Grey-Fuzzy Hybrid Optimization and Cascade Neural Network Modelling in Hard Turning of AISI D2 Steel

Nowadays hard turning is noticed to be the most dominating machining activity especially for difficult cut metallic alloys. Attributes of dry are highly influenced by amount heat generation during cutting. Some major challenges rapid tool wear, lower tool-life span, and poor surface finish but simultaneously generated enough provide thermal softening work material facilitates easier shear deformation thus easy Also, plenty works reported utilization various cooling methods as well coolants which successfully retard intensity cutting this leads additional cost environmental health issues. However, still, there scope select proper materials, its geometry, appropriate values parameters get favorable outcomes under avoid cost, environmental, issue. Considering these challenges, current utilizes PVD-coated (TiAlN) carbide insert in AISI D2 steel. The multi-responses like tool-flank chip morphology, reduction coefficient considered. amalgamation input processing variables must optimum effectual performance process materials turning. Generally, Fuzzy logic hypothesis represents uncertainties co-related with fuzziness, deficiency data concerned problem. Further, achieve best combination terms, grey-fuzzy hybrid optimization (Type I Type II) utilized considering Gaussian membership function. II system attributed 15 % less error (between GRG GFG) compared I. Hence, optimal set terms. terms found t-1 (0.15 mm), s-4 (0.25 mm/rev) Vc-2 (100 m/min) comparable results obtained spray impingement using CVD literature. can assessed condition a PVD at industrial uses. six different types cascade-forward-back propagation neural network modelling accomplished. Among all models, CFBNN-4 model exhibited prediction mean absolute 2.278% flank wear (VBc) 0.112% (CRC). recommended other engineering problems. research may immense importance manufacturers industry.