Positive-Unlabelled Learning based Novelty Detection for Industrial Chillers

Sandra Corasaniti,Ron Van de Sand,Jörg Reiff-Stephan

doi:10.52825/thwildauensp.v1i.32

Abstract

Chiller systems are used in many different applications in both the industrial and the commercial sector. They are considered major energy consumers and thus contribute a non-negligible factor to environmental pollution as well as to the overall operating cost. In addition, chillers, especially in industrial applications, are often associated with high reliability requirements, as unplanned system downtimes are usually costly. As many studies over the past decades have shown, the presence of faults can lead to significant performance degradation and thus higher energy consumption of these systems. Thus, data-driven fault detection plays an ever-increasing role in terms of energy efficient control strategies. However, labelled data to train associated algorithms are often only available to a limited extent, which consequently inhibits the broad application of such technologies. Therefore, this paper presents an approach that exploits only a small amount of labelled and large amounts of unlabelled data in the training phase in order to detect fault related anomalies. For this, the model utilizes the residual space of the data transformed through principal component analyses in conjunction with a biased support vector machine, which can be ascribed to the concept of semi-supervised learning, or more specifically, positive-unlabelled learning.

Highlights

Chillers are applied across many different fields of both industrial and commercial applications
This paper proposes a novel approach, namely the principal component analysis (PCA)-R-biased support vector machine (BSVM) algorithm, for PU learning based novelty detection for industrial chillers and validates its performance based on two datasets
The model is characterized by two essential aspects; first, it is based on the residual components (RC) space after processing the data using PCA, and second, it is trained in a semi-supervised fashion as unlabelled data is exploited in the training phase

Summary

Introduction

Chillers are applied across many different fields of both industrial and commercial applications. FD contributes to saving operation as well as service costs This can help to predict system malfunctions and prevents unplanned downtimes, which is especially important for industrial applications as a chiller breakdown may cause an entire process line to stop [5]. These approaches can be divided into model-based and data-driven [6]–[8], whereas the former utilizes a reference model to detect abnormal behaviour The latter, relies on self-adapting algorithms that only require historical machine data [3] making it possible to develop FD models without any prior assumptions about the systems structure or the expected fault characteristics.

Related Works

Results

Summary