Article: A classification and prediction model with the sparrow search-probabilistic neural network algorithm for transformer fault diagnosis Journal: International Journal of Sensor Networks (IJSNET) 2024 Vol.44 No.4 pp.249 - 257 Abstract: We present a fault prediction model for transformers to improve the accuracy of transformer fault (TF) prediction. The model is predicated on a probabilistic neural network (PNN) that is optimised using three gas ratios with the help of the sparrow search algorithm (SSA). First, we monitor real-time gas concentrations and calculate the essential gas ratio by installing a smart gas sensor inside the transformer. The PNN is optimised by using the SSA algorithm. Subsequently, a mapping model between gas ratios and fault types is established. At last, we assess the model's prediction performance by calculating the mean square error. The results we got demonstrate that this method achieves a prediction accuracy of 90%, which is superior to the back propagation (BP) network, the k-nearest neighbour (KNN), and the support vector machine (SVM). This research offers an efficient and dependable approach for TF prediction. Inderscience Publishers - linking academia, business and industry through research

Title: A classification and prediction model with the sparrow search-probabilistic neural network algorithm for transformer fault diagnosis

Authors: Ling Hu; Lanlan Yin; Feng Mo; Zhixun Liang; Zhong Ruan; Yuting Wang

Addresses: Artificial Intelligence, Liuzhou Railway Vocational Technical College, Liuzhou, Guangxi, 545616, China ' Big Data and Computer Science, Hechi University, Hechi, Guangxi, 546300, China ' Mathematics and Physics, Hechi University, Hechi, Guangxi, 546300, China ' Big Data and Computer Science, Hechi University, Hechi, Guangxi, 546300, China ' Big Data and Computer Science, Hechi University, Hechi, Guangxi, 546300, China ' Big Data and Computer Science, Hechi University, Hechi, Guangxi, 546300, China

Abstract: We present a fault prediction model for transformers to improve the accuracy of transformer fault (TF) prediction. The model is predicated on a probabilistic neural network (PNN) that is optimised using three gas ratios with the help of the sparrow search algorithm (SSA). First, we monitor real-time gas concentrations and calculate the essential gas ratio by installing a smart gas sensor inside the transformer. The PNN is optimised by using the SSA algorithm. Subsequently, a mapping model between gas ratios and fault types is established. At last, we assess the model's prediction performance by calculating the mean square error. The results we got demonstrate that this method achieves a prediction accuracy of 90%, which is superior to the back propagation (BP) network, the k-nearest neighbour (KNN), and the support vector machine (SVM). This research offers an efficient and dependable approach for TF prediction.

Keywords: probabilistic neural network; PNN; transformer fault; sparrow search algorithm; SSA; transformer fault diagnosis; classification; prediction.

DOI: 10.1504/IJSNET.2024.138499

International Journal of Sensor Networks, 2024 Vol.44 No.4, pp.249 - 257

Received: 30 Oct 2023
Accepted: 10 Nov 2023
Published online: 08 May 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A classification and prediction model with the sparrow search-probabilistic neural network algorithm for transformer fault diagnosis

Keep up-to-date