Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
8 results
Search Results
Item Fault Diagnosis of Face Milling Tool using Decision Tree and Sound Signal(Elsevier Ltd, 2018) Madhusudana, C.K.; Kumar, K.; Narendranath, S.The monitoring of machining process can improve the quality of product and economy of production. The monitoring system helps to recognize and monitor the surface roughness, dimensional tolerance and tool condition. In this way, the condition monitoring system provides precise dimensional products, high productivity and enhanced machine tool life. This paper presents the classification of healthy and faulty conditions of the face milling tool using Decision tree (J48 algorithm) technique through machine learning approach. The sound signals of the face milling tool under healthy and faulty conditions are acquired. A set of discrete wavelet features are extracted from the sound signals using discrete wavelet transform (DWT) method. Decision tree technique is used to select prominent features out of all extracted features. The selected features are fed to the same algorithm for classification. Output of the algorithm is used to study and categorize the tool conditions. The decision tree model has provided a good classification accuracy of about 81% for the given sound signals and can be considered for fault diagnosis/condition monitoring. From the experimental results, it is suggested that the proposed method which comprises of decision tree and DWT techniques with sound signals can be recommended for the applications of fault diagnosis of the face milling tool. © 2017 Elsevier Ltd. All rights reserved.Item Determination of transient and steady state cutting in face milling operation using recurrence quantification analysis(2009) Mhalsekar, S.D.; Mohan, G.; Rao, S.S.; Gangadharan, K.V.Typical face milling operation involves transient and steady state cutting phases. Identification and distinction of the cutting state will primarily help in understanding the fundamentals of forced vibration, deflection and dynamic stability in milling system at the beginning and end of a cutting pass. Such type of investigation has advantages in process planning, tool geometry optimization and on-line fault diagnosis. An effort to provide estimation of transient and steady state cutting has been made using Recurrence Quantification Analysis (RQA) of vibration signals. RQA is a novel nonlinear analytical tool. It starts with construction of recurrence plot using embedded dimension and time delay. The recurrence plot is than quantified resulting in RQA. Face milling of H11 chromium steel has been carried out at two different cutting conditions and analyzed. The resulting RQA parameters could identify and distinguish transient and steady state cutting. © 2006-2009 Asian Research Publishing Network (ARPN).Item Development of a surface roughness prediction system for machining of hot chromium steel (AISI H11) based on artificial neural network(Medwell Journals medwellonline@gmail.com, 2010) Rai, R.; Shettigar, A.; Rao, S.S.; ShriramAn attempt have been made to apply the principles of artificial neural networks (ANN) towards developing a prediction model for surface roughness during the machining of high chromium steel through face milling process. Now a days, hot chromium steel is prominently used in die and mould industry as well as in press tools, helicopter rotor blades, etc. Initially, Taguchi design of experiments was applied while conducting the experiments to reduce the time and cost of experiment. Multilayer perceptron (MLP) network using Feed Forward Error Back propagation was chosen as the neural network architecture to describe the process model. The experiments were conducted on a C.N.C milling machine using carbide cutters. Pearson correlation coefficient was also calculated to analyze the correlation between the system inputs and selected system output i.e. surface roughness. The results of ANN modeling were substantiated by testing and validation of the resulting surface roughness values and the results have been encouraging. The outputs of Pearson correlation coefficient also showed a strong correlation between the feed per tooth and surface roughness, followed by cutting speed. © 2006-2010 Asian Research Publishing Network (ARPN).Item Condition monitoring of face milling tool using K-star algorithm and histogram features of vibration signal(Elsevier B.V., 2016) Madhusudana, C.K.; Kumar, H.; Narendranath, S.This paper deals with the fault diagnosis of the face milling tool based on machine learning approach using histogram features and K-star algorithm technique. Vibration signals of the milling tool under healthy and different fault conditions are acquired during machining of steel alloy 42CrMo4. Histogram features are extracted from the acquired signals. The decision tree is used to select the salient features out of all the extracted features and these selected features are used as an input to the classifier. K-star algorithm is used as a classifier and the output of the model is utilised to study and classify the different conditions of the face milling tool. Based on the experimental results, K-star algorithm is provided a better classification accuracy in the range from 94% to 96% with histogram features and is acceptable for fault diagnosis. © 2016 Karabuk UniversityItem Face milling tool condition monitoring using sound signal(Springer, 2017) Madhusudana, C.K.; Kumar, H.; Narendranath, S.This article presents the fault diagnosis of the face milling tool using sound signal. During milling, sound signals of the face milling tool under healthy and fault conditions are acquired. Discrete wavelet transform (DWT) features are extracted from the acquired sound signals. The support vector machine (SVM) technique is used to classify the face milling tool conditions using the extracted DWT features. Also, a comparison of classification efficiencies of different classifiers with respect to different features extraction methods is carried out. It is shown that, all extracted DWT features demonstrate better results than those obtained from selected statistical features and empirical mode decomposition features. The SVM technique is the best classifier as it has given an encouraging result in this study when compared to other classifiers, and it has provided 83% classification accuracy for the given experimental conditions and workpiece of steel alloy 42CrMo4. Hence, the SVM method and DWT technique can be put forward for the applications of condition monitoring of the face milling tool with sound signal. © 2017, The Society for Reliability Engineering, Quality and Operations Management (SREQOM), India and The Division of Operation and Maintenance, Lulea University of Technology, Sweden.Item Use of discrete wavelet features and support vector machine for fault diagnosis of face milling tool(Tech Science Press sale@techscience.com, 2018) Madhusudana, C.K.; Gangadhar, N.; Kumar, H.; Narendranath, S.This paper presents the fault diagnosis of face milling tool based on machine learning approach. While machining, spindle vibration signals in feed direction under healthy and faulty conditions of the milling tool are acquired. A set of discrete wavelet features is extracted from the vibration signals using discrete wavelet transform (DWT) technique. The decision tree technique is used to select significant features out of all extracted wavelet features. C-support vector classification (C-SVC) and ?-support vector classification (?-SVC) models with different kernel functions of support vector machine (SVM) are used to study and classify the tool condition based on selected features. From the results obtained, C-SVC is the best model than ?-SVC and it can be able to give 94.5% classification accuracy for face milling of special steel alloy 42CrMo4. © © 2018 Tech Science Press..Item Machining Parameters Optimization of AA6061 Using Response Surface Methodology and Particle Swarm Optimization(SpringerOpen, 2018) Lmalghan, R.; Karthik, K.; Shettigar, A.; Rao, S.; Herbert, M.The influence of cutting parameters on the responses in face milling has been examined. Spindle speed, feed rate and depth of cut have been considered as the influential factors. In accordance with the design of experiments (DOE) a series of experiments have been carried out. The paper exemplifies on the optimizing the process parameters in milling through the application of Response surface methodology (RSM), RSM-based Particle Swarm Optimization (PSO) technique and Desirability approach. These aforesaid techniques have been applied to experimentally establish data of AA6061 aluminium material to study the effect of process parameters on the responses such as cutting force, surface roughness and power consumption. By adopting the multiple regression techniques, the interaction between the process parameters are acquired. The optimal parameters have been found by adopting the multi-response optimization techniques, i.e. desirability approach and PSO. The performance capability of PSO and desirability approach is investigated and found that the values obtained from PSO are comparable with the values of desirability approach. © 2018, Korean Society for Precision Engineering and Springer-Verlag GmbH Germany, part of Springer Nature.Item Application of back propagation algorithms in neural network based identification responses of AISI 316 face milling cryogenic machining technique(Taylor and Francis Ltd., 2022) Karthik, K.R.; Malghan, R.L.; Shettigar, A.; Rao, S.S.; Herbert, M.A.The paper explores the potential study of artificial neural network (ANN) for prediction of response surface roughness (Ra) in face milling operation with respect to cryogenic approach. The model of Ra was expressed as the main factor in face milling of spindle speed, feed rate, depth of cut and coolant type. The ANN is trained using four various back propagation algorithms (BPA). The emphasis of the paper is to investigate the performance and the accuracy of the attained results depicts the effectiveness of the trained ANN in identifying the predicted Ra. The incorporated various BPA in predicting the Ra. The performance comparative study is made among statistical (Response Surface Methodology (RSM)) and ANN (BPA–training algorithm) methods. The various incorporated BPA algorithms are Gradient Descent (GD), Scaled Conjugate Gradient Descent (SCGD), Levenberg Marquardt (LM) and Bayesian Neural Network (BNN). Afterwards the best suitable BPA is identified in predicting Ra for AISI 316 in face milling operation using liquid nitrogen (LN2) as cutting fluid. The outperformed BPA is identified based on the attained deviation percentage and time required for the training the network. © 2020 Engineers Australia.