Automatic testing system and method for explosion-proof valve

Abstract

The invention discloses an automatic testing system for an explosion-proof valve, and relates to the technical field of performance testing. The system comprises a predicted blasting value determination module used for calculating a predicted blasting value of an anti-blasting valve; the data transmission module is used for transmitting the simulation blasting parameter value to the blasting simulation robot; the dynamic weight value determining module is used for calculating the dynamic weight value of each blasting parameter; the prediction error calculation module is used for calculating a prediction error; the simulated blasting parameter value updating module is used for continuously updating the predicted blasting value and the first simulated blasting value of the anti-blasting valve; the dynamic weight value updating module is used for continuously updating the prediction error; the actual blasting module is used for transmitting the simulated blasting parameter value with the minimum prediction error to the blasting test platform; and the test module is used for judging whether the anti-explosion valve passes the explosion test or not. According to the scheme, the experiment cost is reduced, the efficiency of the whole testing process is improved, and high-quality input parameters can be provided for actual testing.

Description

Technical Field

[0001] The present application relates to the technical field of performance testing, and in particular to an automated testing system and method for explosion-proof wave valves. Background Art

[0002] Explosion-proof valves are widely used in key areas such as petrochemical facilities, military facilities, nuclear power plants, underground projects and civil air defense projects. When these facilities are facing the threat of explosion shock waves, explosion-proof valves are important protective equipment, and their performance and reliability are directly related to the safety of personnel and equipment inside the facilities.

[0003] Nowadays, the test of explosion-proof valves is usually carried out by manual inspection, focusing on the verification of explosion-proof performance and sealing performance. For explosion-proof performance, the valve's ability to withstand extreme pressure is tested by simulating the explosion shock wave environment to ensure that its structure is intact and effectively blocks the propagation of shock waves. For sealing performance, pressure testing or smoke testing are used to test the tightness of the valve after closing to ensure no leakage and protect the internal space from external threats.

[0004] However, manual testing usually relies on the experience and operation of testers, which is slow and inefficient. Manual testing requires a lot of human resources and has higher overall costs. In addition, the results of manual testing may be affected by the subjective judgment of testers, and there may be differences between different testers, making it difficult to ensure the stability and consistency of test results. Summary of the invention

[0005] In order to overcome the shortcomings of the prior art, the present application provides an automated testing system and method for explosion-proof valves, which solves the problem that the performance of explosion-proof valves generally depends on the experience and operation of testers in the prior art, and the execution speed is slow and the efficiency is insufficient; manual testing requires a large amount of human resources and the overall cost is higher; and the results of manual testing may be affected by the subjective judgment of the testers, and there may be differences between different testers, resulting in the difficulty in ensuring the stability and consistency of the test results.

[0006] In a first aspect, an embodiment of the present application provides an automated testing system for an explosion-proof valve, the system comprising: A predicted blasting value determination module is used to obtain a preset simulated blasting parameter range for each blasting parameter, and input the initial value of the preset simulated blasting parameter range as the simulated blasting parameter value into a preset blasting prediction model to obtain a predicted blasting value of the anti-blasting valve; wherein the blasting parameters include pressure, temperature and torque; the predicted blasting value includes a predicted deformation, a predicted damage value, a predicted maximum stress value and a predicted internal pressure change value; A data transmission module, used for transmitting the simulated blasting parameter value to the blasting simulation robot, so that the blasting simulation robot can perform blasting simulation according to the simulated blasting parameter value; A dynamic weight value determination module is used to obtain a first simulated blasting value of the anti-blasting valve obtained by blasting simulation, and calculate the dynamic weight value of each blasting parameter in the simulated blasting parameter value according to the predicted blasting value, the first simulated blasting value and a preset dynamic weight calculation formula; A prediction error calculation module, for calculating the prediction error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value under the simulated blasting parameter value according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and a preset error calculation formula; A simulated blasting parameter value updating module, used to continuously update the simulated blasting parameter value according to a preset adjustment step length and an initial value of a preset simulated blasting parameter range, and continuously input the updated simulated blasting parameter value into a preset blasting prediction model, and transmit it to a blasting simulation robot, and continuously update the predicted blasting value of the anti-blasting valve and the first simulated blasting value; A dynamic weight value updating module, for continuously updating the dynamic weight values ​​of each blasting parameter at different simulated blasting parameter values ​​according to the continuously updated predicted blasting value, the first simulated blasting value and the preset dynamic weight calculation formula, and continuously updating the predicted error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula, until the simulated blasting parameter value is adjusted to the maximum value of the preset simulated blasting parameter range; The actual blasting module is used to transmit the simulated blasting parameter value with the smallest prediction error to the blasting test platform, so that the blasting test platform can perform actual blasting test according to the minimum simulated blasting parameter value; The test module is used to receive the actual explosion value of the anti-explosion valve transmitted by the explosion test platform, and if the actual explosion value reaches a preset explosion test standard, it is determined that the anti-explosion valve passes the explosion test.

[0007] Furthermore, the preset dynamic weight calculation formula is: ; Wherein, P is the simulated blasting parameter value of each blasting parameter; is the dynamic weight value of the ith blasting parameter under the simulated blasting parameter value; is the preset weight adjustment coefficient; is the predicted blasting value of the ith blasting parameter under the simulated blasting parameter value; is the first simulated blasting value of the i-th blasting parameter under the simulated blasting parameter value.

[0008] Furthermore, the preset error calculation formula is: ; in, is the prediction error; is the index index, ranging from 1 to 3; P is the simulated blasting parameter value of each blasting parameter; is the dynamic weight value of the ith blasting parameter under the simulated blasting parameter value; is the predicted blasting value of the ith blasting parameter under the simulated blasting parameter value; is the first simulated blasting value of the i-th blasting parameter under the simulated blasting parameter value.

[0009] Furthermore, the system further comprises a sealing performance prediction model construction module, wherein the sealing performance prediction model construction module is used to: Acquire historical environmental data, historical load data, historical vibration data, historical leakage amount and historical deformation amount of the explosion-proof valve seal, and create a first data set according to the historical environmental data, historical load data and historical vibration data; labeling the leakage amount label of the first data set according to the historical leakage amount, and labeling the deformation amount label of the first data set according to the historical deformation amount; A sealing performance prediction model is constructed, and the sealing performance prediction model is trained according to the first data set, the leakage amount label, and the deformation amount label until the sealing performance prediction model reaches a preset sealing performance prediction model training standard.

[0010] Furthermore, the system further comprises a sealing performance testing module, and the sealing performance testing module is used to: Acquire real-time environmental data, real-time load data and real-time vibration data of the explosion-proof valve seal, input the real-time environmental data, real-time load data and real-time vibration data into a sealing performance prediction model, and obtain a predicted leakage amount and a predicted deformation amount of the explosion-proof valve seal; A preset sealing performance evaluation standard is obtained. If the predicted leakage amount and the predicted deformation amount reach the preset sealing performance evaluation standard, it is determined that the anti-explosion valve has passed the sealing performance test.

[0011] Furthermore, the system further comprises a blasting fatigue test module, and the blasting fatigue test module is used to: The simulated blasting parameter value with the smallest prediction error and the preset simulated blasting time interval are transmitted to the blasting simulation robot, so that the blasting simulation robot can continue to perform blasting simulation according to the simulated blasting parameter value with the smallest prediction error and the preset simulated blasting time interval; Continuously acquiring a second simulated blasting value and a number of simulated blasting times obtained by the blasting simulation until the number of simulated blasting times reaches a preset simulated blasting threshold, and transmitting a stop simulated blasting instruction to the blasting simulation robot; If all the second simulated explosion values ​​exceed the preset explosion fatigue test standard, it is determined that the anti-explosion valve has passed the explosion fatigue test.

