Operation Pattern Recognition of the Refrigeration, Heating and Hot Water Combined Air-Conditioning System in Building Based on Clustering Method

Guo, Yabin; Liu, Jiangyan; Liu, Changhai; Zhu, Jinhua; Lu, Jiarui; Li, Yuduo

doi:10.3390/pr11030812

Cited by 4 publications

(3 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additional studies were carried out by Liu and Zhao with extended PR methods for different control systems [6,7]. In addition, PR was also applied to an air-conditioning system in building state estimation and fault diagnosis [8]. Over the past decades, PR has played a central role in the control system modelling domain in terms of data-driven approaches.…”

Section: Introductionmentioning

confidence: 99%

Pattern-Moving-Modelling and Analysis Based on Clustered Generalized Cell Mapping for a Class of Complex Systems

Li,

Xu,

2024

Processes

View full text Add to dashboard Cite

Considering a class of complex nonlinear systems whose dynamics are mostly governed by statistical regulations, the pattern-moving theory was developed to characterise such systems and successfully estimate the outputs or states. However, since the pattern class variable is not computable directly, this study establishes a clustered generalized cell mapping (C-GCM) to reveal system characteristics. C-GCM is a two-stage approach consisting of a pattern-moving-based description and analysis method. First, a density algorithm, named density-based spatial clustering of applications with noise (DBSCAN), is designed to obtain cell space Ω and the corresponding classification guidelines; this algorithm is initiated after the initial pre-image cells, and the total number of entity cells amounts to Ns. Then, the GCM provides several image cells based on a cell mapping function that refers to the multivariate ARMAX model. The global dynamic analysis employing both searching and storing algorithms depend on the attractor, domain of attraction, and periodic cell groups. At last, simulation results of two examples emphasise the practicality as well as efficacy of the technique suggested. The chief aim of this study was to offer a new perspective for a class of complex systems that could inspire research into nonmechanistic principles modelling and application to nonlinear systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Pattern-Moving-Modelling and Analysis Based on Clustered Generalized Cell Mapping for a Class of Complex Systems

Li,

Xu,

2024

Processes

View full text Add to dashboard Cite

show abstract

“…In addition to the previously mentioned widely employed methods, there are several other approaches in use, including autoencoder [28], semi-supervised learning [29], as well as unsupervised learning methods such as principal component analysis [30], association rules mining [31], and cluster analysis [32], and other novel methods, e.g., domain adaptation networks with parameter-free adaptively rectified linear units [33], dual-path mixed-domain residual threshold networks [34], and wavelet neural network [35].…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation of Chiller Fault Detection and Diagnosis Using Only Field-Installed Sensors

Wang,

Guo,

Zhou

et al. 2023

Processes

View full text Add to dashboard Cite

Owing to the rapid expansion of data science, data-driven methods have emerged as a dominant trend in chiller fault detection and diagnosis (FDD). Most of these methods prioritize feature selection to achieve optimal diagnostic performance. However, on-site research indicates a common installation of a limited number of sensors, coupled with a necessity to minimize diagnostic costs. This discrepancy between existing research’s feature selection principles and the current on-site sensor installation status presents a significant challenge. To facilitate the practical implementation of data-driven methods in real chiller units, this study addresses a critical question: under the constraint of limited on-site sensor installations, what is the optimal performance achievable by data-driven methods and their improved versions? To answer this, only features derived from commonly installed sensors on field chillers are chosen as indicators for typical chiller faults. The FDD performance of six frequently used data-driven methods, namely, back-propagation neural network, convolutional neural network, support vector machine, support vector data description, Bayesian network, and random forest, along with their improved versions, is comprehensively evaluated and validated using experimental data, considering four evaluation metrics. The conclusions drawn in this paper provide valuable insights for users/manufacturers with limited or no budget, detailing the best achievable diagnostic performance for each typical fault and offering guidance for those aiming to further enhance FDD performance.

show abstract

“…In recent years, with the rapid advancements in computer technology and artificial intelligence, data-driven methods have gained significant popularity in the field of fault diagnosis [7]. Examples of such methods include support vector machine (SVM) [8], convolutional neural network (CNN) [9], global density-weighted support vector data description [10], association rule mining [11], and unsupervised clustering models such as K-means, Gaussian mixture model clustering, and spectral clustering [12], among others.…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Based on Fusion of Residuals and Data for Chillers

et al. 2023

View full text Add to dashboard Cite

Feature data refer to direct measurements of specific features, while feature residuals represent the deviations between these measurements and their corresponding benchmark values. Both types of information offer unique insights into the system’s behavior. However, conventional diagnostic systems often struggle to effectively integrate and utilize both types of information concurrently. To address this limitation and improve diagnostic performance, a hybrid method based on the Bayesian network (BN) is proposed. This method enables the parallel fusion of feature residuals and feature data within a unified diagnostic model, and a comprehensive framework for developing this hybrid method is also given. In the hybrid BN, the symptom layer consists of residual nodes representing feature residuals and data nodes representing measured feature data. By applying the proposed method to two chillers and comparing it with state-of-the-art existing methods, we demonstrate its effectiveness and superiority. The results highlight that the proposed method not only accommodates the absence of either type of information but also leverages both of them to enhance diagnostic performance. Compared to using a single type of node, the hybrid method achieves a maximum improvement of 24.5% in diagnostic accuracy, with significant enhancements in F-measure observed for refrigerant leakage fault (34.5%) and excessive lubricant fault (32.8%), respectively.

show abstract

Operation Pattern Recognition of the Refrigeration, Heating and Hot Water Combined Air-Conditioning System in Building Based on Clustering Method

Cited by 4 publications

References 41 publications

Pattern-Moving-Modelling and Analysis Based on Clustered Generalized Cell Mapping for a Class of Complex Systems

Pattern-Moving-Modelling and Analysis Based on Clustered Generalized Cell Mapping for a Class of Complex Systems

Performance Evaluation of Chiller Fault Detection and Diagnosis Using Only Field-Installed Sensors

Fault Diagnosis Based on Fusion of Residuals and Data for Chillers

Contact Info

Product

Resources

About