A method and system for decoupling test of multi-loads in indoor explosions of residential buildings

Abstract

The present application relates to a method and system for testing multi-load decoupling of indoor explosions in residential buildings, and belongs to the field of explosion effect testing. The method includes: obtaining raw sensor data and raw image data; based on the raw sensor data and raw image data, using multiple single-load algorithms to analyze different loads to obtain multiple single-load analysis results; integrating all single-load analysis results into an explosion effect data set, and using a multi-load decoupling model to process the explosion effect data set to obtain multi-load decoupling analysis results; the multi-load decoupling model is constructed using a multi-load correlation analysis algorithm, a load contribution evaluation algorithm, and a multi-load decoupling algorithm; comparing actual explosion test results with multi-load decoupling analysis results, and determining the explosion multi-load decoupling effect based on the comparison results. The present application can realize multi-load decoupling testing of indoor explosions in residential buildings, improving the accuracy and reliability of the test.

Description

Technical Field

[0001] The present application relates to the field of explosion effect testing, and specifically to a method and system for decoupling indoor explosion multi-load testing in residential areas, which is used to evaluate and study the impact of loads on building structures and internal facilities. Background Art

[0002] With the acceleration of urbanization, the safety of indoor spaces for residents has received increasing attention. In some special cases, such as explosions caused by gas leaks, they can pose a serious threat to the lives and property safety of residents. At present, the testing methods for indoor explosions in residential buildings mainly focus on small-scale experiments or the measurement of specific parameters. There is a lack of decoupled testing methods for full-scale residential indoor large spaces with multiple loads. Existing testing methods often cannot fully and accurately reflect the changes in various physical parameters during the explosion process, and it is difficult to effectively decouple different loads, such as overpressure, thermal radiation, shock waves, etc. The coupling effects of these loads are crucial to structural safety and personnel safety.

[0003] To improve the accuracy of investigations and post-explosion responses in residential areas, a new testing method is urgently needed to simulate the explosion process in a real residential environment and accurately measure and analyze the various loads generated by the explosion. Therefore, developing a decoupled testing method for full-scale, large-space, and multi-load explosions in residential areas is crucial for improving prevention and response capabilities for residential areas and protecting people's lives and property. Summary of the Invention

[0004] The embodiments of the present application provide a method and system for decoupling testing of multi-loads for indoor explosions in residential areas, so as to solve the problems of low testing accuracy and poor reliability in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for decoupling a residential indoor explosion multi-load test, comprising:

[0006] Obtaining raw sensor data collected by various types of sensors in the residential indoor explosion multi-load decoupling test system and raw image data collected by various types of image acquisition devices;

[0007] Based on the original sensor data and the original image data, using multiple single load algorithms to perform analysis of different loads to obtain multiple single load analysis results;

[0008] All single load analysis results are integrated into an explosion effect data set, and the explosion effect data set is processed using a multi-load decoupling model to obtain a multi-load decoupling analysis result; the multi-load decoupling model is constructed using a multi-load correlation analysis algorithm, a load contribution evaluation algorithm, and a multi-load decoupling algorithm;

[0009] The actual explosion test results are compared with the multi-load decoupling analysis results, and the explosion multi-load decoupling effect is determined based on the comparison results.

[0010] Preferably, a multi-load decoupling model is used to process the explosion effect data set to obtain a multi-load decoupling analysis result; the multi-load decoupling model is constructed using a multi-load correlation analysis algorithm, a load contribution evaluation algorithm and a multi-load decoupling algorithm, including:

[0011] A multi-load correlation analysis algorithm is used to perform correlation analysis on the explosion effect data set to obtain a load correlation matrix;

[0012] The load contribution evaluation algorithm is used to evaluate the load correlation matrix to obtain a load contribution matrix;

[0013] The load contribution matrix is ​​processed using a multi-load decoupling algorithm to obtain a decoupling effect matrix; wherein the multi-load decoupling algorithm performs different decoupling analyses on different sub-areas based on the location of the explosion source and the explosion impact range;

[0014] The time series analysis algorithm is used to analyze the decoupling effect matrix and obtain the multi-load decoupling analysis results.

[0015] Preferably, the multi-load decoupling algorithm is used to process the load contribution matrix to obtain a decoupling effect matrix, including:

[0016] Determining the location of the explosion source and the explosion impact range based on the raw sensor data and the raw image data, and dividing the indoor area of ​​the residents into a plurality of sub-areas based on the location of the explosion source and the explosion impact range; the plurality of sub-areas include sub-areas of a first level and sub-areas of a second level; the second level is lower than the first level, and the explosion source is located in the sub-area of ​​the first level;

[0017] Splitting the load contribution matrix into load contribution matrices of each sub-region according to the sub-region;

[0018] Preprocessing the load contribution matrix of each sub-region to obtain a preprocessed load contribution matrix of each sub-region;

[0019] For each sub-region, a feature extraction method is used to extract features from the pre-processed load contribution matrix to obtain a feature matrix;

[0020] Different decoupling analysis methods are used to perform decoupling analysis on the characteristic matrices of sub-regions at different levels to obtain the decoupling intermediate matrix of each sub-region;

[0021] Constructing an explosion effect knowledge graph, and using domain knowledge in the explosion effect knowledge graph to adjust the decoupling intermediate matrix of each sub-region respectively, to obtain an adjusted decoupling intermediate matrix of each sub-region;

[0022] Effect separation is performed on the adjusted decoupling intermediate matrix of each sub-region to obtain a decoupling separation matrix for each region, and the decoupling separation matrices of all regions are spliced ​​to obtain a decoupling effect matrix.

[0023] Preferably, the decoupling analysis is performed on the characteristic matrices of sub-regions of different levels using different decoupling analysis methods to obtain the decoupling intermediate matrix of each sub-region, including:

[0024] Performing regression analysis on the feature matrix of the first-level sub-region using a principal component regression algorithm to obtain a first principal component regression result, performing decoupling analysis on the feature matrix of the first-level sub-region using a neural network model to obtain a first neural network decoupling result, performing ensemble learning processing on the feature matrix of the first-level sub-region using an ensemble learning method to obtain a first ensemble learning decoupling result; performing regression analysis on the feature matrix of the first-level sub-region using a partial least squares regression algorithm to obtain a first partial least squares regression result; taking a weighted average of the first principal component regression result, the first neural network decoupling result, the first ensemble learning decoupling result, and the first partial least squares regression result to obtain a decoupled intermediate matrix of the first-level sub-region;

[0025] The principal component regression algorithm is used to perform regression analysis on the characteristic matrix of the second-level sub-region to obtain a second principal component regression result, and the partial least squares regression algorithm is used to perform regression analysis on the characteristic matrix of the second-level sub-region to obtain a second partial least squares regression result; the first principal component regression result and the second partial least squares regression result are weighted and averaged to obtain a decoupled intermediate matrix of the second-level sub-region.

