible. The construction of the test system and the subsequent repeated detection of the test samples require a large amount of capital, manpower, and material resources, and the preparation cycle is relatively long. Moreover, there are certain safety hazards during the test process. Therefore, a new measurement method is needed to evaluate the reliability of explosion-proof equipment and provide a basis for its design, processing, and manufacturing. Summary of the Invention

[0004] This application provides an explosion-proof performance evaluation method and system for explosion-proof equipment. The multi-source heterogeneous data fusion method can collect different characteristic parameters of explosion-proof equipment through multiple sensors, represent multiple physical quantities, and construct a multi-source heterogeneous data fusion model to solve the problem of the singularity of data in traditional detection methods. Combining digital twin technology, the test process is visualized, and through the multi-modal fusion evaluation method, the deficiencies existing in the current explosion-proof performance test are made up for.

[0005] Solve the deficiencies existing in the traditional explosion-proof performance test and improve the comprehensiveness and reliability of the performance evaluation of explosion-proof equipment.

[0006] In a first aspect, this application provides an explosion-proof performance evaluation method for explosion-proof equipment, and the method includes:

[0007] Provide a data acquisition module for collecting multi-source heterogeneous data, preprocessing and fusing the multi-source heterogeneous data to obtain fused data, where the multi-source heterogeneous data includes pressure data, vibration data, visual images, and gas concentration change data;

[0008] Provide a model construction module. Based on the geometric characteristics of explosion-proof equipment, use 3D modeling software to construct a geometric model, simplify the geometric model to establish a simplified model of the explosion-proof equipment, perform mesh division on the simplified model, record the coordinates and numbers of mesh nodes, and then conduct finite element analysis. Based on the finite element analysis results, construct a finite element reduced-order model and a stress distribution surrogate model, and fuse the finite element reduced-order model and the stress distribution surrogate model to construct a fusion optimization model;

[0009] Provide a performance evaluation module. Extract the first pressure data and the first vibration data from the fusion data, establish a feature-level information fusion evaluation model based on the radial basis function (RBF) neural network according to the data characteristics of the first pressure data and the first vibration data, and then input the first pressure data and the first vibration data into the feature-level information fusion evaluation model to obtain the safety level of the explosion-proof equipment;

[0010] Provide a visual display module. Use digital twin software to develop a visualization interface, construct a digital twin system of the explosion-proof equipment, and based on the fusion data and the fusion optimization model, display the performance and state of the explosion-proof equipment during the test process in the digital twin system.

[0011] Combined with the first aspect, in the first implementation manner of the first aspect of this application, the preprocessing and fusion include:

[0012] Convert multi-source heterogeneous data into a unified format and store it in a database;

[0013] Adopt a linear fitting method to establish an interpolation function of "data point - time" to interpolate and predict missing data;

[0014] Adopt the non-local means method to denoise the multi-source heterogeneous data after interpolation processing;

[0015] Use the Kalman filter algorithm to perform redundancy processing on the denoised multi-source heterogeneous data;

[0016] Synchronize the multi-source heterogeneous data after redundancy processing through time frames to ensure the alignment of data sources at different time scales.

[0017] Combined with the first aspect, in the second implementation manner of the first aspect of this application, the simplification processing includes: analyze the geometric model, delete the screw holes and welds in the geometric model according to the analysis results, and homogenize the elastic modulus and density of the material.

[0018] In combination with the first aspect, in the third implementation manner of the first aspect of the present application, the finite element analysis includes: constructing a shell structure analysis model of the explosion process of the explosion-proof equipment by using a dynamic analysis method, and setting the gas type and concentration inside the explosion-proof equipment at the initial moment, as well as the initial pressure, temperature, ignition position and flame shape of the explosion, and outputting the finite element analysis results, where the finite element analysis results include the stress magnitude and deformation condition of the mesh division.

