Deep‐learning based fault diagnosis using computer‐visualised power flow. Issue 17 (29th August 2018)

• Record Type: Journal Article
• Authors: Wang, Songyan; Fan, Shixiong; Chen, Jianwen; Liu, Xingwei; Hao, Bowen; Yu, Jilai
• Is Part Of: IET generation, transmission & distribution. Volume 12:Issue 17(2018)
• Page Start: 3985
• Page End: 3992
• Publication Date: 2018-08-29
• Subjects: learning (artificial intelligence) -- fault diagnosis -- neural nets -- load flow; topologies -- computer‐visualised images -- massive power‐flow image samples -- convolutional neural network -- system state -- branch flow -- sample generation process -- deep‐learning based method -- system faults -- computer‐visualised power flow -- system topology -- branch breaking -- generator -- operation security -- power system -- deep‐learning based fault diagnosis method -- topology changes -- power flow samples -- different system states; Electric power production -- Periodicals; Electric power transmission -- Periodicals; Electric power distribution -- Periodicals; 621.3105
• DOI: 10.1049/iet-gtd.2018.5254
• Languages: English
• ISSNs: 1751-8687

Abstract

Abstract : Changes in system topology, such as branch breaking and the loss of a generator or load, may profoundly influence the operation security of the power system. This study introduces a novel deep‐learning based fault diagnosis method using power flow to diagnose topology changes in the power system. Power flow samples with different system states and topologies are first computed numerically; then, they are transformed into computer‐visualised images. Using massive power‐flow image samples, a convolutional neural network that aims to identify the system state is trained. A feature‐map restriction technique is used to restructure the network. To enhance the robustness of the network, the random noise of branch flow is considered in the sample generation process. The results show that the proposed deep‐learning based method may diagnose system faults effectively.