Photovoltaic Power Generation Fault Diagnosis Model Based on Multi-Source Data Fusion Using Neural Network Algorithms

Abstract

Research on fault diagnosis of photovoltaic (PV) power generation has long been troubled by two bottlenecks. First, the simple concatenation or fusion of multi-source heterogeneous data fails to effectively utilize the embedded information. Second, traditional diagnostic models lack the capacity to generalize effectively under complex operating conditions. Therefore, this paper proposes a multi-source data fusion diagnosis model based on an adaptive fusion mechanism: by constructing a “data layer-feature layer” collaborative architecture, it can realize the fusion of signals from the same source at the data layer and the dynamic fusion of heterogeneous information at the feature layer by using Adaptive Convolutional Neural Network (Adaptive CNN), leveraging the advantages of spatial feature extraction through signal-image conversion. Experimental results show that the accuracy of the model reaches 99.0% on the dataset, and the macro-average F1-Score is improved to 98.8%. Compared with the traditional direct splicing and fusion methods, the accuracy and F1-Score are improved by 10.3% and 11.7%, respectively. At the same time, this study not only verifies the advantages of the adaptive hybrid fusion framework but also provides a technical route with high engineering application value for high-reliability PV intelligent operation and maintenance systems.