Integrated DBSCAN-Based Segmentation of Tractor Activity into Productive and Non-Productive States from GPS Data Devi prasad Maharana, Purushottam Gangsar, Nitin Dharmadhikari, Anand Kumar Pandey SAE Technical Papers, 2026 <div class="section abstract"><div class="htmlview paragraph">Accurate identification of Productive and Non-Productive States or tractor duty cycles—comprising working, idle, and transport states—is critical for performance analysis, fuel optimization, and emissions modeling in agriculture machinery and fleet monitoring. This study explores the application of integrated unsupervised machine learning (ML) techniques to classify duty cycles using GPS-derived parameters such as speed, location variance, and temporal patterns. Unlike supervised approaches, the proposed method does not rely on several labeled engine and vehicle parameters, making it scalable and adaptable across diverse operational contexts. Clustering algorithm DBSCAN (Density-Based Spatial Clustering of Applications with Noise) in integration with hybrid rule-based and a road feature is employed to segment GPS data into distinct behavioral states. Feature engineering focuses on extracting motion signatures and spatial-temporal features that correlate with operational modes. Validation against manually annotated datasets demonstrates high accuracy in distinguishing idle, working, and transport phases. Furthermore, the present study demonstrates that by accurately determining the operational status of the tractor, unnecessary idling can be prevented through an idle avoidance system. Additionally, after assessing transport and working conditions, a movement-based control system for tire pressure adjustment is proposed. Both strategies have the potential to reduce fuel consumption by approximately 5-7%; however, this lies outside the scope of the present work. The framework offers a robust, data-driven solution for duty cycle monitoring and can be integrated into telematics systems for predictive maintenance and operational efficiency of the tractors.</div></div>
Identification of Productive and Non-Productive Activities in Agricultural Machinery Using ECU and GPS Parameters through Machine Learning Devi prasad Maharana, Purushottam Gangsar, Varun gokhale, Anand Kumar Pandey SAE Technical Papers, 2026 <div class="section abstract"><div class="htmlview paragraph">Any agricultural operation (such as cultivation, rotavation, ploughing, and harrowing) includes both productive and non-productive activities (like transportation, stops, and idling) in the field. Non-productive work can mislead the actual load profile, fuel consumption, and emissions. In this project, a machine learning-based methodology has been developed to differentiate between effective operations and non-productive activities, utilizing data collected in the field from data loggers installed on the machinery. Measurements were conducted on various machines across the country in all major applications to minimize the influence of any individual sample deviation and to account for variability in customer operating practices. Few critical parameters such as Engine Speed, Exhaust Gas Temperature, Actual Engine Percentage Torque, GPS Speed etc.) were selected after screening and analyzing more than 100 CAN and GPS parameters. The critical parameters were subsequently integrated with road features and various machine learning algorithms (such as KNN, Decision Tree, and Support Vector Machine (SVM). The results demonstrate that the current methodology effectively differentiates between productive operations and non-productive activities (such as transportation and idling) in major agricultural operations, thereby aiding in design-related decision-making</div></div>
Machine Learning Based off-Road Vehicle Turn Identification Using Vehicle & GPS Parameters Purushottam Gangsar SAE Technical Papers, 2025 <div class="section abstract"><div class="htmlview paragraph">Identification of different types of turns during field operation of off-road vehicles is critical in the overall vehicle development as it is helpful in identifying &amp; optimizing machine performance, correct duty cycle, fuel economy, stability analysis, accurate path planning, customer usage pattern &amp; designing the critical components, etc. In this study, a machine learning (ML) based methodology has been developed to detect the off-road vehicle turns using vehicle &amp; GPS parameters. Three most common types of off-road vehicles turn conditions e.g., Straight line, Bulb turn, and Three-Point turn have been considered. Different vehicle parameters (like latitude &amp; longitude, compass bearing, yaw rate, vehicle speed, swash plate angle, engine speed, percent load at vehicle speed, raise lower front &amp; PTO channels) generated during field test have been used here. These vehicle parameters are further processed, analysed and used in ML learning model building. Four ML models e.g., SVM, K-NN, Gaussian Naïve Byes and Random Forest have been used here. Experimental results show that the present ML based methodology can identify most common vehicle turns considered in this study with a good accuracy.</div></div>
Impact of Hybrid Electric Vehicles on Energy Consumption and Emission Reduction for Agricultural Applications Lakshmi P. Prasad, Satyanarayana PS, Tejas Paygude, Purushottam Gangsar, Mangesh Thakre, Nagesh Choudhary, Ajinkya Gitapathi SAE Technical Papers, 2025 <div class="section abstract"><div class="htmlview paragraph">As the agricultural industry seeks to enhance sustainability and reduce operational costs, the introduction of mild hybrid technology in tractors presents a promising solution. This paper focuses on downsizing internal combustion (IC) engine, coupled with integration of electric motor, to reduce fuel consumption and meet stringent emission regulations while maintaining power requirement for agricultural applications in India. The hybridization aims to deliver instant power boosts during peak loads and capitalizes on energy recovery during part loads and braking. Furthermore, the idle avoidance feature minimizes fuel consumption during periods of inactivity thus improving fuel efficiency. The hybridization also aims to hybridize auxiliary systems for flexible power management, enabling operation of either engine, auxiliaries, or both as needed.</div><div class="htmlview paragraph">A newly developed hybrid supervisory control prototype efficiently manages electric power and mechanical power, enabling intelligent management of auxiliary power consumption. This approach eliminates belt-driven mechanical loads, allowing auxiliaries to operate independently and on-demand, thus optimizing performance and fuel efficiency. Virtual simulations of hybrid electric tractor were conducted to assess the impact of intelligent auxiliary management on vehicle performance and fuel consumption, as detailed in this paper. The findings indicate that adopting such technologies in agricultural machinery not only enhances operational efficiency but also aligns with global efforts towards sustainable farming practices. This paper advocates for continued research and development in hybrid technologies to further advance the agricultural sector's transition towards environmentally friendly solutions.</div></div>
Intelligent Diagnosis for Fuel Line Fault of Diesel Engine Based on Vibration Signatures Parag Chaudhari, Purushottam Gangsar, Nitin Dharmadhikari, Sachin Pawar, Devendra Mandke SAE Technical Papers, 2024 <div class="section abstract"><div class="htmlview paragraph">Early fault detection is vital in maintaining system stability and to decrease the cost associated with maintenance. This paper presents an approach to identify the fuel line failure for a diesel engine based on vibration signals and machine learning. Vibration measurements are performed on the fuel line of the engine for both normal and faulty conditions for engine ramp up condition. After acquiring the time domain vibration signals, various features were extracted and have been analyzed in time and time-frequency domains. Based on the most effective feature, a machine learning model (i.e., support vector machine (SVM)) for fault diagnosis is developed. Results showed that the proposed SVM based model can detect the fuel line fault correctly. This study can be useful for early detection of this critical fault in diesel engine and take useful decision before any catastrophic failure happens because of this fault.</div></div>
A review on deep learning based condition monitoring and fault diagnosis of rotating machinery Purushottam Gangsar, Aditya Raj Bajpei, Rajkumar Porwal Noise and Vibration Worldwide, 2022 Rotating machine faults are unavoidable; thus, early diagnosis is essential to avoid further damage to the machine or other machine attached to it. Various signal analysis based conventional techniques have been developed and used in the industries to identify various defects in the rotating machines. In last two decades, researchers have shifted their focus to automated or intelligent fault diagnosis based on Artificial Intelligence (AI) techniques due to a variety of issues in conventional fault analysis techniques, such as a dependence on machine operating circumstances, human interference, and expert abilities. In AI based techniques, various machine learning (ML) and deep learning (DL) techniques have been successfully applied for fault diagnosis of various rotating machines. From last half decade DL have been gaining popularity due to its attractive characteristic of automated feature learning and solving big data, unbalanced data, big computational burden and over-fitting problems of conventional ML techniques. Advances in DL methodologies have prompted interest in DL based intelligent fault diagnosis in the industry in the last five to 6 years. This review paper summarizes recent research and developments on DL based fault diagnosis in the last five to 6 years for various critical rotating machineries in industry such as electric motors, rotor-bearing systems, gear and gearbox, wind turbines, pumps, and compressors.
Integrated DBSCAN-Based Segmentation of Tractor Activity into Productive and Non-Productive States from GPS Data Maharana, Devi prasad, Gangsar Purushottam, Dharmadhikari N WCX SAE World Congress Experience 370157 , 2026 2026
Predictive Maintenance Techniques for Off-Highway Vehicles: Current State and Future Perspectives P Gangsar, P Chaudhari Lecture Notes in Mechanical Engineering. Springer, Cham, 153-165 , 2026 2026
Identification of Productive and Non-Productive Activities in Agricultural Machinery Using ECU and GPS Parameters through Machine Learning D Maharana, P Gangsar, V Gokhale, AK Pandey Symposium on International Automotive Technology (2026) 369687 , 2026 2026
Machine Learning Based Implement Identification for Off-Highway Vehicles Using Engine, Vehicle, GPS & Beacon Parameters D Maharana, P Gangsar, M Dutta, A Daroga, R Joseph, A Pandey 18th WCEAM Proceedings: Automation, Digital Transformation, Industry 4.0 … , 2026 2026
Machine Learning Based off-Road Vehicle Turn Identification Using Vehicle & GPS Parameters AF R Rai, P Gangsar, R Joseph, M Malik, M Dutta Off-Highway Technical Conference 2025 , 2025 2025
Impact of Hybrid Electric Vehicles on Energy Consumption and Emission Reduction for Agricultural Applications LP Prasad, S PS, T Paygude, P Gangsar, M Thakre, N Choudhary, ... WCX SAE World Congress Experience 288445 , 2025 2025 Citations: 2
Intelligent diagnosis for fuel line fault of diesel engine based on vibration signatures P Chaudhari, P Gangsar, N Dharmadhikari, S Pawar, D Mandke Symposium on International Automotive Technology , 2024 2024 Citations: 4
Artificial intelligence application in fault diagnostics of rotating industrial machines: A state-of-the-art review V Singh, P Gangsar, R Porwal, A Atulkar Journal of Intelligent Manufacturing 34 (3), 931-960 , 2023 2023 Citations: 182
A review on deep learning based condition monitoring and fault diagnosis of rotating machinery P Gangsar, AR Bajpei, R Porwal Noise & vibration worldwide 53 (11), 550-578 , 2022 2022 Citations: 50
Diagnostics of combined mechanical and electrical faults of an electromechanical system for steady and ramp-up speeds P Gangsar, M Chouksey, A Parey, Z Ali Journal of Vibration Engineering & Technologies 10 (4), 1431-1450 , 2022 2022 Citations: 15
Machine learning-based fault prediction of electromechanical system with current and vibration signals P Gangsar, V Singh, M Chouksey, A Parey International Conference on Vibration Engineering and Technology of … , 2021 2021 Citations: 5
Artificial neural network–based fault diagnosis for induction motors under similar, interpolated and extrapolated operating conditions A Chouhan, P Gangsar, R Porwal, CK Mechefske Noise & Vibration Worldwide 52 (10), 323-333 , 2021 2021 Citations: 22
An intelligent and robust fault diagnostics for an electromechanical system using vibration and current signals P Gangsar, Z Ali, M Chouksey, A Parey Recent Advances in Manufacturing, Automation, Design and Energy Technologies … , 2021 2021 Citations: 5
Deep learning based optimum fault diagnosis of electrical and mechanical faults in induction motor V Singh, P Gangsar, A Atulkar, R Porwal IOP Conference Series: Materials Science and Engineering 1136 (1), 012059 , 2021 2021 Citations: 3
Unbalance detection in rotating machinery based on support vector machine using time and frequency domain vibration features P Gangsar, RK Pandey, M Chouksey Noise & Vibration Worldwide 52 (4-5), 75-85 , 2021 2021 Citations: 27
An Intelligent and Robust Fault Diagnostics for an Electromechanical System using Vibration and Current Signals AP Purushottam Gangsar, Zeeshan Ali, Manoj Chouksey International Conference on Future Technology (ICOFT)-2020, NIT, Puducherry , 2020 2020
Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review P Gangsar, R Tiwari Mechanical systems and signal processing 144, 106908 , 2020 2020 Citations: 761
Artificial neural network based fault diagnostics for three phase induction motors under similar operating conditions A Chouhan, P Gangsar, R Porwal, CK Mechefske Vibroengineering Procedia 30, 55-60 , 2020 2020 Citations: 25
Artificial Neural Network Based Fault Diagnostics for Induction Motors in Different Machine Tool Applications MC Abhisar Chouhan, Purushottam Gangsar, Rajkumar Porwal International Conference on Precision, Meso, Micro and Nano Engineering … , 2019 2019
Online diagnostics of mechanical and electrical faults in induction motor using multiclass support vector machine algorithms based on frequency domain vibration and current signals P Gangsar, R Tiwari ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B … , 2019 2019 Citations: 24
MOST CITED SCHOLAR PUBLICATIONS
Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review P Gangsar, R Tiwari Mechanical systems and signal processing 144, 106908 , 2020 2020 Citations: 761
Artificial intelligence application in fault diagnostics of rotating industrial machines: A state-of-the-art review V Singh, P Gangsar, R Porwal, A Atulkar Journal of Intelligent Manufacturing 34 (3), 931-960 , 2023 2023 Citations: 182
Comparative investigation of vibration and current monitoring for prediction of mechanical and electrical faults in induction motor based on multiclass-support vector machine … P Gangsar, R Tiwari Mechanical Systems and Signal Processing 94, 464-481 , 2017 2017 Citations: 169
A support vector machine based fault diagnostics of Induction motors for practical situation of multi-sensor limited data case P Gangsar, R Tiwari Measurement 135, 694-711 , 2019 2019 Citations: 85
Multifault diagnosis of induction motor at intermediate operating conditions using wavelet packet transform and support vector machine P Gangsar, R Tiwari Journal of Dynamic Systems, Measurement, and Control 140 (8), 081014 , 2018 2018 Citations: 59
A review on deep learning based condition monitoring and fault diagnosis of rotating machinery P Gangsar, AR Bajpei, R Porwal Noise & vibration worldwide 53 (11), 550-578 , 2022 2022 Citations: 50
Diagnostics of mechanical and electrical faults in induction motors using wavelet-based features of vibration and current through support vector machine algorithms for various … P Gangsar, R Tiwari Journal of the Brazilian Society of Mechanical Sciences and Engineering 41 … , 2019 2019 Citations: 48
Multiclass fault taxonomy in rolling bearings at interpolated and extrapolated speeds based on time domain vibration data by SVM algorithms P Gangsar, R Tiwari Journal of Failure Analysis and Prevention 14 (6), 826-837 , 2014 2014 Citations: 29
Unbalance detection in rotating machinery based on support vector machine using time and frequency domain vibration features P Gangsar, RK Pandey, M Chouksey Noise & Vibration Worldwide 52 (4-5), 75-85 , 2021 2021 Citations: 27
Taxonomy of induction-motor mechanical-fault based on time-domain vibration signals by multiclass SVM classifiers P Gangsar, R Tiwari Intelligent Industrial Systems 2 (3), 269-281 , 2016 2016 Citations: 26
Artificial neural network based fault diagnostics for three phase induction motors under similar operating conditions A Chouhan, P Gangsar, R Porwal, CK Mechefske Vibroengineering Procedia 30, 55-60 , 2020 2020 Citations: 25
Online diagnostics of mechanical and electrical faults in induction motor using multiclass support vector machine algorithms based on frequency domain vibration and current signals P Gangsar, R Tiwari ASCE-ASME Journal of Risk and Uncertainty in Engineering Systems, Part B … , 2019 2019 Citations: 24
Artificial neural network–based fault diagnosis for induction motors under similar, interpolated and extrapolated operating conditions A Chouhan, P Gangsar, R Porwal, CK Mechefske Noise & Vibration Worldwide 52 (10), 323-333 , 2021 2021 Citations: 22
Diagnostics of combined mechanical and electrical faults of an electromechanical system for steady and ramp-up speeds P Gangsar, M Chouksey, A Parey, Z Ali Journal of Vibration Engineering & Technologies 10 (4), 1431-1450 , 2022 2022 Citations: 15
Effect of noise on support vector machine based fault diagnosis of IM using vibration and current signatures P Gangsar, R Tiwari MATEC Web of Conferences 211, 03009 , 2018 2018 Citations: 6
Machine learning-based fault prediction of electromechanical system with current and vibration signals P Gangsar, V Singh, M Chouksey, A Parey International Conference on Vibration Engineering and Technology of … , 2021 2021 Citations: 5
An intelligent and robust fault diagnostics for an electromechanical system using vibration and current signals P Gangsar, Z Ali, M Chouksey, A Parey Recent Advances in Manufacturing, Automation, Design and Energy Technologies … , 2021 2021 Citations: 5
Performance analysis of support vector machine and wavelet packet transform based fault diagnostics of induction motor at various operating conditions P Gangsar, R Tiwari International conference on rotor dynamics, 32-42 , 2018 2018 Citations: 5
Analysis of Time, frequency and wavelet based features of vibration and current signals for fault diagnosis of induction motors using SVM P Gangsar, R Tiwari Gas Turbine India Conference 58516, V002T05A027 , 2017 2017 Citations: 5
Intelligent diagnosis for fuel line fault of diesel engine based on vibration signatures P Chaudhari, P Gangsar, N Dharmadhikari, S Pawar, D Mandke Symposium on International Automotive Technology , 2024 2024 Citations: 4
