CN116047300A - Controller for predicting characteristic parameters of battery and method thereof - Google Patents
Controller for predicting characteristic parameters of battery and method thereof Download PDFInfo
- Publication number
- CN116047300A CN116047300A CN202211318676.6A CN202211318676A CN116047300A CN 116047300 A CN116047300 A CN 116047300A CN 202211318676 A CN202211318676 A CN 202211318676A CN 116047300 A CN116047300 A CN 116047300A
- Authority
- CN
- China
- Prior art keywords
- battery
- characteristic parameter
- controller
- voltage
- models
- 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 34
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000012706 support-vector machine Methods 0.000 claims abstract description 11
- 238000012544 monitoring process Methods 0.000 claims abstract description 9
- 230000008859 change Effects 0.000 claims abstract description 8
- 230000036541 health Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 9
- 230000015654 memory Effects 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 5
- 210000002569 neuron Anatomy 0.000 claims description 5
- 229910001416 lithium ion Inorganic materials 0.000 description 12
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 238000010801 machine learning Methods 0.000 description 8
- 239000013598 vector Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 241000288105 Grus Species 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 125000004122 cyclic group Chemical group 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/382—Arrangements for monitoring battery or accumulator variables, e.g. SoC
- G01R31/3835—Arrangements for monitoring battery or accumulator variables, e.g. SoC involving only voltage measurements
Abstract
A controller 110 and method to predict characteristic parameters of a battery 102 are provided. Wherein the controller 110 is configured to: monitoring at least one voltage discharge cycle 114 (shown in fig. 2) of the battery 102; extracting a variable comprising a start voltage and a time change (Δt) corresponding to a voltage drop (Δv) from the start voltage to the end voltage; processing variables through a first set of pre-trained models 116 including Extreme Learning Machines (ELMs) and Support Vector Machines (SVMs); and predicting a first characteristic parameter of the battery 102 based on the first set of pre-trained models 116. The previous state of the battery 102 is unknown and only the current state is measured and processed to determine the first characteristic parameter. The output of the first characteristic parameter is also used to predict the second characteristic parameter.
Description
Technical Field
The present invention relates to a controller and a method for predicting a characteristic parameter of a battery.
Background
As the world is moving towards electric vehicles, the capacity storage capability of the battery is becoming extremely important. Lithium ion (Li-ion) batteries are very important in almost every field involving capacity storage. The battery has certain desirable characteristics, such as its light weight and high energy density. Some disadvantages are high manufacturing costs and short life. This requires extensive research into the focus of different kinds of lithium ion batteries, their modeling and life prediction to avoid inefficiency, equipment damage and accidents. Health management and monitoring of lithium ion batteries is critical to the proper operation of the device and continuous monitoring of the batteries is not always possible. Predicting future capacity and Remaining Useful Life (RUL) with uncertainty quantification is a critical but challenging problem in battery health diagnostic and management applications.
According to the prior art, CN112684363 discloses a lithium ion battery health state estimation method based on a discharging process. The invention discloses a lithium ion battery health state estimation method based on a discharging process, and belongs to the field of lithium ion batteries. The method comprises the following steps: 1, performing cyclic charge and discharge experiments on a lithium ion battery, wherein the cyclic charge and discharge experiments comprise a constant-current charge process, a constant-voltage charge process and a constant-current discharge process, and recording average discharge temperature, current, voltage, time and capacity data acquired in each process; 2, extracting three health factors, namely an equal voltage discharge time difference, an equal time discharge voltage difference and an average discharge temperature, taking the health factors as input vectors, and taking output vectors as battery SOH;3, processing the extracted three health factors by a principal component analysis method, reducing an input vector formed by the three health factors into two dimensions, and guiding the input vector into a bidirectional extreme learning machine for training; and 4, performing principal component analysis processing on the three extracted health factors under the online condition to obtain an input vector of the bidirectional extreme learning machine, and performing model output to obtain the battery SOH. The method is simple, convenient and accurate.
Drawings
Embodiments of the present disclosure are described with reference to the following drawings,
FIG. 1 illustrates a block diagram of a system including a controller to predict a characteristic parameter of a battery in accordance with an embodiment of the present invention;
FIG. 2 illustrates a discharge cycle diagram of a battery for deriving features according to an embodiment of the invention; and
fig. 3 illustrates a method for predicting characteristic parameters of a battery according to the present invention.
Detailed Description
Fig. 1 illustrates a block diagram of a system including a controller to predict characteristic parameters of a battery according to an embodiment of the present invention. Wherein the controller 110 is configured to: monitoring at least one voltage discharge cycle 114 (shown in fig. 2) of the battery 102; extracting a variable comprising a start voltage, a time change (Δt) corresponding to a voltage drop (Δv) from the start voltage to the end voltage; processing variables through a first set of pre-trained models 116 including Extreme Learning Machines (ELMs) and Support Vector Machines (SVMs); and predicting a first characteristic parameter of the battery 102 as an output 122 based on the first set of pre-trained models 116. The previous state of the battery 102 is unknown and only the current state is measured and processed to determine the first characteristic parameter.
The controller 110 takes the input as a single voltage discharge cycle 114 of the battery 102, performs feature extraction using Machine Learning (ML) techniques, and processes through a first set of pre-trained models 116 including ELM and SVR to predict a first characteristic parameter. The first set of pre-training models 116 is trained using the collected data sets or data sets available for different types of batteries 102. Feature engineering is performed for different variables and the best relevant variable is selected to estimate the first characteristic parameter.
According to an embodiment of the invention, the controller 110 is configured to predict the second characteristic parameter. The controller 110 receives values of the first characteristic parameter from the first set of pre-trained models 116 as inputs including a previous value, a current value, and a next value derived from the voltage discharge cycle 114. The controller 110 processes the values through a second set of pre-trained models 118 including long-short term memory (LSTM) and gated current cells (GRUs) and predicts a second characteristic parameter of the battery 102 as an output 122 in addition to the first characteristic parameter. The first characteristic parameter of the battery 102 is state of health (SOH), and the second characteristic parameter of the battery 102 is remaining life (RUL). In addition, for ELM, the number of hidden neurons is selected to be six and activation is selected to be sigmoid. However, the number of hidden neurons and activation is configurable as desired.
The controller 110 is connected/provided with necessary signal detection, acquisition and processing circuitry along with sensors (if needed). The controller 110 includes memory elements 112 such as Random Access Memory (RAM) and/or Read Only Memory (ROM), analog to digital converters (ADCs) (and vice versa, digital to analog converters (DACs)), clocks, timers, counters, and at least one processor (capable of machine learning) that are connected to each other and to other components through a communication bus channel. The memory element 112 has pre-stored logic or instructions or programs or applications or modules/models and/or thresholds that are accessed by at least one processor in accordance with defined routines. The internal components of the controller 110 are not explained as prior art and should not be construed in a limiting manner. The controller 110 may also include a communication unit to communicate with external devices such as cloud computing units, remote servers, etc., through wireless or wired means such as global system for mobile communications (GSM), 3G, 4G, 5G, wi-Fi, bluetooth, ethernet, serial networks, and the like.
According to an embodiment of the present invention, the controller 110 is at least one selected from the group consisting of an internal device and an external device. The internal device is at least one selected from a Battery Management System (BMS) 104, a Vehicle Control Unit (VCU) 106, and the external device is at least one selected from a cloud server 108 and a user device. In the case of an internal device, the BMS 104 receives signals directly from the battery 102 and provides outputs regarding the first and second characteristic parameters. Similarly, the VCU 106 receives the necessary signals from the BMS 104, and the BMS 104 monitors the discharge voltage cycle 114 of the battery 102 to provide an output regarding the first characteristic parameter and the second characteristic parameter. Alternatively, the BMS 104 and VCU 106 together are used to process the voltage discharge cycle 114 to provide an output. In the case of an external device, the cloud server 108 receives signals from the vehicle 120 through a telematics unit (not shown) or through a user device. Similarly, the user device receives signals from the telematics unit. The connection between the user device, cloud server 108 and telematics unit is established using known suitable wired or wireless communication means such as, but not limited to, bluetooth TM Wi-Fi, universal Serial Bus (USB), GSM, 3G, 4G, 5G, and the like.
