Search

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 (MRR). 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 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. [ABSTRACT FROM AUTHOR]

Chatter is a type of self-excited vibration that expresses variations in frequency and energy dispersion during the milling process and invariably results in poor part quality and a lower material removal rate. An efficacious chatter detection approach is necessary to anticipate the chatter's nascent stage. Feature extraction is an important step in identifying chatter. In this paper, an efficient PF-based multi-mode signal processing method, i.e., Spline-Based Local Mean Decomposition (SBLMD), has been used to decompose the experimentally acquired sound signals into a series of PFs and then, selected PFs have been used to reconstruct the new chatter signal, which is rich in information. Further, two three-layer ANN-based prediction models are established to predict the CI and MRR. Three process-related variables, such as tool speed, feed speed, and cut depth, have been used to develop ANN models. Statistical comparisons have been conducted to obtain the optimal training algorithm and have found that the LM-based training algorithm was the best among the five other training algorithms. For the estimates of CI and MRR, the neurons in the hidden layer are optimized at 5 and 7 with the least mean squared errors (MSE), respectively. After applying MOPSO to ANN-based prediction models, the MOPSO-optimized ANNs are very sensitive to optimizing input layers. The optimal ranges for the Cut Depth (CD), Feed Speed (FS) and Tool Speed (TS) are 1.56–1.77 mm, 77–97 mm/min, and 2380–2880 rpm, respectively. [ABSTRACT FROM AUTHOR]

In recent decades, a lot of work has been done to mitigate self-excited vibration effects in milling operations. Still, a robust methodology is yet to be developed that can suggest stability bounds pertaining to higher metal removal rates (MRRs). In the present work, experimentally-acquired acoustic signals in milling operations have been computed using a modified spline-based local mean decomposition technique in order to cite tool chatter features. Further, three artificial neural network training algorithms; resilient propagation, conjugate gradient-based and Levenbergâ€"Marquardt algorithms, and two activation functions; hyperbolic tangent sigmoid and log sigmoid, have been used to train the acquired chatter vibration and MRR data set. Over-fitting or under-fitting issues may arise from the random selection of a number of hidden neurons. The solution to these problems is also proposed in this paper. Among these training algorithms and activation functions, a suitable one has been selected and further invoked to develop prediction models of chatter severity and MRR. Finally, multi-objective particle swarm optimization has been invoked to optimize the developed prediction models to obtain the most favourable range of input parameters pertaining to stable milling with higher productivity. [ABSTRACT FROM AUTHOR]

• Acquired raw chatter signals can be well processed using spline-based local mean decomposition. • It is not possible to assess the influence of feed rate on chatter severity using stability lobe diagram. • A new statistical parameter has been evaluated for ascertain stability regimes in milling. • Online monitoring of milling process can be well executed considering the ascertained statistical parameter. In the present work, a novel online monitoring system has been developed using a new modified spline based local mean decomposition technique for the identification of tool chatter onset pertaining to the three input milling parameters viz. feed rate, axial depth of cut and spindle speed. Acquired sound signals of machining at various cutting parameters are processed using a Spline Based Local Mean Decomposition (SBLMD) technique. A series of product functions are extracted from the processed signal. Prominent PF's are combined to reconstruct the signal representing chatter. Reconstructed chatter signal has been analysed to extract tool chatter features. Finally, online monitoring of tool chatter is executed considering the ascertained chatter severity threshold. Viability of the proposed methodology is validated by performing more experiments and the results indicated that it can be well adopted for the online monitoring of tool chatter. [ABSTRACT FROM AUTHOR]