In this study, an improved sliding mode control (ISMC) method combining continuous non‐singular terminal sliding mode (CNTSM) and linear active disturbance rejection control (LADRC) for permanent magnet synchronous motor (PMSM) servo system is proposed to improve the performance of PMSM. Based on the mathematical model of PMSM, combined with SMC theory and LADRC theory, CNTSM controller based on continuous function is proposed to solve the singularity of terminal sliding mode (TSM) control. In order to solve the contradiction between the convergence performance of sliding mode control and the ability of chattering suppression, fuzzy control is introduced to adjust the gain of sliding mode controller in real time. LADRC is developed to ensure the current starting conditions of the motor and improve the robustness. Moreover, the asymptotic stability of the system is guaranteed by the Lyapunov theorem and it is verified by the AISim MBD servo motor experimental platform. Experiments show that the algorithm has good tracking performance and robustness.

Short-term wind power forecasting plays an important role in wind power generation systems. In order to improve the accuracy of wind power forecasting, many researchers have proposed a large number of wind power forecasting models. However, traditional forecasting models ignore data preprocessing and the limitations of a single forecasting model, resulting in low forecasting accuracy. Aiming at the shortcomings of the existing models, a combined forecasting model based on secondary decomposition technique and grey wolf optimizer (GWO) is proposed. In the process of forecasting, firstly, the complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) and wavelet transform (WT) are used to preprocess the wind power data. Then, least squares support vector machine (LSSVM), extreme learning machine (ELM) and back propagation neural network (BPNN) are established to forecast the decomposed components respectively. In order to improve the forecasting performance, the parameters in LSSVM, ELM, and BPNN are tuned by GWO. Finally, the GWO is used to determine the weight coefficient of each single forecasting model, and the weighted combination is used to obtain the final forecasting result. The simulation results show that the forecasting model has better forecasting performance than other forecasting models.

Aiming at the problems of error detection and missing detection in night target detection, this paper proposes a night target detection algorithm based on YOLOv7(You Only Look Once v7). The algorithm proposed in this paper preprocesses images by means of square equalization and Gamma transform. The GSConv(Group Separable Convolution) module is introduced to reduce the number of parameters and the amount of calculation to improve the detection effect. ShuffleNetv2_×1.5 is introduced as the feature extraction Network to reduce the number of Network parameters while maintaining high tracking accuracy. The hard-swish activation function is adopted to greatly reduce the delay cost. At last, Scylla Intersection over Union function is used instead of Efficient Intersection over Union function to optimize the loss function and improve the robustness. Experimental results demonstrate that the average detection accuracy of the proposed improved YOLOv7 model is 88.1%. It can effectively improve the detection accuracy and accuracy of night target detection.

In order to improve the iris classification rate, a novel biogeography‐based optimization algorithm (NBBO) based on local search and nonuniform variation was proposed in this paper. Firstly, the linear migration model was replaced by a hyperbolic cotangent model which was closer to the natural law. And, the local search strategy was added to traditional BBO algorithm migration operation to enhance the global search ability of the algorithm. Then, the nonuniform variation was introduced to enhance the algorithm in the later iteration. The algorithm could achieve a stronger iris classifier by lifting weaker similarity classifiers during the training stage. On this base, the convergence condition of NBBO was proposed by using the Markov chain strategy. Finally, simulation results were given to demonstrate the effectiveness and efficiency of the proposed iris classification method.

Aiming at the problems of speed overshoot, slow convergence and poor anti-interference in the control of permanent-magnet synchronous motors (PMSMs) without a position sensor, a pulse vibration high-frequency signal injection method for a permanent-magnet synchronous motor with an improved sliding mode control was designed. Firstly, the improved approach rate function is combined with the improved non-singular fast terminal sliding mode surface to design the non-singular fast terminal sliding mode controller (NFTSMC), which is used in the speed loop to improve the speed convergence ability and reduce its overshoot. Secondly, in order to eliminate the influence of the band-pass filter on the system bandwidth in the traditional high-frequency injection method, a pulse vibration high-frequency signal injection method that injects high-frequency voltage signals and synchronous current signals into the $\widehat{d}$ axis of the estimated two-phase rotation coordinate system $\widehat{d}\widehat{q}$ and the $\alpha \beta$ axis of the two-phase stationary coordinate system $\alpha \beta$ was designed to estimate the motor position and speed to achieve sensorless control. Finally, the above control strategy was compared with the speed loop PI and the traditional sliding mode controller (SMC) of the speed loop, respectively. The simulation and experimental results show that whether it is a no-load variable speed or fixed speed loading, the above control strategy can effectively reduce the speed overshoot, accelerate the speed convergence and improve the load capacity of the system.