CN116722249A - Battery thermal runaway early warning protection system and protection method thereof - Google Patents
Battery thermal runaway early warning protection system and protection method thereof Download PDFInfo
- Publication number
- CN116722249A CN116722249A CN202310897113.5A CN202310897113A CN116722249A CN 116722249 A CN116722249 A CN 116722249A CN 202310897113 A CN202310897113 A CN 202310897113A CN 116722249 A CN116722249 A CN 116722249A
- Authority
- CN
- China
- Prior art keywords
- battery
- thermal runaway
- temperature
- data
- protection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012544 monitoring process Methods 0.000 claims abstract description 82
- 238000013135 deep learning Methods 0.000 claims abstract description 14
- 238000007726 management method Methods 0.000 claims description 33
- 230000002159 abnormal effect Effects 0.000 claims description 23
- 230000008859 change Effects 0.000 claims description 15
- 230000005856 abnormality Effects 0.000 claims description 14
- 238000013528 artificial neural network Methods 0.000 claims description 14
- 238000005259 measurement Methods 0.000 claims description 13
- 238000005192 partition Methods 0.000 claims description 13
- 238000011217 control strategy Methods 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 10
- 238000012502 risk assessment Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 238000003745 diagnosis Methods 0.000 claims description 7
- 230000007613 environmental effect Effects 0.000 claims description 7
- 238000000556 factor analysis Methods 0.000 claims description 7
- 238000009529 body temperature measurement Methods 0.000 claims description 6
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 6
- 238000013136 deep learning model Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000005457 optimization Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000000638 solvent extraction Methods 0.000 claims description 5
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 4
- 238000001816 cooling Methods 0.000 claims description 4
- 238000013524 data verification Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000008485 antagonism Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000008439 repair process Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 230000000630 rising effect Effects 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 230000009471 action Effects 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 description 4
- 230000001681 protective effect Effects 0.000 description 4
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 3
- 229910052744 lithium Inorganic materials 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000002035 prolonged effect Effects 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/48—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte
- H01M10/486—Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte for measuring temperature
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/425—Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing
- H01M2010/4271—Battery management systems including electronic circuits, e.g. control of current or voltage to keep battery in healthy state, cell balancing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Abstract
The invention relates to the technical field of battery thermal runaway early warning protection systems, in particular to a battery thermal runaway early warning protection system and a protection method thereof. According to the invention, a thermal runaway event is found in advance through a deep learning prediction model, a self-adaptive protection strategy dynamically adjusts protection parameters, a high-precision thermistor and a temperature sensor monitor the battery temperature in real time, a partitioned battery monitoring system monitors the battery in real time, the battery with problems is helped to be positioned quickly, the accurate positioning of a problem source is realized, the temperature rise rate and the temperature rise amplitude of a battery pack are reduced, the measures can be combined to remarkably improve the early warning accuracy and timeliness, the battery pack is protected in a personalized way, damage is prevented, the problem battery is prevented from being damaged, and corrective action is taken by accurately positioning the problem battery, so that the problem is prevented from spreading, and more efficient and safe battery operation is provided.
Description
Technical Field
The invention relates to the technical field of battery thermal runaway early warning protection systems, in particular to a battery thermal runaway early warning protection system and a protection method thereof.
Background
The battery thermal runaway early warning protection system is a system designed for monitoring and preventing overheat and thermal runaway conditions of a lithium battery. Lithium batteries may undergo thermal runaway under overcharge, overdischarge, external short-circuit, excessive current or high-temperature environmental conditions, resulting in serious safety problems such as fire or explosion. The lithium battery thermal runaway early warning protection system aims to find potential problems of the battery in time and take measures to prevent accidents. The system is widely applied to aspects of electric automobiles, renewable energy storage systems, portable electronic equipment and the like so as to protect personal safety and property safety.
In the actual use process of the battery thermal runaway early warning protection system, the traditional Battery Management System (BMS) and the thermal runaway early warning algorithm mainly depend on simple thresholds and rules, lack of deep understanding of complex battery behaviors, and may not accurately predict and timely respond to the thermal runaway risk of the battery. In addition, conventional battery protection measures are often cut-away, and no personalized protection strategy is provided for different areas in the battery pack and the actual situation of the single cells. Finally, conventional charge and discharge control strategies may not be sufficiently optimized, resulting in an excessively rapid rise in battery temperature, increasing the risk of thermal runaway. These disadvantages limit the application of conventional solutions to high performance, high safety-requiring battery systems and also increase the operational risk of the battery systems.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a battery thermal runaway early warning protection system and a protection method thereof.
In order to achieve the above purpose, the present invention adopts the following technical scheme: a battery thermal runaway early warning protection system consists of a battery management unit, a monitoring hardware unit, a partitioned battery monitoring unit and a dynamic battery protection unit;
the battery management unit comprises a thermal runaway prediction model, a self-adaptive protection strategy and a charge-discharge control strategy, wherein the thermal runaway prediction model is specifically a thermal runaway prediction model driven by deep learning;
the monitoring hardware unit comprises a thermistor and a temperature sensor;
the partitioned battery monitoring unit comprises a battery pack partitioning sub-module, a region independent monitoring sub-module and a fault positioning sub-module;
the dynamic battery protection unit comprises intelligent protection measures and personalized protection strategies.
As a further scheme of the invention, the thermal runaway prediction model driven by deep learning adopts a cyclic neural network (RNN) to carry out deep analysis on temperature data of the battery pack, extracts more useful features from the battery pack through a multi-layer network structure and self-adaptive weight learning, learns the complex mode and trend of temperature change and predicts a potential thermal runaway event;
the self-adaptive protection strategy is to dynamically adjust protection parameters and measures according to the change of real-time monitoring data and battery states by adopting a self-adaptive control algorithm which is specifically used for controlling the FLC through fuzzy logic, so as to adapt to different working states and environmental conditions, adjust a protection threshold value, a protection triggering condition and a response speed according to the actual situation of the battery pack, and provide protection measures;
the charge-discharge control strategy uses an optimization algorithm which specifically predicts and controls the MPC by a model to control the charge rate, the discharge power and the charge cut-off voltage parameters, reduces the rate and the amplitude of the rise of the temperature of the battery pack and reduces the thermal runaway risk by optimally adjusting the charge-discharge process of the battery pack, and obtains the optimal control strategy by referring to the multi-factor relationship comprising the temperature, the current and the voltage so as to achieve the effects of effectively controlling the temperature of the battery and reducing the thermal runaway risk.
As a further scheme of the invention, the thermistor acquires the resistance value of the thermistor periodically or in real time through a voltage dividing circuit and a bridge circuit, acquires an accurate temperature value through a table look-up or interpolation mode by using a temperature-resistance curve, performs moving average filtering by adopting a digital filtering algorithm, performs error compensation by comparing the measured values of other temperature sensors, and improves the accuracy and stability of measurement;
the temperature sensor is arranged in the battery pack, measurement data of the temperature sensor is transmitted to the battery management unit for processing through the serial communication interface SPI, temperature measurement errors are corrected through a table look-up, interpolation or polynomial fitting mode according to nonlinear characteristics of the temperature sensor, a known temperature source is used for calibration, and sensor measurement values are corrected and adjusted to improve measurement data reliability.
As a further scheme of the invention, the battery pack partitioning sub-module divides the battery pack into a plurality of areas based on a dividing algorithm by referring to the positions, the connection modes and the capacities of the batteries, so as to ensure the relative balance of the number of the batteries in each area;
the region independent monitoring submodule is arranged inside each region and monitors the state of each single battery in the region in real time, including voltage monitoring, temperature monitoring and current monitoring;
when thermal runaway occurs, the fault positioning sub-module identifies the abnormal battery or area by monitoring the voltage, temperature and current parameters of each area of the battery pack, uses an abnormality detection algorithm, combines the physical model and historical data of the battery pack, uses a multi-factor analysis algorithm to determine which battery or area is likely to be the main cause of the fault, designs a positioning strategy to determine the position of the fault battery according to the abnormality detection result and the multi-factor analysis result, and performs judgment based on the voltage difference, the temperature change and the current abnormality factor, and fuses the data of the area monitoring sub-module with the fault positioning algorithm to position the fault.
As a further scheme of the invention, the intelligent protection measures adopt a risk assessment algorithm based on rules, according to real-time monitoring data and output of a prediction model, the degree of risk is judged by referring to the change trend and the threshold value of temperature, current and voltage indexes, the thermal runaway risk of the battery pack is assessed, and when the system detects that the thermal runaway risk exists in the battery pack, the protection measures are automatically adjusted, including cutting off the connection between the battery pack and an external circuit, reducing the charge and discharge rate of the battery and starting a cooling system;
the personalized protection strategy establishes personalized protection measures for each area according to the thermal runaway risk of each area and actual conditions, wherein the actual conditions comprise the temperature, the voltage and the internal resistance parameters of the single battery, and the personalized protection measures comprise adjusting a protection threshold value, changing the charge and discharge rate and setting a temperature alarm limit.
A battery thermal runaway early warning protection method comprises the following steps:
analyzing the temperature data of the battery pack by using a deep learning model, and predicting a thermal runaway event;
the self-adaptive protection strategy and the fuzzy logic control algorithm are applied to dynamically adjust the protection parameters, so that the method is suitable for different environments;
optimizing a charge-discharge strategy by adopting a model predictive control algorithm, reducing the temperature rising rate and reducing the thermal runaway risk;
monitoring the temperature of the battery by using a thermistor and a temperature sensor, and timely transmitting data to a battery management unit;
abnormal batteries and fault reasons are identified through the partition battery monitoring units, and protection measures are automatically adjusted according to thermal runaway risks based on intelligent protection measures and personalized protection strategies.
As a further aspect of the present invention, the step of predicting a thermal runaway event specifically includes:
introducing a data enhancement technology in a data preprocessing stage, including random cutting, rotation, scaling and translation, and expanding a training data set;
processing the battery pack temperature data using a deep neural network architecture that draws attention mechanisms to capture important spatiotemporal features in the temperature data;
learning an implicit representation of the battery pack temperature data by generating an antagonism network GAN;
combining current, voltage and humidity data, carrying out multi-mode data fusion and analysis, and obtaining more comprehensive information;
model evaluation is performed and the trained and evaluated model is applied to real-time data to predict thermal runaway events of the battery pack in real-time.
As a further scheme of the invention, the step of optimizing the charge-discharge strategy by adopting the model predictive control algorithm comprises the following steps:
collecting temperature data, current data and voltage data of a battery pack, establishing a deep learning-based cyclic neural network (RNN) model, and training historical data;
based on the temperature prediction result, generating an optimized charge-discharge strategy through a model prediction control algorithm, and applying the generated optimized charge-discharge strategy to an actual battery system.
As a further aspect of the present invention, the step of transmitting data to the battery management unit specifically includes:
transmitting the battery temperature data measured by the sensor to a battery management unit through a cable or wireless transmission mode;
converting the sensor signal into a temperature value, and performing unit conversion and data verification;
comparing the battery temperature data with a preset threshold value in combination with other information in the system to evaluate the thermal runaway risk;
based on the temperature data and the thermal runaway risk assessment results, the battery management unit monitors the status of the battery in real time and triggers an alarm when needed.
As a further aspect of the present invention, the step of identifying the abnormal battery and the cause of the fault specifically includes:
based on the data collected by the battery monitoring unit, developing a fault diagnosis algorithm to detect and identify abnormal batteries and fault reasons;
applying the developed fault diagnosis algorithm to the monitoring data, and carrying out abnormality detection on the battery state of each partition;
identifying a fault cause by data association, feature extraction and fault mode aiming at the detected abnormal battery;
and adopting corresponding measures to repair or replace the affected battery.
