Article
Green & Sustainable Science & Technology
Tingting Li, Mengqiu Deng, Yang Zhao, Xuejun Zhang, Chaobo Zhang
Summary: A proactive AHU fault isolation method is proposed in this study to introduce dynamic disturbances and generate additional diagnostic information for isolating serious faults. Proactive fault isolation rules are developed based on the additional diagnostic information, which have been evaluated on a simulated air-conditioning system to effectively isolate the serious faults of AHUs.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2021)
Article
Computer Science, Artificial Intelligence
Chengdong Li, Yulong Yu, Linyuan Shang, Hanyuan Zhang, Yongqing Jiang
Summary: This paper proposes an AHU fault diagnosis model based on probabilistic slow feature analysis (PSFA) and attention residual network (AResNet) to improve the accuracy of fault diagnosis. The proposed model is built using the PSFA method and AResNet, and experiments are conducted on the experimental data with different noise levels. The results show that the proposed PSFA-AResNet model outperforms other popular methods in fault diagnosis performance under three different noise levels.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Construction & Building Technology
Ying Yan, Jun Cai, Tao Li, Wan Zhang, Liangliang Sun
Summary: Air handling units play a crucial role in HVAC systems, and fault prognosis using Hidden Semi-Markov Models can accurately estimate Remaining Useful Life to prevent unexpected breakdowns and reduce maintenance costs. This study introduces a revised scaled method and a new discrete statistical process control method to improve state estimation accuracy, along with a backward recursive method for efficient RUL estimation. The experimental results demonstrate the effectiveness and accuracy of the proposed approach in predicting RULs of components and systems.
ENERGY AND BUILDINGS
(2021)
Article
Mathematics, Interdisciplinary Applications
Alessio Perinelli, Roberto Iuppa, Leonardo Ricci
Summary: This paper investigates the use of Takens estimator for correlation dimension estimation on a sphere. It shows that using geodetic and Euclidean metrics results in different biases through two analytically tractable cases. The analysis provides a cue for studying fractal geometries in seismology.
CHAOS SOLITONS & FRACTALS
(2023)
Article
Construction & Building Technology
Fanyong Cheng, Wenjian Cai, Xin Zhang, Huanyue Liao, Can Cui
Summary: This paper introduces a novel fault detection and diagnosis method using multiscale convolutional neural networks for Air Handling Unit in HVAC system. By utilizing three different scale kernels and an end-to-end learning strategy, the proposed method can effectively extract discriminative features to improve diagnostic performance. The comparison results show that the proposed MCNNs-based FDD method outperforms other commonly used methods.
ENERGY AND BUILDINGS
(2021)
Article
Physics, Multidisciplinary
Xiangyu Cao, Raoul Santachiara
Summary: A nontrivial percolation transition in level set percolation within the two-dimensional Gaussian free field has been identified, with the critical point characterized and properties such as exponentially diverging correlation length and critical clusters exhibiting logarithmic fractals. The area of these clusters scales with linear size as A similar to L-2/root lnL, while two-point connectivity decays logarithmically with distance. These findings are supported by numerical simulations, with potential interpretations in conformal field theory discussed.
PHYSICAL REVIEW LETTERS
(2021)
Article
Mathematics, Interdisciplinary Applications
Rui Wang, Abhinandan Kumar Singh, Subash Reddy Kolan, Evangelos Tsotsas
Summary: This study investigates the relationship between the box counting (BC) and power law (PL) methods for estimating the fractal dimension of aggregates. The results show that the BC fractal dimension is greater than the PL fractal dimension when the PL fractal dimension is less than or equal to 2.5, and vice versa when the PL fractal dimension is greater than 2.5. The study also proposes a projection method to obtain two-dimensional projection images of the aggregates and establishes correlations between the two-dimensional BC fractal dimension and the three-dimensional and PL fractal dimensions.
CHAOS SOLITONS & FRACTALS
(2022)
Article
Construction & Building Technology
Antonio Rosato, Francesco Guarino, Mohammad El Youssef, Alfonso Capozzoli, Massimiliano Masullo, Luigi Maffei
Summary: This study investigates the performance of a single-duct dual-fan constant air volume air-handling unit (AHU) during Italian cooling and heating seasons and analyzes its operation and key operating parameters under different fault conditions.
ENERGY AND BUILDINGS
(2022)
Article
Physics, Fluids & Plasmas
Jack Murdoch Moore, Haiying Wang, Michael Small, Gang Yan, Huijie Yang, Changgui Gu
Summary: The network correlation dimension controls the distribution of network distance in terms of a power-law model and has significant impacts on both structural properties and dynamical processes. We have developed new maximum likelihood methods that can robustly and objectively identify network correlation dimension as well as a bounded interval of distances where the model accurately represents the structure. We have also compared the traditional practice of estimating correlation dimension with a proposed alternative method using the fraction of nodes at a distance modeled as a power law.
Article
Construction & Building Technology
Yulong Yu, Hanyuan Zhang, Wei Peng, Ruiqi Wang, Chengdong Li
Summary: This paper proposes an images based deep learning model for fault diagnosis of AHU. The method extracts and ranks features using kernel slow feature analysis, transforms them into two-dimensional grayscale images, and uses convolutional neural networks (CNNs) for fault diagnosis.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Acoustics
Xiaomin Yang, Yongbing Xiang, Bingzhen Jiang
Summary: The study successfully diagnosed multiple faults in bearings by combining probabilistic principal component analysis with Higuchi fractal dimension transformation. By segmenting the original vibration signal and estimating the average fractal dimension with the Higuchi approach, fault features were extracted using the fast Fourier transform algorithm for clear diagnostic results.
JOURNAL OF VIBRATION AND CONTROL
(2022)
Article
Engineering, Mechanical
Zhiyi Zhang
Summary: Fatigue performance is crucial for materials and welded joints in engineering structures. The study on A6005 aluminum alloy welded joints revealed that the linear fatigue stress-life model was rational, and the presence of metallic oxides or discrete barlike materials could lead to crack nucleation.
ENGINEERING FAILURE ANALYSIS
(2021)
Article
Engineering, Chemical
Wahiba Bounoua, Azzeddine Bakdi
Summary: This study introduces a novel Dynamic Kernel PCA method for process monitoring in nonlinear dynamical systems, using the powerful theory of the nonlinear Fractal Dimension. The Fractal-based DKPCA integrates the two strategies to overcome the shortcomings of traditional methods and showed superior performance in fault detection and diagnosis compared to contemporary approaches.
CHEMICAL ENGINEERING SCIENCE
(2021)
Article
Energy & Fuels
Baicun Yang, Lei Xue, Yongting Duan, Miaomiao Wang
Summary: The study found a proportional relationship between the fracability and brittleness of shale gas reservoirs, with the ratio of fractal dimension and Weibull shape parameter close to a constant value of 2. This relationship is significant for the fracturing and recovery of shale-gas reservoirs, particularly in low-brittleness shale.
GEOMECHANICS AND GEOPHYSICS FOR GEO-ENERGY AND GEO-RESOURCES
(2021)
Article
Construction & Building Technology
Tianyi Zhao, Jiteng Li, Peng Wang, Sungmin Yoon, Jiaqiang Wang
Summary: This study proposes a method that uses Gaussian mixture model to preprocess historical data in order to address the uncertainty issue in calibration results caused by the dynamic nature of operating conditions in air conditioning systems. By applying the VBEM algorithm and EM algorithm to cluster and solve the GMM, the clustering results are incorporated into a virtual in-situ calibration method, leading to improved accuracy of the sensors.
ENERGY AND BUILDINGS
(2022)
Article
Thermodynamics
Zhimin Du, Ling Chen, Xinqiao Jin
Article
Construction & Building Technology
Yijun Wang, Xinqiao Jin, Zhimin Du, Xu Zhu
ENERGY AND BUILDINGS
(2018)
Article
Thermodynamics
Zhijie Chen, Xu Zhu, Xinqiao Jin, Zhimin Du
INTERNATIONAL JOURNAL OF REFRIGERATION
(2020)
Article
Construction & Building Technology
Xu Zhu, Kang Chen, Burkay Anduv, Xinqiao Jin, Zhimin Du
Summary: This paper proposes a generic framework for transferring prior knowledge from a source chiller to build a diagnostic model for a new target chiller. The method involves standardizing heterogeneous data, applying domain adaption transfer learning to overcome domain shift, and utilizing domain adversarial neural network to generate the diagnostic model for the target chiller. Results show that the transferred diagnostic model yields decent performance, outperforming conventional machine learning models.
BUILDING AND ENVIRONMENT
(2021)
Article
Construction & Building Technology
Xinbin Liang, Pengcheng Li, Siliang Chen, Xinqiao Jin, Zhimin Du
Summary: This study proposes an online data simulation method under variable operational conditions and improves the diagnostic performance of FDD models using an unsupervised partial domain adaption algorithm. Experimental results show that this method can achieve significant performance improvement.
BUILDING AND ENVIRONMENT
(2022)
Article
Construction & Building Technology
Pengcheng Li, Zhurong Liu, Burkay Anduv, Xu Zhu, Xinqiao Jin, Zhimin Du
Summary: This paper proposes a novel multiple faults diagnosis method for chillers based on multi-label learning and specific feature combinations enhanced ELM-KNN, which aims to improve the accuracy of fault diagnosis models for multiple faults. By using a small amount of single fault data in training, the model achieves better diagnosis performance for both normal operation and multiple faults.
BUILDING AND ENVIRONMENT
(2022)
Article
Thermodynamics
Kang Chen, Xu Zhu, Burkay Anduv, Xinqiao Jin, Zhimin Du
Summary: This paper proposes an intelligent digital twin framework for HVAC systems and presents a broad learning system (BLS) to build the simulation layer of the chiller and its digital twin platform. Experimental results show that the proposed method has better prediction precision and can be updated in real-time within a shorter time.
Article
Thermodynamics
Zhimin Du, Siliang Chen, Burkay Anduv, Xu Zhu, Xinqiao Jin
Summary: The collection of sensor data from HVAC chillers has enabled the development of smart cloud management systems to improve energy efficiency in buildings. However, current smart energy management techniques and fault diagnosis methods have limitations in terms of response speed and generalization capacity. This study proposes a novel IoT intelligent agent-based cloud management system for HVAC systems, integrating a fundamental framework with a machine learning algorithm for fault detection and diagnosis. By preprocessing the data and using an extreme gradient boosting algorithm, the proposed methodology achieves superior overall generalization performance compared to conventional methods.
INTERNATIONAL JOURNAL OF REFRIGERATION
(2023)
Article
Thermodynamics
Zhimin Du, Xinbin Liang, Siliang Chen, Xu Zhu, Kang Chen, Xinqiao Jin
Summary: This paper proposes a knowledge-infused neural network for smart management in energy system of smart city. It can diagnose faults of HVAC systems and shows acceptable generalization performance for out-of-distribution datasets. The self-assessment strategy using C-score provides reasonable online evaluation and the knowledge-infused neural network outperforms other models.
Article
Thermodynamics
Xinbin Liang, Xu Zhu, Kang Chen, Siliang Chen, Xinqiao Jin, Zhimin Du
Summary: This paper proposes a concept called the rejection ability of data-driven models to address the issue of online data being outside the scope of training data. Experimental results show that the introduction of rejection methods significantly improves model performance.
Article
Construction & Building Technology
Kang Chen, Siliang Chen, Xu Zhu, Xinqiao Jin, Zhimin Du
Summary: This paper proposes an interpretable mechanism mining enhanced deep learning method for fault detection and diagnosis (FDD) model transfer among different HVAC systems. By conducting fault simulation experiments and training a one-dimensional convolutional neural network (1D-CNN), a general FDD model is obtained and verified on another type of chiller. The testing results indicate that the retrained transfer model has a good diagnostic effect for the target chiller.
BUILDING AND ENVIRONMENT
(2023)
Article
Construction & Building Technology
Zhimin Du, Siliang Chen, Pengcheng Li, Kang Chen, Xinbin Liang, Xu Zhu, Xinqiao Jin
Summary: This paper proposes a knowledge-embedded deep belief network (DBN) method to diagnose multiple faults in chillers in buildings. The characteristics of electronic-thermal and thermal-thermal faults are analyzed, and the sensor biases are successfully decoupled. Representative features are extracted using the proposed DBN model. The proposed method integrates knowledge-embedded DBN, extreme learning machine (ELM), and k-nearest neighbor (KNN) as the diagnosis model.
