Abstract
The k-nearest neighbor (kNN) method only uses samples’ paired distance to perform fault detection. It can overcome the nonlinearity, multimodality, and non-Gaussianity of process data. However, the nearest neighbors found by kNN on a data set containing a lot of outliers or noises may not be actual or trustworthy neighbors but a kind of pseudo neighbor, which will degrade process monitoring performance. This paper presents a new fault detection scheme using the mutual k-nearest neighbor (MkNN) method to solve this problem. The primary characteristic of our approach is that the calculation of the distance statistics for process monitoring uses MkNN rule instead of kNN. The advantage of the proposed approach is that the influence of outliers in the training data is eliminated, and the fault samples without MkNNs can be directly detected, which improves the performance of fault detection. In addition, the mutual protection phenomenon of outliers is explored. The numerical examples and Tenessee Eastman process illustrate the effectiveness of the proposed method.
Highlights
Data are being generated all the time in industrial processes
mutual k-nearest neighbor (MkNN) can more identify outliers when the value of k1 is generally smaller than k2
Due to outliers in the training samples, part of the neighbors of the samples found using k-nearest neighbor (kNN) rule in the training phase are pseudo-neighbors. These pseudo-neighbors seriously affect the determination of the control threshold and result in poor fault detection performance
Summary
Data are being generated all the time in industrial processes. Since industry became a separate category from social production, data collection and use in industrial production has gradually increased. In this context, data-driven multivariate statistical process monitoring (MSPM) methods have developed leaps and bounds [1,2], where principal component analysis (PCA) methods are the most widely used [3–6]. There are cases where PCA-based fault detection methods do not perform well. The detection threshold of Hotelling-T2 and squared prediction error (SPE) are calculated based on the premise that process variables satisfy a normal or Gaussian distribution. The traditional PCA-based process monitoring method has poor monitoring performance when facing the above problems [12–16]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
