Paramita Chattopadhyay

Enhancement of thermal conductivity of transformer oil by exfoliated white graphene nanosheets

Well-dispersed exfoliated white graphene (h-BN) nanosheet in transformer oil was prepared at various weight percentages. The nanofluid transformer oil showed excellent stability over long time duration and significant improvement of thermal conductivity (>45% for 0.05 wt.%)due to large surface area and high thermal conductivity of h-BN nanosheets.

Challenges in implementation of ANN in embedded system

Artificial Neural Networks (ANN) provides a simple and efficient method to implement highly non-linear complex systems due to its “Universal Function Approximation” capabilities. However lack of a simple hardware design that is capable of adopting any changes in operating environment of the system limits the applicability of ANN in automotive and industrial environment. The most challenging task for implementation of ANN in embedded plat-form is realization of non-linear sigmoidal activation function. This paper aims to address various hardware implementation issues of ANN in terms of speed, accuracy and resource utilization. Inverse Definite Minimum Time (IDMT) characteristic has been realized and verified using XILINX Spartan-3AN FPGA with very simple ANN model. Sigmoid activation function played a very crucial role in designing and implementation of ANN. Among various techniques piece wise linear approximation (PLAN) has found to be the most optimized and hardware friendly methods for implementing of sigmoid function on reconfigurable FPGA platform.

A wavelet-based fault localization in transmission network

The proposed technique consists of a pre-processing unit based on Continuous Wavelet Transform (CWT) in combination with an Artificial Neural Networks (ANN). CWT acts as an extractor of distinctive features in the transient current signals at the sending and receiving end of the transmission line. This information is then fed to the ANN for detecting the fault type and location of fault. The results presented clearly indicate that the present technique is very fast, computationally efficient and intelligent enough to accurately identify three different types of fault (LG & LLG) and their locations.

FPGA friendly fault detection technique for drive fed induction motor

FPGA based embedded system for continuous online monitoring has gained importance in recent years. The existing FPGA based methodologies rely on transient analysis, which unnecessarily gives undue stress to the motor. Also, FFT is used which consumes large resource in the hardware unit. In this paper a DWT based algorithm is designed and implemented in FPGA to detect Broken rotor bar fault using vibration signal at low loading condition at steady state. The main contribution of this work is considerable reduction of hardware resource by use of 2-length filter for DWT and RMS energy based decision block for fault detection. In addition, there is flexibility in extending the algorithm for multi-class fault detection by controlling the required frequency band of DWT.

Application of data mining in fault diagnosis of induction motor

Data driven approaches are gaining popularity in the field of condition monitoring due to their knowledge based fault identification capability for wide range of motor operation. Particularly the method, based on mining the data can encompass the wide behavioral operation of induction motor drive system in industries. Therefore, appropriate low cost instrumentation embedding an efficient algorithm becomes the industrial demand for fault diagnosis of induction motor drive. A hardware friendly algorithm for multi-class fault diagnosis by applying data mining technique is proposed in this paper. Most frequently associated faults like bearing fault, stator inter-turn fault, broken rotor bar fault are investigated for a drive fed induction motor. Discrete wavelet transform-Inverse discrete wavelet transform (DWT-IDWT) algorithm is used to obtain the unique characteristics from each synthesized sub-band and these filtered signals are exploited for feature extraction. A feature selection technique based on Genetic Algorithm (GA) is utilized to identify the potential features for reducing the dimensionality of the feature space. The use of smallest length filter of 2 coefficients (db1) for DWT-IDWT algorithm and 6 relevant features has made the proposed algorithm computationally efficient. The classification accuracy for the investigated multiple faults are found to be quite appreciable. Further, a comparative study is also done using different classifiers: k-NN, MLP and RBF.

Tri-Axial Vibration Analysis Using Data Mining for Multi Class Fault Diagnosis in Induction Motor

Induction motor frame vibration is believed to contain certain crucial information which not only helps detecting faults but also capable of diagnosing different types of faults that occur. The vibration data can be in radial, axial and tangential directions. The frequency content of the three different directions are compared and analyzed using data mining techniques to find the most informative vibration data and to extract the vital information that can be effectively used to diagnose multiple induction motor faults. The vibration data is decomposed using powerful signal processing tools like Continuous Wavelet Transform CWT and Hilbert Transform HT. Statistical features are extracted from the decomposition coefficients obtained. Finally, data mining is applied to extract knowledge. Three types of data mining tools are deployed: sequential greedy search GS, heuristic genetic algorithm GA and deterministic rough set theory RST. The classification accuracy is judged by five types of classifiers: k-Nearest Neighbors k-NN, Multilayer Perceptron MLP, Radial Basis Function RBF and Support Vector Machine SVM, and Simple logistic. The benefits of using all the tri-axial data combined for vibration monitoring and diagnostics is also explored. The results indicate that tri-axial vibration combined provides the most informative knowledge for multi-class fault diagnosis in induction motor. However, it was also found that multi-class fault diagnosis can also be done quite effectively using only the tangential vibration signal with the help of data mining knowledge discovery.