Fig. 2 illustrates a discharge cycle diagram of a battery for deriving features according to an embodiment of the invention. The X-axis 202 represents time and the Y-axis 204 represents voltage, both in suitable units. Thus, the resulting curve 208 is the voltage discharge cycle 114 from the starting voltage 206 until the ending voltage. The end voltage is either zero or a value before zero, as desired. The change in voltage is represented by a decreasing constant value (e.g., 0.10 volts) or a variable value Δv, and the corresponding change Δt in time is measured. In the figure, three time differences, i.e. Δt, are measured for three ΔV with constant voltage drop 1 、Δt 2 And Deltat 3 . These are three consecutive values, wherein the three consecutive values of the first characteristic parameter are derived/obtained using the first set of pre-trained models 116.
According to the invention, the operation of the invention is envisaged. The controller 110 is the BMS 104 of the vehicle 120. The vehicle 120 is driven by the driver from a particular starting voltage until it discharges. Thus, the battery 102 discharges over a single drive cycle or multiple drive cycles. The controller 110 monitors the voltage discharge cycle 114 of the battery 102 and extracts variables including the starting voltage and time change, as explained above. The variables are fed into a first set of pre-trained models 116 comprising ELMs and SVMs and an output comprising predicted values of the first characteristic values is obtained. Three consecutive values of the first characteristic value are taken and fed into a second set of pre-trained models 118 comprising LSTM and GRU, and predicted values of the second characteristic parameter are obtained. Here, the values of the first characteristic parameter and the second characteristic parameter are predicted using only the current voltage discharge cycle 114 without using the history or past information of the battery 102. An example of a vehicle 120 is provided, however, battery 102-based appliances are equally possible.
Fig. 3 illustrates a method for predicting characteristic parameters of a battery according to the present invention. The method includes a plurality of steps, wherein step 302 includes monitoring at least one voltage discharge cycle 114 of the battery 102. Step 304 includes extracting a variable including a start voltage and a time change (Δt) corresponding to a voltage drop (Δv) from the start voltage to the end voltage. Step 306 includes processing the variable through a first set of pre-trained models 116 including an Extreme Learning Machine (ELM) and a Support Vector Machine (SVM). Step 308 includes predicting a first characteristic parameter of the battery 102 based on the first set of pre-trained models 116.
The method further includes a step 310, the step 310 including receiving values of the first characteristic parameter from the first set of pre-trained models 116 as inputs including a previous value, a current value, and a next value derived from the voltage discharge cycle 114. Step 314 includes processing the values through a second set of pre-training models 118, the second set of pre-training models 118 including Long Short Term Memory (LSTM) and gated current cells (GRUs). Step 316 includes predicting a second characteristic parameter of the battery 102 using the second set of pre-trained models 118.
The first characteristic parameter of the battery 102 is state of health (SOH), and the second characteristic parameter of the battery 102 is Remaining Useful Life (RUL). The method is performed/implemented using only one current-voltage discharge cycle without using any other history or characteristics of the battery 102. The method is implemented by the controller 110, the controller 110 being at least one selected from the group consisting of an internal device and an external device. The internal device is at least one selected from a Battery Management System (BMS) 104, a Vehicle Control Unit (VCU) 106, and the external device is at least one selected from a cloud server 108 and a user device. In addition, for ELM, the number of hidden neurons is selected to be six and activation is selected to be sigmoid.
According to an embodiment of the present invention, an intelligent based method is provided to estimate SOH and RUL of a lithium ion battery 102 having an unknown state. The SOH amount determines the life of a given battery 102. RUL is the time required to reach 70-80% of its original value. The controller 110 uses advanced machine learning model based SOH-RUL estimation of the lithium ion battery 102, which creates a good business in the field of electric vehicles (BEV) operated by the battery 102 and other industrial/home appliances using the lithium ion battery 102. An integrated intelligent data driven model for SOH and RUL estimation is provided. The controller 110 and method enable comprehensive data analysis of the aging of the battery 102 using the most advanced algorithms for extracting features from the analysis. No past information about the battery 102 is used or needed, and therefore the first and second characteristic parameters are evaluated and predicted based on the unknown state of the battery 102.