[0012] Furthermore, the system further comprises a door opening and closing fatigue test module, and the door opening and closing fatigue test module is used to: Acquire preset switch parameters, preset position and angle parameters, preset applied force data, and preset switching times, and transmit the preset switch parameters, preset position and angle parameters, preset applied force data, and preset switching times to a fatigue simulation robot, so that the fatigue simulation robot can simulate the normal switching operation of the explosion-proof valve according to the preset switch parameters, preset position and angle parameters, preset applied force data, and preset switching times; The actual position data, actual angle data, switching force data and preset door opening and closing fatigue test standard of the explosion-proof valve switch component during each door opening and closing simulation are obtained. If the actual position data, actual angle data and switching force data reach the preset door opening and closing fatigue test standard, it is determined that the explosion-proof valve has passed the door opening and closing fatigue test.

[0013] Furthermore, the training process of the preset blasting prediction model includes: Obtaining historical simulated blasting parameter values ​​and historical blasting values ​​of each blasting parameter, and marking blasting value labels of the historical simulated blasting parameter values ​​according to the historical blasting values; wherein the historical blasting values ​​include historical deformation, historical damage value, historical maximum stress value, and historical internal pressure change value; the blasting value labels include deformation label, damage value label, maximum stress value label, and internal pressure change value label; A blasting prediction model is constructed, and the blasting prediction model is trained according to the historical simulated blasting parameter values ​​and blasting value labels until the blasting prediction model reaches a preset blasting prediction model training standard.

[0014] Furthermore, the system further comprises a model updating module, wherein the model updating module is used for: Continuously updating the historical simulated blasting parameter values ​​and historical blasting values ​​of each blasting parameter, and marking the blasting value labels of the historical simulated blasting parameter values ​​according to the historical blasting values; The model running time is continuously monitored. If the model running time reaches the preset model update time, the blasting prediction model is trained according to the updated historical simulated blasting parameter values ​​and blasting value labels until the blasting prediction model reaches the preset blasting prediction model training standard.

[0015] In a second aspect, an embodiment of the present application provides an automated testing method for an explosion-proof valve, the method comprising: Obtaining a preset simulated blasting parameter range for each blasting parameter, inputting the initial value of the preset simulated blasting parameter range as a simulated blasting parameter value into a preset blasting prediction model, and obtaining a predicted blasting value of the anti-blasting valve; wherein the blasting parameters include pressure, temperature and torque; and the predicted blasting value includes a predicted deformation, a predicted damage value, a predicted maximum stress value and a predicted internal pressure change value; Transmitting the simulated blasting parameter value to the blasting simulation robot, so that the blasting simulation robot performs blasting simulation according to the simulated blasting parameter value; Obtaining a first simulated blasting value of the anti-blasting valve obtained by blasting simulation, and calculating the dynamic weight value of each blasting parameter in the simulated blasting parameter value according to the predicted blasting value, the first simulated blasting value and a preset dynamic weight calculation formula; According to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula, the predicted error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value under the simulated blasting parameter value is calculated; According to a preset adjustment step length and an initial value of a preset simulated blasting parameter range, the simulated blasting parameter value is continuously updated, and the updated simulated blasting parameter value is continuously input into a preset blasting prediction model, and transmitted to a blasting simulation robot, and the predicted blasting value of the anti-blasting valve and the first simulated blasting value are continuously updated; According to the continuously updated predicted blasting value, the first simulated blasting value and the preset dynamic weight calculation formula, the dynamic weight value of each blasting parameter at different simulated blasting parameter values ​​is continuously updated, and according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula, the predicted blasting value of the anti-blasting valve and the predicted error of the first simulated blasting value are continuously updated until the simulated blasting parameter value is adjusted to the maximum value of the preset simulated blasting parameter range; The simulated blasting parameter value with the smallest prediction error is transmitted to the blasting test platform, so that the blasting test platform can perform actual blasting test according to the smallest simulated blasting parameter value; The actual explosion value of the explosion-proof valve transmitted by the explosion test platform is received, and if the actual explosion value reaches a preset explosion test standard, it is determined that the explosion-proof valve passes the explosion test.

[0016] In the above-mentioned automated testing system and method of the explosion-proof wave valve in the embodiment of the present application, a large number of virtual blasting simulations are performed using a blasting simulation robot and a blasting prediction model, which greatly reduces the need and number of actual blasting, and can avoid expensive actual blasting tests under undesirable parameters, thereby reducing experimental costs. Automated data transmission and parameter updates make the process from simulation testing to actual blasting smoother, improving the efficiency of the overall testing process. At the same time, the continuously updated blasting parameter values ​​and prediction errors can ensure that the data at each step is more accurate, thereby providing high-quality input parameters for actual testing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural schematic diagram of an automated testing system for explosion-proof wave valves provided in Example 1 of the present application; Figure 2 It is a structural schematic diagram of an automated testing system for explosion-proof wave valves provided in Example 2 of the present application; Figure 3 It is a structural schematic diagram of an automated testing system for explosion-proof wave valves provided in Example 3 of the present application; Figure 4 It is a flow chart of the automated testing method for explosion-proof wave valves provided in the fourth embodiment of the present application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present application clearer, the specific embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. It is understood that the specific embodiments described herein are only used to explain the present application, rather than to limit the present application. It should also be noted that, for the convenience of description, only part of the present application is shown in the accompanying drawings, but not all of the content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow chart describes each operation (or step) as a sequential process, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but it can also have additional steps not included in the accompanying drawings. The process can correspond to a method, a function, a procedure, a subroutine, a subprogram, etc.

[0019] The following will be combined with the drawings in the embodiments of the present application to clearly describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments in the present application belong to the scope of protection of this application.

[0020] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship.

[0021] The following is a detailed description of the automatic testing system for explosion-proof wave valves provided in the embodiments of the present application through specific embodiments and their application scenarios in conjunction with the accompanying drawings. Example

[0022] Figure 1 1 is a schematic diagram of the structure of the automatic testing system for explosion-proof valves provided in Example 1 of the present application. The system includes: A predicted blasting value determination module is used to obtain a preset simulated blasting parameter range for each blasting parameter, and input the initial value of the preset simulated blasting parameter range as the simulated blasting parameter value into a preset blasting prediction model to obtain a predicted blasting value of the anti-blasting valve; wherein the blasting parameters include pressure, temperature and torque; the predicted blasting value includes a predicted deformation, a predicted damage value, a predicted maximum stress value and a predicted internal pressure change value; A data transmission module, used for transmitting the simulated blasting parameter value to the blasting simulation robot, so that the blasting simulation robot can perform blasting simulation according to the simulated blasting parameter value; A dynamic weight value determination module is used to obtain a first simulated blasting value of the anti-blasting valve obtained by blasting simulation, and calculate the dynamic weight value of each blasting parameter in the simulated blasting parameter value according to the predicted blasting value, the first simulated blasting value and a preset dynamic weight calculation formula; A prediction error calculation module, for calculating the prediction error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value under the simulated blasting parameter value according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and a preset error calculation formula; A simulated blasting parameter value updating module, used to continuously update the simulated blasting parameter value according to a preset adjustment step length and an initial value of a preset simulated blasting parameter range, and continuously input the updated simulated blasting parameter value into a preset blasting prediction model, and transmit it to a blasting simulation robot, and continuously update the predicted blasting value of the anti-blasting valve and the first simulated blasting value; A dynamic weight value updating module, for continuously updating the dynamic weight values ​​of each blasting parameter at different simulated blasting parameter values ​​according to the continuously updated predicted blasting value, the first simulated blasting value and the preset dynamic weight calculation formula, and continuously updating the predicted error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula, until the simulated blasting parameter value is adjusted to the maximum value of the preset simulated blasting parameter range; The actual blasting module is used to transmit the simulated blasting parameter value with the smallest prediction error to the blasting test platform, so that the blasting test platform can perform actual blasting test according to the minimum simulated blasting parameter value; The test module is used to receive the actual explosion value of the anti-explosion valve transmitted by the explosion test platform, and if the actual explosion value reaches a preset explosion test standard, it is determined that the anti-explosion valve passes the explosion test.