[0019] In combination with the first aspect, in the fourth implementation manner of the first aspect of the present application, using the POD algorithm to perform reduced-order model training on the shell structure analysis model to construct a finite element reduced-order model, including:

[0020] Performing multiple finite element analyses to obtain simulation data under different working conditions, where the simulation data includes the spatial and temporal distribution of stress;

[0021] Extracting any simulation data, generating a simulation vector based on any simulation data, and combining all simulation vectors to generate a data matrix;

[0022] Calculating the covariance matrix of the data matrix, performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues and eigenvectors;

[0023] Sorting the eigenvectors based on the magnitude of the eigenvalues, selecting the first k eigenvectors with high contribution degrees, defining them as the main eigenvectors, and constructing a finite element reduced-order model based on the main eigenvectors.

[0024] In combination with the first aspect, in the fifth implementation manner of the first aspect of the present application, the construction method of the stress distribution surrogate model is: obtaining simulation data, dividing the simulation data into a training set and a test set according to a preset ratio, using the training set to train a random forest network to obtain a surrogate model, and then using the test set to verify and optimize the surrogate model to generate a stress distribution surrogate model.

[0025] In combination with the first aspect, in the sixth implementation manner of the first aspect of the present application, the construction method of the fusion optimization model is: inputting the simulation data into the stress distribution surrogate model to obtain predicted values, calculating the similarity between the label values and the predicted values by using the coefficient of determination, evaluating the prediction results of the stress distribution surrogate model, and correcting the output of the finite element reduced-order model based on the prediction results to obtain a fusion optimization model.

[0026] In combination with the first aspect, in the seventh implementation manner of the first aspect of the present application, before obtaining the safety level, optimizing the first diagnosis result of the RBF neural network by using the improved D-S evidence theory, including:

[0027] Using a CNN neural network to diagnose the fusion data to obtain a second diagnosis result;

[0028] Normalize the first diagnostic result and the second diagnostic result and use them as the new basic probability assignment value BPA;

[0029] Re-obtain the evidence of the two neural networks through the weighted idea, and achieve decision-level fusion through the evidence theory combination rule to obtain the safety level.

[0030] Combined with the first aspect, in the eighth implementation manner of the first aspect of this application, the visual display module is also used to:

[0031] According to the coordinates and numbers of the nodes after grid division of the simplified model, use three-dimensional visualization technology to reconstruct the geometric model in the digital twin system;

[0032] Input the fusion data into the fusion optimization model to obtain the stress magnitude and deformation degree of the nodes of the simplified grid model;

[0033] According to the stress magnitude and deformation degree, use different color gradients for mapping, assign corresponding colors to each node of the geometric model, and display the performance and state of the explosion-proof equipment during the test process.

[0034] In the second aspect, this application provides an explosion-proof performance evaluation system for explosion-proof equipment to implement the explosion-proof performance evaluation method for explosion-proof equipment described in the first aspect. The system includes: a data acquisition module, a model construction module, a performance evaluation module, and a visual display module;

[0035] The data acquisition module is used to collect multi-source heterogeneous data, preprocess and fuse the multi-source heterogeneous data to obtain fusion data, where the multi-source heterogeneous data includes pressure data, vibration data, visual images, and gas concentration change data;

[0036] The model construction module is used to construct a geometric model using three-dimensional modeling software according to the geometric characteristics of the explosion-proof equipment, simplify the geometric model to establish a simplified model of the explosion-proof equipment, perform grid division on the simplified model, record the coordinates and numbers of the grid nodes, and then perform finite element analysis. Based on the finite element analysis results, construct a finite element reduced-order model and a stress distribution surrogate model, and fuse the finite element reduced-order model and the stress distribution surrogate model to construct a fusion optimization model;

[0037] The performance evaluation module is used to extract the first pressure data and the first vibration data from the fusion data, establish a feature-level information fusion evaluation model based on the RBF neural network based on the data characteristics of the first pressure data and the first vibration data, and then input the first pressure data and the first vibration data into the feature-level information fusion evaluation model to obtain the safety level of the explosion-proof equipment;

[0038] A visual display module is used to develop a visualization interface using digital twin software, construct a digital twin system of explosion-proof equipment, and display the performance and status of the explosion-proof equipment during the test process in the digital twin system based on the fusion data and the fusion optimization model.

[0039] Compared with the prior art, the beneficial effects of the technical solution of the present application are at least as follows:

[0040] 1. By collecting multi-source heterogeneous data, preprocessing and fusing it, the performance of the explosion-proof equipment in actual use can be more comprehensively reflected, thereby improving the accuracy of evaluation.

[0041] 2. Use 3D modeling software to construct a geometric model of the explosion-proof equipment, perform simplification processing and mesh generation, and combine finite element analysis to accurately simulate the stress distribution and deformation of the explosion-proof equipment under various working conditions, effectively predicting the performance of the explosion-proof equipment in actual applications and improving the accuracy and reliability of evaluation. At the same time, by fusing the finite element reduced-order model and the stress distribution surrogate model to construct a fusion optimization model, the evaluation results can be further optimized, improving the accuracy and efficiency of evaluation.

[0042] 3. By establishing a feature-level information fusion evaluation model based on the RBF neural network, inputting multi-source data into the model for comprehensive analysis, the safety level of the explosion-proof equipment can be more comprehensively evaluated. The introduction of the improved D-S evidence theory and the CNN neural network provides more reliable evaluation results.

[0043] 4. Using digital twin technology to construct a visualization interface can display the performance and status of the explosion-proof equipment in real time, facilitating operators to intuitively understand the operation of the equipment. By using color mapping technology to display stress changes and deformation degrees, the intuitiveness and readability of visualization are further enhanced, helping to quickly identify and locate problems, and improving the efficiency and accuracy of evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 It is a schematic diagram of an embodiment of the explosion-proof performance evaluation method for explosion-proof equipment in the embodiments of the present application;

[0046] Figure 2 It is a schematic diagram of an embodiment of the fusion data generation method in the embodiments of the present application;

[0047] Figure 3 Schematic diagram of an embodiment of the fusion optimization model generation method in the embodiments of the present application;

[0048] Figure 4 Schematic diagram of an embodiment of the explosion-proof performance evaluation system for explosion-proof equipment in the embodiments of the present application. Detailed implementation manners

[0049] The embodiments of the present application provide an explosion-proof performance evaluation method and system for explosion-proof equipment. Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims and above-mentioned drawings of the present application are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data used can be interchanged under appropriate circumstances so that the embodiments described here can be implemented in an order different from that shown or described here. In addition, the terms "comprising" or "having" and any variation thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these process, method, product or device.

[0050] For ease of understanding, the specific process of the embodiments of the present application is described below. Please refer to Figure 1 , an embodiment of the explosion-proof performance evaluation method for explosion-proof equipment in the embodiments of the present application includes:

[0051] Provide a data acquisition module for acquiring multi-source heterogeneous data, preprocessing and fusing the multi-source heterogeneous data to obtain fused data, where the multi-source heterogeneous data includes pressure data, vibration data, visual images, and gas concentration change data.

[0052] Specifically, pressure data, vibration data, and visual images of the explosion-proof equipment during the explosion-proof performance test are respectively acquired through pressure sensors, laser Doppler, and high-speed cameras, and the gas concentration change (such as methane, oxygen, hydrogen, etc.) during the test is acquired through gas concentration sensors. The pressure data is used to evaluate the pressure-bearing capacity of the equipment under the action of explosion shock waves and detect whether there is overpressure or uneven pressure; the vibration data is used to evaluate the vibration characteristics of the equipment and detect whether there is resonance or excessive vibration to evaluate its structural stability; the visual images are used for visual monitoring to detect whether there are cracks, deformations or other damages on the surface of the equipment and evaluate its appearance integrity and structural changes; the gas concentration change is used to evaluate whether the explosion-proof equipment effectively inhibits the leakage of harmful gases during the explosion and detect whether there is gas leakage or concentration exceeding the standard. The accuracy and comprehensiveness of data acquisition directly affect the reliability of the entire evaluation process.

[0053] Provide a model construction module. Based on the geometric characteristics of explosion-proof equipment, use 3D modeling software to construct a geometric model, simplify the geometric model to establish a simplified model of the explosion-proof equipment, perform mesh division on the simplified model, and record the coordinates and numbers of mesh nodes. Subsequently, conduct finite element analysis, construct a finite element reduced-order model and a stress distribution surrogate model based on the finite element analysis results, and fuse the finite element reduced-order model and the stress distribution surrogate model to construct a fusion optimization model.

