Application of Artificial Neural Network and Response Surface Methodology in Modeling of Surface Roughness in WS2 Solid Lubricant Assisted MQL Turning of Inconel 718

International Conference on Recent Advances in Materials & Manufacturing Technologies

Reddy Paturi, Uma Maheshwera^1 ; Devarasetti, Harish^1 ; Fadare, David Abimbola^2 ; Reddy Narala, Suresh Kumar^3

Department of Mechanical Engineering, CVR College of Engineering, Hyderabad

501510, India^1

Department of Mechanical Engineering, Faculty of Technology, University of Ibadan, Ibadan, Nigeria^2

Department of Mechanical Engineering, BITS-Pilani Hyderabad, Hyderabad

500078, India^3

关键词: Coefficient of determination;    Feed-forward back propagation;    Mean absolute percentage error;    Mean Square Error (MSE);    Minimal quantity lubrications;    Modeling of surface roughness;    Performance parameters;    Response surface methodology;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/346/1/012085/pdf
DOI  :  10.1088/1757-899X/346/1/012085

来源: IOP

【 摘 要 】

In the present paper, the artificial neural network (ANN) and response surface methodology (RSM) are used in modeling of surface roughness in WS2(tungsten disulphide) solid lubricant assisted minimal quantity lubrication (MQL) machining. The real time MQL turning of Inconel 718 experimental data considered in this paper was available in the literature [1]. In ANN modeling, performance parameters such as mean square error (MSE), mean absolute percentage error (MAPE) and average error in prediction (AEP) for the experimental data were determined based on Levenberg-Marquardt (LM) feed forward back propagation training algorithm with tansig as transfer function. The MATLAB tool box has been utilized in training and testing of neural network model. Neural network model with three input neurons, one hidden layer with five neurons and one output neuron (3-5-1 architecture) is found to be most confidence and optimal. The coefficient of determination (R2) for both the ANN and RSM model were seen to be 0.998 and 0.982 respectively. The surface roughness predictions from ANN and RSM model were related with experimentally measured values and found to be in good agreement with each other. However, the prediction efficacy of ANN model is relatively high when compared with RSM model predictions.