Papers by Dr.Joydeb Roychaudhury
2009 Ninth International Conference on Hybrid Intelligent Systems, 2009
The problem of failure diagnosis has received a considerable attention in the domain of reliabili... more The problem of failure diagnosis has received a considerable attention in the domain of reliability engineering, process control and computer science. The increasing stringent requirement of quality of a product needs considerable attention in the performance and reliability of the manufacturing system. In general, the feedback control algorithm for a process designed to handle small perturbation that may arise under normal operating condition but can not accommodate any abnormal behavior due to fault. Thus the automated maintenance or early detection of worn equipment is becoming a critical issue. This justifies the need of development of effective methodology in the area of fault aware controller. In this paper we proposed a novel Algorithm and it have been tested and implemented for making Highly reliable system like Automated Cricket Ball Stitching Machine. Considering this need the present paper proposes the work on the development methodology of fault aware controller using embedded processor with reference to an early needle failure detection of a leather stitching machine.
Computer Standards & Interfaces, 2009
Battery powered embedded system can be considered as a power aware system for a safety critical a... more Battery powered embedded system can be considered as a power aware system for a safety critical application. There is a need of saving the battery power for such power aware system so that it can be used more efficiently, particularly in safety critical applications. Present paper describes power optimization procedure using real time scheduling technique having a specific dead line guided by the model based optimum current discharge profile of a battery. In any power aware system 'energy optimization' is one of the major issues for a faithful operation.
Probabilistic duration of power estimation for Nickel-metal-hydride (NiMH) battery under constant load using Kalman filter on chip
For a battery powered safety critical system the safe duration of power for executing a specific ... more For a battery powered safety critical system the safe duration of power for executing a specific task is extremely important. It is necessary to avoid unacceptable consequences due to unwanted battery power failure. An early stage estimation of this duration reduces the overall risk through optimization of current consumption by switching off noncritical load ahead of delivery of power to
A machine learning approach to predict future power demand in real-time for a battery operated car
2014 International Conference on the IMpact of E-Technology on US (IMPETUS), 2014
For any battery-employed system, it is essential for the battery management system to correctly p... more For any battery-employed system, it is essential for the battery management system to correctly predict the present operational condition of the battery. The fail safe operation of a safety critical system like battery operated car or any other lifesaving systems are heavily depend upon earlier prediction of battery life. SOC or State-of-Charge estimation is one of the well-known method to predict the runtime of a battery. Various approaches are adapted by automotive society to correctly predict the runtime or the SOC of a battery like Kalman filter, UKF and many others. This paper proposes a new approach, the method of regression to predict the future power demand of a car while running on the road. The aim is to identify that, the battery will support the run of the car in next 10 seconds or not. The runtime prediction of a battery, not only depends upon the starting SOC but also depends upon other factors like battery health and road profile imposed. To overcome this type of difficulties the self-corrective regression model is proposed and implemented. Experiments performed on different road profiles, validate demanded power by the car in up-coming 10 seconds of its run. The major problem of SoC estimation is to determine initial SoC of a battery. Extensive experiments needed to calculate the initial SoC and which may also vary with the life of the battery. The novelty of this work shows, the method to predict the future power demand by updating its model parameters and without any initial SoC calculation. Model parameters are updated by the introducing new current and voltage sample in the model.
2009 World Congress on Nature & Biologically Inspired Computing (NaBIC), 2009
The main objective of the current paper is to design and validate a sub sate observer which can c... more The main objective of the current paper is to design and validate a sub sate observer which can communicate the health status of the stitching needle to the stitch controller in right time without any false alert signal using Microcontroller and CPLD interfacing. This has been achieved through a design methodology of a fault aware controller which can interact with a stitch controller [8] for automatic decorative cricket ball stitching machine. The reason behind this is it cannot recognize a 'degraded state'-in proper time before turned in to a bad state. Thus it necessary to convert it to a grey scale with proper truth value. In order to impose this aspect -health is estimated by its 'duration of work' -which measured and associated with a degraded state in terms of a specific time duration. The novelty of the paper is that to overcome the Microcontroller based [8] high speed state estimation and observer design by this CPLD.