[0023] First of all, the usage scenario of this scheme can be to determine the simulated blasting parameter value with the smallest prediction error, and enable the blasting platform to perform actual blasting according to the simulated blasting parameter value with the smallest prediction error, determine the actual blasting value, and determine whether the anti-blasting valve passes the blasting test according to the actual blasting value and the preset blasting test standard.

[0024] Based on the above usage scenarios, it can be understood that the executor of the present application can be the automated testing system of the explosion-proof valve, and no excessive limitations are made here.

[0025] In this solution, the blasting parameters may refer to the key variables that need to be set during the blasting simulation of the explosion-proof valve. These variables will affect the performance and damage of the valve. Specifically, they may include pressure: the gas or liquid pressure acting inside or outside the explosion-proof valve, which affects the stress distribution and deformation degree of the valve. Temperature: The temperature applied during the test may affect the mechanical properties of the material, causing the material to soften or reduce its strength. Torque: The torque applied to the valve component during the test, which is used to simulate the effects of dynamic loads such as rotation and twisting.

[0026] The preset simulated burst parameter range can be a preliminarily set numerical range for burst test simulation, defining the upper and lower limits of pressure, temperature, and torque. This range is usually based on design standards or historical test data to determine the maximum and minimum stress conditions that the system can withstand. For example: pressure range: 50~300 MPa, temperature range: -40℃~200℃, torque range: 100~500 Nm.

[0027] The simulated blasting parameter values ​​may be specific values ​​selected from a preset simulated blasting parameter range. When performing blasting simulation, these values ​​are used as inputs in a blasting prediction model to simulate the behavior of the anti-blasting valve under specific working conditions.

[0028] The preset explosion prediction model can be a prediction model based on historical data and material mechanical properties to simulate the performance of the explosion-proof valve under explosion conditions. The model may be a trained finite element analysis model or a machine learning model that can predict the stress, deformation, breakage and other behaviors of the valve under given loads and conditions.

[0029] The predicted burst value can be the result calculated by the burst prediction model, reflecting the physical behavior of the valve under specific burst conditions. These values ​​are used to evaluate whether the performance of the explosion-proof valve meets the requirements. Specifically, they can include the predicted deformation: refers to the degree of deformation of the valve under burst conditions, which may affect its sealing and strength. Predicted damage value: refers to the degree of damage that may occur to the valve during the burst process, reflecting the risk of material failure. Predicted maximum stress value: refers to the maximum stress that the valve bears under burst conditions, used to evaluate whether the material has reached yield or damage. Predicted internal pressure change value: refers to the pressure change inside the valve. Among them, the predicted burst value corresponding to the pressure can be the sum of the predicted deformation and the predicted internal pressure change value; the predicted burst value corresponding to the temperature can be the sum of the predicted damage value and the predicted maximum stress value; the predicted burst value corresponding to the torque can be the sum of the predicted deformation and the predicted maximum stress value.

[0030] The pressure, temperature and torque ranges for the burst test can be determined. These ranges are usually set according to design specifications and material properties. Initial pressure, temperature and torque values ​​are selected from the preset parameter ranges as simulation input values. These parameters are input into the preset burst prediction model to simulate the performance of the anti-blow valve under different conditions. The predicted burst values ​​such as deformation, damage value, maximum stress value and internal pressure change are calculated by the model and associated with the corresponding burst parameters.

[0031] The blasting simulation robot can be an intelligent testing device used to simulate real explosion scenarios. It can perform blasting simulation experiments and collect data in real time based on the input simulated blasting parameters (such as pressure, temperature, torque, etc.) through a combination of mechanical devices and sensors. Its core functions can include accurately applying variables such as pressure, temperature, torque, etc. Recording the performance data of the explosion-proof valve under different blasting conditions (such as deformation, stress value, etc.). Automatically perform multiple blasting simulations to improve experimental efficiency and consistency.

[0032] The preset simulated blasting parameter values ​​(pressure, temperature, torque, etc.) can be input into the blasting simulation robot. The data can be transmitted to the robot's control system through the network, USB and other interfaces. The robot automatically adjusts the blasting environment (such as adjusting pressure and temperature) according to the input parameter values ​​and starts the blasting experiment. The robot monitors the deformation, damage, stress and other data during the blasting process through built-in sensors. These real-time monitored data are stored as the first simulated blasting value for comparison with the predicted blasting value.

[0033] The first simulated explosion value may refer to the performance data collected by the explosion simulation robot in the actual explosion test. Corresponding to the predicted explosion value, it provides the performance of the explosion-proof valve in the actual environment, including deformation: the deformation of the explosion-proof valve during the explosion process (such as material deformation in the stress concentration area). Damage value: the damage after the actual explosion, reflecting the degree of failure of the material. Maximum stress value: the maximum stress borne by the explosion-proof valve during the explosion process, used to evaluate the structural strength. Internal pressure change value: the change trend of the internal pressure of the valve during the explosion process, to evaluate the stability of the sealing performance. The first simulated explosion value corresponding to the pressure may be the sum of the first simulated deformation and the first simulated internal pressure change value; the first simulated explosion value corresponding to the temperature may be the sum of the first simulated damage value and the first simulated maximum stress value; the first simulated explosion value corresponding to the torque may be the sum of the predicted deformation and the predicted maximum stress value.

[0034] Dynamic weight values ​​can be dynamically adjusted values ​​based on the contribution of different blasting parameters (such as pressure, temperature, torque) to the blasting results. These weight values ​​are used to reflect the relative importance of each blasting parameter to the final test results under different conditions.

[0035] From the blasting simulation of the anti-blasting valve, the predicted value of each blasting parameter and the first simulated value obtained by actual simulation are obtained, and then for each blasting parameter, the predicted blasting value and the first simulated blasting value are substituted into the preset dynamic weight calculation formula to obtain the dynamic weight value of each blasting parameter.

[0036] The prediction error can be used to measure the difference between the predicted explosion value of the explosion-proof valve and the actual simulated explosion value.

[0037] For each blasting parameter, the dynamic weight value, the predicted blasting value and the first simulated blasting value may be substituted into a preset error calculation formula to obtain the predicted error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value.

[0038] The preset adjustment step size can refer to the increment or decrement of the parameter value each time the simulated blasting parameter value is updated. The adjustment step size determines the magnitude of the change in the blasting parameters (such as pressure, temperature, torque, etc.) in each iteration. The size of the step size usually needs to be set according to the specific application scenario and optimization algorithm. A smaller step size helps to improve the optimization accuracy, while a larger step size can speed up the optimization process.

[0039] According to the preset range of simulated blasting parameters, the initial value of each blasting parameter, such as the initial value of pressure, temperature, and torque, can be set. Then, the preset adjustment step size is set to define the variation range of each parameter in each iteration. The initial simulated blasting parameter value is input into the preset blasting prediction model to obtain the initial predicted blasting value. The current simulated blasting parameter value is transmitted to the blasting simulation robot, and the robot is allowed to perform the blasting simulation. The first simulated blasting value of the blasting simulation is obtained, including the corresponding deformation, damage value, maximum stress value, and internal pressure change value. Then, according to the current predicted blasting value and the first simulated blasting value, the dynamic weight value of each blasting parameter is calculated by the preset dynamic weight calculation formula. Based on these dynamic weight values, the total prediction error is calculated using the preset error calculation formula. Then, based on the adjustment step size, the current simulated blasting parameter value is updated. The updated simulated blasting parameter value is continuously input into the blasting prediction model and the blasting simulation robot to obtain a new predicted blasting value and the first simulated blasting value. Continue to update the dynamic weight value and error of each parameter according to the dynamic weight calculation formula and the error calculation formula. Repeat this process until all simulated blasting parameter values ​​reach the maximum value of the preset blasting parameter range. In each iteration, obtain the predicted blasting value (from the blasting prediction model) and the first simulated blasting value (from the blasting simulation robot). According to the difference between the predicted blasting value and the first simulated blasting value, the dynamic weight value of each blasting parameter is continuously updated through the preset dynamic weight calculation formula. Then, according to the updated dynamic weight value, the prediction error is continuously updated through the error formula, and in each iteration, check whether the current blasting parameter value reaches the maximum value of the preset parameter range. If the maximum value is not reached, continue to iterate and update the blasting parameter value. If the maximum value of the preset range is reached, stop the iteration.

[0040] The explosion test platform is a device used to actually test the explosion-proof valve under different explosion conditions. Specifically, it can include a pressure control system: used to simulate different pressure conditions. A temperature control system: used to simulate the test environment under different temperature conditions. A torque sensor: monitors the mechanical response of the valve, such as the torque change during the opening and closing process. A stress and deformation monitoring device: used to measure the stress, deformation and damage generated during the test. A data acquisition system: records and transmits various key data during the test.

[0041] The simulated blasting parameter values ​​(such as pressure, temperature, torque, etc.) with the smallest prediction error can be selected from the previous multiple iterative calculations, that is, the parameter combination that the prediction model believes is closest to the actual blasting conditions. These optimal simulated blasting parameter values ​​are transmitted to the blasting test platform. The transmission content includes information such as pressure, temperature, and torque. The test platform automatically sets the test conditions based on the transmitted data, such as adjusting the pressure and temperature to the set values, adjusting the initial state of the equipment torque sensor, etc. The blasting test platform simulates the blasting parameter values ​​based on the minimum error transmitted and starts the actual blasting test. During the actual blasting test, the platform will apply different stress, temperature, and pressure conditions to the anti-blasting valve to simulate the blasting process and record real-time stress, deformation, damage, and internal pressure changes.

[0042] The actual explosion value may be data measured in real time during the test by the explosion test platform, and generally includes: deformation: the actual deformation of the explosion-proof valve during the explosion process, and specifically, may include the actual damage value: the degree of damage to the material or structure, such as cracks, holes, etc. Actual maximum stress value: the maximum stress generated during the explosion process. Actual internal pressure change value: the fluctuation and change of the internal pressure during the explosion process. The actual explosion value corresponding to the pressure may be the sum of the actual deformation and the actual internal pressure change value; the first simulated explosion value corresponding to the temperature may be the sum of the actual damage value and the actual maximum stress value; the actual explosion value corresponding to the torque may be the sum of the actual deformation and the actual maximum stress value.

[0043] The preset burst test standard is a pre-set passing standard used to judge the performance of the explosion-proof valve in the actual burst test. Specifically, it can include the actual deformation: not exceeding a certain value (such as the maximum allowable deformation). The actual damage value: no obvious structural damage, or the damage degree is within the allowable range. The actual maximum stress value: does not exceed the maximum bearing capacity of the material or structure. The actual internal pressure change value: the internal pressure fluctuation remains within the safety threshold.

[0044] The actual burst value can be compared with the preset burst test standard. If all the actual burst values ​​meet or exceed the preset standard, the anti-explosion valve is considered to have passed the burst test. If any of the actual burst values ​​does not meet the standard, the anti-explosion valve is considered to have failed the test and needs to readjust the design or parameters for optimization.

[0045] In the embodiment of the present application, a predicted blasting value determination module is used to obtain a preset simulated blasting parameter range for each blasting parameter, and input the initial value of the preset simulated blasting parameter range as a simulated blasting parameter value into a preset blasting prediction model to obtain a predicted blasting value of the anti-blasting valve; wherein the blasting parameters include pressure, temperature and torque; the predicted blasting value includes a predicted deformation, a predicted damage value, a predicted maximum stress value and a predicted internal pressure change value; a data transmission module is used to transmit the simulated blasting parameter value to a blasting simulation robot, so that the blasting simulation robot can transmit the simulated blasting parameter value according to the simulated blasting parameter value Perform blasting simulation; a dynamic weight value determination module, used to obtain the first simulated blasting value of the anti-blasting valve obtained by blasting simulation, and calculate the dynamic weight value of each blasting parameter under the simulated blasting parameter value according to the predicted blasting value, the first simulated blasting value and the preset dynamic weight calculation formula; a prediction error calculation module, used to calculate the predicted error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value under the simulated blasting parameter value according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula; a simulated blasting parameter value update module, used to update the predicted blasting value of the anti-blasting valve according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula; According to the preset adjustment step size and the initial value of the preset simulated blasting parameter range, the simulated blasting parameter value is continuously updated, and the updated simulated blasting parameter value is continuously input into the preset blasting prediction model, and transmitted to the blasting simulation robot, and the predicted blasting value of the anti-blasting valve and the first simulated blasting value are continuously updated; the dynamic weight value updating module is used to continuously update the dynamic weight value of each blasting parameter at different simulated blasting parameter values ​​according to the continuously updated predicted blasting value, the first simulated blasting value and the preset dynamic weight calculation formula, and according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value The simulated blasting value and the preset error calculation formula continuously update the predicted blasting value of the anti-blasting valve and the predicted error of the first simulated blasting value until the simulated blasting parameter value is adjusted to the maximum value of the preset simulated blasting parameter range; the actual blasting module is used to transmit the simulated blasting parameter value with the smallest predicted error to the blasting test platform, so that the blasting test platform can perform an actual blasting test according to the minimum simulated blasting parameter value; the test module is used to receive the actual blasting value of the anti-blasting valve transmitted by the blasting test platform, and if the actual blasting value reaches the preset blasting test standard, it is determined that the anti-blasting valve has passed the blasting test. Through the above-mentioned automated testing system for the anti-blasting valve, a large number of virtual blasting simulations are performed using blasting simulation robots and blasting prediction models, which greatly reduces the demand and number of actual blasting, and can avoid expensive actual blasting tests under undesirable parameters, thereby reducing experimental costs. Automated data transmission and parameter updates make the process from simulation test to actual blasting smoother, improving the efficiency of the overall testing process. At the same time, the continuously updated blasting parameter values ​​and prediction errors can ensure that the data at each step is more accurate, thereby providing high-quality input parameters for actual testing.

[0046] On the basis of the above technical solution, optionally, the preset dynamic weight calculation formula is: ; Wherein, P is the simulated blasting parameter value of each blasting parameter; is the dynamic weight value of the ith blasting parameter under the simulated blasting parameter value; is the preset weight adjustment coefficient; is the predicted blasting value of the ith blasting parameter under the simulated blasting parameter value; is the first simulated blasting value of the i-th blasting parameter under the simulated blasting parameter value.

[0047] In this solution, the predicted blasting value corresponding to the pressure may be the sum of the predicted deformation and the predicted internal pressure change value; the predicted blasting value corresponding to the temperature may be the sum of the predicted damage value and the predicted maximum stress value; the predicted blasting value corresponding to the torque may be the sum of the predicted deformation and the predicted maximum stress value. The first simulated blasting value corresponding to the pressure may be the sum of the first simulated deformation and the first simulated internal pressure change value; the first simulated blasting value corresponding to the temperature may be the sum of the first simulated damage value and the first simulated maximum stress value; the first simulated blasting value corresponding to the torque may be the sum of the predicted deformation and the predicted maximum stress value. Therefore, when calculating the dynamic weight value of each parameter, the first simulated blasting value, which is the sum of the predicted blasting corresponding to each blasting parameter, may be calculated first, and then substituted into the formula to calculate the dynamic weight value of each parameter. Specifically, the variance between the predicted value and the simulated value of each blasting parameter may be calculated. , substitute the variance into the formula, and calculate the dynamic weight value of each blasting parameter in combination with the preset weight adjustment coefficient.

[0048] On the basis of the above technical solution, optionally, the preset error calculation formula is: ; in, is the prediction error; is the index index, ranging from 1 to 3; P is the simulated blasting parameter value of each blasting parameter; is the dynamic weight value of the ith blasting parameter under the simulated blasting parameter value; is the predicted blasting value of the ith blasting parameter under the simulated blasting parameter value; is the first simulated blasting value of the i-th blasting parameter under the simulated blasting parameter value.

[0049] On the basis of the above technical solution, optionally, the system further comprises a door opening and closing fatigue test module, and the door opening and closing fatigue test module is used to: Acquire preset switch parameters, preset position and angle parameters, preset applied force data, and preset switching times, and transmit the preset switch parameters, preset position and angle parameters, preset applied force data, and preset switching times to a fatigue simulation robot, so that the fatigue simulation robot can simulate the normal switching operation of the explosion-proof valve according to the preset switch parameters, preset position and angle parameters, preset applied force data, and preset switching times; The actual position data, actual angle data, switching force data and preset door opening and closing fatigue test standard of the explosion-proof valve switch component during each door opening and closing simulation are obtained. If the actual position data, actual angle data and switching force data reach the preset door opening and closing fatigue test standard, it is determined that the explosion-proof valve has passed the door opening and closing fatigue test.

[0050] In this solution, the preset switch parameters may refer to various parameters set when simulating the switch operation, such as the speed, frequency, force, etc. of the switch. These parameters help simulate the switch operation in actual use.

[0051] The preset position and angle parameters may include the angle and position settings required for the explosion-proof valve during the opening and closing operation, for example, the opening angle and closing position of the door.

[0052] The preset applied force data may refer to the magnitude and direction of the force applied to the explosion-proof valve during the simulation. This includes the force and pressure applied during the opening and closing process.

[0053] The preset number of switching operations can be the number of switching operations planned to be performed during the simulation. This helps to simulate the fatigue effects of long-term use.

[0054] The fatigue simulation robot can be a special device used to simulate and test the performance of the explosion-proof valve during long-term use. It can perform opening and closing operations according to the set parameters.

[0055] The explosion-proof valve switch component can be the switch system of the explosion-proof valve, including all mechanical components and systems for opening and closing the valve.

[0056] The actual position data may be actual door position data in each switch operation.

[0057] The actual angle data may be actual angle data of the door during the opening and closing operation.

[0058] The switching force data may be actual switching force data applied to the explosion-proof valve.

[0059] The preset switch door fatigue test standard can be a set standard for evaluating whether the explosion-proof valve performs well in simulated switch operations, including the maximum allowable deformation, the maximum allowable fatigue force, etc.

[0060] The preset switch parameters, position and angle parameters, force data and switch times can be input into the fatigue simulation robot, and the switch simulation operation can be performed by the robot. The fatigue simulation robot performs the switch simulation of the anti-blasting valve according to the set parameters. After each switch simulation, the actual position data, actual angle data and switch force data are recorded. The actual data is compared with the preset switch door fatigue test standard. If the actual data meets the standard, it is determined that the anti-blasting valve has passed the switch door fatigue test.

[0061] In this solution, the door opening and closing fatigue test is performed by a robot, which can reduce labor costs. And the parameters are precisely controlled and recorded to improve the accuracy and consistency of the test.

[0062] On the basis of the above technical solution, optionally, the training process of the preset blasting prediction model includes: Obtaining historical simulated blasting parameter values ​​and historical blasting values ​​of each blasting parameter, and marking blasting value labels of the historical simulated blasting parameter values ​​according to the historical blasting values; wherein the historical blasting values ​​include historical deformation, historical damage value, historical maximum stress value, and historical internal pressure change value; the blasting value labels include deformation label, damage value label, maximum stress value label, and internal pressure change value label; A blasting prediction model is constructed, and the blasting prediction model is trained according to the historical simulated blasting parameter values ​​and blasting value labels until the blasting prediction model reaches a preset blasting prediction model training standard.

[0063] In this solution, the historical simulated blasting parameter values ​​may be recorded values ​​of simulated blasting parameters used in past blasting tests, such as simulated pressure, simulated temperature, simulated torque, and the like.

[0064] The historical blasting value may be the actual result value of the past blasting test, and specifically, may include the historical deformation amount: the deformation amount of the material during the blasting process. The historical damage value: the degree of damage to the material after the blasting. The historical maximum stress value: the maximum stress borne by the material during the blasting process. The historical internal pressure change value: the change value of the internal pressure of the material during the blasting process.

[0065] The burst value label can be a data label that marks the historical burst value, which is used as a supervisory signal when training the model. Specifically, it can include: deformation label: a label corresponding to the historical deformation. Damage value label: a label corresponding to the historical damage value. Maximum stress value label: a label corresponding to the historical maximum stress value. Internal pressure change value label: a label corresponding to the historical internal pressure change value.

[0066] The preset burst prediction model training standard can be a standard for evaluating the model training effect, and specifically can include: training error: the prediction error of the model on the training data. Test error: the prediction error of the model on the independent test data. Model accuracy: the accuracy index of the model prediction.

[0067] Historical simulated blasting parameter values ​​and historical blasting values ​​can be collected, and the historical blasting values ​​can be marked as blasting value labels, including deformation labels, damage value labels, maximum stress value labels, and internal pressure change value labels. Combine the historical simulated blasting parameter values ​​and the corresponding blasting value labels to construct a training data set. Then select a suitable machine learning algorithm (such as linear regression, support vector machine, neural network, etc.) and use the prepared data set to train the blasting prediction model. Input the training data set into the model for training, and monitor the training error and test error of the model to ensure that it is within the preset training standard. Evaluate the performance of the model on the test set and check whether it meets the preset training standard. If the standard is met, stop training.

[0068] In this solution, by training with historical data, the model can more accurately predict the blasting results under different simulated blasting parameters. The prediction model can reduce the number of actual blasting tests, thus saving cost and time.

[0069] Based on the above technical solution, optionally, the system further includes a model updating module, and the model updating module is used to: Continuously updating the historical simulated blasting parameter values ​​and historical blasting values ​​of each blasting parameter, and marking the blasting value labels of the historical simulated blasting parameter values ​​according to the historical blasting values; The model running time is continuously monitored. If the model running time reaches the preset model update time, the blasting prediction model is trained according to the updated historical simulated blasting parameter values ​​and blasting value labels until the blasting prediction model reaches the preset blasting prediction model training standard.

[0070] In this solution, the model running time can be the total time from the start of the model running to the current time. For example, the total time from the start of training to the current time.

[0071] The preset model update duration may be a time threshold set by the system. When the model running time reaches or exceeds this time threshold, the model needs to be updated.

[0072] You can continue to collect new historical simulated blasting parameter values ​​and the corresponding historical blasting values. As time goes by, annotate new data and add it to the historical data set. During the model operation, record the time from the start of model training to the present, and regularly check the model's running time. If the model running time reaches the preset model update time, the model needs to be updated. For example, if the preset model update time is 30 days, and the model has been running for 30 days or more, the model update step is triggered. Retrain the model based on the updated historical simulated blasting parameter values ​​and the new blasting value labels. Divide the latest dataset into a training set and a validation set to ensure that the model can be effectively trained and validated. Retrain the blasting prediction model using the updated dataset. Select an appropriate machine learning algorithm and ensure that the performance of the model is monitored during the training process to ensure that the model meets the preset blasting prediction model training standards.

[0073] In this scenario, updating the model regularly can maintain its prediction accuracy, especially when the data or environment changes. By continuously updating, the model can adapt to new data trends and changes, which can improve the reliability of predictions. Example

[0074] Figure 2 Schematic diagram of the structure of the automatic testing system of the explosion-proof valve provided in the second embodiment of the present application. Figure 2 As shown, specifically including the following: The system further comprises a sealing performance prediction model building module 109, wherein the sealing performance prediction model building module is used to: Acquire historical environmental data, historical load data, historical vibration data, historical leakage amount and historical deformation amount of the explosion-proof valve seal, and create a first data set according to the historical environmental data, historical load data and historical vibration data; labeling the leakage amount label of the first data set according to the historical leakage amount, and labeling the deformation amount label of the first data set according to the historical deformation amount; A sealing performance prediction model is constructed, and the sealing performance prediction model is trained according to the first data set, the leakage amount label, and the deformation amount label until the sealing performance prediction model reaches a preset sealing performance prediction model training standard.

