CN-122017600-A - BMS battery management system

CN122017600ACN 122017600 ACN122017600 ACN 122017600ACN-122017600-A

Abstract

The invention discloses a BMS battery management system, relates to the technical field of battery management systems, and solves the technical problem that the fault type of a zinc-nickel battery cannot be accurately identified and predicted in the prior art; according to the method, the operation state evaluation coefficient and the working environment evaluation coefficient of the battery are obtained through calculation through the operation data and the environment data, whether the battery operation state early warning is carried out or not is judged based on the operation state evaluation coefficient and the preset operation state threshold value, whether the environment early warning is carried out or not is judged based on the working environment evaluation coefficient and the preset environment threshold value, the battery fault prediction model is obtained through training of the artificial intelligent model through historical battery data, the operation data of the zinc-nickel battery is detected in real time based on the battery fault prediction model, and the technical problem that the existing BMS system cannot accurately identify and predict the fault type of the zinc-nickel battery is solved.

Inventors

LI HAO
ZENG WEI
DING JINQI
XIA HAIJUN
XIA SHUHUI
ZHENG MINHONG
XU SHIBO
HU SHENGFENG
LIU XIAOYUAN
LIU BIN

Assignees

湖南超弦科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20260304

Claims (10)

1. The BMS battery management system is characterized by comprising a data acquisition module, a data analysis module, a battery early warning module and a fault prediction module; the data acquisition module is used for acquiring the operation data of the zinc-nickel battery and the environment data of the working environment of the zinc-nickel battery; the data analysis module is used for calculating and obtaining the operation state evaluation coefficient of the battery based on the operation data; The battery early warning module judges whether battery operation state early warning is carried out or not based on the operation state evaluation coefficient and a preset operation state threshold value, if yes, early warning information is sent to a user side, if not, continuous detection and judgment are carried out, wherein the user side comprises a mobile phone or a computer, and Judging whether to perform environment early warning based on the working environment evaluation coefficient and a preset environment threshold value, if so, sending early warning information to a user side, otherwise, continuously detecting and judging; The fault prediction module is used for training an artificial intelligence model based on historical battery data to obtain a battery fault prediction model, detecting operation data of the zinc-nickel battery in real time based on the battery fault prediction model to obtain a prediction result, wherein the prediction result comprises a battery health state, a battery charge state and a prediction fault type, the artificial intelligence model comprises a convolutional neural network or a deep confidence network, and And processing the battery based on the early warning information and the prediction result.
2. The BMS battery management system according to claim 1, wherein the data collection module is in communication and/or electrically connected with the data analysis module and the fault prediction module, respectively, and the data analysis module is in communication and/or electrically connected with the battery pre-warning module and the fault prediction module, respectively.
3. The BMS battery management system according to claim 1, wherein the acquiring the operation data of the zinc-nickel battery and the environmental data of the zinc-nickel battery operating environment comprises: The method comprises the steps of collecting operation data of a zinc-nickel battery and environment data of a zinc-nickel battery working environment in real time through data collecting equipment, wherein the operation data comprise the temperature of the battery, the current of the battery, the voltage of the battery, the internal resistance of the battery and the vibration frequency of the battery, and the environment data comprise the environment temperature and the environment humidity.
4. The BMS battery management system according to claim 1, wherein the calculating an operation state evaluation coefficient of the battery based on the operation data comprises: The internal resistance of the battery is marked as R, and the vibration frequency of the battery is marked as Z; by the formula: PY=A×ln (R+1) +B×e++Z/(e++Z+1), calculating to obtain an operation state evaluation coefficient of the battery; wherein PY is an operation state evaluation coefficient of the battery, A, B is a proportionality coefficient, ln # ) Is a logarithmic function based on the natural number e.
5. The BMS battery management system according to claim 1, wherein the calculating the operating environment evaluation coefficient of the battery based on the environment data comprises: marking the ambient temperature as W and the ambient humidity as H; The operation state evaluation coefficient of the battery is calculated by the formula PH=C×ln [ (W-ZW)/(2+1 ] +D× tanhH × lnH), wherein PH is the operation state evaluation coefficient of the battery, C, D is the proportionality coefficient, and tanh is # ) Is a hyperbolic tangent function, and ZW is the optimal environment temperature of the zinc-nickel battery in the working state.
6. The BMS battery management system according to claim 1, wherein the determining whether to perform battery operation state early warning based on the operation state evaluation coefficient and a preset operation state threshold value comprises: Judging whether the running state evaluation coefficient is larger than a preset running state threshold value, if so, generating running state early warning information, and if not, continuously detecting and judging, wherein the preset running state threshold value is set according to running data of an actual battery during working.
7. The BMS battery management system according to claim 1, wherein the determining whether to perform the environmental pre-warning based on the operation environment evaluation coefficient and the preset environment threshold value comprises: Judging whether the working environment evaluation coefficient is larger than a preset environment threshold value, if so, generating environment early warning information, and if not, continuously detecting and judging, wherein the preset environment threshold value is set according to the degree of the influence of the environment on the actual battery.
8. The BMS battery management system of claim 1 wherein the training artificial intelligence model based on historical battery data comprises: s1, marking initial time as t0, marking predicted time as t, and obtaining a predicted time interval t=t-t0; S2, historical battery data at t0 time and predicted time interval Integrating historical battery data at the time t into standard output data, wherein the historical battery data comprises operation data, an operation state evaluation coefficient, a working environment evaluation coefficient and environment data, wherein the initial time is the time before prediction, and the prediction time is the time required to be predicted; s3, training an artificial intelligent model based on standard input data and standard output data to obtain a data prediction model; s4, predicting the operation data of the battery based on a data prediction model to obtain a data prediction result, wherein the data prediction result comprises operation data at the time t, an operation state evaluation coefficient, a working environment evaluation coefficient and environment data; and S5, training the artificial intelligent model based on the data prediction result to obtain a battery fault prediction model.
9. The BMS battery management system of claim 8 wherein the training of the artificial intelligence model based on the data prediction results in a battery failure prediction model comprising: S1, integrating a data prediction result into standard input data, and integrating a battery health state, a battery charge state and a predicted fault type at a time corresponding to the data prediction result into standard output data, wherein the predicted fault type comprises overshoot, overdischarge, short circuit, metal precipitation, electrolyte decomposition, electrode active material falling and electrode passivation; s2, training an artificial intelligent model based on the standard input data and the standard output data to obtain a battery fault prediction model.
10. The BMS battery management system according to claim 1, wherein the processing the battery based on the pre-warning information and the prediction result comprises: The method comprises the steps of sending early warning information and a prediction result to a user side through a wireless transmission technology, displaying the early warning information and the prediction result on the user side, and processing a battery based on the operation state early warning information and the environment early warning or the prediction result, wherein the wireless transmission technology comprises 4G/5G or WIFI.

