A new dual‐motor servo steering system with improved reliability and safety is proposed. But, despite the advantages of the proposed servo system, it is strongly coupled, non‐linear and multivariable, where the biggest challenge lies in its tracking and synchronization control. To improve the tracking and synchronization control performance of the proposed servo system, a tracking and synchronization control strategy based on backstepping super‐twisting control and multi‐level differential coupling is presented. First, a parallel model of the dual‐motor is established. Then, backstepping and super‐twisting control algorithms are integrated while adaptively optimizing key parameters to ensure the robustness and tracking performance of each motor. After that, an angular synchronization controller with multi‐level differential coupling and backstepping super‐twisting algorithm is proposed to compensate for the synchronization error of the dual‐motor system caused by parameter uncertainty. Finally, the simulation is carried out using Simulink to verify the effectiveness of the proposed control strategy.

To improve the control performance of servo systems under time-varying disturbances, a nonsingular terminal super twisting sliding mode control (NTSTC) method based on a reduced-order generalized proportional-integral observer is proposed. The method combines the third-order super-twisting and non-singular fast sliding mode to form an improved non-singular terminal super-twisting controller, while the reduced-order generalized proportional-integral observer is designed to accurately estimate the unknown part of the perturbation in real time and feed-forward compensation for NTSTC. The anti-interference ability and robustness of the motor control system are effectively improved, and the fault-tolerant control of the servo system under parameter disturbance and unknown disturbance is realized. Finally, the effectiveness of the proposed control algorithm is verified by simulation.

A distributed model predictive control method is used to transform the formation and maintenance problem of fixed-wing UAV formation during flight into an online rolling optimization problem to solve in this paper. Firstly, the state estimation model of the neighborhood UAV is established according to the relative information of the UAV. Secondly, the error state model in the three-dimensional inertial coordinate frame of the UAV is established without considering the time delay, sensor error, and external interference. Thirdly, a cost function is designed by introducing the error state of the UAV in the neighborhood. Finally, four UAVs are used to verify that under the action of the controller, the UAVs can quickly form and maintain the desired formation while tracking the reference line.

High precision control is often accompanied by many control parameters, which are interrelated and difficult to adjust directly. It is difficult to convert the system control effect directly into mathematical expression, so it is difficult to optimize it by intelligent algorithm. To solve this problem, we propose an improved sinusoidal gray wolf optimization algorithm (ISGWO). In this algorithm, a particle crossing processing mechanism based on the symmetry idea is introduced to maximize the retention of the position information of the optimal individual and improve the search accuracy of the algorithm. In addition, a differential cross-perturbation strategy is adopted to help the algorithm jump out of the local optimal solution in time, which enhances the development capability of ISGWO. Meanwhile, the position update formula with improved sinusoidal can better balance the development and exploration of ISGWO. The ISGWO algorithm is compared with three improved Gray Wolf algorithms on the CEC2017 test set as well as the synchronization controller. The experimental results show that the ISGWO algorithm has better selectivity, speed and robustness.

Aiming at the limitation of the existing search engine search algorithm and the low reliability of the derived vocabulary relevancy algorithm, a vocabulary relevancy algorithm based on search engine and vocabulary relevancy algorithm is proposed under the background of making full use of the knowledge base of Hownet. Firstly, the main defects of search engine algorithm are considered in two aspects, meaningless text and redundancy. Then, the two problems are solved by using “Hownet” and DSC algorithm. Finally, the search engine-based vocabulary relevancy algorithm is improved by integrating multiple factors such as weight reduction and noise reduction. Experimental results show that compared with the pure improvement method based on the search engine, the method of spearman coefficient and Pearson coefficient were improved, as well as reduce meaningless language segment on the calculation of correlation, verified the “Hownet”, and DSC algorithm into the search engine algorithm can effectively improve the computing performance of relevant vocabulary.