Xin Wen

Accurately estimating the state of charge of a lithium-ion battery plays an important role in managing the health of a battery and estimating its charging state. Traditional state-of-charge estimation methods encounter difficulties in processing the diverse temporal data sequences and predicting adaptive results. To address these problems, we propose a spatial transformer network (STN) for multi-temperature state-of-charge estimation of lithium-ion batteries. The proposed STN consists of a convolutional neural network with a temporal–spatial module and a long short-term memory transformer network, which together are able to efficiently capture the spatiotemporal features. To train the STN under multi-temperature conditions, denoising augmentation and attention prediction are proposed to enhance the model’s generalizability within a unified framework. Experimental results show that the proposed method reduces the mean absolute error and root mean square error by 41% and 43%, respectively, compared with existing methods; in the semi-supervised setting, the respective reductions are 23% and 38%, indicating that effective extraction of the spatiotemporal features along with denoising augmentation is beneficial for estimating the state of charge and can promote the development of battery management systems using semi-supervised learning methods.

This paper presents a novel neural network-based fault detection technique applicable to a class of nonlinear systems. The adaptive observer was designed for fault detection based on a single hidden layer feed-forward wavelet neural network. In order to guarantee network convergence, the network weights are updated according to a modified back-propagation algorithm, and the Lyapunov function is introduced to ensure stability. The proposed fault detection scheme was tested on the actuators of a typical spacecraft attitude control system, and the results demonstrated the effectiveness and feasibility of the proposed observer in detecting nonlinear system failure.