End-to-end chiller fault diagnosis using fused attention mechanism and dynamic cross-entropy under imbalanced datasetsShow others and affiliations
2022 (English)In: Building and Environment, ISSN 0360-1323, E-ISSN 1873-684X, Vol. 212, article id 108821Article in journal (Refereed) Published
Abstract [en]
Fault diagnosis techniques play an increasingly important role in the operation and maintenance of smart city systems. Artificial intelligence improves the efficiency of chiller system fault diagnosis, and greatly reduces the energy consumption of urban buildings. The existing intelligent fault diagnosis methods of chiller mostly rely on balanced training datasets; lacking fault samples makes these methods incompetent to extract reliable features to recognize abnormal machine conditions, resulting in the degraded performance. To overcome the deficiencies of reported studies, a new method, called end-to-end chiller fault diagnosis, is proposed using a fused attention mechanism and dynamic cross-entropy. Firstly, a one-dimensional convolution network (1D-CNN) and long-short term memory (LSTM) are combined to capture the spatial-temporal features from the original data directly. Afterwards, a fused attention mechanism is developed to further refine the extracted features to increase the contribution of crucial features and achieve high-quality diagnostic information mining. Finally, the dynamic cross-entropy (DCE) is designed for updating the imbalance factor in real-time, with more focus on the hard-classified types. The experimental analysis results demonstrate the feasibility and superiority of the proposed method in identifying chiller system faults with imbalanced datasets.
Place, publisher, year, edition, pages
Elsevier, 2022. Vol. 212, article id 108821
Keywords [en]
Chiller fault diagnosis, Dynamic cross-entropy, Fused attention mechanism, Imbalanced datasets, Smart city systems
National Category
Computer Systems
Research subject
Operation and Maintenance
Identifiers
URN: urn:nbn:se:ltu:diva-89161DOI: 10.1016/j.buildenv.2022.108821ISI: 000829304100005Scopus ID: 2-s2.0-85123754923OAI: oai:DiVA.org:ltu-89161DiVA, id: diva2:1636711
Note
Validerad;2022;Nivå 2;2022-02-10 (sofila);
Funder: National Key Research andDevelopment of China (No. 2020YFB1712100); the National NaturalScience Foundation of China (No. 51905160); the Natural ScienceFund for Excellent Young Scholars of Hunan Province (No.2021JJ20017)
2022-02-102022-02-102022-10-28Bibliographically approved