Fast and accurate acquisition of voltage components is the basic requirement for grid-tied inverters to realize various control under unbalanced grids. In view of this situation, a delay sampling period filter (DSPF), which rapidly separates each voltage component by delaying two sampling periods in dq frame, is proposed. In view of the noise interference, a delay operation period filter (DOPF) is proposed to scale the operation period and limit the noise to an acceptable range. The complete positive sequence components (PSC) extraction method based on the developed DOPF+MAF algorithm is presented, combing the advantages of DOPF and MAF for eliminating the double-frequency AC components and high-frequency noise, respectively. Finally, the feasibility and priority of the DOPF+MAF algorithm and PSC extraction method have been verified by the physical experimental results.

The performance of the machine learning-based arc fault diagnosis method is significantly influenced by the effectiveness of features. This paper proposes the use of the feature selection (FS) method to optimize the feature quality and classification result for arc fault diagnosis. An experimental system is constructed to generate arc fault current signals under various conditions. The limitations of the predetermined threshold-based methods in time, frequency, and time-frequency domains are outlined, and the dependence/redundancy issues present in the feature dataset are analyzed. To mitigate the impact of these issues, a Light Gradient Boosting Machine (LightGBM)-based FS method, which establishes the feature importance evaluation criterion for the selected optimal feature subset based on permutation importance, is proposed in this article. The fitness proportionate sharing-based feature clustering (FPS-FC) method searches for potential feature clusters and selects a feature subset with low redundancy to accommodate unlabeled data. Finally, both proposed FS methods are compared with 6 popular supervised/unsupervised methods using 2 classifiers across 7 datasets. The results validate the effectiveness of the LightGBM-based and FPS-FC-based FS methods in enhancing the performance of arc fault diagnosis. In addition, a designed case on Raspberry Pi verifies the feasibility of the proposed methods in real-world applications.

The accuracy of machine learning-based arc fault diagnosis methods relies on the quality of the selected features. First, an experimental system is constructed for collecting realistic arc fault current signals, and different multi-domain feature extraction methods are described. Then, the feature relationships are investigated using various correlation methods to reveal the negative impact of weakly relevant or redundant features on the machine learning model. Based on the combination of feature clustering (FC) and maximal information coefficient (MIC), this paper proposes a feature selection (FS) strategy. The strategy searches for cluster centers through FC and merging processes to obtain non-redundant features with the highest representational abilities. The elimination of weakly relevant clusters and the selection of the most relevant features within clusters are performed based on the MIC scores. Subsequently, a valid feature subset with the highest representativeness and relevance is selected to improve the accuracy of arc fault diagnosis. Finally, the proposed method is evaluated against several popular FS strategies using three typical classifiers on different arc fault feature datasets, and the results show that the strategy effectively improves the accuracy of fault diagnosis. In addition, the cross-validation and hardware tests verify the stability, interference immunity, and feasibility of the proposed method for practical applications.

The suddenness and obscurity of arc faults significantly complicate the detection and prediction of resultant fires, posing a serious threat to power systems and public safety. Accurate prediction and timely identification of fires induced by arc faults are essential. This paper proposes a novel approach for arc fault fire prediction by fusing electrical signals with fire images, instead of relying solely on electrical signal detection. A fire data collection system is developed based on an arc fault experimental setup that adheres to standard requirements. The system collects multimodal data, including diverse types of arc fault signals and fire images. By analyzing this data, the mechanisms through which arc faults initiate and influence fire evolution are elucidated. A specialized tool is developed to annotate key timestamps in multimodal data and construct a high-quality dataset for model development. To address the complex application scenarios of arc fault fires, the Fire Prediction Multimodal Fusion Transformer (FireMulti-Former) model is proposed. The model integrates fault signals and fire images to improve the accuracy of arc fault fire predictions. It uses the Patch Time Series Transformer and the Vision Transformer to extract features from current and image sequences, respectively, and employs a Fusion Transformer to fuse these multimodal features. This approach leverages data complementarity to improve the understanding and discrimination of fire states caused by arc faults. Experimental results show that the FireMultiFormer model achieves high accuracy and stability across various datasets. Case studies validate the model’s ability to recognize and learn different fire states effectively. Ablation studies elucidate the impacts of model configurations and sample parameters on performance. Compared to single-modal and alternative methods, the multimodal model significantly improves performance in fire prediction. Furthermore, the proposed model enhances the performance of conventional arc fault detection methods by integrating image data.

This study mainly elaborates on six installation modes for PV power generation systems, namely, traditional fixed type, vertical single-axis tracking, north-south single-axis tracking, east-west single-axis tracking, dual-axis tracking, and fixed mode on the horizontal plane. Based on the above installation modes, a mathematical model is established for power generation of and solar radiation received by solar cell modules under the temperature of modules and attenuation of power generation. Furthermore, the ratio of energy output under different installation modes to energy output under horizontal installation is calculated by MATLAB. This paper concludes with the comparison of power generation capacity of six devices in Chenggong District of Kunming. It is showed that the utilization rate under dual-axis tracking is the highest and that under horizontal installation is the lowest. The study results can serve as a reference basis for the design of PV projects in low-latitude Class II Region of China (moderately abundant in solar energy resources), and provide data support for the implementation of different tracking modes.