Heavy truck battery changing cabinet structure reliability monitoring method, device, equipment and medium

Abstract

The invention provides a method, a device, equipment and a medium for monitoring the reliability of a heavy truck battery changing cabinet structure, and relates to the technical field of battery changing cabinet structure monitoring. The method adopts a digital twinning technology to fuse physical entity data and virtual entity data, and collects physical data such as stress and displacement of a battery changing cabinet in real time through a sensor; and virtual data are generated by using a Tricksim dynamic model and a finite element model. The data jointly form a twin data set, and real-time monitoring of the reliability of the battery changing cabinet structure is achieved through deep neural network (DNN) model analysis. When a monitored stress or fatigue accumulated damage value exceeds a safety threshold value, the system automatically triggers early warning to remind an operator to handle in time. According to the method, the monitoring precision and the real-time performance are improved, more comprehensive monitoring and early warning functions are realized through virtual entity modeling and a deep learning method, the use safety of the battery replacement vehicle is effectively guaranteed, and the method has important practical application value.

Description

Technical Field

[0001] The present invention relates to the technical field of battery swap cabinet structure monitoring, and in particular to a method, device, equipment and medium for monitoring the structural reliability of a battery swap cabinet for a heavy truck. Background Art

[0002] In the modern transportation industry, heavy trucks (heavy trucks) play an indispensable role. With the enhancement of environmental awareness and the continuous advancement of new energy technologies, the battery swap mode has gradually attracted attention as an efficient and convenient way of energy replenishment. As a key device for realizing the battery swap function, the reliability of the structure of the battery swap cabinet is crucial to ensuring the safety and stability of the battery swap process. In actual applications, the battery swap cabinet faces complex working conditions challenges. It needs to be installed on different vehicles and adapt to various driving scenarios, including different loads, speeds, road conditions, etc. In this complex and changeable alternating load environment for a long time, the structure of the battery swap cabinet may gradually suffer fatigue damage, and may even cause structural failure, thereby affecting the normal operation of the battery swap vehicle and posing a safety hazard.

[0003] At present, the means of monitoring the structural reliability of the power exchange cabinet are relatively limited. Traditional monitoring methods mainly rely on mechanical sensors, which can only provide information on the stress state of the structure at a certain moment, and it is difficult to accurately predict the potential safety risks of the structure, such as fatigue cumulative damage. In addition, although there are some early warning systems in the existing technology that can monitor and transmit some basic information of the power exchange cabinet, there is still a gap in the comprehensive monitoring and early warning functions of the structural reliability.

[0004] In this technical context, it is particularly urgent to develop a system that can monitor the structural reliability of the battery swap cabinet in real time and accurately, and can warn of potential risks in advance. This will not only help improve the operating safety of battery swap vehicles, but also optimize the maintenance strategy of the battery swap cabinet, extend its service life, and reduce operating costs.

[0005] In view of this, this application is filed. Summary of the invention

[0006] The present invention provides a method, device, equipment and medium for monitoring the structural reliability of a heavy truck battery exchange cabinet, which can at least partially improve the above-mentioned problems.

[0007] To achieve the above object, the present invention adopts the following technical solutions: A method for monitoring the structural reliability of a heavy truck power exchange cabinet, comprising: Acquire a physical data set collected by a sensor component configured on a heavy truck and a battery swap cabinet thereof, and establish a virtual entity corresponding to the heavy truck based on the physical data set; Acquire a virtual data set of the virtual entity, and fuse the virtual data set with the physical data set based on digital twin technology to generate a simulation data set; The simulation data set is calculated using a preset DNN model to generate a maximum stress prediction value of the risk point and a fatigue characteristic prediction value of the battery swap cabinet; The predicted value of the maximum stress of the risk point and the predicted value of the fatigue characteristics of the battery swap cabinet are subjected to early warning preprocessing, and early warning prompts are given or predicted values ​​are output.

[0008] The present invention also provides a heavy truck battery exchange cabinet structure reliability monitoring device, which includes: A virtual entity establishment unit, used to obtain a physical data set collected by a sensor component configured on a heavy truck and a battery exchange cabinet thereof, and establish a virtual entity corresponding to the heavy truck based on the physical data set; A fusion unit, used to obtain a virtual data set of the virtual entity, and fuse the virtual data set with the physical data set based on the digital twin technology to generate a simulation data set; A DNN unit, used to calculate the simulation data set using a preset DNN model to generate a maximum stress prediction value of a risk point and a fatigue characteristic prediction value of a battery swap cabinet; The early warning unit is used to perform early warning preprocessing on the maximum stress prediction value of the risk point and the fatigue characteristic prediction value of the battery swap cabinet, and to provide early warning prompts or output prediction values.

[0009] The present invention also provides a heavy-duty truck battery swap cabinet structure reliability monitoring device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the heavy-duty truck battery swap cabinet structure reliability monitoring method as described in any one of the above.

[0010] The present invention also provides a readable storage medium storing a computer program, wherein the computer program can be executed by a processor of a device where the storage medium is located to implement a method for monitoring the structural reliability of a heavy-duty truck battery exchange cabinet as described in any one of the above items.

[0011] In summary, the structural reliability monitoring method of the heavy truck battery swap cabinet adopts digital twin technology to construct a comprehensive mapping of the physical entity and virtual entity of the battery swap cabinet. By installing a variety of sensors on the heavy truck and the battery swap cabinet, physical data such as stress, mass, speed, acceleration and displacement are collected in real time, and virtual data is generated using the Trucksim dynamic model and the finite element model. These physical data are fused with the virtual data to form a twin data set, and the data is trained and learned through the deep neural network (DNN) model to achieve real-time monitoring of the structural reliability of the battery swap cabinet. When the stress of the battery swap cabinet is monitored to exceed the safety threshold or the fatigue cumulative damage value is higher than the set standard, the system will trigger the early warning mechanism and prompt the operator through a voice alarm so that timely measures can be taken. In addition, the system also predicts the fatigue characteristics of the battery swap cabinet through the rain flow counting method and Miner cumulative damage theory, further improving the accuracy and reliability of monitoring.

[0012] The heavy-duty truck battery swap cabinet structure reliability monitoring method not only improves the accuracy and real-time performance of the battery swap cabinet structure reliability monitoring, but also realizes more comprehensive monitoring and early warning functions through virtual entity modeling and deep learning methods, effectively ensuring the safe use of battery swap vehicles. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a flow chart of a method for monitoring the structural reliability of a heavy truck power exchange cabinet provided by the first embodiment of the present invention; Figure 2 It is a schematic diagram of the framework structure of the heavy truck battery swap cabinet structure reliability monitoring method provided by the first embodiment of the present invention; Figure 3 It is a schematic diagram of the basic process of constructing a DNN model provided by an embodiment of the present invention; Figure 4 is a schematic diagram of a DNN model provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of the stress monitoring and early warning process of the risk points of the power exchange cabinet structure provided by an embodiment of the present invention; Figure 6 It is a schematic diagram of the fatigue characteristic monitoring and early warning process of the power exchange cabinet provided by an embodiment of the present invention; Figure 7 It is a module diagram of a heavy truck battery exchange cabinet structure reliability monitoring device provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0015] refer to Figure 1, Figure 2 As shown, the first embodiment of the present invention discloses a method for monitoring the structural reliability of a heavy-duty truck power-swap cabinet, which can be executed by a heavy-duty truck power-swap cabinet structural reliability monitoring device (hereinafter referred to as the monitoring device), and in particular, executed by one or more processors in the monitoring device to implement the following method: S1, obtaining a physical data set collected by a sensor component configured on a heavy truck and a battery swap cabinet thereof, and establishing a virtual entity corresponding to the heavy truck based on the physical data set; Specifically, step S1 includes: obtaining a physical data set collected by a sensor assembly configured on a heavy truck and a battery swap cabinet in a focus area thereof, wherein the physical data set includes stress, mass, velocity, acceleration, and displacement; According to the physical data set, different heavy truck models are built using Trucksim dynamics software, and different road conditions are selected to solve vehicle dynamics parameters to generate a heavy truck Trucksim dynamics model; Based on the geometric model of the power swap cabinet, the finite element model of the power swap cabinet was established using the finite element software Altair HyperWorks; The heavy-duty truck Trucksim dynamic model and the battery swap cabinet finite element model are fused to generate a virtual entity corresponding to the heavy-duty truck, wherein the output of the heavy-duty truck Trucksim dynamic model is introduced into the battery swap cabinet finite element model to combine the dynamic equations of the battery swap cabinet with the physical characteristics of the internal structure.

[0016] Preferably, the sensor assembly includes a resistive strain sensor, a mass sensor, a velocity sensor, an acceleration sensor, and a displacement sensor.

[0017] In this embodiment, a physical data set collected by sensor components configured on heavy trucks and their battery swap cabinets is obtained. These sensor components include resistive strain sensors, mass sensors, velocity sensors, acceleration sensors, and displacement sensors, which are carefully arranged in the areas of interest of heavy trucks and their battery swap cabinets to monitor key parameters such as stress, mass, velocity, acceleration, and displacement of the battery swap cabinets in real time. The collection of these physical data provides a basis for the subsequent establishment of virtual entities, ensuring the comprehensiveness and accuracy of the monitoring data.

[0018] In principle, the stress data sample points collected by the simulation model include but are not limited to the sample points collected by the real vehicle (including the battery swap cabinet). Therefore, the stress data collected by the real vehicle can be used to verify the simulation model to ensure the mapping of mechanical properties between the simulation model and the real vehicle model. In addition, virtual simulation can also be used to present mechanical characteristics that cannot be involved in physical collection data. The categories of sensor components are shown in Table 1.

[0019] Table 1 Sensor categories and their functions

[0020] Since the driving conditions in the working environment of heavy trucks are relatively complex, different changes in working conditions will affect the operating status of the battery swap cabinet. First, various sensors installed on heavy trucks and battery swap cabinets are used to obtain data in real time, and then the data collected under different working conditions are associated with the operating status. The working conditions that may be involved are shown in Table 2.

[0021] Table 2 Heavy truck and battery swap cabinet driving conditions

[0022] Secondly, based on the collected physical data set, different heavy-duty truck models are built using Trucksim dynamics software. When building the model, different road conditions, such as flat roads and rugged roads, are selected to simulate the dynamic behavior of heavy-duty trucks in various actual driving scenarios. By solving the vehicle dynamics parameters, a heavy-duty truck Trucksim dynamics model is generated. This model can accurately reflect the dynamic characteristics of heavy-duty trucks under different working conditions, and provides an important reference for the structural reliability monitoring of the battery swap cabinet. Using this as the input condition for the simulation and testing of the battery swap cabinet, the output of the dynamic model is converted into the time-frequency domain, and the driving condition power spectrum is constructed as the input for the finite element simulation of the battery swap cabinet, as well as the input of the battery swap cabinet structure entity.

[0023] At the same time, based on the geometric model of the power swap cabinet, the finite element model of the power swap cabinet was established using the finite element software Altair HyperWorks. When establishing the finite element model, the material properties, boundary conditions, and excitation conditions were set in detail to ensure that the model can accurately simulate the mechanical properties of the internal structure of the power swap cabinet. Through finite element simulation analysis, key information such as the stress distribution of the power swap cabinet under different working conditions can be obtained, which provides strong support for evaluating the structural reliability of the power swap cabinet.

[0024] In order to achieve a comprehensive mapping of physical entities and virtual entities, the heavy-duty truck Trucksim dynamic model and the battery swap cabinet finite element model are fused. Simply put, combining the Trucksim simulation model and the finite element model, Trucksim is used to establish the dynamic equations, control system and sensor simulation modules of the battery swap cabinet, and the finite element model is used to simulate the mechanical properties of the internal structure of the battery swap cabinet; in order to achieve multi-domain and multi-scale fusion modeling of the overall system of the battery swap cabinet, the actual operation is combined with the theoretical simulation, and the accuracy of the digital twin model is improved. The output of the heavy-duty truck Trucksim dynamic model is introduced into the finite element model of the battery swap cabinet, and the dynamic equations of the battery swap cabinet are combined with the physical properties of the internal structure to generate a virtual entity corresponding to the heavy truck. This fusion processing not only improves the accuracy of the virtual entity, but also enables the virtual entity to more comprehensively reflect the status of the heavy truck and its battery swap cabinet in actual operation, providing a solid foundation for subsequent structural reliability monitoring and early warning.

[0025] S2, obtaining a virtual data set of the virtual entity, and fusing the virtual data set with the physical data set based on digital twin technology to generate a simulation data set; Specifically, step S2 includes: obtaining a virtual data set of the virtual entity, wherein the virtual data set includes amplitude virtual data, frequency virtual data, and stress virtual data; The physical data sets under different working conditions are combined with the virtual data sets, and input into a preset simulation model to generate stress values ​​of risk monitoring points; Extracting the actual stress value of the key area, comparing and verifying the stress value of the risk monitoring point with the actual stress value of the key area, and generating a verification result; When the verification result is not passed, re-using the simulation model for calculation; When the verification result is passed, a risk point stress data set is constructed to generate a simulation data set.

[0026] See also Figure 3In this embodiment, the accuracy and depth of the reliability monitoring of the battery swap cabinet structure are further deepened. First, the virtual data set generated by the virtual entity generated in step S1 is obtained. The virtual data set covers key parameters such as amplitude virtual data, frequency virtual data and stress virtual data. These data are obtained through simulation calculations of the Trucksim dynamic model and the battery swap cabinet finite element model, and can reflect the theoretical mechanical behavior of the battery swap cabinet under different working conditions. Next, the physical data sets under different working conditions are organically combined with the virtual data sets. This process involves matching and integrating the physical data collected by sensors during actual operation, such as stress, mass, speed, acceleration and displacement, with virtual data such as amplitude, frequency and stress in the virtual data set. The integrated data set is input into a preset simulation model, which is based on digital twin technology and can simulate the operating status of the battery swap cabinet under various actual working conditions and generate stress values ​​for risk monitoring points.

[0027] In order to ensure the accuracy and reliability of the simulation data, the actual stress values ​​of the key areas are extracted and compared with the stress values ​​of the risk monitoring points generated by the simulation model. This verification process is a key step to ensure the accuracy of the mapping between the digital twin model and the actual physical entity. If the result of the comparison verification shows that it fails, that is, there is a significant difference between the simulation data and the actual data, the simulation model will be reused for calculation, the model parameters will be adjusted, or the simulation conditions will be reset to improve the accuracy of the simulation data. On the contrary, if the verification result is passed, that is, the simulation data and the actual data are within an acceptable error range, then a risk point stress data set will be constructed and the final simulation data set will be generated. This simulation data set not only contains real-time physical data from sensors, but also integrates verified virtual data, providing rich information for a comprehensive assessment of the reliability of the battery swap cabinet structure.

[0028] Among them, the real-time operating status of heavy trucks and battery swap cabinets can be determined by stress , vehicle load m, speed v, acceleration ɑ, displacement x, these five parameters represent. After obtaining the physical data collected by the sensor and the virtual data obtained by the simulation model, they are compared and verified. Once the verification is passed, the risk point stress data set is constructed.

[0029] S3, using a preset DNN model to calculate the simulation data set to generate a maximum stress prediction value of the risk point and a fatigue characteristic prediction value of the battery swap cabinet; See also Figure 4Specifically, in this embodiment, the DNN algorithm is used to train the data to predict the operating status of the battery swap cabinet of the heavy truck, which is a key link in realizing accurate monitoring of the structural reliability of the battery swap cabinet. Specifically, the simulation data set is deeply calculated using a pre-built and trained deep neural network (DNN) model. The DNN model is trained based on a large amount of historical data and professional knowledge, and can learn and identify the stress change pattern and fatigue accumulation characteristics of the battery swap cabinet under different working conditions.

[0030] When the simulation data set is input into the DNN model, the model uses its complex neural network structure to perform multi-layer abstraction and feature extraction on the data. This process involves the calculation of multiple hidden layers, each of which uses a nonlinear activation function to process the input data, thereby capturing the complex nonlinear relationships in the data. In this way, the DNN model can extract key feature information from the simulation data set, and then generate the predicted value of the maximum stress of the risk point and the predicted value of the fatigue characteristics of the battery swap cabinet.

[0031] The generation of the maximum stress prediction value of the risk point enables the monitoring system to identify the parts of the battery swap cabinet that may have excessive stress in advance, which is crucial for preventing structural damage and failure. The calculation of the fatigue characteristic prediction value of the battery swap cabinet helps to evaluate the fatigue accumulation of the battery swap cabinet during long-term operation, providing a scientific basis for predicting the service life of the battery swap cabinet and formulating a reasonable maintenance plan.

[0032] S4, perform early warning preprocessing on the predicted value of the maximum stress of the risk point and the predicted value of the fatigue characteristic of the battery swap cabinet, and issue an early warning prompt or output the predicted value.

[0033] Specifically, step S4 includes: determining whether the maximum stress prediction value of the risk point exceeds a preset safety threshold; If not, output the maximum stress value of the current working condition; If so, a classification neural network is used to determine the maximum stress value position of the current working condition, the maximum stress value position of the current working condition and its corresponding maximum stress value are output, and a voice alarm prompt is given.

[0034] Determine whether the predicted value of the fatigue characteristic of the battery swap cabinet exceeds a preset safety threshold; If not, output the fatigue cumulative damage value of the current working condition; If so, a classification neural network is used to determine the fatigue characteristic category of the current working condition, output the fatigue cumulative damage value corresponding to the fatigue characteristic category of the current working condition, and issue a voice alarm prompt.

[0035] See also Figure 5 , Figure 6In this embodiment, the predicted value of the maximum stress of the risk point and the predicted value of the fatigue characteristics of the battery swap cabinet are pre-processed for early warning, and the corresponding early warning prompt or output prediction value is given according to the processing result. This process is the core link to realize the intelligent and automated monitoring and early warning system of the structure reliability of the battery swap cabinet, and aims to discover potential safety risks in advance through an effective early warning mechanism to ensure the safe operation of the battery swap vehicle.

[0036] First, the predicted value of the maximum stress at the risk point is evaluated to determine whether it exceeds the preset safety threshold. This safety threshold is pre-set based on the design standards and material properties of the power swap cabinet to ensure the structural safety of the power swap cabinet under normal operating conditions. If the predicted value of the maximum stress at the risk point does not exceed the safety threshold, the system will normally output the maximum stress value under the current working conditions to provide operators with real-time operating status information so that they can understand the current stress condition of the power swap cabinet and conduct reasonable operation management and maintenance planning. Specifically, the stress monitoring of the risk point of the power swap cabinet obtains the stress data of the risk point of the power swap cabinet through a simulation model, predicts the maximum stress at the risk point position through the DNN neural network, and thus determines the position of the maximum stress risk point. If the maximum stress exceeds the safety threshold, the reliability category is judged by the classification neural network and the current status data and voice alarm prompt are output.

[0037] That is, if the predicted maximum stress value at the risk point exceeds the safety threshold, this indicates that there may be a risk of structural damage to the battery swap cabinet. At this time, a classification neural network will be used to accurately judge the location of the maximum stress value under the current working condition. By learning a large amount of historical data and stress distribution patterns, the classification neural network can accurately identify the specific location where the stress is too high. The maximum stress value position and its corresponding maximum stress value under the current working condition will be output, and a voice alarm prompt will be immediately activated to remind operators of potential structural risks so that they can take timely measures, such as reducing loads, adjusting operating parameters, or performing necessary inspections and repairs, thereby effectively avoiding the occurrence of structural failures and ensuring the safe operation of battery swap vehicles.

[0038] Secondly, the predicted value of the fatigue characteristic of the power swap cabinet is evaluated to determine whether it exceeds the preset safety threshold. If the predicted value of the fatigue characteristic of the power swap cabinet does not exceed the safety threshold, the system will output the fatigue cumulative damage value under the current working condition, provide the operator with real-time information on the fatigue status of the power swap cabinet, and help them evaluate the service life and maintenance needs of the power swap cabinet. Conversely, if the predicted value of the fatigue characteristic of the power swap cabinet exceeds the safety threshold, this indicates that the power swap cabinet may be in a high-risk stage of fatigue cumulative damage. At this time, a classification neural network will be used to judge the fatigue characteristic category under the current working condition. The classification neural network can accurately identify the fatigue stage of the power swap cabinet, such as early fatigue, mid-term fatigue, or late fatigue, based on the characteristics of the fatigue cumulative damage value. The fatigue cumulative damage value corresponding to the fatigue characteristic category of the current working condition will be output, and a voice alarm prompt will be activated to remind the operator that the power swap cabinet may need to be repaired or replaced to prevent serious accidents such as fatigue fracture.

[0039] Specifically, the stress data collected from the switch cabinet structure is processed by the DNN model data, and the time stress curve is drawn using the rain flow counting method. Combined with the linear cumulative damage theory - Miner theory, the material resistance index SN curve, according to the Miner cumulative damage theory, it is assumed that there is X level of stress in one cycle. , , ..., , the number of cycles of stress level X is , ..., . The component is under a single stress The number of cycles until fatigue failure occurs is , ..., , this value can be found in the actual S-N curve of the material. The cycle ratio of fatigue damage is / , / , / ..., / , when the stress levels of each level are continuously cycled and the cumulative damage of the component reaches 1, cracks will appear in the component, and then the component will begin to fail. The sum of the critical damage degrees H is: H= = 1. In order to further ensure that the data is authentic and reliable, the above formula has been repeatedly revised through a large number of engineering tests. The test results show that when the value of H is smaller than 1, the data is more authentic and reliable when the value of H is 0.7.

[0040] Linear cumulative damage theory - Miner theory, material resistance index SN curve, can well reflect its fatigue characteristics, thereby converting the residual life of the heavy truck battery swap cabinet. If the cumulative fatigue damage value of the battery swap cabinet is lower than the safety threshold, the classification neural network will determine the fatigue category and output the current status data and voice alarm prompt.

[0041] In this embodiment, the heavy truck battery swap cabinet structure reliability monitoring method involves several battery swap cabinet structure reliability judgment criteria: The first is stress monitoring and early warning of risk points in the battery swap cabinet structure. If the predicted maximum stress of the battery swap cabinet is within the normal working range (85% of the allowable structural stress), the current status information of the predicted battery swap cabinet is output normally without triggering an early warning; if the predicted maximum stress of the battery swap cabinet is higher than the safety threshold (85% of the allowable structural stress), the status information of the battery swap cabinet is output and an early warning is issued to remind the operator to check whether there is any abnormal sound, vibration or friction in the battery swap cabinet.

[0042] The second type is the fatigue characteristic monitoring and early warning of the battery swap cabinet. If the predicted cumulative fatigue damage value of the battery swap cabinet is within the normal working range (H≤0.7), the current state information of the predicted battery swap cabinet is output normally without triggering an early warning; if the predicted cumulative fatigue damage value is higher than the safety threshold (H>0.7), the state information of the battery swap cabinet is output and an early warning is issued to remind the operator to check whether the battery swap cabinet should be repaired or replaced.

[0043] In summary, the structural reliability monitoring method of heavy truck battery swap cabinets provides strong support for the full life cycle management of battery swap cabinets through the organic combination of digital twin technology, deep learning algorithm and intelligent early warning mechanism. It can not only monitor the structural status of the battery swap cabinet in real time and accurately, but also issue early warnings in time when potential risks occur, effectively ensuring the safety of battery swap vehicles, and has important practical application value and broad application prospects.

[0044] See also Figure 7 The second embodiment of the present invention provides a heavy truck battery exchange cabinet structure reliability monitoring device, which includes: A virtual entity establishment unit 201 is used to obtain a physical data set collected by a sensor component configured on a heavy truck and a battery exchange cabinet thereof, and establish a virtual entity corresponding to the heavy truck based on the physical data set; A fusion unit 202 is used to obtain a virtual data set of the virtual entity, and fuse the virtual data set with the physical data set based on the digital twin technology to generate a simulation data set; The DNN unit 203 is used to calculate the simulation data set using a preset DNN model to generate a maximum stress prediction value of a risk point and a fatigue characteristic prediction value of a battery swap cabinet; The early warning unit 204 is used to perform early warning preprocessing on the maximum stress prediction value of the risk point and the fatigue characteristic prediction value of the battery swap cabinet, and to provide early warning prompts or output prediction values.

[0045] The third embodiment of the present invention provides a heavy-duty truck battery swap cabinet structure reliability monitoring device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the heavy-duty truck battery swap cabinet structure reliability monitoring method as described in any one of the above.

[0046] The fourth embodiment of the present invention provides a readable storage medium storing a computer program, wherein the computer program can be executed by a processor of a device where the storage medium is located to implement a method for monitoring the structural reliability of a heavy-duty truck battery exchange cabinet as described in any one of the above items.

[0047] Exemplarily, the above-mentioned devices and process steps can be implemented by a computer program. The computer program can be divided into one or more units. The one or more units are stored in the memory and executed by the processor to complete the present invention.

[0048] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0049] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the present invention by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0050] Wherein, if the electronic device or printer integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0051] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0052] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for monitoring the structural reliability of a heavy truck battery exchange cabinet, characterized in that: include: Acquire a physical data set collected by a sensor component configured on a heavy truck and a battery swap cabinet thereof, and establish a virtual entity corresponding to the heavy truck based on the physical data set; Acquire a virtual data set of the virtual entity, and fuse the virtual data set with the physical data set based on digital twin technology to generate a simulation data set; The simulation data set is calculated using a preset DNN model to generate a maximum stress prediction value of the risk point and a fatigue characteristic prediction value of the battery swap cabinet; The predicted value of the maximum stress of the risk point and the predicted value of the fatigue characteristics of the battery swap cabinet are subjected to early warning preprocessing, and early warning prompts are given or predicted values ​​are output.

2. The method for monitoring the structural reliability of a heavy truck battery exchange cabinet according to claim 1 is characterized in that: Obtain a physical data set collected by a sensor component configured on a heavy truck and its battery swap cabinet, and establish a virtual entity corresponding to the heavy truck based on the physical data set, specifically: Acquire a physical data set collected by a sensor assembly configured on a heavy truck and a battery swap cabinet in a focus area thereof, wherein the physical data set includes stress, mass, velocity, acceleration, and displacement; According to the physical data set, different heavy truck models are built using Trucksim dynamics software, and different road conditions are selected to solve vehicle dynamics parameters to generate a heavy truck Trucksim dynamics model; Based on the geometric model of the power swap cabinet, the finite element model of the power swap cabinet was established using the finite element software Altair HyperWorks; The heavy-duty truck Trucksim dynamic model and the battery swap cabinet finite element model are fused to generate a virtual entity corresponding to the heavy-duty truck, wherein the output of the heavy-duty truck Trucksim dynamic model is introduced into the battery swap cabinet finite element model to combine the dynamic equations of the battery swap cabinet with the physical characteristics of the internal structure.

3. The method for monitoring the structural reliability of a heavy truck battery exchange cabinet according to claim 1 is characterized in that: The sensor assembly includes a resistive strain sensor, a mass sensor, a velocity sensor, an acceleration sensor, and a displacement sensor.

4. The method for monitoring the structural reliability of a heavy truck battery exchange cabinet according to claim 1 is characterized in that: Acquire a virtual data set of the virtual entity, fuse the virtual data set with the physical data set based on digital twin technology, and generate a simulation data set, specifically: Acquire a virtual data set of the virtual entity, wherein the virtual data set includes amplitude virtual data, frequency virtual data, and stress virtual data; The physical data sets under different working conditions are combined with the virtual data sets, and input into a preset simulation model to generate stress values ​​of risk monitoring points; Extracting the actual stress value of the key area, comparing and verifying the stress value of the risk monitoring point with the actual stress value of the key area, and generating a verification result; When the verification result is not passed, re-using the simulation model for calculation; When the verification result is passed, a risk point stress data set is constructed to generate a simulation data set.

5. The method for monitoring the structural reliability of a heavy truck battery swap cabinet according to claim 1 is characterized in that: Perform early warning preprocessing on the predicted value of the maximum stress of the risk point, and issue an early warning prompt or output the predicted value, specifically: Determine whether the maximum stress prediction value of the risk point exceeds a preset safety threshold; If not, output the maximum stress value of the current working condition; If so, a classification neural network is used to determine the maximum stress value position of the current working condition, the maximum stress value position of the current working condition and its corresponding maximum stress value are output, and a voice alarm prompt is given.

6. The method for monitoring the structural reliability of a heavy truck battery exchange cabinet according to claim 1 is characterized in that: Perform early warning preprocessing on the fatigue characteristic prediction value of the battery swap cabinet, and issue an early warning prompt or output the prediction value, specifically: Determine whether the predicted value of the fatigue characteristic of the battery swap cabinet exceeds a preset safety threshold; If not, output the fatigue cumulative damage value of the current working condition; If so, a classification neural network is used to determine the fatigue characteristic category of the current working condition, output the fatigue cumulative damage value corresponding to the fatigue characteristic category of the current working condition, and issue a voice alarm prompt.

7. A heavy truck battery exchange cabinet structure reliability monitoring device, characterized in that: include: A virtual entity establishment unit, used to obtain a physical data set collected by a sensor component configured on a heavy truck and a battery exchange cabinet thereof, and establish a virtual entity corresponding to the heavy truck based on the physical data set; A fusion unit, used to obtain a virtual data set of the virtual entity, and fuse the virtual data set with the physical data set based on the digital twin technology to generate a simulation data set; A DNN unit, used to calculate the simulation data set using a preset DNN model to generate a maximum stress prediction value of a risk point and a fatigue characteristic prediction value of a battery swap cabinet; The early warning unit is used to perform early warning preprocessing on the maximum stress prediction value of the risk point and the fatigue characteristic prediction value of the battery swap cabinet, and to provide early warning prompts or output prediction values.

8. A heavy truck battery exchange cabinet structure reliability monitoring device, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the heavy-duty truck battery exchange cabinet structure reliability monitoring method as described in any one of claims 1 to 6.

9. A readable storage medium, characterized in that: A computer program is stored, and the computer program can be executed by a processor of the device where the storage medium is located to implement the heavy-duty truck battery exchange cabinet structure reliability monitoring method as described in any one of claims 1 to 6.

Images