Case Retrieval Strategy of Turning Process Based on Grey Relational Analysis

Abstract

To solve the problem of long response time when users obtain suitable cutting parameters through the Internet based platform, a case-based reasoning framework is proposed. Specifically, a Hamming distance and Euclidean distance combined method is designed to measure the similarity of case features which have both numeric and category properties. In addition, AHP (Analytic Hierarchy Process) and entropy weight method are integrated to provide features weight, where both user preferences and comprehensive impact of the index have been concerned. Grey relation analysis is used to obtain the similarity of a new problem and alternative cases. Finally, a platform is also developed on Visual Studio 2015, and a case study is demonstrated to verify the practicality and efficiency of the proposed method. This method can obtain cutting parameters which is suitable without iterative calculation. Compared with the traditional PSO (Particle swarm optimization algorithm) and GA (Genetic algorithm), it can obtain faster response speed. This method can provide ideas for selecting processing parameters in industrial production. While guaranteeing the characteristic information is similar, this approach can select processing parameters which is the most appropriate for the production process and a lot of time can be saved.