[0026] Preferably, determining the location of the explosion source and the explosion impact range based on the original sensor data and the original image data includes:

[0027] Performing time difference positioning processing on the raw sensor data using a sensor data positioning algorithm to obtain the first explosion source position;

[0028] Using an image analysis algorithm to perform video analysis, image segmentation, feature extraction, and target tracking on the original image data to obtain the location of the second explosion source;

[0029] The numerical simulation method is used to simulate and analyze the three-dimensional model of the residential interior to obtain the location of the third explosion source and the initial impact range to be adjusted;

[0030] Based on the first explosion source position and the second explosion source position, the third explosion source position and the initial impact range are adjusted to obtain the explosion source position and the explosion impact range.

[0031] Preferably, the preprocessing of the load contribution matrix of each sub-region to obtain the preprocessed load contribution matrix of each sub-region includes:

[0032] The data cleaning algorithm is used to remove noise and outliers from the load contribution matrix of each sub-area to obtain cleaned data;

[0033] Standardizing the cleaned data using a standardization algorithm to make the scales of different features consistent, thereby obtaining standardized data;

[0034] A missing value filling algorithm is used to fill in the missing values ​​of the standardized data to obtain a preprocessed load contribution matrix for each sub-region.

[0035] Preferably, the feature extraction method is used to extract features from the preprocessed load contribution matrix to obtain a feature matrix, including:

[0036] Using a feature selection algorithm to perform feature selection processing on the preprocessed load contribution matrix to obtain a feature parameter list;

[0037] extracting selected feature parameters from the feature parameter list using a feature extraction algorithm to obtain a parameter matrix;

[0038] A feature normalization algorithm is used to normalize all feature parameters in the parameter matrix to generate a feature matrix.

[0039] Preferably, the step of constructing an explosion effect knowledge graph and adjusting the decoupling intermediate matrix of each sub-region using the domain knowledge in the explosion effect knowledge graph to obtain the adjusted decoupling intermediate matrix of each sub-region includes:

[0040] Use the knowledge graph construction algorithm to build the explosion effect knowledge graph;

[0041] The knowledge fusion algorithm is used to fuse the domain knowledge in the explosion effect knowledge graph with the decoupling intermediate results of each sub-region to obtain the fused decoupling intermediate matrix of each sub-region.

[0042] The result correction algorithm is used to correct the decoupling intermediate matrix after fusion of each sub-region in combination with the historical data and prior knowledge in the explosion effect knowledge graph to obtain the adjusted decoupling intermediate matrix of each sub-region.

[0043] Preferably, based on the raw sensor data and the raw image data, multiple single load algorithms are used to perform analysis of different loads to obtain multiple single load analysis results, including:

[0044] The free-field pressure sensor data, temperature sensor data, fragment image data collected by high-speed cameras, velocity target paper data, wall pressure sensor data, concentration sensor data, flame image data recorded by high-speed cameras, building image data collected by ordinary cameras, bird's-eye view video data taken by global camera drones, and local video data taken by motion cameras are preprocessed separately;

[0045] The pre-processed free-field pressure sensor data is processed using a shock wave propagation model algorithm to construct a shock wave propagation model and obtain the propagation path and intensity of the shock wave.

[0046] The pre-processed temperature sensor data is processed using a thermal radiation transfer algorithm to establish a thermal radiation transfer model to obtain the flame temperature change, flame temperature distribution, and thermal radiation impact range during the explosion process.

[0047] The fragment dynamics algorithm is used to process the pre-processed fragment image data and the pre-processed velocity target paper data to calculate the speed and trajectory of indoor wall glass fragments and outdoor glass fragments, and obtain the movement law of the fragments;

[0048] The pre-processed wall pressure sensor data is processed using a structural dynamic response algorithm to evaluate the dynamic response of the building structure under blast loads and determine the extent of damage to the building structure.

[0049] The gas concentration distribution algorithm is used to process the pre-processed concentration sensor data to analyze the changes in the indoor natural gas and liquefied petroleum gas concentration distribution and obtain the gas leakage situation before the explosion;

[0050] The flame propagation velocity algorithm is used to process the pre-processed flame image data to analyze the flame propagation path and velocity and obtain the flame's impact on different areas;

[0051] The building damage pattern recognition algorithm is used to process the pre-processed building image data to identify the building damage pattern;

[0052] The pre-processed overhead video data is processed using a global perspective analysis algorithm to analyze the explosion impact range and explosion mode;

[0053] The pre-processed local video data is processed using a local detail analysis algorithm to analyze the explosion impact and damage details in key areas.

[0054] Through the testing method of the present application, the explosion effects in large indoor space environments of residents, especially the multi-load coupling effects, can be simulated and evaluated more accurately. This embodiment can adopt a multi-load decoupling model constructed based on a multi-load correlation analysis algorithm, a load contribution evaluation algorithm and a multi-load decoupling algorithm to obtain multi-load decoupling analysis results, thereby improving the test accuracy and reliability, and providing a scientific basis for building structure design and safety protection measures, effectively improving the safety of residents indoors.

[0055] In a second aspect, embodiments of the present application provide a residential indoor explosion multi-load decoupling test system, comprising: a test platform serving as a residential room; various types of sensors and image acquisition devices deployed around the test platform; and a processing device for executing any of the methods described in the first aspect. The processing device may be a data acquisition and synchronization control system.

[0056] Exemplarily, a residential indoor explosion multi-load decoupling test system includes a test platform, a gas distribution system, an ignition system, a concentration sensor, a temperature sensor, multiple pressure sensors, an image acquisition system, a building fragment velocity acquisition system, and a data acquisition and synchronization control system; the multiple pressure sensors include a wall pressure sensor and a free-field pressure sensor;

[0057] The test platform has two bedrooms, two living rooms, and one bathroom, a regular rectangular structure with a bedroom, kitchen, bathroom, and living room. The test platform is 14.15 meters long from east to west and 8.3 meters wide from north to south. The gas distribution system includes a combustible gas cylinder, an air cylinder, a circulating gas distribution instrument, a one-way valve, and a gas pipeline. The combustible gas cylinder and the air cylinder are connected to one end of the circulating gas distribution instrument via the gas pipeline. The other end of the circulating gas distribution instrument is connected to the one-way valve, and combustible gas is injected into the test platform through the gas pipeline.

