This is the authors' abstract. We don't add key points for this paper.
In this work, a new local fault classification technique named neighbourhood‐preserving discriminant analysis (NPDA) was developed and applied for fault classification in industrial processes. Rather than using traditional global modelling methods, we used the neighbourhood‐preserving embedding (NPE) algorithm, which describes data features stably and reliably. Taking the latent variables obtained by NPE and Fisher discriminant analysis (FDA) as the classification features, a classification model was constructed by NPDA and used to classify various types of faults. To evaluate fault classification, case studies on a continuous stirred tank heater process and a Tennessee Eastman benchmark process were conducted. The effectiveness of the proposed approach was confirmed, as improved classification results were obtained by NPDA.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Miao et al. (2021) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: