Efficient and stable operation (ESO) of the proton exchange membrane fuel cell (PEMFC) system is challenging because the nonlinearity of system not only aggravates the difficulty of performance analysis but also puts forward higher requirements for controller design. In this article, a hierarchical performance enhancement control strategy (HPECS) is proposed, which can deal with optimal trajectory seeking under multiobjective constraints and nonlinear problem of system separately. In upper optimization level, the multiobjective optimization based on dynamic adjustment of weighting factor is proposed to seek optimal trajectory for ESO of PEMFC system considering the harm of oxygen starvation, oxygen saturation to system, and contradiction characteristic between net power and efficiency; in lower control level, a data-driven constraint adaptive predictive control is proposed for optimal trajectory tracking with the nonlinearity of system. The proposed HPECS is implemented and validated on the experimental PEMFC system. The comparative studies show that the proposed HPECS is superior in performance enhancement, disturbance rejection, and tracking ability. The normalized multiobjective optimization function can be basically guaranteed to above 0.9, and a nearly 7.2% enhancement in average can be also observed, which shows that ESO of PEMFC system can be achieved in changeable working conditions under proposed HPECS.

For solving the problem of sequence failure diagnosis of proton exchange membrane fuel cell (PEMFC) water management subsystem, this paper proposes a PEMFC failure diagnosis method of time series based on bidirectional long short-term memory network (BiLSTM) and t-distributed stochastic neighbour embedding (t-SNE). This approach adopts the normalization strategy to eliminate the influence caused by dimensional differences of different parameters. t-SNE is presented to decrease the dimensionality of normalized data to the estimate of intrinsic dimensionality to extract key characteristic variables. The width of the diagnostic window is set to transform the original single moment diagnosis problem into the fault diagnosis problem of multi-variable time series, which is more consistent with the time scale and physical evolution law of PEMFC water management fault generation. The 672 sets of training sets and 448 sets of test sets are learned and tested by BiLSTM. The experimental results show that the BiLSTM-tSNE method can realize the sequence fault diagnosis of the PEMFC water management subsystem with 96.88% diagnostic accuracy and 24 seconds of operation time. Compared with the conventional approach of multi-class support vector machine algorithm, the training accuracy and testing accuracy of the proposed method is improved by 15% and 16.88% respectively. The operation time of the presented approach is only about 1/28 of multi-class support vector machine algorithm.

This article presents an event-triggered distributed secondary control with predictive compensation based on the model-free predictive control under Denial-of-Service (DoS) attacks in ac/dc-networked microgrids. First, models of ac/dc networked microgrids in both electric network and communication network are established. On this premise, event-triggered distributed secondary control is proposed to solve the problems of strong communication burden and low-power distribution accuracy. Besides, aiming at the impact of DoS attacks on distributed secondary control, a compensation algorithm based on model-free predictive control is designed to estimate the control variables when the DoS attack occurs, which can improve the control performance and maintain the stable operation without a specific system structure system. Then, the convergence of event-triggered distributed secondary control with the condition of whether DoS attacks happen are analyzed. Finally, the effectiveness of the proposed control is verified on the hardware-in-loop (HIL) simulation platform consisting of the RT-LAB simulator, MATLAB/Simulink simulation model, and DSP controller.

Smartload with series-connected dc electric spring (ES) and noncritical load (NCL) structure can compensate for load voltage and improve the power quality. In this article, a distributed virtual inertial control framework based on model predictive control is proposed for low inertia in the dc microgrid. First, the current prediction model of the ES bidirectional full-bridge dc/dc converter is presented. Based on the virtual inertia control, model predictive control is used to optimize virtual capacitance during the operation. When the system suffers from disturbance, virtual capacitance increases to slow down the change of the dc bus voltage. When disturbance happens, the system can be stabilized quickly by reducing the virtual capacitance. Then, the consensus algorithm based on distributed control is established after defining the NCL voltage deviation rate, which can achieve the balance of NCL voltage deviations, and effectively avoid the more significant voltage deviation in one of NCLs. Furthermore, the small-signal model of the proposed control method is developed, and the influence of the proposed controller on the small-signal stability is described by employing the eigenvalue analysis method. Finally, based on the RT-Lab hardware-in-the-loop simulation system, comparisons and analysis are made to verify the effectiveness of the proposed control method under power step conditions.