Compared with the prior art, the invention has the advantages and positive effects that:
according to the invention, more effective features can be extracted from the temperature data of the battery pack through the thermal runaway prediction model driven by deep learning, and the early warning accuracy and timeliness are remarkably improved, so that the situation that serious damage is possibly caused is prevented in advance. Secondly, the self-adaptive protection strategy dynamically adjusts protection parameters and measures according to the real-time monitoring data and the change of the battery state, and creatively provides more efficient and personalized protection measures to prevent battery damage. Furthermore, the introduced high-precision thermistor and temperature sensor can provide more accurate data for monitoring the battery temperature in real time and provide powerful guarantee for fault prevention. The application of the partition battery monitoring system enables the user to monitor each battery cell in real time, helps to quickly locate the battery with problems, achieves accurate location of the problem sources, and can accurately and effectively guide the attention of people to potential problem areas. This helps take corrective action in time, thereby avoiding the spread of battery problems, causing greater damage. By reducing the rate and amplitude of the rise of the temperature of the battery pack, the risk of thermal runaway is reduced, the running efficiency of the battery is ensured, and the potential safety hazard caused by thermal runaway is avoided.
Drawings
Fig. 1 is a schematic diagram of a system frame of a battery thermal runaway early warning protection system and a protection method thereof according to the present invention;
FIG. 2 is a flowchart showing a battery thermal runaway warning protection system and a protection method thereof according to the present invention;
FIG. 3 is a detailed flowchart of step 1 of a battery thermal runaway warning protection system and a protection method thereof according to the present invention;
FIG. 4 is a detailed flowchart of step 3 of a battery thermal runaway warning protection system and a protection method thereof according to the present invention;
FIG. 5 is a detailed flowchart of step 4 of a battery thermal runaway warning protection system and a protection method thereof according to the present invention;
fig. 6 is a detailed flowchart of step 5 of a battery thermal runaway early warning protection system and a protection method thereof according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Example 1
Referring to fig. 1, the present invention provides a technical solution: a battery thermal runaway early warning protection system consists of a battery management unit, a monitoring hardware unit, a partitioned battery monitoring unit and a dynamic battery protection unit;
the battery management unit comprises a thermal runaway prediction model, a self-adaptive protection strategy and a charge-discharge control strategy, wherein the thermal runaway prediction model is specifically a thermal runaway prediction model driven by deep learning;
the monitoring hardware unit comprises a thermistor and a temperature sensor;
the partitioned battery monitoring unit comprises a battery pack partitioned sub-module, a regional independent monitoring sub-module and a fault positioning sub-module;
the dynamic battery protection unit comprises intelligent protection measures and personalized protection strategies.
The system consists of a battery management unit, a monitoring hardware unit, a partitioned battery monitoring unit and a dynamic battery protection unit. The battery management unit is provided with a thermal runaway prediction model, an adaptive protection strategy and a charge-discharge control strategy, wherein the thermal runaway prediction model adopts a deep learning technology. The monitoring hardware unit comprises a thermistor and a temperature sensor, the partitioned battery monitoring unit realizes a partitioned monitoring function through a battery pack partitioned sub-module, a regional independent monitoring sub-module and a fault positioning sub-module, and the dynamic battery protection unit comprises intelligent protection measures and personalized protection strategies. The thermal runaway prediction model driven by deep learning can extract more effective features from the temperature data of the battery pack, and the early warning accuracy and timeliness are remarkably improved, so that the situation that serious damage is possibly caused is prevented in advance. Secondly, the self-adaptive protection strategy dynamically adjusts protection parameters and measures according to the real-time monitoring data and the change of the battery state, and creatively provides more efficient and personalized protection measures to prevent battery damage. Furthermore, the introduced high-precision thermistor and temperature sensor can provide more accurate data for monitoring the battery temperature in real time and provide powerful guarantee for fault prevention. The application of the partition battery monitoring system enables the user to monitor each battery cell in real time, helps to quickly locate the battery with problems, achieves accurate location of the problem sources, and can accurately and effectively guide the attention of people to potential problem areas. This helps take corrective action in time, thereby avoiding the spread of battery problems, causing greater damage. By reducing the rate and amplitude of the rise of the temperature of the battery pack, the risk of thermal runaway is reduced, the running efficiency of the battery is ensured, and the potential safety hazard caused by thermal runaway is avoided.
Referring to fig. 1, a thermal runaway prediction model driven by deep learning is implemented by adopting a cyclic neural network RNN to perform deep analysis on battery pack temperature data, extracting more useful features from the battery pack temperature data through a multi-layer network structure and self-adaptive weight learning, learning a complex mode and trend of temperature change, and predicting a potential thermal runaway event;
the self-adaptive protection strategy is to dynamically adjust protection parameters and measures according to the change of real-time monitoring data and battery states by adopting a self-adaptive control algorithm which is specifically used for controlling the FLC through fuzzy logic, so as to adapt to different working states and environmental conditions, and adjust a protection threshold, a protection triggering condition and a response speed according to the actual situation of the battery pack, and provide protection measures;
the charge-discharge control strategy uses an optimization algorithm which specifically predicts and controls the MPC by a model to control the charge rate, the discharge power and the charge cut-off voltage parameters, reduces the rate and the amplitude of the rise of the temperature of the battery pack and reduces the thermal runaway risk by optimally adjusting the charge-discharge process of the battery pack, and obtains the optimal control strategy by referring to the multi-factor relationship comprising the temperature, the current and the voltage so as to achieve the effects of effective control of the temperature of the battery and reduction of the thermal runaway risk.
The thermal runaway prediction model uses a Recurrent Neural Network (RNN) to conduct deep analysis on battery pack temperature data, and can accurately predict potential thermal runaway events. The self-adaptive protection strategy adopts a Fuzzy Logic Control (FLC) algorithm, and flexibly adjusts protection parameters and measures according to real-time monitoring data and battery state changes so as to adapt to different working states and environmental conditions. The charge-discharge control strategy uses a Model Predictive Control (MPC) optimization algorithm to reduce the rate and magnitude of temperature rise and reduce the risk of thermal runaway by optimizing the charge-discharge process. Comprehensively, the thermal runaway risk can be accurately predicted, the protection strategy can be flexibly adjusted, and the charge and discharge control can be optimized, so that the safety and reliability of a battery system are improved, and the service life of a battery is prolonged.
