In practical control applications, AC permanent magnet synchronous motors need to work in different response characteristics. In order to meet this demand, a controller which can independently realize the different response characteristics of the motor is designed based on neutrosophic theory and genetic algorithm. According to different response characteristics, neutrosophic membership functions are constructed. Then, combined with the cosine measure theorem and genetic algorithm, the neutrosophic self-tuning PID controller is designed. It can adjust the parameters of the controller according to response requirements. Finally, three kinds of controllers with typical system response characteristics are designed by using Simulink. The effectiveness of the designed controller is verified by simulation results.

This chapter introduces an improved proportional-integral-derivative (PID) adjusting method by applying a simulated annealing algorithm (SAA) and the cosine, tangent, exponential measures of single-valued neutrosophic sets (SvNSs). For the approach, characteristic values of the unit step response (rise time, peak time, settling time, undershoot ratio, overshoot ratio, and steady-state error) in the control system should be neutrosophicated by the neutrosophic membership functions. Next, one of cosine, tangent, and exponential measures is used to obtain the similarity measure of the ideal SvNS and the response SvNS to assess the control performance of the PID controller by the optimization values of the PID parameters Kp, Ki, and Kd searched by SAA. The results of the illustrative example obtained by these measures and SAA are better than the existing ones and indicate better PID controller performance. Comparative results can demonstrate the rationality and superiority of the improved PID adjusting method.

No abstract

Artificial neural network has made the rapid development of artificial intelligence with its super-learning ability, making artificial neural network become a research hotspot again. At present, deep learning has been widely used in various fields such as computer vision, speech processing, and natural language processing, and has even played a leading role in some fields. The single image super-resolution reconstruction technique aims to reconstruct a low-resolution image through a series of algorithms to reconstruct a corresponding high-resolution image. This paper first briefly introduces the relevant theories of artificial neural networks, then studies the fast super-resolution reconstruction model, and improves the model layer and filter size to establish a new improved model.