Intuitionistic Fuzzy Expert System based Fault Diagnosis using Dissolved Gas Analysis for Power Transformer

Mani, Geetha,Jerome, Jovitha The Korean Institute of Electrical Engineers 2014 Journal of Electrical Engineering & Technology Vol.9 No.6

In transformer fault diagnosis, dissolved gas analysis (DGA) is been widely employed for a long period and numerous methods have been innovated to interpret its results. Still in some cases it fails to identify the corresponding faults. Due to the limitation of training data and non-linearity, the estimation of key-gas ratio in the transformer oil becomes more complicated. This paper presents Intuitionistic Fuzzy expert System (IFS) to diagnose several faults in a transformer. This revised approach is well suitable to diagnosis the transformer faults and the corresponding action to be taken. The proposed method is applied to an independent data of different power transformers and various case studies of historic trends of transformer units. It has been proved to be a very advantageous tool for transformer diagnosis and upkeep planning. This method has been successfully used to identify the type of fault developing within a transformer even if there is conflict in the results of AI technique applied to DGA data.

Intuitionistic Fuzzy Expert System based Fault Diagnosis using Dissolved Gas Analysis for Power Transformer

Geetha Mani,Jovitha Jerome 대한전기학회 2014 Journal of Electrical Engineering & Technology Vol.9 No.6

In transformer fault diagnosis, dissolved gas analysis (DGA) is been widely employed for a long period and numerous methods have been innovated to interpret its results. Still in some cases it fails to identify the corresponding faults. Due to the limitation of training data and non-linearity, the estimation of key-gas ratio in the transformer oil becomes more complicated. This paper presents Intuitionistic Fuzzy expert System (IFS) to diagnose several faults in a transformer. This revised approach is well suitable to diagnosis the transformer faults and the corresponding action to be taken. The proposed method is applied to an independent data of different power transformers and various case studies of historic trends of transformer units. It has been proved to be a very advantageous tool for transformer diagnosis and upkeep planning. This method has been successfully used to identify the type of fault developing within a transformer even if there is conflict in the results of AI technique applied to DGA data.

Integrating Fuzzy based Fault diagnosis with Constrained Model Predictive Control for Industrial Applications

Mani, Geetha,Sivaraman, Natarajan The Korean Institute of Electrical Engineers 2017 Journal of Electrical Engineering & Technology Vol.12 No.2

An active Fault Tolerant Model Predictive Control (FTMPC) using Fuzzy scheduler is developed. Fault tolerant Control (FTC) system stages are broadly classified into two namely Fault Detection and Isolation (FDI) and fault accommodation. Basically, the faults are identified by means of state estimation techniques. Then using the decision based approach it is isolated. This is usually performed using soft computing techniques. Fuzzy Decision Making (FDM) system classifies the faults. After identification and classification of the faults, the model is selected by using the information obtained from FDI. Then this model is fed into FTC in the form of MPC scheme by Takagi-Sugeno Fuzzy scheduler. The Fault tolerance is performed by switching the appropriate model for each identified faults. Thus by incorporating the fuzzy scheduled based FTC it becomes more efficient. The system will be thereafter able to detect the faults, isolate it and also able to accommodate the faults in the sensors and actuators of the Continuous Stirred Tank Reactor (CSTR) process while the conventional MPC does not have the ability to perform it.

Design and Implementation of a Preemptive Disturbance Rejection Controller for PEM Fuel Cell Air-feed System Subject to Load Changes

Mani, Geetha,Pinagapani, Arun Kumar The Korean Institute of Electrical Engineers 2016 Journal of Electrical Engineering & Technology Vol.11 No.5

Integrating Fuzzy based Fault diagnosis with Constrained Model Predictive Control for Industrial Applications

Geetha Mani,Natarajan Sivaraman 대한전기학회 2017 Journal of Electrical Engineering & Technology Vol.12 No.2

An active Fault Tolerant Model Predictive Control (FTMPC) using Fuzzy scheduler is developed. Fault tolerant Control (FTC) system stages are broadly classified into two namely Fault Detection and Isolation (FDI) and fault accommodation. Basically, the faults are identified by means of state estimation techniques. Then using the decision based approach it is isolated. This is usually performed using soft computing techniques. Fuzzy Decision Making (FDM) system classifies the faults. After identification and classification of the faults, the model is selected by using the information obtained from FDI. Then this model is fed into FTC in the form of MPC scheme by Takagi-Sugeno Fuzzy scheduler. The Fault tolerance is performed by switching the appropriate model for each identified faults. Thus by incorporating the fuzzy scheduled based FTC it becomes more efficient. The system will be thereafter able to detect the faults, isolate it and also able to accommodate the faults in the sensors and actuators of the Continuous Stirred Tank Reactor (CSTR) process while the conventional MPC does not have the ability to perform it.

Design and Implementation of a Preemptive Disturbance Rejection Controller for PEM Fuel Cell Air-feed System Subject to Load Changes

Geetha Mani,Arun Kumar Pinagapani 대한전기학회 2016 Journal of Electrical Engineering & Technology Vol.11 No.5

The paper focuses on the control of air feed system on the PEM fuel cell subject to load changes. For this purpose, a robust regulatory controller (termed as Robustness Tracking Disturbance Overall Aggressiveness (RTDA) controller) is developed to control oxygen excess ratio and compared with widely accepted schemes namely Proportional Integral Derivative (PID), Model Predictive Control (MPC). In all the control schemes, the control objectives aim to maintain the desire oxygen excess ratio while keeping the compressor voltage at its nominal working point under input and output operational constraints. The two different scenarios: (1) Robustness Output tracking and (2) Disturbance rejection for each configuration are compared using computational time and performance indicators like Integral Square Error (IS E). The novel contribution of this work is the comparison of the performance of the schemes with respect to computational time. Simulation results allow evaluating effectiveness of the RTDA controller and the performance of each configuration applied to Polymer Electrolyte Membrane (PEM) Fuel cell air feed system.

Implementation of Virtual Feedback Control of Industrial Processes via Soft Sensing Technique

Geetha Mani 대한전기학회 2020 Journal of Electrical Engineering & Technology Vol.15 No.1

Hardware sensor devices are used for state measurements in many process industries but due to various disturbances and aging efect it causes inaccuracies in measurement. Hence, soft sensing technique is employed. Soft sensing is the method of determining constants and variables of any system according to the performance level based on the measurement from a process. In real-time all process variables cannot be tapped directly. Controlling of those variables are also tedious in nature. Further, by using simple feedback mechanism it cannot be controlled. Hence, there arises need for estimating the unmeasured state using suitable soft sensing techniques. The estimated values can be used as a feedback signal to the external PID controller. This leads to the design of virtual feedback control. In the feedback path, a hardware sensor is replaced with soft sensing technique namely an extended Kalman flter (EKF). But the main drawback of using conventional PID controllers in industries are both servo tracking and disturbance rejection cannot be achieved at the same time. Thus, enhanced PID (EPID) controllers are used to overcome the above demerit. The EPID controller has the capability to instantaneously track the set point variations and reject the disturbances simultaneously. The comparative performance analysis of both conventional PID and EPID integrated with EKF has done in simulated continuous stirred tank reactor non-linear process. The efectiveness of virtual feedback control using EPID has been demonstrated in the real-time level process.

Dynamic Modeling and Validation of PEM Fuel Cell via System Identification Approach

Pinagapani Arun Kumar,Mani Geetha,Chandran K. R.,Pandian Karthik,Sawantmorye Eshwar,Vaghela Purvil 대한전기학회 2021 Journal of Electrical Engineering & Technology Vol.16 No.4

The key issues with non-renewable energy resources are the harmful pollutants they produce. They also pose serious threat to human life and lead to severe atmospheric devastation. Hence, they become non-viable for future generations. With the innovation of fuel cell technology, these diffi culties are wiped out. Fuel Cell technology is considered as the most effi cient and environmental friendly type of energy production. Among the diff erent types of fuel cells, Proton-Exchange Membrane Fuel Cell (PEMFC) is the most distributed type and are widespread in the market, because of its lower operating temperature, reliable performance to frequent load changes, higher effi ciency and good power density. This work primarily focuses on the dynamic modeling and simulation of PEMFC. A voltage model for PEMFC is developed based on experimental data. Estimation of the system model is done by using system identifi cation toolbox in MATLAB. Validation of the estimated model is performed by comparing the estimated model response with fi rst principle nonlinear PEMFC model and with a diff erent real time data.