The controller 110 and method continuously predicts SOH and RUL for the battery 102 for which the previous state is unknown. Feature extraction was performed using correlation analysis and variables were selected after the comprehensive study. The present invention provides a framework that can be used to determine SOH and RUL using only information from the current voltage discharge cycle 114 of the battery 102 without monitoring the operation that has previously occurred. The most advanced machine learning algorithms are tested using a flexible framework, selecting ELM and SVR combinations for SOH estimation, and LSTM and GRU combinations for RUL prediction. The dataset of the lithium-ion battery 102 is used to evaluate performance, which allows the model to be configured with the highest accuracy, providing accurate and reliable estimation/prediction results. The proposed invention combines both SOH and RUL predictions for the battery 102. Furthermore, the prediction does not require any prior information about the battery 102. The proposed data driven approach allows RUL prediction even though past health monitoring has not been completed. The ML model is used for benchmarking purposes and care must be taken that it can be modified, refined, and made better for both SOH and RUL predictions. The proposed framework allows to adapt to such modifications. Integration of advanced machine learning algorithms like ELM, LSTM further improves performance and also helps to overcome the limitations of traditional machine learning models.
It should be understood that the embodiments explained in the above description are illustrative only and do not limit the scope of the present invention. Many such embodiments are contemplated, as well as other modifications and variations in the embodiments explained in the description. The scope of the invention is limited only by the scope of the claims.
Claims (10)
1. A controller (110) for predicting a characteristic parameter of a battery (102), the controller (110) being configured to:
monitoring at least one voltage discharge cycle (114) of the battery (102);
extracting a variable comprising a start voltage and a time change (Δt) corresponding to a voltage drop (Δv) from the start voltage to an end voltage;
processing the variables through a first set of pre-trained models (116) including an Extreme Learning Machine (ELM) and a Support Vector Machine (SVM), and
a first characteristic parameter of the battery (102) is predicted based on the first set of pre-trained models (116).
2. The controller (110) of claim 1, configured to,
receiving values of the first characteristic parameter from the first set of pre-training models (116) as inputs, the inputs including a previous value, a current value, and a next value from the voltage discharge cycle (114);
processing the values by a second set of pre-training models (118), the second set of pre-training models (118) comprising a long-short-term memory (LSTM) and a gated current unit (GRU), an
Predicting a second characteristic parameter of the battery (102) using the second set of pre-trained models (118).
3. The controller (110) of claim 1, the controller (110) being at least one selected from the group consisting of an internal device and an external device, wherein the internal device is at least one selected from a Battery Management System (BMS) (104), a Vehicle Control Unit (VCU) (106), and the external device is at least one selected from a cloud server (108) and a user device.
4. The controller (110) of claim 1, wherein the first characteristic parameter of the battery (102) is a state of health (SOH) and the second characteristic parameter of the battery (102) is a Remaining Useful Life (RUL).
5. The controller (110) of claim 1, wherein for the ELM, the number of hidden neurons is selected to be six and the activation is selected to be sigmoid.
6. A method for predicting a characteristic parameter of a battery (102), the method comprising the steps of:
monitoring at least one voltage discharge cycle (114) of the battery (102);
extracting a variable comprising a start voltage and a time change (Δt) corresponding to a voltage drop (Δv) from the start voltage to an end voltage;
processing the variables through a first set of pre-trained models (116) including an Extreme Learning Machine (ELM) and a Support Vector Machine (SVM), and
a first characteristic parameter of the battery (102) is predicted based on the first set of pre-trained models (116).
7. The method according to claim 6, comprising
Receiving values of the first characteristic parameter from the first set of pre-trained models (116) as inputs including a previous value, a current value, and a next value derived from the voltage discharge cycle (114);
processing the values by a second set of pre-training models (118), the second set of pre-training models (118) comprising a long-short-term memory (LSTM) and a gated current unit (GRU), an
Predicting a second characteristic parameter of the battery (102) using the second set of pre-trained models (118).
