Multi-sensor fusion energy storage device thermal runaway early warning method and system

By using multi-sensor fusion technology and data fusion calculations based on parameters such as ultrasonic signals, early warning of thermal runaway in lithium-ion battery energy storage devices is achieved. This solves the problems of slow warning speed and high false alarm rate in existing technologies, improves emergency response efficiency, and prevents fire and explosion accidents.

CN118942227APending Publication Date: 2024-11-12CHINA PETROLEUM & CHEMICAL CORP +1
View PDF 0 Cites 4 Cited by

Patent Information

Application Number
CN202310532863.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-11
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

Existing thermal runaway early warning technologies for lithium-ion battery energy storage systems suffer from problems such as delayed early warning speed, high rates of missed or false alarms, and slow emergency fire response speed, making them unable to effectively prevent fire and explosion accidents.

Method used

By employing a multi-sensor fusion method, environmental parameters of the energy storage device are acquired, thermal runaway states are set in stages, and data fusion calculations are performed. The thermal runaway state is determined by the fusion feature values ​​of ultrasonic signals, temperature signals, voltage signals, hydrogen concentration signals, carbon monoxide concentration signals, and smoke concentration signals, and corresponding fire-fighting actions are executed.

Benefits of technology

It enables timely early warning of thermal runaway in lithium-ion battery energy storage devices, reduces false alarms and missed alarms, improves emergency response speed, and effectively prevents fire and explosion accidents.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118942227A_ABST
    Figure CN118942227A_ABST
Patent Text Reader

Abstract

The invention provides a multi-sensor fusion energy storage device thermal runaway early warning method and system, and belongs to the field of energy storage device monitoring. The method comprises the following steps: acquiring current monitoring values of various environmental parameters of the energy storage device; setting multi-stage thermal runaway states of the energy storage device in a grading manner, and performing data fusion calculation on the current monitoring values of various environmental parameters according to the multi-stage thermal runaway states to obtain a fusion characteristic value supporting the occurrence of each stage of thermal runaway state; and judging the thermal runaway state of the energy storage device according to the fusion characteristic value supporting the generation of each stage of thermal runaway state. According to the method, the level of the energy storage device in the thermal runaway state is judged through the calculated fusion characteristic value supporting the thermal runaway states of different levels, and a targeted decision is executed, so that thermal accidents of energy storage batteries of different levels are effectively coped with through linkage with various emergency fire fighting measures.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of energy storage device monitoring, and in particular to a multi-sensor fusion energy storage device thermal runaway warning system and a multi-sensor fusion energy storage device thermal runaway warning method. Background Art

[0002] In recent years, as energy and environmental problems have become increasingly severe, the global energy storage industry has developed rapidly. Among the many energy storage technology routes, lithium-ion battery energy storage systems have become the main way to store clean electric energy with their advantages in power density, energy density, cycle life, self-discharge rate and cost. In recent years, the global electrochemical energy storage industry has developed rapidly. According to statistics, the global electrochemical energy storage installed capacity will be 21.1GW in 2021. Among them, the installed capacity of lithium-ion battery energy storage technology is 19.85GW, and the power scale accounts for 93.9%. Lithium-ion batteries may experience thermal runaway under conditions such as mechanical abuse, electrical abuse and thermal abuse, resulting in a series of chemical reactions inside the battery, releasing a large amount of heat and gas, causing the battery temperature to rise sharply in a short period of time. After thermal runaway, lithium-ion batteries usually release a large amount of flammable and toxic smoke, and there is a serious risk of fire and explosion. With the increase in the number of lithium-ion battery energy storage power stations, fire and explosion accidents occur frequently. These accidents will cause certain economic losses and social impacts, threaten people's life safety, and restrict the large-scale development of electrochemical energy storage. Compared with electric vehicles, energy storage power stations have higher installed capacity and larger scale. Once battery thermal runaway occurs, the consequences of the resulting fire and explosion accidents are more serious. Therefore, the safety of energy storage batteries cannot be ignored.

[0003] When a lithium-ion battery experiences thermal runaway, it will experience an internal short circuit diffusion process. However, the mechanism and cause of the internal short circuit of lithium-ion batteries are still unclear, and it is also impossible to predict when the internal short circuit will occur in lithium-ion batteries. Therefore, from a theoretical analysis, thermal runaway of lithium-ion battery cells cannot be avoided. Therefore, thermal runaway warning, prediction and protection of lithium-ion batteries have become necessary technologies. Existing technologies for thermal runaway warning mainly rely on single-threshold spatial gas detection after battery thermal runaway or only early warning and alarm of fires, which have the limitations of delayed warning speed, high rate of missed or false alarms, and slow emergency fire response. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide a multi-sensor fusion energy storage device thermal runaway warning system and a multi-sensor fusion energy storage device thermal runaway warning method, so as to at least solve the above-mentioned problems of delayed warning speed, high missed alarm or false alarm rate, and slow emergency fire response speed.

[0005] In order to achieve the above object, the first aspect of the present invention provides a multi-sensor fusion thermal runaway early warning method for an energy storage device, the method comprising the following steps:

[0006] Obtain current monitoring values ​​of various environmental parameters of the energy storage device;

[0007] The multi-level thermal runaway state of the energy storage device is set in stages, and data fusion calculation is performed on the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state to obtain the fusion characteristic value that supports the occurrence of each level of thermal runaway state;

[0008] The thermal runaway state of the energy storage device is determined based on the fusion characteristic values ​​that support the occurrence of each level of thermal runaway state.

[0009] Preferably, the data fusion calculation of the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state is specifically as follows:

[0010] Calculate the membership of each current monitoring value to each level of thermal runaway state, establish a membership state matrix, and obtain the probability of each current monitoring value occurring in each level of thermal runaway state based on the membership state matrix, which is recorded as the initial BPA;

[0011] Calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters based on the static weights of various environmental parameters;

[0012] The initial BPA of each current monitoring value is corrected according to the dynamic weights of each environmental parameter to obtain the final BPA of each current monitoring value;

[0013] According to the final BPA of each type of current monitoring value, the fusion characteristic value of each level of thermal runaway state is calculated.

[0014] Preferably, the static weights of various environmental parameters are calculated, and the dynamic weights of various environmental parameters are calculated according to the static weights of various environmental parameters as follows:

[0015] Normalize the current monitoring values ​​of various environmental parameters to obtain normalized measurement values;

[0016] The static weights of various environmental parameters are obtained according to the analytic hierarchy process;

[0017] Calculate the dynamic weights ω of various environmental parameters based on the normalized measured values ​​and the static weights of various environmental parameters i ′, the calculation formula is as follows:

[0018]

[0019] Among them, ω i is the static weight of the i-th category monitoring value; x i is the current monitoring value of the i-th category, T(xi ) is the normalized measurement value of the i-th category monitoring value; α is the balancing factor, which is used to adjust the dynamic weight.

[0020] Preferably, the initial BPA of each current monitoring value is corrected according to the dynamic weight of each environmental parameter, and the calculation formula for obtaining the final BPA of each current monitoring value is:

[0021] m x(i) (Y j )=ω′·r ij ;

[0022] Among them, m x(i) (Y j ) is the probability that the current monitoring value of the i-th category supports the occurrence of the j-level thermal runaway state, that is, the final BPA of the current monitoring value of the i-th category; ω′ is the dynamic weight of the current monitoring value of the i-th category; r ij is the probability that the current monitoring value of the i-th category is in the j-level thermal runaway state, that is, the initial BPA of the current monitoring value of the i-th category.

[0023] Preferably, the calculation of the fusion characteristic value of each level of thermal runaway state according to the final BPA of each type of current monitoring value is specifically calculated by the following formula:

[0024]

[0025]

[0026] Among them, m(Y j ) represents the probability of occurrence of the j-level thermal runaway state after the fusion of multiple types of current monitoring values; k is the conflict coefficient, which is used to represent the conflict information between different monitoring values; x i is the current monitoring value of the i-th category; m i (x i ) is the final BPA of the current monitoring value of the i-th category under the i-th level of thermal runaway state; Y j is the probability of thermal runaway state at level j.

[0027] Preferably, the calculation of the membership of each type of current monitoring value to each level of thermal runaway state is specifically as follows:

[0028] According to the historical monitoring values ​​of various environmental parameters when each level of thermal runaway state occurs, the membership degree of various current monitoring values ​​to each level of thermal runaway state is obtained.

[0029] Preferably, the environmental parameters include ultrasonic signals, temperature signals, voltage signals, hydrogen concentration signals, carbon monoxide concentration signals and smoke concentration signals.

[0030] Preferably, the method further comprises:

[0031] According to the determined level of the thermal runaway state of the energy storage device, a firefighting action corresponding to the level of the thermal runaway state is executed.

[0032] In a second aspect, the present invention provides a multi-sensor fusion thermal runaway warning system for an energy storage device, the system comprising:

[0033] A data acquisition module, used to collect current monitoring values ​​of various environmental parameters of the energy storage device;

[0034] The main control module stores historical monitoring values ​​of various environmental parameters of the energy storage device and is used to set the multi-level thermal runaway state of the energy storage device in a hierarchical manner;

[0035] A data fusion module is used to obtain the current monitoring values ​​of various environmental parameters of the energy storage device, perform data fusion calculations on the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state, and obtain fusion characteristic values ​​that support the occurrence of each level of thermal runaway state;

[0036] The main control module is also used to determine the thermal runaway state of the energy storage device according to the fusion characteristic value that supports the occurrence of each level of thermal runaway state.

[0037] Preferably, the data fusion module includes:

[0038] The initial BPA calculation unit is used to calculate the membership of various current monitoring values ​​to each level of thermal runaway state, establish a membership state matrix, obtain the probability of various current monitoring values ​​occurring in each level of thermal runaway state based on the membership state matrix, and obtain the initial BPA;

[0039] A dynamic weight calculation unit, used to calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters according to the static weights of various environmental parameters;

[0040] A BPA correction unit, used to correct the initial BPA of various current monitoring values ​​according to the dynamic weights of various environmental parameters to obtain the final BPA of various current monitoring values;

[0041] The data fusion unit is used to calculate the fusion characteristic value of each level of thermal runaway state according to the final BPA of various current monitoring values.

[0042] Preferably, the dynamic weight unit comprises:

[0043] A normalization processing unit, used for normalizing the current monitoring values ​​of various operating parameters to obtain normalized measurement values;

[0044] A static weight calculation unit is used to obtain the static weights of various environmental parameters according to the hierarchical analysis method;

[0045] The dynamic weight calculation unit is used to calculate the dynamic weights of various environmental parameters according to the normalized measurement value and the static weights of various environmental parameters.

[0046] Preferably, the environmental parameters include ultrasonic signals, temperature signals, voltage signals, hydrogen concentration signals, carbon monoxide concentration signals and smoke concentration signals; the data acquisition module includes a signal acquisition unit;

[0047] The signal acquisition unit comprises:

[0048] Sound sensor, used to collect ultrasonic signals of gas leakage;

[0049] A temperature sensor, used to detect a temperature signal of the energy storage device;

[0050] A voltage sensor, used to detect a voltage signal of the energy storage device;

[0051] A hydrogen sensor, used to detect the hydrogen concentration signal of the energy storage device;

[0052] A carbon monoxide sensor, used to detect a carbon monoxide concentration signal of an energy storage device;

[0053] The smoke sensor is used to detect the smoke concentration signal of the energy storage device.

[0054] Preferably, the main control module includes a thermal runaway state classification unit and a thermal runaway state judgment unit.

[0055] The thermal runaway classification unit is used to classify and set the thermal runaway state of the energy storage device; the thermal runaway state of the energy storage device is a normal operation state, a first-level thermal runaway state, a second-level thermal runaway state, and a third-level thermal runaway state;

[0056] The thermal runaway judgment unit is used to judge the thermal runaway state of the energy storage device according to the fusion characteristic value supporting the occurrence of each level of thermal runaway state.

[0057] Preferably, the system further comprises an execution module, and the execution module is used to execute corresponding firefighting actions according to the level of thermal runaway state of the energy storage device determined by the main control module.

[0058] Preferably, the firefighting action includes a first-level firefighting action, a second-level firefighting action, and a third-level firefighting action;

[0059] The first-level fire fighting action is: troubleshooting and clearing the fault;

[0060] The secondary firefighting action is: cutting off the energy storage device and starting the firefighting device;

[0061] The three-level fire fighting action is: automatically cutting off the energy storage device and automatically starting the fire fighting device.

[0062] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions. When the computer instructions are executed on a computer, the computer executes the thermal runaway warning method for an energy storage device using multi-sensor fusion as described above.

[0063] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the thermal runaway warning method for an energy storage device using multi-sensor fusion as described above when executing the computer program.

[0064] The present invention uses the acoustic signal of a small amount of gas leakage in the very early stage of thermal runaway as a criterion for determining thermal runaway of the energy storage battery, and integrates it with traditional characteristic parameters such as pressure, temperature, gas, and smoke for calculation, so as to achieve more timely and comprehensive thermal runaway warning. By calculating the integrated characteristic values ​​supporting different levels of thermal runaway states, the level of the thermal runaway state of the energy storage device is judged, and targeted decisions are executed, so as to effectively respond to different levels of thermal accidents of energy storage batteries through linkage with various emergency fire fighting measures.

[0065] The ultrasonic signal is an early characteristic parameter. The present invention realizes timely early warning of thermal runaway by monitoring the early characteristic parameter.

[0066] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0068] Figure 1 This is a flow chart of a method for thermal runaway warning of an energy storage device using multi-sensor fusion provided in Example 1 of the present invention;

[0069] Figure 2 This is a flow chart of data fusion calculation provided by Example 1 of the present invention. DETAILED DESCRIPTION

[0070] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0071] Example 1

[0072] Figure 1FIG. 1 is a block diagram of a thermal runaway warning system for an energy storage device using multi-sensor fusion according to an embodiment of the present invention. Figure 1 As shown, this embodiment provides a multi-sensor fusion thermal runaway warning method for an energy storage device, the method comprising the following steps:

[0073] S1. Obtain the current monitoring values ​​of various environmental parameters of the energy storage device;

[0074] S2. Setting the multi-level thermal runaway state of the energy storage device in a hierarchical manner, performing data fusion calculation on the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state, and obtaining the fusion characteristic value that supports the occurrence of each level of thermal runaway state;

[0075] In this embodiment, the thermal runaway state of the energy storage device is divided into a normal operating state, a first-level thermal runaway state, a second-level thermal runaway state, and a third-level thermal runaway state.

[0076] The multiple types of environmental parameters include: ultrasonic signal, temperature signal, voltage signal, hydrogen concentration signal, carbon monoxide concentration signal and smoke concentration signal.

[0077] The ultrasonic signal is an ultrasonic signal of gas leakage. By collecting the ultrasonic signal of gas leakage of the energy storage device, gas leakage occurs in the earliest stage of thermal runaway of the energy storage device, and gas leakage is not easy to be monitored. Therefore, this embodiment collects the ultrasonic signal of gas leakage to achieve early control of thermal runaway of the energy storage device.

[0078] The temperature signal is used to monitor the temperature of the energy storage device; the voltage signal is used to monitor the voltage of the energy storage device; the hydrogen concentration signal is used to monitor the hydrogen concentration in the energy storage device, the carbon monoxide concentration signal is used to monitor the carbon monoxide concentration of the energy storage device; and the smoke concentration signal is used to monitor the smoke concentration of the energy storage device.

[0079] In this embodiment, the ultrasonic signal is collected by a sound sensor, the temperature signal is collected by a temperature sensor, the voltage signal is collected by a voltage sensor, the hydrogen concentration signal is collected by a hydrogen sensor, the carbon monoxide concentration signal is collected by a carbon monoxide sensor, and the smoke concentration signal is collected by a smoke sensor.

[0080] In this embodiment, the sound sensor is arranged inside the battery module of the energy storage device to measure and judge the gas leakage in the early stage of thermal runaway of the battery module; the temperature sensor is also arranged inside the battery module of the energy storage device to measure the temperature of the battery module; the voltage sensor is used to detect the voltage of the battery module; the hydrogen sensor is used to measure the hydrogen concentration signal inside the energy storage device, the carbon monoxide sensor is used to measure the carbon monoxide concentration signal inside the energy storage device, and the smoke sensor is used to measure the smoke concentration signal inside the energy storage device. The signal acquisition unit sends the above signal to the main control module, which analyzes and processes the above signal.

[0081] The existing technology only monitors the gas concentration. When the energy storage system is operating normally, if there is warning gas in the air at this time, it may be interfered by the gas in the air, resulting in false alarms; the gas leakage concentration of the energy storage device before complete thermal runaway is low, and it is easy to miss alarms in the early stage. In the above two cases, placing the sound sensor, hydrogen sensor, carbon monoxide sensor and smoke sensor on the surface of the battery module can quickly identify the sound of gas leakage, avoid false alarms and miss alarms caused by a single sensor, and achieve early warning of thermal runaway.

[0082] Among them, the normal operating status indicates that the current monitoring values ​​of multiple types of environmental parameters of the energy storage device are within the normal operating threshold.

[0083] The first-level thermal runaway state indicates that the body temperature of the energy storage device rises, abnormal batteries emit smoke, and temperature and ultrasonic sensors respond.

[0084] The secondary thermal runaway state indicates that the body temperature of the energy storage device rises rapidly, a large amount of smoke escapes, and the hydrogen sensor, carbon monoxide sensor, and voltage sensor respond.

[0085] The third-level thermal runaway state indicates that thermal runaway reactions continue to occur inside the energy storage device, producing a large amount of smoke and causing the smoke sensor to respond.

[0086] like Figure 2 As shown, in this embodiment, the data fusion calculation of multiple types of current monitoring values ​​according to the multi-level thermal runaway state is specifically as follows:

[0087] S21. Calculate the membership of each current monitoring value to each level of thermal runaway state, establish a membership state matrix, and obtain the probability of each current monitoring value occurring in each level of thermal runaway state based on the membership state matrix, which is recorded as the initial BPA.

[0088] In this embodiment, the degree of membership of each type of current monitoring value to each level of thermal runaway state is calculated as follows:

[0089] The membership of each type of current monitoring value to each level of thermal runaway state is calculated by combining triangular and semi-trapezoidal fuzzy membership functions.

[0090] Normal operation:

[0091] Level 1 thermal runaway state:

[0092] Secondary thermal runaway state:

[0093] Level 3 thermal runaway state:

[0094] In the above formulas (1) to (4), μ1 to μ4 represent the membership of the sensor to different warning states, with a value range of [0, 1]. x represents the value of the real-time output data of each sensor after preprocessing. x1 to x4 represent the classification thresholds of different levels of thermal runaway states, which are obtained from experiments on thermal runaway of different batteries.

[0095] The membership state matrix state is as follows:

[0096]

[0097] In the formula, r mn represents the output x of the mth sensor m The probability of being in state n.

[0098] In this embodiment, the membership state matrix is:

[0099]

[0100] When the gas in the energy storage device escapes slowly, the energy storage system has not yet begun to truly thermally run away. At this time, a small amount of gas escapes and the temperature rises. Therefore, at this stage, the gas leakage ultrasonic monitoring data and temperature data will deviate greatly from the normal operating values, and the data output by other sensors (hydrogen concentration in the cabin, voltage, carbon monoxide concentration, etc.) have not yet detected parameter fluctuations. If all parameter sensors use conventional weight calculation methods throughout the process, the actual operating status of the energy storage system cannot be accurately reflected. In order to accurately express the thermal runaway characteristics according to different stages, a variable weighting method based on the thermal runaway development stage is established. The specific method is as follows:

[0101] S22. Calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters based on the static weights of various environmental parameters;

[0102] In this embodiment, the static weights of various environmental parameters are calculated, and the dynamic weights of various environmental parameters are calculated according to the static weights of various environmental parameters. Specifically,

[0103] Normalize the current monitoring values ​​of multiple types of environmental parameters to obtain normalized measurement values;

[0104] Specifically, the data of each sensor is normalized: Where x is the measured value of the i-th type of monitoring result, x max 、x min are the maximum and minimum values ​​of the measured samples;

[0105] The static weights of various environmental parameters are obtained according to the analytic hierarchy process;

[0106] The dynamic weights of various environmental parameters are calculated based on the normalized measured values ​​and the static weights of various environmental parameters. The calculation formula is as follows:

[0107]

[0108] Among them, ω i is the static weight of the i-th environmental parameter; T(x i ) is the normalized measured value of the current measured value of the i-th environmental parameter; α is the balancing factor used to adjust the dynamic weight; x i is the current monitoring value of the i-th category.

[0109] The initial BPA is corrected according to the dynamic weights of various environmental parameters to obtain the final BPA;

[0110] According to the final BPA of each type of current monitoring value, the fusion characteristic value of each level of thermal runaway state is calculated.

[0111] S23. In this embodiment, the initial BPA of each current monitoring value is corrected according to the dynamic weight of each environmental parameter, and the calculation formula for obtaining the final BPA of each current monitoring value is:

[0112] m x(i) (Y j )=ω′·r ij ;

[0113] Among them, m x(i) (Y j ) is the probability that the current monitoring value of the i-th category supports the occurrence of the j-level thermal runaway state, that is, the final BPA of the current monitoring value of the i-th category; ω′ is the dynamic weight of the current monitoring value of the i-th category; r ij is the probability that the current monitoring value of the i-th category is in the j-level thermal runaway state, that is, the initial BPA of the current monitoring value of the i-th category.

[0114] S24. In this embodiment, the calculation of the fusion characteristic value of each level of thermal runaway state according to the final BPA of each type of current monitoring value is specifically calculated using the following formula:

[0115]

[0116]

[0117] Among them, m(Y j ) represents the probability of occurrence of the j-level thermal runaway state after the fusion of various current monitoring values; k is the conflict coefficient, which is used to represent the conflict information between different monitoring values; x i is the current monitoring value of the i-th category; m i (x i ) is the final BPA of the current monitoring value of the i-th category under the i-th level of thermal runaway state; Y j is the probability of thermal runaway state at level j.

[0118] When the calculation result of k is between (0,1), it means that the "evidence" provided by each sensor can be integrated with each other. If k=1, it means that the information provided by each sensor conflicts with each other.

[0119] The above data fusion formula can be used to obtain the degree of support of the current monitoring values ​​of multiple types of environmental parameters for each level of thermal runaway state, that is, the fusion characteristic value of multiple types of current monitoring values ​​supporting the occurrence of each level of thermal runaway state.

[0120] In this embodiment,

[0121] The fusion characteristic value of multiple types of current monitoring values ​​supporting normal operation is 0.1;

[0122] The characteristic fusion value of multiple types of current monitoring values ​​supporting the first-level thermal runaway state is 0.3;

[0123] The characteristic fusion value of multiple types of current monitoring values ​​supporting the secondary thermal runaway state is 0.2;

[0124] The characteristic fusion value of multiple types of current monitoring values ​​supporting the third-level thermal runaway state is 0.4;

[0125] S3. Determine the thermal runaway state of the energy storage device according to the fusion characteristic value that supports the occurrence of each level of thermal runaway state.

[0126] Specifically, the thermal runaway state corresponding to the largest fusion characteristic value among the fusion characteristic values ​​supporting the occurrence of each level of thermal runaway state is selected as the thermal runaway state of the energy storage device.

[0127] S4. Execute firefighting actions corresponding to the warning level of the thermal runaway state according to the determined warning level of the thermal runaway state of the energy storage device.

[0128] In this embodiment, corresponding warning information is issued according to the above judgment result to quickly handle the accident when thermal runaway occurs in the energy storage device.

[0129] Corresponding to the thermal runaway state, this embodiment provides three levels of warning information and three levels of firefighting actions;

[0130] The three-level warning information corresponds to the three-level thermal runaway state, and the three-level firefighting action corresponds to the three-level warning information: the three-level warning information includes the first-level warning information, the second-level warning information and the third-level warning information.

[0131] The specific firefighting actions are as follows:

[0132] The first-level fire fighting action is: troubleshooting and clearing the fault;

[0133] The secondary firefighting action is: cutting off the energy storage device and starting the firefighting device;

[0134] The three-level fire fighting action is: automatically cutting off the energy storage device and automatically starting the fire fighting device.

[0135] According to the above calculated characteristic fusion values ​​supporting each level of thermal runaway state, it is judged that the energy storage device is in the third level of thermal runaway state, the corresponding third level warning information is output, and the third level fire fighting action is executed.

[0136] In this embodiment, the calculation of the membership of each type of current monitoring value to each level of thermal runaway state is specifically: obtaining the membership of each type of current monitoring value to each level of thermal runaway state according to the historical monitoring values ​​of multiple types of environmental parameters when each level of thermal runaway state occurs.

[0137] In this embodiment, the multiple types of environmental parameters include ultrasonic signals, temperature signals, voltage signals, hydrogen concentration signals, carbon monoxide concentration signals, and smoke concentration signals.

[0138] Example 2

[0139] This embodiment provides a multi-sensor fusion thermal runaway warning system for an energy storage device, the system comprising:

[0140] A data acquisition module, used to collect current monitoring values ​​of various environmental parameters of the energy storage device;

[0141] The main control module stores historical monitoring values ​​of various environmental parameters of the energy storage device and is used to set the multi-level thermal runaway state of the energy storage device in a hierarchical manner;

[0142] A data fusion module is used to obtain the current monitoring values ​​of various environmental parameters of the energy storage device, perform data fusion calculations on the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state, and obtain fusion characteristic values ​​that support the occurrence of each level of thermal runaway state;

[0143] The main control module is also used to determine the thermal runaway state of the energy storage device according to the fusion characteristic value that supports the occurrence of each level of thermal runaway state.

[0144] In this embodiment, the data fusion module includes:

[0145] The initial BPA calculation unit is used to calculate the membership of various current monitoring values ​​to each level of thermal runaway state, and establish a membership state matrix. Based on the membership state matrix, the probability of various current monitoring values ​​occurring in each level of thermal runaway state is obtained to obtain the initial BPA.

[0146] Specifically, a combination of triangular and semi-trapezoidal fuzzy membership functions is used to calculate the membership of various current monitoring values ​​to each level of thermal runaway state.

[0147] Normal operation:

[0148] Level 1 thermal runaway state:

[0149] Secondary thermal runaway state:

[0150] Level 3 thermal runaway state:

[0151] In the above formulas (1) to (4), μ1 to μ4 represent the membership of the sensor to different warning states, with a value range of [0, 1]. x represents the value of the real-time output data of each sensor after preprocessing. x1 to x4 represent the classification thresholds of different levels of thermal runaway states, which are obtained from experiments on thermal runaway of different batteries.

[0152] The membership state matrix state is as follows:

[0153]

[0154] In the formula, r mn represents the output x of the mth sensor m The probability of being in state n.

[0155] In this embodiment, the membership state matrix is:

[0156]

[0157] The dynamic weight calculation unit is used to calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters according to the static weights of various environmental parameters.

[0158] In this embodiment, the dynamic weight unit includes:

[0159] A normalization processing unit, used for normalizing the current monitoring values ​​of multiple types of environmental parameters to obtain normalized measurement values;

[0160] A static weight calculation unit is used to obtain the static weights of various environmental parameters according to the hierarchical analysis method;

[0161] The dynamic weight calculation unit is used to calculate the dynamic weights of various environmental parameters according to the normalized measurement value and the static weights of various environmental parameters.

[0162] When the gas in the energy storage device escapes slowly, the energy storage system has not yet begun to truly thermally run away. At this time, a small amount of gas escapes and the temperature rises. Therefore, at this stage, the gas leakage ultrasonic monitoring data and temperature data will deviate greatly from the normal operating values, and the data output by other sensors (hydrogen concentration in the cabin, voltage, carbon monoxide concentration, etc.) have not yet detected parameter fluctuations. If all parameter sensors use conventional weight calculation methods throughout the process, the actual operating status of the energy storage system cannot be accurately reflected. In order to accurately express the thermal runaway characteristics according to different stages, a variable weighting method based on the thermal runaway development stage is established. The specific method is as follows:

[0163] Calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters based on the static weights of various environmental parameters;

[0164] In this embodiment, the static weights of various environmental parameters are calculated, and the dynamic weights of various environmental parameters are calculated according to the static weights of various environmental parameters. Specifically,

[0165] Normalize the current monitoring values ​​of multiple types of environmental parameters to obtain normalized measurement values;

[0166] The static weights of various environmental parameters are obtained according to the analytic hierarchy process;

[0167] The dynamic weights of various environmental parameters are calculated based on the normalized measured values ​​and the static weights of various environmental parameters. The calculation formula is as follows:

[0168]

[0169] Among them, ω i is the static weight of the i-th environmental parameter; T(x i ) is the normalized measured value of the current measured value of the i-th environmental parameter; α is the balancing factor used to adjust the dynamic weight; x i is the current monitoring value of the i-th category.

[0170] The BPA correction unit is used to correct the initial BPA of various current monitoring values ​​according to the dynamic weights of various environmental parameters to obtain the final BPA of various current monitoring values.

[0171] In this embodiment, the initial BPA is corrected according to the dynamic weights of multiple types of environmental parameters, and the calculation formula for obtaining the final BPA is:

[0172] m x(i) (Yj )=ω′·r ij ;

[0173] Among them, m x(i) (Y j ) is the probability that the current monitoring value of the i-th category supports the occurrence of the j-level thermal runaway state, that is, the final BPA; ω′ is the dynamic weight of the i-th category environmental parameter; r ij It is the probability that the current monitoring value of the i-th category is in the j-level thermal runaway state, that is, the initial BPA.

[0174] The data fusion unit calculates the fusion characteristic value of each level of thermal runaway state according to the final BPA of various current monitoring values.

[0175] In this embodiment, the calculation of the fusion characteristic value of each level of thermal runaway state according to the final BPA of each type of current monitoring value is specifically calculated using the following formula:

[0176]

[0177]

[0178] Among them, m(Y j ) represents the probability of occurrence of the j-level thermal runaway state after the fusion of various current monitoring values; k is the conflict coefficient, which is used to represent the conflict information between different monitoring values; x i is the current monitoring value of the i-th category; m i (x i ) is the final BPA of the current monitoring value of the i-th category under the i-th level of thermal runaway state; Y j is the probability of thermal runaway state at level j.

[0179] When the calculation result of k is between (0,1), it means that the "evidence" provided by each sensor can be integrated with each other. If k=1, it means that the information provided by each sensor conflicts with each other.

[0180] The above data fusion formula can be used to obtain the degree of support of the current monitoring values ​​of multiple types of environmental parameters for each level of thermal runaway state, that is, the fusion characteristic value of multiple types of current monitoring values ​​supporting the occurrence of each level of thermal runaway state.

[0181] In this embodiment,

[0182] The fusion characteristic value of multiple types of current monitoring values ​​supporting normal operation is 0.1;

[0183] The characteristic fusion value of multiple types of current monitoring values ​​supporting the first-level thermal runaway state is 0.3;

[0184] The characteristic fusion value of multiple types of current monitoring values ​​supporting the secondary thermal runaway state is 0.2;

[0185] The characteristic fusion value of multiple types of current monitoring values ​​supporting the third-level thermal runaway state is 0.4;

[0186] The thermal runaway state of the energy storage device is determined based on the fusion characteristic values ​​that support the occurrence of each level of thermal runaway state.

[0187] Specifically, the thermal runaway state corresponding to the largest fusion characteristic value among the fusion characteristic values ​​supporting the occurrence of each level of thermal runaway state is selected as the thermal runaway state of the energy storage device.

[0188] In this embodiment, corresponding warning information is issued according to the above judgment result to quickly handle the accident when thermal runaway occurs in the energy storage device.

[0189] Corresponding to the thermal runaway state, this embodiment provides three levels of warning information and three levels of firefighting actions;

[0190] The three-level warning information corresponds to the three-level thermal runaway state, and the three-level firefighting action corresponds to the three-level warning information: the three-level warning information includes the first-level warning information, the second-level warning information and the third-level warning information.

[0191] The specific firefighting actions are as follows:

[0192] The first-level fire fighting action is: troubleshooting and clearing the fault;

[0193] The secondary firefighting action is: cutting off the energy storage device and starting the firefighting device;

[0194] The three-level fire fighting action is: automatically cutting off the energy storage device and automatically starting the fire fighting device.

[0195] According to the above calculated characteristic fusion values ​​supporting each level of thermal runaway state, it is judged that the energy storage device is in the third level of thermal runaway state, the corresponding third level warning information is output, and the third level fire fighting action is executed.

[0196] In this embodiment, the data acquisition module includes a signal acquisition unit;

[0197] The signal acquisition unit includes: a sound sensor, a temperature sensor, a voltage sensor, a hydrogen sensor, a carbon monoxide sensor and a smoke sensor;

[0198] The sound sensor is used to collect ultrasonic signals of gas leakage;

[0199] The temperature sensor is used to detect the temperature signal of the energy storage device;

[0200] The voltage sensor is used to detect the voltage signal of the energy storage device;

[0201] The hydrogen sensor is used to detect the hydrogen concentration signal of the energy storage device;

[0202] The carbon monoxide sensor is used to detect the carbon monoxide concentration signal of the energy storage device;

[0203] The smoke sensor is used to detect the smoke concentration signal of the energy storage device.

[0204] In this embodiment, the main control module includes a thermal runaway state classification unit and a thermal runaway state judgment unit.

[0205] The thermal runaway classification unit is used to classify and set the thermal runaway state of the energy storage device; the thermal runaway state of the energy storage device is a normal operation state, a first-level thermal runaway state, a second-level thermal runaway state, and a third-level thermal runaway state;

[0206] The thermal runaway judgment unit is used to judge the thermal runaway state of the energy storage device according to the fusion characteristic value supporting the occurrence of each level of thermal runaway state.

[0207] In this embodiment, the system further includes an execution module, which executes corresponding firefighting actions according to the level of thermal runaway of the energy storage device determined by the main control module.

[0208] In this embodiment, the firefighting action includes a first-level firefighting action, a second-level firefighting action, and a third-level firefighting action;

[0209] The first-level fire fighting action is: troubleshooting and clearing the fault;

[0210] The secondary firefighting action is: cutting off the energy storage device and starting the firefighting device;

[0211] The three-level fire fighting action is: automatically cutting off the energy storage device and automatically starting the fire fighting device.

[0212] The present invention uses the acoustic signal of a small amount of gas leakage in the very early stage of thermal runaway as a criterion for determining thermal runaway of the energy storage battery, and integrates it with traditional characteristic parameters such as pressure, temperature, gas, and smoke for calculation, so as to achieve more timely and comprehensive thermal runaway warning. By calculating the integrated characteristic values ​​of different levels of thermal runaway states, the level of the thermal runaway state of the energy storage device can be judged, and targeted decisions can be made, so as to effectively respond to different levels of thermal accidents of energy storage batteries through linkage with various emergency fire fighting measures.

[0213] The ultrasonic signal is an early characteristic parameter. The present invention realizes timely early warning of thermal runaway by monitoring the early characteristic parameter.

[0214] Example 3

[0215] This embodiment provides a multi-sensor fusion thermal runaway early warning method for an energy storage device, the method comprising the following steps:

[0216] Obtain current monitoring values ​​of various environmental parameters of the energy storage device;

[0217] The multi-level thermal runaway state of the energy storage device is set in stages, and data fusion calculation is performed on the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state to obtain the fusion characteristic value that supports the occurrence of each level of thermal runaway state;

[0218] In this embodiment, the thermal runaway state of the energy storage device is divided into a normal operating state, a first-level thermal runaway state, a second-level thermal runaway state, and a third-level thermal runaway state.

[0219] The multiple types of environmental parameters include: ultrasonic signal, temperature signal, voltage signal, hydrogen concentration signal, carbon monoxide concentration signal and smoke concentration signal.

[0220] The ultrasonic signal is an ultrasonic signal of gas leakage. By collecting the ultrasonic signal of gas leakage of the energy storage device, gas leakage occurs in the earliest stage of thermal runaway of the energy storage device, and gas leakage is not easy to be monitored. Therefore, this embodiment collects the ultrasonic signal of gas leakage to achieve early control of thermal runaway of the energy storage device.

[0221] The temperature signal is used to monitor the temperature of the energy storage device; the voltage signal is used to monitor the voltage of the energy storage device; the hydrogen concentration signal is used to monitor the hydrogen concentration in the energy storage device, the carbon monoxide concentration signal is used to monitor the carbon monoxide concentration of the energy storage device; and the smoke concentration signal is used to monitor the smoke concentration of the energy storage device.

[0222] In this embodiment, the ultrasonic signal is collected by a sound sensor, the temperature signal is collected by a temperature sensor, the voltage signal is collected by a voltage sensor, the hydrogen concentration signal is collected by a hydrogen sensor, the carbon monoxide concentration signal is collected by a carbon monoxide sensor, and the smoke concentration signal is collected by a smoke sensor.

[0223] In this embodiment, the sound sensor is arranged inside the battery module of the energy storage device to measure and judge the gas leakage in the early stage of thermal runaway of the battery module; the temperature sensor is also arranged inside the battery module of the energy storage device to measure the temperature of the battery module; the voltage sensor is used to detect the voltage of the battery module; the hydrogen sensor is used to measure the hydrogen concentration signal inside the energy storage device, the carbon monoxide sensor is used to measure the carbon monoxide concentration signal inside the energy storage device, and the smoke sensor is used to measure the smoke concentration signal inside the energy storage device. The signal acquisition unit sends the above signal to the main control module, which analyzes and processes the above signal.

[0224] The existing technology only monitors the gas concentration. When the energy storage system is operating normally, if there is warning gas in the air at this time, it may be interfered by the gas in the air, resulting in false alarms; the gas leakage concentration of the energy storage device before complete thermal runaway is low, and it is easy to miss alarms in the early stage. In the above two cases, placing the sound sensor, hydrogen sensor, carbon monoxide sensor and smoke sensor on the surface of the battery module can quickly identify the sound of gas leakage, avoid false alarms and miss alarms caused by a single sensor, and achieve early warning of thermal runaway.

[0225] Among them, the normal operating status indicates that the current monitoring values ​​of multiple types of environmental parameters of the energy storage device are within the normal operating threshold.

[0226] The first-level thermal runaway state indicates that the body temperature of the energy storage device rises, abnormal batteries emit smoke, and temperature and ultrasonic sensors respond.

[0227] The secondary thermal runaway state indicates that the body temperature of the energy storage device rises rapidly, a large amount of smoke escapes, and the hydrogen sensor, carbon monoxide sensor, and voltage sensor respond.

[0228] The third-level thermal runaway state indicates that thermal runaway reactions continue to occur inside the energy storage device, producing a large amount of smoke and causing the smoke sensor to respond.

[0229] In this embodiment, the data fusion calculation of multiple types of monitoring results according to the multi-level thermal runaway state is specifically as follows:

[0230] The membership of each type of current monitoring value to each level of thermal runaway state is calculated, and a membership state matrix is ​​established. Based on the membership state matrix, the probability of each type of current monitoring value occurring in each level of thermal runaway state is obtained, which is recorded as the initial BPA.

[0231] In this embodiment, the degree of membership of each type of current monitoring value to each level of thermal runaway state is calculated as follows:

[0232] The membership of each type of current monitoring value to each level of thermal runaway state is calculated by combining triangular and semi-trapezoidal fuzzy membership functions.

[0233] In this embodiment, the membership state matrix is:

[0234]

[0235] When the gas in the energy storage device escapes slowly, the energy storage system has not yet begun to truly thermally run away. At this time, a small amount of gas escapes and the temperature rises. Therefore, at this stage, the gas leakage ultrasonic monitoring data and temperature data will deviate greatly from the normal operating values, and the data output by other sensors (hydrogen concentration in the cabin, voltage, carbon monoxide concentration, etc.) have not yet detected parameter fluctuations. If all parameter sensors use conventional weight calculation methods throughout the process, the actual operating status of the energy storage system cannot be accurately reflected. In order to accurately express the thermal runaway characteristics according to different stages, a variable weighting method based on the thermal runaway development stage is established. The specific method is as follows:

[0236] Calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters based on the static weights of various environmental parameters;

[0237] In this embodiment, the static weights of various environmental parameters are calculated, and the dynamic weights of various environmental parameters are calculated according to the static weights of various environmental parameters. Specifically,

[0238] Normalize the current monitoring values ​​of multiple types of environmental parameters to obtain normalized measurement values;

[0239] The static weights of various environmental parameters are obtained according to the analytic hierarchy process;

[0240] The dynamic weights of various environmental parameters are calculated based on the normalized measured values ​​and the static weights of various environmental parameters. The calculation formula is as follows:

[0241]

[0242] Among them, ω i is the static weight of the i-th environmental parameter; T(x i ) is the normalized measured value of the current measured value of the i-th environmental parameter; α is the balancing factor used to adjust the dynamic weight; x i is the current monitoring value of the i-th category.

[0243] The initial BPA is corrected according to the dynamic weights of various environmental parameters to obtain the final BPA;

[0244] According to the final BPA of each type of current monitoring value, the fusion characteristic value of each level of thermal runaway state is calculated.

[0245] In this embodiment, the initial BPA of each current monitoring value is corrected according to the dynamic weight of each environmental parameter, and the calculation formula for obtaining the final BPA of each current monitoring value is:

[0246] m x(i) (Y j )=ω′·r ij ;

[0247] Among them, m x(i) (Y j ) is the probability that the current monitoring value of the i-th category supports the occurrence of the j-level thermal runaway state, that is, the final BPA of the current monitoring value of the i-th category; ω′ is the dynamic weight of the current monitoring value of the i-th category; r ij is the probability that the current monitoring value of the i-th category is in the j-level thermal runaway state, that is, the initial BPA of the current monitoring value of the i-th category.

[0248] In this embodiment, the calculation of the fusion characteristic value of each level of thermal runaway state according to the final BPA of each type of current monitoring value is specifically calculated using the following formula:

[0249]

[0250]

[0251] Among them, m(Y j ) represents the probability of occurrence of the j-level thermal runaway state after the fusion of various current monitoring values; k is the conflict coefficient, which is used to represent the conflict information between different monitoring values; x i is the current monitoring value of the i-th category; m i (x i ) is the final BPA of the current monitoring value of the i-th category under the i-th level of thermal runaway state; Y j is the probability of thermal runaway state at level j.

[0252] When the calculation result of k is between (0,1), it means that the "evidence" provided by each sensor can be integrated with each other. If k=1, it means that the information provided by each sensor conflicts with each other.

[0253] The above data fusion formula can be used to obtain the degree of support of the current monitoring values ​​of multiple types of environmental parameters for each level of thermal runaway state, that is, the fusion characteristic value of multiple types of current monitoring values ​​supporting the occurrence of each level of thermal runaway state.

[0254] In this embodiment,

[0255] The fusion characteristic value of multiple types of current monitoring values ​​supporting normal operation is 0.1;

[0256] The characteristic fusion value of multiple types of current monitoring values ​​supporting the first-level thermal runaway state is 0.2;

[0257] The characteristic fusion value of multiple types of current monitoring values ​​supporting the secondary thermal runaway state is 0.2;

[0258] The characteristic fusion value of multiple types of current monitoring values ​​supporting the third-level thermal runaway state is 0.2;

[0259] The characteristic fusion value of multiple types of current monitoring values ​​supporting the fourth level of thermal runaway state is 0.3;

[0260] The thermal runaway state of the energy storage device is determined based on the fusion characteristic values ​​that support the occurrence of each level of thermal runaway state.

[0261] Specifically, the thermal runaway state corresponding to the largest fusion characteristic value among the fusion characteristic values ​​supporting the occurrence of each level of thermal runaway state is selected as the thermal runaway state of the energy storage device.

[0262] In this embodiment, corresponding warning information is issued according to the above judgment result to quickly handle the accident when thermal runaway occurs in the energy storage device.

[0263] Corresponding to the thermal runaway state, this embodiment provides four levels of warning information and four levels of firefighting actions;

[0264] The four-level warning information corresponds to the four-level thermal runaway state, and the four-level firefighting action corresponds to the four-level warning information: the four-level warning information includes the first-level warning information, the second-level warning information, the third-level warning information and the fourth-level warning information.

[0265] The specific firefighting actions are as follows:

[0266] The first-level firefighting action is to notify personnel to conduct early troubleshooting, and reset the sound sensor and temperature sensor after a delay of 2 minutes respectively. The sound sensor and temperature sensor will start working again and monitor the ultrasonic signal and temperature signal of the energy storage device in real time.

[0267] The specific secondary firefighting actions are: automatically cut off the power supply to the energy storage device, based on the troubleshooting of the energy storage device;

[0268] The specific actions of the third-level firefighting are: automatically cutting off the power supply of the energy storage device and manually starting the firefighting device to carry out local firefighting for the faults found.

[0269] The specific actions of the fourth level fire fighting are: automatically cutting off the power supply of the energy storage device, and automatically starting the fire fighting device, and performing fire fighting actions on the energy storage device through the fire fighting device.

[0270] According to the above calculated characteristic fusion values ​​supporting each level of thermal runaway state, it is judged that the energy storage device is in a level 4 thermal runaway state, the corresponding level 4 warning information is output, and the level 4 fire fighting action is executed.

[0271] In this embodiment, the multiple types of environmental parameters include ultrasonic signals, temperature signals, voltage signals, hydrogen concentration signals, carbon monoxide concentration signals, and smoke concentration signals.

[0272] Example 4

[0273] An embodiment of the present application provides an electronic device, the device including a processor, a memory, and a program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program:

[0274] Obtain current monitoring values ​​of various environmental parameters of the energy storage device;

[0275] The multi-level thermal runaway state of the energy storage device is set in stages, and data fusion calculation is performed on the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state to obtain the fusion characteristic value that supports the occurrence of each level of thermal runaway state;

[0276] The thermal runaway state of the energy storage device is determined based on the fusion characteristic values ​​that support the occurrence of each level of thermal runaway state.

[0277] In this embodiment, the data fusion calculation of the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state is specifically as follows:

[0278] Calculate the membership of each current monitoring value to each level of thermal runaway state, establish a membership state matrix, and obtain the probability of each current monitoring value occurring in each level of thermal runaway state based on the membership state matrix, which is recorded as the initial BPA;

[0279] Calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters based on the static weights of various environmental parameters;

[0280] The initial BPA of each current monitoring value is corrected according to the dynamic weights of each environmental parameter to obtain the final BPA of each current monitoring value;

[0281] According to the final BPA of each type of current monitoring value, the fusion characteristic value of each level of thermal runaway state is calculated.

[0282] In this embodiment, the static weights of various environmental parameters are calculated, and the dynamic weights of various environmental parameters are calculated according to the static weights of various environmental parameters. Specifically,

[0283] Normalize the current monitoring values ​​of various environmental parameters to obtain normalized measurement values;

[0284] The static weights of various environmental parameters are obtained according to the analytic hierarchy process;

[0285] Calculate the dynamic weights ω of various environmental parameters based on the normalized measured values ​​and the static weights of various environmental parameters i ′, the calculation formula is as follows:

[0286]

[0287] Among them, ω i is the static weight of the i-th category monitoring value; x i is the current monitoring value of the i-th category, T(x i ) is the normalized measurement value of the i-th category monitoring value; α is the balancing factor, which is used to adjust the dynamic weight.

[0288] In this embodiment, the initial BPA of each current monitoring value is corrected according to the dynamic weight of each environmental parameter, and the calculation formula for obtaining the final BPA of each current monitoring value is:

[0289] m x(i) (Y j )=ω′·r ij ;

[0290] Among them, m x(i) (Y j ) is the probability that the current monitoring value of the i-th category supports the occurrence of the j-level thermal runaway state, that is, the final BPA of the current monitoring value of the i-th category; ω′ is the dynamic weight of the current monitoring value of the i-th category; r ij is the probability that the current monitoring value of the i-th category is in the j-level thermal runaway state, that is, the initial BPA of the current monitoring value of the i-th category.

[0291] Preferably, the calculation of the fusion characteristic value of each level of thermal runaway state according to the final BPA of each type of current monitoring value is specifically calculated by the following formula:

[0292]

[0293]

[0294] Among them, m(Y j ) represents the probability of occurrence of the j-level thermal runaway state after the fusion of multiple types of current monitoring values; k is the conflict coefficient, which is used to represent the conflict information between different monitoring values; x i is the current monitoring value of the i-th category; m i (x i ) is the final BPA of the current monitoring value of the i-th category under the i-th level of thermal runaway state; Y j is the probability of thermal runaway state at level j.

[0295] In this embodiment, the environmental parameters include an ultrasonic signal, a temperature signal, a voltage signal, a hydrogen concentration signal, a carbon monoxide concentration signal, and a smoke concentration signal.

[0296] In this embodiment, the method further includes: executing a firefighting action corresponding to the level of the thermal runaway state according to the determined level of the thermal runaway state of the energy storage device.

[0297] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0298] Example 5

[0299] The present application provides a computer-readable storage medium storing computer instructions, wherein when the computer instructions are executed on a computer, the computer implements the following method:

[0300] Obtain current monitoring values ​​of various environmental parameters of the energy storage device;

[0301] The multi-level thermal runaway state of the energy storage device is set in stages, and data fusion calculation is performed on the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state to obtain the fusion characteristic value that supports the occurrence of each level of thermal runaway state;

[0302] The thermal runaway state of the energy storage device is determined based on the fusion characteristic values ​​that support the occurrence of each level of thermal runaway state.

[0303] In this embodiment, the data fusion calculation of the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state is specifically as follows:

[0304] Calculate the membership of each current monitoring value to each level of thermal runaway state, establish a membership state matrix, and obtain the probability of each current monitoring value occurring in each level of thermal runaway state based on the membership state matrix, which is recorded as the initial BPA;

[0305] Calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters based on the static weights of various environmental parameters;

[0306] The initial BPA of each current monitoring value is corrected according to the dynamic weights of each environmental parameter to obtain the final BPA of each current monitoring value;

[0307] According to the final BPA of each type of current monitoring value, the fusion characteristic value of each level of thermal runaway state is calculated.

[0308] In this embodiment, the static weights of various environmental parameters are calculated, and the dynamic weights of various environmental parameters are calculated according to the static weights of various environmental parameters. Specifically,

[0309] Normalize the current monitoring values ​​of various environmental parameters to obtain normalized measurement values;

[0310] The static weights of various environmental parameters are obtained according to the analytic hierarchy process;

[0311] Calculate the dynamic weights ω of various environmental parameters based on the normalized measured values ​​and the static weights of various environmental parameters i ′, the calculation formula is as follows:

[0312]

[0313] Among them, ω i is the static weight of the i-th category monitoring value; x i is the current monitoring value of the i-th category, T(x i ) is the normalized measurement value of the i-th category monitoring value; α is the balancing factor, which is used to adjust the dynamic weight.

[0314] In this embodiment, the initial BPA of each current monitoring value is corrected according to the dynamic weight of each environmental parameter, and the calculation formula for obtaining the final BPA of each current monitoring value is:

[0315] m x(i) (Y j )=ω′·r ij ;

[0316] Among them, m x(i) (Y j ) is the probability that the current monitoring value of the i-th category supports the occurrence of the j-level thermal runaway state, that is, the final BPA of the current monitoring value of the i-th category; ω′ is the dynamic weight of the current monitoring value of the i-th category; r ij is the probability that the current monitoring value of the i-th category is in the j-level thermal runaway state, that is, the initial BPA of the current monitoring value of the i-th category.

[0317] In this embodiment, the calculation of the fusion characteristic value of each level of thermal runaway state according to the final BPA of each type of current monitoring value is specifically calculated using the following formula:

[0318]

[0319]

[0320] Among them, m(Y j ) represents the probability of occurrence of the j-level thermal runaway state after the fusion of multiple types of current monitoring values; k is the conflict coefficient, which is used to represent the conflict information between different monitoring values; x i is the current monitoring value of the i-th category; m i (x i ) is the final BPA of the current monitoring value of the i-th category under the i-th level of thermal runaway state; Y j is the probability of thermal runaway state at level j.

[0321] In this embodiment, the environmental parameters include an ultrasonic signal, a temperature signal, a voltage signal, a hydrogen concentration signal, a carbon monoxide concentration signal, and a smoke concentration signal.

[0322] In this embodiment, the method further includes: executing a firefighting action corresponding to the level of the thermal runaway state according to the determined level of the thermal runaway state of the energy storage device.

[0323] Those skilled in the art will understand that all or part of the steps in the method for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a single-chip microcomputer, a chip or a processor (processor) perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0324] The optional embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the technical concept of the embodiments of the present invention, the technical scheme of the embodiments of the present invention can be subjected to a variety of simple modifications, and these simple modifications all belong to the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In addition, the various different embodiments of the present invention can also be arbitrarily combined, as long as they do not violate the ideas of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A multi-sensor fusion thermal runaway early warning method for energy storage device, characterized in that: The method comprises the following steps: Obtain current monitoring values ​​of various environmental parameters of the energy storage device; The multi-level thermal runaway state of the energy storage device is set in stages, and data fusion calculation is performed on the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state to obtain the fusion characteristic value that supports the occurrence of each level of thermal runaway state; The thermal runaway state of the energy storage device is determined based on the fusion characteristic values ​​that support the occurrence of each level of thermal runaway state.

2. The multi-sensor fusion thermal runaway early warning method for energy storage device according to claim 1, characterized in that: The data fusion calculation of the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state is specifically as follows: Calculate the membership of each current monitoring value to each level of thermal runaway state, establish a membership state matrix, and obtain the probability of each current monitoring value occurring in each level of thermal runaway state based on the membership state matrix, which is recorded as the initial BPA; Calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters based on the static weights of various environmental parameters; The initial BPA of each current monitoring value is corrected according to the dynamic weights of each environmental parameter to obtain the final BPA of each current monitoring value; According to the final BPA of each type of current monitoring value, the fusion characteristic value of each level of thermal runaway state is calculated.

3. The multi-sensor fusion thermal runaway early warning method for energy storage device according to claim 2 is characterized in that: The static weights of various environmental parameters are calculated, and the dynamic weights of various environmental parameters are calculated according to the static weights of various environmental parameters. Specifically, Normalize the current monitoring values ​​of various environmental parameters to obtain normalized measurement values; The static weights of various environmental parameters are obtained according to the analytic hierarchy process; Calculate the dynamic weights ω of various environmental parameters based on the normalized measured values ​​and the static weights of various environmental parameters i ′, the calculation formula is as follows: Among them, ω i is the static weight of the i-th category monitoring value; x i is the current monitoring value of the i-th category, T(x i ) is the normalized measurement value of the i-th category monitoring value; α is the balancing factor, which is used to adjust the dynamic weight.

4. The multi-sensor fusion thermal runaway early warning method for energy storage device according to claim 3 is characterized in that: The initial BPA of each current monitoring value is corrected according to the dynamic weights of various environmental parameters, and the calculation formula for obtaining the final BPA of each current monitoring value is: m x(i) (Y j )=ω′·r ij ; Among them, m x(i) (Y j ) is the probability that the current monitoring value of the i-th category supports the occurrence of the j-level thermal runaway state, that is, the final BPA of the current monitoring value of the i-th category; ω′ is the dynamic weight of the current monitoring value of the i-th category; r ij is the probability that the current monitoring value of the i-th category is in the j-level thermal runaway state, that is, the initial BPA of the current monitoring value of the i-th category.

5. The multi-sensor fusion thermal runaway early warning method for energy storage device according to claim 4 is characterized in that: The calculation of the fusion characteristic value of each level of thermal runaway state based on the final BPA of each type of current monitoring value is specifically calculated using the following formula: Among them, m(Y j ) represents the probability of occurrence of the j-level thermal runaway state after the fusion of various current monitoring values; k is the conflict coefficient, which is used to represent the conflict information between different monitoring values; x i is the current monitoring value of the i-th category; m i (x i ) is the final BPA of the current monitoring value of the i-th category under the i-th level of thermal runaway state; Y j is the probability of thermal runaway state at level j.

6. The multi-sensor fusion thermal runaway early warning method for energy storage device according to claim 2, characterized in that: The calculation of the membership of each type of current monitoring value to each level of thermal runaway state is specifically as follows: According to the historical monitoring values ​​of various environmental parameters when each level of thermal runaway state occurs, the membership degree of various current monitoring values ​​to each level of thermal runaway state is obtained.

7. The thermal runaway early warning method of the multi-sensor fusion energy storage device according to claim 1 is characterized in that: The environmental parameters include ultrasonic signals, temperature signals, voltage signals, hydrogen concentration signals, carbon monoxide concentration signals, and smoke concentration signals.

8. The multi-sensor fusion thermal runaway early warning method for energy storage device according to claim 1, characterized in that: The method further comprises: According to the determined level of the thermal runaway state of the energy storage device, a firefighting action corresponding to the level of the thermal runaway state is executed.

9. A multi-sensor fusion thermal runaway warning system for energy storage devices, characterized in that: The system comprises: A data acquisition module, used to collect current monitoring values ​​of various environmental parameters of the energy storage device; The main control module stores historical monitoring values ​​of various environmental parameters of the energy storage device and is used to set the multi-level thermal runaway state of the energy storage device in a hierarchical manner; A data fusion module is used to obtain the current monitoring values ​​of various environmental parameters of the energy storage device, perform data fusion calculations on the current monitoring values ​​of various environmental parameters according to the multi-level thermal runaway state, and obtain fusion characteristic values ​​that support the occurrence of each level of thermal runaway state; The main control module is also used to determine the thermal runaway state of the energy storage device according to the fusion characteristic value that supports the occurrence of each level of thermal runaway state.

10. The multi-sensor fusion energy storage device thermal runaway warning system according to claim 9, characterized in that: The data fusion module comprises: The initial BPA calculation unit is used to calculate the membership of various current monitoring values ​​to each level of thermal runaway state, establish a membership state matrix, obtain the probability of various current monitoring values ​​occurring in each level of thermal runaway state based on the membership state matrix, and obtain the initial BPA; A dynamic weight calculation unit, used to calculate the static weights of various environmental parameters, and calculate the dynamic weights of various environmental parameters according to the static weights of various environmental parameters; A BPA correction unit, used to correct the initial BPA of various current monitoring values ​​according to the dynamic weights of various environmental parameters to obtain the final BPA of various current monitoring values; The data fusion unit is used to calculate the fusion characteristic value of each level of thermal runaway state according to the final BPA of various current monitoring values.

11. The multi-sensor fusion energy storage device thermal runaway warning system according to claim 10, characterized in that: The dynamic weight unit comprises: A normalization processing unit is used to normalize the current monitoring values ​​of various environmental parameters to obtain normalized measurement values; A static weight calculation unit is used to obtain the static weights of various environmental parameters according to the analytic hierarchy process; The dynamic weight calculation unit is used to calculate the dynamic weights of various environmental parameters according to the normalized measurement value and the static weights of various environmental parameters.

12. The multi-sensor fusion energy storage device thermal runaway warning system according to claim 9, characterized in that: The environmental parameters include ultrasonic signals, temperature signals, voltage signals, hydrogen concentration signals, carbon monoxide concentration signals and smoke concentration signals; the data acquisition module includes a signal acquisition unit; the signal acquisition unit includes: Sound sensor, used to collect ultrasonic signals of gas leakage; A temperature sensor, used to detect a temperature signal of the energy storage device; A voltage sensor, used to detect a voltage signal of the energy storage device; A hydrogen sensor, used to detect the hydrogen concentration signal of the energy storage device; A carbon monoxide sensor, used to detect a carbon monoxide concentration signal of an energy storage device; The smoke sensor is used to detect the smoke concentration signal of the energy storage device.

13. The multi-sensor fusion energy storage device thermal runaway warning system according to claim 9, characterized in that: The main control module includes a thermal runaway state classification unit and a thermal runaway state judgment unit. The thermal runaway classification unit is used to set the thermal runaway state of the energy storage device in a graded manner; The thermal runaway state of the energy storage device is a normal operating state, a first-level thermal runaway state, a second-level thermal runaway state, and a third-level thermal runaway state; The thermal runaway judgment unit is used to judge the thermal runaway state of the energy storage device according to the fusion characteristic value supporting the occurrence of each level of thermal runaway state.

14. The multi-sensor fusion energy storage device thermal runaway warning system according to claim 9, characterized in that: The system further comprises an execution module, which is used to execute corresponding firefighting actions according to the level of thermal runaway state of the energy storage device determined by the main control module.

15. The multi-sensor fusion energy storage device thermal runaway warning system according to claim 14, characterized in that: The firefighting actions include first-level firefighting actions, second-level firefighting actions and third-level firefighting actions; The first-level fire fighting action is: troubleshooting and clearing the fault; The secondary firefighting action is: cutting off the energy storage device and starting the firefighting device; The three-level fire fighting action is: automatically cutting off the energy storage device and automatically starting the fire fighting device.

16. A computer-readable storage medium storing computer instructions, characterized in that: When the computer instructions are executed on a computer, the computer executes the thermal runaway warning method for an energy storage device using multi-sensor fusion as described in any one of claims 1 to 8.

17. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the multi-sensor fusion energy storage device thermal runaway warning method according to any one of claims 1 to 8 is implemented.

Citation Information

Cited By

  • Thermal runaway early warning threshold calculation method and device and thermal runaway early warning method based on fuzzy logic

    CN119538054A

  • Mining area environment monitoring method and system

    CN120218424A

  • Energy storage equipment safety protection early warning system applied to industrial park

    CN120689968A

  • Energy storage device safety protection early warning system applied to industrial park

    CN120689968B