Microgrid fault diagnosis based on whale optimization algorithm optimizing BP neural network

Haizhe Yu; Li Sun; Bin Wu

doi:10.1117/12.3024373

13 May 2024 Microgrid fault diagnosis based on whale optimization algorithm optimizing BP neural network

Haizhe Yu, Li Sun, Bin Wu

Proceedings Volume 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023); 131598D (2024) https://doi.org/10.1117/12.3024373
Event: Eighth International Conference on Energy System, Electricity and Power (ESEP 2023), 2023, Wuhan, China

Abstract

Aiming at the microgrid (MG) fault diagnosis problem, this paper proposes a new microgrid fault diagnosis method that comprehensively utilizes wavelet feature extraction and whale optimization algorithm to optimize BP neural network. First, by applying wavelet transform to extract features of the current signals in the microgrid system, a representation with time-frequency domain characteristics was obtained. Subsequently, a failure mode library was constructed with the help of these features, which provided a key basis for fault diagnosis. On this basis, the whale algorithm is optimized for the weights and biases of the BP neural network, which effectively improves the training speed and generalization performance. By applying the method proposed in this article to the microgrid system, we make an in-depth comparison with BP neural network, RNF neural network to obtain better results. The experimental results clearly show that this method greatly enhances the accuracy and efficiency of microgrid fault diagnosis and provides strong support to ensure the safe operation of the microgrid system

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Haizhe Yu, Li Sun, and Bin Wu "Microgrid fault diagnosis based on whale optimization algorithm optimizing BP neural network", Proc. SPIE 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023), 131598D (13 May 2024); https://doi.org/10.1117/12.3024373

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available