Papers by Keyword: Evolutionary Strategy

Abstract: A novel prediction method which combined evolutionary strategy with least-square support vector machine is presented and applied to the trend prediction of hydraulic liquid leakage in this paper. In order to improve the prediction performance, the evolutionary strategy is employed to optimize the internal parameters of least-square support vector machine. Through the experiment study, the result validated the effectiveness of the prediction method, and it is also demonstrated that the method is able to do the short-term fault prediction for the hydraulic system.

Abstract: Many industrial applications require efficient servo drives and speed control to obtain the necessary performance with respect to different applications. As time passes, artificial intelligence has grown and replaced many traditional control methods in order to attain greater robustness to uncertainties, faster dynamic response and smaller position and speed errors. This paper briefly reviews several artificial intelligence implementations in synchronous motor control systems and briefly indicates the advantages and disadvantages of each method.

Abstract: Minimum zone circle (MZC), minimum circumscribed circle (MCC), maximum inscribed circle (MIC) and least square circle (LSC) are four common methods used to evaluate circularity errors. A novel particle swarm optimization algorithm based on self-adapted comprehensive learning (ACL-PSO) is proposed to evaluate circularity errors with real coded strategy. In the algorithm, population learning mechanism and velocity mutation strategy are adopted. In the meantime, ACL-PSO is applied to the unified evaluation of circularity error. The experiment results evaluated by different methods indicate that the proposed algorithm not only converges to the global optimum rapidly, but also has good stability, and it is easy to generalize.