Referring to fig. 1, the thermistor periodically or in real time acquires the resistance value of the thermistor through a voltage dividing circuit and a bridge circuit, acquires an accurate temperature value through a table look-up or interpolation mode by using a temperature-resistance curve, performs moving average filtering by adopting a digital filtering algorithm, performs error compensation by comparing the measured values of other temperature sensors, and improves the accuracy and stability of measurement;
the temperature sensor is arranged in the battery pack, measurement data of the temperature sensor is transmitted to the battery management unit for processing through the serial communication interface SPI, temperature measurement errors are corrected through a table look-up, interpolation or polynomial fitting mode according to nonlinear characteristics of the temperature sensor, a known temperature source is used for calibration, and sensor measurement values are corrected and adjusted to improve measurement data reliability.
Firstly, the thermistor periodically or in real time collects the resistance value of the thermistor through a voltage dividing circuit or a bridge circuit, and an accurate temperature value is obtained by utilizing a temperature-resistance curve. And a digital filtering algorithm is adopted to carry out moving average filtering, so that noise interference is reduced, and the accuracy and stability of temperature measurement are improved. In addition, the accuracy and the reliability of the measured data are further improved by comparing and compensating errors with the measured values of other temperature sensors.
Next, the temperature sensor is installed inside the battery pack, and transmits measurement data to the battery management unit through the serial communication interface for processing. For the nonlinear characteristics of the temperature sensor, the temperature measurement error is corrected by adopting methods such as table lookup, interpolation or polynomial fitting. Through the calibration process, the known temperature source is utilized to correct and adjust the measured value of the sensor, so that the reliability and accuracy of the measured data are improved.
In summary, the application of the thermistor and the temperature sensor makes the temperature measurement more accurate, stable and reliable. This helps the system accurately monitor the temperature change of the battery pack, detect potential thermal runaway risks in time, and take necessary protective measures. From the implementation point of view, the measures have feasibility and effectiveness in the aspects of resistance value acquisition, temperature correction, data processing and the like, and the safety and reliability of the battery system can be improved.
Referring to fig. 1, the battery pack partitioning sub-module divides the battery pack into a plurality of areas based on a dividing algorithm by referring to the positions, connection modes and capacities of the batteries, so as to ensure the relative balance of the number of batteries in each area;
the regional independent monitoring submodule is arranged inside each region and monitors the state of each single battery in the region in real time, including voltage monitoring, temperature monitoring and current monitoring;
when thermal runaway occurs, the fault positioning sub-module identifies abnormal batteries or areas by monitoring voltage, temperature and current parameters of each area of the battery pack, uses an abnormality detection algorithm, combines a physical model and historical data of the battery pack, uses a multi-factor analysis algorithm to determine which battery or area is likely to be a main cause of a fault, designs a positioning strategy to determine the position of the fault battery according to an abnormality detection result and a multi-factor analysis result, and performs judgment based on voltage difference, temperature change and current abnormality factors to fuse data of the area monitoring sub-module with the fault positioning algorithm and position the fault.
Through the application of the battery pack partition sub-module, the region independent monitoring sub-module and the fault positioning sub-module, the safety monitoring and the fault positioning of the battery pack are realized.
The battery pack is divided into a plurality of areas by the battery pack partition submodule according to the factors such as the position, the connection mode and the capacity, and the relative balance of the number of batteries in each area is ensured, so that the balance and the service life of the battery pack are improved.
The regional independent monitoring submodule is arranged in each region, and abnormal conditions can be rapidly detected by monitoring state parameters such as voltage, temperature and current of each single battery in real time, so that the accuracy and timeliness of fault monitoring are improved. When a thermal runaway event occurs, the fault positioning sub-module utilizes an abnormality detection algorithm to identify the battery or the area with the abnormality, and combines the physical model of the battery pack and the historical data to determine the main cause of the fault by using a multi-factor analysis algorithm. The location of the failed battery is determined by a positioning strategy based on factors such as voltage differences, temperature changes, and current anomalies. Comprehensively, the independent monitoring and fault positioning of the battery pack are realized. By improving the balance, timeliness and accuracy of the battery pack, the scheme can improve the safety and reliability of the battery pack and support rapid fault location and maintenance measures. From the implementation point of view, the design and integration of the sub-modules have feasibility and practicality, and can provide effective support for the management and maintenance of the battery pack.
Referring to fig. 1, the intelligent protection measures adopt a risk assessment algorithm based on rules, according to real-time monitoring data and output of a prediction model, the degree of risk is judged by referring to the change trend and threshold of temperature, current and voltage indexes, the thermal runaway risk of the battery pack is assessed, and when the system detects that the thermal runaway risk exists in the battery pack, the protection measures are automatically adjusted, including cutting off the connection between the battery pack and an external circuit, reducing the charge and discharge rate of the battery, and starting a cooling system;
the personalized protection strategy establishes personalized protection measures for each area according to the thermal runaway risk of each area and the actual situation, wherein the actual situation comprises the temperature, the voltage and the internal resistance parameters of the single battery, and the personalized protection measures comprise adjusting the protection threshold value, changing the charge and discharge rate and setting the temperature alarm limit.
And the rule-based risk assessment algorithm utilizes real-time monitoring data and the output of a prediction model to evaluate the thermal runaway risk of the battery pack by referring to the change trend and the threshold value of indexes such as temperature, current, voltage and the like. According to the evaluation result, protection measures such as cutting off the connection of the battery pack to an external circuit, reducing the charge and discharge rate, starting a cooling system, etc. are automatically adjusted to cope with the potential risk.
The personalized protection strategy establishes personalized protection measures for each area according to the thermal runaway risk and actual conditions of each area. By considering parameters such as temperature, voltage, internal resistance and the like of the single battery, the protection threshold is adjusted, the charge and discharge rate is changed, the temperature alarm limit is set and the like, so that the thermal runaway risk of the battery is reduced to the greatest extent.
From the implementation point of view, the rule-based risk assessment algorithm and the personalized protection strategy have feasibility and practicality. By applying the real-time monitoring data and the prediction model, the thermal runaway risk can be accurately estimated and the protection measures can be automatically adjusted. The personalized protection strategy considers the characteristics of each area and can be adjusted correspondingly according to actual conditions. These measures help to improve the safety, reliability and stability of the battery pack. Meanwhile, through different levels of protection measures, the thermal runaway risk can be effectively treated, and the battery pack is protected from potential hazards to the greatest extent.