[0054] Specifically, the geometric characteristics of explosion-proof equipment usually come from design drawings, CAD models, or actual measurement data. Using these geometric characteristics, construct a geometric model of the explosion-proof equipment through 3D modeling software (such as SolidWorks, AutoCAD, ANSYS, etc.). Among them, according to the complexity and accuracy requirements of the explosion-proof equipment, select a suitable 3D modeling software. For example, for complex curved surface structures, a software with powerful curved surface modeling functions can be selected.

[0055] To reduce the computational amount and improve the analysis efficiency, after the geometric model is constructed, simplify it to obtain a simplified model. Subsequently, perform mesh division on the simplified model and discretize it into a finite number of elements for facilitating numerical calculation. Common mesh division methods include tetrahedral meshes, hexahedral meshes, etc. Selecting a suitable mesh type and density can improve the analysis accuracy and efficiency. Based on the theories of elasticity and plasticity, decompose the force-bearing situation of the explosion-proof equipment into the mechanical behaviors of finite elements for solution to analyze the stress distribution, deformation conditions, etc. of the explosion-proof equipment under the action of explosion shock waves, and evaluate its structural strength and stability.

[0056] To reduce the complexity of the model, improve the computational efficiency, and at the same time maintain the key analysis accuracy, adopt model reduction techniques such as principal component analysis (PCA), singular value decomposition (SVD), etc. to extract the main features of the model and construct a finite element reduced-order model; at the same time, to establish the mathematical relationship between the stress distribution and geometric parameters, material properties, etc. for quickly predicting the stress distribution, adopt methods such as regression analysis and neural networks to establish a stress distribution surrogate model. Through methods such as data fusion and model combination, integrate the finite element reduced-order model and the stress distribution surrogate model to form a comprehensive fusion optimization model, further improving the performance and computational accuracy of the model.

[0057] Provide a performance evaluation module. Extract the first pressure data and the first vibration data from the fusion data, establish a feature-level information fusion evaluation model based on the RBF neural network based on the data characteristics of the first pressure data and the first vibration data. Subsequently, input the first pressure data and the first vibration data into the feature-level information fusion evaluation model to obtain the safety level of the explosion-proof equipment.

[0058] Specifically, according to the data characteristics of pressure and vibration signals, different methods are used for feature extraction. Combining the non-linear relationship between pressure and vibration data and the semantic variables of the evaluation method, a feature-level information fusion evaluation model based on RBF neural network is established.

[0059] Using different characteristic information collected by pressure sensors and laser Doppler as the input layer and the safety level as the output layer, the characteristic data is obtained by finite element method analysis. , the data center of the RBF neural network is , and the weight between the hidden layer and the output layer is . The mathematical model of the established RBF neural network is , and the output represents the membership degree of the explosion-proof equipment belonging to each safety level. Generally, its safety level is determined according to the principle of maximum membership degree, and the reliability of the explosion-proof equipment is evaluated at the feature level.

[0060] Provide a visual display module, use digital twin software to develop a visual interface, construct a digital twin system of explosion-proof equipment, and based on the fusion data and fusion optimization model, display the performance and status of the explosion-proof equipment during the test process in the digital twin system.

[0061] Specifically, use digital twin software to develop a visual interface and construct a virtual measurement system for explosion-proof equipment; use pressure sensors, laser Doppler, high-speed cameras and gas concentration sensors to collect the measured data of pressure signals, vibration signals, visual images and various gas concentrations during the explosion-proof performance test of the explosion-proof equipment in real time, and form the measured data into a measured data packet and upload it to the database server; the digital twin system sends a request instruction to obtain the measured data to the server through wireless communication. After the server checks that the instruction is consistent with the preset instruction in the server, the server sends the measured data packet to the digital twin system; the digital twin system analyzes the obtained measured data packet to obtain the measured data of the explosion-proof equipment and stores it in the digital twin system in categories; input the measured data and calculation data into the fusion optimization model to realize the virtual measurement and reliability evaluation of the explosion-proof equipment.

[0062] In a specific embodiment, the preprocessing and fusion include:

[0063] (1) Convert multi-source heterogeneous data into a unified format and store it in the database.

[0064] (2) Establish an interpolation function of "data point - time" by linear fitting to interpolate and predict missing data.

[0065] (3) Use the non-local mean method to denoise the multi-source heterogeneous data after interpolation processing.

[0066] (4) Use the Kalman filter algorithm to perform redundancy processing on the multi-source heterogeneous data after denoising.

[0067] (5) Synchronize the multi-source heterogeneous data after redundancy processing through time frames to ensure the alignment of data sources at different time scales.

[0068] Specifically, convert the acquisition formats of different sensors into a unified format (such as JSON, CSV, etc.) and store them in a database; use the complete data points in the dataset to find the pattern of the data sequence, establish an interpolation function of "data point - time" in a linear fitting manner, and finally predict the true values of the missing data in the real-time sequence according to the interpolation function; select the non-local means method to perform denoising processing on the multi-source heterogeneous data, effectively removing the dirty data and retaining and strengthening the valid data in the time series as much as possible; use the Kalman filter algorithm to perform redundancy processing on the multi-source heterogeneous data, obtaining a good filtering estimation effect. After the filtering algorithm, it can better reduce data redundancy, achieve a better data combination, and have higher accuracy; synchronize the acquired multi-source data through time frames, model the multi-source heterogeneous data in the database, create a data table, use the data of different sensors as different columns, and set the unit length of the time frame to ensure the alignment of data sources at different time scales and achieve the fusion of multi-source heterogeneous data at the data level.

[0069] The flowchart of the fusion data generation method is as Figure 2 shown.

[0070] In a specific embodiment, the simplification process includes: analyzing the geometric model, deleting the screw holes and welds in the geometric model according to the analysis results, and homogenizing the elastic modulus and density of the material.

[0071] Specifically, through the analysis of the geometric model, simply process its screw holes and welds using the deletion method, use uniform material properties to replace the non-uniform material distribution, assume that the elastic modulus and density of the material are uniform throughout the structure, and establish a simplified model of the explosion-proof equipment.

[0072] In a specific embodiment, performing finite element analysis includes: using the dynamic analysis method to construct a shell structure analysis model of the explosion process of the explosion-proof equipment, and setting the gas type and concentration inside the explosion-proof equipment at the initial moment, as well as the initial pressure, temperature, ignition position, and flame shape of the explosion, and outputting the finite element analysis results. The finite element analysis results include the stress magnitude and deformation situation of the mesh division.

[0073] Specifically, a kinetic analysis method in the finite element analysis method is used to construct an analysis model of the shell structure during the explosion of explosion-proof equipment. The types and concentrations of gases inside the explosion-proof equipment at the initial moment, the initial pressure, temperature, ignition position, and flame shape of the explosion are set, and the finite element analysis results of the geometric model of the explosion-proof equipment are output. The finite element analysis results of the geometric model of the explosion-proof equipment include the stress magnitude and deformation condition of the mesh division of the geometric model of the explosion-proof equipment. Indicates the stress distribution in the th simulation result, where is the spatial coordinate, and is the time.

[0074] In a specific embodiment, the POD algorithm is used to perform reduced-order model training on the shell structure analysis model to construct a finite element reduced-order model, including:

[0075] (1) Perform multiple finite element analyses to obtain simulation data under different working conditions. Among them, the simulation data includes the distribution of stress in space and time.

[0076] (2) Extract any simulation data, generate a simulation vector based on any simulation data, and combine all simulation vectors to generate a data matrix.

[0077] (3) Calculate the covariance matrix of the data matrix, perform eigenvalue decomposition on the covariance matrix, and obtain eigenvalues and eigenvectors.

[0078] (4) Sort the eigenvectors based on the magnitudes of the eigenvalues, select the first k eigenvectors with high contribution degrees, define them as the main eigenvectors, and construct a finite element reduced-order model based on the main eigenvectors.

[0079] Specifically, the POD algorithm is used to perform reduced-order model training on the original finite element model. The distribution of the stress of a simulation sample in space and time is represented as a vector , there are times of different simulation results, and these simulation results are combined into a data matrix . For the matrix , calculate its covariance matrix , and perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues and eigenvectors: . Select the first few eigenvectors with large eigenvalues and high contribution degrees to construct a reduced-order model. The original stress and strain field can be approximated in the following way: , where is a time function, representing the time variation coefficient of the th mode. Through reduced-order processing, the calculation speed of the finite element model is improved.

