This paper studies the optimal design and control scheme of a spoke-type interior permanent magnet motor (SIPM). An asymmetric rotor structure with flux barriers is designed to improve the torque density of SIPM. The design method improves the torque density by approximating the maximum value of the magnetic torque and the reluctance torque, wherein the torque components are separated by the frozen permeability method (FPM) to evaluate the contribution. This scheme does not increase the amount of permanent magnets or the motor size, and reduces motor weight while increasing motor torque output. Firstly, the asymmetric flux barriers are applied in a 27/4 SIPM to illustrate the design principle. Further, by optimizing the width of flux barriers, based on finite-element analyze (FEA), a higher torque density is obtained. Compared with the basic model, the output torque and the torque density of the optimal model are both increased. Based on the optimal model, an angle scanning method is proposed to orient the flux vector and dq-axis. Then, the mathematical model of the optimal model is established, and the maximum torque per ampere (MTPA) control system is designed. Compared with the conventional control system, the proposed control system has a higher torque per ampere (TPA), which shows that the designed control system can give full play to the advantages of the high torque density.

Building an automatic seizure onset prediction model based on multi-channel electroencephalography (EEG) signals has been a hot topic in computer science and neuroscience field for a long time. In this research, we collect EEG data from different epilepsy patients and EEG devices and reconstruct and combine the EEG signals using an innovative electric field encephalography (EFEG) method, which establishes a virtual electric field vector, enabling extraction of electric field components and increasing detection accuracy compared to the conventional method. We extract a number of important features from the reconstructed signals and pass them through an ensemble model based on support vector machine (SVM), Random Forest (RF), and deep neural network (DNN) classifiers. By applying this EFEG channel combination method, we can achieve the highest detection accuracy at 87% which is 6% to 17% higher than the conventional channel averaging combination method. Meanwhile, to reduce the potential overfitting problem caused by DNN models on a small dataset and limited training patient, we ensemble the DNN model with two "weaker" classifiers to ensure the best performance in model transferring for different patients. Based on these methods, we can achieve the highest detection accuracy at 82% on a new patient using a different EEG device. Thus, we believe our method has good potential to be applied on different commercial and clinical devices.

No abstract

No abstract