Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
13 results
Search Results
Item Fault diagnosis of helical gear box using decision tree through vibration signals(RAMS Consultants, 2013) Sugumaran, V.; Jain, D.; Amarnath, M.; Kumar, H.This paper uses vibration signals acquired from gears in good and simulated faulty conditions for the purpose of fault diagnosis through machine learning approach. The descriptive statistical features were extracted from vibration signals and the important ones were selected using decision tree (dimensionality reduction). The selected features were then used for classification using J48 decision tree algorithm. The paper also discusses the effect of various parameters on classification accuracy. © RAMS Consultants.Item Fault diagnosis of deep groove ball bearing through discrete wavelet features using support vector machine(COMADEM International rajbknrao@btinternet.com, 2014) Vernekar, K.; Kumar, H.; Gangadharan, K.V.Bearings are the most important and frequently used machine components in most of the rotating machinery. In industry, breakdown of such crucial components causes heavy losses. So prevention of failure of such components is very essential. This paper presents an online fault detection of a bearing used in an internal combustion engine through machine learning approach using vibration signals of bearing in healthy and simulated faulty conditions. Vibration signals are acquired from bearing in healthy as well as different simulated fault conditions of bearing. The Discrete Wavelet Transform (DWT) features were extracted from vibration signals using MATLAB program. Decision tree technique (J48 algorithm) has been used for important feature selection out of extracted DWT features. Support vector machine is being used as a classifier and obtained results found with classification accuracy of 98.67%.The advantage of machine learning technique for fault diagnosis over conventional vibration analysis approach has demonstrated in this paper.Item Fault diagnosis studies of face milling cutter using machine learning approach(Multi-Science Publishing Co. Ltd claims@sagepub.com, 2016) Madhusudana, C.K.; Budati, S.; Gangadhar, N.; Kumar, H.; Narendranath, S.Successful automation of a machining process system requires an effective and efficient tool condition monitoring system to ensure high productivity, products of desired dimensions, and long machine tool life. As such the component's processing quality and increased system reliability will be guaranteed. This paper presents a classification of healthy and faulty conditions of the face milling tool by using the Naive Bayes technique. A set of descriptive statistical parameters is extracted from the vibration signals. The decision tree technique is used to select significant features out of all statistical extracted features. The selected features are fed to the Naive Bayes algorithm. The output of the algorithm is used to study and classify the milling tool condition and it is found that the Naive Bayes model is able to give 96.9% classification accuracy. Also the performances of the different classifiers are compared. Based on the results obtained, the Naive Bayes technique can be recommended for online monitoring and fault diagnosis of the face milling tool. © 2016 The Author(s).Item Condition monitoring of roller bearing by K-star classifier and K-nearest neighborhood classifier using sound signal(Tech Science Press sale@techscience.com, 2017) Sharma, R.K.; Sugumaran, V.; Kumar, H.; Amarnath, M.Most of the machineries in small or large scale industry have rotating element supported by bearings for rigid support and accurate movement. For proper functioning of machinery, condition monitoring of the bearing is very important. In present study sound signal is used to continuously monitor bearing health as sound signals of rotating machineries carry dynamic information of components. There are numerous studies in literature that are reporting superiority of vibration signal of bearing fault diagnosis. However, there are very few studies done using sound signal. The cost associated with condition monitoring using sound signal (Microphone) is less than the cost of transducer used to acquire vibration signal (Accelerometer). This paper employs sound signal for condition monitoring of roller bearing by K-star classifier and k-nearest neighborhood classifier. The statistical feature extraction is performed from acquired sound signals. Then two layer feature selection is done using J48 decision tree algorithm and random tree algorithm. These selected features were classified using K-star classifier and k-nearest neighborhood classifier and parametric optimization is performed to achieve the maximum classification accuracy. The classification results for both K-star classifier and k-nearest neighborhood classifier for condition monitoring of roller bearing using sound signals were compared. © Copyright 2017 Tech Science Press.Item Engine gearbox fault diagnosis using machine learning approach(Emerald Group Publishing Ltd. Howard House Wagon Lane, Bingley BD16 1WA, 2018) Vernekar, K.; Kumar, H.; Gangadharan, K.V.Purpose: Bearings and gears are major components in any rotatory machines and, thus, gained interest for condition monitoring. The failure of such critical components may cause an increase in down time and maintenance cost. Condition monitoring using the machine learning approach is a conceivable solution for the problem raised during the operation of the machinery system. The paper aims to discuss these issues. Design/methodology/approach: This paper aims engine gearbox fault diagnosis based on a decision tree and artificial neural network algorithm. Findings: The experimental result (classification accuracy 85.55 percent) validates that the proposed approach is an effective method for engine gearbox fault diagnosis. Originality/value: This paper attempts to diagnose the faults in engine gearbox based on the machine learning approach with the combination of statistical features of vibration signals, decision tree and multi-layer perceptron neural network techniques. © 2018, Emerald Publishing Limited.Item Hybrid wavelet packet machine learning approaches for drought modeling(Springer, 2020) Das, P.; Naganna, S.R.; Deka, P.C.; Pushparaj, J.Among all the natural disasters, drought has the most catastrophic encroachment on the surrounding and environment. Gulbarga, one of the semi-arid districts of Karnataka state, India receives about 700 mm of average annual rainfall and is drought inclined. In this study, the forecasting of drought for the district has been carried out for a lead time of 1 month and 6 months. The multi-temporal Standardized Precipitation Index (SPI) has been used as the drought quantifying parameter due to the fact that it is calculated on the basis of one simplest parameter, i.e., rainfall and additionally due to its ease of use. The fine resolution daily gridded precipitation data (0.25º × 0.25º) procured from Indian Meteorological Department (IMD) of 21 grid locations within the study area have been used for the analysis. Forecasting of drought plays a significant role in drought preparedness and mitigation plans. With the advent of machine learning (ML) techniques over the past few decades, forecasting of any hydrologic event has become easier and more accurate. However, the use of these techniques for drought forecasting is still obscure. In this study, Artificial Neural Network (ANN) and Support Vector Regression (SVR) techniques have been employed to examine their accuracy in drought forecasting over shorter and longer lead times. Furthermore, two hybrid approaches have been formulated by coupling a data transformation method with each of the aforementioned ML approaches. At the outset, pre-processing of input data (i.e., SPI) has been carried out using Wavelet Packet Transform (WPT) and then used as inputs to ANN and SVR models to induce hybrid WP-ANN and WP-SVR models. The performance of the hybrid models has been evaluated based on the statistical indices such as R2 (co-efficient of determination), RMSE (Root Mean Square Error), and MAE (Mean Absolute Error). The results showed that the hybrid techniques have better forecast performance than the standalone machine learning approaches. Hybrid WP-ANN model performed relatively better than WP-SVR model for most of the grid locations. Also, the forecasting results deteriorated as the lead time increased from 1 to 6 months. © 2020, Springer-Verlag GmbH Germany, part of Springer Nature.Item Efficient deep learning techniques for the detection of phishing websites(Springer, 2020) Somesha, M.; Pais, A.R.; Rao, R.S.; Rathour, V.S.Phishing is a fraudulent practice and a form of cyber-attack designed and executed with the sole purpose of gathering sensitive information by masquerading the genuine websites. Phishers fool users by replicating the original and genuine contents to reveal personal information such as security number, credit card number, password, etc. There are many anti-phishing techniques such as blacklist- or whitelist-, heuristic-feature- and visual-similarity-based methods proposed as of today. Modern browsers adapt to reduce the chances of users getting trapped into a vicious agenda, but still users fall as prey to phishers and end up revealing their secret information. In a previous work, the authors proposed a machine learning approach based on heuristic features for phishing website detection and achieved an accuracy of 99.5% using 18 features. In this paper, we have proposed novel phishing URL detection models using (a) Deep Neural Network (DNN), (b) Long Short-Term Memory (LSTM) and (c) Convolution Neural Network (CNN) using only 10 features of our earlier work. The proposed technique achieves an accuracy of 99.52% for DNN, 99.57% for LSTM and 99.43% for CNN. The proposed techniques utilize only one third-party service feature, thus making it more robust to failure and increases the speed of phishing detection. © 2020, Indian Academy of Sciences.Item Mechanical response of additively manufactured foam: A machine learning approach(Elsevier B.V., 2022) Neelam, R.; Kulkarni, S.A.; Bharath, H.S.; Powar, S.; Doddamani, M.This paper uses ensemble and automated machine learning algorithms to predict the mechanical properties (tensile and flexural strength) of a three-dimensionally printed (3DP) foamed structure. The closed cell foams were made from the most commonly used thermoplastic, High-Density Polyethylene (HDPE). The hollow glass microspheres are infused in HDPE at varying volume %. The available data on these foams' mechanical properties are used by the chosen machine learning (ML) algorithms to propose the best suited algorithm for such a three-phased microstructure as these closed cell foams exhibit. Finally, the strength predictions from the models were validated using experimental data. The models were trained with nozzle temperature, bed temperature, and force values as input parameters. The output parameters predicted were the tensile and flexural strength. LightGBM outperforms all other models in terms of performance among ensemble-based models, while H2OAutoML outperforms all other models. All the ML algorithms produced models with greater than 95% accuracy. Finally, memory and time consumption for each model are presented. © 2022 The AuthorsItem Characterizing Structural Heterogeneity in Metallic Glasses: A Molecular Dynamics-Guided Machine Learning Approach(Springer, 2024) Li, H.; Mohanty, H.The main objective of this research is to develop a robust Bayesian machine learning (ML) model capable of predicting and characterizing the structural heterogeneity in metallic glasses (MGs). The model is constructed using input data obtained from molecular dynamics simulations of CuZr MGs, encompassing a wide range of alloying compositions and simulation parameters. The ML model utilized crucial output variables: the 2D fractal dimension (with a fractal exponent ranging from 1.55 to 1.81) and correlation function (correlation length spanning from 1.1 to 4.05 nm), demonstrating inverse and direct relationships with the degree of heterogeneity, respectively. The results demonstrate the model's high predictive performance, with accuracy values of 0.9398 for the fractal dimension and 0.9639 for the correlation length. It is noteworthy that the correlation length proves to be a reliable indicator for low to intermediate levels of structural heterogeneity, while the fractal dimension effectively characterizes high-level heterogeneity in MGs. Moreover, the integration of both indicators complements each other in accurately predicting structural heterogeneity. Additionally, the developed ML model showcases its versatility in effectively characterizing MG samples exposed to diverse treatments, such as annealing and rejuvenation processes. © The Indian Institute of Metals - IIM 2023.Item Advancing solar PV panel power prediction: A comparative machine learning approach in fluctuating environmental conditions(Elsevier Ltd, 2024) Tripathi, A.K.; Mangalpady, M.; Elumalai, P.V.; Karthik, K.; Khan, S.A.; Asif, M.; Koppula, K.S.Solar photovoltaic (PV) panels play a crucial role in sustainable energy generation, yet their power output often faces uncertainties due to dynamic weather conditions. In this study, a comparative machine learning approach is introduced, utilizing multivariate regression (MR), support vector machine regression (SVMR), and Gaussian regression (GR) techniques for precise solar PV panel power prediction. The investigation into the impact of environmental factors—solar radiation, ambient temperature, and relative humidity—on PV panel output reveals the superior predictive capabilities of SVMR models. With a mean squared error (MSE) of 0.038, a mean absolute error (MAE) of 0.17, and an R2 value of 0.99, SVMR outperforms GR and MR models. Conversely, Gaussian regression demonstrates comparatively weaker performance, yielding an R2 of 0.88, an MSE of 0.49, and an MAE of 0.63. This research underscores the reliability and enhanced accuracy of the proposed SVMR model in forecasting solar PV panel output. The outcomes presented herein carry significant implications for promoting the widespread adoption of PV panels in electricity generation, particularly in challenging environmental conditions. The findings offer valuable insights into optimizing solar PV deployment, ultimately contributing to the expansion of solar power generation in the national energy landscape. Moreover, the comparative analysis provides insights into how anticipated PV power generation can adapt to varying weather conditions, encompassing factors such as temperature, humidity, and solar radiation. © 2024 The Authors