Typical Equipment Classification based on Optimized C4.5 Algorithm

Abstract

Equipment management is essential for power grid enterprises to achieve scientific management, including project investment management, maintenance, operation management, and cost budget management. Screening standard power grid equipment is fundamental for power grid projects and power grid operations. This paper proposes to use an optimized C4.5 algorithm to screen typical assets. The optimized C4.5 algorithm simplifies calculating the information gain rate and is more efficient after running. In this article, all of 726 samples are used to exam the accuracy of the DT in the application of power grid typical equipment. The results show that the classification accuracy of the modified method is 93.17%, the classification error rate is 3.8%, and the classification omission rate is 4.12%.