AU2021101964A4 - Artificial intelligence based smart electric vehicle battery management system - Google Patents
Artificial intelligence based smart electric vehicle battery management system Download PDFInfo
- Publication number
- AU2021101964A4 AU2021101964A4 AU2021101964A AU2021101964A AU2021101964A4 AU 2021101964 A4 AU2021101964 A4 AU 2021101964A4 AU 2021101964 A AU2021101964 A AU 2021101964A AU 2021101964 A AU2021101964 A AU 2021101964A AU 2021101964 A4 AU2021101964 A4 AU 2021101964A4
- Authority
- AU
- Australia
- Prior art keywords
- battery
- battery management
- artificial intelligence
- management system
- algorithm
- 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.)
- Ceased
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 230000015556 catabolic process Effects 0.000 claims abstract description 7
- 238000006731 degradation reaction Methods 0.000 claims abstract description 7
- 238000011002 quantification Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 abstract description 13
- 238000010801 machine learning Methods 0.000 abstract description 5
- 230000032683 aging Effects 0.000 abstract description 3
- 101150052583 CALM1 gene Proteins 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 230000010354 integration Effects 0.000 abstract description 2
- 238000012423 maintenance Methods 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 23
- 238000012549 training Methods 0.000 description 9
- 238000000034 method Methods 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 229910001416 lithium ion Inorganic materials 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 101100257262 Caenorhabditis elegans soc-1 gene Proteins 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0224—Process history based detection method, e.g. whereby history implies the availability of large amounts of data
- G05B23/024—Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L58/00—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles
- B60L58/10—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries
- B60L58/16—Methods or circuit arrangements for monitoring or controlling batteries or fuel cells, specially adapted for electric vehicles for monitoring or controlling batteries responding to battery ageing, e.g. to the number of charging cycles or the state of health [SoH]
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Power Engineering (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Secondary Cells (AREA)
Abstract
ARTIFICIAL INTELLIGENCE BASED SMART ELECTRIC
VEHICLE BATTERY MANAGEMENT SYSTEM
In the current decade, electric vehicles have attracted human community due to
low cost of operation and maintenance but it can provide optimal performance only
by smart management of battery. This invention focuses on machine learning
technology for developing a self-reconfigurable, flexible and reliable model for
battery management of electric vehicles. This work gives significant solution for
the issues of battery management in electric vehicles based on the integration of
concept of artificial intelligence with grid connected vehicle. Firstly, Cyber
Physical system (CPS) is utilized for managing the issues of battery management
then a classical artificial intelligence algorithm - support vector regression (SVR)
algorithm is utilized for establishing a precise model of battery in cloud. Finally
battery degradation quantification is done based on rain-flow cycle counting
algorithm for dealing with issues related to aging of battery based on the model of
the battery.
9
CYBER SYSTEM:CL OUD-BASED
IATERYF MODEUNGYAND MONHRING
DC||p ] Cam1 alg0-tlm
ciban Kernelery mam )
Selled ) (V (WI lv Actuate
Data Command
commVneFatFin Networ
Sens or hA P
PM13ICA4L WORLD BA TER F AND YEHICLES
Figure 1. Proposed Artificial Intelligence based Battery Management System
X
X2 Ki
Support Kernel Output
Temna olae Vector Function layer
Figure 2. Support vector regression with Kernel Function and its Parameters
10
Description
ARTIFICIAL INTELLIGENCE BASED SMART ELECTRIC VEHICLE BATTERY MANAGEMENT SYSTEM In the current decade, electric vehicles have attracted human community due to
low cost of operation and maintenance but it can provide optimal performance only
by smart management of battery. This invention focuses on machine learning
technology for developing a self-reconfigurable, flexible and reliable model for
battery management of electric vehicles. This work gives significant solution for
the issues of battery management in electric vehicles based on the integration of
concept of artificial intelligence with grid connected vehicle. Firstly, Cyber
Physical system (CPS) is utilized for managing the issues of battery management
then a classical artificial intelligence algorithm - support vector regression (SVR)
algorithm is utilized for establishing a precise model of battery in cloud. Finally
battery degradation quantification is done based on rain-flow cycle counting
algorithm for dealing with issues related to aging of battery based on the model of
the battery.
DC||p ] Cam1 alg0-tlm
ciban mam Kernelery
) Selled ) (V (WI lv Actuate Data Command
commVneFatFinNetwor
Sens or hAP
PM13ICA4L WORLD BA TER F AND YEHICLES
Figure 1. Proposed Artificial Intelligence based Battery Management System
X2 Ki
Support Kernel Output Temna olae Vector Function layer
Figure 2. Support vector regression with Kernel Function and its Parameters
FORM 2
THEPATENTSACT,1970 (39 of 1970) AND THE PATENTS RULES, 2003
(See Section 10; rule 13)
The following specification particularly describes the invention and the manner in which it is to be performed
Description
Major component of electric vehicles (EV) are battery power and its
management system as for EVs challenging issue is to develop self reconfigurable,
flexible and reliable battery management system (BMS). As the volume of dataset
is insufficient for building accurate battery model in BMS vehicles, Cyber Physical
System (CPS) is utilized for multi-function control method utilized for multi
resources as it is widely used in smart homes, cloud computation and big data
centers. In this invention, machine learning based battery management system of
electric vehicle is proposed utilizing CPS.
Aging of batteries has greater impact on battery output hence lifetime
prediction of batteries is of major concern, hence conventionally fractional order
model and electrochemical model are utilized to predict lifetime of batteries.
Analysis of fatigue damage of batteries along with life prediction and energy
storage capability can be analyzed by rain flow counting, hence in this invention
quantification of battery degradation is done using rain flow counting algorithm.
Support vector regression (SVR) algorithm is a novel machine learning method
which works on principle of structural risk minimization is utilized in this work for
modeling of battery in an optimal way.
In this invention, novel CPS-BMS Battery Management system proposed
utilizing network physics for improving reliability and stability in dynamic and
multivariable environment based on characteristics of CPS system such as high
data storage capacity, high computation power and high real time data
transmission. Firstly a cloud based Cyber system is developed for BMS for storing
the electric vehicle battery data in real time. A conjunction working mode between
Vehicle BMS (V-BMS) and Cloud BMS (C-BMS) is built by utilizing ability of
communication of information of CPS in this work for improving the accuracy and
working efficiency of V-BMS.
Physically a transmission module is added in vehicles along with ordinary
BMS system. The phenomenon of degradation in lithium ion battery is affected
mainly by depth of discharge and cycle number. Analysis of fatigue data is done by
rain-flow cycle-counting algorithm which is conventionally used for estimation of
metal fatigue by recording the number of cycles along with its corresponding
amplitude. Support vector regression (SVR) algorithm is utilized for implementing
the model of battery management system where the internal operation of SVR
algorithm is done by a special kernel function mapping the input data to high
dimensional space based on the characteristics of the input data of the battery
management system.
" In this invention, input to the battery management system are terminal
voltage, temperature, current along with SoC as output as in conventional
management system, along with which total depth of discharge (TDOD) and
total number of cycles (TNOC) are considered as additional inputs for taking
battery model as impact of battery degradation.
• Cloud based battery management system approximates the function as
follows SoC= f(SOC 1,I,TU,TNOCTDOD)
• Support vector regression (SVR) algorithm has biggest difference of kernel
function layer compared to back propagation neural network.
• In kernel function layer, non linear transformation of input data occurs to a
high dimensional space where all the parameters of this layer are pre
determined before training process hence does not requires training.
• In this invention, Artificial Intelligence based algorithm namely Support
vector regression (SVR) algorithm is utilized for modeling battery
management system as its characteristics are distinguished more easily in
high dimensional space thereby improving classification accuracy and
regression. Kernel function of Support vector regression (SVR) algorithm
and its loss function are represented as follows where x and x 'represents the input data and training data point respectively, c and d are model hyper parameter.
