How to improve the application potential of deep learning model in HVAC fault diagnosis: Based on pruning and interpretable deep learning method

Gao, Yuan; Miyata, Shohei; Akashi, Yasunori

doi:10.1016/j.apenergy.2023.121591

Cited by 16 publications

(9 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, the primary focus of this study lies in the strategic incorporation of normal states into the analysis, presenting several advantages that clearly distinguish it from the work presented in [ 24 ]. This approach proves to be particularly valuable, x as it effectively addresses several key challenges in fault detection and diagnosis within HVAC systems.…”

Section: Results and Discussionmentioning

confidence: 99%

“…The simulation model is subjected to a 24-h test, during which data are gathered at 1-min intervals for each sensor reading. By incorporating 194 sensor readings into the HVAC system analysis, this approach offers distinct advantages compared to relying solely on the 47 AHU operational parameters [ 24 ]. Moreover, increasing the frequency of sensor data sampling to every 1-min interval provides a more complete understanding of system behavior.…”

Section: Hvac Faults Simulation Using Hvacsim+mentioning

confidence: 99%

“…By emphasizing occupancy periods, a practical understanding of HVAC system behavior is achieved, enhancing the relevance and applicability of the findings. The approach sets this study apart from [ 24 ], highlighting the benefits of exclusively considering occupancy periods in HVAC system analysis.…”

Section: Hvac Faults Simulation Using Hvacsim+mentioning

confidence: 99%

“…This targeted strategy during occupy period avoids additional steps, such as pruning and LRP, which would otherwise be needed to sort through less informative nighttime data. This focused technique not only enhances accuracy but also streamlines the architecture of the model, maintaining efficiency without the added complexity of 24-h training [ 24 ]. This methodology fits well with HVAC fault detection needs, ensuring accuracy, simplicity, and efficiency.…”

Section: Hvac Faults Simulation Using Hvacsim+mentioning

confidence: 99%

“…To overcome this challenge, emerging techniques such as Gramian angular fields (GAF) transform time-series data into spatial representations, with recent advancements integrating algorithms with CNNs to enhance fault diagnosis capabilities [ 21 , 22 , 23 ]. In [ 24 ], the GAF-2DCNNs approach focuses on enhancing the deep learning application for HVAC fault detection system is proposed. It involves using pruning to significantly decrease model parameters and incorporating layer-wise relevance propagation (LRP) for improving model interpretability.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Advancing Fault Detection in HVAC Systems: Unifying Gramian Angular Field and 2D Deep Convolutional Neural Networks for Enhanced Performance

Tun,

Wong,

Ling

2023

Sensors

View full text Add to dashboard Cite

Efficiency and comfort in buildings rely on on well-functioning HVAC systems. However, system faults can compromise performance. Modern data-driven fault detection methods, considering diverse techniques, encounter challenges in understanding intricate interactions and adapting to dynamic conditions present in HVAC systems during occupancy periods. Implementing fault detection during active operation, which aligns with real-world scenarios and captures dynamic interactions and environmental changes, is considered highly valuable. To address this, utilizing the dynamic simulation system HVAC SIMulation PLUS (HVACSIM+), an HVAC fault model was developed using 194 sensor signals from each HVAC component within a single-story, four-room building. The advanced HVAC fault detection framework, leveraging simulated HVAC operational scenarios with the Gramian angular field (GAF) and two-dimensional convolutional neural networks (GAF-2DCNNs), offers a robust and proactive solution. By utilizing the GAF capacity to convert time-series sensor data into informative 2D images, integrated with 2DCNN for automated feature extraction, hidden temporal relationships within 1D signals are captured. After training on nine significant HVAC faults and normal conditions during occupancy, the effectiveness of the proposed GAF-2DCNN is evaluated through comparisons with support vector machine (SVM), random forest (RF), and hybrid RF-SVM, one-dimensional convolutional neural networks (1D-CNNs). The results demonstrates an impressive overall accuracy of 97%, accompanied by precision, recall, and F1 scores that surpass 90% for individual HVAC faults. Through the introduction of the unified approach that integrates HVACSIM+ simulated data and GAF-2DCNN, a notable enhancement in robustness and reliability for handling substantial HVAC faults is achieved.

show abstract

Section: Results and Discussionmentioning

confidence: 99%

Section: Hvac Faults Simulation Using Hvacsim+mentioning

confidence: 99%

Section: Hvac Faults Simulation Using Hvacsim+mentioning

confidence: 99%

Section: Hvac Faults Simulation Using Hvacsim+mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Advancing Fault Detection in HVAC Systems: Unifying Gramian Angular Field and 2D Deep Convolutional Neural Networks for Enhanced Performance

Tun,

Wong,

Ling

2023

Sensors

View full text Add to dashboard Cite

show abstract

Solving flood problems with deep learning technology: Research status, strategies, and future directions

Li,

Zhu,

et al. 2024

Sustainable Development

View full text Add to dashboard Cite

As a frequent and devastating natural disaster worldwide, floods are influenced by complex factors. Building flood models for simulating, monitoring, and forecasting floods is crucial to reduce the risk of disasters and minimize damage to people and property. With advancements in computing power and the impressive capabilities of deep learning in such areas as classification and prediction, there has been growing interest in using this technology in flood research. There is also a growing body of research into building flood data‐driven models with deep learning. Based on this, this study adopts a mixed‐method approach of bibliometric and qualitative analyses to provide an overview of the research. The research status is revealed in a bibliometric visualization, where the research objects are defined from the flood perspective, and the research strategies are explained from the deep learning perspective to provide a comprehensive and in‐depth understanding of the flood problem and how to apply deep learning to solve it. In addition, the study reflects on the future direction of improvement and innovation needed to promote the further development and exploration of deep learning in flood research.

show abstract

A roulette wheel-based pruning method to simplify cumbersome deep neural networks

Chan,

Yiu,

Guo

et al. 2024

Neural Comput & Applic

View full text Add to dashboard Cite

Deep neural networks (DNNs) have been applied in many pattern recognition or object detection applications. DNNs generally consist of millions or even billions of parameters. These demanding computational storage and requirements impede deployments of DNNs in resource-limited devices, such as mobile devices, micro-controllers. Simplification techniques such as pruning have commonly been used to slim DNN sizes. Pruning approaches generally quantify the importance of each component such as network weight. Weight values or weight gradients in training are commonly used as the importance metric. Small weights are pruned and large weights are kept. However, small weights are possible to be connected with significant weights which have impact to DNN outputs. DNN accuracy can be degraded significantly after the pruning process. This paper proposes a roulette wheel-like pruning algorithm, in order to simplify a trained DNN while keeping the DNN accuracy. The proposed algorithm generates a branch of pruned DNNs which are generated by a roulette wheel operator. Similar to the roulette wheel selection in genetic algorithms, small weights are more likely to be pruned but they can be kept; large weights are more likely to be kept but they can be pruned. The slimmest DNN with the best accuracy is selected from the branch. The performance of the proposed pruning algorithm is evaluated by two deterministic datasets and four non-deterministic datasets. Experimental results show that the proposed pruning algorithm generates simpler DNNs while DNN accuracy can be kept, compared to several existing pruning approaches.

show abstract

How to improve the application potential of deep learning model in HVAC fault diagnosis: Based on pruning and interpretable deep learning method

Cited by 16 publications

References 35 publications

Advancing Fault Detection in HVAC Systems: Unifying Gramian Angular Field and 2D Deep Convolutional Neural Networks for Enhanced Performance

Advancing Fault Detection in HVAC Systems: Unifying Gramian Angular Field and 2D Deep Convolutional Neural Networks for Enhanced Performance

Solving flood problems with deep learning technology: Research status, strategies, and future directions

A roulette wheel-based pruning method to simplify cumbersome deep neural networks

Contact Info

Product

Resources

About