Referring to fig. 2, a battery thermal runaway early warning protection method includes the following steps:
analyzing the temperature data of the battery pack by using a deep learning model, and predicting a thermal runaway event;
the self-adaptive protection strategy and the fuzzy logic control algorithm are applied to dynamically adjust the protection parameters, so that the method is suitable for different environments;
optimizing a charge-discharge strategy by adopting a model predictive control algorithm, reducing the temperature rising rate and reducing the thermal runaway risk;
monitoring the temperature of the battery by using a thermistor and a temperature sensor, and timely transmitting data to a battery management unit;
abnormal batteries and fault reasons are identified through the partition battery monitoring units, and protection measures are automatically adjusted according to thermal runaway risks based on intelligent protection measures and personalized protection strategies.
First, the deep learning model is utilized to analyze and predict the temperature data of the battery pack, so that the signs of the thermal runaway event can be found in advance, and thus, protective measures can be taken in time. And secondly, applying an adaptive protection strategy and a fuzzy logic control algorithm, and dynamically adjusting protection parameters to adapt to different environmental conditions. Thus, the effectiveness of the protection measures under various conditions can be ensured, and the safety and the robustness of the battery pack are improved. And a model predictive control algorithm is adopted to optimize a charge-discharge strategy, so that the temperature rise rate of the battery is reduced, and the thermal runaway risk is reduced. The temperature of the battery pack can be effectively controlled by reasonably controlling the charge and discharge process, and the thermal runaway condition caused by overhigh temperature is avoided. The method also monitors battery temperature using a thermistor and a temperature sensor and transmits data to the battery management unit in real time. Therefore, the temperature information can be timely acquired so as to quickly respond to the potential thermal runaway risk and ensure that the battery pack is in a safety range. Abnormal batteries and fault reasons are identified through the partition battery monitoring unit, and protection measures are automatically adjusted based on intelligent protection measures and personalized protection strategies. The personalized protection strategy optimizes protection measures according to the thermal runaway risks of different areas, and improves the accuracy and pertinence of protection.
Referring to fig. 3, the steps for predicting a thermal runaway event are specifically:
introducing a data enhancement technology in a data preprocessing stage, including random cutting, rotation, scaling and translation, and expanding a training data set;
processing the battery pack temperature data using a deep neural network architecture that draws attention mechanisms to capture important spatiotemporal features in the temperature data;
learning an implicit representation of the battery pack temperature data by generating an antagonism network GAN;
combining current, voltage and humidity data, carrying out multi-mode data fusion and analysis, and obtaining more comprehensive information;
model evaluation is performed and the trained and evaluated model is applied to real-time data to predict thermal runaway events of the battery pack in real-time.
The step of predicting a thermal runaway event combines data preprocessing, deep neural network architecture of attention mechanisms, application of generating a countermeasure network (GAN), multimodal data fusion and analysis, and model evaluation and real-time application. In the data preprocessing stage, the battery pack temperature data are processed by introducing a data enhancement technology, a training data set is expanded, and the diversity and generalization capability of the data are improved. And then, processing the temperature data of the battery pack by adopting a deep neural network architecture and combining an attention mechanism so as to capture key space-time characteristics and improve the accuracy of prediction. Generating a countermeasure network (GAN) is introduced, learning an implicit representation of the battery temperature data. By using the GAN generator and the discriminant model, realistic temperature data is generated, more samples are provided for training and prediction, and the robustness and learning ability of the model are enhanced. And carrying out multi-mode data fusion and analysis, combining related data such as current, voltage, humidity and the like, synthesizing information provided by each sensor, acquiring more comprehensive and rich data characteristics, and improving the prediction capability of thermal runaway events. And evaluating the trained model to verify the prediction performance of the model. And then the model is applied to real-time data, the thermal runaway event of the battery pack is predicted in real time, real-time monitoring and early warning are realized, and protective measures are taken in time. Integrating these steps can effectively predict thermal runaway events of the battery pack, and improve prediction accuracy and robustness. Meanwhile, through comprehensive application of data enhancement, deep neural network, GAN, multi-mode data fusion and real-time application, beneficial support can be provided, and adaptability and practicability of the model are enhanced. These steps are important for accurately predicting battery thermal runaway events and preventing potential risk.
Referring to fig. 4, the steps of optimizing the charge-discharge strategy by using the model predictive control algorithm are specifically as follows:
collecting temperature data, current data and voltage data of a battery pack, establishing a deep learning-based cyclic neural network (RNN) model, and training historical data;
based on the temperature prediction result, generating an optimized charge-discharge strategy through a model prediction control algorithm, and applying the generated optimized charge-discharge strategy to an actual battery system.
First, temperature data, current and voltage of the battery pack and other related data are collected, a deep learning-based Recurrent Neural Network (RNN) model is established, and the relation between the temperature and other factors is learned through training of historical data. And then, carrying out temperature prediction by using the trained RNN model, and generating an optimized charge-discharge strategy by adopting a model prediction control algorithm based on a prediction result. These strategies optimize the charge-discharge process based on the current temperature prediction results and a preset objective function to reduce the rate of temperature rise and reduce the risk of thermal runaway. And finally, applying the generated optimized charge-discharge strategy to an actual battery system, implementing the optimized strategy by controlling the charge-discharge process, and monitoring the battery temperature and the system performance index. Thus, the safety of the battery can be improved, the service life of the battery can be prolonged, and the energy utilization efficiency can be improved. Meanwhile, the model predictive control algorithm can feed back and adjust according to the real-time temperature data, so that the dynamic optimization of the charge and discharge strategy is realized, and the adaptability and the robustness of the system are improved. From the implementation point of view, the algorithm can optimize the charge-discharge strategy, improve the safety, reliability and performance of the battery pack, effectively manage the battery system, avoid the risk of thermal runaway, and improve the energy utilization efficiency and service life.
