The aim of this paper is to optimize the AWJM process parameters for machining green composites (GC) using a hybrid expert system. A hybrid expert system consists of subtractive clustering (SC)-Takagi–Sugeno–Kang (TSK)-based fuzzy logic method coupled with multi-objective optimization of ratio analysis (MOORA). Here, the SC-TSK method is used for the extraction of cluster centers and the modeling of the AWJM process, while MOORA is used for the optimization of AWJM parameters. Work used Taguchi design (L27) orthogonal array for experimentation and historical data generation for expert system considering working pressure (WP), stand of distance (SoD) and nozzle speed (NS) as input conditions and material removal rate (MRR), and surface roughness (Ra) as output responses. From the optimization, optimal setting obtained for AWJM process are WP (300 MPa, level 3), SoD (3.5 mm, level 3), NS(175 mm/min, level 3), and corresponding values of MRR (295.56 mm3/sec) and Ra (0.189 µm). Finally, the validity and adequacy of the proposed model is done through confirmation tests and result shows comparable and acceptable with experimental results.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Optimization of AWJM Process Parameters on Machining of Green Composites Using a Hybrid Expert System

  • Jagadish

摘要

The aim of this paper is to optimize the AWJM process parameters for machining green composites (GC) using a hybrid expert system. A hybrid expert system consists of subtractive clustering (SC)-Takagi–Sugeno–Kang (TSK)-based fuzzy logic method coupled with multi-objective optimization of ratio analysis (MOORA). Here, the SC-TSK method is used for the extraction of cluster centers and the modeling of the AWJM process, while MOORA is used for the optimization of AWJM parameters. Work used Taguchi design (L27) orthogonal array for experimentation and historical data generation for expert system considering working pressure (WP), stand of distance (SoD) and nozzle speed (NS) as input conditions and material removal rate (MRR), and surface roughness (Ra) as output responses. From the optimization, optimal setting obtained for AWJM process are WP (300 MPa, level 3), SoD (3.5 mm, level 3), NS(175 mm/min, level 3), and corresponding values of MRR (295.56 mm3/sec) and Ra (0.189 µm). Finally, the validity and adequacy of the proposed model is done through confirmation tests and result shows comparable and acceptable with experimental results.