Articles written in Sadhana
Volume 44 Issue 6 June 2019 Article ID 0150
Laser cladding is a complex manufacturing process involving more than 19 variables related to laser source, workpiece movement, powder-substrate material combinations, clad geometry, powder flow dynamics, shrouding gas flow and so on. Significant research efforts have been directed to analytical-numericalempiricalmodelling of laser cladding and also in-process monitoring and control of the process. Still, due to complicated physics there is a dearth of simple analytical model for estimation of dilution in laser cladding. Its experimental measurement requires suitable micrographs of the clad cross section perpendicular to the clad path. This is a time-consuming and destructive way of measurement. Numerical models are time consuming to evaluate and hence not suitable for fast decision making or real-time control implementation. The analytical models available, despite having many approximations, are a little complicated, require fair amount computer programming and often need suitable prior guessing of range of output parameters for adjustment of constant values in the models. This poses some challenges for use and having an intuitive guidance, for a beginner/unskilled operator. Besides, their complexity may erect barrier in the way of their implementation for real time monitoring and control. This work proposes a simple linear regression model, formed based on energy balance approach, to estimate dilution in laser cladding. After fitting to a set of data, within a suitable process parameter window, for a particular clad-substrate material combination, this model can estimate dilution as a function of input/easily measureable parameters, viz. laser power, scan speed, clad width and clad height. The model fitted well to the experimental data taken from literature.
Volume 46 All articles Published: 3 July 2021 Article ID 0130
Among several factors that are having a profound impact on the overall machining process efficiency, cutting tool wear is the most significant one. Monitoring and identification of cutting tool wear state well before to its failure is important to achieve superior machining quality and profitable production. With the recent advancements in computational hardware, significant amount of research is being carried out on using deep learning techniques, in specific, convolution neural networks (CNN) for developing cutting tool wear monitoringsystem. Although, few researchers reported the use of CNN as a pathway to tool wear classification problems with significant results, the fundamental methodology adopted by these techniques still needs to be investigated. Hence, in the present work, a deep CNN architecture is designed by choosing appropriate hyper-parameters and a CNN model is developed by selecting proper training parameters for cutting tool wear classification. Machined surface images acquired during turning operation performed on mild steel components under dry condition by uncoated carbide inserts as cutting tool are used as input data to the CNN model for predicting the tool condition. The proposed model, whose classification performance is independent of machining conditions, has capability to extract the features and classify the cutting tool among the two classes (i.e., unworn and worn classes). Accuracies of 96.3% and 99.9% are realized for classification of tool flank wear from raw and minimally preprocessed(contrast enhanced) machined surface images, respectively.