Recognition Method of Knob Gear in Substation Based on YOLOv4 and Darknet53-DUC-DSNT.

When unattended substations are popular, the knob is a vital monitoring object for unattended substations. However, in the actual scene of the substation, the recognition method of a knob gear has low accuracy. The main reasons are as follows. Firstly, the SNR of knob images is low due to the influence of lighting conditions, which are challenging to extract image features. Secondly, the image deviates from the front view affected by the shooting angle; that knob has a certain deformation, which causes the feature judgment to be disturbed. Finally, the feature distribution of each kind of knob is inconsistent, which interferes with image extraction features and leads to weak spatial generalization ability. For the above problems, we propose a three-stage knob gear recognition method based on YOLOv4 and Darknet53-DUC-DSNT models for the first time and apply key point detection of deep learning to knob gear recognition for the first time. Firstly, YOLOv4 is used as the knob area detector to find knobs from a picture of a cabinet panel. Then, Darknet53, which can extract features, is used as the backbone network for keypoint detection of knobs, combined with DUC structure to recover detailed information and DSNT structure to enhance feature extraction and improve spatial generalization ability. Finally, we obtained the knob gear by calculating the angle between the line of the rotating center point and the pointing point and horizontal direction. The experimental results show that this method effectively solves the above problems and improves the performance of knob gear detection.

Multi-Source Information Fusion Based on Negation of Reconstructed Basic Probability Assignment with Padded Gaussian Distribution and Belief Entropy.

Multi-source information fusion is widely used because of its similarity to practical engineering situations. With the development of science and technology, the sources of information collected under engineering projects and scientific research are more diverse. To extract helpful information from multi-source information, in this paper, we propose a multi-source information fusion method based on the Dempster-Shafer (DS) evidence theory with the negation of reconstructed basic probability assignments (nrBPA). To determine the initial basic probability assignment (BPA), the Gaussian distribution BPA functions with padding terms are used. After that, nrBPAs are determined by two processes, reassigning the high blur degree BPA and transforming them into the form of negation. In addition, evidence of preliminary fusion is obtained using the entropy weight method based on the improved belief entropy of nrBPAs. The final fusion results are calculated from the preliminary fused evidence through the Dempster's combination rule. In the experimental section, the UCI iris data set and the wine data set are used for validating the arithmetic processes of the proposed method. In the comparative analysis, the effectiveness of the BPA determination using a padded Gaussian function is verified by discussing the classification task with the iris data set. Subsequently, the comparison with other methods using the cross-validation method proves that the proposed method is robust. Notably, the classification accuracy of the iris data set using the proposed method can reach an accuracy of 97.04%, which is higher than many other methods.

An Improved K-Means Algorithm Based on Evidence Distance.

The main influencing factors of the clustering effect of the k-means algorithm are the selection of the initial clustering center and the distance measurement between the sample points. The traditional k-mean algorithm uses Euclidean distance to measure the distance between sample points, thus it suffers from low differentiation of attributes between sample points and is prone to local optimal solutions. For this feature, this paper proposes an improved k-means algorithm based on evidence distance. Firstly, the attribute values of sample points are modelled as the basic probability assignment (BPA) of sample points. Then, the traditional Euclidean distance is replaced by the evidence distance for measuring the distance between sample points, and finally k-means clustering is carried out using UCI data. Experimental comparisons are made with the traditional k-means algorithm, the k-means algorithm based on the aggregation distance parameter, and the Gaussian mixture model. The experimental results show that the improved k-means algorithm based on evidence distance proposed in this paper has a better clustering effect and the convergence of the algorithm is also better.