[0058] The ignition system includes an igniter and an ignition rod. The igniter is an adjustable multifunctional igniter with adjustable ignition energy and ignition mode. The ignition rod is installed at the kitchen switch, the bottom of the appliance, the top of the kitchen, and the living room switch to restore the ignition position in the event of a gas explosion in a residential building.

[0059] The concentration sensor is mounted on a mounting rod located at the center of each indoor space and is used to monitor changes in the indoor natural gas and liquefied petroleum gas concentration distribution;

[0060] The temperature sensors are located at the center of each room and outside doors and windows to collect temperature changes of the flame during the explosion process.

[0061] The pressure sensors include free-field pressure sensors and wall pressure sensors. The free-field pressure sensors are located outside each door and window to collect outdoor overpressure changes to obtain the propagation path and intensity of the shock wave. The wall pressure sensors are located on the inside of the roof and walls to collect indoor overpressure changes to determine the extent of damage to the building structure.

[0062] The image acquisition system includes the following image acquisition devices: a high-speed camera, a global camera drone, and a motion camera; the high-speed camera is located outside the room; the global camera drone is located on the top of the room and hovers in a safe position directly above the room; the motion camera is located at the top of the corners of the living room and bedroom;

[0063] The building fragment velocity collection system includes a velocity measuring target paper and a high-speed camera; the velocity measuring target paper is set on the side of the indoor brick-concrete partition wall that may collapse, and is used to measure the velocity of indoor wall fragments; the high-speed camera is used to capture and calculate the velocity of outdoor glass fragments;

[0064] The data acquisition and synchronization control system includes a data acquisition instrument and a synchronization controller; the data acquisition instrument is used to store, record and analyze test data; the synchronization controller is used to coordinately control the residential indoor explosion multi-load decoupling test system. The purpose of the embodiment of the present application is to provide a residential indoor explosion multi-load decoupling test system to solve the problems of low test accuracy and poor reliability in existing methods. Specific purposes include: realizing explosion testing of full-scale residential indoor large spaces and comprehensively obtaining various physical parameters during the explosion process; and, decoupling analysis of multiple loads during the explosion process to provide a scientific basis for the prevention and control of explosion accidents, thereby improving the accuracy and reliability of the test method and reducing the test cost and risk.

[0065] Preferably, the total construction area of ​​the test platform is 117.445 m 2 The interior area is 100.125 m 2 , each room has a window.

[0066] Preferably, the concentration sensors are set to 15, with 3 concentration sensors installed on each mounting pole, for a total of 5 mounting poles; the concentration sensors are respectively arranged at a position corresponding to 0.5 m from the ground, a middle position and a position 0.1 m from the top, for real-time monitoring of changes in gas concentration in the vertical direction indoors (i.e., changes in the concentration of natural gas and liquefied petroleum gas), providing a basis for controlling explosion conditions; the concentration sensor has an accuracy of ≤±1% FS and has explosion-proof function.

[0067] Preferably, the temperature sensor can be of a certain model with a measuring range of 0~2300℃ and a response time of ≤2ms; the temperature sensor is 1.4 m from the ground and a total of 11 sensors are set to realize temperature monitoring of different areas.

[0068] Preferably, the free-field pressure sensor is a certain model of pressure sensor with a range of 0.001-200 MPa and a response frequency of 50-500 kHz; a total of 22 free-field pressure sensors are provided, 3 each are arranged outside the entrance door, kitchen, bathroom, and second bedroom window, 5 are arranged each outside the living room and master bedroom window, and the sensor spacing is 1 m.

[0069] Preferably, the wall pressure sensor is a specified type of pressure sensor with a measuring range of 0.001-20 MPa; there are 19 wall pressure sensors in total, of which one is arranged at the center of the top of the space, one is arranged at a height of 1.4 m next to the door and window, and one is arranged at a height of 2.1 m on the wall without windows.

[0070] Preferably, two high-speed cameras are set outside the room to record the explosion flame propagation speed and the building fragmentation speed.

[0071] Preferably, it also includes a common camera for recording the damage to the building before and after the explosion.

[0072] Through the collaborative work of the above systems, the embodiments of the present application can comprehensively and accurately obtain various physical parameters during the explosion process and perform decoupling analysis of multiple loads during the explosion process, providing a scientific basis for the prevention and control of explosion accidents. Furthermore, the embodiments of the present application adopt reasonable fixed installation and protective measures to reduce the risk and equipment damage rate during the test process, and improve the safety and sustainability of the test. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 A schematic diagram of the structure of a full-scale residential indoor large space testing platform provided in this embodiment;

[0074] Figure 2 A schematic diagram of the arrangement of a concentration sensor provided in this embodiment;

[0075] Figure 3 A schematic diagram of the arrangement of temperature sensors provided in this embodiment;

[0076] Figure 4 A schematic diagram of the arrangement of a free-field pressure sensor provided in this embodiment;

[0077] Figure 5 A schematic diagram of the arrangement of a wall pressure sensor provided in this embodiment;

[0078] Figure 6 A schematic diagram of the arrangement of an image acquisition device provided in this embodiment;

[0079] Figure 7 A schematic diagram of the layout of a building fragment velocity acquisition device provided in this embodiment;

[0080] Figure 8 A schematic diagram of the structure of a residential indoor explosion multi-load decoupling test system provided in an embodiment of the present application;

[0081] Figure 9 A flow chart of a method for testing multi-load decoupling of indoor explosions in residential areas provided in an embodiment of the present application.

[0082] Among them, 1-test platform; 2-speed measurement target paper; 3-wall pressure sensor; 4-igniter; 5-ignition rod; 6-synchronization controller; 7-data acquisition instrument; 8-concentration sensor; 9-temperature sensor; 10-free field pressure sensor; 11-infrared thermometer; 12-high-speed camera; 13-ordinary camera; 14-gas cylinder; 15-circulating gas distribution device; 16-one-way valve; 17-global camera drone; 18-motion camera. DETAILED DESCRIPTION

[0083] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the method scheme in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary method personnel in this field without making creative efforts are within the scope of protection of this application.

[0084] An embodiment of the present application provides a multi-load decoupling test system for indoor explosions in residential areas, comprising: a test platform serving as a residential room, various types of sensors and various types of image acquisition devices deployed around the test platform, and a processing device for executing a multi-load decoupling test method for indoor explosions in residential areas.

[0085] For example, Figure 8 As shown, an embodiment of the present application provides a multi-load decoupling test system for indoor explosions in residents, including: a test platform 1, a gas distribution system, an ignition system, a concentration sensor 8, a temperature sensor 9, a wall pressure sensor 3, a free-field pressure sensor 10, an image acquisition system, a building fragment velocity acquisition system, and a data acquisition and synchronization control system.

[0086] The test platform 1 is a typical full-size residential building with a regular rectangular structure. For example, it can be a two-bedroom, two-living room and one-bathroom building, with a bedroom, kitchen, bathroom, living room and other scenes. The interior is furnished with furniture such as tables, chairs, sofas, beds and electrical appliances, which truly restores the real indoor environment. Figure 1 As shown. For example, the test platform can be 14.15 meters long from east to west and 8.3 meters wide from north to south, with a total floor area of ​​117.445 square meters and an interior floor area of ​​100.125 square meters. This is the first full-scale experimental test platform for gas explosions in China, measuring at least 100 square meters for typical residential structures. In this embodiment, each room has a window to enable and record the gas explosion pressure relief process.

[0087] The gas distribution system is responsible for mixing combustible gas and air in a certain proportion and delivering them to the test platform 1 to simulate a gas leak. The gas distribution system includes components such as gas cylinders 14, a circulating gas distribution device 15, a one-way valve 16, and a gas pipeline. Gas cylinders 14 can include combustible gas cylinders or air cylinders.

[0088] The ignition system includes an igniter 4 and an ignition rod 5. The igniter 4 can adjust the ignition energy and ignition mode. The ignition rod 5 is arranged at typical locations that cause gas explosions, such as kitchen switches, the bottom of electrical appliances, the top of the kitchen, and the switch in the living room. It is used to restore the ignition location (or the location of the explosion source) of a gas explosion accident in a residential building.

[0089] For example, the concentration sensor 8 is mounted on a mounting rod, which is located at the center of each indoor space. Figure 2 As shown in the figure, 15 concentration sensors are installed, with three sensors mounted on each mounting pole, for a total of five mounting poles. These sensors are located at 0.5 m above the ground, in the middle, and 0.1 m from the top. They monitor vertical gas concentration changes in real time, providing a basis for controlling explosion conditions. The concentration sensors have an accuracy of ≤±1% FS and are explosion-proof.

[0090] The temperature sensors 9 are located at the center of each room and outside doors and windows. Figure 3 The temperature sensor is a certain model with a range of 0-2300°C and a response time of ≤2 ms. Eleven temperature sensors are located 1.4 m above the ground to monitor the temperature in different areas.

[0091] The pressure sensor includes a free-field pressure sensor 10 and a wall pressure sensor 3. The free-field pressure sensor is located outside each door and window and is a certain type of pressure sensor with a measuring range of 0.001-200 MPa and a response frequency of 50-500 kHz. Figure 4As shown in the figure, there are 22 sensors in total, 3 each outside the entrance door, kitchen, bathroom, and second bedroom window, and 5 each outside the living room and master bedroom window. The sensor spacing is 1 m. The wall pressure sensor is a specified type of pressure sensor with a range of 0.001-20 MPa; Figure 5 As shown, there are 19 in total, one at the center of the top of the space, one at a height of 1.4 m next to the door and window, and one at a height of 2.1 m on the wall without windows.

[0092] The image acquisition system includes a high-speed camera 12, a global camera drone 17, a motion camera 18 and a common camera 13, such as Figure 6 As shown in the figure, a high-speed camera is installed outside the room; a global camera drone is installed on the top of the room, hovering in a safe position directly above the room; action cameras are installed in the corners of the living room and bedroom; and ordinary cameras are used to record the damage to the building before and after the explosion.

[0093] The building debris speed acquisition system includes a speed measuring target paper 2 and a high-speed camera 12. Figure 7 The speed measuring target paper is placed on the side of the indoor brick-concrete partition wall that may collapse, and is used to measure the speed of indoor wall fragments; the high-speed camera is used to capture and calculate the speed of outdoor glass fragments.

[0094] Optionally, the building debris velocity acquisition system further includes an infrared thermometer 11, which can be used to measure and monitor temperature changes during and after the explosion.

[0095] The data acquisition and synchronization control system includes a synchronization controller 6 and a data acquisition instrument 7. The data acquisition instrument is used to store, record and analyze test data; the synchronization controller is used to coordinately control the indoor explosion multi-load decoupling test system for residents.

[0096] Through the collaborative work of the above-mentioned systems, the present application can comprehensively and accurately obtain various physical parameters during the explosion process, and perform decoupling analysis on multiple loads during the explosion process, providing a scientific basis for the prevention and control of explosion accidents. At the same time, the present application adopts reasonable fixed installation and protective measures to reduce the risk and equipment damage rate during the test process, and improve the safety and sustainability of the test. Through the testing method of the present application, the explosion effects in large indoor space environments of residents can be more accurately simulated and evaluated, providing a scientific basis for building structure design, prevention and control of explosion accidents, and effectively improving the safety of residents indoors.

[0097] Figure 9 This is a flow chart of a method for testing multi-load decoupling of indoor explosions in a residential building provided by an embodiment of the present application. Figure 9 As shown, the method includes:

[0098] S91. Obtain original sensor data collected by various types of sensors in the residential indoor explosion multi-load decoupling test system and original image data collected by various types of image acquisition devices.

[0099] Raw sensor data refers to unprocessed data collected by various sensors (such as pressure sensors and temperature sensors) in the residential indoor explosion multi-load decoupling test system. Raw image data refers to unprocessed image or video data collected by various image acquisition devices (such as high-speed cameras and standard cameras) in the residential indoor explosion multi-load decoupling test system.

[0100] S92. Based on the original sensor data and the original image data, use multiple single load algorithms to analyze different loads to obtain multiple single load analysis results.

[0101] Among them, the single load algorithm is used to analyze a single type of load (such as pressure, temperature, etc.). By analyzing a single type of load, the characteristics and effects of the load are extracted.

[0102] S93. All single load analysis results are integrated into an explosion effect data set, and the explosion effect data set is processed using a multi-load decoupling model to obtain a multi-load decoupling analysis result; the multi-load decoupling model is constructed using a multi-load correlation analysis algorithm, a load contribution evaluation algorithm, and a multi-load decoupling algorithm.

[0103] The explosion effect dataset is a comprehensive dataset formed by integrating all single-load analysis results. The multi-load decoupling model is used to process and analyze multi-load data, decomposing complex multi-load effects into multiple independent load effects. The multi-load correlation analysis algorithm is used to construct a load correlation matrix, revealing the correlations between different loads. The load contribution evaluation algorithm is used to construct a load contribution matrix, quantifying the impact of each load. The multi-load decoupling analysis results include the effects of each independent load and time-varying curves.

[0104] S94. Compare the actual explosion test results with the multi-load decoupling analysis results, and determine the explosion multi-load decoupling effect based on the comparison results.

[0105] Among them, the actual explosion test results are data and observations obtained through actual explosion tests, which are used to compare with the multi-load decoupling analysis results to verify the accuracy of the multi-load decoupling model.

[0106] In this embodiment, different types of data are obtained through a variety of sensors and image acquisition devices, which helps to fully understand the explosion process. By analyzing each load separately through a single load algorithm, the characteristics and effects of each load can be extracted more finely. All single load analysis results are integrated into a comprehensive data set to facilitate comprehensive integrated analysis. Through the multi-load decoupling model, complex multi-load effects are decomposed into multiple independent load effects, improving the clarity and accuracy of the analysis. Therefore, this embodiment can more clearly identify and analyze the effects of each load by decomposing the complex multi-load effects into multiple independent load effects, improve the accuracy of the decoupling analysis, and thus improve the accuracy and reliability of the test.

[0107] In some embodiments, S92, based on the raw sensor data and the raw image data, multiple single load algorithms are used to perform analysis of different loads to obtain multiple single load analysis results, including:

[0108] Step 921: Preprocess the free-field pressure sensor data, temperature sensor data, fragment image data captured by a high-speed camera, velocity target data, wall pressure sensor data, concentration sensor data, flame image data recorded by a high-speed camera, building image data captured by a standard camera, bird's-eye view video data captured by a global camera drone, and local video data captured by a motion camera. Step 922: Process the preprocessed free-field pressure sensor data using a shock wave propagation model algorithm to construct a shock wave propagation model and determine the propagation path and intensity of the shock wave. Step 923: Process the preprocessed temperature sensor data using a thermal radiation transfer algorithm to construct a thermal radiation transfer model and determine the flame temperature changes, flame temperature distribution, and thermal radiation impact range during the explosion. Step 924: Process the preprocessed fragment image data and preprocessed velocity target data using a fragment dynamics algorithm to calculate the velocity and trajectory of glass fragments from indoor walls and outdoor windows, thereby determining the motion patterns of the fragments. Step 925: Process the preprocessed wall pressure sensor data using a structural dynamic response algorithm to assess the dynamic response of the building structure under blast loads and determine the extent of damage. Step 926: Process the preprocessed concentration sensor data using a gas concentration distribution algorithm to analyze changes in the indoor natural gas and liquefied petroleum gas concentration distribution and determine the gas leakage situation before the explosion. Step 927: Process the preprocessed flame image data using a flame propagation velocity algorithm to analyze the flame propagation path and velocity and determine the flame's impact on different areas. Step 928: Process the preprocessed building image data using a building damage pattern recognition algorithm to identify building damage patterns. Step 929: Process the preprocessed overhead video data using a global perspective analysis algorithm to analyze the explosion impact range and explosion pattern. Step 930: Process the preprocessed local video data using a local detail analysis algorithm to analyze the explosion impact and damage details in key areas.

[0109] This embodiment pre-processes and performs special analysis on free-field pressure sensor data, temperature sensor data, fragment image data collected by high-speed cameras, speed target paper data, wall pressure sensor data, concentration sensor data, flame image data recorded by high-speed cameras, building image data collected by ordinary cameras, overhead video data taken by global camera drones, and local video data taken by motion cameras, so as to comprehensively and meticulously extract the characteristics and effects of each load. This not only improves the accuracy and reliability of the data, but also provides a solid foundation for subsequent multi-load decoupling analysis. Specifically, these steps can construct a shock wave propagation model, establish a thermal radiation transmission model, calculate the motion law of fragments, evaluate the dynamic response of building structures, analyze gas concentration distribution, study flame propagation speed, identify building damage modes, analyze the scope and mode of explosion impact, and analyze the explosion impact and damage details in key areas, thereby comprehensively improving the accuracy and reliability of explosion multi-load decoupling testing.

[0110] In some embodiments, in S93, a multi-load decoupling model is used to process the explosion effect dataset to obtain a multi-load decoupling analysis result; the multi-load decoupling model is constructed using a multi-load correlation analysis algorithm, a load contribution evaluation algorithm, and a multi-load decoupling algorithm, including:

[0111] Step 931: Use a multi-load correlation analysis algorithm to perform correlation analysis on the explosion effect data set to obtain a load correlation matrix.

[0112] Step 932: Use a load contribution evaluation algorithm to evaluate the load correlation matrix to obtain a load contribution matrix.

[0113] Step 933: Use a multi-load decoupling algorithm to process the load contribution matrix to obtain a decoupling effect matrix; wherein the multi-load decoupling algorithm performs different decoupling analyses on different sub-areas based on the location of the explosion source and the explosion impact range.

[0114] Step 934: Use a time series analysis algorithm to analyze the decoupling effect matrix to obtain a multi-load decoupling analysis result.

[0115] As can be seen from the above process, this embodiment utilizes a multi-load correlation analysis algorithm, a load contribution assessment algorithm, and a multi-load decoupling algorithm to perform layer-by-layer analysis and processing of the explosion effect dataset. This method comprehensively reveals the correlations between different loads, quantifies the contribution of each load, and decomposes complex multi-load effects into multiple independent load effects. In particular, the multi-load decoupling algorithm performs differentiated decoupling analysis on different sub-regions based on the location and impact range of the explosion source, further improving the accuracy and reliability of the decoupling results. Finally, the decoupling effect matrix is ​​analyzed using a time series analysis algorithm to obtain detailed multi-load decoupling analysis results.

[0116] In the above embodiment, the design of the multi-load decoupling algorithm has a significant impact on improving test accuracy. Therefore, this embodiment specifically describes the design of the multi-load decoupling algorithm. Exemplarily, step 933 uses the multi-load decoupling algorithm to process the load contribution matrix to obtain a decoupling effect matrix, including:

[0117] Step a1: Determine the location of the explosion source and the explosion impact range based on the original sensor data and the original image data, and divide the indoor area of ​​the residents into multiple sub-areas based on the location of the explosion source and the explosion impact range; the multiple sub-areas include first-level sub-areas and second-level sub-areas; the second level is lower than the first level, and the explosion source is in the first-level sub-area.

[0118] Step a2: Split the load contribution matrix into the load contribution matrix of each sub-region according to the sub-region.

[0119] Step a3: preprocess the load contribution matrix of each sub-region to obtain the preprocessed load contribution matrix of each sub-region.

[0120] Step a4: For each sub-region, a feature extraction method is used to extract features from the pre-processed load contribution matrix to obtain a feature matrix.

[0121] Step a5: perform decoupling analysis on the feature matrices of sub-regions of different levels using different decoupling analysis methods to obtain a decoupling intermediate matrix for each sub-region.

[0122] Step a6: construct an explosion effect knowledge graph, and use the domain knowledge in the explosion effect knowledge graph to adjust the decoupling intermediate matrix of each sub-region respectively to obtain the adjusted decoupling intermediate matrix of each sub-region.

[0123] Step a7: performing effect separation on the adjusted decoupling intermediate matrix of each sub-region to obtain a decoupling separation matrix for each region, and concatenating the decoupling separation matrices of all regions to obtain a decoupling effect matrix.

[0124] As can be seen from the above description, this embodiment determines the location and impact range of the explosion source based on raw sensor data and image data, and divides the indoor area of ​​residents into sub-areas of different levels, allowing for targeted and detailed decoupling analysis of each sub-area. Specifically, by preprocessing, feature extraction, and processing the load contribution matrix of each sub-area using different decoupling analysis methods, and combining it with the domain knowledge in the explosion effect knowledge graph for adjustment, precise decoupling of each sub-area is ultimately achieved. This method not only improves the accuracy and reliability of the decoupling results, but also enables detailed analysis of the explosion effects of each sub-area, improving the accuracy and reliability of the explosion multi-load decoupling test.

[0125] In the above embodiment, step a1, determining the explosion source location and explosion impact range based on raw sensor data and raw image data, includes: step a11, performing time difference positioning processing on the raw sensor data using a sensor data positioning algorithm to obtain a first explosion source location; step a12, performing video analysis, image segmentation, feature extraction, and target tracking on the raw image data using an image analysis algorithm to obtain a second explosion source location; step a13, performing simulation analysis on a three-dimensional indoor model of a residential building using a numerical simulation method to obtain a third explosion source location and an initial impact range to be adjusted; and step a14, adjusting the third explosion source location and initial impact range based on the first and second explosion source locations to obtain the explosion source location and explosion impact range.

[0126] This example employs a sensor data positioning algorithm, an image analysis algorithm, and numerical simulation methods to determine the explosion source's location and initial impact range from multiple perspectives, including time-difference positioning, video analysis, and simulation analysis. Preliminary results from these multiple methods are comprehensively adjusted to ultimately determine the precise explosion source location and impact range. This approach not only improves positioning accuracy and reliability but also provides more comprehensive and detailed information in complex environments, supporting subsequent multi-load decoupling analysis and explosion effect assessment.

[0127] In the above embodiment, step a3, preprocessing the load contribution matrix of each sub-region to obtain the preprocessed load contribution matrix of each sub-region, includes: step a31, using a data cleaning algorithm to remove noise and outliers from the load contribution matrix of each sub-region to obtain cleaned data;

[0128] Step a32: Use a standardization algorithm to standardize the cleaned data to make the scales of different features consistent, thereby obtaining standardized data; Step a33: Use a missing value filling algorithm to fill in the missing values ​​of the standardized data, thereby obtaining the preprocessed load contribution matrix of each sub-region.

[0129] Therefore, this embodiment significantly improves the quality and consistency of the load contribution matrix for each subregion by using a data cleaning algorithm to remove noise and outliers, a normalization algorithm to align the scales of different features, and a missing value filling algorithm to handle missing data. This not only ensures the accuracy and reliability of subsequent analysis but also provides a clean, complete, and standardized data foundation for multi-load decoupling analysis, thereby enhancing the effectiveness and credibility of the entire decoupling process.

[0130] In the above embodiment, in step a4, a feature extraction method is used to extract features from the preprocessed load contribution matrix to obtain a feature matrix, including:

[0131] Step a41: Use a feature selection algorithm to perform feature selection processing on the preprocessed load contribution matrix to obtain a feature parameter list; step a42: Use a feature extraction algorithm to extract selected feature parameters from the feature parameter list to obtain a parameter matrix; step a43: Use a feature normalization algorithm to normalize all feature parameters in the parameter matrix to generate a feature matrix.

[0132] This embodiment uses a feature selection algorithm to screen out important feature parameters, uses a feature extraction algorithm to extract selected feature parameters, and uses a feature normalization algorithm to normalize the feature parameters. This can significantly improve the quality and representativeness of the feature matrix, reduce data redundancy and noise, and ensure the comparability and consistency between different features. It provides efficient, accurate, and reliable feature data for subsequent multi-load decoupling analysis, thereby improving the effectiveness and credibility of the entire analysis process.

[0133] In the above embodiment, step a5, performing decoupling analysis on the feature matrices of sub-regions of different levels using different decoupling analysis methods to obtain a decoupling intermediate matrix for each sub-region, includes:

[0134] Step a51: Use the principal component regression algorithm to perform regression analysis on the characteristic matrix of the first-level sub-region to obtain a first principal component regression result, use the neural network model to perform decoupling analysis on the characteristic matrix of the first-level sub-region to obtain a first neural network decoupling result, use the ensemble learning method to perform ensemble learning processing on the characteristic matrix of the first-level sub-region to obtain a first ensemble learning decoupling result; use the partial least squares regression algorithm to perform regression analysis on the characteristic matrix of the first-level sub-region to obtain a first partial least squares regression result; take the weighted average of the first principal component regression result, the first neural network decoupling result, the first ensemble learning decoupling result, and the first partial least squares regression result to obtain a decoupled intermediate matrix of the first-level sub-region.

[0135] Optionally, the principal component regression algorithm can be sparse principal component analysis. The neural network model includes an attention mechanism and a base model, wherein:

[0136] ;

[0137] ;

[0138] ;

[0139] Among them, A is the attention weight matrix, which represents the degree of attention of each query vector to each key vector. is a check vector, which can refer to the features extracted from the feature matrix of the first-level sub-region, is the key vector, which is also the feature extracted from the feature matrix of the first-level sub-region; represents the transpose of K; is the dimension of the key vector, It is the square root of the dimension of the key vector, which is used to scale the dot product result to prevent the gradient from disappearing or exploding; is a vector of values, usually the feature representation in the feature matrix of the first-level subregion. is the decoupling result of the first neural network, Output results for attention; Output results for the basic model; The weight coefficient of the attention output is used to balance the contributions of the attention mechanism and the underlying model, and can be adjusted based on actual conditions. The attention mechanism allows neural network models to more flexibly capture the important parts of input features when processing complex data, thereby improving the quality of feature representation.

[0140] Step a52: Use the principal component regression algorithm to perform regression analysis on the characteristic matrix of the second-level sub-region to obtain a second principal component regression result, and use the partial least squares regression algorithm to perform regression analysis on the characteristic matrix of the second-level sub-region to obtain a second partial least squares regression result; take the weighted average of the first principal component regression result and the second partial least squares regression result to obtain a decoupled intermediate matrix of the second-level sub-region.

[0141] This example uses a variety of algorithms, including principal component regression, neural networks, ensemble learning, and partial least squares regression, to perform detailed decoupling analysis on sub-regions of different levels. The weighted average of these multiple results significantly improves the accuracy and reliability of the decoupling results. This approach not only leverages the strengths of different algorithms and mitigates the limitations of a single algorithm, but also enables differentiated analysis strategies for sub-regions of different levels, providing more comprehensive and detailed data support for multi-load decoupling analysis and enhancing the effectiveness and reliability of the entire decoupling process.

[0142] In the above embodiment, step a6, constructing an explosion effect knowledge graph and adjusting the decoupling intermediate matrix of each sub-region using the domain knowledge in the explosion effect knowledge graph to obtain the adjusted decoupling intermediate matrix of each sub-region, includes: step a61, constructing the explosion effect knowledge graph using a knowledge graph construction algorithm; step a62, fusing the domain knowledge in the explosion effect knowledge graph with the decoupling intermediate results of each sub-region using a knowledge fusion algorithm to obtain the fused decoupling intermediate matrix of each sub-region; and step a63, correcting the fused decoupling intermediate matrix of each sub-region using a result correction algorithm, combining historical data and prior knowledge in the explosion effect knowledge graph to obtain the adjusted decoupling intermediate matrix of each sub-region.

[0143] This example significantly improves the accuracy and reliability of decoupling results by constructing a knowledge graph of explosion effects and employing a knowledge fusion algorithm to integrate domain knowledge with intermediate decoupling results. This approach, combined with historical data and prior knowledge, uses a result correction algorithm to perform correction processing. This approach not only fully leverages domain knowledge and historical data, enhancing the interpretability and credibility of the model, but also effectively corrects potential errors, providing more scientific and accurate data support for multi-load decoupling analysis and improving the effectiveness of the entire decoupling process.

[0144] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 9 The embodiment shown is a method for testing indoor explosion multiple loads decoupling in residential areas.

[0145] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0146] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0147] Through the description of the above embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored on a computer-readable storage medium, such as a magnetic disk or optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for decoupling multi-load test of indoor explosion in residential areas, characterized in that: include: Obtaining raw sensor data collected by various types of sensors in the residential indoor explosion multi-load decoupling test system and raw image data collected by various types of image acquisition devices; Based on the original sensor data and the original image data, using multiple single load algorithms to perform analysis of different loads to obtain multiple single load analysis results; Integrating all single load analysis results into an explosion effect data set, and processing the explosion effect data set using a multi-load decoupling model to obtain a multi-load decoupling analysis result; The multi-load decoupling model is constructed by using a multi-load correlation analysis algorithm, a load contribution evaluation algorithm and a multi-load decoupling algorithm; Comparing the actual explosion test results with the multi-load decoupling analysis results, and determining the explosion multi-load decoupling effect based on the comparison results; The explosion effect data set is processed using a multi-load decoupling model to obtain a multi-load decoupling analysis result; The multi-load decoupling model is constructed using a multi-load correlation analysis algorithm, a load contribution evaluation algorithm, and a multi-load decoupling algorithm, including: A multi-load correlation analysis algorithm is used to perform correlation analysis on the explosion effect data set to obtain a load correlation matrix; The load contribution evaluation algorithm is used to evaluate the load correlation matrix to obtain a load contribution matrix; The load contribution matrix is ​​processed using a multi-load decoupling algorithm to obtain a decoupling effect matrix; wherein the multi-load decoupling algorithm performs different decoupling analyses on different sub-areas based on the location of the explosion source and the explosion impact range; The time series analysis algorithm is used to analyze the decoupling effect matrix and obtain the multi-load decoupling analysis results.

2. A method for testing indoor explosion multi-load decoupling in residential buildings according to claim 1, characterized in that: The multi-load decoupling algorithm is used to process the load contribution matrix to obtain a decoupling effect matrix, including: Determining the location of the explosion source and the explosion impact range based on the raw sensor data and the raw image data, and dividing the indoor area of ​​the residents into a plurality of sub-areas based on the location of the explosion source and the explosion impact range; the plurality of sub-areas include sub-areas of a first level and sub-areas of a second level; the second level is lower than the first level, and the explosion source is located in the sub-area of ​​the first level; Splitting the load contribution matrix into load contribution matrices of each sub-region according to the sub-region; Preprocessing the load contribution matrix of each sub-region to obtain a preprocessed load contribution matrix of each sub-region; For each sub-region, a feature extraction method is used to extract features from the pre-processed load contribution matrix to obtain a feature matrix; Different decoupling analysis methods are used to perform decoupling analysis on the characteristic matrices of sub-regions at different levels to obtain the decoupling intermediate matrix of each sub-region; Constructing an explosion effect knowledge graph, and using domain knowledge in the explosion effect knowledge graph to adjust the decoupling intermediate matrix of each sub-region respectively, to obtain an adjusted decoupling intermediate matrix of each sub-region; Effect separation is performed on the adjusted decoupling intermediate matrix of each sub-region to obtain a decoupling separation matrix for each region, and the decoupling separation matrices of all regions are spliced ​​to obtain a decoupling effect matrix.

3. A method for testing indoor explosion multi-load decoupling of a residential building according to claim 2, characterized in that: The decoupling analysis is performed on the characteristic matrices of sub-regions of different levels using different decoupling analysis methods to obtain a decoupling intermediate matrix for each sub-region, including: Performing regression analysis on the feature matrix of the first-level sub-region using a principal component regression algorithm to obtain a first principal component regression result, performing decoupling analysis on the feature matrix of the first-level sub-region using a neural network model to obtain a first neural network decoupling result, performing ensemble learning processing on the feature matrix of the first-level sub-region using an ensemble learning method to obtain a first ensemble learning decoupling result; performing regression analysis on the feature matrix of the first-level sub-region using a partial least squares regression algorithm to obtain a first partial least squares regression result; taking a weighted average of the first principal component regression result, the first neural network decoupling result, the first ensemble learning decoupling result, and the first partial least squares regression result to obtain a decoupled intermediate matrix of the first-level sub-region; The principal component regression algorithm is used to perform regression analysis on the characteristic matrix of the second-level sub-region to obtain a second principal component regression result, and the partial least squares regression algorithm is used to perform regression analysis on the characteristic matrix of the second-level sub-region to obtain a second partial least squares regression result; the first principal component regression result and the second partial least squares regression result are weighted and averaged to obtain a decoupled intermediate matrix of the second-level sub-region.

4. A method for testing indoor explosion multi-load decoupling in residential buildings according to claim 2, characterized in that: Determining the location of the explosion source and the explosion impact range based on the original sensor data and the original image data includes: Performing time difference positioning processing on the raw sensor data using a sensor data positioning algorithm to obtain the first explosion source position; Using an image analysis algorithm to perform video analysis, image segmentation, feature extraction, and target tracking on the original image data to obtain the location of the second explosion source; The numerical simulation method is used to simulate and analyze the three-dimensional model of the residential interior to obtain the location of the third explosion source and the initial impact range to be adjusted; Based on the first explosion source position and the second explosion source position, the third explosion source position and the initial impact range are adjusted to obtain the explosion source position and the explosion impact range.

5. The method for testing indoor explosion multi-load decoupling of a residential building according to claim 2, characterized in that: The preprocessing of the load contribution matrix of each sub-region to obtain the preprocessed load contribution matrix of each sub-region includes: The data cleaning algorithm is used to remove noise and outliers from the load contribution matrix of each sub-area to obtain cleaned data; Standardizing the cleaned data using a standardization algorithm to make the scales of different features consistent, thereby obtaining standardized data; A missing value filling algorithm is used to fill in the missing values ​​of the standardized data to obtain a preprocessed load contribution matrix for each sub-region.

6. A method for testing indoor explosion multi-load decoupling of a residential building according to claim 2, characterized in that: The feature extraction method is used to extract features from the preprocessed load contribution matrix to obtain a feature matrix, including: Using a feature selection algorithm to perform feature selection processing on the preprocessed load contribution matrix to obtain a feature parameter list; extracting selected feature parameters from the feature parameter list using a feature extraction algorithm to obtain a parameter matrix; A feature normalization algorithm is used to normalize all feature parameters in the parameter matrix to generate a feature matrix.

7. The method for testing indoor explosion multi-load decoupling in a residential building according to claim 2, characterized in that: The step of constructing the explosion effect knowledge graph and adjusting the decoupling intermediate matrix of each sub-region using the domain knowledge in the explosion effect knowledge graph to obtain the adjusted decoupling intermediate matrix of each sub-region includes: Use the knowledge graph construction algorithm to build the explosion effect knowledge graph; The knowledge fusion algorithm is used to fuse the domain knowledge in the explosion effect knowledge graph with the decoupling intermediate results of each sub-region to obtain the fused decoupling intermediate matrix of each sub-region. The result correction algorithm is used to correct the decoupling intermediate matrix after fusion of each sub-region in combination with the historical data and prior knowledge in the explosion effect knowledge graph to obtain the adjusted decoupling intermediate matrix of each sub-region.

8. The method for testing indoor explosion multi-load decoupling in a residential building according to claim 1, characterized in that: Based on the raw sensor data and the raw image data, multiple single load algorithms are used to perform analysis of different loads to obtain multiple single load analysis results, including: The free-field pressure sensor data, temperature sensor data, fragment image data collected by high-speed cameras, velocity target paper data, wall pressure sensor data, concentration sensor data, flame image data recorded by high-speed cameras, building image data collected by ordinary cameras, bird's-eye view video data taken by global camera drones, and local video data taken by motion cameras are preprocessed separately; The pre-processed free-field pressure sensor data is processed using a shock wave propagation model algorithm to construct a shock wave propagation model and obtain the propagation path and intensity of the shock wave. The pre-processed temperature sensor data is processed using a thermal radiation transfer algorithm to establish a thermal radiation transfer model to obtain the flame temperature change, flame temperature distribution, and thermal radiation impact range during the explosion process. The fragment dynamics algorithm is used to process the pre-processed fragment image data and the pre-processed velocity target paper data to calculate the speed and trajectory of indoor wall glass fragments and outdoor glass fragments, and obtain the movement law of the fragments; The pre-processed wall pressure sensor data is processed using a structural dynamic response algorithm to evaluate the dynamic response of the building structure under blast loads and determine the extent of damage to the building structure. The gas concentration distribution algorithm is used to process the pre-processed concentration sensor data to analyze the changes in the indoor natural gas and liquefied petroleum gas concentration distribution and obtain the gas leakage situation before the explosion; The flame propagation velocity algorithm is used to process the pre-processed flame image data to analyze the flame propagation path and velocity and obtain the flame's impact on different areas; The building damage pattern recognition algorithm is used to process the pre-processed building image data to identify the building damage pattern; The pre-processed overhead video data is processed using a global perspective analysis algorithm to analyze the explosion impact range and explosion mode; The pre-processed local video data is processed using a local detail analysis algorithm to analyze the explosion impact and damage details in key areas.

9. A residential indoor explosion multi-load decoupling test system, characterized in that: include: A test platform for a residential room, various types of sensors and image acquisition devices deployed around the test platform, and processing equipment for executing a multi-load decoupling test method for explosions in residential rooms as described in any one of claims 1 to 8.

Images