A novel improved data-temporal attention network reconstruction model-based method for fault diagnosis of chiller sensors

Abstract

Accurate measurement of sensors is the basis for the reliable operation of complex systems. To improve the fault diagnosis performance of the air-cooled chiller sensor, an improved data-temporal attention network is proposed, and an improved data-temporal attention network–based method for sensor fault diagnosis is established. First, the method combines the “memory” capability of the bidirectional improved long short-term memory network and the feature extraction capability of the multi-scale convolutional neural network to fully explore the time correlation of the chiller sensor, the data correlation between the physical quantities, and the dynamic response characteristics of the physical quantities. In addition, data and time attention mechanisms are introduced into the encoder and decoder, respectively, and valuable information is enhanced through weight distribution to capture relevant features further. Second, relying on the advantages of the “end-to-end” network structure of the improved data-temporal attention network model, the fault sensor is directly located by comparing the absolute reconstruction error vector with the fault threshold vector. Finally, it is verified by the datasets collected from a real air-cooled chiller platform that the proposed method has achieved an excellent fault diagnosis effect. The ablation experiment confirms that each improvement step can effectively improve the reconstruction performance of the network, which enhances the sensitivity of fault sensor identification. Compared with existing mainstream methods, the state-of-the-art framework presented in this article reveals its superiority.