Lithium battery thermal runaway detection system based on multi-sensor fusion

Abstract

The invention discloses a multi-sensor fused lithium battery thermal runaway detection system, and relates to the technical field of lithium batteries, comprising: deploying a miniature NTC sensor, a multi-gas sensor array, a photoelectric smoke sensor and a voiceprint recognition sensor in a lithium battery; the operation data of the lithium battery is detected in real time based on a thermal runaway test method, and the thermal runaway of the lithium battery is detected; the method is used for solving the problems that in an existing lithium battery thermal runaway detection system, simple logic superposition is generally adopted for the detection result of a composite sensor, time sequence correlation analysis and a multi-source data fusion algorithm are lacked, and even if part of detection data is accurately obtained through the sensor, collaborative analysis of multi-dimensional characteristic signals is lacked, and therefore the detection result of the composite sensor cannot be accurately detected. And the thermal runaway of the lithium battery cannot be effectively judged.

Description

Technical Field

[0001] The present invention relates to the technical field of lithium batteries, and in particular to a multi-sensor fusion lithium battery thermal runaway detection system. Background Art

[0002] Lithium batteries are an energy device widely used in modern life. Their core component contains lithium, whether it is metallic lithium, lithium alloy, lithium ion, or lithium polymer, they are all indispensable components; lithium battery thermal runaway refers to the chain reaction phenomenon that occurs in lithium batteries under specific conditions, causing the battery temperature to rise sharply and may cause fire or explosion; its mechanism mainly includes the decomposition of the solid electrolyte interface film, the reaction of positive and negative active substances with the electrolyte, the decomposition of the electrolyte itself, and the reaction of the negative active substance with the binder.

[0003] Existing methods for detecting thermal runaway of lithium batteries usually improve the accuracy of data collection and the detection accuracy of detectors in data collection of multiple sensors, such as by adjusting the angle between the detection light sources and the color of the detection light sources to optimize the detection. Although this improvement method can improve the accuracy of data detection, it usually uses simple logical superposition for the detection results of composite sensors, lacks time series correlation analysis and multi-source data fusion algorithms, and cannot distinguish between normal charging and discharging temperature rise and thermal runaway precursors. At the same time, there is a lack of data detection of the pressure relief valve. As a result, even if some detection data is accurately obtained through the sensor, the lack of coordinated analysis of multi-dimensional characteristic signals will still cause the problem of being unable to effectively judge the thermal runaway of the lithium battery. For example, in the patent application with publication number CN119087263A, a multi-data fusion lithium battery thermal runaway detector is disclosed. and detection method, this solution is to improve the detection accuracy of the lithium battery thermal runaway detector by optimizing the luminescence of the dual-band dual-path smoke sensor, the angle between the first full-band photodiode and the detection light source, and the angle between the second full-band photodiode and the detection light source. Other improvements for lithium battery thermal runaway detection are usually detection in a single sensor, which still cannot solve the problem that the detection results of the composite sensor usually adopt simple logical superposition, lack of time series correlation analysis and multi-source data fusion algorithm, and cannot distinguish between normal charging and discharging temperature rise and thermal runaway precursors. At the same time, there is a lack of data detection of the pressure relief valve, resulting in the problem that even if some detection data is accurately obtained through the sensor, the thermal runaway of the lithium battery cannot be effectively judged due to the lack of coordinated analysis of multi-dimensional characteristic signals. In view of this, it is necessary to improve the existing lithium battery thermal runaway detection method. Summary of the Invention

[0004] The present invention aims to solve at least one of the technical problems in the prior art to a certain extent. By proposing a multi-sensor fusion lithium battery thermal runaway detection system, it is used to solve the problem that in the existing lithium battery thermal runaway detection system, the detection results of the composite sensor are usually treated with simple logical superposition, lacking time series correlation analysis and multi-source data fusion algorithm, and cannot distinguish between normal charging and discharging temperature rise and thermal runaway precursors. At the same time, there is a lack of data detection of the pressure relief valve. As a result, even if some detection data is accurately obtained through the sensor, the lack of coordinated analysis of multi-dimensional characteristic signals will still make it impossible to effectively judge the thermal runaway of the lithium battery.

[0005] To achieve the above objectives, the present application provides a multi-sensor fusion lithium battery thermal runaway detection system, including a multi-level hardware deployment module, a thermal runaway test and data acquisition module, and a thermal runaway detection module;

[0006] The multi-level hardware deployment module is used to deploy micro NTC sensors, multi-gas sensor arrays, photoelectric smoke sensors, and voiceprint recognition sensors within lithium batteries. The multi-gas sensor array includes electrochemical CO sensors, semiconductor H2 sensors, and semiconductor VOC sensors.

[0007] The thermal runaway test and data acquisition module is used to test the thermal runaway of lithium batteries using the thermal runaway test method based on sensors deployed in the lithium battery, and obtain the standard temperature slope, CO judgment standard, H2 judgment standard, VOC judgment standard, density judgment standard, decibel judgment standard and width judgment standard based on the test results;

[0008] The thermal runaway detection module is used to perform real-time detection of the operating data of the lithium battery based on sensors deployed in the lithium battery, and to detect thermal runaway of the lithium battery based on the detection results and the thermal runaway judgment algorithm.

[0009] Furthermore, the multi-level hardware deployment module includes multiple hardware deployment units, each of which is configured with multiple hardware deployment strategies and a data acquisition board. The multiple hardware deployment strategies are used to deploy multiple sensors, and the data acquisition board is used to receive sensor data from multiple sensors. The multiple hardware deployment strategies include:

[0010] Obtain a prismatic cell of a lithium battery, and embed a micro NTC sensor inside the prismatic cell of the lithium battery, wherein the micro NTC sensor is connected to a data acquisition board via a flexible PCB;

[0011] A lithium battery module is obtained, and a multi-gas sensor array is installed at the vent of the battery module, wherein the multi-gas sensor array is connected to a data acquisition board via a flexible PCB.

[0012] Furthermore, the multi-hardware deployment strategy also includes:

[0013] Obtain an area within the space where the lithium battery pressure relief valve is located where a voiceprint recognition module can be deployed, and record this area as the voiceprint placement area. Deploy a MEMS microphone array within the voiceprint placement area, where the MEMS microphone array consists of three voiceprint recognition modules forming an equilateral triangle.

[0014] Deploy photoelectric smoke sensors in the space where the lithium battery is located.

[0015] Furthermore, the thermal runaway test and data acquisition module includes a thermal runaway test unit and a data acquisition and analysis unit. The thermal runaway test unit is configured with a thermal runaway test strategy, which includes:

[0016] Perform multiple thermal runaway tests on the lithium battery deployed through the multi-level hardware deployment module using a thermal runaway test method, and send the multiple test results to a data acquisition and analysis unit;

[0017] The thermal runaway test method is to place the lithium battery in a standard experimental environment and conduct a simulated thermal runaway test on the lithium battery. The simulated thermal runaway test is used to simulate the thermal runaway of the lithium battery, and the experimental process based on the time sequence includes the initial stage of thermal runaway latency, the thermal runaway trigger period and the violent reaction period.

[0018] The data obtained by the micro NTC sensor, multi-gas sensor array, photoelectric smoke sensor and voiceprint recognition sensor during the thermal runaway latent stage, thermal runaway trigger stage and violent reaction stage of the simulated thermal runaway experiment are respectively obtained and recorded as a test result of the thermal runaway test method.

[0019] Furthermore, the data collection and analysis unit is configured with a data collection and analysis strategy, which includes:

[0020] For any test result sent by the thermal runaway test unit: For the test result of the micro NTC sensor: establish a plane rectangular coordinate system, recorded as the temperature sensing coordinate system, where the unit of the X-axis of the temperature sensing coordinate system is min, and the unit of the Y-axis is ℃; based on the test result of the micro NTC sensor, draw a corresponding curve in the temperature sensing coordinate system, and record it as the temperature test curve, and record the slope of the point with the horizontal coordinate T1 in the temperature test curve as the temperature runaway slope, where T1 is the time when the thermal runaway trigger period starts.

[0021] Furthermore, the data collection and analysis strategy also includes:

[0022] For the test results of the multi-gas sensor array: establish a plane rectangular coordinate system, recorded as the gas sensor coordinate system, where the unit of the X-axis of the gas sensor coordinate system is min, and the unit of the Y-axis is ppm or ppb; based on the test results of the multi-gas sensor array, draw the curves corresponding to the electrochemical CO sensor, semiconductor H2 sensor, and semiconductor VOC sensor in the gas sensor coordinate system, and record them as the CO test curve, H2 test curve, and VOC test curve, respectively, where the unit of the Y-axis of the CO test curve and the H2 test curve is ppm, and the unit of the Y-axis of the VOC test curve is ppb;

[0023] Obtain the threshold values ​​corresponding to the gas anomaly judgment criteria for CO, H2, and VOC, respectively, and record them as Y1, Y2, and Y3, respectively. Record the points with ordinates Y1, Y2, and Y3 in the CO test curve, H2 test curve, and VOC test curve as CO anomaly points, H2 anomaly points, and VOC anomaly points, respectively. Record the points with abscissas T1 in the CO test curve, H2 test curve, and VOC test curve as CO out-of-control points, H2 out-of-control points, and VOC out-of-control points, respectively.

[0024] The point corresponding to the minimum value of the horizontal coordinate between the CO abnormal point and the CO out-of-control point is recorded as the CO judgment point; the point corresponding to the minimum value of the horizontal coordinate between the H2 abnormal point and the H2 out-of-control point is recorded as the H2 judgment point; the point corresponding to the minimum value of the horizontal coordinate between the VOC abnormal point and the VOC out-of-control point is recorded as the VOC judgment point.

[0025] Furthermore, the data collection and analysis strategy also includes:

[0026] For the test results of the photoelectric smoke sensor: the smoke density detected by the photoelectric smoke sensor at the beginning of the thermal runaway trigger period is recorded as the thermal runaway density.

[0027] Furthermore, the data collection and analysis strategy also includes:

[0028] For the test results of the voiceprint recognition sensor: the decibel and pulse width obtained by matching the MEMS microphone array at the beginning of the thermal runaway trigger period are recorded as the thermal runaway decibel and thermal runaway width.

[0029] Furthermore, the data collection and analysis strategy also includes:

[0030] Based on multiple test results sent by the thermal runaway test unit, the average value of the temperature runaway slopes obtained in all test results is recorded as the standard temperature slope; the average value of the vertical coordinates of the CO judgment points in all test results is recorded as the CO judgment standard; the average value of the vertical coordinates of the H2 judgment points in all test results is recorded as the H2 judgment standard; the average value of the vertical coordinates of the VOC judgment points in all test results is recorded as the VOC judgment standard; the average value of the thermal runaway density in all test results is recorded as the density judgment standard; the average values ​​of the thermal runaway decibels and thermal runaway widths in all test results are recorded as the decibel judgment standard and the width judgment standard, respectively.

[0031] Furthermore, the thermal runaway detection module is configured with a thermal runaway detection unit, and the thermal runaway detection unit is configured with a thermal runaway detection strategy, which includes:

[0032] When the lithium battery is operating, the operating data of the lithium battery is detected in real time based on the sensors deployed in the lithium battery, and the thermal runaway judgment algorithm is used in real time to obtain the thermal runaway judgment parameters. The thermal runaway judgment algorithm is: Wherein, F is the thermal runaway judgment parameter, a1 is the latest slope of the curve corresponding to the test results of the micro-NTC sensor obtained in real time based on the temperature sensing coordinate system, and a0 is the standard temperature slope; b1, c1, and d1 are the test results of the electrochemical CO sensor, semiconductor H2 sensor, and semiconductor VOC sensor obtained in real time, respectively, and b0, c0, and d0 are the CO judgment standard, H2 judgment standard, and VOC judgment standard, respectively; e1 is the smoke density obtained in real time based on the photoelectric smoke sensor, and e0 is the density judgment standard; f1 and g1 are the decibel and pulse width obtained in real time based on the MEMS microphone array, and f0 and g0 are the decibel judgment standard and pulse width judgment standard respectively;

[0033] When F is greater than or equal to 1, the thermal runaway state of the lithium battery is determined to be thermal runaway;

[0034] When F is less than 1, the thermal runaway state of the lithium battery is determined to be non-existent.

[0035] Beneficial effects of the present invention: The present application first deploys a micro NTC sensor, a multi-gas sensor array, a photoelectric smoke sensor, and a voiceprint recognition sensor in a lithium battery; then, based on the sensors deployed in the lithium battery, the thermal runaway of the lithium battery is tested, and based on the test results, the standard temperature slope, CO judgment standard, H2 judgment standard, VOC judgment standard, density judgment standard, decibel judgment standard, and width judgment standard are obtained; finally, based on the sensors deployed in the lithium battery, the operating data of the lithium battery is detected in real time, and the thermal runaway of the lithium battery is detected based on the detection results and the thermal runaway judgment algorithm. The advantage of this is that by deploying a micro NTC sensor, Multi-gas sensor arrays and photoelectric smoke sensors can perform diversified detection of thermal runaway of lithium batteries, improving the accuracy of thermal runaway detection from multiple detection angles. At the same time, by adding voiceprint recognition sensors, the lack of data detection on the pressure relief valve in existing improvements can be compensated, thereby making the detection of composite sensors more comprehensive. At the same time, through the thermal runaway test method, the judgment criteria corresponding to multiple test results are obtained and the thermal runaway of lithium batteries is detected based on the test results and the thermal runaway judgment algorithm. This can improve the accuracy of the judgment of lithium battery thermal runaway through multi-dimensional data, thereby preventing the problem of ineffective judgment of lithium battery thermal runaway due to the lack of collaborative analysis of multi-dimensional characteristic signals. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 is a functional block diagram of the system of the present invention;

[0037] Figure 2 Schematic diagram of the hardware deployment and detection process of the present invention. DETAILED DESCRIPTION

[0038] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0039] See also Figure 1 As shown, the present application provides a multi-sensor fusion lithium battery thermal runaway detection system, including a multi-level hardware deployment module, a thermal runaway test and data acquisition module, and a thermal runaway detection module;

[0040] The multi-level hardware deployment module is used to deploy micro NTC sensors, multi-gas sensor arrays, photoelectric smoke sensors, and voiceprint recognition sensors within lithium batteries. The multi-gas sensor array includes electrochemical CO sensors, semiconductor H2 sensors, and semiconductor VOC sensors.

[0041] See also Figure 2 As shown, the multi-level hardware deployment module includes multiple hardware deployment units, which are configured with multiple hardware deployment strategies and a data acquisition board. The multiple hardware deployment strategies are used to deploy multiple sensors, and the data acquisition board is used to receive sensor data from multiple sensors. The multiple hardware deployment strategies include:

[0042] Obtain a prismatic cell of a lithium battery, and embed a micro NTC sensor inside the prismatic cell of the lithium battery, wherein the micro NTC sensor is connected to a data acquisition board via a flexible PCB;

[0043] Obtain a lithium battery module and install a multi-gas sensor array at the vent of the battery module, wherein the multi-gas sensor array is connected to a data acquisition board via a flexible PCB;

[0044] Obtain an area within the space where the lithium battery pressure relief valve is located where a voiceprint recognition module can be deployed, and record this area as the voiceprint placement area. Deploy a MEMS microphone array within the voiceprint placement area, where the MEMS microphone array consists of three voiceprint recognition modules forming an equilateral triangle.

[0045] In the specific implementation process, the included angle of the triangle formed by the three voiceprint recognition modules that make up the MEMS microphone array is 120 degrees. This ensures that the signal-to-noise ratio of the target sound source is enhanced through beamforming technology, thereby improving the accuracy of data detection of the pressure relief valve. In actual application, the MEMS microphone array can be adjusted according to the actual equipment that can be built to detect the sound source signal-to-noise ratio.

[0046] Deploy photoelectric smoke sensors in the space where the lithium battery is located.

[0047] The thermal runaway test and data acquisition module is used to test the thermal runaway of lithium batteries using the thermal runaway test method based on sensors deployed in the lithium battery, and obtain the standard temperature slope, CO judgment standard, H2 judgment standard, VOC judgment standard, density judgment standard, decibel judgment standard and width judgment standard based on the test results;

[0048] The thermal runaway test and data acquisition module includes a thermal runaway test unit and a data acquisition and analysis unit. The thermal runaway test unit is equipped with a thermal runaway test strategy, which includes:

[0049] Perform multiple thermal runaway tests on the lithium battery deployed through the multi-level hardware deployment module using a thermal runaway test method, and send the multiple test results to a data acquisition and analysis unit;

[0050] The thermal runaway test method is to place the lithium battery in a standard experimental environment and conduct a simulated thermal runaway test on the lithium battery. The simulated thermal runaway test is used to simulate the thermal runaway of the lithium battery, and the experimental process based on the time sequence includes the initial stage of thermal runaway latency, the thermal runaway trigger period and the violent reaction period.

[0051] In this embodiment, the standard state is an ambient temperature of 25°C and an ambient humidity of 50%. In actual application, the standard state can be adjusted according to the actual operating environment of the lithium battery.

[0052] In the specific implementation process, by simulating the early stage of thermal runaway latency, the thermal runaway trigger period, and the intense reaction period, it is possible to obtain more comprehensive data changes of the lithium battery before, during, and after entering thermal runaway, so as to improve the data validity and accuracy during data acquisition and data analysis, thereby improving the accuracy of the thermal runaway detection module in judging the thermal runaway of the lithium battery;

[0053] The data obtained by the micro NTC sensor, multi-gas sensor array, photoelectric smoke sensor and voiceprint recognition sensor during the thermal runaway latent stage, thermal runaway trigger stage and violent reaction stage of the simulated thermal runaway experiment are respectively obtained and recorded as a test result of the thermal runaway test method.

[0054] The data acquisition and analysis strategy includes: for any test result sent by the thermal runaway test unit: for the test result of the micro NTC sensor: establishing a plane rectangular coordinate system, recorded as the temperature sensing coordinate system, where the unit of the X-axis of the temperature sensing coordinate system is min and the unit of the Y-axis is ° C; drawing a corresponding curve in the temperature sensing coordinate system based on the test result of the micro NTC sensor, and recording it as the temperature test curve; recording the slope of the point with the horizontal coordinate T1 in the temperature test curve as the temperature runaway slope, where T1 is the time when the thermal runaway trigger period begins;

[0055] In a specific implementation process, for example, in a data analysis, if the slope of the point T1 in the temperature test curve obtained is 1°C / min, the temperature runaway slope can be recorded as 1°C / min. By obtaining the temperature runaway slope, the temperature change rate when the lithium battery has thermal runaway can be obtained, which helps to improve the accuracy of judging the thermal runaway of the lithium battery in subsequent analysis.

[0056] For the test results of the multi-gas sensor array: establish a plane rectangular coordinate system, recorded as the gas sensor coordinate system, where the unit of the X-axis of the gas sensor coordinate system is min, and the unit of the Y-axis is ppm or ppb; based on the test results of the multi-gas sensor array, draw the curves corresponding to the electrochemical CO sensor, semiconductor H2 sensor, and semiconductor VOC sensor in the gas sensor coordinate system, and record them as the CO test curve, H2 test curve, and VOC test curve, respectively, where the unit of the Y-axis of the CO test curve and the H2 test curve is ppm, and the unit of the Y-axis of the VOC test curve is ppb;

[0057] Obtain the threshold values ​​corresponding to the gas anomaly judgment criteria for CO, H2, and VOC, respectively, and record them as Y1, Y2, and Y3, respectively. Record the points with ordinates Y1, Y2, and Y3 in the CO test curve, H2 test curve, and VOC test curve as CO anomaly points, H2 anomaly points, and VOC anomaly points, respectively. Record the points with abscissas T1 in the CO test curve, H2 test curve, and VOC test curve as CO out-of-control points, H2 out-of-control points, and VOC out-of-control points, respectively.

[0058] In the specific implementation process, for example, during a data analysis, the CO gas abnormality judgment standard is 32ppm, then Y1 can be recorded as 32ppm, and the abscissa of the CO out-of-control point obtained from the CO test curve is 35ppm, indicating that when the lithium battery has thermal runaway, the CO ppm concentration is greater than the gas abnormality judgment standard; to ensure the safety of the space where the lithium battery is located, an early warning should be issued when the CO concentration reaches 32ppm, so the CO judgment point can be set as the CO abnormality point;

[0059] The point corresponding to the minimum value of the horizontal coordinate of the CO abnormal point and the CO out-of-control point is recorded as the CO judgment point; the point corresponding to the minimum value of the horizontal coordinate of the H2 abnormal point and the H2 out-of-control point is recorded as the H2 judgment point; the point corresponding to the minimum value of the horizontal coordinate of the VOC abnormal point and the VOC out-of-control point is recorded as the VOC judgment point;

[0060] For the test results of the photoelectric smoke sensor: the smoke density detected by the photoelectric smoke sensor at the beginning of the thermal runaway trigger period is recorded as the thermal runaway density;

[0061] For the test results of the voiceprint recognition sensor: the decibel and pulse width obtained by matching the MEMS microphone array at the beginning of the thermal runaway trigger period are recorded as the thermal runaway decibel and thermal runaway width.

[0062] The data collection and analysis strategy also includes: based on multiple test results sent by the thermal runaway test unit, recording the average value of the temperature runaway slopes obtained in all test results as the standard temperature slope; recording the average value of the vertical coordinates of the CO judgment points in all test results as the CO judgment standard; recording the average value of the vertical coordinates of the H2 judgment points in all test results as the H2 judgment standard; recording the average value of the vertical coordinates of the VOC judgment points in all test results as the VOC judgment standard; recording the average value of the thermal runaway density in all test results as the density judgment standard; and recording the average values ​​of the thermal runaway decibels and thermal runaway widths in all test results as the decibel judgment standard and the width judgment standard, respectively.

[0063] The thermal runaway detection module is used to perform real-time detection of lithium battery operating data based on sensors deployed within the lithium battery, and to detect thermal runaway of the lithium battery based on the detection results and the thermal runaway judgment algorithm. The thermal runaway detection module is equipped with a thermal runaway detection unit, which is equipped with a thermal runaway detection strategy. The thermal runaway detection strategy includes:

[0064] When the lithium battery is operating, the operating data of the lithium battery is detected in real time based on the sensors deployed in the lithium battery, and the thermal runaway judgment algorithm is used in real time to obtain the thermal runaway judgment parameters. The thermal runaway judgment algorithm is: Wherein, F is the thermal runaway judgment parameter, a1 is the latest slope of the curve corresponding to the test results of the micro-NTC sensor obtained in real time based on the temperature sensing coordinate system, and a0 is the standard temperature slope; b1, c1, and d1 are the test results of the electrochemical CO sensor, semiconductor H2 sensor, and semiconductor VOC sensor obtained in real time, respectively, and b0, c0, and d0 are the CO judgment standard, H2 judgment standard, and VOC judgment standard, respectively; e1 is the smoke density obtained in real time based on the photoelectric smoke sensor, and e0 is the density judgment standard; f1 and g1 are the decibel and pulse width obtained in real time based on the MEMS microphone array, and f0 and g0 are the decibel judgment standard and pulse width judgment standard respectively;

[0065] In a specific implementation process, for example, during a data processing, a1, b1, c1, d1, e1, f1, and g1 are obtained as 2°C / min, 100ppm, 500ppm, 50ppb, 3%obs / m, 0, and 20ms, respectively; a0, b0, c0, d0, e0, f0, and g0 are obtained as 1°C / min, 32ppm, 200ppm, 10ppb, 1%obs / m, 80dB, and 40ms, respectively. Then, through data calculation, it can be obtained that the thermal runaway judgment parameter is approximately 2.1. In this embodiment, when the thermal runaway judgment parameter is greater than 1, it indicates that the data obtained by any one or more of the micro NTC sensor, the multi-gas sensor array, the photoelectric smoke sensor, and the voiceprint recognition sensor are abnormal data when the lithium battery is in a thermal runaway state. Therefore, the thermal runaway state of the lithium battery at this time can be determined as a thermal runaway state.

[0066] When F is greater than or equal to 1, the thermal runaway state of the lithium battery is determined to be thermal runaway;

[0067] When F is less than 1, the thermal runaway state of the lithium battery is determined to be non-existent.

[0068] Working principle: First, a micro NTC sensor, a multi-gas sensor array, a photoelectric smoke sensor, and a voiceprint recognition sensor are deployed in the lithium battery. Among them, the multi-gas sensor array includes an electrochemical CO sensor, a semiconductor H2 sensor, and a semiconductor VOC sensor. Then, the thermal runaway of the lithium battery is tested based on the sensors deployed in the lithium battery, and the standard temperature slope, CO judgment standard, H2 judgment standard, VOC judgment standard, density judgment standard, decibel judgment standard, and width judgment standard are obtained based on the test results. Finally, the operating data of the lithium battery is detected in real time based on the sensors deployed in the lithium battery, and the thermal runaway of the lithium battery is detected based on the detection results and the thermal runaway judgment algorithm.

[0069] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of systems, modules and units can be electrical, mechanical or other forms.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. Multi-sensor fusion lithium battery thermal runaway detection system, characterized by: Includes multi-level hardware deployment module, thermal runaway test and data acquisition module, and thermal runaway detection module; The multi-level hardware deployment module is used to deploy micro NTC sensors, multi-gas sensor arrays, photoelectric smoke sensors, and voiceprint recognition sensors within lithium batteries. The multi-gas sensor array includes electrochemical CO sensors, semiconductor H2 sensors, and semiconductor VOC sensors. The thermal runaway test and data acquisition module is used to test the thermal runaway of lithium batteries using the thermal runaway test method based on sensors deployed in the lithium battery, and obtain the standard temperature slope, CO judgment standard, H2 judgment standard, VOC judgment standard, density judgment standard, decibel judgment standard and width judgment standard based on the test results; The thermal runaway detection module is used to perform real-time detection of the operating data of the lithium battery based on sensors deployed in the lithium battery, and to detect thermal runaway of the lithium battery based on the detection results and the thermal runaway judgment algorithm.

2. The multi-sensor fusion lithium battery thermal runaway detection system according to claim 1, characterized in that: The multi-level hardware deployment module includes multiple hardware deployment units, each of which is configured with multiple hardware deployment strategies and a data acquisition board. The multiple hardware deployment strategies are used to deploy multiple sensors, and the data acquisition board is used to receive sensor data from multiple sensors. Multiple hardware deployment strategies include: Obtain a prismatic cell of a lithium battery, and embed a micro NTC sensor inside the prismatic cell of the lithium battery, wherein the micro NTC sensor is connected to a data acquisition board via a flexible PCB; A lithium battery module is obtained, and a multi-gas sensor array is installed at the vent of the battery module, wherein the multi-gas sensor array is connected to a data acquisition board via a flexible PCB.

3. The multi-sensor fusion lithium battery thermal runaway detection system according to claim 2, characterized in that: Multiple hardware deployment strategies also include: Obtain an area within the space where the lithium battery pressure relief valve is located where a voiceprint recognition module can be deployed, and record this area as the voiceprint placement area. Deploy a MEMS microphone array within the voiceprint placement area, where the MEMS microphone array consists of three voiceprint recognition modules forming an equilateral triangle. Deploy photoelectric smoke sensors in the space where the lithium battery is located.

4. The multi-sensor fusion lithium battery thermal runaway detection system according to claim 3, characterized in that: The thermal runaway test and data acquisition module includes a thermal runaway test unit and a data acquisition and analysis unit. The thermal runaway test unit is equipped with a thermal runaway test strategy, which includes: Perform multiple thermal runaway tests on the lithium battery deployed through the multi-level hardware deployment module using a thermal runaway test method, and send the multiple test results to a data acquisition and analysis unit; The thermal runaway test method is to place the lithium battery in a standard experimental environment and conduct a simulated thermal runaway test on the lithium battery. The simulated thermal runaway test is used to simulate the thermal runaway of the lithium battery, and the experimental process based on the time sequence includes the initial stage of thermal runaway latency, the thermal runaway trigger period and the violent reaction period. The data obtained by the micro NTC sensor, multi-gas sensor array, photoelectric smoke sensor and voiceprint recognition sensor during the thermal runaway latent stage, thermal runaway trigger stage and violent reaction stage of the simulated thermal runaway experiment are respectively obtained and recorded as a test result of the thermal runaway test method.

5. The multi-sensor fusion lithium battery thermal runaway detection system according to claim 4, characterized in that: The data acquisition and analysis unit is configured with a data acquisition and analysis strategy, which includes: For any test result sent by the thermal runaway test unit: For the test result of the micro NTC sensor: establish a plane rectangular coordinate system, recorded as the temperature sensing coordinate system, where the unit of the X-axis of the temperature sensing coordinate system is min, and the unit of the Y-axis is ℃; based on the test result of the micro NTC sensor, draw a corresponding curve in the temperature sensing coordinate system, and record it as the temperature test curve, and record the slope of the point with the horizontal coordinate T1 in the temperature test curve as the temperature runaway slope, where T1 is the time when the thermal runaway trigger period starts.

