Ashok Kumar Kumawat
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ashok Kumar Kumawat has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
Raja Rout
Department of Mechanical Engineering, Thapar Institute of Engineering and Technology, Patiala, Punjab, India
5 shared publicationsRenu Kumawat
Manipal University Jaipur,Department of Computer and Communication Engg,Jaipur,India
3 shared publicationsManish Rawat
Manipal University Jaipur,Department of Mechatronics Engineering,Jaipur,India
2 shared publications- Manish Rawat
Department of Mechatronics Engineering, Manipal University Jaipur, Jaipur 303007, Rajasthan, India
2 shared publications Sandeep Rana
Deptt. of Electronics & Communication Engg., Graphic Era Hill University, Dehradun, India
2 shared publications- Devdutt Patel
Department of Mechatronics Engineering, Manipal University Jaipur, Jaipur, India
1 shared publication
Latest Publications
- Open Access
- 19 June 2026
- Published by Springer Nature in Discover Internet of Things
- Vol. 6 (1)
AI-powered fault diagnosis and estimation of remaining useful life using IoT framework
Unexpected malfunctions in industrial rotating machinery frequently result in decreased output and higher operating expenses. To achieve real-time anomaly identification and remaining useful life estimation, this work presents a novel predictive maintenance architecture that combines IoT-based multi-sensor, edge inference, and an interpretable AI model. For thorough data collection, the pro posed system uses an ESP32 board interfaced with the various sensors. The edge computing node is a Raspberry Pi 5, which runs the proposed hybrid Random Forest algorithm for remaining useful life prediction and fault categorisation. With a mean absolute error of 1.58 h, an inference latency of 38 ms per cycle, and an accuracy of 99.0%, F1-Score of 99.3%, and Remaining Useful Life (RUL) prediction with R2 = 0.9995, trained and evaluated on 1200 samples collected from a single induction motor testbed. Email notifications, IoT-based alerting via Blynk, and real-time visualization via a Tkinter dashboard interface prompt a response to crucial circumstances. Decision trans parency was achieved through the use of SHapley Additive exPlanations (SHAP) attribution analysis. The results suggest suitability for Industry 4.0 deployment in small enterprises.
- 19 June 2026
- Published by Springer Nature in Discover Internet of Things
- Vol. 6 (1)
Open AccessAI-powered fault diagnosis and estimation of remaining useful life using IoT framework
Unexpected malfunctions in industrial rotating machinery frequently result in decreased output and higher operating expenses. To achieve real-time anomaly identification and remaining useful life estimation, this work presents a novel predictive maintenance architecture that combines IoT-based multi-sensor, edge inference, and an interpretable AI model. For thorough data collection, the pro posed system uses an ESP32 board interfaced with the various sensors. The edge computing node is a Raspberry Pi 5, which runs the proposed hybrid Random Forest algorithm for remaining useful life prediction and fault categorisation. With a mean absolute error of 1.58 h, an inference latency of 38 ms per cycle, and an accuracy of 99.0%, F1-Score of 99.3%, and Remaining Useful Life (RUL) prediction with R2 = 0.9995, trained and evaluated on 1200 samples collected from a single induction motor testbed. Email notifications, IoT-based alerting via Blynk, and real-time visualization via a Tkinter dashboard interface prompt a response to crucial circumstances. Decision trans parency was achieved through the use of SHapley Additive exPlanations (SHAP) attribution analysis. The results suggest suitability for Industry 4.0 deployment in small enterprises.
- Open Access
- 10 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 89160-89171
Discrete-Time Value Iteration-Based Position Tracking Control for Electro-Hydraulic Systems With Unmeasured States
novel infinite-horizon linear quadratic tracking (LQT) problem for the discrete-time system with unmeasured states is presented in this paper. The reference trajectory dynamics and the electro-hydraulic system are combined to create an augmented system. A new Bellman equation is derived to evaluate the value function associated with the devised policy. The LQT problem of the augmented system dynamics is solved by adaptive dynamic programming. Herein, a discrete-time value iteration (VI) algorithm is proposed that generates a control signal for the proportional directional control (PDC) valve, satisfying the actuation limits of [-10V, 10V]. To confirm the efficacy of the proposed control approach, three experiments utilizing square wave and multi-step reference trajectories are shown. The experimental findings verify that tracking error converges to an arbitrarily tiny neighborhood and that the electro-hydraulic actuator system’s tracking performance is enhanced.
- 10 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 89160-89171
Open AccessDiscrete-Time Value Iteration-Based Position Tracking Control for Electro-Hydraulic Systems With Unmeasured States
novel infinite-horizon linear quadratic tracking (LQT) problem for the discrete-time system with unmeasured states is presented in this paper. The reference trajectory dynamics and the electro-hydraulic system are combined to create an augmented system. A new Bellman equation is derived to evaluate the value function associated with the devised policy. The LQT problem of the augmented system dynamics is solved by adaptive dynamic programming. Herein, a discrete-time value iteration (VI) algorithm is proposed that generates a control signal for the proportional directional control (PDC) valve, satisfying the actuation limits of [-10V, 10V]. To confirm the efficacy of the proposed control approach, three experiments utilizing square wave and multi-step reference trajectories are shown. The experimental findings verify that tracking error converges to an arbitrarily tiny neighborhood and that the electro-hydraulic actuator system’s tracking performance is enhanced.
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
Discrete-Time and Nonlinear System Control Using ‘fmincon’ Optimization: Simulation
A simulation-based approach for managing discrete-time and nonlinear systems using MATLAB's ‘fmincon’ optimization tool is presented in this study. Constrained nonlinear programming is used to manage input constraints, safety requirements, and complicated system dynamics, offering a flexible substitute for conventional control techniques. In order to account for practical constraints such actuator constraints, disturbance rejection, and system uncertainties, the suggested approach formulates the control problem as an optimum with constraints. A multi-signal desired trajectory second-order nonlinear systems are used to illustrate the concept. The method's capacity to enforce safety restrictions, maintain stability, and achieve the requisite tracking performance is validated by simulation results. The method can be applied to a variety of adaptive control applications since it is flexible enough to incorporate unique cost functions, disturbances, and limitations.
- 19 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-3
Discrete-Time and Nonlinear System Control Using ‘fmincon’ Optimization: Simulation
A simulation-based approach for managing discrete-time and nonlinear systems using MATLAB's ‘fmincon’ optimization tool is presented in this study. Constrained nonlinear programming is used to manage input constraints, safety requirements, and complicated system dynamics, offering a flexible substitute for conventional control techniques. In order to account for practical constraints such actuator constraints, disturbance rejection, and system uncertainties, the suggested approach formulates the control problem as an optimum with constraints. A multi-signal desired trajectory second-order nonlinear systems are used to illustrate the concept. The method's capacity to enforce safety restrictions, maintain stability, and achieve the requisite tracking performance is validated by simulation results. The method can be applied to a variety of adaptive control applications since it is flexible enough to incorporate unique cost functions, disturbances, and limitations.
- Open Access
- 10 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 159597-159609
Reinforcement Learning-Based Position Tracking Control for Proportional Directional Control Valve-Based Electro-Hydraulic System
This paper presents a reinforcement learning-based discrete-time control strategy for nonlinear electro-hydraulic actuator systems equipped with a proportional directional control valve. The proposed method incorporates a Lyapunov-based stability framework, ensuring bounded tracking errors and neural network weights despite modeling uncertainties and external disturbances. A discrete-time dynamic model of the electro-hydraulic actuator system is derived, and unmeasured system states are estimated using an extended Kalman filter. The controller is validated through both MATLAB simulations and real-time hardware experiments involving sensors, a hydraulic cylinder, a proportional directional control valve, and a data acquisition system. The obtained results demonstrate accurate trajectory tracking in the presence of modeling uncertainties, disturbances, and real-time adaptability of neural network weights, highlighting the effectiveness of the proposed controller for industrial electro-hydraulic systems.
- 10 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 159597-159609
Open AccessReinforcement Learning-Based Position Tracking Control for Proportional Directional Control Valve-Based Electro-Hydraulic System
This paper presents a reinforcement learning-based discrete-time control strategy for nonlinear electro-hydraulic actuator systems equipped with a proportional directional control valve. The proposed method incorporates a Lyapunov-based stability framework, ensuring bounded tracking errors and neural network weights despite modeling uncertainties and external disturbances. A discrete-time dynamic model of the electro-hydraulic actuator system is derived, and unmeasured system states are estimated using an extended Kalman filter. The controller is validated through both MATLAB simulations and real-time hardware experiments involving sensors, a hydraulic cylinder, a proportional directional control valve, and a data acquisition system. The obtained results demonstrate accurate trajectory tracking in the presence of modeling uncertainties, disturbances, and real-time adaptability of neural network weights, highlighting the effectiveness of the proposed controller for industrial electro-hydraulic systems.
- 8 July 2023
- Published by Springer Nature
- p. 119-126
Interfacing of Industrial Inductive Proximity Sensor with NI DAQ and Speed Measurement
- 8 July 2023
- Published by Springer Nature
- p. 119-126
Interfacing of Industrial Inductive Proximity Sensor with NI DAQ and Speed Measurement
- 18 May 2023
- Published by ASME International in Journal of Dynamic Systems, Measurement, and Control
- Vol. 145 (7) , 1-12
Discrete-Time Constrained Controller for Proportional Directional Control Valve-Based Electrohydraulic System With Parametric Uncertainty and Disturbances
This paper develops a discrete constrained controller for electrohydraulic system (EHS) controlled by proportional directional control (PDC) valve while taking parametric uncertainties into account. The proposed controller solves the discrete barrier Lyapunov function via convex optimization while taking into consideration the system constraints such as state and actuator constraints. The proposed control law successfully tracks the reference trajectory while satisfying the state and actuator constraints. It is proven that the tracking error always converges to an arbitrary small neighborhood which is validated using Lyapunov stability analysis. The effectiveness of the proposed discrete barrier Lyapunov function based constrained controller was verified in a simulation environment and also through experimentation. From the simulation and experimental results, it is clear that the proposed controller drives the load to accurately track the reference trajectory in the presence of uncertainty and unknown disturbances.
- 18 May 2023
- Published by ASME International in Journal of Dynamic Systems, Measurement, and Control
- Vol. 145 (7) , 1-12
Discrete-Time Constrained Controller for Proportional Directional Control Valve-Based Electrohydraulic System With Parametric Uncertainty and Disturbances
This paper develops a discrete constrained controller for electrohydraulic system (EHS) controlled by proportional directional control (PDC) valve while taking parametric uncertainties into account. The proposed controller solves the discrete barrier Lyapunov function via convex optimization while taking into consideration the system constraints such as state and actuator constraints. The proposed control law successfully tracks the reference trajectory while satisfying the state and actuator constraints. It is proven that the tracking error always converges to an arbitrary small neighborhood which is validated using Lyapunov stability analysis. The effectiveness of the proposed discrete barrier Lyapunov function based constrained controller was verified in a simulation environment and also through experimentation. From the simulation and experimental results, it is clear that the proposed controller drives the load to accurately track the reference trajectory in the presence of uncertainty and unknown disturbances.
- 17 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 253-258
IoT Enabled Low-Cost Real-Time Remote Air Quality Monitoring and Forecasting System
Gas poisoning and other health problems can be greatly avoided using forecasting and prediction of air quality. These metrics were previously observed using huge, pricey, and fixed air quality monitoring stations. Due to their high cost, these stations cannot be installed in many locations, which results in a dearth of monitoring stations in many locations. These problems can be solved with the use of compact, affordable, and portable air quality monitoring systems. Additionally, it is possible to automate and monitor air quality using inexpensive air quality monitoring equipment. These systems can be used in any home and office, car and etc. In this paper, we built and put into action a portable, affordable, and tiny hardware platform for monitoring air quality that can be accessed remotely through a web application. Additionally, we have used a dataset and certain forecasting algorithms to predict each parameter over a given time frame.
- 17 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 253-258
IoT Enabled Low-Cost Real-Time Remote Air Quality Monitoring and Forecasting System
Gas poisoning and other health problems can be greatly avoided using forecasting and prediction of air quality. These metrics were previously observed using huge, pricey, and fixed air quality monitoring stations. Due to their high cost, these stations cannot be installed in many locations, which results in a dearth of monitoring stations in many locations. These problems can be solved with the use of compact, affordable, and portable air quality monitoring systems. Additionally, it is possible to automate and monitor air quality using inexpensive air quality monitoring equipment. These systems can be used in any home and office, car and etc. In this paper, we built and put into action a portable, affordable, and tiny hardware platform for monitoring air quality that can be accessed remotely through a web application. Additionally, we have used a dataset and certain forecasting algorithms to predict each parameter over a given time frame.
- 24 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Continuous Time LQR Based Position Control for an Electro-Hydraulic Actuation System
Electro-hydraulic actuators are used a lot in the industry because they have several benefits. In this study, we concentrated on managing the load position with a proportional directional control valve and a hydraulic cylinder. First, the linear quadratic regulator(LQR) control approach is discussed for a generalized linear system. Second, a linear state space mathematical model of the electro-hydraulic actuator system was built, and the control process was applied to the proposed settings. Finally, MATLAB simulation results show that the proposed solution is better. These results are based on the LQR controller implementation and load position error analysis.
- 24 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Continuous Time LQR Based Position Control for an Electro-Hydraulic Actuation System
Electro-hydraulic actuators are used a lot in the industry because they have several benefits. In this study, we concentrated on managing the load position with a proportional directional control valve and a hydraulic cylinder. First, the linear quadratic regulator(LQR) control approach is discussed for a generalized linear system. Second, a linear state space mathematical model of the electro-hydraulic actuator system was built, and the control process was applied to the proposed settings. Finally, MATLAB simulation results show that the proposed solution is better. These results are based on the LQR controller implementation and load position error analysis.
- 16 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Road Traffic Density Surveillance System using IR Sensor, Image Processing and Raspberry Pi: A Comparative Analysis
In our present time, the use of vehicles has become widespread which has given rise to the problem of traffic congestion a common sight in day-to-day life. And with the increased sales of vehicles in recent years the problem is almost considered as a known factor that gives rise to noise and air pollution in coming years. This imminent problem gives validation to the use of de-congestion methods, some of which are more efficient traffic signs and constant traffic monitoring to prevent a standstill event that is known to devolve into traffic jams. Traffic monitoring can be done with the help of Frame comparison as well as Edge Detection in tandem with IR sensors that give a rough estimate of how far the traffic congestion goes. In this paper we have focused on the merging of three different approaches viz. the IR Sensor in passive mode, Real-time Background Subtraction in a semi-active mode, and Real-time Canny Image Processing in an active mode in an efficient manner in a prototype and analyzed their performance using Raspberry pi for selection of a preferred system. The results obtained reduce traffic congestion using the dynamic times allocated to the higher traffic lanes until an average time, which is assumed with lower traffic lanes. This method is inexpensive and easily implemented with Raspberry Pi's help to run it arguably efficiently on medium-traffic areas.
- 16 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Road Traffic Density Surveillance System using IR Sensor, Image Processing and Raspberry Pi: A Comparative Analysis
In our present time, the use of vehicles has become widespread which has given rise to the problem of traffic congestion a common sight in day-to-day life. And with the increased sales of vehicles in recent years the problem is almost considered as a known factor that gives rise to noise and air pollution in coming years. This imminent problem gives validation to the use of de-congestion methods, some of which are more efficient traffic signs and constant traffic monitoring to prevent a standstill event that is known to devolve into traffic jams. Traffic monitoring can be done with the help of Frame comparison as well as Edge Detection in tandem with IR sensors that give a rough estimate of how far the traffic congestion goes. In this paper we have focused on the merging of three different approaches viz. the IR Sensor in passive mode, Real-time Background Subtraction in a semi-active mode, and Real-time Canny Image Processing in an active mode in an efficient manner in a prototype and analyzed their performance using Raspberry pi for selection of a preferred system. The results obtained reduce traffic congestion using the dynamic times allocated to the higher traffic lanes until an average time, which is assumed with lower traffic lanes. This method is inexpensive and easily implemented with Raspberry Pi's help to run it arguably efficiently on medium-traffic areas.
- 5 September 2021
- Published by Springer Nature
- p. 240-249
Comparing Classification Algorithms on Predicting Loans
- 5 September 2021
- Published by Springer Nature
- p. 240-249
Comparing Classification Algorithms on Predicting Loans