BUILDING AND ENVIRONMENT
(2023)
Article
Construction & Building Technology
Zhimin Du, Kang Chen, Siliang Chen, Jinning He, Xu Zhu, Xinqiao Jin
Summary: The automation of fault diagnosis and smart management is crucial for the reliability of data centers' HVAC systems. Machine learning using historical data is an efficient method for developing smart management tools. However, the imbalanced training data, with more fault-free data than fault data, limits the diagnosis capacity of machine learning models. To address this issue, a deep learning-based generative adversarial network is proposed to integrate with an incremental learning SVM model to diagnose commonly occurred faults in data center air conditioning systems. The experimental results demonstrate that this approach achieves acceptable diagnosis accuracies.
ENERGY AND BUILDINGS
(2023)
Article
Energy & Fuels
Xinbin Liang, Siliang Chen, Xu Zhu, Xinqiao Jin, Zhimin Du
Summary: The task of building energy prediction (BEP) is crucial for various research areas, such as energy management and fault detection. This paper proposes a hybrid prediction model that combines deep ensemble and autoregressive models to improve building energy efficiency. Experimental results show that this hybrid model outperforms existing models in long-term predictions.
Article
Thermodynamics
Xing Fang, Xinqiao Jin, Zhimin Du, Yijun Wang, Wantao Shi
APPLIED THERMAL ENGINEERING
(2017)
Article
Construction & Building Technology
Samiran Khorat, Debashish Das, Rupali Khatun, Sk Mohammad Aziz, Prashant Anand, Ansar Khan, Mattheos Santamouris, Dev Niyogi
Summary: Cool roofs can effectively mitigate heatwave-induced excess heat and enhance thermal comfort in urban areas. Implementing cool roofs can significantly improve urban meteorology and thermal comfort, reducing energy flux and heat stress.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Qi Li, Jiayu Chen, Xiaowei Luo
Summary: This study focuses on the vertical wind conditions as a main external factor that limits the energy assessment of high-rise buildings in urban areas. Traditional tools for energy assessment of buildings use a universal vertical wind profile estimation, without taking into account the unique wind speed in each direction induced by the various shapes and configurations of buildings in cities. To address this limitation, the study developed an omnidirectional urban vertical wind speed estimation method using direction-dependent building morphologies and machine learning algorithms.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Xiaojun Luo, Lamine Mahdjoubi
Summary: This paper presents an integrated blockchain and machine learning-based energy management framework for multiple forms of energy allocation and transmission among multiple domestic buildings. Machine learning is used to predict energy generation and consumption patterns, and the proposed framework establishes optimal and automated energy allocation through peer-to-peer energy transactions. The approach contributes to the reduction of greenhouse gas emissions and enhances environmental sustainability.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Ying Yu, Yuanwei Xiao, Jinshuai Chou, Xingyu Wang, Liu Yang
Summary: This study proposes a dual-layer optimization design method to maximize the energy sharing potential, enhance collaborative benefits, and reduce the storage capacity of building clusters. Case studies show that the proposed design significantly improves the performance of building clusters, reduces energy storage capacity, and shortens the payback period.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Felix Langner, Weimin Wang, Moritz Frahm, Veit Hagenmeyer
Summary: This paper compares two main approaches to consider uncertainties in model predictive control (MPC) for buildings: robust and stochastic MPC. The results show that compared to a deterministic MPC, the robust MPC increases the electricity cost while providing complete temperature constraint satisfaction, while the stochastic MPC slightly increases the electricity cost but fulfills the thermal comfort requirements.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Somil Yadav, Caroline Hachem-Vermette
Summary: This study proposes a mathematical model to evaluate the performance of a Double Skin Facade (DSF) system and its impact on indoor conditions. The model considers various design parameters and analyzes their effects on the system's electrical output and room temperature.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Ruijun Chen, Holly Samuelson, Yukai Zou, Xianghan Zheng, Yifan Cao
Summary: This research introduces an innovative resilient design framework that optimizes building performance by considering a holistic life cycle perspective and accounting for climate projection uncertainties. The study finds that future climate scenarios significantly impact building life cycle performance, with wall U-value, windows U-value, and wall density being major factors. By using ensemble learning and optimization algorithms, predictions for carbon emissions, cost, and indoor discomfort hours can be made, and the best resilient design scheme can be selected. Applying this framework leads to significant improvements in building life cycle performance.
ENERGY AND BUILDINGS
(2024)
