A Novel Semi-Supervised Data-Driven Method for Chiller Fault Diagnosis with Unlabeled Data

TL;DR

This paper introduces a semi-supervised fault diagnosis method for chillers that leverages unlabeled data using a semi-generative adversarial network, significantly improving diagnostic accuracy with fewer labeled samples.

Contribution

The paper presents a novel semi-supervised approach using semi-generative adversarial networks to enhance chiller fault diagnosis with limited labeled data.

Findings

Improves diagnostic accuracy to 84% with only 80 labeled samples.

Reduces the need for labeled data by about 60%.

Effectively utilizes unlabeled data to boost fault diagnosis performance.

Abstract

In practical chiller systems, applying efficient fault diagnosis techniques can significantly reduce energy consumption and improve energy efficiency of buildings. The success of the existing methods for fault diagnosis of chillers relies on the condition that sufficient labeled data are available for training. However, label acquisition is laborious and costly in practice. Usually, the number of labeled data is limited and most data available are unlabeled. The existing methods cannot exploit the information contained in unlabeled data, which significantly limits the improvement of fault diagnosis performance in chiller systems. To make effective use of unlabeled data to further improve fault diagnosis performance and reduce the dependency on labeled data, we proposed a novel semi-supervised data-driven fault diagnosis method for chiller systems based on the semi-generative adversarial network, which incorporates both unlabeled and labeled data into learning process. The semi-generative adversarial network can learn the information of data distribution from unlabeled data and this information can help to significantly improve the diagnostic performance. Experimental results demonstrate the effectiveness of the proposed method. Under the scenario that there are only 80 labeled samples and 16000 unlabeled samples, the proposed method can improve the diagnostic accuracy to 84%, while the supervised baseline methods only reach the accuracy of 65% at most. Besides, the minimal required number of labeled samples can be reduced by about 60% with the proposed method when there are enough unlabeled samples.