E(n)= - - n jy-C"I< r |1y, -c,\- otherwise
K(xx) =exp( ) 11E=EVN 0,2 E =Y.E(n) Mi=1
• SVR can tolerate the maximum E deviation between the regression predicted
value yn and the sample true value c,, , where the prediction result is
considered to be correct in the interval area centered on the predicted value
y, with the width 2E with E(n) is the value of loss function during n times
training with sample c, .
• Accuracy of lithium ion battery management can be improved using the
above loss function. Error cannot be avoided if the training data comes from
the results of sensor measurements involved in battery management system.
• Overfitting problems are prone by the neural network if the error value is
used as one of the real value for training of neural network hence in turn
increases difficulty of training of the neural network.
• In SVR algorithm, slack variables are introduced where they allow data
points in regression process only within certain margin in interval of 2E.
The invention is herein described, with the accompanying block diagrams.
• Wherein:
• Figure 1. Proposed Machine Learning based Battery Management System
• Figure 2. Support vector regression with Kernel Function and its Parameters
• In this system deterioration of the battery life is avoided and reduced by
rejection of bad point data from the total set of data points in the area.
• In battery management issue, bad point problem is solved by implementing
slack variable method where it is inevitable to get bad point data to appear in
the process. Dead point data involved in the battery data cannot be
discriminated by BP network as the regression training easily breaks
relationship between mapping of input and output of original data.
• This causes BP network to get repeatedly trained without any convergence.
• SVR achieves better return results as it discards these bad point data
automatically in the total data set collected from battery data.
• The regression results of the SVR using both insensitive & slack variables
for two-dimensional data are accurate & reliable for the management system
• The data points in the area have no effect on the regression, and the bad
point data has no effect on the regression result as the slack variable exists.
• Number of these data points is much smaller than the total number of
training data. Hence SVR does under sampling instead of random sampling.
• The purpose of under sampling is to reduce the influence of noise in the
sample data on the regression effect and eliminate the influence of the dead
point hence SVR can tolerate the maximum r deviation.
Claims (6)
1. Development of Artificial Intelligence based algorithm for battery
management system is focused in this invention for electric vehicles.
2. Grid connected vehicle is integrated with concept of artificial intelligence
for managing batteries of electric vehicles.
3. In this invention, input to the battery management system is terminal
voltage, temperature, current.
4. Support vector regression (SVR) algorithm is able to model the battery
management system for reliable performance.
5. Rain flow cycle counting algorithm is able to perform battery degradation
quantification for simulating battery degradation.
6. Error from the battery management system can be reduced to less than 4%.
Figure 1. Proposed Artificial Intelligence based Battery Management System
Figure 2. Support vector regression with Kernel Function and its Parameters
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021101964A AU2021101964A4 (en) | 2021-04-16 | 2021-04-16 | Artificial intelligence based smart electric vehicle battery management system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021101964A AU2021101964A4 (en) | 2021-04-16 | 2021-04-16 | Artificial intelligence based smart electric vehicle battery management system |
Publications (1)
Publication Number | Publication Date |
---|---|
AU2021101964A4 true AU2021101964A4 (en) | 2021-06-03 |
Family
ID=76132886
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
AU2021101964A Ceased AU2021101964A4 (en) | 2021-04-16 | 2021-04-16 | Artificial intelligence based smart electric vehicle battery management system |
Country Status (1)
Country | Link |
---|---|
AU (1) | AU2021101964A4 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113752843A (en) * | 2021-11-05 | 2021-12-07 | 北京航空航天大学 | Power battery thermal runaway early warning device and method based on Saybolt physical system |
CN113771691A (en) * | 2021-11-09 | 2021-12-10 | 北京航空航天大学 | Full life cycle power battery management device and method based on Saybolt physical system |
WO2022164400A3 (en) * | 2021-11-08 | 2023-12-07 | Eatron Technologies Limited | Test method performed with design of experiment created by an artificial intelligence |
-
2021
- 2021-04-16 AU AU2021101964A patent/AU2021101964A4/en not_active Ceased
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113752843A (en) * | 2021-11-05 | 2021-12-07 | 北京航空航天大学 | Power battery thermal runaway early warning device and method based on Saybolt physical system |
WO2022164400A3 (en) * | 2021-11-08 | 2023-12-07 | Eatron Technologies Limited | Test method performed with design of experiment created by an artificial intelligence |
CN113771691A (en) * | 2021-11-09 | 2021-12-10 | 北京航空航天大学 | Full life cycle power battery management device and method based on Saybolt physical system |
CN113771691B (en) * | 2021-11-09 | 2022-02-15 | 北京航空航天大学 | Full life cycle power battery management device and method based on Saybolt physical system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | Improved anti-noise adaptive long short-term memory neural network modeling for the robust remaining useful life prediction of lithium-ion batteries | |
Hu et al. | Battery health prediction using fusion-based feature selection and machine learning | |
Liu et al. | Towards long lifetime battery: AI-based manufacturing and management | |
AU2021101964A4 (en) | Artificial intelligence based smart electric vehicle battery management system | |
Zhang et al. | A deep learning method for lithium-ion battery remaining useful life prediction based on sparse segment data via cloud computing system | |
Li et al. | A comparative study of battery state-of-health estimation based on empirical mode decomposition and neural network | |
Mamo et al. | Long short-term memory with attention mechanism for state of charge estimation of lithium-ion batteries | |
Li et al. | On-line estimation method of lithium-ion battery health status based on PSO-SVM | |
Sanz-Gorrachategui et al. | Remaining useful life estimation for LFP cells in second-life applications | |
Wang et al. | A method based on improved ant lion optimization and support vector regression for remaining useful life estimation of lithium‐ion batteries | |
Zhang et al. | Intelligent state of charge estimation of battery pack based on particle swarm optimization algorithm improved radical basis function neural network | |
Li et al. | State‐of‐health prediction for lithium‐ion batteries via electrochemical impedance spectroscopy and artificial neural networks | |
CN114636932A (en) | Method and system for predicting remaining service life of battery | |
CN115792677A (en) | Lithium ion battery life prediction method based on improved ELM | |
CN114578234A (en) | Lithium ion battery degradation and capacity prediction model considering causality characteristics | |
Yüksek et al. | A novel state of health estimation approach based on polynomial model for lithium-ion batteries | |
Mazzi et al. | Lithium-ion battery state of health estimation using a hybrid model based on a convolutional neural network and bidirectional gated recurrent unit | |
Beltran et al. | Machine learning techniques suitability to estimate the retained capacity in lithium-ion batteries from partial charge/discharge curves | |
Zhang et al. | Remaining useful life prediction of lithium-ion batteries based on TCN-DCN fusion model combined with IRRS filtering | |
Li et al. | Machine learning algorithm based battery modeling and management method: A Cyber-Physical System perspective | |
Zhang et al. | The early prediction of lithium-ion battery remaining useful life using a novel long short-term memory network | |
Upashrutti et al. | Estimation of State of Charge of EV Batteries-A Machine Learning Approach | |
Channegowda et al. | An attention‐based synthetic battery data augmentation technique to overcome limited dataset challenges | |
Jayaraman et al. | Accurate state of charge prediction for lithium-ion batteries in electric vehicles using deep learning and dimensionality reduction | |
Zequera et al. | Data Science-based Techniques for Modelling and Diagnostics of Battery Cells Based on End-of-Life criteria |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FGI | Letters patent sealed or granted (innovation patent) | ||
MK22 | Patent ceased section 143a(d), or expired - non payment of renewal fee or expiry |