Fault Detection in Machine Bearings Using Deep Learning A. Vaishnavi, Anju Sharma, VPS Naidu SAE Technical Papers, 2024 <div class="section abstract"><div class="htmlview paragraph">In the contemporary industrial landscape, machinery stands as the cornerstone of various sectors. Over time, these machines undergo wear and tear due to extensive use, leading to the introduction of subtle faults into the machine readings. Recognizing the pivotal role of machinery in diverse industries, the timely detection of these faults becomes imperative. Early fault detection is crucial for preventing costly downtimes, ensuring operational efficiency, and enhancing overall safety. This paper addresses the need for an effective condition monitoring and fault detection system, focusing specifically on the application of the Long Short-Term Memory (LSTM) deep learning model for fault detection in bearings using accelerometer data. The preprocessing phase involves extracting time domain features, encompassing normal, differentiated, integrated, and carefully selected signals, to create an informative dataset tailored for the LSTM model. This model is then meticulously trained on the dataset to discern and accurately diagnose faults within the machinery. The research meticulously observes and reports that the LSTM model achieves an impressive 100% accuracy in fault detection, showcasing its robust capabilities in identifying subtle anomalies within the machine vibrations. In conclusion, the study underscores the critical importance of early fault detection in industrial machinery and highlights the efficacy of the LSTM model in this domain. The singular focus on the LSTM model demonstrates its proficiency in achieving accurate fault detection, contributing significantly to the predictive maintenance field. This research not only advances fault detection methodologies but also fosters a more reliable and sustainable industrial landscape, emphasizing the potential of deep learning techniques, particularly the LSTM model, in ensuring the optimal performance and longevity of machinery in diverse industrial settings.</div></div>
Optimizing bearing health condition monitoring: exploring correlation feature selection algorithm Anju Sharma, Taruv Harshita Priya, VPS Naidu Engineering Research Express, 2024 Vibration signals are a critical source of information for detecting and diagnosing bearing faults, making this research particularly relevant to the condition monitoring of industrial machinery, particularly bearings using vibration signals. This study delves into how feature selection can be done using Pearson’s Correlation Co-efficient within the context of monitoring bearing health conditions, utilizing two distinct approaches. Approach-1 involves feature selection without considering labels, while Approach-2 incorporates labels for feature selection. Comparative analysis is conducted against outcomes obtained when all features are selected. The research scrutinizes the impact of feature selection on classifier performance, accuracy, and execution times, utilizing various machine learning algorithms such as Decision Tree (DT), K Nearest Neighbor (KNN), Support Vector Machine (SVM), and Naïve Bayes (NB). The findings underscore that feature selection significantly enhances classifier accuracy while reducing execution times. Specifically, only DT and KNN with 50 neighbors achieved 100% accuracy when all features were considered. However, with feature selection using Approach-1 (without labels), DT, KNN, SVM (excluding 100 neighbors), and NB (with Normal/Gaussian kernel) attained 100% accuracy. Employing Approach-2 (with labeled features), DT with 0.7 and 0.9 thresholds, SVM-G with all thresholds (0.6, 0.7, and 0.9), KNN with all thresholds (except 100 neighbors), and NB-n (with all thresholds) achieved 100% accuracy. The study emphasizes the pivotal role of feature selection using Pearson’s Correlation Coefficient in enhancing machine learning classifier performance, offering promising avenues for future research and practical applications across diverse domains.
Machine Learning-based Bearing Fault Classification Using Higher Order Spectral Analysis Anju Sharma, G.K. Patra, V.P.S. Naidu Defence Science Journal, 2024 In the defense sector, where mission success often hinges on the reliability of complex mechanical systems, the health of bearings within aircraft, naval vessels, ground vehicles, missile systems, drones, and robotic platforms is paramount. Different signal processing techniques along with Higher Order Spectral Analysis (HOSA) have been used in literature for the fault diagnosis of bearings. Bispectral analysis offers a valuable means of finding higher-order statistical associations within signals, thus proving to detect the nonlinearities among Gaussian and non-Gaussian data. Their resilience to noise and capacity to unveil concealed information render them advantageous across a range of applications. Therefore, this research proposesa novel approach of utilizing the features extracted directly from the Bispectrum for classifying the bearing faults, departing from the common practice in other literature where the Bispectrum is treated as an image for fault classification. In this work vibration signalsare used to detect the bearing faults. The features from the non-redundant region and diagonal slice of the Bispectrum are used to capture the statistical and higher-order spectral characteristics of the vibration signal. A set of sixteen machine learning models, viz., Decision Trees, K-Nearest Neighbors, Naive Bayes, and Support Vector Machine, is employed to classify the bearing faults. The evaluation process involves a robust 10-fold cross-validation technique. The results reveal that the Decision Tree algorithm outperformed all others, achieving a remarkable accuracy rate of 100 %. The naive Bayes algorithm also demonstrated the least performance, with an accuracy score of 99.68 %. The results obtained from these algorithms have been compared with those achieved using Convolutional Neural Network (CNN), revealing that the training time of these algorithms is significantly shorter in comparison to CNN.
Bispectral analysis and information fusion technique for bearing fault classification Anju Sharma, G K Patra, V P S Naidu Measurement Science and Technology, 2024 The feasibility and effectiveness of data fusion for the fault classification of bearing faults have been very well iterated in the literature. However, all previous endeavors have been limited to time, frequency, and time-frequency domain techniques. The use of higher-order spectral analysis (HOSA), especially Bispectrum and Trispectrum, for fault detection is gaining importance in recent studies due to the many advantages of HOSA. Bispectral features provide a valuable tool for capturing higher-order statistical relationships in signals, making them particularly effective in detecting nonlinearities and distinguishing between Gaussian and non-Gaussian data. Their robustness to noise and ability to reveal hidden information make them advantageous in applications such as vibration analysis, speech recognition, and image processing, where complex signal interactions and nonlinearity play a significant role in data interpretation and pattern recognition. This paper proposes a methodology for the fusion of the data from the vibration and the acoustic sensors for the fault detection of roller element bearings using bispectral features. Higher-order spectral characteristics are derived from vibration and acoustic sensor data, and they are fused using artificial neural networks and various other machine learning algorithms like support vector machine, K nearest neighbor, Naïve Bayes algorithm, and decision tree. This work primarily aims to evaluate the performance of each classifier when applied to the fused data, in contrast to the performance when using individual sensor data alone. The outcomes revealed that, even though the accuracy of the acoustic sensor data was lower in comparison to the vibration sensor data, which exhibited the highest performance of 100% accuracy with nearly all the classifiers, the fused data achieved remarkable results of 100% accuracy with artificial neural networks and decision trees. However, the Naïve Bayes algorithm yielded the lowest accuracy when applied to the fused data. The primary objective of this paper is to demonstrate the application of bispectrum analysis for data fusion and to enhance confidence in fault detection. It achieves this by maintaining the capability to accurately and dependably detect faults, even when a single sensor encounters issues or falls short of anticipated performance standards.
Exploration of an unconventional validation tool to investigate aero engine transonic fan flutter signature A.N. Viswanatha Rao, T.N. Satish, V.P.S. Naidu, Soumendu Jana International Journal of Turbo and Jet Engines, 2023 Flutter, an aeroelastic blade vibration phenomena, experienced by the fan of an developmental aero gas turbine engine, result in blade failure. Hence, suitable flutter detection instrumentation is required during engine testing. Flutter signature capture from revolving blades is a challenging task that necessitates either a complicated strain gauge-based rotating instrumentation or a noncontact tip timing system. Authors investigated a unique way for identifying, measuring, and validating flutter signature by assessing wall static pressure pulsations produced during blade tip transit across a casing mounted high bandwidth sensor during this research. The authors devised a mathematical model to explain signal spectrum components that feature both amplitude and angle modulation properties at the same time. The theory was tested using first-stage fan rotor blades that were fluttering in the first flexural mode (1F) and forming the second nodal diameter (2ND). The approach’s estimated blade deflection was compared to measurements taken using a traditional tip timing method up to 7 mm and determined to be within 1% inaccuracy. This research provides a low-cost, easy alternative technique for measuring flutter during engine development testing.
Machine learning augmented multi-sensor data fusion to detect aero engine fan rotor blade flutter A. N. Viswanatha Rao, T. N. Satish, V. P. S. Naidu, Soumendu Jana International Journal of Turbo and Jet Engines, 2023 Flutter-induced fatigue failure investigation of the fan blades of aero-engines necessitates extensive testing. During engine ground testing, strain gauges on rotor fan blades and casing vibration sensors were employed to investigate structural dynamic aspects. The correlation between strain sensor signals and fan casing vibration signals allowed the diagnosis of fluttering fan blades. For automated flutter detection during engine development testing, a machine learning-augmented information fusion methodology was developed. The method analyses casing vibration signals by extracting time-domain statistical features, intrinsic mode function characteristics through empirical mode decomposition, and recurrence quantification features. Feature vectors obtained from a relatively large set of engine tests were subjected to dimension reduction by applying machine learning techniques to rank them. Reduced feature vector space was labelled as “flutter” or “normal” based on the correlation of rotor strain gauge signals. In addition, the labelled feature vectors were employed to train classifier models using supervised learning-based algorithms such as Support Vector Machines, Linear Discriminant Analysis, K-means Clustering, and Artificial Neural Networks. Using only vibration signals from the casing, the trained and validated classifiers were able to detect flutter in fan baldes with a 99% probability during subsequent testing.
