A Neuro-fuzzy Approach to Select Cutting Parameters for Commercial Die Manufacturing

Abstract

Surface roughness is a quality index for machined surfaces. In this study an algorithm has been developed to determine the feasible solutions for cutting parameters in order to obtain desired surface roughness for three dimensional dies. Here the average surface roughness values for a commercial die material EN24 after ball end milling operation have been measured after experiments with different cutting parameters. These datasets have been used for training and testing different prediction models like artificial neural network (ANN), response surface methodology (RSM), adaptive neuro-fuzzy inference system (ANFIS) and mathematical equation based on machining theories. ANFIS model has been selected as better prediction model because it has shown minimum value of root mean square error (RMSE) and mean absolute percentage error (MAPE) for training and testing datasets. This ANFIS model has been used further for predicting surface roughness of a typical die made of EN24 after ball end milling operation.

Applications of Fuzzy Logic, Artificial Neural Network and Neuro-Fuzzy in Industrial Engineering

“…The choice of optimal cutting parameters is crucial in each machining procedure for increasing the quality of machined productions as well as to decrease the machining expenses. In [35], an adaptive neuro-fuzzy inference system is introduced to model and predict surface roughness in ball end milling of a die material. The algorithm developed in that paper presets the cutting parameters for a favorable level of surface roughness.…”

ANFİS Model ile Mg Alaşımlarının Sıkıştırılabilirliğinin Tahminleme Performasının İncelenmesi

“…2013, Çelik ve Kıvak 2016, Kara et al 2017, Basmaci 2018, Yıldırım 2019, Jeyaprakash et al 2020, Kechagias et al 2020. Ancak literatür incelendiğinde benzer alanlarda tahminleme için ANFİS kullanımının da arttığı gözlemlenmiştir (Hossain and Ahmad 2014, Maher et al 2014, Shivakoti et al 2019, Ergül ve Kurt 2021. Shivakoti ve arkadaşları yaptıkları çalışmada; 202 paslanmaz çeliğinin işlenmesinde yüzey pürüzlülüğü ve talaş kaldırma oranın tahmini için L16 ortogonal dizine göre ANFİS modelleri geliştirmişlerdir.…”

Modeling of cutting parameters in turning of PEEK composite using artificial neural networks and adaptive-neural fuzzy inference systems

“…11 To the best of our knowledge, ANFIS, which merges fuzzy logic and the ANN, was not investigated in the machining of PEEK for predicting surface roughness. Moreover, ANFIS was applied successfully to the machining of alloys, such as Inconel 690, 18 die material EN24, 19 and aluminum alloy A7075-T6. 12 However, the performance of ANFIS in some plastic composites was evaluated in several studies.…”