Lithium-ion batteries have emerged as the state-of-the-art energy storage for portable electronics, electrified vehicles, and smart grids. An enabling Battery Management System holds the key for efficient and reliable system operation, in which State-of-Charge (SOC) estimation and State-of-Health (SOH) monitoring are of particular importance. In this article, an SOC and SOH co-estimation scheme is proposed based on the fractional-order calculus. First, a fractional-order equivalent circuit model is established and parameterized using a Hybrid Genetic Algorithm/Particle Swarm Optimization method. This model is capable of predicting the voltage response with the root-mean-squared error less than 10 mV under various driving-cycle-based tests. Comparative studies show that it improves the modeling accuracy appreciably from its second- and third-order counterparts. Then, a dual fractional-order extended Kalman filter is put forward to realize simultaneous SOC and SOH estimation. Extensive experimental results show that the maximum steady-state errors of SOC and SOH estimation can be achieved within 1%, in the presence of initial deviation, noise, and disturbance. The resilience of the co-estimation scheme against battery aging is also verified through experimentation.

Electrochemical impedance spectrum (EIS) applied in fuel cell characterization and diagnosis facilitates its system management in the vehicular application, but the first consideration of impedance-based management is how to obtain impedance online. The traditional laboratory method based on sine sweep is unsuitable for vehicular EIS measurement as limited by measured time and equipment price. In this article, we design an excitation device that can generate the square wave signal containing many harmonics as the excitation current. Besides, introduce S-transform (ST) for online broadband fuel cell impedance spectrum fast calculation, whose window width can be adaptively changed with frequency, and meanwhile, preserving high computational efficiency by fast Fourier transform operation. Based on this, the performance of ST and the previous method based on Morlet wavelet transform (MWT) is compared under different operating conditions. Extensive experimental results show that the ST can calculate impedance with the mean relative error of less than 3% based on appropriate excitation, while the computed time can be saved by nearly 95% as compared to MWT. Furthermore, the effectiveness and robustness of ST against different current densities, cell temperatures, fault scenarios with various fault degrees, and stable time are also verified through experimentation.

Establishing an accurate fault diagnosis system for the proton exchange membrane (PEM) fuel cell is essential for ensuring stable performance and delaying degradation. In this paper, a novel fault diagnosis method fusing characteristic impedance for the PEM fuel cell based on a hybrid deep learning network by combing the residual network (ResNet) and long short-term memory (LSTM) is proposed. Specifically, the characteristic impedance that can reflect internal dynamics loss is fused as the feature input alongside other commonly vehicular measurement signals and decoded to form a feature matrix. The feature matrix is then transferred to realize 25 categories of fault detection, including different degrees of membrane drying, flooding, and air starvation. The results showed the accuracy of ResNet-LSTM can reach 99.632% with a good balance of computational burden and is higher than that of a single LSTM, ResNet, and convolutional neural network, as well as traditional machine learning methods because such the hybrid structure can make full use of feature learning capability of ResNet and the time series analysis capability of LSTM. Moreover, the proposed hybrid framework is further validated and compared under different proportions of training samples, noise levels, and input signals.

In this study, an online adaptive anti-surge control (OAASC) strategy is proposed for proton exchange membrane (PEM) fuel cell system. Insufficient attention has been given to the issue of the surge in the air supply system, which can damage the compressor and stack, reducing the fuel cell vehicle’s efficiency and lifespan. The OAASC approach employs a multiple time-domain sliding window technique and characteristic energy-based correction to detect and adaptively contain surges before they become serious. A dynamic model of the fuel cell air supply system with surge prediction is established using a two-stage parameter identification process and is verified through 60 kW fuel cell engine experiments. Simulation and experimental comparisons between OAASC and standard industrial methods are conducted to evaluate the proposed method’s performance. The experimental results demonstrate that the proposed strategy improves control performance, with surges being detected within 0.2 s and recovering within 0.5 s.