More intelligent and robust estimation of battery state-of-charge with an improved regularized extreme learning machine

Self Cite

Summary This paper investigates a Fletcher‐Reeves conjugate gradient optimized multi‐reservoir echo state network (FRCG‐MESN) to identify battery state of charge (SOC). First, an echo state network with multiple reservoirs is established to estimate battery SOC by using its discharge terminal voltage and current as the inputs, and the FR conjugate gradient algorithm is explored to tune the output weights of the MESN to avoid calculating the inverse matrix. Second, an appropriate amount of Gaussian noise with zero mean is added to the training set to prevent overfitting. Finally, a battery test platform is adopted to sample the discharging data under two working conditions: the Los Angeles 92 and the urban dynamometer driving schedule. The simulation results show that the presented FRCG‐MESN method can accurately identify the battery SOC with different initial SOCs. Applying an appropriate amount of noise to the training set can prevent overfitting efficiently.

Section: The Neural Network-based Soc Estimation Methodsmentioning

confidence: 99%

A Fletcher‐Reeves conjugate gradient optimized multi‐reservoir echo state network for state of charge estimation in vehicle battery

Wang

Jiao

2022

Self Cite

“…For example, Shu et al 12 showed an SOC prediction framework for LIB incorporating long short-term memory network and achieved good results. Wang et al 13 investigated a regularized extreme learning machine combined with optimization algorithms for intelligent and robust SOC results. However, the lack of valid experimental data and the time cost in processing data cannot give a guarantee that these ML methods are applied widely in battery states online estimation.…”

Section: Introductionmentioning

confidence: 99%

Low‐complexity state of charge and anode potential prediction for lithium‐ion batteries using a simplified electrochemical model‐based observer under variable load condition

Pang

Geng

et al. 2022

The accurate knowledge of the physics-based state of charge (SOC) and anode potential for lithium-ion batteries (LIBs) plays an essential role in the driving range prediction and charge strategy optimization of electric vehicles (EVs). However, the SOC estimation based on empirical equivalent circuit models and the lack of anode potential information makes it challenging in developing advanced battery management systems for EVs. For this reason, this paper proposes a low-complexity SOC and anode potential prediction method for LIBs using a simplified electrochemical model (SEM)-based observer under variable load condition. First, based on the Padé approximation and volume average method, a reduced-order SEM is proposed and verified. Then, a lowcomplexity proportional-integral-differential observer framework incorporating the SEM is developed to obtain the physics-based SOC and anode potential.

“…Chin et al presented an adaptive ELM based algorithm with the characteristics of online sequential to predict the battery SOC under different ambient temperatures 47 . Jiao et al explored a regularized ELM based Fletcher‐Reeves conjugate gradient algorithm to estimate battery SOC 48,49 …”

Section: Introductionmentioning

confidence: 99%

“…Jiao et al explored a regularized ELM basedFletcher-Reeves conjugate gradient algorithm to estimate battery SOC 48,49. …”

mentioning

confidence: 99%

A beetle antennae search optimized recurrent extreme learning machine for battery state of charge estimation

Wang

2022

Self Cite

Summary The extreme learning machine (ELM) is a single‐hidden layer feedforword neural network (FNN) without training hidden layer weights/biases. By constructing a recurrent extreme learning machine (Recurrent‐ELM) with time delay lines to model battery dynamic characteristics, a beetle antennae search based recursive least squares (BAS‐RLS) method is explored to online realize the state of charge (SOC) estimation. The contents include: (1) To decrease the computational burden, the ELM model with fixed hidden layer weights is adopted to model battery SOC, and a RLS algorithm is studied to online estimate SOC by using the sampled terminal voltages and currents; (2) To solve the modeling accuracy problem, a Recurrent‐ELM model with past/present voltages and currents, and past SOC as inputs is constructed by adding time delay lines to capture battery dynamic characteristics, so as to promote the battery modeling accuracy; (3) To determine suitable neuron numbers in the hidden layer, the BAS method is introduced to find the optimal neuron number in the hidden layer to promote intelligence of the Recurrent‐ELM based RLS algorithm. Simulation results indicate that the proposed model and method has high precision in SOC estimation compared with traditional method.