As one of the most promising types of fuel cells, the proton exchange membrane fuel cells (PEMFCs) can be utilized in many applications. However, it still faces two main challenges before large-scale industrial applications, namely short lifetime and high costs. The aim of this paper is to establish an accurate online short-term prognostics method to help users extend the lifetime and reduce the cost of PEMFCs. First, we compare the shortterm prognostics accuracy and computational efficiency of several different methods including the elman neural network, the group method of data handling, the adaptive neuro-fuzzy inference system (ANFIS) with different fuzzy inference system creation strategies, and the wavelet decomposition approach. Test results show that the ANFIS with fuzzy-c-means (ANFIS-FCM) strategy has the best short-term prognostics performance. Then, we propose an automatic parameter adjustment method for ANFIS-FCM by using the particle swarm optimization (PSO) algorithm.Test results show that the PSO algorithm can effectively adjust the parameters and achieve improved prognostics results. Finally, the proposed prognostics methods are verified on a PEM FC experimental platform. Experimental results show that the proposed methods have great potential for practical applications.

Proton exchange membrane fuel cells are considered as one of the most promising power sources for transportation in the near future. Proper and robust thermal management is a key issue in fuel cell applications. This paper mainly studies the sensor fault detection and isolation and fault tolerant control for the thermal management of proton exchange membrane fuel cell systems. The thermal model of fuel cell is established and analyzed by structure analysis, and the residual generator of sensor faults are designed by Dulmage Mendelsohn decomposition to rearrange the bi-adjacency matrix of the thermal model. A sliding-mode-based active fault tolerant control strategy is proposed for the thermal management of fuel cell systems. The effectivenesses of the proposed fault detection and isolation method and active fault tolerant control strategy are verified on a fuel cell test bench. The experimental results show that the temperature of the proton exchange membrane fuel cell stack can be maintained at the reference value with high accuracy even when sensor fails.

Health management can effectively extend the service life of proton exchange membrane fuel cells and reduce the maintenance cost. This paper proposes a health management method for the proton exchange membrane fuel cells based on an active fault tolerant control method. With the advantages of low cost and high speed, a stack voltage model is developed for the condition monitoring. The fast electrochemical impedance spectroscopy measurement is performed when the condition monitoring module detects faults. Then, the distribution of relaxation time is used to extract the characteristics of electrochemical impedance spectroscopy for fault diagnosis. Thereafter, based on the diagnosis results, the performance recovery strategies are incorporated to cope with the faults. This paper adopts three typical fuel cell faults, namely flooding, membrane drying, and air starvation, to demonstrate the effectiveness of the proposed health management. Experimental results show that the proposed health management can realize real-time health monitoring and rapid fault diagnosis, and achieve effective recovery of performance under faulty conditions, thereby significantly improving the reliability of the proton exchange membrane fuel cell system.

Durability is considered as one of the main technical obstacles to the large-scale commercialization of proton exchange membrane fuel cells (PEMFCs), which can be effectively improved through degradation prediction techniques. This article proposes a stacked echo state network (ESN) based on the genetic algorithm (GA) to predict the future degradation trend of PEMFCs. By alternately using the projection layer and the encoding layer, the proposed method can make full use of the temporal kernel property of the ESN to encode the multiscale and multilevel dynamics of the stack voltage, thereby obtaining more robust generalization performance and higher accuracy than the existing methods. Specifically, a stack voltage time series of PEMFCs is projected into the high-dimensional echo state space of the reservoir. Then, an autoencoder projects the echo state representation into the low-dimensional feature space. After that, the GA is utilized to optimize the hyperparameters of the developed model. Based on two open-source datasets of PEMFCs with different accelerated test conditions, this article systematically tested the proposed degradation prediction methods based on different model structures. Test results demonstrate that the proposed method is superior to traditional prediction methods in terms of accuracy and generalization performance.

The practical long-term application of power-assisted exoskeleton robots requires lightweight, high-efficient, and high-control precision actuators. Based on the improvement of hardware design and control method, this article proposes a complete drive solution for the joint drive of exoskeleton robots and promotes the research of robot joint drive based on the pump-controlled hydraulic system. Specifically, a compact, backdrivable, and energy-efficient drive unit, lightweight electrohydrostatic actuator (LEHA) with a weight of 2.5 kg and a rated power of 340 W is designed first. Then, by combining the fifth-order high-precision dynamics model of LEHA and virtual decomposition control method, a high-performance controller with $L_{2}$ and $L_{\infty }$ stability is developed to realize the precise position trajectory tracking control of LEHA. Experimental results based on actual exoskeleton robot knee joints show that the proposed solution has high trajectory tracking performance over the frequency range of human body swing phase motion (0.5–1.5 Hz) and different loads (0–20 kg). Moreover, compared with the valve-controlled hydraulic power system with the same exoskeleton robot knee joint and wearer, test results show that the average efficiency increased by 18.13% after using LEHA under the swing phase test.

Flow mismatch, strong nonlinearity, and complex disturbance are the main challenges that electro-hydrostatic actuator (EHA) control faces. This article proposes a three-port piston pump to replace the two-port piston pump in traditional EHA to solve the flow mismatch problem caused by asymmetric cylinders. Then, for the complex disturbance problem in EHA control, an extended state observer and a nonlinear disturbance observer are designed to estimate matched and mismatched disturbances, respectively. On this basis, the virtual decomposition control method is adopted. The EHA is virtually decomposed into three subsystems, and the controllers of each subsystem are designed separately to realize the high-precision nonlinear control of the EHA. Next, the stability of the proposed control method and observer is proved. Finally, the proposed three-port pump, observer, and controller are systematically verified based on the simulation model and the EHA experimental platform. Simulation and experimental results show that the proposed three-port pump solves the flow mismatch problem without increasing the weight and volume of the EHA. The designed two observers can accurately estimate the matching and mismatching disturbances during the EHA operation. By combining designed observers and the virtual decomposition control method, the accuracy and robustness of EHA control can be greatly improved.