Monitoring the operation status of power equipment is the key to keep the power system functioning normally. This paper describes in detail the design process of the overall monitoring system, analyzes the effective collection and processing of data, and introduces the decision tree classification algorithm to predict and judge the situation of faulty power equipment. The system designed in this paper is compared and experimented with the fractional order system and the improved association rule system to study the monitoring accuracy and monitoring energy consumption of this system, as well as the diagnostic accuracy of the selected decision tree classification algorithm in the case of equipment failure. Compared with other monitoring systems, the monitoring system designed in this paper not only has good synchronization with the actual state of the test transformer in terms of timeliness, but also maintains a high degree of fit between the current state parameter monitoring results and the actual values, and the accuracy can be stabilized at about 98.5%. The energy consumption of the monitoring system designed in this paper is about 6%, which is much lower than that of the other two systems of 36% and 12%, and has the advantage of low energy consumption. The decision tree classification algorithm chosen in this paper has a significantly higher accuracy value than the two conventional fault diagnosis algorithms, with an average accuracy value of about 90%. Using the online monitoring system designed in this paper can improve monitoring accuracy, reduce energy consumption, and maintain the smooth operation of power equipment.