CN116387661A - Lithium battery safety operation and maintenance management system and lithium battery health state assessment method - Google Patents
Lithium battery safety operation and maintenance management system and lithium battery health state assessment method Download PDFInfo
- Publication number
- CN116387661A CN116387661A CN202310060033.4A CN202310060033A CN116387661A CN 116387661 A CN116387661 A CN 116387661A CN 202310060033 A CN202310060033 A CN 202310060033A CN 116387661 A CN116387661 A CN 116387661A
- Authority
- CN
- China
- Prior art keywords
- lithium battery
- health
- battery
- lithium
- maintenance management
- 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
- 229910052744 lithium Inorganic materials 0.000 title claims abstract description 345
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 title claims abstract description 344
- 230000036541 health Effects 0.000 title claims abstract description 130
- 238000012423 maintenance Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000012544 monitoring process Methods 0.000 claims abstract description 41
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 238000013210 evaluation model Methods 0.000 claims description 33
- 230000015556 catabolic process Effects 0.000 claims description 14
- 238000006731 degradation reaction Methods 0.000 claims description 14
- 239000006185 dispersion Substances 0.000 claims description 8
- 230000017525 heat dissipation Effects 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000009471 action Effects 0.000 claims description 3
- 230000003862 health status Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000004146 energy storage Methods 0.000 abstract description 13
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000013527 convolutional neural network Methods 0.000 description 37
- 238000012549 training Methods 0.000 description 11
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 8
- 229910001416 lithium ion Inorganic materials 0.000 description 8
- 239000000284 extract Substances 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 238000012300 Sequence Analysis Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000004927 fusion Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000000306 recurrent effect Effects 0.000 description 2
- 241000288105 Grus Species 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000383 hazardous chemical Substances 0.000 description 1
- 231100000206 health hazard Toxicity 0.000 description 1
- 150000002641 lithium Chemical class 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Secondary Cells (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention discloses a lithium battery safety operation and maintenance management system and a lithium battery health state assessment method, which overcome the problems that potential safety hazards of a lithium battery are not considered when a lithium battery fault is detected in the prior art, detection results are inaccurate, and when the health state of the lithium battery is predicted, the correlation among different characteristics is ignored, so that the accuracy of the predicted results is lower, and the system comprises: the lithium battery serial-parallel network comprises a plurality of battery packs, and realizes automatic cutting-off when a potential safety hazard exists in one battery pack and replacement of the battery pack by a standby battery pack; the lithium battery controller is used for collecting lithium battery operation parameters of the lithium battery serial-parallel network and uploading the collected lithium battery operation parameters to the lithium battery intelligent operation and maintenance management unit; and the intelligent operation and maintenance management unit for the lithium battery is used for completing the on-line operation monitoring and the health state evaluation of the series-parallel network of the lithium battery. The prediction precision of the lithium battery health state is improved, and the safe and economical operation of the lithium battery energy storage system is realized.
Description
Technical Field
The invention relates to the technical field of safe operation and maintenance of lithium batteries, in particular to a safe operation and maintenance management system of a lithium battery and a health state evaluation method of the lithium battery.
Background
The lithium ion battery energy storage system has the advantages of high energy efficiency, high response speed and the like, and is widely applied to the fields of intelligent energy network construction, terminal energy utilization electrification, renewable energy large-scale access and the like. With the increasing size of energy storage systems, the realization of intelligent safe operation and maintenance of lithium battery energy storage systems has become a trend. However, because the lithium battery has high requirements on the use environment and conditions, safety accidents can sometimes happen, and as the use times are increased, potential safety hazards or obvious degradation phenomena can occur to the lithium battery. Therefore, it is necessary to monitor the online safe operation condition of the lithium battery in real time, track and evaluate the state of health (SOH) and the remaining service life (remaining useful life, RUL) in real time, and rapidly switch the backup battery pack when the performance degradation or the potential safety hazard exists in the lithium battery pack, so as to ensure the safe and normal operation of the system.
At present, the research on the safe operation of the lithium battery is mainly divided into online fault detection and residual life prediction of the lithium battery. The online fault detection mainly comprises the steps of monitoring the charging voltage and temperature of a battery, performing fault alarm and switching the standby battery when the voltage and the temperature exceed a certain threshold range, and calculating the residual capacity (SOC) through the battery current. But this approach does not take into account the potential health hazards of the battery.
The method for predicting the health state of the lithium battery mainly comprises a model-based method, however, most of models in the methods directly stack an LSTM network or a CNN or simply splice different extracted features, so that on one hand, the correlation between the different features is ignored, the accuracy of a predicted result is low, and on the other hand, the characteristics of different network structure layers are not fully utilized.
In addition, a single lithium battery cannot meet the requirements of practical application scenes, and in the practical use process, a plurality of lithium batteries are usually required to be connected in parallel in a fixed series-parallel manner to form a lithium battery pack or a lithium battery network. However, since the lithium battery has potential safety hazards due to long-time overcharge, overdischarge and long-time high-temperature operation in long-term use, once a certain single lithium battery has performance degradation, the fixed serial-parallel connection method can only stop the operation of the whole lithium battery network, and the safe and economical operation of the lithium battery energy storage system cannot be realized.
Disclosure of Invention
The invention aims to overcome the problems that potential safety hazards of a lithium battery are not considered when the lithium battery is detected to be faulty in the prior art, the detection result is inaccurate, and the correlation among different characteristics is ignored when the health state of the lithium battery is predicted, so that the accuracy of the predicted result is low; meanwhile, the potential safety hazard of the lithium battery pack can be found in real time by adopting the lithium battery pack, switching can be carried out when the lithium battery fails, the whole network can still normally operate, and the safe and economical operation of the lithium battery energy storage system is realized.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a lithium battery safety operation and maintenance management system, comprising:
the lithium battery serial-parallel network comprises a plurality of battery packs, and under the control of the intelligent operation and maintenance management unit of the lithium battery, the automatic cutting-off of one battery pack when potential safety hazards exist is realized, and the battery packs are used for replacing the potential safety hazards;
the lithium battery controller is used for collecting lithium battery operation parameters of the lithium battery serial-parallel network and uploading the collected lithium battery operation parameters to the lithium battery intelligent operation and maintenance management unit;
and the lithium battery intelligent operation and maintenance management unit is used for completing on-line operation monitoring and health state evaluation of the lithium battery serial-parallel network according to the lithium battery operation parameters acquired by the lithium battery controller.
The lithium battery pack controller is designed, and online operation parameters of the lithium battery are collected, so that potential safety hazards of the lithium battery pack can be found in real time, and sudden safety faults can be found in time; the designed lithium battery network structure can flexibly switch the standby battery pack, and can dynamically and rapidly switch the standby battery pack when sudden safety accidents or serious performance degradation of the lithium battery occur, so that the whole lithium battery network can still operate, the situation that the emergency is prevented is not only achieved, a new way is provided for the economic operation of the lithium battery energy storage system, and the safe and economic operation of the lithium battery energy storage system is realized.
Preferably, the lithium battery serial-parallel network comprises M rows and N columns of lithium battery packs, and each lithium battery pack is formed by connecting a plurality of single batteries in series; the lithium battery packs of each row are connected in parallel, and the last row of lithium battery packs is used as a standby row; the lithium battery packs of each row are connected in series; the last action of each column of battery packs is that column of battery packs; each battery pack and each column of battery packs is configured with a change-over switch.
Each battery pack and each column of battery packs are provided with a change-over switch, and in normal operation, the lithium battery network has M-1 rows and N-1 columns, and when a certain battery pack has potential safety hazard, the battery pack is automatically cut off and replaced by a standby battery pack in the column; when the batteries in a certain column need maintenance, the column is cut off and switched to a standby column.
Preferably, the lithium battery controller includes:
the battery pack monitoring module is used for collecting charging voltage and current of the lithium batteries in the lithium battery serial-parallel network and transmitting the collected voltage and current data to the control module;
the temperature acquisition module is used for acquiring the temperature of the lithium batteries in the lithium battery series-parallel network and transmitting the acquired temperature data to the control module;
and the control module is used for starting the heat dissipation module of the lithium battery controller to cool when the temperature of the lithium battery exceeds a threshold value.
The control module is used for realizing operation and maintenance monitoring of the lithium battery serial-parallel network, and the control module is used for transmitting the lithium battery charging voltage and current acquired by the battery pack monitoring module and the lithium battery temperature acquired by the temperature acquisition module, and the control module is used for controlling the heat dissipation module to operate. The lithium battery controller transmits the collected lithium battery operation parameters (charging voltage, charging current and battery surface temperature) to the lithium battery intelligent operation and maintenance management unit of the upper computer through a communication interface (for example, a CAN interface).
Preferably, the lithium battery intelligent operation and maintenance management unit includes:
the on-line operation monitoring module judges whether the single lithium battery has potential safety hazards according to the operation parameters of the lithium battery, and disconnects the lithium battery pack with the potential safety hazards to switch the standby battery pack;
and the lithium battery health state evaluation module is used for estimating the electric capacity of the lithium battery according to the operation parameters of the lithium battery, predicting the health state SOH of the lithium battery and the residual service life RUL of the lithium battery, disconnecting the lithium battery pack with serious performance degradation, and switching the standby battery pack.
The high-efficiency practical lithium battery network safety operation and maintenance system provided by the invention can discover potential safety hazards of the lithium battery pack in real time, and the designed lithium battery network structure can flexibly switch the standby battery pack.
A lithium battery state of health assessment method comprising the steps of:
s1: constructing a GRU-CNN-based lithium battery health state evaluation model;
s2: the health factors of the lithium battery are used as an input time sequence of an evaluation model, a gating circulation module GRU of the evaluation model is utilized to process the input time sequence in parallel, time sequence characteristics are extracted, the health factors at the next moment are predicted, and CNN is adopted to map the health factor characteristics extracted by the GRU to a higher-dimensional characteristic space;
s3: and predicting the state of health SOH and the residual service life RUL of the lithium battery by using the lithium battery state of health evaluation model to realize the evaluation of the state of health of the lithium battery.
According to the invention, firstly, a GRU-CNN-based lithium battery health state evaluation model is constructed, then, health factors (including charging current, charging voltage and battery temperature of the lithium battery) of the lithium battery are utilized as input features of the model, and finally, the degradation condition (the health state SOH and the residual service life RUL) of the lithium battery is predicted in advance by the lithium battery health state evaluation model.
