Journal of instrumentation technology & innovations, Dec 23, 2016
The aim of this work is to design the LQR based state observer for controlling the position of a ... more The aim of this work is to design the LQR based state observer for controlling the position of a DC servo motor. The Luenburger observer is used to design the observer. The feedback controller gain is calculated using LQR technique and the overall system is simulated on MATLAB/Simulink. After observing the observer based feedback system in MATLAB/simulation, the overall system is implemented on dSPACE DS1104 Controller board. The result is tested using the versatile Control Desk software. When compared to other techniques, Usage of DS1104 controller board for system design and implementation minimizes the design and testing time. Results show that controlling the position using this stated method is more effective than PID control. Keywords: State observer, Luenburger observer, dSPACE DS1104, Control desk Cite this Article Shivaraju M A, Sudarshan Patil Kulkarni. Design and Implementation of LQR with State Observer for Position Control of DC Servo Motor Using dSPACE DS-1104. Journal of Instrumentation Technology and Innovations. 2016; 6(3): 21–28p.
With the increasing economical-developments and urban population, the number of vehicles on road ... more With the increasing economical-developments and urban population, the number of vehicles on road is increasing as well and hence the traffic. There comes the need to lower the congestion of roads caused due to vehicular traffic. Out of numerous vehicle detection and tracking techniques, this paper deals with Image- processing-based methods simulated using MATLAB Simulink. Few such methods are Background subtraction with gaussian and Kalman Filter, Blob analysis, Horn- Schunck, Particle Filter and Monte Carlo method. Background subtraction is the most familiar one these days followed by the Morphological operations. It depends on certain parameters like accuracy, time for processing, segmenting, and complexity. The various traffic parameters like the speed of the car, count, and its tracking are calculated using its threshold values in some of the detection methods. The work proposed is done in real-time taking the challenging examples. The results mentioned throw light on the lustiness of the study proposed.
The paper describes the design and implementation of an autonomous service robot which is capable... more The paper describes the design and implementation of an autonomous service robot which is capable of performing household chores. The main objective is to design and build a robot that can fetch and deliver the articles within a given space. The robot navigates to the target object, picks the object and then navigates back to the user. The paper also describes the integration of various mechanisms involved, such as Object detection and tracking using an open source deep learning neural network object classifier, navigating the robot based on the depth data, determining the exact position of the object using pose estimation (6 DOF pose) of ArUco marker detection in ROS and utilizing this information to pick the object by performing inverse kinematics. The system is designed keeping in mind the self -governance of the robot. i.e. the entire system will be capable of running on a minicomputer such as Raspberry Pi and the intense operations are isolated from the robot and are run on a server.
With growing emphasis on human identification, iris recognition has recently received increasing ... more With growing emphasis on human identification, iris recognition has recently received increasing attention. Iris feature extraction is the crucial stage of the whole iris recognition process. Through analyzing iris feature extraction and matching method, iris features are not consistent because most feature extraction techniques are sensitive to the variations of captured image data. In this paper we use the Scale
In this paper a recently developed analytical tool is explained and used to determine the effect ... more In this paper a recently developed analytical tool is explained and used to determine the effect on stability of standard error recovery systems on a model of a Boeing 737 used for research at the NASA Langley Research Center. In particular, this paper analyzes the effect of error recovery rollback, reset, and cold restart systems in a digital flight controller
Proceedings. The 21st Digital Avionics Systems Conference, Jun 26, 2003
Abstract In this paper a modeling framework is introduced for describing how complex recovery alg... more Abstract In this paper a modeling framework is introduced for describing how complex recovery algorithms used to implement safety critical control systems on a recoverable computer can affect the stability and performance characteristics of the closed-loop system ...
2020 IEEE International Conference for Innovation in Technology (INOCON), Nov 6, 2020
In recent times, human lip-readers are being presented as valuable in the assemble of scientific ... more In recent times, human lip-readers are being presented as valuable in the assemble of scientific proof. But, like all human beings, they grieve from unpredictability in analyzing the lip movement. Here an intelligent system is designed in such a way that it predicts the output for the lip reading. Proposed audio visual speech recognition (AVSR) system uses local proprietary dataset to detect the English word spoken by the speaker in the video, by using feed forward neural networks (FFNN) and Long-Short-Term-Memory (LSTM) network. The audio features selected are Mel Frequency Cepstral Coefficients (MFCC), MEL, CONTRAST, TONNETZ and CHROMA. In case of visual feature based model development, difference of location of various points around the lip of current frame and previous frame has been considered. These features are extracted for each video in the dataset. Using the extracted audio features a Deep Neural Newark having feed forward architecture is trained and using the extracted visual features a LSTM recurrent neural network is developed. In the audio and visual feature based model, accuracy is 91.42% and 80% respectively. Finally, audio and video models are integrated using feed forward neural network. Final model is capable of taking more appropriate decision while predicting the spoken word. The accuracy of integrated model is 92.38%.
Journal of instrumentation technology & innovations, Dec 23, 2016
The aim of this work is to design the LQR based state observer for controlling the position of a ... more The aim of this work is to design the LQR based state observer for controlling the position of a DC servo motor. The Luenburger observer is used to design the observer. The feedback controller gain is calculated using LQR technique and the overall system is simulated on MATLAB/Simulink. After observing the observer based feedback system in MATLAB/simulation, the overall system is implemented on dSPACE DS1104 Controller board. The result is tested using the versatile Control Desk software. When compared to other techniques, Usage of DS1104 controller board for system design and implementation minimizes the design and testing time. Results show that controlling the position using this stated method is more effective than PID control. Keywords: State observer, Luenburger observer, dSPACE DS1104, Control desk Cite this Article Shivaraju M A, Sudarshan Patil Kulkarni. Design and Implementation of LQR with State Observer for Position Control of DC Servo Motor Using dSPACE DS-1104. Journal of Instrumentation Technology and Innovations. 2016; 6(3): 21–28p.
With the increasing economical-developments and urban population, the number of vehicles on road ... more With the increasing economical-developments and urban population, the number of vehicles on road is increasing as well and hence the traffic. There comes the need to lower the congestion of roads caused due to vehicular traffic. Out of numerous vehicle detection and tracking techniques, this paper deals with Image- processing-based methods simulated using MATLAB Simulink. Few such methods are Background subtraction with gaussian and Kalman Filter, Blob analysis, Horn- Schunck, Particle Filter and Monte Carlo method. Background subtraction is the most familiar one these days followed by the Morphological operations. It depends on certain parameters like accuracy, time for processing, segmenting, and complexity. The various traffic parameters like the speed of the car, count, and its tracking are calculated using its threshold values in some of the detection methods. The work proposed is done in real-time taking the challenging examples. The results mentioned throw light on the lustiness of the study proposed.
The paper describes the design and implementation of an autonomous service robot which is capable... more The paper describes the design and implementation of an autonomous service robot which is capable of performing household chores. The main objective is to design and build a robot that can fetch and deliver the articles within a given space. The robot navigates to the target object, picks the object and then navigates back to the user. The paper also describes the integration of various mechanisms involved, such as Object detection and tracking using an open source deep learning neural network object classifier, navigating the robot based on the depth data, determining the exact position of the object using pose estimation (6 DOF pose) of ArUco marker detection in ROS and utilizing this information to pick the object by performing inverse kinematics. The system is designed keeping in mind the self -governance of the robot. i.e. the entire system will be capable of running on a minicomputer such as Raspberry Pi and the intense operations are isolated from the robot and are run on a server.
With growing emphasis on human identification, iris recognition has recently received increasing ... more With growing emphasis on human identification, iris recognition has recently received increasing attention. Iris feature extraction is the crucial stage of the whole iris recognition process. Through analyzing iris feature extraction and matching method, iris features are not consistent because most feature extraction techniques are sensitive to the variations of captured image data. In this paper we use the Scale
In this paper a recently developed analytical tool is explained and used to determine the effect ... more In this paper a recently developed analytical tool is explained and used to determine the effect on stability of standard error recovery systems on a model of a Boeing 737 used for research at the NASA Langley Research Center. In particular, this paper analyzes the effect of error recovery rollback, reset, and cold restart systems in a digital flight controller
Proceedings. The 21st Digital Avionics Systems Conference, Jun 26, 2003
Abstract In this paper a modeling framework is introduced for describing how complex recovery alg... more Abstract In this paper a modeling framework is introduced for describing how complex recovery algorithms used to implement safety critical control systems on a recoverable computer can affect the stability and performance characteristics of the closed-loop system ...
2020 IEEE International Conference for Innovation in Technology (INOCON), Nov 6, 2020
In recent times, human lip-readers are being presented as valuable in the assemble of scientific ... more In recent times, human lip-readers are being presented as valuable in the assemble of scientific proof. But, like all human beings, they grieve from unpredictability in analyzing the lip movement. Here an intelligent system is designed in such a way that it predicts the output for the lip reading. Proposed audio visual speech recognition (AVSR) system uses local proprietary dataset to detect the English word spoken by the speaker in the video, by using feed forward neural networks (FFNN) and Long-Short-Term-Memory (LSTM) network. The audio features selected are Mel Frequency Cepstral Coefficients (MFCC), MEL, CONTRAST, TONNETZ and CHROMA. In case of visual feature based model development, difference of location of various points around the lip of current frame and previous frame has been considered. These features are extracted for each video in the dataset. Using the extracted audio features a Deep Neural Newark having feed forward architecture is trained and using the extracted visual features a LSTM recurrent neural network is developed. In the audio and visual feature based model, accuracy is 91.42% and 80% respectively. Finally, audio and video models are integrated using feed forward neural network. Final model is capable of taking more appropriate decision while predicting the spoken word. The accuracy of integrated model is 92.38%.
Uploads
Papers by sudarshan Patilkulkarni