Sewage treatment fault diagnosis method based on weighted extreme learning machine integrated algorithm

[0045] Please see attached figure 1 and figure 2 , with figure 1 And attached figure 2 It is a flow chart of the sewage treatment fault diagnosis method based on the weighted extreme learning machine integration algorithm in this embodiment. The data of the experimental simulation comes from the University of California database (UCI), which is the daily monitoring data of a sewage treatment plant. The dimension of each sample in the entire data set is 38, and there are 380 complete records of all attribute values. The monitored water bodies total There are 13 states, and each state is replaced by a number. In order to simplify the complexity of the classification, we divide the samples into four categories according to the nature of the sample categories, as shown in Table 1. In Table 1, category 1 is the normal situation, category 2 is the normal situation with the performance exceeding the average value, category 3 is the normal situation with low influent flow rate, ...