[0075] In this embodiment, the explosion-proof valve seal may be a sealing component used in an explosion-proof valve, which is responsible for providing effective sealing under explosion or extreme pressure conditions, preventing leakage and ensuring the safety and functionality of the equipment.

[0076] The historical environmental data may be historical data recording the explosion-proof valve under different environmental conditions, such as temperature, humidity, air pressure, etc.

[0077] The historical load data may be the load data recorded that the seal is subjected to during use, including pressure, torque, etc.

[0078] Historical vibration data can be a record of the vibrations experienced by the seal during operation, which may affect its performance and life.

[0079] The historical leakage volume may be data recording the leakage volume of the seal during actual use, reflecting the historical performance of the sealing performance.

[0080] The historical deformation amount may be data recording the deformation amount of the seal during use, reflecting the durability and deformation condition of the seal.

[0081] The first data set may be a data set that combines historical environmental data, historical load data, and historical vibration data, which is used to analyze how these factors affect the performance of the seal and to train models, predict performance, and optimize design.

[0082] The historical environmental data, load data, vibration data, leakage and deformation of the anti-explosion valve seal can be obtained from the sensor system or maintenance records of the equipment to ensure the accuracy and completeness of the data. The collected data is cleaned to remove outliers and noise to ensure the consistency and accuracy of the data. The environmental data, load data and vibration data are then integrated into one data set. Ensure that each record contains data from all three aspects for comprehensive analysis, and then organize the historical environmental data, historical load data and historical vibration data into the first data set.

[0083] The leakage label can refer to the actual leakage value corresponding to each sample. This label is used to represent the leakage performance of the seal under specific conditions for supervised learning when training and evaluating the model.

[0084] The deformation label may refer to the actual deformation value corresponding to each sample. This label is used to indicate the deformation of the seal under specific conditions so as to perform supervised learning when training and evaluating the model.

[0085] A corresponding leakage amount label may be allocated to each piece of data in the first data set according to the historical leakage amount data, and a corresponding deformation amount label may be allocated to each piece of data in the first data set according to the historical deformation amount.

[0086] The sealing performance prediction model can be a machine learning model used to predict the performance of anti-explosion valve seals. Such a model is usually trained and predicted based on historical data (such as environmental conditions, load data, vibration data) and actual leakage and deformation. The goal of the model is to predict the future leakage and deformation of the seal based on these input data to evaluate its sealing performance.

[0087] The preset sealing performance prediction model training standard can be a standard for evaluating the model training effect. Specifically, it can include prediction accuracy: the prediction accuracy of the model on the training set and the validation set (such as mean square error, mean absolute error, R2 value, etc.). Convergence: whether the model training process is stable and whether the loss function converges to the expected range. Overfitting and underfitting: whether the performance of the model on the training set and the test set is consistent, avoiding overfitting or underfitting. Training time: whether the model training is completed within a reasonable time.

[0088] The data set can be divided into a training set, a validation set, and a test set. Usually, the training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to finally evaluate the model performance. Choose a suitable machine learning algorithm, such as linear regression, support vector machine, random forest, neural network, etc. This depends on the characteristics of the data and the prediction target. Use the training set data and the leakage label and deformation label to train the model. The input data includes environmental conditions, load data, vibration data, and the output data is leakage and deformation. According to the performance of the validation set, adjust the model's hyperparameters (such as learning rate, regularization coefficient, number of trees, etc.) to optimize the model performance. Use the test set data to evaluate the performance of the model. Calculate prediction accuracy indicators such as mean square error (MSE), mean absolute error (MAE), R2 value, etc. Ensure that the model performance meets the preset training standards. For example, the mean square error is lower than a certain threshold and the R2 value is higher than a certain threshold. If the model does not meet the preset standards, analyze the shortcomings of the model. It may be necessary to readjust the model structure, increase the amount of data, or improve feature engineering. According to the analysis results, adjust the model settings and retrain until the model performance meets the standards.

[0089] In this embodiment, by using historical data for training, the model can learn from past experience and provide more accurate sealing performance predictions.

[0090] On the basis of the above technical solution, optionally, the system further comprises a sealing performance testing module, and the sealing performance testing module is used to: Acquire real-time environmental data, real-time load data and real-time vibration data of the explosion-proof valve seal, input the real-time environmental data, real-time load data and real-time vibration data into a sealing performance prediction model, and obtain a predicted leakage amount and a predicted deformation amount of the explosion-proof valve seal; A preset sealing performance evaluation standard is obtained. If the predicted leakage amount and the predicted deformation amount reach the preset sealing performance evaluation standard, it is determined that the anti-explosion valve has passed the sealing performance test.

[0091] In this solution, real-time environmental data may include current environmental conditions, such as temperature, humidity, atmospheric pressure, etc. These data affect the sealing performance, especially under extreme or changing environmental conditions.

[0092] Real-time load data may include the load currently applied to the seal, such as pressure, torque, etc. These loads will affect the deformation and sealing effect of the seal.

[0093] Real-time vibration data can record the vibration conditions in the current environment, including vibration frequency, amplitude, etc. Vibration will affect the structure and performance of seals.

[0094] The predicted leakage amount can be based on real-time environmental data, load data and vibration data, and the sealing performance prediction model provides a predicted value for the amount of possible leakage of the seal.

[0095] Predicted deformation can be based on real-time data, and the model predicts the amount of deformation that may occur in the seal. This helps to understand the degree of deformation of the seal in actual use.

[0096] The preset sealing performance evaluation standard can be a set standard used to evaluate whether the sealing performance is qualified. It usually includes the threshold value of the maximum leakage and deformation allowed. For example, the leakage should not exceed a certain value and the deformation should be kept within a certain range.

[0097] Environmental data, load data and vibration data can be collected in real time through sensors and monitoring systems. The acquired real-time environmental data, real-time load data and real-time vibration data are input into the sealing performance prediction model. The model will use these data to calculate and output the predicted leakage and predicted deformation. Finally, the predicted leakage and predicted deformation are compared with the preset evaluation criteria. If the predicted value meets or exceeds the standard, it is considered that the anti-explosion valve has passed the sealing performance test; if the predicted value exceeds the standard, further inspection or adjustment of the seal is required.

[0098] In this solution, through real-time monitoring and prediction, sealing problems of the explosion-proof valve, such as leakage or deformation, can be discovered in time. This helps to repair or adjust the problem before it becomes serious, thereby improving the reliability and safety of the product. Example

[0099] Figure 3 Schematic diagram of the structure of the automatic testing system for explosion-proof valves provided in the third embodiment of the present application. Figure 3 As shown, specifically including the following: The system further comprises a burst fatigue test module 110, which is used for: The simulated blasting parameter value with the smallest prediction error and the preset simulated blasting time interval are transmitted to the blasting simulation robot, so that the blasting simulation robot can continue to perform blasting simulation according to the simulated blasting parameter value with the smallest prediction error and the preset simulated blasting time interval; Continuously acquiring a second simulated blasting value and a number of simulated blasting times obtained by the blasting simulation until the number of simulated blasting times reaches a preset simulated blasting threshold, and transmitting a stop simulated blasting instruction to the blasting simulation robot; If all the second simulated explosion values ​​exceed the preset explosion fatigue test standard, it is determined that the anti-explosion valve has passed the explosion fatigue test.

[0100] In this embodiment, the preset simulated blasting time interval may refer to the time interval between each blasting simulation, which ensures that the time interval of the blasting simulation process remains consistent, and helps to evaluate the performance of the anti-blasting valve at a specific frequency.

[0101] The second simulated explosion value may refer to the performance data of the explosion-proof valve obtained in the second simulated explosion, which generally includes deformation, damage value, maximum stress value and internal pressure change value.

[0102] The number of simulated blasting times may refer to the total number of blasting simulations performed in a specified simulated blasting process.

[0103] The preset simulated blasting threshold may refer to the maximum number of simulated blasting times set when performing a simulated blasting test. For example, the simulated blasting threshold may be set to 50 times.

[0104] The stop simulation blasting instruction may be an instruction for terminating the blasting simulation process. Once the instruction is issued, the robot should stop further blasting simulation.

[0105] The preset burst fatigue test standard may refer to a standard for evaluating the performance of a burst-proof valve, which generally includes a series of deformation, damage value, maximum stress value and internal pressure change value. These standards are used to determine whether the valve has passed the burst fatigue test.

[0106] The simulated blasting parameter value with the smallest prediction error and the preset simulated blasting time interval can be transmitted to the blasting simulation robot. The robot performs continuous blasting simulation according to the parameter value and the time interval. The second simulated blasting value (performance data of each simulation) and the number of simulated blasting are continuously obtained. When the number of simulated blasting reaches a preset threshold, an instruction to stop the simulated blasting is sent to the robot. All the second simulated blasting values ​​are checked to see if they meet the preset blasting fatigue test standard, and whether the anti-blasting valve passes the test.

[0107] In this embodiment, by precisely controlling the simulated explosion parameters and time intervals, consistent and repetitive test conditions can be provided, which helps to ensure the accuracy and reliability of the test results and reduce test errors. By continuously performing multiple simulated explosions and recording performance data, the performance of the explosion-proof valve under different conditions can be fully evaluated, which helps to identify potential fatigue problems and verify the stability of the valve in long-term use. Example

[0108] Figure 4 1 is a flow chart of an automated testing method for explosion-proof valves provided in Example 4 of the present application. Figure 4 As shown, the specific steps include: S401, obtaining a preset simulated blasting parameter range for each blasting parameter, inputting the initial value of the preset simulated blasting parameter range as a simulated blasting parameter value into a preset blasting prediction model, and obtaining a predicted blasting value of the anti-blasting valve; wherein the blasting parameters include pressure, temperature and torque; and the predicted blasting value includes a predicted deformation, a predicted damage value, a predicted maximum stress value and a predicted internal pressure change value.

[0109] S402, transmitting the simulated blasting parameter values ​​to a blasting simulation robot, so that the blasting simulation robot performs blasting simulation according to the simulated blasting parameter values.

[0110] S403, obtaining a first simulated blasting value of the anti-blasting valve obtained by blasting simulation, and calculating the dynamic weight value of each blasting parameter in the simulated blasting parameter value according to the predicted blasting value, the first simulated blasting value and a preset dynamic weight calculation formula.

[0111] S404, calculating the predicted error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value under the simulated blasting parameter value according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula.

[0112] S405, continuously updating the simulated blasting parameter values ​​according to the preset adjustment step size and the initial value of the preset simulated blasting parameter range, continuously inputting the updated simulated blasting parameter values ​​into the preset blasting prediction model, and transmitting them to the blasting simulation robot, continuously updating the predicted blasting value of the anti-blasting valve and the first simulated blasting value.

[0113] S406, based on the continuously updated predicted blasting value, the first simulated blasting value and the preset dynamic weight calculation formula, the dynamic weight value of each blasting parameter at different simulated blasting parameter values ​​is continuously updated, and based on the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula, the predicted blasting value of the anti-blasting valve and the predicted error of the first simulated blasting value are continuously updated until the simulated blasting parameter value is adjusted to the maximum value of the preset simulated blasting parameter range.

[0114] S407, transmitting the simulated blasting parameter value with the smallest prediction error to the blasting test platform, so that the blasting test platform can perform actual blasting test according to the smallest simulated blasting parameter value.

[0115] S408, receiving the actual explosion value of the explosion-proof valve transmitted by the explosion test platform, and if the actual explosion value reaches a preset explosion test standard, determining that the explosion-proof valve passes the explosion test.

[0116] In this embodiment, a preset simulated blasting parameter range of each blasting parameter is obtained, and the initial value of the preset simulated blasting parameter range is input as a simulated blasting parameter value into a preset blasting prediction model to obtain a predicted blasting value of the anti-blasting valve; wherein, the blasting parameters include pressure, temperature and torque; the predicted blasting value includes a predicted deformation, a predicted damage value, a predicted maximum stress value and a predicted internal pressure change value; the simulated blasting parameter value is transmitted to a blasting simulation robot, so that the blasting simulation robot performs blasting simulation according to the simulated blasting parameter value; the first simulated blasting value of the anti-blasting valve obtained by the blasting simulation is obtained, and the dynamic weight value of each blasting parameter under the simulated blasting parameter value is calculated according to the predicted blasting value, the first simulated blasting value and a preset dynamic weight calculation formula; the predicted error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value under the simulated blasting parameter value is calculated according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and a preset error calculation formula; according to the preset adjustment step size and the preset simulated blasting The initial value of the parameter range is continuously updated, and the updated simulated blasting parameter value is continuously input into the preset blasting prediction model, and transmitted to the blasting simulation robot, and the predicted blasting value of the anti-blasting valve and the first simulated blasting value are continuously updated; according to the continuously updated predicted blasting value, the first simulated blasting value and the preset dynamic weight calculation formula, the dynamic weight value of each blasting parameter at different simulated blasting parameter values ​​is continuously updated, and according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula, the predicted blasting value of the anti-blasting valve and the predicted error of the first simulated blasting value are continuously updated until the simulated blasting parameter value is adjusted to the maximum value of the preset simulated blasting parameter range; the simulated blasting parameter value with the smallest prediction error is transmitted to the blasting test platform, so that the blasting test platform can perform an actual blasting test according to the smallest simulated blasting parameter value; the actual blasting value of the anti-blasting valve transmitted by the blasting test platform is received, and if the actual blasting value reaches the preset blasting test standard, it is determined that the anti-blasting valve has passed the blasting test. Through the above-mentioned automated testing method for explosion-proof wave valves, a large number of virtual blasting simulations are performed using blasting simulation robots and blasting prediction models, which greatly reduces the need and number of actual blasting, and can avoid expensive actual blasting tests under undesirable parameters, thereby reducing experimental costs. Automated data transmission and parameter updates make the process from simulation testing to actual blasting smoother, improving the efficiency of the overall testing process. At the same time, the continuously updated blasting parameter values ​​and prediction errors can ensure that the data at each step is more accurate, thereby providing high-quality input parameters for actual testing.

[0117] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0118] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a computer software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0119] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

[0120] The above are only preferred embodiments of the present application and the technical principles used. The present application is not limited to the specific embodiments described herein, and various obvious changes, readjustments and substitutions that can be made by those skilled in the art will not deviate from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the claims.

Claims

1. An automatic testing system for explosion-proof valves, characterized in that: The system comprises: A predicted blasting value determination module is used to obtain a preset simulated blasting parameter range for each blasting parameter, and input the initial value of the preset simulated blasting parameter range as the simulated blasting parameter value into a preset blasting prediction model to obtain a predicted blasting value of the anti-blasting valve; wherein the blasting parameters include pressure, temperature and torque; the predicted blasting value includes a predicted deformation, a predicted damage value, a predicted maximum stress value and a predicted internal pressure change value; A data transmission module, used for transmitting the simulated blasting parameter value to the blasting simulation robot, so that the blasting simulation robot can perform blasting simulation according to the simulated blasting parameter value; A dynamic weight value determination module is used to obtain a first simulated blasting value of the anti-blasting valve obtained by blasting simulation, and calculate the dynamic weight value of each blasting parameter in the simulated blasting parameter value according to the predicted blasting value, the first simulated blasting value and a preset dynamic weight calculation formula; A prediction error calculation module, for calculating the prediction error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value under the simulated blasting parameter value according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and a preset error calculation formula; A simulated blasting parameter value updating module, used to continuously update the simulated blasting parameter value according to a preset adjustment step length and an initial value of a preset simulated blasting parameter range, and continuously input the updated simulated blasting parameter value into a preset blasting prediction model, and transmit it to a blasting simulation robot, and continuously update the predicted blasting value of the anti-blasting valve and the first simulated blasting value; A dynamic weight value updating module, for continuously updating the dynamic weight values ​​of each blasting parameter at different simulated blasting parameter values ​​according to the continuously updated predicted blasting value, the first simulated blasting value and the preset dynamic weight calculation formula, and continuously updating the predicted error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula, until the simulated blasting parameter value is adjusted to the maximum value of the preset simulated blasting parameter range; The actual blasting module is used to transmit the simulated blasting parameter value with the smallest prediction error to the blasting test platform, so that the blasting test platform can perform actual blasting test according to the minimum simulated blasting parameter value; The test module is used to receive the actual explosion value of the anti-explosion valve transmitted by the explosion test platform, and if the actual explosion value reaches a preset explosion test standard, it is determined that the anti-explosion valve passes the explosion test.

2. The automatic testing system for explosion-proof valves according to claim 1, characterized in that: The preset dynamic weight calculation formula is: ； Wherein, P is the simulated blasting parameter value of each blasting parameter; is the dynamic weight value of the ith blasting parameter under the simulated blasting parameter value; is the preset weight adjustment coefficient; is the predicted blasting value of the ith blasting parameter under the simulated blasting parameter value; is the first simulated blasting value of the i-th blasting parameter under the simulated blasting parameter value.

3. The automatic testing system for explosion-proof valves according to claim 1, characterized in that: The preset error calculation formula is: ； in, is the prediction error; is the index index, ranging from 1 to 3; P is the simulated blasting parameter value of each blasting parameter; is the dynamic weight value of the ith blasting parameter under the simulated blasting parameter value; is the predicted blasting value of the ith blasting parameter under the simulated blasting parameter value; is the first simulated blasting value of the i-th blasting parameter under the simulated blasting parameter value.

4. The automatic testing system for explosion-proof valves according to claim 1, characterized in that: The system further includes a sealing performance prediction model building module, wherein the sealing performance prediction model building module is used to: Acquire historical environmental data, historical load data, historical vibration data, historical leakage amount and historical deformation amount of the explosion-proof valve seal, and create a first data set according to the historical environmental data, historical load data and historical vibration data; labeling the leakage amount label of the first data set according to the historical leakage amount, and labeling the deformation amount label of the first data set according to the historical deformation amount; A sealing performance prediction model is constructed, and the sealing performance prediction model is trained according to the first data set, the leakage amount label, and the deformation amount label until the sealing performance prediction model reaches a preset sealing performance prediction model training standard.

5. The automatic testing system for explosion-proof valves according to claim 4, characterized in that: The system further comprises a sealing performance testing module, which is used to: Acquire real-time environmental data, real-time load data and real-time vibration data of the explosion-proof valve seal, input the real-time environmental data, real-time load data and real-time vibration data into a sealing performance prediction model, and obtain a predicted leakage amount and a predicted deformation amount of the explosion-proof valve seal; A preset sealing performance evaluation standard is obtained. If the predicted leakage amount and the predicted deformation amount reach the preset sealing performance evaluation standard, it is determined that the anti-explosion valve has passed the sealing performance test.

6. The automatic testing system for explosion-proof valves according to claim 1, characterized in that: The system further comprises a burst fatigue test module, wherein the burst fatigue test module is used for: The simulated blasting parameter value with the smallest prediction error and the preset simulated blasting time interval are transmitted to the blasting simulation robot, so that the blasting simulation robot can continue to perform blasting simulation according to the simulated blasting parameter value with the smallest prediction error and the preset simulated blasting time interval; Continuously acquiring a second simulated blasting value and a number of simulated blasting times obtained by the blasting simulation until the number of simulated blasting times reaches a preset simulated blasting threshold, and transmitting a stop simulated blasting instruction to the blasting simulation robot; If all the second simulated explosion values ​​exceed the preset explosion fatigue test standard, it is determined that the anti-explosion valve has passed the explosion fatigue test.

7. The automatic testing system for explosion-proof valves according to claim 1, characterized in that: The system further comprises a door opening and closing fatigue test module, wherein the door opening and closing fatigue test module is used for: Acquire preset switch parameters, preset position and angle parameters, preset applied force data, and preset switching times, and transmit the preset switch parameters, preset position and angle parameters, preset applied force data, and preset switching times to a fatigue simulation robot, so that the fatigue simulation robot can simulate the normal switching operation of the explosion-proof valve according to the preset switch parameters, preset position and angle parameters, preset applied force data, and preset switching times; The actual position data, actual angle data, switching force data and preset door opening and closing fatigue test standard of the explosion-proof valve switch component during each door opening and closing simulation are obtained. If the actual position data, actual angle data and switching force data reach the preset door opening and closing fatigue test standard, it is determined that the explosion-proof valve has passed the door opening and closing fatigue test.

8. The automatic testing system for explosion-proof valves according to claim 1, characterized in that: The training process of the preset blasting prediction model includes: Obtaining historical simulated blasting parameter values ​​and historical blasting values ​​of each blasting parameter, and marking blasting value labels of the historical simulated blasting parameter values ​​according to the historical blasting values; wherein the historical blasting values ​​include historical deformation, historical damage value, historical maximum stress value, and historical internal pressure change value; the blasting value labels include deformation label, damage value label, maximum stress value label, and internal pressure change value label; A blasting prediction model is constructed, and the blasting prediction model is trained according to the historical simulated blasting parameter values ​​and blasting value labels until the blasting prediction model reaches a preset blasting prediction model training standard.

9. The automatic testing system for explosion-proof valves according to claim 8, characterized in that: The system further comprises a model updating module, wherein the model updating module is used for: Continuously updating the historical simulated blasting parameter values ​​and historical blasting values ​​of each blasting parameter, and marking the blasting value labels of the historical simulated blasting parameter values ​​according to the historical blasting values; The model running time is continuously monitored. If the model running time reaches the preset model update time, the blasting prediction model is trained according to the updated historical simulated blasting parameter values ​​and blasting value labels until the blasting prediction model reaches the preset blasting prediction model training standard.

10. An automated testing method for explosion-proof valves, characterized in that: The method comprises: Obtaining a preset simulated blasting parameter range for each blasting parameter, inputting the initial value of the preset simulated blasting parameter range as a simulated blasting parameter value into a preset blasting prediction model, and obtaining a predicted blasting value of the anti-blasting valve; wherein the blasting parameters include pressure, temperature and torque; and the predicted blasting value includes a predicted deformation, a predicted damage value, a predicted maximum stress value and a predicted internal pressure change value; Transmitting the simulated blasting parameter value to the blasting simulation robot, so that the blasting simulation robot performs blasting simulation according to the simulated blasting parameter value; Obtaining a first simulated blasting value of the anti-blasting valve obtained by blasting simulation, and calculating the dynamic weight value of each blasting parameter in the simulated blasting parameter value according to the predicted blasting value, the first simulated blasting value and a preset dynamic weight calculation formula; According to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula, the predicted error between the predicted blasting value of the anti-blasting valve and the first simulated blasting value under the simulated blasting parameter value is calculated; According to a preset adjustment step length and an initial value of a preset simulated blasting parameter range, the simulated blasting parameter value is continuously updated, and the updated simulated blasting parameter value is continuously input into a preset blasting prediction model, and transmitted to a blasting simulation robot, and the predicted blasting value of the anti-blasting valve and the first simulated blasting value are continuously updated; According to the continuously updated predicted blasting value, the first simulated blasting value and the preset dynamic weight calculation formula, the dynamic weight value of each blasting parameter at different simulated blasting parameter values ​​is continuously updated, and according to the dynamic weight value of each blasting parameter, the predicted blasting value, the first simulated blasting value and the preset error calculation formula, the predicted blasting value of the anti-blasting valve and the predicted error of the first simulated blasting value are continuously updated until the simulated blasting parameter value is adjusted to the maximum value of the preset simulated blasting parameter range; The simulated blasting parameter value with the smallest prediction error is transmitted to the blasting test platform, so that the blasting test platform can perform actual blasting test according to the smallest simulated blasting parameter value; The actual explosion value of the explosion-proof valve transmitted by the explosion test platform is received, and if the actual explosion value reaches a preset explosion test standard, it is determined that the explosion-proof valve passes the explosion test.

Images