Machine Learning Algorithms for Phonocardiogram Signal Classification Chaitra Nijalingappa, VPS Naidu 4th International Conference on Communication Computing and Industry 6 0 C216 2023, 2023 Cardiac conditions remain a significant cause of illness and mortality worldwide. Early and accurate diagnosis is crucial for prompt therapies and improved patient outcomes. Phonocardiography, which analyses heart sounds graphically, can assist in identifying various pathologies such as valvar disorders, myocardial infarction, heart murmurs, and abnormal heart rhythms. In this study, we utilised two databases. Dataset 1 has two categories: normal and murmur heart sounds. Dataset 2 has five categories, including one normal and four abnormal types. This report extracts time domain features, frequency domain features, MFCCs, and DWT-based features, which leads to extracting the 77 features in total from phonocardiogram signals. Feature selection techniques were applied and identified the best 21 features out of 77 features with Dataset 1 and the best 14 out of 77 features with Dataset 2. Disease classification uses k-nearest neighbour (KNN), cubic support vector machine (SVM), Kernel SVM, Logistic Regression, and Fine Tree algorithms in MATLAB. The proposed methodology achieved a training accuracy of 94.1% and a testing accuracy of 100% for dataset 1. Similarly, a training accuracy of 98.3% and testing accuracy of 100 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup> for dataset 2. This report demonstrates its potential for clinical applications.
Blur Removal and Image Merging for Image Enhancement on Python Chaitanya Patange, VPS Naidu 2023 International Conference on Network Multimedia and Information Technology Nmitcon 2023, 2023 Image Fusion is important to retrieve useful information from a set of images that are given by the user and merge/fuse these images to generate a single output image which is very informative and useful when compared to the input images. In the present work, the blurred images were fused to make clear and informative images. Humans and machines will have good use of the resulting processed image for understanding the details of the captured images through image processing or image fusion methods. In this paper, the image fusion techniques were developed and tested on the Python platform. The image fusion techniques were carried out by suitable algorithms for blur detection and image correction. Another work was carried out to merge images with user-defined parameters to have enhanced image parameters. Image fusion is used in artificial intelligence (AI), intelligent robots, stereo camera fusion, medical imaging, manufacturing process monitoring, electronic circuit design and inspection etc.
Performance Evaluation of Classifiers for ECG Signal Analysis Sundari Tribhuvanam, H C Nagaraj, V P S Naidu 2023 International Conference on Artificial Intelligence and Applications Icaia 2023 and Alliance Technology Conference Atcon 1 2023 Proceeding, 2023 The cardiac well-being of humans can be monitored by non-invasive electrocardiogram (ECG) to a greater extent. Subtle changes in ECG waveform can be identified by computer-assisted tools. Machine learning algorithms play an important role in arrhythmia classification. This paper presents a comparative analysis of various classifiers to support ECG classification. The classification model detects seven arrhythmia types from the generated dataset derived from arrhythmia database of MIT-BIH. The proposed technique considers ECG beat features in time domain based on ECG morphology and statistics. Arrhythmia classification is carried out for seven classes. Performance evaluation is carried out for different classifiers with accuracy, sensitivity, specificity, and F1-score as the evaluation metrics. Classification accuracy up to 97%, Recall up to 92%, F1-score up to 91% and precision up to 91% is achieved with specific classifiers across various arrhythmia classes under consideration.
UAS Simulator: A Laboratory Set-Up Abhishek Kasana, Ajay Misra, VPS Naidu International Conference on Emerging Trends in Information Technology and Engineering Ic Etite 2020, 2020
Stress detection from EEG using power ratio Taruv Harshita Priya, P. Mahalakshmi, VPS Naidu, M. Srinivas International Conference on Emerging Trends in Information Technology and Engineering Ic Etite 2020, 2020
Arrhythmia classification with single beat ECG evaluation and support vector machine Department of Electronics, University of Mysore, Mysore, India., Sundari Tribhuvanam*, H. C. Nagaraj, Department of Electronics, Nitte Research, Education Academy, Bengaluru-India., V.P.S. Naidu, MSDF, FMCD, CSIR-NAL, Bengaluru-India. International Journal of Innovative Technology and Exploring Engineering, 2019
ECG Abnormality Classification with Single Beat Analysis Sundari Tribhuvanam, H C Nagaraj, V P S Naidu Proceedings International Conference on Vision Towards Emerging Trends in Communication and Networking Vitecon 2019, 2019
Survey on UAV navigation in GPS denied environments G Balamurugan, J Valarmathi, V P S Naidu International Conference on Signal Processing Communication Power and Embedded System Scopes 2016 Proceedings, 2017
MAS simulator: A laboratory set up B. Indhu, N. Sivakumaran, A Srikanth, V P S Naidu Proceedings 2015 International Conference on Cognitive Computing and Information Processing Ccip 2015, 2015
Vulnerability, resilience and dynamism of the custom economy in Melanesia Household Vulnerability and Resilience to Economic Shocks Findings from Melanesia, 2014
Gender security and trade: The millennium development goals in the Pacific Development in an Insecure and Gendered World the Relevance of the Millennium Goals, 2010
Decentralized multi passive sensor system for 3D target tracking 46th AIAA Aerospace Sciences Meeting and Exhibit, 2008
Evaluation of acceleration and jerk models in radar and IRST data fusion for tracking evasive maneuvering target 46th AIAA Aerospace Sciences Meeting and Exhibit, 2008
Target tracking and fusion using imaging sensor and ground based radar data Collection of Technical Papers AIAA Guidance Navigation and Control Conference, 2005
Data association and fusion algorithms for tracking in presence of measurement loss Journal of the Institution of Engineers India Aerospace Engineering Journal, 2005
Autoregressive (AR) based power spectral analysis of heart rate time series signal (HRTS signal) IEEE Region 10 Annual International Conference Proceedings TENCON, 2003
Evaluation of data association and fusion algorithms for tracking in the presence of measurement loss AIAA Guidance Navigation and Control Conference and Exhibit, 2003
Data fusion mathematics: theory and practice JR Raol, SS Selvi, SK Kashyap, A Sanketh CRC Press , 2025 2025 Citations: 70
Feature Tracking/Mapping Using a Vision and GPS/INS System on a UAV Platform JR Raol, VPS Naidu Mathematical Modelling of Aerospace Dynamic Systems with Practical … , 2025 2025
Satellite Orbit Determination JR Raol, VPS Naidu Mathematical Modelling of Aerospace Dynamic Systems with Practical … , 2025 2025
Object Detection and Tracking from UAV with Thermal Camera JR Raol, VPS Naidu Mathematical Modelling of Aerospace Dynamic Systems with Practical … , 2025 2025
Terrain-Assisted Underwater Vehicle Navigation JR Raol, VPS Naidu Mathematical Modelling of Aerospace Dynamic Systems with Practical … , 2025 2025
Models Used in Target Tracking and Data Fusion JR Raol, VPS Naidu Mathematical Modelling of Aerospace Dynamic Systems with Practical … , 2025 2025
Flight Mechanics Models JR Raol, VPS Naidu Mathematical Modelling of Aerospace Dynamic Systems with Practical … , 2025 2025
Mathematical Modelling of Aerospace Dynamic Systems with Practical Applications JR Raol, VPS Naidu CRC Press , 2025 2025
Gearbox fault detection in industrial and wind turbine applications using a deterministic GMF parameter and SVM algorithm S Suresh, TN Reddy, VPS Naidu, G Chakaravarthi Manufacturing Technology Today 24 (3-4), 1-11 , 2025 2025
MULTI-SCALE RECURRENCE QUANTIFICATION ANALYSIS OF TIME SERIES FOR BEARING HEALTH MONITORING A SHARMA, VPS NAIDU SCIENCE AND CULTURE 91, 73-82 , 2025 2025
Optimizing bearing health condition monitoring: exploring correlation feature selection algorithm A Sharma, TH Priya, VPS Naidu Engineering Research Express 6 (2), 025511 , 2024 2024 Citations: 4
Fault Detection in Machine Bearings Using Deep Learning A Vaishnavi, A Sharma, VPS Naidu AeroCON 2024 , 2024 2024
Machine learning based bearing fault classification using higher order spectral analysis A Sharma, GK Patra, VPS Naidu Defence Science Journal 74 (4), 505-516 , 2024 2024 Citations: 7
Simulation and Fault Classification of Rolling Element Bearings for Precision Machinery Health Monitoring A Sharma, TH Priya, VS Priya, VPS Naidu ISAMPE National Conference on Composites, 117-136 , 2024 2024
Exploration of an unconventional validation tool to investigate aero engine transonic fan flutter signature AN Viswanatha Rao, TN Satish, VPS Naidu, S Jana International Journal of Turbo & Jet-Engines 40 (s1), s155-s168 , 2024 2024 Citations: 3
Machine learning augmented multi-sensor data fusion to detect aero engine fan rotor blade flutter ANV Rao, TN Satish, VPS Naidu, S Jana International Journal of Turbo & Jet-Engines 40 (s1), s485-s506 , 2024 2024 Citations: 8
Bispectral analysis and information fusion technique for bearing fault classification A Sharma, GK Patra, VPS Naidu Measurement Science and Technology 35 (1), 015124 , 2024 2024 Citations: 12
Passive Ranging with a Team of Aircraft using Angle Only Tracks S Ailneni, SK Kashyap, VPS Naidu, A Saraf, NK Sinha 2023 Ninth Indian Control Conference (ICC), 108-113 , 2023 2023 Citations: 1
Machine Learning Algorithms for Phonocardiogram Signal Classification C Nijalingappa, VPS Naidu 2023 4th International Conference on Communication, Computing and Industry 6 … , 2023 2023 Citations: 2
Modeling of Underwater Acoustic signal propagation of LFM and HFM pulse: An Active Sonar Communication systems VS Naidu, PR Kumar, KS Babu 2023 International Symposium on Ocean Technology (SYMPOL), 1-7 , 2023 2023 Citations: 3
MOST CITED SCHOLAR PUBLICATIONS
Pixel-level image fusion using wavelets and principal component analysis VPS Naidu, JR Raol Defence science journal 58 (3), 338-352 , 2008 2008 Citations: 633
Multi-sensor data fusion with MATLAB JR Raol CRC press , 2009 2009 Citations: 356
Survey on UAV navigation in GPS denied environments G Balamurugan, J Valarmathi, VPS Naidu 2016 International conference on signal processing, communication, power and … , 2016 2016 Citations: 293
Discrete cosine transform based image fusion techniques VPS Naidu Journal of Communication, Navigation and Signal Processing 1 (1), 35-45 , 2012 2012 Citations: 104
Hybrid DDCT-PCA based multi sensor image fusion VPS Naidu Journal of Optics 43 (1), 48-61 , 2014 2014 Citations: 73
Data fusion mathematics: theory and practice JR Raol, SS Selvi, SK Kashyap, A Sanketh CRC Press , 2025 2025 Citations: 70
A novel image fusion technique using DCT based Laplacian pyramid VPS Naidu, B Elias International Journal of Inventive Engineering and Sciences (IJIES) ISSN … , 2013 2013 Citations: 65
Stress detection from EEG using power ratio TH Priya, P Mahalakshmi, VPS Naidu, M Srinivas 2020 International conference on emerging trends in information technology … , 2020 2020 Citations: 58
Sense and avoid technology in unmanned aerial vehicles: A review BN Chand, P Mahalakshmi, VPS Naidu 2017 International Conference on Electrical, Electronics, Communication … , 2017 2017 Citations: 40
Multi-resolution image fusion by FFT VPS Naidu 2011 International Conference on Image Information Processing, 1-6 , 2011 2011 Citations: 38
Novel image fusion techniques using DCT VPS Naidu International Journal of computer science and business informatics 5 (1), 1-18 , 2013 2013 Citations: 35
Three model IMM-EKF for tracking targets executing evasive maneuvers VPS Naidu, G Gopalaratnam, N Shanthakumar 45th AIAA Aerospace Sciences Meeting and Exhibit, 1204 , 2007 2007 Citations: 35
Multi-modal medical image fusion using multi-resolution discrete sine transform VPS Naidu, M Divya, P Mahalakshmi Control and Data Fusion e-Journal 1 (2), 13-26 , 2017 2017 Citations: 26
Evaluation of data association and fusion algorithms for tracking in the presence of measurement loss VP Naidu, G Girija, J Raol AIAA Guidance, Navigation, and Control Conference and Exhibit, 5733 , 2003 2003 Citations: 26
Application of vision based techniques for UAV position estimation KC Saranya, VPS Naidu, V Singhal, BM Tanuja 2016 International Conference on Research Advances in Integrated Navigation … , 2016 2016 Citations: 23
Fusion of out of focus images using principal component analysis and spatial frequency VPS Naidu, JR Raol Journal of Aerospace Sciences and Technologies, 216-225 , 2008 2008 Citations: 23
Bearing health condition monitoring: time domain analysis L Pratyusha, S Priya, VPS Naidu International Journal of Advanced Research in Electrical, Electronics and … , 2014 2014 Citations: 21
Geo-fencing for unmanned aerial vehicle P Pratyusha, V Naidu International Journal of Computer Applications 975, 8887 , 2013 2013 Citations: 21
