Probabilistic Neural Network Based Identification of External faults Experienced by 3-Phase Induction Motors

Abstract

Fault diagnosis and condition assessment (FDCA) of rotating machines is critical due to the pivotal role that these machines play in our industries. Proper FDCA not only augments the machine’s operative lifecycle, it also improves its efficiency, thus reducing chances of cataclysmic failure. This paper defines a realistic FDCA method for 3-phase induction motors using an open source dataset. External faults experienced by IM are monitored by the probabilistic neural network (PNN) whose performance characteristics are then compared with those of Multi-Layer Perceptron (MLP) revealing that the PNN algorithm is much quicker, thereby resulting in lessening of the workload experienced by a computer substantially. RMS value of 3-phase voltages and currents are utilized as input variable for model formation to identify the 6 types of external faults experienced by IMs’ and normal operating (NF) condition. The developed system is then put to the test utilizing a sample set of 160 readings to highlight the efficiency and accuracy of the system for multiple fault scenarios.

Authors and Affiliations

Vihan Talur and Saarang Rastogi , A. P. Mittal Hasmat Malik

Keywords

Related Articles

Probabilistic Neural Network Based Identification of External faults Experienced by 3-Phase Induction Motors

Fault diagnosis and condition assessment (FDCA) of rotating machines is critical due to the pivotal role that these machines play in our industries. Proper FDCA not only augments the machine’s operative lifecycle, it als...

Reducing Duplicate Defects

Testers or users submit bug reports to identify various issues with applications. Sometimes two or more bug reports correspond to the same defect. To address this issue on duplicate defects we came up with multiple appro...

Cloud Computing Testing Evaluation

Testing becomes an important process in software development not only in terms of exposure but also in terms of performance, usability, safety, security, reusability. Also software testing is an essential activity to sof...

Bearing Fault Analysis using Frequency and Wavelet Techniques

Bearing fault diagnosis is important in condition monitoring of any rotating machine. Early fault detection in machineries can save millions of dollars in emergency maintenance cost. Different techniques are used for fau...

Multilevel Framework of ICT for Improvement in Public Distribution System for Developing Countries

Some developing countries are facing severe problems now days which are hindering their speed of development and future prospects. There is unrest in citizens for public institutions due to corruption, less accountabilit...

Download PDF file
  • EP ID EP148106
  • DOI -
  • Views 99
  • Downloads 0

How To Cite

Vihan Talur and Saarang Rastogi, A. P. Mittal Hasmat Malik (2015). Probabilistic Neural Network Based Identification of External faults Experienced by 3-Phase Induction Motors. International Journal of Computational Engineering and Management IJCEM, 18(3), 1-8. https://europub.co.uk/articles/-A-148106