A robust online fault detection and diagnosis strategy of centrifugal chiller systems for building energy efficiency

Tran, Dinh Anh Tuan; Chen, Youming; Chau, Minh Quang; Ning, Baisong

doi:10.1016/j.enbuild.2015.09.044

Cited by 58 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it has a disadvantage of having a lower heat efficiency and higher energy consumption compared to other plant systems. Developed countries typically apply high-efficiency centrifugal chillers that are more energy efficient and have lower CO 2 emissions, along with a condensing HW boiler [81][82][83][84]. Thus, we selected the condensing HW boiler + centrifugal chiller model as an alternative for the base-model absorption chiller-heater.…”

Section: Selection Of Active Systems (Cases 6-13)mentioning

confidence: 99%

Analysis of Energy Saving Potential in High-Performance Building Technologies under Korean Climatic Conditions

2018

View full text Add to dashboard Cite

This study aims to suggest a basis for the selection of technologies for developing high-performance buildings to reduce energy consumption and greenhouse gas emissions. Energy-saving technologies comprising 15 cases were categorized into passive, active, and renewable energy systems. EnergyPlus v8.8.0 was used to analyze the contribution of each technology in reducing the primary energy consumptions and CO 2 emissions in the Korean climate. The primary energy consumptions of the base model were 464.1 and 485.1 kWh/m 2 a in the Incheon and Jeju region, respectively, and the CO 2 emissions were 83.4 and 87.4 kgCO 2 /m 2 a, respectively. Each technology (cases 1-15) provided different energy-saving contributions in the Korean climate depending on their characteristics. The heating, cooling, and other energy-saving contributions of each technology indicate that their saving rates can be used when selecting suitable technologies during the cooling and heating seasons. Case 15 (active chilled beam with dedicated outdoor air system + ground source heat pump) showed the highest energy saving rate. In case 15, the Incheon and Jeju models were reduced by 189.4 (59.2%) and 206.2 kWh/m 2 a (57.4%) compared to the base case, respectively, and the CO 2 emissions were reduced by up to 32.7 (60.8%) and 35.6 kgCO 2 /m 2 a (59.3%), respectively.

show abstract

Section: Selection Of Active Systems (Cases 6-13)mentioning

confidence: 99%

Analysis of Energy Saving Potential in High-Performance Building Technologies under Korean Climatic Conditions

2018

View full text Add to dashboard Cite

show abstract

“…Table 4 summarizes the major supervised learning algorithms used in building HVAC system FDD and their applications. Linear Discriminant Analysis (LDA) [60] Linear Classifier [61], [62] Bayesian Network Classifier (BNC) [63], [64] Air Terminal unit SVM [70] Whole system ANN [71] Apart from supervised learning, clustering is also applied in FDD to preprocess the time series dataset for grouping diverse system behaviors.…”

Section: Machine Learning For Building Operation and Maintenancementioning

confidence: 99%

State-of-the-art on research and applications of machine learning in the building life cycle

Hong

Wang

Luo

et al. 2020

Energy and Buildings

229

View full text Add to dashboard Cite

Fueled by big data, powerful and affordable computing resources, and advanced algorithms, machine learning has been explored and applied to buildings research for the past decades and has demonstrated its potential to enhance building performance. This study systematically surveyed how machine learning has been applied at different stages of building life cycle. By conducting a literature search on the Web of Knowledge platform, we found 9579 papers in this field and selected 153 papers for an in-depth review. The number of published papers is increasing year by year, with a focus on building design, operation, and control. However, no study was found using machine learning in building commissioning. There are successful pilot studies on fault detection and diagnosis of HVAC equipment and systems, load prediction, energy baseline estimate, load shape clustering, occupancy prediction, and learning occupant behaviors and energy use patterns. None of the existing studies were adopted broadly by the building industry, due to common challenges including (1) lack of large scale labeled data to train and validate the model, (2) lack of model transferability, which limits a model trained with one data-rich building to be used in another building with limited data, (3) lack of strong justification of costs and benefits of deploying machine learning, and (4) the performance might not be reliable and robust for the stated goals, as the method might work for some buildings but could not be generalized to others. Findings from the study can inform future machine learning research to improve occupant comfort, energy efficiency, demand flexibility, and resilience of buildings, as well as to inspire young researchers in the field to explore multidisciplinary approaches that integrate building science, computing science, data science, and social science.

show abstract

“…The rules associated with faults and PIs can be applied to separate chiller faults from faultfree operations. Regarding the high degree of non-linearity and dynamics of HVAC&R, several non-linear regression approaches have been employed to develop more faultsensitive reference models including support vector regression (SVR) [141], radial basis function (RBF) [145], kriging (KRG) [143], and least squares support vector regression (LSSVR) [144]. The fault sensitivity of PIs could deteriorate with varying system operating conditions.…”

Section: ) Theoretical Deduction Analysis (Tda)mentioning

confidence: 99%

Review on Fault Detection and Diagnosis Feature Engineering in Building Heating, Ventilation, Air Conditioning and Refrigeration Systems

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

A robust online fault detection and diagnosis strategy of centrifugal chiller systems for building energy efficiency

Cited by 58 publications

References 17 publications

Analysis of Energy Saving Potential in High-Performance Building Technologies under Korean Climatic Conditions

Analysis of Energy Saving Potential in High-Performance Building Technologies under Korean Climatic Conditions

State-of-the-art on research and applications of machine learning in the building life cycle

Review on Fault Detection and Diagnosis Feature Engineering in Building Heating, Ventilation, Air Conditioning and Refrigeration Systems

Contact Info

Product

Resources

About