[0080] In a specific embodiment, the method for constructing the stress distribution surrogate model is as follows: Obtain simulation data, divide the simulation data into a training set and a test set according to a preset ratio, use the training set to train a random forest network to obtain a surrogate model, and then use the test set to verify and optimize the surrogate model to generate a stress distribution surrogate model.

[0081] In a specific embodiment, the method for constructing the fusion optimization model is as follows: Input the simulation data into the stress distribution surrogate model to obtain predicted values, calculate the similarity between the label values and the predicted values using the coefficient of determination, evaluate the prediction results of the stress distribution surrogate model, and correct the output of the finite element reduced-order model based on the prediction results to obtain a fusion optimization model.

[0082] Specifically, according to the simulation data, the training set and the test set are divided in a ratio of 7:3. A surrogate model for the stress change on the surface of the explosion-proof equipment housing is trained through a random forest network. The coefficient of determination is used to calculate the similarity between the label values and the predicted values, evaluate the prediction results of the surrogate model, and use the prediction results of the surrogate model to correct the output of the finite element reduced-order model to improve the calculation accuracy of the model.

[0083] The flowchart of the method for generating the fusion optimization model is as Figure 3 shown.

[0084] In a specific embodiment, before obtaining the safety level, the improved D-S evidence theory is used to optimize the first diagnostic result of the RBF neural network, including:

[0085] (1) Use a CNN neural network to diagnose the fusion data to obtain a second diagnostic result.

[0086] (2) Normalize the first diagnostic result and the second diagnostic result and use them as the new basic probability assignment value BPA.

[0087] (3) Re-obtain the evidence of the two neural networks through the weighted idea and achieve decision-level fusion through the evidence theory combination rule to obtain the safety level.

[0088] Specifically, aiming at the problems existing in the diagnosis of the RBF neural network, the improved D-S evidence theory is used for optimization. The combination of two neural networks, RBF and CNN, and the evidence theory is adopted. After the diagnostic outputs of the respective neural networks are processed in a normalized manner, the results are used as the new basic probability assignment value (BPA). The normalization formula is:

[0089] ;

[0090] where represents the BPA value of the type of fault, and represents the network output error, and the error calculation formula is:

[0091] ;

[0092] where , respectively represent the ideal output and the actual output of the th neuron of the th network.

[0093] Re-obtain the evidences of the two neural networks using the weighted idea, and then realize the decision-level fusion through the combination rule of the evidence theory to obtain the final safety level evaluation result.

[0094] Perform quantization analysis on the semantic variable set , input the test set explosion-proof enclosure damage sample data into the network for safety level assessment, and make the BPA value significantly improved compared with the single neural network through the improved evidence theory fusion method, verify the effectiveness of the method, and realize the evaluation of the safety level of explosion-proof equipment.

[0095] In a specific embodiment, the visual display module is also used to:

[0096] (1) According to the coordinates and numbers of the nodes after grid division of the simplified model, use three-dimensional visualization technology to reconstruct the geometric model in the digital twin system;

[0097] (2) Input the fusion data into the fusion optimization model to obtain the stress magnitude and deformation degree of the nodes of the simplified grid model;

[0098] (3) According to the stress magnitude and deformation degree, use different color gradients for mapping, assign corresponding colors to each node of the geometric model, and display the performance and state of the explosion-proof equipment during the test process.

[0099] Specifically, a pressure sensor, a laser Doppler, a high-speed camera, and a gas concentration sensor are used to collect the measured data of the pressure signal, vibration signal, visual image, and various gas concentrations during the explosion-proof performance test of the explosion-proof equipment in real time, and the measured data is formed into a measured data packet and uploaded to the database server; the digital twin system sends a request instruction to obtain the measured data to the server through wireless communication. After the server verifies that the instruction is consistent with the preset instruction in the server, the server sends the measured data packet to the digital twin system; the digital twin system analyzes the obtained measured data packet to obtain the measured data of the explosion-proof equipment and stores it in the digital twin system in categories; according to the coordinates and numbers of the grid division nodes of the geometric simplified model of the explosion-proof equipment, the geometric model of the explosion-proof equipment is reconstructed in the digital twin system using three-dimensional visualization technology; the measured data is input into the optimized surrogate model of the stress change on the shell surface to predict the stress change and deformation degree of the nodes of the simplified grid model of the explosion-proof equipment, and the data is stored; the digital twin system uses color mapping technology to assign corresponding colors to the nodes of the geometric model of the explosion-proof equipment according to the calculated structural stress and structural deformation data for the reconstructed geometric model of the explosion-proof equipment, and displays the performance and state of the explosion-proof equipment during the test process to achieve virtual measurement of the explosion-proof equipment.

