研究目的
To experimentally investigate the recast layer formation during laser trepan drilling of Inconel-718 and predict the recast layer formation using the adaptive neuro-fuzzy inference system (ANFIS).
研究成果
The ANFIS-based prediction of recast layer thickness has been found adequate. Prediction made by ANFIS has been experimentally validated and found that average % error in prediction is less than 5%. The methodology will serve as a guideline to the practitioners during the machining of hard materials with good accuracy and precision.
研究不足
The study is limited to the laser trepan drilling of Inconel-718 sheet and the prediction of recast layer thickness using ANFIS. The methodology may need further validation for other materials and drilling conditions.
1：Experimental Design and Method Selection
Experiments are performed on 1.4-mm-thick Inconel-718 sheet using pulsed Nd: YAG laser. Recast layer thickness has been measured for each experiment followed by the ANFIS-based prediction of recast layer.
2：Sample Selection and Data Sources
The Inconel-718 sheet has been used for performing the experiment. The dimension of the sheet is 140 × 140 × 1.4 mm.
3：List of Experimental Equipment and Materials
250-W average power solid-state-pulsed Nd: YAG laser, scanning electron microscope (SEM) model—JSM-6010LA.
4：Experimental Procedures and Operational Workflow
Experiments are performed based on Box–Behnken design (BBD)-based response surface methodology (RSM). Recast layer thickness has been measured for each experiment followed by the ANFIS-based prediction of recast layer.
5：Data Analysis Methods
ANFIS learning process is adaptive in nature. MATLAB software has been used for analyses and testing of data set.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
