© 2018, Taiwan Fuzzy Systems Association and Springer-Verlag GmbH Germany, part of Springer Nature. Electronic nose devices consisting of a matrix of sensors to sense the smell of various target gases have received considerable attention during the past two decades. This paper presents an efficient classification algorithm for a self-designed electronic nose, which integrates both genetic algorithms (GAs) and fuzzy support vector machines (FSVMs) to detect the target odor. GAs are applied to select the informative features and the optimal model parameters of FSVMs. FSVMs are adopted as fitness evaluation criterion and the sequent odor classifier, which can reduce the outlier effects and provide a robust and accurate classification. This proposed algorithm has been compared with some commonly used learning algorithms, such as support vector machine, the k-nearest neighbors and other combination algorithms. This study is based on experimental data collected from the response of the UTS NOS.E, which is the electronic nose system developed by the University of Technology Sydney NOS.E team. In comparison with other approaches, the experiment results show that the proposed odor classification algorithm can significantly improve the classification accuracy by selecting high-quality features and reach to 92.05% classification accuracy.

© 2017 IEEE. Accurate lithium-ion battery power capability prediction gives an indication for managing power flows in or out of batteries within the safe operating area, which is one of the primary challenging functions of battery management systems (BMSs). The battery direct current resistance (DCR) is typically employed for power capability prediction, but its characteristic depends significantly on the ambient temperature. It is essential to investigate systematically the temperature dependence of battery DCR for achieving reliable power capability prediction. Based on a large amount of battery test data, a battery DCR model is proposed for quantitatively describing its temperature dependence. This model is then applied for battery power capability prediction, and the results are verified by experimental results.

© assigned jointly to the European Power Electronics and Drives Association & the Institute of Electrical and Electronics Engineers (IEEE). For reducing the inconsistent state of charges (SOCs) of lithium-ion battery cells and making the full use of battery packs, effective battery balancing technology should be in place for battery management systems. Since aged battery packs usually suffer from not only non-uniform cell SOCs and voltages but also non-uniform cell capacities, it is more challenging to balance an aged battery pack than a new one. This paper proposes a model predictive control (MPC) based balancing strategy to fully charge battery packs under such inconsistent conditions, especially for aged battery packs. The algorithm of the proposed strategy for computing the required average balancing current and the predicted balancing current for each cell is presented, followed by employing a minimum cost function value between these two currents to control the operation model of the equalizer for each cell. The simulation results verify the effectiveness of the proposed approach. Compared with the conventional average SOC strategy, the proposed MPC based strategy can effectively avoid over-equalization during the balancing process, thus reducing balancing energy consumption.

This study investigates the nonlinear/linear behaviors of human heart rate response to treadmill exercise, for young and healthy subjects. The heart rate of the subject is measured, starting at a speed of 7 km/h, and increasing until the maximum heart rate for the subject is reached. The obtained nonlinear model is complicated and is not robust. Furthermore, sustained exercise at maximum heart rate is not always safe. For these reasons, this is not a suitable method for running exercise. Instead, we develop simple linear models for the same speed range, which is suitable for treadmill running exercise. We also propose a new model, called dasiaH modelpsila, to predict the percentage of heart rate reserve during running exercise. It has been proven that the presented model can predict the percentage change of heart rate for running exercise in the identified linear response range.

This paper proposed a nonlinear model predictive control (MPC) method for the control of gantry crane. One of the main motivations to apply MPC to control gantry crane is based on its ability to handle control constraints for multivariable systems. A pre-compensator is constructed to compensate the input nonlinearity (nonsymmetric dead zone with saturation) by using its inverse function. By well tuning the weighting function matrices, the control system can properly compromise the control between crane position and swing angle. The proposed control algorithm was implemented for the control of gantry crane system in System Control Lab of University of Technology, Sydney (UTS), and achieved desired experimental results.