6. The multi-sensor fusion lithium battery thermal runaway detection system according to claim 5, characterized in that: The data collection and analysis strategy also includes: For the test results of the multi-gas sensor array: establish a plane rectangular coordinate system, recorded as the gas sensor coordinate system, where the unit of the X-axis of the gas sensor coordinate system is min, and the unit of the Y-axis is ppm or ppb; based on the test results of the multi-gas sensor array, draw the curves corresponding to the electrochemical CO sensor, semiconductor H2 sensor, and semiconductor VOC sensor in the gas sensor coordinate system, and record them as the CO test curve, H2 test curve, and VOC test curve, respectively, where the unit of the Y-axis of the CO test curve and the H2 test curve is ppm, and the unit of the Y-axis of the VOC test curve is ppb; Obtain the threshold values ​​corresponding to the gas anomaly judgment criteria for CO, H2, and VOC, respectively, and record them as Y1, Y2, and Y3, respectively. Record the points with ordinates Y1, Y2, and Y3 in the CO test curve, H2 test curve, and VOC test curve as CO anomaly points, H2 anomaly points, and VOC anomaly points, respectively. Record the points with abscissas T1 in the CO test curve, H2 test curve, and VOC test curve as CO out-of-control points, H2 out-of-control points, and VOC out-of-control points, respectively. The point corresponding to the minimum value of the horizontal coordinate between the CO abnormal point and the CO out-of-control point is recorded as the CO judgment point; the point corresponding to the minimum value of the horizontal coordinate between the H2 abnormal point and the H2 out-of-control point is recorded as the H2 judgment point; the point corresponding to the minimum value of the horizontal coordinate between the VOC abnormal point and the VOC out-of-control point is recorded as the VOC judgment point.

7. The multi-sensor fusion lithium battery thermal runaway detection system according to claim 6, characterized in that: The data collection and analysis strategy also includes: For the test results of the photoelectric smoke sensor: the smoke density detected by the photoelectric smoke sensor at the beginning of the thermal runaway trigger period is recorded as the thermal runaway density.

8. The multi-sensor fusion lithium battery thermal runaway detection system according to claim 7, characterized in that: The data collection and analysis strategy also includes: For the test results of the voiceprint recognition sensor: the decibel and pulse width obtained by matching the MEMS microphone array at the beginning of the thermal runaway trigger period are recorded as the thermal runaway decibel and thermal runaway width.

9. The multi-sensor fusion lithium battery thermal runaway detection system according to claim 8, characterized in that: The data collection and analysis strategy also includes: Based on multiple test results sent by the thermal runaway test unit, the average value of the temperature runaway slopes obtained in all test results is recorded as the standard temperature slope; the average value of the vertical coordinates of the CO judgment points in all test results is recorded as the CO judgment standard; the average value of the vertical coordinates of the H2 judgment points in all test results is recorded as the H2 judgment standard; the average value of the vertical coordinates of the VOC judgment points in all test results is recorded as the VOC judgment standard; the average value of the thermal runaway density in all test results is recorded as the density judgment standard; the average values ​​of the thermal runaway decibels and thermal runaway widths in all test results are recorded as the decibel judgment standard and the width judgment standard, respectively.

10. The multi-sensor fusion lithium battery thermal runaway detection system according to claim 9, characterized in that: The thermal runaway detection module is equipped with a thermal runaway detection unit, which is equipped with a thermal runaway detection strategy. The thermal runaway detection strategy includes: When the lithium battery is operating, the operating data of the lithium battery is detected in real time based on the sensors deployed in the lithium battery, and the thermal runaway judgment algorithm is used in real time to obtain the thermal runaway judgment parameters. The thermal runaway judgment algorithm is: Wherein, F is the thermal runaway judgment parameter, a1 is the latest slope of the curve corresponding to the test results of the micro-NTC sensor obtained in real time based on the temperature sensing coordinate system, and a0 is the standard temperature slope; b1, c1, and d1 are the test results of the electrochemical CO sensor, semiconductor H2 sensor, and semiconductor VOC sensor obtained in real time, respectively, and b0, c0, and d0 are the CO judgment standard, H2 judgment standard, and VOC judgment standard, respectively; e1 is the smoke density obtained in real time based on the photoelectric smoke sensor, and e0 is the density judgment standard; f1 and g1 are the decibel and pulse width obtained in real time based on the MEMS microphone array, and f0 and g0 are the decibel judgment standard and pulse width judgment standard respectively; When F is greater than or equal to 1, the thermal runaway state of the lithium battery is determined to be thermal runaway; When F is less than 1, the thermal runaway state of the lithium battery is determined to be non-existent.

Images