8. The method of claim 7, wherein the first characteristic parameter of the battery (102) is a state of health (SOH) and the second characteristic parameter of the battery (102) is a Remaining Useful Life (RUL).
9. The method of claim 6, wherein the method is implemented by at least one selected from the group consisting of an internal device and an external device, wherein the internal device is at least one selected from a Battery Management System (BMS) (104) and a Vehicle Control Unit (VCU) (106), and the external device is at least one selected from a cloud server (108) and a user device.
10. The method of claim 6, wherein for the ELM, the number of hidden neurons is selected to be six and activation is selected to be sigmoid.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| IN202141049000 | 2021-10-27 | ||
| IN202141049000 | 2021-10-27 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116047300A true CN116047300A (en) | 2023-05-02 |
Family
ID=85796156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211318676.6A Pending CN116047300A (en) | 2021-10-27 | 2022-10-26 | Controller for predicting characteristic parameters of battery and method thereof |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116047300A (en) |
| DE (1) | DE102022211063A1 (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117054892B (en) * | 2023-10-11 | 2024-02-27 | 特变电工西安电气科技有限公司 | Evaluation method, device and management method for battery state of energy storage power station |
| CN117368777B (en) * | 2023-10-17 | 2024-03-22 | 昆明理工大学 | Lithium ion battery life prediction method and system based on small sample learning algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112684363A (en) | 2020-12-18 | 2021-04-20 | 北京工业大学 | Lithium ion battery health state estimation method based on discharge process |
-
2022
- 2022-10-19 DE DE102022211063.3A patent/DE102022211063A1/en active Pending
- 2022-10-26 CN CN202211318676.6A patent/CN116047300A/en active Pending
Also Published As
| Publication number | Publication date |
|---|---|
| DE102022211063A1 (en) | 2023-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Park et al. | LSTM-based battery remaining useful life prediction with multi-channel charging profiles | |
| Song et al. | Combined CNN-LSTM network for state-of-charge estimation of lithium-ion batteries | |
| CN110568361B (en) | Method for predicting health state of power battery | |
| US20220239122A1 (en) | Server-side characterisation of rechargeable batteries | |
| Zhao et al. | A compact methodology via a recurrent neural network for accurate equivalent circuit type modeling of lithium-ion batteries | |
| CN110398697B (en) | Lithium ion health state estimation method based on charging process | |
| KR102424528B1 (en) | Method and device to estimate state of battery | |
| CN116047300A (en) | Controller for predicting characteristic parameters of battery and method thereof | |
| CN110161425B (en) | Method for predicting remaining service life based on lithium battery degradation stage division | |
| KR102215450B1 (en) | Method and device to learn and estimate battery state information | |
| KR20160067510A (en) | Method and apparatus for estimating state of battery | |
| Mamo et al. | Long short-term memory with attention mechanism for state of charge estimation of lithium-ion batteries | |
| CN112630662B (en) | Power battery SOH estimation method based on data driving and multi-parameter fusion | |
| KR20220073829A (en) | Battery Performance Prediction | |
| CN111999648A (en) | Lithium battery residual life prediction method based on long-term and short-term memory network | |
| Xia et al. | Lithium-ion battery ageing behavior pattern characterization and state-of-health estimation using data-driven method | |
| US11835589B2 (en) | Method and apparatus for machine-individual improvement of the lifetime of a battery in a battery-operated machine | |
| Bak et al. | Accurate estimation of battery SOH and RUL based on a progressive lstm with a time compensated entropy index | |
| WO2022144542A1 (en) | Method for predicting condition parameter degradation of a cell | |
| US20230305069A1 (en) | Method for battery capacity estimation, electronic apparatus, and storage medium | |
| US20230305073A1 (en) | Method and apparatus for providing a predicted aging state of a device battery based on a predicted usage pattern | |
| CN114223084A (en) | Method for aligning data of a first control unit with a second control unit to determine an accurate prediction value | |
| CN116080470A (en) | Power battery monitoring method and device for electric automobile, server and medium | |
| CN116031508A (en) | Lithium ion battery management system and method based on deep learning | |
| CN113721151B (en) | Battery capacity estimation model and method based on double-tower deep learning network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |