Multivariate time series prediction is a critical problem that is encountered in many fields, and recurrent neural network (RNN)‐based approaches have been widely used to address this problem. However, traditional RNN‐based approaches for predicting multivariate time series are still facing challenges, as time series are often related to each other and historical observations in real‐world applications. To address this limitation, this paper proposes a spatiotemporal self‐attention mechanism‐based LSTNet, which is a multivariate time series forecasting model. The proposed model leverages two self‐attention strategies, spatial and temporal self‐attention, to focus on the most relevant information among time series. The spatial self‐attention is used to discover the dependences between variables, while temporal attention is employed to capture the relationship among historical observations. Moreover, a standard deviation term is added to the objective function to track multivariate time series effectively. To evaluate the proposed method’s performance, extensive experiments are conducted on multiple benchmarked datasets. The experimental results show that the proposed method outperforms several baseline methods significantly. Therefore, the proposed spatiotemporal self‐attention‐based LSTNet is a promising approach for predicting multivariate time series.
Considering the defect detection issues in electroluminescence (EL) of photovoltaic (PV) cell systems, lots of factors result in performance degradation, including defect diversity, data imbalance, scale difference, etc. Focal-EIoU loss, an effective defect detection solution for EL, is proposed based on the improved YOLOv5. Firstly, by analyzing the detection background and scale characteristics of EL defects, a binary classification is carried out in the system. Subsequently, a cascade detection network based on YOLOv5 is designed to further extract features from the binary-classified defects. The defect localization and classification are achieved in this way. To address the problem of imbalanced defect samples, a loss function is designed based on EIoU and Focal-F1 Loss. Experimental results are illustrated to show the effectiveness. Compared with the existing CNN-based deep learning approaches, the proposed focal loss calculation-based method can effectively improve the performance of handling sample imbalance. Moreover, in the detection of 12 types of defects, the Yolov5 algorithms can always obtain higher MAP (mean average precision) even with different parameter levels (Yolov5m: 0.791 vs. 0.857, Yolov5l: 0.798 vs. 0.862, Yolov5x: 0.802 vs. 0.867, Yolov5s: 0.793 vs. 0.865).
A few experimental studies on thermal tactile perception have shown the influence of the thermal contact resistance which relates to contact surface roughness and pressure. In this paper, the theoretical influence of the skin thickness and the thermal contact resistance is studied on the thermal model describing the temperature evolution in skin and materials when they come in contact. The thermal theoretical profile for reproducing a thermal cue for given contact thermal resistance is also presented. Compared to existing models of thermal simulation, the method proposed here has the advantage that the parameters of skin structure and thermal contact resistance in target temperature profiles can be adjusted in thermal perception simulation according to different skin features or surface roughness if necessary. The experimental results of surface roughness recognition were also presented.
For back electromotive force-based sensorless control in permanent magnet synchronous motor (PMSM) drives, the conventional phase-locked loop (PLL) exhibits a $\pm \pi$ position estimation error during speed reversal. This article presents an octant Newton–Raphson method (ONRM)-based PLL, which employs a newly defined objective function and a position octant method. It not only ensures the position estimation converges correctly during speed reversal but also improves dynamic performance compared to the conventional PLL. The applicability condition of the ONRM in the presence of noise is also analyzed in detail. Subsequently, due to the noise sensitivity of the ONRM, a reduced-order extended Kalman filter is designed to filter out the nonGaussian noise in the position estimation while simultaneously estimating the speed. The effectiveness of the proposed sensorless control scheme is verified on a 1.5 kW PMSM drive platform.
28 June 2024 in Measurement Science and Technology
In the field of fault diagnosis for factory machinery systems, the development of deep learning methods has been hindered by the challenge of acquiring fault data, highlighting the need to extract noise robust features from limited labeled data. In this paper, a light and efficient complex-domain acoustic feature extraction method, complex-domain principal frequency convolution network (CPFCN) is proposed for fault diagnosis in rotating machinery, which consists of a principal frequency filter (PFF) and stacked convolution network (SCN). The PFF filters out non-principal frequency noise to focus on the predominant frequency. The SCN is designed to effectively extract the amplitude and phase features, which can fully leverage the complex-domain information within the acoustic data. The experimental results show that the proposed CPFCN have 33% increasing in accuracy while 87% reduction in training time and 41% reduction in feature extraction time. Additionally, the proposed framework has improved the accuracy by 59% on the dataset with noise compared to the best-performing method in the experimental study, achieving stronger noise robustness in the case of limited samples.