Next Article in Journal
Intelligent Mobile Wireless Network for Toxic Gas Cloud Monitoring and Tracking
Previous Article in Journal
THz Sensing of Human Skin: A Review of Skin Modeling Approaches
Article

A Novel Transformers Fault Diagnosis Method Based on Probabilistic Neural Network and Bio-Inspired Optimizer

1
College of Information Engineering, Nanchang University, Nanchang 330031, China
2
College of Qianhu, Nanchang University, Nanchang 330031, China
*
Author to whom correspondence should be addressed.
Academic Editor: Yolanda Vidal
Sensors 2021, 21(11), 3623; https://doi.org/10.3390/s21113623
Received: 16 April 2021 / Revised: 14 May 2021 / Accepted: 17 May 2021 / Published: 23 May 2021
(This article belongs to the Section Fault Diagnosis & Sensors)
Since it is difficult for the traditional fault diagnosis method based on dissolved gas analysis (DGA) to meet today’s engineering needs in terms of diagnostic accuracy and stability, this paper proposes an artificial intelligence fault diagnosis method based on a probabilistic neural network (PNN) and bio-inspired optimizer. The PNN is used as the basic classifier of the fault diagnosis model, and the bio-inspired optimizer, improved salp swarm algorithm (ISSA), is used to optimize the hidden layer smoothing factor of PNN, which stably improves the classification performance of PNN. Compared with the traditional SSA, the sine cosine algorithm (SCA) and disruption operator are introduced in ISSA, which effectively improves the exploration capability and convergence speed. To verify the engineering applicability of the proposed method, the ISSA-PNN model was developed and tested using sensor data provided by Jiangxi Province Power Supply Company. In addition, the method is compared with machine learning methods such as support vector machine (SVM), back propagation neural network (BPNN), multi-layer perceptron (MLP), and traditional fault diagnosis methods such as the international electrotechnical commission (IEC) ratio method. The results show that the proposed method has a strong learning ability for complex fault data and has advantages in accuracy and robustness compared to other methods. View Full-Text
Keywords: improved salp swarm algorithm; sine cosine algorithm; probabilistic neural network; disruption operator; power transformer; fault diagnosis improved salp swarm algorithm; sine cosine algorithm; probabilistic neural network; disruption operator; power transformer; fault diagnosis
Show Figures

Figure 1

MDPI and ACS Style

Tao, L.; Yang, X.; Zhou, Y.; Yang, L. A Novel Transformers Fault Diagnosis Method Based on Probabilistic Neural Network and Bio-Inspired Optimizer. Sensors 2021, 21, 3623. https://doi.org/10.3390/s21113623

AMA Style

Tao L, Yang X, Zhou Y, Yang L. A Novel Transformers Fault Diagnosis Method Based on Probabilistic Neural Network and Bio-Inspired Optimizer. Sensors. 2021; 21(11):3623. https://doi.org/10.3390/s21113623

Chicago/Turabian Style

Tao, Lingyu, Xiaohui Yang, Yichen Zhou, and Li Yang. 2021. "A Novel Transformers Fault Diagnosis Method Based on Probabilistic Neural Network and Bio-Inspired Optimizer" Sensors 21, no. 11: 3623. https://doi.org/10.3390/s21113623

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop