Feature extraction is a key step of intelligent bearing fault diagnosis. However, bearing vibration signals are usually nonlinear, non-stationary signal with strong noises. Extracting the effective status feature of bearing is challenging. Thus, a new rolling bearing status feature extraction method based on variational mode decomposition (VMD) and improved envelope spectral entropy (IESE) is proposed in this paper. First, the bearing vibrational signals are decomposed into different intrinsic mode functions (IMF) by VMD. Then, the envelope spectral entropy of each IMF is calculated and the IESE is obtained by reconstructing the envelope spectral entropy to build original feature sets. Finally, the original feature set is fused by the joint approximate diagonalization eigen (JADE) to obtain a new one. The new feature set is trained and tested by using SVM to identify the bearing status. The feasibility of the proposed method for feature extraction is verified by three experimental cases. Compared with several methods, the performance of this proposed method is better than those of other methods.

This paper proposes a multi-objective energy management strategy (EMS) based on multi-agent reinforcement learning (MARL) for a hybrid electric vehicle equipped with an engine-generator set (EGS) and a hybrid energy storage system (HESS, consisting of a battery and ultracapacitor). First, besides improving fuel economy, maintaining battery state of charge (SOC), reducing battery degradation and constraint on ultracapacitor SOC are also taken into consideration, formulating multi-objective energy management. Then, the problem is solved using MARL which combines game theory and reinforcement learning. In this framework, EGS and HESS are viewed as two intelligent agents respectively, and their interactions are described as a general-sum stochastic game. Following the principle of MARL, the two agents can learn the optimal control policy which guarantees the Nash equilibrium of multiple objectives, thus achieving a satisfactory balance among them. In the simulation, the MARL-based EMS is compared with single-agent reinforcement learning (SARL) which ignores the relations of different agents, and dynamic programming (DP) which integrates various targets into a single cost function with weight coefficients. The simulation results verify the superiority of the proposed EMS in optimizing multiple objectives.

As a fundamental task of hybrid electric vehicles (HEVs), energy management strategies are critical for improving the performance. This paper proposes a new queue-Dyna reinforcement learning (RL) algorithm based energy management strategy (EMS), which can substantially reduce the online learning time while guarantees the control performance compared with widely used Q-learning. To solve the existing problems of direct and indirect RL based EMSs, a blended RL algorithm, Dyna, is introduced first. By reusing the actual experience to construct a model online, Dyna integrates direct and indirect RL, and thus has the advantages of both. Furthermore, two novel strategies of backward focusing and prioritized sweeping are incorporated in the Dyna framework, developing the queue-Dyna algorithm. To the best of our knowledge, it's the first attempt of adopting queue-Dyna in the EMS of a HEV. A comparative simulation of direct RL, indirect RL, Dyna and queue-Dyna is implemented, and the results demonstrate the proposed algorithm achieves a great improvement in fast learning and maintains satisfied fuel consumption. At last, a hardware-in-the-loop experiment verified the real-time performance of the proposed EMS.