State of Charge Estimation for Lithium-Ion Battery Using Recurrent NARX Neural Network Model Based Lighting Search Algorithm

被引:118
作者
Lipu, Molla S. Hossain [1 ,2 ]
Hannan, Mahammad A. [3 ]
Hussain, Aini [1 ]
Saad, Mohamad H. M. [1 ]
Ayob, Afida [1 ]
Blaabjerg, Frede [4 ]
机构
[1] Univ Kebangsaan Malaysia, Fac Engn & Built Environm, Ctr Integrated Syst Engn & Adv Technol INTEGRA, Bangi 43600, Malaysia
[2] Univ Asia Pacific, Dept Elect & Elect Engn, Dhaka 1209, Bangladesh
[3] Univ Tenaga Nas, Dept Elect Power Engn, Kajang 43000, Malaysia
[4] Aalborg Univ, Dept Energy Technol, DK-9100 Aalborg, Denmark
关键词
State of charge; lithium-ion battery; NARX neural network; lighting search algorithm; ELECTRIC VEHICLE APPLICATIONS; UNSCENTED KALMAN FILTER; EQUALIZATION CONTROLLER; FEATURE-SELECTION; STORAGE-SYSTEMS; VOLTAGE; OBSERVER; MACHINE; CELLS; GAIN;
D O I
10.1109/ACCESS.2018.2837156
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
State of charge (SOC) is one of the crucial parameters in a lithium-ion battery. The accurate estimation of SOC guarantees the safe and efficient operation of a specific application. However, SOC estimation with high accuracy is a serious concern to the automobile engineer due to the battery nonlinear characteristics and complex electrochemical reactions. This paper presents an improved nonlinear autoregressive with exogenous input (NARX)-based neural network (NARXNN) algorithm for an accurate and robust SOC estimation of lithium-ion battery which is effective and computationally rich for controlling dynamic system and predicting time series. However, the accuracy of recurrent NARXNN depends on the amount of input order, output order, and hidden layer neurons. The unique contribution of the improved recurrent NARXNN-based SOC estimation is developed using lighting search algorithm (LSA) forfinding the best value of input delays, feedback delays, and hidden layer neurons. The contributions are summarized as: 1) the computational capability of NARXNN model which does not require battery model and parameters rather only needs current, voltage, and temperature sensors; 2) the effectiveness of LSA which is verified with particle swarm optimization; 3) the adaptability, efficiency, and robustness of the model which are evaluated using FUDS and US06 drive cycles at varying temperatures conditions; and 4) the performance of the proposed model which is compared with back propagation neural network and radial basis function neural network optimized by LSA using different error statistical terms and computational time. Furthermore, a comparative analysis of SOC estimation in proposed method and existing techniques is presented for validation of NARXNN performance. The results prove that the proposed NARXNN model achieves higher accuracy with less computational time than other existing SOC algorithms under different temperature conditions and electric vehicle drive cycles.
引用
收藏
页码:28150 / 28161
页数:12
相关论文
共 39 条
[1]   Support Vector Machines Used to Estimate the Battery State of Charge [J].
Alvarez Anton, Juan Carlos ;
Garcia Nieto, Paulino Jose ;
Blanco Viejo, Cecilio ;
Vilan Vilan, Jose Antonio .
IEEE TRANSACTIONS ON POWER ELECTRONICS, 2013, 28 (12) :5919-5926
[2]  
[Anonymous], 2013, Global greenhouse gas emissions data
[3]   Evaluation of LiFePO4 Batteries for Electric Vehicle Applications [J].
Ansean, David ;
Gonzalez, Manuela ;
Garcia, Victor M. ;
Viera, Juan C. ;
Anton, Juan C. ;
Blanco, Cecilio .
IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2015, 51 (02) :1855-1863
[4]   NA Neural Network Modelling of Mushroom Dynamic Vapour Sorption Kinetics [J].
Argyropoulos, Dimitrios ;
Paraforos, Dimitris S. ;
Alex, Rainer ;
Griepentrog, Hans W. ;
Mueller, Joachim .
IFAC PAPERSONLINE, 2016, 49 (16) :305-310
[5]   Real-Time Model-Based Estimation of SOC and SOH for Energy Storage Systems [J].
Cacciato, Mario ;
Nobile, Giovanni ;
Scarcella, Giuseppe ;
Scelba, Giacomo .
IEEE TRANSACTIONS ON POWER ELECTRONICS, 2017, 32 (01) :794-803
[6]   State of Charge and State of Health Estimation for Lithium Batteries Using Recurrent Neural Networks [J].
Chaoui, Hicham ;
Ibe-Ekeocha, Chinemerem Christopher .
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY, 2017, 66 (10) :8773-8783
[7]   State-of-Charge Estimation for Lithium-Ion Batteries Using Neural Networks and EKF [J].
Charkhgard, Mohammad ;
Farrokhi, Mohammad .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2010, 57 (12) :4178-4187
[8]   Long Short-Term Memory Networks for Accurate State-of-Charge Estimation of Li-ion Batteries [J].
Chemali, Ephrem ;
Kollmeyer, Phillip J. ;
Preindl, Matthias ;
Ahmed, Ryan ;
Emadi, Ali .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2018, 65 (08) :6730-6739
[9]   State-of-charge determination from EMF voltage estimation: Using impedance, terminal voltage, and current for lead-acid and lithium-ion batteries [J].
Coleman, Martin ;
Lee, Chi Kwan ;
Zhu, Chunbo ;
Hurley, William Gerard .
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2007, 54 (05) :2550-2557
[10]   Effects of additives on thermal stability of Li ion cells [J].
Doughty, DH ;
Roth, EP ;
Crafts, CC ;
Nagasubramanian, G ;
Henriksen, G ;
Amine, K .
JOURNAL OF POWER SOURCES, 2005, 146 (1-2) :116-120