Referring to fig. 5, the steps for transmitting data to the battery management unit are specifically as follows:
transmitting the battery temperature data measured by the sensor to a battery management unit through a cable or wireless transmission mode;
converting the sensor signal into a temperature value, and performing unit conversion and data verification;
comparing the battery temperature data with a preset threshold value in combination with other information in the system to evaluate the thermal runaway risk;
based on the temperature data and the thermal runaway risk assessment results, the battery management unit monitors the status of the battery in real time and triggers an alarm when needed.
First, battery temperature data measured by the sensor is transmitted to the battery management unit using a cable or wireless transmission. In the battery management unit, the sensor signal is converted and processed, converted into a temperature value, and subjected to unit conversion and data verification. Next, the battery temperature data is compared to a preset threshold, and a thermal runaway risk assessment is performed in combination with other information in the system. Based on the temperature data and the results of the thermal runaway risk assessment, the battery management unit monitors the status of the battery in real time and triggers an alarm or takes other protective measures when needed. The following beneficial effects can be achieved by implementing these steps: monitoring the state of the battery in real time, finding out abnormal conditions in time, and taking measures to protect the safety of the battery; through a preset threshold value and thermal runaway evaluation, timely identifying potential thermal runaway risks and taking preventive measures; real-time feedback and alarm notification are provided so that personnel can take steps quickly to cope with possible dangerous situations. In summary, transmitting data to the battery management unit and implementing real-time monitoring and alarm triggering can improve the safety of the battery system, protect the battery and related devices, and timely prevent and cope with potential thermal runaway risks.
Referring to fig. 6, the steps for identifying the abnormal battery and the failure cause are specifically as follows:
based on the data collected by the battery monitoring unit, developing a fault diagnosis algorithm to detect and identify abnormal batteries and fault reasons;
applying the developed fault diagnosis algorithm to the monitoring data, and carrying out abnormality detection on the battery state of each partition;
identifying a fault cause by data association, feature extraction and fault mode aiming at the detected abnormal battery;
and adopting corresponding measures to repair or replace the affected battery.
First, battery-related data is collected by a battery monitoring unit, and a fault diagnosis algorithm is developed to detect and identify abnormal batteries and causes of faults. And applying the developed algorithm to the monitoring data, detecting the state of each battery partition abnormally, and identifying the fault cause. The reasons for abnormal batteries can be deduced through data association, feature extraction and failure mode analysis. Once the cause of the fault is identified, corresponding measures such as repairing the battery connection, recalibrating the battery management system, or replacing the affected battery will be taken. From an implementation perspective, these steps help to identify faults in time, improve battery system reliability, optimize maintenance planning, and save costs. Accurate identification of abnormal batteries and causes of failure can prevent further damage to equipment, extend battery life, and avoid ineffective maintenance and replacement, thereby improving system performance and efficiency.
Working principle: first, the battery pack temperature data is analyzed and predicted using a deep learning model to discover signs of thermal runaway events in advance. And secondly, a self-adaptive protection strategy and a fuzzy logic control algorithm are applied, and protection parameters are dynamically adjusted to adapt to different environmental conditions, so that the effectiveness and the robustness of protection measures are ensured. Meanwhile, a charge-discharge strategy is optimized through a model predictive control algorithm, so that the temperature rise rate of the battery is reduced, and the risk of thermal runaway is reduced. In addition, the temperature of the battery is monitored in real time by using a thermistor and a temperature sensor, and data is transmitted to a battery management unit, so that potential thermal runaway risks can be responded timely. And identifying abnormal batteries and fault reasons through the partition battery monitoring units, and automatically adjusting the protection measures according to the intelligent protection measures and the personalized protection strategies. By integrating the steps, the method can effectively predict the thermal runaway event, dynamically adjust the protection parameters, optimize the charge-discharge strategy, monitor the temperature in real time and accurately identify the abnormal battery, thereby improving the safety and stability of the battery pack and reducing the risk of thermal runaway.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (10)
1. The battery thermal runaway early warning protection system is characterized by comprising a battery management unit, a monitoring hardware unit, a partitioned battery monitoring unit and a dynamic battery protection unit;
the battery management unit comprises a thermal runaway prediction model, a self-adaptive protection strategy and a charge-discharge control strategy, wherein the thermal runaway prediction model is specifically a thermal runaway prediction model driven by deep learning;
the monitoring hardware unit comprises a thermistor and a temperature sensor;
the partitioned battery monitoring unit comprises a battery pack partitioning sub-module, a region independent monitoring sub-module and a fault positioning sub-module;
the dynamic battery protection unit comprises intelligent protection measures and personalized protection strategies.
2. The battery thermal runaway early warning protection system according to claim 1, wherein the deep learning driven thermal runaway prediction model adopts a cyclic neural network RNN to perform deep analysis on battery pack temperature data, extracts more useful features from the battery pack temperature data through a multi-layer network structure and adaptive weight learning, learns complex modes and trends of temperature variation, and predicts potential thermal runaway events;
the self-adaptive protection strategy is to dynamically adjust protection parameters and measures according to the change of real-time monitoring data and battery states by adopting a self-adaptive control algorithm which is specifically used for controlling the FLC through fuzzy logic, so as to adapt to different working states and environmental conditions, adjust a protection threshold value, a protection triggering condition and a response speed according to the actual situation of the battery pack, and provide protection measures;
the charge-discharge control strategy uses an optimization algorithm which specifically predicts and controls the MPC by a model to control the charge rate, the discharge power and the charge cut-off voltage parameters, reduces the rate and the amplitude of the rise of the temperature of the battery pack and reduces the thermal runaway risk by optimally adjusting the charge-discharge process of the battery pack, and obtains the optimal control strategy by referring to the multi-factor relationship comprising the temperature, the current and the voltage so as to achieve the effects of effectively controlling the temperature of the battery and reducing the thermal runaway risk.