[0100] The measured data and the calculated data are input into the multi-modal fusion evaluation model, and the safety level of the explosion-proof equipment is output to realize the reliability evaluation of the explosion-proof equipment.

[0101] The explosion-proof performance evaluation method for explosion-proof equipment in the embodiments of the present application has been described above. Next, the explosion-proof performance evaluation system for explosion-proof equipment in the embodiments of the present application will be described. Please refer to Figure 4 An embodiment of the explosion-proof performance evaluation system for explosion-proof equipment in the embodiments of the present application includes: a data acquisition module 10, a model construction module 20, a performance evaluation module 30, and a visual display module 40.

[0102] The data acquisition module 10 is used to collect multi-source heterogeneous data, preprocess and fuse the multi-source heterogeneous data to obtain fused data, where the multi-source heterogeneous data includes pressure data, vibration data, visual images, and gas concentration change data.

[0103] The model construction module 20 is used to construct a geometric model using three-dimensional modeling software according to the geometric characteristics of the explosion-proof equipment, simplify the geometric model to establish a simplified model of the explosion-proof equipment, perform grid division on the simplified model, record the coordinates and numbers of the grid nodes, and then perform finite element analysis. Based on the finite element analysis results, a finite element reduced-order model and a stress distribution surrogate model are constructed, and the finite element reduced-order model and the stress distribution surrogate model are fused to construct a fused optimization model.

[0104] The performance evaluation module 30 is used to extract the first pressure data and the first vibration data from the fusion data, establish a feature layer information fusion evaluation model based on the RBF neural network according to the data characteristics of the first pressure data and the first vibration data, and then input the first pressure data and the first vibration data into the feature layer information fusion evaluation model to obtain the safety level of the explosion-proof equipment.

[0105] The visual display module 40 is used to develop a visualization interface using digital twin software, construct a digital twin system of the explosion-proof equipment, and display the performance and status of the explosion-proof equipment during the test process in the digital twin system based on the fusion data and the fusion optimization model.

[0106] Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the above-described systems, systems, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0107] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the essence of the technical solution of this application, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0108] The above is the case. The above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or perform equivalent replacements for some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of various embodiments of this application.

Claims

1. An explosion-proof performance evaluation method for explosion-proof equipment, characterized in that The method includes: Providing a data acquisition module for acquiring multi-source heterogeneous data, preprocessing and fusing the multi-source heterogeneous data to obtain fused data, wherein the multi-source heterogeneous data includes pressure data, vibration data, visual images, and gas concentration change data; Providing a model construction module, based on the geometric characteristics of the explosion-proof equipment, using 3D modeling software to construct a geometric model, simplifying the geometric model to establish a simplified model of the explosion-proof equipment, dividing the simplified model into grids and recording the coordinates and numbers of grid nodes, performing multiple finite element analyses to obtain simulation data under different working conditions, wherein the simulation data includes the distribution of stress in space and time; extracting any one of the simulation data, generating a simulation vector based on any one of the simulation data, combining all simulation vectors to generate a data matrix; calculating the covariance matrix of the data matrix, performing eigen-decomposition on the covariance matrix to obtain eigenvalues and eigenvectors; sorting the eigenvectors based on the magnitudes of the eigenvalues, selecting the top k eigenvectors with high contribution degrees, defining them as main eigenvectors, and constructing a finite element reduced-order model based on the main eigenvectors; obtaining the simulation data, dividing the simulation data into a training set and a test set according to a preset ratio, training a random forest network using the training set to obtain a surrogate model, and then using the test set to verify and optimize the surrogate model to generate a stress distribution surrogate model; inputting the simulation data into the stress distribution surrogate model to obtain predicted values, calculating the similarity between the label values and the predicted values using the coefficient of determination, evaluating the prediction results of the stress distribution surrogate model, and correcting the output of the finite element reduced-order model based on the prediction results to obtain a fusion optimization model; Providing a performance evaluation module, extracting first pressure data and first vibration data from the fused data, establishing a feature-level information fusion evaluation model based on the RBF neural network based on the data characteristics of the first pressure data and the first vibration data, and then inputting the first pressure data and the first vibration data into the feature-level information fusion evaluation model to obtain the safety level of the explosion-proof equipment; Providing a visual display module, using digital twin software to develop a visualization interface, constructing a digital twin system of the explosion-proof equipment, and reconstructing the geometric model in the digital twin system using 3D visualization technology according to the coordinates and numbers of the grid nodes; inputting the fused data into the fusion optimization model to obtain the stress magnitudes and deformation degrees of the grid nodes; mapping according to different color gradients based on the stress magnitudes and the deformation degrees, assigning corresponding colors to each grid node of the geometric model, and displaying the performance and state of the explosion-proof equipment during the test process in the digital twin system.

2. The explosion-proof performance evaluation method for explosion-proof equipment according to claim 1, wherein The preprocessing and fusion include: Converting the multi-source heterogeneous data into a unified format and storing it in a database; Establishing an interpolation function of "data point - time" by means of linear fitting to interpolate and predict missing data; Perform denoising processing on the multi-source heterogeneous data after interpolation processing using the non-local mean method; Perform redundancy processing on the multi-source heterogeneous data after denoising processing using the Kalman filter algorithm; Perform synchronization processing on the multi-source heterogeneous data after redundancy processing through time frames to ensure the alignment of data sources at different time scales.

3. The explosion-proof performance evaluation method for explosion-proof equipment according to claim 1, wherein, The simplification processing includes: analyzing the geometric model, deleting the screw holes and welds in the geometric model according to the analysis results, and homogenizing the elastic modulus and density of the material.

4. The explosion-proof performance evaluation method for explosion-proof equipment according to claim 1, characterized in that, The finite element analysis includes: constructing a shell structure analysis model of the explosion process of the explosion-proof equipment using the dynamic analysis method, and setting the gas type and concentration inside the explosion-proof equipment at the initial moment, as well as the initial pressure, temperature, ignition position and flame shape of the explosion, and outputting the results of the finite element analysis. The results of the finite element analysis include the stress magnitude and deformation conditions of the mesh division.

5. An explosion-proof performance evaluation system for explosion-proof equipment, which implements the explosion-proof performance evaluation method for explosion-proof equipment according to any one of claims 1-4, characterized in that, The system includes: a data acquisition module, a model construction module, a performance evaluation module and a visual display module; The data acquisition module is used to collect multi-source heterogeneous data, perform preprocessing and fusion on the multi-source heterogeneous data, and obtain fusion data. Among them, the multi-source heterogeneous data includes pressure data, vibration data, visual images and gas concentration change data; The model construction module is used to construct a geometric model using 3D modeling software according to the geometric characteristics of the explosion-proof equipment, perform simplification processing on the geometric model to establish a simplified model of the explosion-proof equipment, perform mesh division on the simplified model and record the coordinates and numbers of the mesh nodes, and then perform finite element analysis. Based on the results of the finite element analysis, a finite element reduced-order model and a stress distribution surrogate model are constructed, and the finite element reduced-order model and the stress distribution surrogate model are fused to construct a fusion optimization model; The performance evaluation module is used to extract the first pressure data and the first vibration data from the fusion data, establish a feature-level information fusion evaluation model based on the RBF neural network based on the data characteristics of the first pressure data and the first vibration data, and then input the first pressure data and the first vibration data into the feature-level information fusion evaluation model to obtain the safety level of the explosion-proof equipment; The visual display module is used to develop a visualization interface using digital twin software, construct a digital twin system of the explosion-proof equipment, and display the performance and state of the explosion-proof equipment during the test in the digital twin system based on the fusion data and the fusion optimization model.

Images