Plasma cutting is an effective way to cut hard metals. In this process, three output parameters cutting width (kerf), surface roughness (Ra) and heat-affected zone (HAZ) are critical factors which affect the quality and efficiency of the cutting. In this paper, an experimental study was conducted to investigate the cutting quality in terms of kerf, Ra, and HAZ for the 309 stainless steel plasma cutting. First, the research tested the effect of input parameters including current, gas pressure, and cutting speed on the process outputs. Then, the results were used to develop three predictive models by intelligent systems based on genetic algorithm (GA) and artificial neural network (ANN). Finally, a hybrid technique of genetically optimized neural network systems (GONNs) was designed and employed to simultaneously optimize the process outputs. The results show that the implemented strategy is an effective method for optimizing the output parameters in the plasma cutting process.
This paper presents a fuzzy sliding mode controller (FSMC) and an integral sliding mode controller (ISMC) separately to control position of a quadrotor with an uncertain mass in the presence of wind disturbance and compares the operation of these controllers. Euler-Newton method is used to derive the quadrotor dynamic equations that considers the wind effect. The outer loop controller determines the desired angles of the quadrotor which are stabilized by a feedback linearization controller as the inner loop control. Also, the stability proof of FSMC and ISMC is done. Finally, simulation results are utilized to represent the operation of the control approaches and compare their performances.