AI in HVAC fault detection and diagnosis: A systematic review

Energy Reviews, Journal Year: 2024, Volume and Issue: 3(2), P. 100071 - 100071

Published: Feb. 9, 2024

Recent studies show that artificial intelligence (AI), such as machine learning and deep learning, models can be adopted have advantages in fault detection diagnosis for building energy systems. This paper aims to conduct a comprehensive systematic literature review on (FDD) methods heating, ventilation, air conditioning (HVAC) covers the period from 2013 2023 identify analyze existing research this field. Our work concentrates explicitly synthesizing AI-based FDD techniques, particularly summarizing these offering classification. First, we discuss challenges while developing HVAC Next, classify into three categories: those based traditional hybrid AI models. Additionally, also examine physical model-based compare them with methods. The analysis concludes FDD, despite its higher accuracy reduced reliance expert knowledge, has garnered considerable interest compared physics-based However, it still encounters difficulties dynamic time-varying environments achieving resolution. Addressing is essential facilitate widespread adoption of HVAC.

Language: Английский

---

A new chiller fault diagnosis method under the imbalanced data environment via combining an improved generative adversarial network with an enhanced deep extreme learning machine

Engineering Applications of Artificial Intelligence, Journal Year: 2024, Volume and Issue: 137, P. 109218 - 109218

Published: Aug. 31, 2024

Language: Английский

---

Review of resampling techniques for the treatment of imbalanced industrial data classification in equipment condition monitoring

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 126, P. 106911 - 106911

Published: Aug. 17, 2023

Language: Английский

---

End-to-end residual learning embedded ACWGAN for AHU FDD with limited fault data

Building and Environment, Journal Year: 2025, Volume and Issue: 270, P. 112529 - 112529

Published: Jan. 5, 2025

Language: Английский

---

Data and knowledge fusion-driven Bayesian networks for interpretable fault diagnosis of HVAC systems

International Journal of Refrigeration, Journal Year: 2024, Volume and Issue: 161, P. 101 - 112

Published: Feb. 17, 2024

Language: Английский

---

Data-Augmentation Based CBAM-ResNet-GCN Method for Unbalance Fault Diagnosis of Rotating Machinery

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 34785 - 34799

Published: Jan. 1, 2024

In practical engineering scenarios, machines are seldom in a faulty operating state, so it is difficult to get enough available sample data train the fault diagnosis model, leading problem of small and unbalanced number rotating machinery samples low accuracy. To solve this problem, paper introduces novel approach diagnosis. This involves integration Convolutional Attention Residual Network (CBAM-ResNet) with Graph Neural (GCN). Firstly, comprehensively exploit time-domain information from one-dimensional vibration signals, study utilize Gram Angular Field (GAF) coding transform traits signals into two-dimensional image characteristics. The resultant then expanded by applying Wasserstein Distance Gradient Penalty Generation Adversarial (WGAN-GP) produce representative image. Secondly, input CBAM-ResNet perform focused feature extraction construct matrix. Lastly, adjacency matrix derived through Layer (GGL); subsequently, utilized as inputs for GCN. After deep extraction, classification executed via Softmax. Performance tests were conducted using Case Western Reserve University bearing dataset planetary gearbox dataset. method demonstrated remarkable results, achieving an accuracy over 99% on surpassing 98% 0dB noise compared various other models. illustrates effectiveness feasibility proposed method.

Language: Английский

---

Single imbalanced domain generalization network for intelligent fault diagnosis of compressors in HVAC systems under unseen working conditions

Energy and Buildings, Journal Year: 2024, Volume and Issue: 312, P. 114192 - 114192

Published: April 18, 2024

Language: Английский

---

Improved convolutional neural network chiller early fault diagnosis by gradient-based feature-level model interpretation and feature learning

Applied Thermal Engineering, Journal Year: 2023, Volume and Issue: 236, P. 121549 - 121549

Published: Sept. 7, 2023

Language: Английский

---

Performance and parameter optimization design of microchannel heat sink with different cavity and rib combinations

Case Studies in Thermal Engineering, Journal Year: 2023, Volume and Issue: 53, P. 103843 - 103843

Published: Dec. 3, 2023

Microchannel heat sinks play a crucial role in dissipating microelectronic systems computer data centers. To enhance their thermal performance, this study proposes combined microchannel design consisting of various cavity shapes and straight ribs, analyzes its transfer flow performance through numerical simulation. The characteristics sink with different rib structures are compared. Moreover, the four parameters including relative length (α), width (β), ribs (γ) (λ) investigated, effects Reynolds number variation on Nusselt (Nu), friction coefficient (f) enhancement efficiency (η) studied. optimization process employs an artificial neural network multi-objective genetic algorithm to determine optimal compromise solution model, utilizing as evaluation indices. results show that rectangular rounded is best comprehensive average η approximately 9.7 % higher than non-straight ribbed model. Furthermore, studied yields distinct number, coefficient, efficiency. Notably, achieved when Nu = 13.59679 f 0.11855, corresponding parameter values α 0.1575, β 0.3931, γ 0.0714, λ 1.2149. Ultimately, these provide valuable insights into structural combination models.

Language: Английский

---

Advancements in data center cooling systems: From refrigeration to high performance cooling

Energy and Buildings, Journal Year: 2024, Volume and Issue: 320, P. 114634 - 114634

Published: Aug. 5, 2024

Language: Английский

---