The lithium battery health state assessment model takes health factors as an input time sequence of the model, a gating circulation unit GRU respectively processes the time sequence in parallel, extracts time sequence characteristics, predicts the health factors at the next moment, and adopts CNN to map the health factor characteristics extracted by the GRU to a higher-dimensional characteristic space. And introducing the GRU into time sequence analysis, comprehensively considering time sequences of different health factors, and processing the GRU characteristic map after splicing and fusion by using a CNN network, so that the network can learn the correlation among the health factors. The prediction error is smaller, and the accuracy of lithium battery health state assessment and prediction is improved.
Preferably, in the step S3, predicting the lithium battery health state SOH by using the lithium battery health state estimation model further includes:
a1: acquiring lithium battery monitoring data, performing z-score standardized pretreatment on the original lithium battery monitoring data, and unifying dimensions to obtain lithium battery health factors;
a2: extracting time sequence characteristic information of the lithium battery health factor by using a gate control circulation module GRU, and forming a new indirect health factor;
a3: characteristic stitching is carried out on the extracted indirect health factors, and the extracted indirect health factors are used as input of a CNN network;
a4: and outputting the predicted battery capacity through a fully connected network, and calculating the residual capacity of the lithium battery predicted by the evaluation model by using the ratio of the predicted battery capacity to the initial capacity to obtain the predicted value of the state of health SOH of the lithium battery.
The GRU-CNN lithium battery health state evaluation model provided by the invention firstly uses mutually parallel GRU modules to respectively extract time sequence information of current, voltage and temperature, so that the manual extraction of characteristics is avoided, and the robustness of the system can be improved. The three extraction branches run in parallel without interference, and are finally spliced together through a feature fusion technology to form features with higher dimensionality. The CNN network can compensate for the spatial features that the GRU lacks. Because of the inherent relation among different monitoring data in the process of charging and discharging the lithium battery, the GRU is simply used to extract information across the characteristics, so that the CNN network is used to make up for the missing spatial characteristics. Three direct health factors in the charge-discharge cycle of the lithium battery, namely charging current, charging voltage and temperature, are comprehensively considered, the time sequence of the three monitoring data is used as the input of a GRU (Gated Recurrent Unit) network to extract an indirect health factor, and then the indirect health factor and SOH are fitted through the CNN (Convolutional Neural Network) network.
Preferably, in the step A1, for the time series of the lithium battery monitoring data, performing linear variation by using dispersion normalization, and setting the numerical result within the interval of [0,1 ]; the standard calculation formula of the dispersion is as follows:
wherein x is t For monitoring data (current, voltage or temperature) at time t, x max For the maximum value of the monitored data, x min The minimum value of the data is monitored for the item.
And performing z-score standardized pretreatment on the original lithium battery monitoring data, and unifying dimensions.
Preferably, when extracting the time series characteristic information, sequentially extracting vectors with fixed length by adopting a sliding window with fixed length; each gate cycle module GRU contains two GRU units, each of which upscales the received time series vector.
The GRU (Gate Recurrent Unit gating circulating unit) is a variant of LSTM (Long Short-Term Memory), is a circulating neural network model widely applied to time series processing, can obtain performance equivalent to LSTM with smaller parameter quantity under the condition of full adjustment of super parameters, has simpler GRU structure, and has fewer training samples and better prediction effect compared with LSTM. According to the invention, GRU and CNN are combined to construct a lithium battery health state assessment model.
Preferably, the predicting the remaining service life RUL of the lithium battery by using the lithium battery health state evaluation model further comprises: and calculating the charge-discharge cycle times required by the lithium battery to decay from the current residual capacity to the failure threshold value after a certain charge-discharge cycle by utilizing the predicted residual capacity of the lithium battery, and predicting the residual service life RUL of the lithium battery.
The GRU-CNN-based lithium battery health state evaluation model can well model the relation between the time sequence characteristics of health factors and the capacity change of the lithium battery, and improves the prediction accuracy.
Therefore, the invention has the following beneficial effects: 1. introducing the GRU into time sequence analysis, comprehensively considering time sequences of different health factors, and processing, splicing and fusing GRU characteristic graphs by using a CNN (computer numerical network), so that the network can learn the correlation among the health factors, and the prediction accuracy of the health state of the lithium battery is improved; 2. the lithium battery pack is adopted, the potential safety hazard of the lithium battery pack can be found in real time, the switching can be carried out when the lithium battery fails, the whole network can still normally operate, and the safe and economical operation of the lithium battery energy storage system is realized; 3. the method realizes the accurate and rapid assessment of the safety operation of the lithium battery on the safety line and the health state, and provides technical support for the reliable, stable and safe operation of the lithium battery energy storage system.
Drawings
Fig. 1 is a schematic diagram of a system structure of a lithium battery safety operation and maintenance management system in the present invention.
Fig. 2 is a flowchart showing the steps of the lithium battery state-of-health evaluation method according to the present invention.
Fig. 3 is a schematic structural diagram of a GRU-CNN-based lithium battery health status assessment model according to the present invention.
Fig. 4 is a graph of MAE values for various numbers of training samples for a B0005 battery in an example.
Fig. 5 is a B0005 battery RUL prediction result in an embodiment.
Fig. 6 is a B0006 battery RUL prediction result in the embodiment.
In the figure: 1. a lithium battery series-parallel network; 2. a lithium battery controller; 3. the intelligent operation and maintenance management unit of the lithium battery; 4. a lithium battery pack; 5. a temperature acquisition module; 6. a battery pack monitoring module; 7. a heat dissipation module; 8. a control module; 9. an online operation monitoring module; 10. and a lithium battery health state evaluation module.
Detailed Description
The invention is described in further detail below with reference to the attached drawings and detailed description:
embodiment one:
the embodiment is a lithium battery safety operation and maintenance management system, as shown in fig. 1, including: the lithium battery intelligent operation and maintenance management system comprises a lithium battery serial-parallel network 1, a lithium battery controller 2 and a lithium battery intelligent operation and maintenance management unit 3, wherein the lithium battery serial-parallel network is connected with the lithium battery controller, and the lithium battery controller is connected with the lithium battery intelligent operation and maintenance management unit.
The lithium battery serial-parallel network comprises a plurality of battery packs, and under the control of the lithium battery intelligent operation and maintenance management unit, the automatic cutting-off of a certain battery pack when potential safety hazards exist is realized, and the battery packs are used for replacing the potential safety hazards; the lithium battery controller collects lithium battery operation parameters of the lithium battery serial-parallel network and uploads the collected lithium battery operation parameters to the lithium battery intelligent operation and maintenance management unit; and the intelligent operation and maintenance management unit of the lithium battery completes the on-line operation monitoring and the health state evaluation of the series-parallel network of the lithium battery according to the lithium battery operation parameters acquired by the lithium battery controller.
The invention designs the lithium battery pack controller, acquires the on-line operation parameters of the lithium battery, can find the potential safety hazard of the lithium battery pack in real time, and can find the sudden safety fault in time; the designed lithium battery network structure can flexibly switch the standby battery pack, and can dynamically and rapidly switch the standby battery pack when sudden safety accidents or serious performance degradation of the lithium battery occur, so that the whole lithium battery network can still operate, the situation that the emergency is prevented is not only achieved, a new way is provided for the economic operation of the lithium battery energy storage system, and the safe and economic operation of the lithium battery energy storage system is realized.
Specific:
1. and the lithium battery is connected in series and parallel.
The lithium battery serial-parallel network comprises M rows and N columns of lithium battery packs, wherein each lithium battery pack is formed by connecting a plurality of single batteries in series (in the embodiment, each lithium battery pack is formed by connecting 12 single batteries in series); the lithium battery packs of each row are connected in parallel, and the last row of lithium battery packs is used as a standby row; the lithium battery packs of each row are connected in series; the last action of each column of battery packs is that column of battery packs; each battery pack and each column of battery packs is configured with a change-over switch.
In normal operation, the lithium battery network has M-1 rows and N-1 columns, and when a certain battery pack has potential safety hazard, the battery pack is automatically cut off and replaced by a standby battery pack in the column; when the batteries in a certain column need maintenance, the column is cut off and switched to a standby column.
2. A lithium battery controller.
The lithium battery controller comprises a battery pack monitoring module 6, a temperature acquisition module 5, a control module 8 and a heat dissipation module 7, wherein the battery pack monitoring module and the temperature acquisition module are connected with the lithium battery pack, the control module is connected with the battery pack monitoring module, the temperature acquisition module and the heat dissipation module, and the heat dissipation module is connected with the lithium battery pack.
The battery pack monitoring module is used for collecting charging voltage and current of the lithium battery in the lithium battery serial-parallel network and transmitting the collected voltage and current data to the control module, and the battery pack monitoring module in the embodiment adopts an LTC6804 chip and a peripheral circuit connected with the chip; the temperature acquisition module is used for acquiring the temperature of the lithium batteries in the lithium battery series-parallel network and transmitting the acquired temperature data to the control module; the control module starts the heat dissipation module of the lithium battery controller to cool when the temperature of the lithium battery exceeds a threshold value, and in the embodiment, the control module adopts a singlechip.
The lithium battery controller transmits the acquired lithium battery operation parameters to lithium battery intelligent operation and maintenance management system software of the upper computer through the communication interface; and the intelligent operation and maintenance management system software of the lithium battery is used as an intelligent operation and maintenance management unit of the lithium battery.
3. And the intelligent operation and maintenance management unit of the lithium battery.
The lithium battery intelligent operation and maintenance management unit comprises an online operation monitoring module 9 and a lithium battery health state evaluation module 10, wherein the online operation monitoring module is connected with the lithium battery controller and the lithium battery serial-parallel network respectively, and the lithium battery health state evaluation module is connected with the lithium battery controller and the lithium battery serial-parallel network respectively.
When the lithium battery pack is in operation, the online operation monitoring module judges whether the single lithium battery has potential safety hazards according to the operation parameters of the lithium battery, and disconnects the lithium battery pack with the potential safety hazards to switch the standby battery pack; and the lithium battery health state evaluation module is used for estimating the electric capacity of the lithium battery according to the operation parameters of the lithium battery, predicting the health state SOH of the lithium battery and the residual service life RUL of the lithium battery, disconnecting the lithium battery pack with serious performance degradation, and switching the standby battery pack.
According to the invention, the potential safety hazard of the lithium battery is found in time by monitoring the voltage and the surface temperature of the lithium battery on line, and the safety operation and maintenance controller of the lithium battery pack is used for rapidly switching the standby battery pack when the performance degradation or the potential safety hazard exists in the lithium battery pack. The method realizes the accurate and rapid assessment of the safety operation of the lithium battery on the safety line and the health state, and provides technical support for the reliable, stable and safe operation of the lithium battery energy storage system.
The high-efficiency practical lithium battery network safe operation and maintenance system provided by the invention not only can monitor the online safe operation condition of the lithium battery in real time, but also can accurately evaluate the health state of the lithium battery in time, and automatically switch the standby battery when the potential safety hazard is found, so as to ensure the safe and normal operation of the system.
The embodiment also provides a lithium battery health state evaluation method, as shown in fig. 2, comprising the following steps: firstly, constructing a GRU-CNN-based lithium battery health state evaluation model; secondly, taking the health factor of the lithium battery as an input time sequence of an evaluation model, utilizing a gate control circulation module GRU of the evaluation model to process the input time sequence in parallel, extracting time sequence characteristics, predicting the health factor at the next moment, and adopting CNN to map the health factor characteristics extracted by the GRU to a higher-dimensional characteristic space; and thirdly, predicting the state of health SOH and the residual service life RUL of the lithium battery by using a lithium battery state of health evaluation model to realize the evaluation of the state of health of the lithium battery.
According to the invention, firstly, a GRU-CNN-based lithium battery health state evaluation model is constructed, then, health factors (including charging current, charging voltage and battery temperature of the lithium battery) of the lithium battery are utilized as input features of the model, and finally, the degradation condition (the health state SOH and the residual service life RUL) of the lithium battery is predicted in advance by the lithium battery health state evaluation model. And introducing the GRU into time sequence analysis, comprehensively considering time sequences of different health factors, and processing the GRU characteristic map after splicing and fusion by using a CNN network, so that the network can learn the correlation among the health factors. The prediction error is smaller, and the accuracy of lithium battery health state assessment and prediction is improved.
The method for evaluating the health state of the lithium battery is further described below:
the first step: and constructing a GRU-CNN-based lithium battery health state evaluation model.
The structure of the lithium battery health state evaluation model based on the GRU-CNN is shown in fig. 3, 3 health factors, namely charging voltage, charging current and charging temperature, are selected as input time sequences of the model, and 3 gating cycle units GRU respectively process the 3 time sequences in parallel, extract time sequence characteristics and further predict current, voltage and temperature values at the next moment.
And a second step of: and taking the health factor of the lithium battery as an input time sequence of an evaluation model, utilizing a gate control circulation module GRU of the evaluation model to process the input time sequence in parallel, extracting time sequence characteristics, predicting the health factor at the next moment, and mapping the health factor characteristics extracted by the GRU to a higher-dimensional characteristic space by adopting CNN.
Given that GRUs are not good at generalizing these predictive data and fitting their relationship to capacity. According to the embodiment, the CNN is used for mapping the health factor characteristics extracted by the GRU to a higher-dimensional characteristic space, and the CNN can capture the local spatial characteristics of the spliced characteristic diagram and simultaneously the GRU can extract the time sequence characteristics of the global sequence, so that the lithium battery health state assessment model based on the GRU-CNN can well model the relationship between the time sequence characteristics of the health factor and the lithium battery capacity change, and the prediction accuracy is improved.
And a third step of: and predicting the state of health SOH and the residual service life RUL of the lithium battery by using the lithium battery state of health evaluation model to realize the evaluation of the state of health of the lithium battery.
1. And predicting the state of health SOH of the lithium battery by using the lithium battery state of health evaluation model.
A1: acquiring lithium battery monitoring data, performing z-score standardized pretreatment on the original lithium battery monitoring data, unifying dimensions to obtain lithium battery health factors, and improving comparability of the data;
for the time sequence of the lithium battery monitoring data, performing linear change by using dispersion standardization, and enabling a numerical result to fall in a [0,1] interval; the standard calculation formula of the dispersion is as follows:
wherein x is t For monitoring data (current, voltage or temperature) at time t, x max For the maximum value of the monitored data, x min The minimum value of the data is monitored for the item.
A2: extracting time sequence characteristic information of three health factors of the lithium battery by using three parallel gating circulation modules GRU, and forming new indirect health factors; in this embodiment, when extracting time sequence feature information, a fixed length sliding window is adopted to sequentially extract vectors with fixed length; each gate cycle module GRU contains two GRU units, each of which upscales the received time series vector.
A3: the extracted indirect health factors are subjected to characteristic splicing and serve as input of a CNN network, so that the network can capture deeper local characteristics more sharply, and the accuracy of network prediction can be improved by utilizing the spatial characteristics of the spliced characteristic diagrams.
A4: and outputting the predicted battery capacity through a fully connected network, and calculating the residual capacity of the lithium battery predicted by the evaluation model by using the ratio of the predicted battery capacity to the initial capacity to obtain the predicted value of the state of health SOH of the lithium battery.
The state of health SOH of the lithium battery is mainly characterized by physical quantities such as the internal resistance, capacity or peak power of the lithium battery and is used for judging the performance degradation degree of the lithium ion battery. The capacity of the lithium ion battery has a good continuous degradation trend, and the capacity is used as an important parameter capable of directly representing the current capacity of the lithium ion battery for storing electric energy and is widely used as an evaluation index of the health state of the lithium ion battery. Typically, the predicted value of SOH for a lithium battery is calculated from the ratio of battery capacity predicted by a state of health assessment model to initial capacity.
The present embodiment first selects 3 health factors: the time sequence of the charging voltage, the charging current and the charging temperature is input into a lithium battery health state evaluation model of the GRU-CNN, then the battery capacity predicted by the model is converted into a lithium battery health state SOH value, and the SOH value is used as a predicted true value index, so that the influences of factors such as different cycle modes and different residual life of the lithium battery can be reduced, and the accuracy of residual life prediction is further improved.
2. And predicting the residual service life RUL of the lithium battery by using the lithium battery health state evaluation model.
The remaining service life RUL of the lithium battery refers to the number of charge-discharge cycles required for the lithium battery to decay from the current remaining capacity to the failure threshold after a certain charge-discharge cycle.
Based on the relationship between SOH and RUL, the present embodiment converts SOH data in the original cyclic data into RUL data and retrains as a label value for network training, and predicts RUL.
And calculating the charge-discharge cycle times required by the lithium battery to decay from the current residual capacity to the failure threshold value after a certain charge-discharge cycle by utilizing the predicted residual capacity of the lithium battery, and predicting the residual service life RUL of the lithium battery.
The lithium battery health state evaluation method of the present application is analyzed by specific examples as follows:
this example uses NASA's 18650 type lithium battery dataset that includes a set of four lithium ion batteries (B0005, B0006, B0007, B0018) operating in three different modes of operation, charge, discharge and impedance, at room temperature. The charging mode was performed at a constant current of 1.5A until the battery voltage reached 4.2V, and then charging was continued in the constant voltage mode until the charging current was reduced to 20mA. The discharge mode was performed at a constant current of 2A until the voltages of the four batteries were reduced to 2.7V,2.5V,2.2V and 2.5V, respectively. Repeated charge and discharge cycles result in accelerated aging of the battery, which is manifested in a decay in battery capacity. The test stops when the battery reaches an end of life (EOL) standard, i.e., the capacity decays to 70% of rated capacity.
In this embodiment, the SOH value average absolute error (Mean Absolute Error, MAE) is selected as an index to evaluate and train the model:
wherein m is the total number of monitoring points, y i Representing the true SOH value at time iThe SOH predicted value at time i is indicated.
For the time sequence of the lithium battery monitoring data (current, voltage and temperature), linear change is carried out by using dispersion standardization, and the numerical result falls in the [0,1] interval so as to improve the calculation speed of the model. The standard calculation formula of the dispersion is as follows:
wherein x is t For monitoring data (current, voltage or temperature) at time t, x max For the maximum value of the monitored data, x min The minimum value of the data is monitored for the item.
After preprocessing data, the embodiment adopts a time slider window with the length of 10 and the step length of 1, sequentially intercepts training samples with the fixed length of 10 as input of a GRU-CNN evaluation model, and predicts the state quantity and the hidden state at the current moment.
In order to verify the accuracy of predicting the SOH of the lithium ion battery by the GRU-CNN model, the embodiment selects a ConvLSTM network and a BP network as comparison because the LSTM network and the BP network are commonly used for predicting the health state of the lithium ion battery.
Taking a B0005 battery pack as an example, the present embodiment analyzes the influence of the number of training samples on the model predictive performance: when the number of training samples of the training set is 80, 100 and 120 respectively, the prediction performance of the model is evaluated, and the corresponding MAE index is shown in FIG. 4.
When the training sample is 100, the average prediction error MAE of the GRU-CNN lithium battery health state evaluation model is minimum, and when the training sample number is increased from 100 to 120, the performance of the GRU-CNN model is slightly reduced along with the increase of the training sample number. Therefore, the present embodiment selects the number of training samples to be 100.
The model is often not fit well due to outliers in the battery prediction of B0005. Therefore, taking the B0005 as an example, the step length is set to 100, and the MAE and RMSE of the three models are evaluated, and the results are shown in the following table, so that the MAE and RMSE of the GRU-CNN model of the present invention are obviously smaller than those of the other two models, which also indicates that the prediction accuracy is higher.
Comparison of predicted results of different methods under the condition that the step length of the B0005 battery pack is 100:
Method | MAE | RMSE |
BP | 0.0723% | 2.69% |
ConvLSTM | 0.0429% | 2.07% |
GRU-CNN | 0.0135% | 1.16% |
in this example, using the B0005 and B0006 battery packs as an example, the prediction accuracy of the remaining RUL of the lithium battery with the increase of the number of charging cycles was analyzed, and the results are shown in fig. 5 and 6. As can be seen from fig. 5 and 6, as the cycle number of the lithium battery increases, the prediction curve more conforms to the real RUL decreasing trend and shows a stronger linear relationship. After 130 cycles, the remaining battery life RUL (i.e., the number of remaining charges) is substantially reduced to within 2.
The table below gives the actual RUL and predicted RUL values for the B0005 battery at 81, 101, 131 and 161 cycles, respectively, and calculates the average error. It can be seen that the RUL prediction error gradually decreases with increasing number of charging cycles, and the average prediction error is less than 2%.
GRU-CNN predicts the remaining useful life of B0005 battery:
according to the invention, potential safety hazards of the lithium battery are timely found by on-line monitoring of the voltage and the surface temperature of the lithium battery, an on-line evaluation model of the health state of the lithium battery based on GRU-CNN is provided, and the working voltage, the current and the environmental temperature of the lithium battery are used as input characteristics of the model to predict the degradation condition of the lithium battery in advance. And introducing the GRU into time sequence analysis, comprehensively considering time sequences of different health factors, and processing the GRU characteristic map after splicing and fusion by using a CNN network, so that the network can learn the correlation among the health factors. The lithium battery health state assessment model provided by the invention has smaller prediction error for the SOH lithium battery, and improves the accuracy of lithium battery health state assessment prediction.
The above-described embodiment is only a preferred embodiment of the present invention, and is not limited in any way, and other variations and modifications may be made without departing from the technical aspects set forth in the claims.
Claims (9)
1. A lithium battery safety operation and maintenance management system, comprising:
the lithium battery serial-parallel network comprises a plurality of battery packs, and under the control of the intelligent operation and maintenance management unit of the lithium battery, the automatic cutting-off of one battery pack when potential safety hazards exist is realized, and the battery packs are used for replacing the potential safety hazards;
the lithium battery controller is used for collecting lithium battery operation parameters of the lithium battery serial-parallel network and uploading the collected lithium battery operation parameters to the lithium battery intelligent operation and maintenance management unit;
and the lithium battery intelligent operation and maintenance management unit is used for completing on-line operation monitoring and health state evaluation of the lithium battery serial-parallel network according to the lithium battery operation parameters acquired by the lithium battery controller.
2. The lithium battery safety operation and maintenance management system according to claim 1, wherein the lithium battery serial-parallel network comprises M rows and N columns of lithium battery packs, and each lithium battery pack is formed by connecting a plurality of single batteries in series; the lithium battery packs of each row are connected in parallel, and the last row of lithium battery packs is used as a standby row; the lithium battery packs of each row are connected in series; the last action of each column of battery packs is that column of battery packs;
each battery pack and each column of battery packs is configured with a change-over switch.
3. The lithium battery safety operation and maintenance management system according to claim 1 or 2, wherein the lithium battery controller comprises:
the battery pack monitoring module is used for collecting charging voltage and current of the lithium batteries in the lithium battery serial-parallel network and transmitting the collected voltage and current data to the control module;
the temperature acquisition module is used for acquiring the temperature of the lithium batteries in the lithium battery series-parallel network and transmitting the acquired temperature data to the control module;
and the control module is used for starting the heat dissipation module of the lithium battery controller to cool when the temperature of the lithium battery exceeds a threshold value.
4. The lithium battery safety operation and maintenance management system according to claim 1 or 2, wherein the lithium battery intelligent operation and maintenance management unit comprises:
the on-line operation monitoring module judges whether the single lithium battery has potential safety hazards according to the operation parameters of the lithium battery, and disconnects the lithium battery pack with the potential safety hazards to switch the standby battery pack;
and the lithium battery health state evaluation module is used for estimating the electric capacity of the lithium battery according to the operation parameters of the lithium battery, predicting the health state SOH of the lithium battery and the residual service life RUL of the lithium battery, disconnecting the lithium battery pack with serious performance degradation, and switching the standby battery pack.
5. A lithium battery health state assessment method applied to the lithium battery safety operation and maintenance management system as claimed in any one of claims 1 to 4, and characterized by comprising the following steps:
s1: constructing a GRU-CNN-based lithium battery health state evaluation model;
s2: the health factors of the lithium battery are used as an input time sequence of an evaluation model, a gating circulation module GRU of the evaluation model is utilized to process the input time sequence in parallel, time sequence characteristics are extracted, the health factors at the next moment are predicted, and CNN is adopted to map the health factor characteristics extracted by the GRU to a higher-dimensional characteristic space;
s3: and predicting the state of health SOH and the residual service life RUL of the lithium battery by using the lithium battery state of health evaluation model to realize the evaluation of the state of health of the lithium battery.
6. The method according to claim 5, wherein in the step S3, predicting the SOH of the lithium battery using the lithium battery state of health estimation model further comprises:
a1: acquiring lithium battery monitoring data, performing z-score standardized pretreatment on the original lithium battery monitoring data, and unifying dimensions to obtain lithium battery health factors;
a2: extracting time sequence characteristic information of the lithium battery health factor by using a gate control circulation module GRU, and forming a new indirect health factor;
a3: characteristic stitching is carried out on the extracted indirect health factors, and the extracted indirect health factors are used as input of a CNN network;
a4: and outputting the predicted battery capacity through a fully connected network, and calculating the residual capacity of the lithium battery predicted by the evaluation model by using the ratio of the predicted battery capacity to the initial capacity to obtain the predicted value of the state of health SOH of the lithium battery.
7. The method for evaluating the health status of a lithium battery according to claim 6, wherein in the step A1, for the time series of the monitoring data of the lithium battery, linear variation is performed by using dispersion normalization, and the numerical result falls within the interval [0,1 ]; the standard calculation formula of the dispersion is as follows:
wherein x is t For the monitoring data at time t, x max For the maximum value of the monitored data, x min The minimum value of the data is monitored for the item.
8. The method for evaluating the health status of a lithium battery according to claim 5, 6 or 7, wherein, when extracting the time-series characteristic information, a fixed-length vector is sequentially extracted using a fixed-length sliding window; each gate cycle module GRU contains two GRU units, each of which upscales the received time series vector.
9. The method for estimating a state of health of a lithium battery according to claim 5, 6 or 7, wherein predicting the remaining service life RUL of the lithium battery using the lithium battery state of health estimation model further comprises: and calculating the charge-discharge cycle times required by the lithium battery to decay from the current residual capacity to the failure threshold value after a certain charge-discharge cycle by utilizing the predicted residual capacity of the lithium battery, and predicting the residual service life RUL of the lithium battery.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310060033.4A CN116387661A (en) | 2023-01-18 | 2023-01-18 | Lithium battery safety operation and maintenance management system and lithium battery health state assessment method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310060033.4A CN116387661A (en) | 2023-01-18 | 2023-01-18 | Lithium battery safety operation and maintenance management system and lithium battery health state assessment method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116387661A true CN116387661A (en) | 2023-07-04 |
Family
ID=86970100
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310060033.4A Pending CN116387661A (en) | 2023-01-18 | 2023-01-18 | Lithium battery safety operation and maintenance management system and lithium battery health state assessment method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116387661A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117458010A (en) * | 2023-12-20 | 2024-01-26 | 超耐斯(深圳)新能源集团有限公司 | Lithium battery energy storage monitoring system based on data analysis |
CN117706406A (en) * | 2024-02-05 | 2024-03-15 | 安徽布拉特智能科技有限公司 | Lithium battery health state monitoring model, method, system and storage medium |
CN117825973A (en) * | 2024-03-01 | 2024-04-05 | 深圳市健网科技有限公司 | Lithium battery state estimation method and system for distributed energy storage system |
-
2023
- 2023-01-18 CN CN202310060033.4A patent/CN116387661A/en active Pending
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117458010A (en) * | 2023-12-20 | 2024-01-26 | 超耐斯(深圳)新能源集团有限公司 | Lithium battery energy storage monitoring system based on data analysis |
CN117458010B (en) * | 2023-12-20 | 2024-04-02 | 超耐斯(深圳)新能源集团有限公司 | Lithium battery energy storage monitoring system based on data analysis |
CN117706406A (en) * | 2024-02-05 | 2024-03-15 | 安徽布拉特智能科技有限公司 | Lithium battery health state monitoring model, method, system and storage medium |
CN117706406B (en) * | 2024-02-05 | 2024-04-16 | 安徽布拉特智能科技有限公司 | Lithium battery health state monitoring model, method, system and storage medium |
CN117825973A (en) * | 2024-03-01 | 2024-04-05 | 深圳市健网科技有限公司 | Lithium battery state estimation method and system for distributed energy storage system |
CN117825973B (en) * | 2024-03-01 | 2024-05-17 | 深圳市健网科技有限公司 | Lithium battery state estimation method and system for distributed energy storage system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116387661A (en) | Lithium battery safety operation and maintenance management system and lithium battery health state assessment method | |
CN114050633B (en) | Dynamic management and control method and device for lithium battery energy storage system and electronic equipment | |
CN113156917B (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
CN104198942B (en) | A kind of online judgement system of analysing valve control type lead-acid accumulator battery failure | |
CN106199450A (en) | A kind of battery health evaluation system and method | |
CN116660759B (en) | Battery life prediction method and device based on BMS battery management system | |
CN113629856B (en) | Intelligent power supply management method and system for deep sea mobile platform battery | |
CN114252716A (en) | Power grid fault diagnosis method and device and storage medium | |
CN108646184B (en) | Internal damage detection device and method based on initial discharge characteristics of storage battery | |
CN117054892B (en) | Evaluation method, device and management method for battery state of energy storage power station | |
CN111525197B (en) | Storage battery SOH real-time estimation system and method | |
CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product | |
CN116400239B (en) | Intelligent energy storage monitoring method for iron-chromium flow battery | |
CN115825756B (en) | Multi-stage fault diagnosis method and system for distributed energy storage power station | |
CN116298947B (en) | Storage battery nuclear capacity monitoring device | |
CN117491872A (en) | Reconfigurable battery module fault multistage diagnosis method | |
CN111391694A (en) | Multi-level rapid data monitoring method and system for operation and maintenance of charging station | |
CN113949618B (en) | Communication fault early warning system based on big data | |
CN113866644A (en) | Method and device for predicting usable time and capacity of battery | |
Kim et al. | Artificial intelligence-based hardware fault detection for battery balancing circuits | |
CN209927995U (en) | Battery pack open circuit detection device | |
CN113572161A (en) | Online state monitoring and evaluating method for energy storage system of disaster-resistant bottom-protecting power grid | |
CN110556918A (en) | Transformer substation storage battery monitoring method and system | |
CN115864596A (en) | 12V lithium battery management method | |
CN117665621A (en) | Full life cycle on-line measuring system of storage battery |
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 |