3. The battery thermal runaway early warning protection system according to claim 1, wherein the thermistor acquires the resistance value of the thermistor periodically or in real time through a voltage dividing circuit and a bridge circuit, acquires an accurate temperature value through a table look-up or interpolation mode by using a temperature-resistance curve, performs moving average filtering by adopting a digital filtering algorithm, performs error compensation by comparing the measured values of other temperature sensors, and improves the accuracy and stability of measurement;
the temperature sensor is arranged in the battery pack, measurement data of the temperature sensor is transmitted to the battery management unit for processing through the serial communication interface SPI, temperature measurement errors are corrected through a table look-up, interpolation or polynomial fitting mode according to nonlinear characteristics of the temperature sensor, a known temperature source is used for calibration, and sensor measurement values are corrected and adjusted to improve measurement data reliability.
4. The battery thermal runaway early warning protection system according to claim 1, wherein the battery pack partitioning sub-module divides the battery pack into a plurality of areas based on a division algorithm by referring to the positions, connection modes and capacities of the batteries, and ensures the relative balance of the number of batteries in each area;
the region independent monitoring submodule is arranged inside each region and monitors the state of each single battery in the region in real time, including voltage monitoring, temperature monitoring and current monitoring;
when thermal runaway occurs, the fault positioning sub-module identifies the abnormal battery or area by monitoring the voltage, temperature and current parameters of each area of the battery pack, uses an abnormality detection algorithm, combines the physical model and historical data of the battery pack, uses a multi-factor analysis algorithm to determine which battery or area is likely to be the main cause of the fault, designs a positioning strategy to determine the position of the fault battery according to the abnormality detection result and the multi-factor analysis result, and performs judgment based on the voltage difference, the temperature change and the current abnormality factor, and fuses the data of the area monitoring sub-module with the fault positioning algorithm to position the fault.
5. The battery thermal runaway early warning protection system according to claim 1, wherein the intelligent protection measures adopt a rule-based risk assessment algorithm, judge the degree of risk according to real-time monitoring data and output of a prediction model, and refer to the change trend and threshold of temperature, current and voltage indexes, evaluate the thermal runaway risk of the battery pack, and automatically adjust the protection measures when the system detects that the battery pack has the thermal runaway risk, including cutting off the connection between the battery pack and an external circuit, reducing the battery charge and discharge rate, and starting a cooling system;
the personalized protection strategy establishes personalized protection measures for each area according to the thermal runaway risk of each area and actual conditions, wherein the actual conditions comprise the temperature, the voltage and the internal resistance parameters of the single battery, and the personalized protection measures comprise adjusting a protection threshold value, changing the charge and discharge rate and setting a temperature alarm limit.
6. The battery thermal runaway early warning protection method is characterized by comprising the following steps of:
analyzing the temperature data of the battery pack by using a deep learning model, and predicting a thermal runaway event;
the self-adaptive protection strategy and the fuzzy logic control algorithm are applied to dynamically adjust the protection parameters, so that the method is suitable for different environments;
optimizing a charge-discharge strategy by adopting a model predictive control algorithm, reducing the temperature rising rate and reducing the thermal runaway risk;
monitoring the temperature of the battery by using a thermistor and a temperature sensor, and timely transmitting data to a battery management unit;
abnormal batteries and fault reasons are identified through the partition battery monitoring units, and protection measures are automatically adjusted according to thermal runaway risks based on intelligent protection measures and personalized protection strategies.
7. The battery thermal runaway warning protection method of claim 6, wherein the step of predicting a thermal runaway event specifically comprises:
introducing a data enhancement technology in a data preprocessing stage, including random cutting, rotation, scaling and translation, and expanding a training data set;
processing the battery pack temperature data using a deep neural network architecture that draws attention mechanisms to capture important spatiotemporal features in the temperature data;
learning an implicit representation of the battery pack temperature data by generating an antagonism network GAN;
combining current, voltage and humidity data, carrying out multi-mode data fusion and analysis, and obtaining more comprehensive information;
model evaluation is performed and the trained and evaluated model is applied to real-time data to predict thermal runaway events of the battery pack in real-time.
8. The battery thermal runaway warning protection method according to claim 6, wherein the step of optimizing the charge-discharge strategy by using the model predictive control algorithm specifically comprises:
collecting temperature data, current data and voltage data of a battery pack, establishing a deep learning-based cyclic neural network (RNN) model, and training historical data;
based on the temperature prediction result, generating an optimized charge-discharge strategy through a model prediction control algorithm, and applying the generated optimized charge-discharge strategy to an actual battery system.
9. The method for thermal runaway warning protection of a battery according to claim 6, wherein the step of transmitting data to the battery management unit comprises:
transmitting the battery temperature data measured by the sensor to a battery management unit through a cable or wireless transmission mode;
converting the sensor signal into a temperature value, and performing unit conversion and data verification;
comparing the battery temperature data with a preset threshold value in combination with other information in the system to evaluate the thermal runaway risk;
based on the temperature data and the thermal runaway risk assessment results, the battery management unit monitors the status of the battery in real time and triggers an alarm when needed.
10. The battery thermal runaway warning protection method according to claim 6, wherein the step of identifying abnormal batteries and causes of faults specifically comprises:
based on the data collected by the battery monitoring unit, developing a fault diagnosis algorithm to detect and identify abnormal batteries and fault reasons;
applying the developed fault diagnosis algorithm to the monitoring data, and carrying out abnormality detection on the battery state of each partition;
identifying a fault cause by data association, feature extraction and fault mode aiming at the detected abnormal battery;
and adopting corresponding measures to repair or replace the affected battery.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310897113.5A CN116722249A (en) | 2023-07-20 | 2023-07-20 | Battery thermal runaway early warning protection system and protection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310897113.5A CN116722249A (en) | 2023-07-20 | 2023-07-20 | Battery thermal runaway early warning protection system and protection method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116722249A true CN116722249A (en) | 2023-09-08 |
Family
ID=87869892
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310897113.5A Pending CN116722249A (en) | 2023-07-20 | 2023-07-20 | Battery thermal runaway early warning protection system and protection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116722249A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117244196A (en) * | 2023-11-17 | 2023-12-19 | 杭州高特电子设备股份有限公司 | Fire control method and device for energy storage battery, computer equipment and storage medium |
| CN117310519A (en) * | 2023-11-30 | 2023-12-29 | 交通运输部东海航海保障中心上海航标处 | Energy storage battery leakage-proof detection device and system for new energy navigation mark |
| CN117349596A (en) * | 2023-12-04 | 2024-01-05 | 深圳汉德霍尔科技有限公司 | Battery abnormal state monitoring and early warning system based on multiple sensors |
| CN117495109A (en) * | 2023-12-29 | 2024-02-02 | 国网山东省电力公司禹城市供电公司 | Electricity stealing user identification system based on deep well network |
| CN117554825A (en) * | 2024-01-11 | 2024-02-13 | 深圳市北测检测技术有限公司 | Charging safety performance detection method and system for electric automobile |
| CN117783885A (en) * | 2024-02-23 | 2024-03-29 | 福建省宇安机电设备有限公司 | Electrochemical mechanism-based energy storage battery thermal runaway prediction method and system |
| CN117799498A (en) * | 2024-03-01 | 2024-04-02 | 湘潭南方电机车制造有限公司 | Comprehensive protection system for explosion-proof storage battery electric locomotive |
| CN117783885B (en) * | 2024-02-23 | 2024-05-10 | 福建省宇安机电设备有限公司 | Electrochemical mechanism-based energy storage battery thermal runaway prediction method and system |
-
2023
- 2023-07-20 CN CN202310897113.5A patent/CN116722249A/en active Pending
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117244196B (en) * | 2023-11-17 | 2024-02-20 | 杭州高特电子设备股份有限公司 | Fire control method and device for energy storage battery, computer equipment and storage medium |
| CN117244196A (en) * | 2023-11-17 | 2023-12-19 | 杭州高特电子设备股份有限公司 | Fire control method and device for energy storage battery, computer equipment and storage medium |
| CN117310519A (en) * | 2023-11-30 | 2023-12-29 | 交通运输部东海航海保障中心上海航标处 | Energy storage battery leakage-proof detection device and system for new energy navigation mark |
| CN117310519B (en) * | 2023-11-30 | 2024-02-13 | 交通运输部东海航海保障中心上海航标处 | Energy storage battery leakage-proof detection device and system for new energy navigation mark |
| CN117349596A (en) * | 2023-12-04 | 2024-01-05 | 深圳汉德霍尔科技有限公司 | Battery abnormal state monitoring and early warning system based on multiple sensors |
| CN117349596B (en) * | 2023-12-04 | 2024-03-29 | 深圳汉德霍尔科技有限公司 | Battery abnormal state monitoring and early warning system based on multiple sensors |
| CN117495109A (en) * | 2023-12-29 | 2024-02-02 | 国网山东省电力公司禹城市供电公司 | Electricity stealing user identification system based on deep well network |
| CN117495109B (en) * | 2023-12-29 | 2024-03-22 | 国网山东省电力公司禹城市供电公司 | Power stealing user identification system based on neural network |
| CN117554825B (en) * | 2024-01-11 | 2024-03-19 | 深圳市北测检测技术有限公司 | Charging safety performance detection method and system for electric automobile |
| CN117554825A (en) * | 2024-01-11 | 2024-02-13 | 深圳市北测检测技术有限公司 | Charging safety performance detection method and system for electric automobile |
| CN117783885A (en) * | 2024-02-23 | 2024-03-29 | 福建省宇安机电设备有限公司 | Electrochemical mechanism-based energy storage battery thermal runaway prediction method and system |
| CN117783885B (en) * | 2024-02-23 | 2024-05-10 | 福建省宇安机电设备有限公司 | Electrochemical mechanism-based energy storage battery thermal runaway prediction method and system |
| CN117799498A (en) * | 2024-03-01 | 2024-04-02 | 湘潭南方电机车制造有限公司 | Comprehensive protection system for explosion-proof storage battery electric locomotive |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116722249A (en) | Battery thermal runaway early warning protection system and protection method thereof | |
| CN111060821B (en) | Battery management system and method with early warning function of lithium battery fault | |
| CN116435634B (en) | Storage battery temperature state monitoring and management system | |
| KR20180028467A (en) | Li-ion battery safety monitoring | |
| CN107942255B (en) | Transformer substation storage battery state evaluation method based on data fusion technology | |
| CN116961186A (en) | Lithium battery control system and control method thereof | |
| CN111928901A (en) | Early warning system and method for power exchange cabinet | |
| CN115979349A (en) | Power station space environment monitoring method and system | |
| CN116198349A (en) | Charging method of lithium battery system | |
| CN111428984A (en) | Risk early warning and analysis method of intelligent safety electricity utilization management system | |
| CN114167296A (en) | Device and method for monitoring remote charging and discharging nuclear capacity of storage battery | |
| CN117577975A (en) | Remote management system for lithium battery BMS | |
| CN116488300A (en) | Multifunctional mobile equipment charging protection device | |
| CN116885766A (en) | Control method and system for grid-connected operation of distributed power supply | |
| CN113572161B (en) | Energy storage system on-line state monitoring and evaluating method for disaster-resistant and bottom-protected power grid | |
| AU2020103212A4 (en) | IoT AND MACHINE LEARNING-BASED POWER DISTRIBUTION MANAGEMENT SYSTEM | |
| CN116794540A (en) | Battery performance prejudging method, device and storage medium | |
| CN116087775A (en) | Method for evaluating safety state of battery and battery management system | |
| CN112255554A (en) | Direct current system battery health status and internal fault monitoring device | |
| CN114537213B (en) | Power battery processing method, device, equipment and storage medium | |
| Zhang et al. | Research on fault diagnosis and safety early warning strategy of electric vehicle charge and discharge based on artificial intelligence | |
| CN116879794B (en) | Energy storage power failure detection early warning system | |
| CN114760137B (en) | Method and system for evaluating cooperative situation of information side and physical side of information physical system of active power distribution network aiming at network attack | |
| CN116593902B (en) | Fault diagnosis method based on fusion of performance parameters of iron lithium battery into AI model | |
| CN117410597B (en) | Intelligent potential safety hazard monitoring and processing method and system applied to energy storage power supply |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |