A Distributed PCA-Based Multi-Condition Fault Monitoring Method

[0073] This embodiment provides a multi-working-condition fault monitoring method based on distributed PCA. This embodiment takes a common chemical process—TE process (Tennessee Eastman Process) as an example; the experimental data comes from the TE process, and the TE process 21 faults were monitored; see Figure 4 , the method includes:

[0074] Step 1: Obtain the normal working condition data set, and standardize it to obtain the data set through the LNS method. The LNS method is:

[0075] Assuming that the m-dimensional original process data is , the LNS method uses the local neighborhood mean and standard deviation information of each sample to standardize, so as to normalize each working condition and obtain standardized data with a single distribution. The standardized data is:

[0076]

[0077] in, represents the sample x i Among the a nearest neighbors in X, the distance criterion is determined by the Euclidean distance; represents the sample x i the first ...