☆ 4.7 Article

Automated fault detection and diagnosis of chiller water plants based on convolutional neural network and knowledge distillation

BUILDING AND ENVIRONMENT (2023)

Related references

Note: Only part of the references are listed.

Article Construction & Building Technology

Model predictive control of a building renewable energy system based on a long short-term hybrid model

Yuan Gao et al.

Summary: This study proposes a hybrid prediction model and MPC framework to optimize the combination of solar PV and batteries in building energy systems. Validated with real building data, the results show significant improvements in battery safety and combined heat and power operation using the proposed framework.

SUSTAINABLE CITIES AND SOCIETY (2023)

Add to Collection

Review Energy & Fuels

A review of data-driven fault detection and diagnostics for building HVAC systems

Zhelun Chen et al.

Summary: This paper reviews and summarizes the literature on data-driven fault detection and diagnostics (FDD) for building HVAC systems, focusing on the process, systems studied, and evaluation metrics. It identifies challenges such as real-building deployment, performance evaluation, scalability, interpretability, cyber security, data privacy, and user experience that data-driven FDD methods still face despite promising performance reported in the literature.

APPLIED ENERGY (2023)

Add to Collection

Article Construction & Building Technology

Improving training efficiency for scalable automated fault detection and diagnosis in chilled water plants by transfer learning

Shohei Miyata et al.

Summary: Automated fault detection and diagnosis (AFDD) is crucial for improving the energy efficiency of air conditioning systems. The authors proposed an AFDD method using a fault dataset created by simulation, but it is difficult to apply to different systems due to substantial computation time required. This study focused on transfer learning and found that reducing the fault dataset and re-training a CNN with only some parameters can achieve reasonable diagnostic performance with significantly reduced computation time.

ENERGY AND BUILDINGS (2023)

Add to Collection

Article Energy & Fuels

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

Yuan Gao et al.

Summary: Automated Fault Detection and Diagnosis (AFDD) is crucial for improving the energy efficiency of air conditioning systems. Deep learning, with its exceptional performance in image classification, is gaining popularity in the context of AFDD for HVAC systems. However, the deployment cost of deep models is increased due to their large parameter size and lack of interpretability.

APPLIED ENERGY (2023)

Add to Collection

Article Thermodynamics

Characteristics of thermal stratification and its effects on HVAC energy consumption for an atrium building in south China

Baolian Dai et al.

Summary: An increasing number of public buildings have functional zones without physical partitioning, leading to non-uniform thermal environments. Understanding the influence of this phenomenon on HVAC energy consumption is of great significance.

ENERGY (2022)

Add to Collection

Article Construction & Building Technology

Methodology of evaluating the sewage heat utilization potential by modelling the urban sewage state prediction model

Wei-An Chen et al.

Summary: This study aims to develop a methodology for evaluating the potential of sewage heat utilization based on an urban sewage state prediction model. The constructed prediction model is applied to actual areas to assess the sewage heat utilization potential, without the need for measuring sewage flow rate and temperature data.

SUSTAINABLE CITIES AND SOCIETY (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Evaluating time series encoding techniques for Predictive Maintenance

Aniello De Santo et al.

Summary: Predictive Maintenance is crucial for minimizing downtime and fault rate in modern industrial scenarios. Machine learning and deep learning approaches show promise for accurate predictions, but their data-heavy requirements limit their real-world applications. This paper proposes a framework to evaluate time series encoding techniques applied to image classifiers for predictive maintenance tasks.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Add to Collection

Article Construction & Building Technology

Next-generation energy systems for sustainable smart cities: Roles of transfer learning

Yassine Himeur et al.

Summary: Smart cities aim to reduce wasted energy, improve grid stability, and meet service demand by adopting next-generation energy systems and leveraging artificial intelligence, IoT, and communication technologies to collect and analyze real-time big data. However, training machine learning algorithms for energy-related tasks in sustainable smart cities is a challenging data science task. Transfer learning has been proposed as a promising solution to address these challenges.

SUSTAINABLE CITIES AND SOCIETY (2022)

Add to Collection

Article Energy & Fuels

Using discrete Bayesian networks for diagnosing and isolating cross-level faults in HVAC systems

Yimin Chen et al.

Summary: Fault detection and diagnosis (FDD) technologies are crucial for ensuring satisfactory building performance. This study proposes a novel method based on discrete Bayesian Network (DisBN) for diagnosing cross-level faults in HVAC systems. Experimental results demonstrate the effectiveness of the proposed method.

APPLIED ENERGY (2022)

Add to Collection

Article Energy & Fuels

A data-driven methodology for enhanced measurement and verification of energy efficiency savings in commercial buildings

Benedetto Grillone et al.

Summary: The study proposes a novel data-driven methodology for measuring energy efficiency savings in commercial buildings through clustering techniques and innovative technology to provide accurate dynamic energy savings estimates.

APPLIED ENERGY (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

A data-driven approach to simultaneous fault detection and diagnosis in data centers

Sahar Asgari et al.

Summary: A rapid and accurate FDD strategy for data center cooling systems is proposed, which uses data-driven fault classifiers to predict multiple simultaneous faults, and the effect of adding Gaussian white noise to training data is discussed, showing high accuracy even in low noise environments.

APPLIED SOFT COMPUTING (2021)

Add to Collection

Article Construction & Building Technology

Fault detection diagnostic for HVAC systems via deep learning algorithms

Saman Taheri et al.

Summary: Deep learning algorithms, particularly deep recurrent neural networks (DRNNs), have gained attention for fault detection diagnostic in HVAC systems due to their high detection accuracy. Challenges include exploring bespoke DRNN configurations and optimizing hyperparameters, but the study successfully introduces and compares different configurations to achieve high performance. The final DRNN model outperforms other advanced data-driven techniques such as random forest and gradient boosting, showcasing its effectiveness in fault detection for HVAC systems.

ENERGY AND BUILDINGS (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Knowledge Distillation: A Survey

Jianping Gou et al.

Summary: This paper provides a comprehensive survey of knowledge distillation, covering knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison, and applications. It also briefly reviews challenges in knowledge distillation and discusses future research directions.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2021)

Add to Collection

Review Energy & Fuels

Data-Driven Machine Learning for Fault Detection and Diagnosis in Nuclear Power Plants: A Review

Guang Hu et al.

Summary: This review discusses the current status, principles, characteristics, and latest applications of DDML in fault diagnosis and detection in nuclear power plants, as well as future development trends.

FRONTIERS IN ENERGY RESEARCH (2021)

Add to Collection

Article Construction & Building Technology

A knowledge-guided and data-driven method for building HVAC systems fault diagnosis

Tingting Li et al.

Summary: Fault diagnosis plays a critical role in energy conservation of building HVAC systems. This paper proposes a knowledge-guided and data-driven fault diagnosis method that integrates the advantages of both knowledge-driven and data-driven methods, accurately interprets faults, and reveals fault mechanisms through local causal graphs.

BUILDING AND ENVIRONMENT (2021)

Add to Collection

Article Chemistry, Analytical

An Online Data-Driven Fault Diagnosis Method for Air Handling Units by Rule and Convolutional Neural Networks

Huanyue Liao et al.

Summary: An online data-driven diagnosis method combining rule-based method and CNNs was proposed for fault diagnosis of AHU in HVAC systems, achieving an accurate identification of fault types with a 99.15% accuracy in offline testing and fast online detection. Experimental results validate the performance improvement of the proposed RACNN method.

SENSORS (2021)

Add to Collection

Article Mathematics, Applied

Universality of deep convolutional neural networks

Ding-Xuan Zhou

APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS (2020)

Add to Collection

Article Thermodynamics

Fault detection and diagnosis for heat source system using convolutional neural network with imaged faulty behavior data

Shohei Miyata et al.

SCIENCE AND TECHNOLOGY FOR THE BUILT ENVIRONMENT (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Knowledge distilling based model compression and feature learning in fault diagnosis

Wenfeng Zhang et al.

APPLIED SOFT COMPUTING (2020)

Add to Collection

Article Chemistry, Analytical

Sensor Classification Using Convolutional Neural Network by Encoding Multivariate Time Series as Two-Dimensional Colored Images

Chao-Lung Yang et al.

SENSORS (2020)

Add to Collection

Article Construction & Building Technology

A hybrid data mining approach for anomaly detection and evaluation in residential buildings energy data

Chengliang Xu et al.

ENERGY AND BUILDINGS (2020)

Add to Collection

Article Construction & Building Technology

Deep learning and transfer learning models of energy consumption forecasting for a building with poor information data

Yuan Gao et al.

ENERGY AND BUILDINGS (2020)

Add to Collection

Review Construction & Building Technology

Fault detection and diagnosis of large-scale HVAC systems in buildings using data-driven methods: A comprehensive review

Maryam Sadat Mirnaghi et al.

ENERGY AND BUILDINGS (2020)

Add to Collection

Article Construction & Building Technology

Deep-learning-based fault detection and diagnosis of air-handling units

Kuei-Peng Lee et al.

BUILDING AND ENVIRONMENT (2019)

Add to Collection

Review Green & Sustainable Science & Technology

Artificial intelligence-based fault detection and diagnosis methods for building energy systems: Advantages, challenges and the future

Yang Zhao et al.

RENEWABLE & SUSTAINABLE ENERGY REVIEWS (2019)

Add to Collection

Article Energy & Fuels

Experimental and numerical investigation of energy saving potential of centralized and decentralized pumping systems

Mingzhe Liu et al.

APPLIED ENERGY (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Modelling and experimental performance analysis of solar-assisted ground source heat pump system

Hikmet Esen et al.

JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE (2017)

Add to Collection

Article Computer Science, Artificial Intelligence

An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition

Baoguang Shi et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Add to Collection

Article Energy & Fuels

Fault detection and operation optimization in district heating substations based on data mining techniques

Puning Xue et al.

APPLIED ENERGY (2017)

Add to Collection

Article Construction & Building Technology

Bayesian network based FDD strategy for variable air volume terminals

Fu Xiao et al.

AUTOMATION IN CONSTRUCTION (2014)

Add to Collection

Article Construction & Building Technology

Fault detection and diagnosis for buildings and HVAC systems using combined neural networks and subtractive clustering analysis

Zhimin Du et al.

BUILDING AND ENVIRONMENT (2014)

Add to Collection

Review Thermodynamics

Methods for fault detection, diagnostics, and prognostics for building systems - A review, part I

S Katipamula et al.

HVAC&R RESEARCH (2005)

Add to Collection

Article Operations Research & Management Science

A tutorial on the cross-entropy method

PT De Boer et al.

ANNALS OF OPERATIONS RESEARCH (2005)

Add to Collection

© Peeref 2019-2024. All rights reserved.