What is it about?
This paper proposes a new method that substation equipment 3D identification is based on KNN classification of subspace feature vector. The advantage of KNN algorithm is fast, and the classification accuracy is improved greatly after PSO algorithm is used to optimize the weight of each subspace. The classification accuracy can be improved by dividing the subspace in more detail regardless of the classification time.
Featured Image
Photo by Tyler Casey on Unsplash
Why is it important?
The feature vector of subspaces is formed by extracting the angle features of each subspace, after dividing point cloud into the same size subspaces. The feature vector is used to classify and recognize. In order to select the appropriate size of subspace according to actual classification requirements, this paper gives a further research on the classification accuracy with subspaces of different sizes. Compared with the improved ICP classification method, experiment results show that the KNN algorithm can classify fast, and the KNN algorithm based on PSO algorithm has a significant improvement in classification.
Perspectives
It can be seen that the method proposed in this paper has a good recognition accuracy by comparison test. At the same time, it has more satisfactory recognition efficiency. As the key to reconstruct substation, recognition technology of substation equipment is beneficial to truly reproduce the objective environment by digital information on the computer. It also accelerates the rise and construction of intelligent substation.
Yong Luo
Zhengzhou University
Read the Original
This page is a summary of: Substation Equipment 3D Identification Based on KNN Classification of Subspace Feature Vector, Journal of Intelligent Systems, October 2017, De Gruyter,
DOI: 10.1515/jisys-2017-0272.
You can read the full text:
Contributors
The following have contributed to this page
