Ascertaining higher MRR at chatter free milling using spline-based local mean decomposition and artificial neural network based hybrid approach

Document Type : Article


Mechanical Engineering Department, Jaypee University of Engineering and Technology, Guna (M.P.), India, 473226


Chatter is a type of self-induced vibration that reflects fluctuations in both frequency and energy dispersion during the milling process, inevitably resulting in substandard part quality and diminished material removal rates. It is essential to employ a robust chatter detection method to anticipate its emergence in the early stages. This study introduces an efficient Product Function (PF) based multi-mode signal processing technique, specifically the spline-based local mean decomposition (SBLMD). This method is applied to decompose sound signals acquired through experimentation into a series of effective PF’s. Subsequently, selected PFs are employed to reconstruct a new chatter signal that is information-rich. Additionally, prediction models based on Artificial Neural Networks (ANN) are established to predict Chatter Indicator (CI) and Material Removal Rate (MRR) using three different activation algorithms: Tan Sigmoid (TANSIG), Log Sigmoid (LOGSIG), and Purely Linear (PURELIN). Statistical comparisons have been conducted in order to obtain the optimal activation algorithm and found out that data set trained with LOGSIG gives minimal error. Moreover, an optimal range of input parameters has been selected pertaining to minimum chatter and maximum MRR. Confirmation tests on the obtained set of parameters have been carried out in order to analyse and authenticate the proposed technique.


Main Subjects