Recently, research on data-driven bearing fault diagnosis methods has attracted increasing attention due to the availability of massive condition monitoring data. However, most existing methods still have difficulties in learning representative features from the raw data. In addition, they assume that the feature distribution of training data in source domain is the same as that of testing data in target domain, which is invalid in many real-world bearing fault diagnosis problems. Since deep learning has the automatic feature extraction ability and ensemble learning can improve the accuracy and generalization performance of classifiers, this paper proposes a novel bearing fault diagnosis method based on deep convolutional neural network (CNN) and random forest (RF) ensemble learning. Firstly, time domain vibration signals are converted into two dimensional (2D) gray-scale images containing abundant fault information by continuous wavelet transform (CWT). Secondly, a CNN model based on LeNet-5 is built to automatically extract multi-level features that are sensitive to the detection of faults from the images. Finally, the multi-level features containing both local and global information are utilized to diagnose bearing faults by the ensemble of multiple RF classifiers. In particular, low-level features containing local characteristics and accurate details in the hidden layers are combined to improve the diagnostic performance. The effectiveness of the proposed method is validated by two sets of bearing data collected from reliance electric motor and rolling mill, respectively. The experimental results indicate that the proposed method achieves high accuracy in bearing fault diagnosis under complex operational conditions and is superior to traditional methods and standard deep learning methods.

In this paper the application of a PI observer technique to dynamical systems with nonlinearities is proposed. The PI observer has two feedback loops, a proportional loop and an integral loop of the estimation error. In this way the PI observer combines the structures of the practical orientated nonlinearity observer developed by the third author and the classical Luenberger observer. The structure and the estimation performance of the PI observer are discussed and analysed. The results show that the PI observer can estimate the states not only of linear systems, but also, more significantly, of systems with any arbitrary external input which appear as unknown input, nonlinearity or unmodelled dynamics. It is shown that the PI observer works with weak assumptions, which can be fulfilled by many classes of systems to be observed. Owing to the weak assumptions it can improve many observer-based technical solutions as diagnosis or control based on observers. In the paper the conditions are given and proved. The design method is declared and carried out with illustrative examples of a linear system and of a nonlinear system of a link manipulator with flexible joints. The results are good and they show the efficiency of the PI observer. In the case of nonlinear systems the advantages of ‘robustness’ and the model independency of the proposed observer scheme can be shown clearly.

In light of increasing alerts about limited energy sources and environment degradation, it has become essential to search for alternatives to thermal engine-based vehicles which are a major source of air pollution and fossil fuel depletion. Hybrid electric vehicles (HEVs), encompassing multiple energy sources, are a short-term solution that meets the performance requirements and contributes to fuel saving and emission reduction aims. Power management methods such as regulating efficient energy flow to the vehicle propulsion, are core technologies of HEVs. Intelligent power management methods, capable of acquiring optimal power handling, accommodating system inaccuracies, and suiting real-time applications can significantly improve the powertrain efficiency at different operating conditions. Rule-based methods are simply structured and easily implementable in real-time; however, a limited optimality in power handling decisions can be achieved. Optimization-based methods are more capable of achieving this optimality at the price of augmented computational load. In the last few years, these optimization-based methods have been under development to suit real-time application using more predictive, recognitive, and artificial intelligence tools. This paper presents a review-based discussion about these new trends in real-time optimal power management methods. More focus is given to the adaptation tools used to boost methods optimality in real-time. The contribution of this work can be identified in two points: First, to provide researchers and scholars with an overview of different power management methods. Second, to point out the state-of-the-art trends in real-time optimal methods and to highlight promising approaches for future development.

Current research and development in recognizing and predicting driving behaviors plays an important role in the development of Advanced Driver Assistance Systems (ADAS). For this reason, many machine learning approaches have been developed and applied. Hidden Markov Model (HMM) is a suitable algorithm due to its ability to handle time series data and state transition descriptions. Therefore, this contribution will focus on a review of HMM and its applications. The aim of this contribution is to analyze the current state of various driving behavior models and related HMM-based algorithms. By examining the current available approaches, a review is provided with respect to: i) influencing factors of driving behaviors corresponding to the research objectives of different driving models, ii) summarizing HMM related methods applied to driving behavior studies, and iii) discussing limitations, issues, and future potential works of the HMM-based algorithms. Conclusions with respect to the development of intelligent driving assistant system and vehicle dynamics control systems are given.

This paper presents a novel method, advisory dynamic programming (AD-DP), for power management of a fuel cell hybrid vehicle (FCHEV). The presented method embraces a new understanding of vehicle states as driver-dependent and - independent states in time domain to define a suitable state space to be used for dynamic programming. Driver-dependent states are defined in terms of multiple characteristic parameters for vehicle speed and power demand, corporately. Driver-independent states are defined in terms of discrete values for supercapacitor's state of charge $SoC_{sc}$ . Transition costs between all states in the state space are calculated offline and tabulated in look-up tables for online implementation. A state predictive model is developed based on the transition statistics of driver-dependent states for a suitable number of driving cycles. Backward calculation of the total transition cost for the predicted horizon in state space is used to define optimal power split strategy for the powertrain. The formulation of optimal control problem, in terms of situation- based solutions related to vehicle states, enables a significant reduction of computational steps and hence addresses the main challenge of real-time applications. The algorithm is adapted in terms of optimization horizon and number of discrete states for DIS to suit the real-time application. Experimental application of AD-DP, using an emulation test-rig, is conducted over different driving cycles. The obtained results reveal an improvement in energy efficiency up to 29 % compared to the adaptive rule- based method. The contribution of this paper can be identified as: first, development of a corporate definition for vehicle states, that can be further implemented in optimization-based power management methods. Second, the formulation of an adaptive DP that requires lower computational steps and hence suits real- time applications in hybrid electric vehicles.