Thermal-mechanical safety online intelligent detection system and method for battery structure

Abstract

The present invention belongs to the technical field of online battery detection, and provides a battery structure thermal safety online intelligent detection system and method. The system includes a fiber grating array sensor, which is used to detect the temperature and strain of the battery structure in real time online to obtain a dynamic array sensor signal of the battery structure; a processor, which is configured to: process the dynamic array sensor signal of the battery structure, and then predict the quantified result of the thermal damage of the battery structure based on a pre-trained thermal damage prediction model. It significantly improves the finite element simulation accuracy of the thermal damage of the battery structure, and on this basis effectively improves the intelligent prediction accuracy of the thermal damage prediction model, thereby achieving high-precision identification of damage location, damage type and degree.

Description

Technical Field

[0001] The present invention belongs to the technical field of battery online detection, and in particular relates to a thermal-mechanical safety online intelligent detection system and method for a battery structure. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Traditional battery management systems include online detection of battery current, voltage and temperature. Some battery management systems also include online detection of pressure and strain. Electrical measurement technology is generally used, that is, electrical sensors, such as ammeters for measuring current, voltmeters for measuring voltage, thermocouple temperature sensors for measuring temperature, piezoelectric sensors for measuring pressure, and resistance strain gauges for measuring strain. Electrical sensors are discrete sensors. Each electrical sensor needs to have an independent and complete transmission circuit. In the high voltage environment of batteries, especially power batteries, the electrical sensors and their transmission circuits need to be reliably insulated and protected from chemical corrosion. In the vehicle environment, the electrical sensors and their transmission circuits need to be reliably fixed, resistant to friction and wear, resistant to aging, and resistant to fatigue. Otherwise, the electrical sensors themselves become a major hidden danger to battery safety. Electrical sensors are inherently susceptible to electromagnetic interference, which affects detection stability and detection accuracy. Therefore, the amount of electrical sensors used in batteries is very small.

[0004] However, the battery structure (including the battery box, the outer surface of the battery module in the battery box, the outer surface of the battery in the battery module, and the structure and cables used to fix the battery packaging) is complex and changeable, and is a typical multi-scale, multi-level, multi-material, multi-interface, thermal-mechanical coupling problem. The research on a series of key technologies such as thermal-mechanical damage mechanism modeling and simulation of battery structures, sensor optimization layout, dynamic array sensor signal processing, and real-time online intelligent prediction is basically blank, and it is impossible to achieve online intelligent detection of thermal-mechanical safety of battery structures. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a thermal-mechanical safety online intelligent detection system and method for battery structure, which integrates the spatial distribution and time evolution characteristics of temperature, stress strain, damage degree and morphology of the battery structure.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] The first aspect of the present invention provides a battery structure thermal-mechanical safety online intelligent detection system, which includes:

[0008] Fiber Bragg grating array sensor, which is used to detect the temperature and strain of the battery structure in real time and obtain the dynamic array sensing signal of the battery structure;

[0009] A processor configured to: process a dynamic array sensor signal of a battery structure, and then predict a quantitative result of thermal-mechanical damage to the battery structure based on a pre-trained thermal-mechanical damage prediction model;

[0010] The training process of the thermal-mechanical damage prediction model is as follows:

[0011] According to the comparison result of the simulation value of the finite element model based on the thermal-mechanical damage of the battery structure and the dynamic array sensor signal of the battery structure under the corresponding conditions, the finite element model is adjusted and optimized;

[0012] The simulation results obtained from the optimized finite element model are used as training data to directly train the thermal-mechanical damage prediction model;

[0013] The thermal-mechanical damage prediction results of the thermal-mechanical damage prediction model for the battery structure are compared with the dynamic array sensor signals of the battery structure under corresponding conditions, and the thermal-mechanical damage prediction model is verified based on the errors between the two; if the accuracy requirements are met, a trained thermal-mechanical damage prediction model is obtained; otherwise, the thermal-mechanical damage prediction model is continued to be trained until the accuracy requirements are met.

[0014] As an implementation mode, the fiber grating array sensor is attached to the surface of the battery structure.

[0015] Preferably, the fiber grating array sensor is attached to the outer surface and inner surface of the battery box body, the outer surface of the battery module in the battery box, the outer surface of the battery in the battery module and the outer surface of the cable.

[0016] As an implementation mode, the fiber grating array sensor is built into a colloid used for fixing the battery package.

[0017] Among them, fiber grating sensors belong to optical sensors. Fiber gratings have the characteristics of small size, light weight, high sensitivity, strong anti-electromagnetic interference ability, corrosion resistance, high temperature resistance, integration of sensing and transmission, and self-networking. They are suitable for both embedding inside structural parts and being surface-mounted on structural parts. Among them, the long-period fiber grating has the characteristics of distributed sensing, but the positioning accuracy is not high; the short-period fiber grating has the characteristics of quasi-distributed sensing and high positioning accuracy; fiber grating sensors can avoid the intrinsic limitations of electrical sensors.

[0018] As an implementation method, the finite element model of thermal-mechanical damage to the battery structure is constructed using multi-physics field coupled multi-scale finite element simulation software, which is used to numerically analyze the spatial distribution and time evolution of temperature, stress strain and damage morphology of the battery structure.

[0019] As an implementation method, a corresponding number of battery structure thermal-mechanical damage finite element simulations are carried out according to the number of training samples required by the thermal-mechanical damage prediction model.

[0020] As an implementation manner, the processor is further configured to:

[0021] Based on the quantified results of thermal-mechanical damage to the battery structure, the corresponding state-based maintenance and repair plans are matched from the plan database.

[0022] The second aspect of the present invention provides a detection method using the battery structure thermal-mechanical safety online intelligent detection system as described above, which comprises:

[0023] Acquire the temperature and strain of the battery structure in real time online to obtain the dynamic array sensor signal of the battery structure;

[0024] Based on the pre-trained thermal-mechanical damage prediction model, the quantitative results of thermal-mechanical damage of the battery structure are predicted;

[0025] The training process of the thermal-mechanical damage prediction model is as follows:

[0026] According to the comparison result of the simulation value of the finite element model based on the thermal-mechanical damage of the battery structure and the dynamic array sensor signal of the battery structure under the corresponding conditions, the finite element model is adjusted and optimized;

[0027] The simulation results obtained from the optimized finite element model are used as training data to directly train the thermal-mechanical damage prediction model;

[0028] The thermal-mechanical damage prediction results of the thermal-mechanical damage prediction model for the battery structure are compared with the dynamic array sensor signals of the battery structure under corresponding conditions, and the thermal-mechanical damage prediction model is verified based on the errors between the two; if the accuracy requirements are met, a trained thermal-mechanical damage prediction model is obtained; otherwise, the thermal-mechanical damage prediction model is continued to be trained until the accuracy requirements are met.

[0029] As an implementation method, the finite element model of thermal-mechanical damage to the battery structure is constructed using multi-physics field coupled multi-scale finite element simulation software, which is used to numerically analyze the spatial distribution and time evolution of temperature, stress strain and damage morphology of the battery structure.

[0030] As an implementation method, a corresponding number of battery structure thermal-mechanical damage finite element simulations are carried out according to the number of training samples required by the thermal-mechanical damage prediction model.

[0031] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps in the detection method as described above when the program is executed by a processor.

[0032] A fourth aspect of the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the detection method described above when executing the program.

[0033] Compared with the prior art, the present invention has the following beneficial effects:

[0034] (1) The present invention uses a fiber grating array sensor to detect the temperature and strain of the battery structure and obtain a dynamic array sensing signal of the battery structure, which significantly improves the finite element simulation accuracy of thermal-mechanical damage to the battery structure and effectively improves the intelligent prediction accuracy of the thermal-mechanical damage prediction model on this basis, thereby achieving high-precision intelligent identification of damage location, damage type and degree.

[0035] (2) The battery structure thermal-mechanical safety online intelligent detection system and method of the present invention not only integrates artificial intelligence technology, but is also based on heat transfer, composite material science, solid structure mechanics, damage mechanics and sensor detection technology, so that battery safety information can be provided in a hierarchical manner to direct battery users, professional battery maintainers and repairers, battery manufacturers and complete system integrators.

[0036] (3) The battery structure thermal-mechanical safety online intelligent detection system and method of the present invention can not only provide battery structure safety information and status-based maintenance and repair plans in real time online when the battery is in use, but also have a technical improvement period based on scientific theories and knowledge systems in the research and development stage before the battery is put into use, so as to achieve the effect that the battery structure thermal-mechanical safety online intelligent detection system is driven by both mechanism and data, thereby realizing the low-cost, high-efficiency and high-precision battery structure thermal-mechanical safety online intelligent detection system development.

[0037] (4) The battery structure thermal-mechanical safety online intelligent detection system and method of the present invention enables the battery service health status to be quantitatively evaluated in real time online, which helps to optimize the design of battery cell materials and manufacturing processes, battery module packaging materials and processes, and battery pack packaging materials and processes.

[0038] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0040] Figure 1 This is a schematic diagram of the thermal-mechanical safety online intelligent detection principle of the battery structure according to an embodiment of the present invention;

[0041] Figure 2 It is a schematic diagram of the structure of a fiber grating array sensor according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0043] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0044] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0045] Embodiment 1

[0046] This embodiment provides a battery structure thermal-mechanical safety online intelligent detection system, which includes a fiber grating array sensor and a processor.

[0047] (1) Fiber Bragg Grating Array Sensor

[0048] like Figure 2 As shown, the fiber grating array sensor is used to detect the temperature and strain of the battery structure in real time online to obtain a dynamic array sensing signal of the battery structure.

[0049] In a specific implementation process, the fiber grating array sensor is attached to the surface of the battery structure.

[0050] In other embodiments, the fiber grating array sensor is embedded in a colloid used for fixing the battery package.

[0051] The fiber grating sensing network formed in this way can ensure high survival rate and stable detection life.

[0052] (2) Processor

[0053] The processor is configured to: process the dynamic array sensor signal of the battery structure, and then predict the quantified result of the thermal-mechanical damage of the battery structure based on a pre-trained thermal-mechanical damage prediction model.

[0054] Among them, refer to Figure 1 , the training process of the thermal-mechanical damage prediction model is:

[0055] Step 1: According to the comparison results between the simulation value of the finite element model based on the thermal-mechanical damage of the battery structure and the dynamic array sensor signal of the battery structure under corresponding conditions, the finite element model is adjusted and optimized.

[0056] In some embodiments, the finite element model of thermal-mechanical damage to the battery structure is constructed using multi-physics field coupled multi-scale finite element simulation software, which is used to numerically analyze the spatial distribution and time evolution of temperature, stress strain and damage morphology of the battery structure.

[0057] It should be noted here that, in other embodiments, based on material parameters, geometric models, mechanical loads and constraints, simulation analysis of the finite element model of thermal-mechanical damage to the battery structure can also be carried out on a general finite element simulation software platform.

[0058] Specifically, a portion (e.g., 80%) of the temperature and strain detected by the fiber grating sensors are randomly selected and recorded as indirect training data of the thermal-mechanical damage prediction model, and the remaining temperature and strain detected by the fiber grating sensors are recorded as verification data of the thermal-mechanical damage prediction model; the above-mentioned indirect training data of the thermal-mechanical damage prediction model are compared with the corresponding finite element simulation results of thermal-mechanical damage of the battery structure, and then the corresponding battery structure thermal-mechanical damage finite element model and algorithm are adjusted and optimized according to the errors of the two, so as to effectively improve the finite element simulation accuracy of the thermal-mechanical process and damage of the battery structure.

[0059] Among them, according to the number of direct training samples required by the thermal-mechanical damage prediction model, a corresponding number of finite element simulations of thermal-mechanical damage of battery structures are carried out.

[0060] Step 2: Use the simulation results obtained from the optimized finite element model as training data to directly train the thermal-mechanical damage prediction model.

[0061] Step 3: Compare the thermal-mechanical damage prediction results of the thermal-mechanical damage prediction model for the battery structure with the dynamic array sensor signal of the battery structure under corresponding conditions, and verify the thermal-mechanical damage prediction model based on the errors between the two; if the accuracy requirements are met, a trained thermal-mechanical damage prediction model is obtained; otherwise, continue to train the thermal-mechanical damage prediction model until the accuracy requirements are met.

[0062] Preferably, the trained thermal-mechanical damage prediction model for battery structure is used to predict the temperature and strain of the battery structure measurement points and the fiber Bragg grating axis corresponding to the thermal-mechanical damage prediction model verification data, and then the temperature and strain predicted by the thermal-mechanical damage prediction model are compared with the thermal-mechanical damage prediction model verification data to evaluate their errors; if the above error is acceptable, it indicates that the thermal-mechanical damage prediction model for battery structure used for dynamic array sensor signal processing is reasonably established; if the above error is still unacceptable, the indirect training data and verification data of the thermal-mechanical damage prediction model are randomly divided again (even supplemented by the online detection data of the fiber Bragg grating array sensor), and the above finite element simulation and thermal-mechanical damage prediction model training process are repeated until the thermal-mechanical damage prediction model for battery structure used for dynamic array sensor signal processing is reasonably established.

[0063] Among them, the thermal-mechanical damage prediction model is an artificial intelligence model, including but not limited to deep neural network models, expert system models, random decision forest models, support vector machine models, and learning vector quantization models.

[0064] In one or more embodiments, the processor is further configured to:

[0065] Based on the quantified results of thermal-mechanical damage to the battery structure, the corresponding state-based maintenance and repair plans are matched from the plan database.

[0066] For example: When the quantification results of the thermal-mechanical damage of the energy storage battery structure of the photovoltaic energy storage power station find that the third battery module is in a high temperature risk state, the corresponding state-based maintenance plan is matched from the plan database: the flow rate of the cooling water corresponding to the third battery module is accelerated to cool the third battery module.

[0067] For example: when the quantification results of the thermal-mechanical damage of the power battery structure of a new energy vehicle find that the 5th battery module is in a strain damage risk state, the corresponding state-based maintenance plan is matched from the plan database: first, the flow rate of the cooling water corresponding to the 5th battery module is accelerated to cool down the 5th battery module; if the strain damage risk state of the 5th battery module is lifted, continue to use the 5th battery module normally; if the strain damage risk state of the 5th battery module is still not lifted, stop the charging and discharging of the 5th battery module; if the strain damage risk state of the 5th battery module is still not lifted after the 5th battery module stops working for 60 minutes, it is necessary to stop the vehicle for inspection and repair of the 5th battery module.

[0068] For example, when the quantification results of thermal-mechanical damage to the power battery structure of a new energy vehicle find that the bottom shell of the battery box is at risk of strain damage, a corresponding state-based maintenance plan is matched from the solution database: send the battery box to a professional auto repair shop to check the quality of the bottom shell.

[0069] Embodiment 2

[0070] Reference Figure 1 This embodiment provides a detection method using the battery structure thermal-mechanical safety online intelligent detection system as described above, which includes:

[0071] Acquire the temperature and strain of the battery structure in real time online to obtain the dynamic array sensor signal of the battery structure;

[0072] Based on the pre-trained thermal-mechanical damage prediction model, the quantitative results of thermal-mechanical damage of the battery structure are predicted;

[0073] The training process of the thermal-mechanical damage prediction model is as follows:

[0074] According to the comparison results of the simulation value of the finite element model based on the thermal-mechanical damage of the battery structure and the dynamic array sensor signal of the battery structure under the corresponding conditions, the finite element model is adjusted and optimized;

[0075] The simulation results obtained from the optimized finite element model are used as training data to directly train the thermal-mechanical damage prediction model;

[0076] The thermal-mechanical damage prediction results of the thermal-mechanical damage prediction model for the battery structure are compared with the dynamic array sensor signals of the battery structure under corresponding conditions, and the thermal-mechanical damage prediction model is verified based on the errors between the two; if the accuracy requirements are met, a trained thermal-mechanical damage prediction model is obtained; otherwise, the thermal-mechanical damage prediction model is continued to be trained until the accuracy requirements are met.

[0077] As an implementation method, the finite element model of thermal-mechanical damage to the battery structure is constructed using multi-physics field coupled multi-scale finite element simulation software, which is used to numerically analyze the spatial distribution and time evolution of temperature, stress strain and damage morphology of the battery structure.

[0078] As an implementation method, a corresponding number of finite element simulations of thermal-mechanical damage of battery structures are carried out according to the number of direct training samples required by the thermal-mechanical damage prediction model.

[0079] Embodiment 3

[0080] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the detection method described above are implemented.

[0081] Embodiment 4

[0082] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the detection method described above when executing the program.

[0083] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram and the combination of processes and / or blocks in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0084] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A battery structure thermal-mechanical safety online intelligent detection system, characterized in that: include: Fiber Bragg grating array sensor, which is used to detect the temperature and strain of the battery structure in real time and obtain the dynamic array sensing signal of the battery structure; A processor configured to: process a dynamic array sensor signal of a battery structure, and then predict a quantitative result of thermal-mechanical damage to the battery structure based on a pre-trained thermal-mechanical damage prediction model; The training process of the thermal-mechanical damage prediction model is as follows: According to the comparison result of the simulation value of the finite element model based on the thermal-mechanical damage of the battery structure and the dynamic array sensor signal of the battery structure under the corresponding conditions, the finite element model is adjusted and optimized; The simulation results obtained from the optimized finite element model are used as training data to directly train the thermal-mechanical damage prediction model; The thermal-mechanical damage prediction results of the thermal-mechanical damage prediction model for the battery structure are compared with the dynamic array sensor signals of the battery structure under corresponding conditions, and the thermal-mechanical damage prediction model is verified based on the errors between the two; if the accuracy requirements are met, a trained thermal-mechanical damage prediction model is obtained; otherwise, the thermal-mechanical damage prediction model is continued to be trained until the accuracy requirements are met.

2. The battery structure thermal-mechanical safety online intelligent detection system according to claim 1, characterized in that: The fiber grating array sensor is attached to the surface of the battery structure; Or the fiber grating array sensor is built into a colloid used for battery packaging and fixing.

3. The battery structure thermal-mechanical safety online intelligent detection system according to claim 1, characterized in that: The finite element model of thermal-mechanical damage to the battery structure is constructed using multi-physics field coupled multi-scale finite element simulation software, and is used to numerically analyze the spatial distribution and time evolution of temperature, stress strain and damage morphology of the battery structure.

4. The battery structure thermal-mechanical safety online intelligent detection system according to claim 1, characterized in that: According to the number of training samples required by the thermal-mechanical damage prediction model, a corresponding number of finite element simulations of thermal-mechanical damage of battery structures are carried out.

5. The battery structure thermal-mechanical safety online intelligent detection system according to claim 1, characterized in that: The processor is further configured to: Based on the quantified results of thermal-mechanical damage to the battery structure, the corresponding state-based maintenance and repair plans are matched from the plan database.

6. A detection method using the battery structure thermal-mechanical safety online intelligent detection system as claimed in claim 1, characterized in that: include: Acquire the temperature and strain of the battery structure in real time online to obtain the dynamic array sensor signal of the battery structure; Based on the pre-trained thermal-mechanical damage prediction model, the quantitative results of thermal-mechanical damage of the battery structure are predicted; The training process of the thermal-mechanical damage prediction model is as follows: According to the comparison result of the simulation value of the finite element model based on the thermal-mechanical damage of the battery structure and the dynamic array sensor signal of the battery structure under the corresponding conditions, the finite element model is adjusted and optimized; The simulation results obtained from the optimized finite element model are used as training data to directly train the thermal-mechanical damage prediction model; The thermal-mechanical damage prediction results of the thermal-mechanical damage prediction model for the battery structure are compared with the dynamic array sensor signals of the battery structure under corresponding conditions, and the thermal-mechanical damage prediction model is verified based on the errors between the two; if the accuracy requirements are met, a trained thermal-mechanical damage prediction model is obtained; otherwise, the thermal-mechanical damage prediction model is continued to be trained until the accuracy requirements are met.

7. The detection method according to claim 6, characterized in that The finite element model of thermal-mechanical damage to the battery structure is constructed using multi-physics field coupled multi-scale finite element simulation software, and is used to numerically analyze the spatial distribution and time evolution of temperature, stress strain and damage morphology of the battery structure.

8. The detection method according to claim 6, characterized in that: According to the number of training samples required by the thermal-mechanical damage prediction model, a corresponding number of finite element simulations of thermal-mechanical damage of battery structures are carried out.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps in the detection method as described in any one of claims 6 to 8 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps in the detection method according to any one of claims 6 to 8 are implemented.

Images