{"title":"Prediction of Optimum Cutting Parameters to obtain Desired Surface in Finish Pass end Milling of Aluminium Alloy with Carbide Tool using Artificial Neural Network","authors":"Anjan Kumar Kakati, M. Chandrasekaran, Amitava Mandal, Amit Kumar Singh","country":null,"institution":"","volume":57,"journal":"International Journal of Mechanical and Mechatronics Engineering","pagesStart":1922,"pagesEnd":1929,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/6621","abstract":"End milling process is one of the common metal\r\ncutting operations used for machining parts in manufacturing\r\nindustry. It is usually performed at the final stage in manufacturing a\r\nproduct and surface roughness of the produced job plays an\r\nimportant role. In general, the surface roughness affects wear\r\nresistance, ductility, tensile, fatigue strength, etc., for machined parts\r\nand cannot be neglected in design. In the present work an\r\nexperimental investigation of end milling of aluminium alloy with\r\ncarbide tool is carried out and the effect of different cutting\r\nparameters on the response are studied with three-dimensional\r\nsurface plots. An artificial neural network (ANN) is used to establish\r\nthe relationship between the surface roughness and the input cutting\r\nparameters (i.e., spindle speed, feed, and depth of cut). The Matlab\r\nANN toolbox works on feed forward back propagation algorithm is\r\nused for modeling purpose. 3-12-1 network structure having\r\nminimum average prediction error found as best network architecture\r\nfor predicting surface roughness value. The network predicts surface\r\nroughness for unseen data and found that the result\/prediction is\r\nbetter. For desired surface finish of the component to be produced\r\nthere are many different combination of cutting parameters are\r\navailable. The optimum cutting parameter for obtaining desired\r\nsurface finish, to maximize tool life is predicted. The methodology is\r\ndemonstrated, number of problems are solved and algorithm is coded\r\nin Matlab\u00ae.","references":null,"publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 57, 2011"}