I am Rakesh Kumar working as an assistant professor in school of EEE at SASTRA Deemed University from June 2009 till date (9 years). I have completed doctoral research and attained my PhD in the area of sensor fusion for mobile robots from SASTRA Deemed University as an in-service candidate. Completed my masters in instrumentation engineering from the prestigious Madras institute of technology (MIT), Chennai. I have consistently excelled in teaching and progressed the research throughout the career accumulating a rich academic experience and a number of research publications. With the instrumentation engineering (interdisciplinary department Address: Thanjavur, Tamil Nadu, India
Dispersion nature of water droplets over the insulator surface is used for hydrophobicity classif... more Dispersion nature of water droplets over the insulator surface is used for hydrophobicity classification. Stochastic nature of water dispersions makes naive Bayesian classifier a preferable choice, which has been investigated in this work. Twelve features describing the characteristics of water droplets are extracted from the binary image using BLOB (Binary Large Objects) analysis. Ambient light intensity is a significant factor that affects the binary image quality. As these insulators are installed in the outside environment, variations in ambient light intensity are inevitable. An adaptive threshold technique is proposed to compensate for ambient light variations. Six classes of various ambient light intensities have been considered in this study, and the proposed adaptive threshold technique can produce quality binary image consistently. Features extracted from the binary image are ordered according to their principal components using principal component analysis (PCA). Improvement in classification accuracy with the accumulation of ordered features is analyzed. Results illustrate the use of the first eight features provides a reliable classification accuracy of 97.6% for test image samples. In comparison with the other existing classifiers, the proposed classifier illustrates optimal performance in terms of classification accuracy and computational time.
Hydrophobicity of polymeric insulator plays a vital role in determining the insulation quality in... more Hydrophobicity of polymeric insulator plays a vital role in determining the insulation quality in outdoor overhead electrical transmission and distribution lines. Loss of hydrophobicity increases the leakage current and leads to flashover. Monitoring hydrophobicity becomes a fundamental requirement to ensure continuity of power line operations. Hydrophobicity of polymeric insulator is classified according to STRI (Swedish Transmission Research Institute) guidelines. This paper proposes an intelligent ANFIS (Adaptive Neuro-Fuzzy Inference System) based classifier to determine the hydrophobicity quality using the digital image of the insulator. Ten statistical features are extracted from the digital images. Two stages of feature reduction are employed to reduce the number of features. Pre-design stage uses PCA (Principal Component Analysis) and reduces the number of features to six from ten and the post-design stage analyzes the accumulation effect to reduce the number of features to four. Various ANFIS classifiers are trained using these reduced features extracted from the image. The performance of these ANFIS classifiers is evaluated in both field and laboratory specimens. Results indicate classification accuracy of 96.4% and 93.3% during the training and testing phase when triangular membership function with linear output function is employed in ANFIS. A GUI (Graphical User Interface) has also been designed to facilitate the use of the proposed system by field operators.
Industrial control system (ICS) encompasses the several types of the control systems which is pla... more Industrial control system (ICS) encompasses the several types of the control systems which is placed in the various applications like industrial production, distributed control systems, small control configuration system and so on. The ICS developing process the model predictive controller (MPC) is utilized because of the easy concepts and controller tuning package. At the time of ICS implementation process, it consists of computing power problem which leads to reduce the entire ICS power. To reduce the problem present in the MPC, it has been optimized by utilizing MPC and the quadratic problem is overcome by applying the several quadric methods such as, sequential quadratic programming, barrier function and iterative interior point quadratic optimization are used. From the optimized controller system, the pilot scale distillation control system is developed and the performance of the proposed system is developed using state space model which is analyzed in terms of the error metrics and mean cost metrics. Keywords Industrial control system · Model predictive controller · Sequential quadratic programming · Barrier function · Iterative interior point (IIP) · Quadratic optimization methods
Most senior citizens are often neglected and are helpless in times of medical emergencies, as the... more Most senior citizens are often neglected and are helpless in times of medical emergencies, as they are alone in their twilight years. To tackle this, we have come up with a prospective Remote Health Monitoring and Alert System (RHMAS). In elderly people heart attacks are associated with symptoms like, body temperature fluctuations, high BP, profuse sweating, improper cardiac rhythm etc. Our solution is to integrate robust sensors capable of sensing and monitoring these symptoms with a microcontroller to alert the next of kin and health services during emergencies. Since most devices for this purpose are wired, a wireless device wouldn't interfere with the movement of the user The proposed system consists of a Photo-Plethysmography (PPG) based pulse sensor, to detect arrhythmia, a temperature sensor to constantly monitor their body temperature and a sweat sensor to monitor the Galvanic Skin Response (GSR). A GSM module will send an alert to the next of kin if the monitored data deviates from the nominal body condition. If the monitored data reaches emergency levels, health services would also be alerted.
Robustness of the controller is vital in many process industries. The robust controller will not ... more Robustness of the controller is vital in many process industries. The robust controller will not only compensate for disturbance but also for the parametric variation in the process itself. This paper proposes the design of such a robust propositional-integral (PI) controller for a non-linear level control process, like hemi-spherical tank system, using volumetric observer. In a level control system, the volume has a linear relation to the differences in inflow and outflow, whereas the rate change in height is non-linearly related to the flow difference. The robustness of the proposed controller was enhanced by using volume error instead of level error. The volume error is derived by using a volumetric observer, which observes the tank volume and a volume estimator, which estimate the desired tank volume. This enables a linear controller like PI controller to be more robust over the entire span of tank height. The robustness of the proposed controller was compared with the conventional controller and its performance is validated by using the averaged performance indices like averaged-ISE, ITAE and IAE. Simulation results illustrates that the proposed controller has faster response and lesser oscillations.
1 Abstract—Sensor fusion based localization techniques often need accurate estimate of the fast a... more 1 Abstract—Sensor fusion based localization techniques often need accurate estimate of the fast and uncertain scene change in environment. To determine the scene change from two consecutive LIDAR scans, this paper proposes a novel technique called 'keep zero as zero' polar correlation. As it name implies any zero in the scan data is kept isolated from scene change estimation as it do not carry any information about scene change. Unlike existing techniques, the proposed methodology employs minimization of selective horizontal and vertically shifted sum of difference between the scans to estimate scene change in terms of rotation and translation. Minimization of the proposed correlation function across the specified search space can guarantee an accurate estimate of scene change without any ambiguity. The performance of the proposed method is tested experimentally on a mobile robot in two modes depending on the scene change. In the first mode, scene change is detected using dynamic LIDAR, whereas static LIDAR is used in the second mode. The proposed methodology is found to be more robust to environmental uncertainties with a reliable level of localization accuracy.
1 Abstract—Wheel slip compensation is vital for building accurate and reliable dead reckoning bas... more 1 Abstract—Wheel slip compensation is vital for building accurate and reliable dead reckoning based robot localization and mapping algorithms. This investigation presents stochastic slip compensation scheme for robot localization and mapping. Main idea of the slip compensation technique is to use wheel-slip data obtained from experiments to model the variations in slip velocity as Gaussian distributions. This leads to a family of models that are switched depending on the input command. To obtain the wheel-slip measurements, experiments are conducted on a wheeled mobile robot and the measurements thus obtained are used to build the Gaussian models. Then the localization and mapping algorithm is tested on an experimental terrain and a new metric called the map spread factor is used to evaluate the ability of the slip compensation technique. Our results clearly indicate that the proposed methodology improves the accuracy by 72.55% for rotation and 66.67% for translation motion as against an uncompensated mapping system. The proposed compensation technique eliminates the need for extro receptive sensors for slip compensation, complex feature extraction and association algorithms. As a result, we obtain a simple slip compensation scheme for localization and mapping.
Dispersion nature of water droplets over the insulator surface is used for hydrophobicity classif... more Dispersion nature of water droplets over the insulator surface is used for hydrophobicity classification. Stochastic nature of water dispersions makes naive Bayesian classifier a preferable choice, which has been investigated in this work. Twelve features describing the characteristics of water droplets are extracted from the binary image using BLOB (Binary Large Objects) analysis. Ambient light intensity is a significant factor that affects the binary image quality. As these insulators are installed in the outside environment, variations in ambient light intensity are inevitable. An adaptive threshold technique is proposed to compensate for ambient light variations. Six classes of various ambient light intensities have been considered in this study, and the proposed adaptive threshold technique can produce quality binary image consistently. Features extracted from the binary image are ordered according to their principal components using principal component analysis (PCA). Improvement in classification accuracy with the accumulation of ordered features is analyzed. Results illustrate the use of the first eight features provides a reliable classification accuracy of 97.6% for test image samples. In comparison with the other existing classifiers, the proposed classifier illustrates optimal performance in terms of classification accuracy and computational time.
Hydrophobicity of polymeric insulator plays a vital role in determining the insulation quality in... more Hydrophobicity of polymeric insulator plays a vital role in determining the insulation quality in outdoor overhead electrical transmission and distribution lines. Loss of hydrophobicity increases the leakage current and leads to flashover. Monitoring hydrophobicity becomes a fundamental requirement to ensure continuity of power line operations. Hydrophobicity of polymeric insulator is classified according to STRI (Swedish Transmission Research Institute) guidelines. This paper proposes an intelligent ANFIS (Adaptive Neuro-Fuzzy Inference System) based classifier to determine the hydrophobicity quality using the digital image of the insulator. Ten statistical features are extracted from the digital images. Two stages of feature reduction are employed to reduce the number of features. Pre-design stage uses PCA (Principal Component Analysis) and reduces the number of features to six from ten and the post-design stage analyzes the accumulation effect to reduce the number of features to four. Various ANFIS classifiers are trained using these reduced features extracted from the image. The performance of these ANFIS classifiers is evaluated in both field and laboratory specimens. Results indicate classification accuracy of 96.4% and 93.3% during the training and testing phase when triangular membership function with linear output function is employed in ANFIS. A GUI (Graphical User Interface) has also been designed to facilitate the use of the proposed system by field operators.
Industrial control system (ICS) encompasses the several types of the control systems which is pla... more Industrial control system (ICS) encompasses the several types of the control systems which is placed in the various applications like industrial production, distributed control systems, small control configuration system and so on. The ICS developing process the model predictive controller (MPC) is utilized because of the easy concepts and controller tuning package. At the time of ICS implementation process, it consists of computing power problem which leads to reduce the entire ICS power. To reduce the problem present in the MPC, it has been optimized by utilizing MPC and the quadratic problem is overcome by applying the several quadric methods such as, sequential quadratic programming, barrier function and iterative interior point quadratic optimization are used. From the optimized controller system, the pilot scale distillation control system is developed and the performance of the proposed system is developed using state space model which is analyzed in terms of the error metrics and mean cost metrics. Keywords Industrial control system · Model predictive controller · Sequential quadratic programming · Barrier function · Iterative interior point (IIP) · Quadratic optimization methods
Most senior citizens are often neglected and are helpless in times of medical emergencies, as the... more Most senior citizens are often neglected and are helpless in times of medical emergencies, as they are alone in their twilight years. To tackle this, we have come up with a prospective Remote Health Monitoring and Alert System (RHMAS). In elderly people heart attacks are associated with symptoms like, body temperature fluctuations, high BP, profuse sweating, improper cardiac rhythm etc. Our solution is to integrate robust sensors capable of sensing and monitoring these symptoms with a microcontroller to alert the next of kin and health services during emergencies. Since most devices for this purpose are wired, a wireless device wouldn't interfere with the movement of the user The proposed system consists of a Photo-Plethysmography (PPG) based pulse sensor, to detect arrhythmia, a temperature sensor to constantly monitor their body temperature and a sweat sensor to monitor the Galvanic Skin Response (GSR). A GSM module will send an alert to the next of kin if the monitored data deviates from the nominal body condition. If the monitored data reaches emergency levels, health services would also be alerted.
Robustness of the controller is vital in many process industries. The robust controller will not ... more Robustness of the controller is vital in many process industries. The robust controller will not only compensate for disturbance but also for the parametric variation in the process itself. This paper proposes the design of such a robust propositional-integral (PI) controller for a non-linear level control process, like hemi-spherical tank system, using volumetric observer. In a level control system, the volume has a linear relation to the differences in inflow and outflow, whereas the rate change in height is non-linearly related to the flow difference. The robustness of the proposed controller was enhanced by using volume error instead of level error. The volume error is derived by using a volumetric observer, which observes the tank volume and a volume estimator, which estimate the desired tank volume. This enables a linear controller like PI controller to be more robust over the entire span of tank height. The robustness of the proposed controller was compared with the conventional controller and its performance is validated by using the averaged performance indices like averaged-ISE, ITAE and IAE. Simulation results illustrates that the proposed controller has faster response and lesser oscillations.
1 Abstract—Sensor fusion based localization techniques often need accurate estimate of the fast a... more 1 Abstract—Sensor fusion based localization techniques often need accurate estimate of the fast and uncertain scene change in environment. To determine the scene change from two consecutive LIDAR scans, this paper proposes a novel technique called 'keep zero as zero' polar correlation. As it name implies any zero in the scan data is kept isolated from scene change estimation as it do not carry any information about scene change. Unlike existing techniques, the proposed methodology employs minimization of selective horizontal and vertically shifted sum of difference between the scans to estimate scene change in terms of rotation and translation. Minimization of the proposed correlation function across the specified search space can guarantee an accurate estimate of scene change without any ambiguity. The performance of the proposed method is tested experimentally on a mobile robot in two modes depending on the scene change. In the first mode, scene change is detected using dynamic LIDAR, whereas static LIDAR is used in the second mode. The proposed methodology is found to be more robust to environmental uncertainties with a reliable level of localization accuracy.
1 Abstract—Wheel slip compensation is vital for building accurate and reliable dead reckoning bas... more 1 Abstract—Wheel slip compensation is vital for building accurate and reliable dead reckoning based robot localization and mapping algorithms. This investigation presents stochastic slip compensation scheme for robot localization and mapping. Main idea of the slip compensation technique is to use wheel-slip data obtained from experiments to model the variations in slip velocity as Gaussian distributions. This leads to a family of models that are switched depending on the input command. To obtain the wheel-slip measurements, experiments are conducted on a wheeled mobile robot and the measurements thus obtained are used to build the Gaussian models. Then the localization and mapping algorithm is tested on an experimental terrain and a new metric called the map spread factor is used to evaluate the ability of the slip compensation technique. Our results clearly indicate that the proposed methodology improves the accuracy by 72.55% for rotation and 66.67% for translation motion as against an uncompensated mapping system. The proposed compensation technique eliminates the need for extro receptive sensors for slip compensation, complex feature extraction and association algorithms. As a result, we obtain a simple slip compensation scheme for localization and mapping.
Uploads
Papers by rakesh kumar