Description

BMS battery management system Technical Field The invention belongs to the field of battery management systems, and particularly relates to a BMS battery management system. Background BMS battery management system is an electronic system for monitoring and managing the health of a battery pack, especially in electric vehicles, energy storage systems, and other applications using rechargeable batteries. However, most of the current BMS battery management systems are directed at management of lithium ion batteries, and lack of a system for effectively managing zinc-nickel batteries, and the existing battery management systems can only improve the utilization rate of the zinc-nickel batteries to a low degree, and cannot accurately monitor the phenomena of overcharge and overdischarge of the zinc-nickel batteries, so that the health condition and the service life of the batteries cannot be guaranteed. The prior art (published application No. CN 116387645A) discloses a zinc-nickel battery BMS power management system, which comprises a battery protection module, a parameter detection module, an equalizing charge module, an electric quantity management module, a S0C module and an SOH module, wherein the battery protection module is used for controlling the voltage, the current, the power and the temperature of a battery, the parameter detection module is used for detecting battery parameters of the battery to obtain first detection data, the equalizing charge module is used for equalizing charge of the battery to enable each single battery in the battery to be in a synchronous working state, the electric quantity management module is used for measuring the charge electric quantity and the discharge electric quantity of the battery to obtain measurement data, the S0C module is used for monitoring the residual electric quantity of the battery to enable the battery to work in a safe state, the temperature management module is used for detecting the real-time temperature of the battery to obtain second detection data, and the SOH module is used for determining the health state of the battery according to the first detection data, the measurement data and the second detection data. The invention can realize the balance of the electric quantity at any time of charging and discharging the battery pack, ensure the health condition of the battery pack and greatly prolong the service life of the battery pack. However, the prior art does not consider that the fault diagnosis algorithm and protection strategy preset in the existing BMS system are mainly based on common fault modes of the lithium ion battery, such as overcharge, overdischarge, short circuit, and the like. However, the zinc-nickel battery has a specific failure mode, such as metal precipitation, electrolyte decomposition, etc., which results in the problem that the existing BMS cannot accurately identify and predict the specific failures. Accordingly, the present invention is directed to a BMS battery management system for solving the above-mentioned problems. Disclosure of Invention The invention aims to at least solve one of the technical problems in the prior art, and therefore, the invention provides a BMS battery management system which is used for solving the problems that a preset fault diagnosis algorithm and a protection strategy in the prior art are mainly based on common fault modes of a lithium ion battery, such as overcharge, overdischarge, short circuit and the like. However, zinc-nickel batteries have their own failure modes, such as metal precipitation, electrolyte decomposition, etc., which results in the technical problem that the existing BMS cannot accurately identify and predict these specific failures. In order to achieve the above object, a first aspect of the present invention provides a BMS battery management system, comprising a data acquisition module, a data analysis module, a battery early warning module and a fault prediction module; the data acquisition module is used for acquiring the operation data of the zinc-nickel battery and the environment data of the working environment of the zinc-nickel battery; the data analysis module is used for calculating and obtaining the operation state evaluation coefficient of the battery based on the operation data; The battery early warning module judges whether battery operation state early warning is carried out or not based on the operation state evaluation coefficient and a preset operation state threshold value, if yes, early warning information is sent to a user side, if not, continuous detection and judgment are carried out, wherein the user side comprises a mobile phone or a computer, and Judging whether to perform environment early warning based on the working environment evaluation coefficient and a preset environment threshold value, if so, sending early warning information to a user side, otherwise, continuously detecting and judging; The fault prediction module is used for trainin