Investigations on machinability characteristics of Cast Aluminum Alloy based (LM 26+Graphite+Fly ash) Hybrid Metal Matrix Composites for automobile components

被引:14
|
作者
Prakash, C. [1 ]
Senthil, P. [1 ]
Manikandan, N. [2 ]
Palanisamy, D. [3 ]
机构
[1] Natl Inst Technol, Dept Prod Engn, Tiruchirappalli, Tamil Nadu, India
[2] Sree Vidyanikethan Engn Coll Autonomous, Micro Machining Res Ctr, Dept Mech Engn, Tirupati, Andhra Pradesh, India
[3] Adhi Coll Engn & Technol, Dr APJ Abdulkalam Res Ctr, Dept Mech Engn, Kancheepuram, Tamil Nadu, India
关键词
Hybrid; composites; graphite; flyash; circularity; perpendicularity; prediction; ANFIS; WEAR BEHAVIOR; CARBIDE; OPTIMIZATION; PERFORMANCE; PREDICTION; PARAMETERS; PARTICLES; EDM;
D O I
10.1080/10426914.2021.1962531
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
LM 26 is a category of cast aluminum alloy which is having exceptional characteristics that leads to use of this alloy as primary choice for making automobile components. Metal matrix composite (MMC) materials are having improved characteristics and believed as an alternate for plentiful engineering industries. Due to reinforcement added, the materials became harder and result in inferior machining performance by traditional approaches. Wire electrical discharge machining (WEDM) is one among the advanced and also a conversant approach engaged for making intricate forms. In this exploration, an investigation on machinability of WEDM of stir-casted hybrid MMC (LM26+ Graphite+Fly ash) and evolution of hybrid adaptive neuro fuzzy inference system (ANFIS) model for predicting the desired variables. The ascendance of variables named as pulse on (Ton), pulse off (Toff), dielectric fluid flushing pressure, wire feed, and servo voltage in contrast to preferred output measures like material removal rate, surface finish, dimensional deviation, and form/orientation tolerance errors were investigated. A hybrid approach combining grey and ANFIS model has been developed to foretell the desired measures, and comparison has been done on the experimental and predicted results. The performance of the model is investigated and proved that the model can predict the desired measures.
引用
收藏
页码:748 / 763
页数:16
相关论文
共 23 条