A machine learning approach to predict future power demand in real-time for a battery operated car
2014 International Conference on the IMpact of E-Technology on US (IMPETUS), 2014
For any battery-employed system, it is essential for the battery management system to correctly p... more For any battery-employed system, it is essential for the battery management system to correctly predict the present operational condition of the battery. The fail safe operation of a safety critical system like battery operated car or any other lifesaving systems are heavily depend upon earlier prediction of battery life. SOC or State-of-Charge estimation is one of the well-known method to predict the runtime of a battery. Various approaches are adapted by automotive society to correctly predict the runtime or the SOC of a battery like Kalman filter, UKF and many others. This paper proposes a new approach, the method of regression to predict the future power demand of a car while running on the road. The aim is to identify that, the battery will support the run of the car in next 10 seconds or not. The runtime prediction of a battery, not only depends upon the starting SOC but also depends upon other factors like battery health and road profile imposed. To overcome this type of difficulties the self-corrective regression model is proposed and implemented. Experiments performed on different road profiles, validate demanded power by the car in up-coming 10 seconds of its run. The major problem of SoC estimation is to determine initial SoC of a battery. Extensive experiments needed to calculate the initial SoC and which may also vary with the life of the battery. The novelty of this work shows, the method to predict the future power demand by updating its model parameters and without any initial SoC calculation. Model parameters are updated by the introducing new current and voltage sample in the model.
The problem of failure diagnosis has received a considerable attention in the domain of reliabili... more The problem of failure diagnosis has received a considerable attention in the domain of reliability engineering, process control and computer science. The increasing stringent requirement of quality of a product needs considerable attention in the performance and reliability of the manufacturing system. In general, the feedback control algorithm for a process designed to handle small perturbation that may arise under normal operating condition but can not accommodate any abnormal behavior due to fault. Thus the automated maintenance or early detection of worn equipment is becoming a critical issue. This justifies the need of development of effective methodology in the area of fault aware controller. In this paper we proposed a novel Algorithm and it have been tested and implemented for making Highly reliable system like Automated Cricket Ball Stitching Machine. Considering this need the present paper proposes the work on the development methodology of fault aware controller using em...
Intelligent battery management system for runtime optimization of an electric car
2013 International Conference on Information Communication and Embedded Systems (ICICES), 2013
ABSTRACT The operation of any battery-powered system is often limited by the support-time from ba... more ABSTRACT The operation of any battery-powered system is often limited by the support-time from battery. Hence, an optimized use of available energy content of battery is required in real-time scenario. In this paper, a methodology for maximizing the run-time of a battery driven car by varying the speed of the motor according to the available energy content of the battery has been presented. The battery model with less complexity is used for accurately estimating and tracking the state of charge of the battery. This has been investigated using a battery powered small car in the laboratory consisting of DC motor and lead-acid battery is used. The model and proposed algorithm are found to be computationally efficient for design and real time implementation of energy aware battery-powered systems.
Battery powered embedded system can be considered as a power aware system for a safety critical a... more Battery powered embedded system can be considered as a power aware system for a safety critical application. There is a need of saving the battery power for such power aware system so that it can be used more efficiently, particularly in safety critical applications. Present paper describes power optimization procedure using real time scheduling technique having a specific dead line guided by the model based optimum current discharge profile of a battery. In any power aware system ‘energy optimization’ is one of the major issues for a faithful operation
2009 Second International Conference on Emerging Trends in Engineering & Technology, 2009
In this paper we propose a Lossless data compressor in high level throughput using re programable... more In this paper we propose a Lossless data compressor in high level throughput using re programable FPGA technology.Real time data compression is expected to play a crucial role in high rate data communication applications. Most available approaches have largely overlooked the impact of mixed pixels and subpixel targets, which can be accurately modeled and uncovered by resorting to the wealth of spectral information provided by hyperspectral image data. In this paper, we proposed an FPGA-based data compressor on the concept of CAM and Dictionary based compression technique has been proposed in this paper. It has been implemented on a Xilinx Spartan3-II FPGA formed by several millions of gates, and with high computational power and compact size, which make this reconfigurable device very appealing for onboard, real-time data processing.
For a battery powered safety critical system the safe duration of power for executing a specific ... more For a battery powered safety critical system the safe duration of power for executing a specific task is extremely important. It is necessary to avoid unacceptable consequences due
One of the main problems of a solar PV plant is low generation of electricity during adverse weat... more One of the main problems of a solar PV plant is low generation of electricity during adverse weather when the generated power is less than the claimed demand of power. Under this condition it is not possible to generate more electricity as per demand once the power plant is designed. When the supply of electricity to the consumers reduces
and when there is no option for manipulation of power - a blackout out or load shedding is the inevitable. Online demand regulation i.e regulate the claimed demand of the individual consumer depending on predicted power generation is an alternate option in this constrained situation. The paper will address this particular issue through a novel predictive model driven demand management. The goal is to develop a predictive model which can predict the generation from a remote point of use (load point) without any direct intervention into the power generation system i.e solar rechargeable battery system.
One of the main problems of a solar PV plant is low generation of electricity during adverse weat... more One of the main problems of a solar PV plant is low generation of electricity during adverse weather when the generated power is less than the claimed demand of power. Under this condition it is not possible to generate more electricity as per demand once the power plant is designed. When the supply of electricity to the consumers reduces
and when there is no option for manipulation of power - a blackout out or load shedding is the inevitable. Online demand regulation i.e regulate the claimed demand of the individual consumer depending on predicted power generation is an alternate option in this constrained situation. The paper will address this particular issue through a novel predictive model driven demand management. The goal is to develop a predictive model which can predict the generation from a remote point of use (load point) without any direct intervention into the power generation system i.e solar rechargeable battery system.
A key objective of solar mini grid initiatives is to increase safe and sustainable energy to iso... more A key objective of solar mini grid initiatives is to increase safe and sustainable energy to isolated remote areas where conventional electricity is unapproachable due to geographic issues. One challenge with such integrated solar mini grid is low generation of electricity during adverse weather condition when generated power is less than claimed demand. As it is difficult to predict this generation deficiency from remote customers end it finally leads to untimed outage without any early warning. While manually developing sophisticated prediction models may be feasible for such power plant for loss of supply prediction, but developing them for customers distributed under mini grid is a challenging issue. To address this we explore automatically creating site-specific battery behavior prediction models which can predict average battery storage in a day from available sunlight intensity for feasible load dispatch respecting remote generation.
Activity represents an action having a start time, end time, and duration. A number of such activ... more Activity represents an action having a start time, end time, and duration. A number of such activities (related to a particular task) form an activity Database (ADB), which maintains the
state of all activities used to perform a task and serves as an integrating component to estimate the quality of performance of the task. An episode is defined as a set of sequential activities performed by an user that occur periodically to perform a task.
We present a method for Cognitive load estimation from task analysis that helps to detect anomaly at an early stage. To
implement this we create a smart environment to monitor different activities through sensors which enhanced the interaction between human and an agent(here a personal computer) through seamlessly communicating different actions related data available from sensor under operating
condition. This leads to develop an activity based cognitive load estimation system which is used to estimate human behavior during performing a task through a model. The proposed method for cognitive load estimation is based on recent research in the field of Human- Computer Interaction (HCI).
Drafts by Dr.Joydeb Roychaudhury
Object handling capability or human grasp quality is often severely hampered due to various unavo... more Object handling capability or human grasp quality is often severely hampered due to various unavoidable circumstances like old age, stroke, accidents, several neuronal disorders, etc. Such mishaps lead to loss of desired mobility in hand and fingers thereby deteriorating the human-object interaction. In agreement with the data released by the Registrar General of India, more than half of the 30 million victims of cardiovascular disease such as stroke are in rural areas (Business Line, January 5, 2016). Unfortunately modern grasp impairment diagnostic system till date is beyond the reach of the poverty stricken rural class of the society due cost and non availability of experts. In this research article, we have made an attempt to estimate the quality of such grasping impairment using a hand data glove based diagnostic tool that periodically generate patient’s grasping capability in home and then forward the same to the remote expert through internet. A Bayesian inference has been adapted to estimate the probabilistic outcome which can estimate the current status of impairment and also predict the time of recovery in absence of expert. Thus with minimum intervention of the concerned doctor staying away from the patient , it is possible get necessary advice for treatment and time of recovery
Uploads
Papers by Dr.Joydeb Roychaudhury
and when there is no option for manipulation of power - a blackout out or load shedding is the inevitable. Online demand regulation i.e regulate the claimed demand of the individual consumer depending on predicted power generation is an alternate option in this constrained situation. The paper will address this particular issue through a novel predictive model driven demand management. The goal is to develop a predictive model which can predict the generation from a remote point of use (load point) without any direct intervention into the power generation system i.e solar rechargeable battery system.
and when there is no option for manipulation of power - a blackout out or load shedding is the inevitable. Online demand regulation i.e regulate the claimed demand of the individual consumer depending on predicted power generation is an alternate option in this constrained situation. The paper will address this particular issue through a novel predictive model driven demand management. The goal is to develop a predictive model which can predict the generation from a remote point of use (load point) without any direct intervention into the power generation system i.e solar rechargeable battery system.
state of all activities used to perform a task and serves as an integrating component to estimate the quality of performance of the task. An episode is defined as a set of sequential activities performed by an user that occur periodically to perform a task.
We present a method for Cognitive load estimation from task analysis that helps to detect anomaly at an early stage. To
implement this we create a smart environment to monitor different activities through sensors which enhanced the interaction between human and an agent(here a personal computer) through seamlessly communicating different actions related data available from sensor under operating
condition. This leads to develop an activity based cognitive load estimation system which is used to estimate human behavior during performing a task through a model. The proposed method for cognitive load estimation is based on recent research in the field of Human- Computer Interaction (HCI).
Drafts by Dr.Joydeb Roychaudhury