Data-driven Fault Detection and Diagnosis for HVAC water chillers

Beghi, Alessandro; Brignoli, Riccardo; Cecchinato, Luca; Menegazzo, Gabriele; Rampazzo, Mirco; Simmini, Francesco

doi:10.1016/j.conengprac.2016.04.018

Cited by 153 publications

(59 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A bottom-up approach focuses on the component or subsystem level, whereas the top-down approach is based on a whole building-level analysis [26]. Both methods use explicit input-output models to compare the actual operation to the ideal operation [38]. However, in the bottom-up approach, this comparison is used to detect faults in the particular system element [13], as opposed to the top-down approach which detects faults in the whole building system [26].…”

Section: Quantitative Model-based Fddmentioning

confidence: 99%

“…Due to the data required in the quantitative model-based approach, it can be expensive, as it typically results in extensive experimental campaigns to set up and introduce additional input and output measurements that are not available through the BAS [38]. They are also a computationally demanding solution to FDD and require the use of a general-purpose computer since the BAS has limited available processor and memory capacity [28].…”

Section: Quantitative Model-based Fddmentioning

confidence: 99%

“…HVAC systems are intrinsically nonlinear, multi-input-multi-output (MIMO) with interrelated parameters, and they exhibit such attributes as unmodelled dynamics, large-grained uncertainty, and incomplete knowledge of key parameter values. Therefore, the development of robust models for this kind of system is a burdensome task [38]. "…”

Section: Quantitative Model-based Fddmentioning

confidence: 99%

“…Not requiring an explicit model of the system is extremely advantageous when combining this with the large amount of data that can now be obtained through recent developments in monitoring systems [38]. Furthermore, this approach can easily be extended to systems that are comprised of different structures [38]. Conversely, this data-driven approach requires a lot of training data [5].…”

Section: Process History-based Fddmentioning

confidence: 99%

“…It became a major area of interest towards the beginning of the 21 st century [34] and interest has continued to grow as a result of the increasing focus in global energy consumption, and increased complexity of building systems [34]. There are three FDD techniques that may be utilized: Qualitative Model-Based, Quantitative Model-Based, and Process History-Based [13,18,26,35,36,37,38].…”

Section: Introduction To Fddmentioning

confidence: 99%

See 4 more Smart Citations

A Quantitative Model-Based Fault Detection & Diagnostics (FDD) System for Zone-Level Inefficiencies

Berquist¹

View full text Add to dashboard Cite

Heating, ventilation and air-conditioning (HVAC) systems account for a significant portion of energy consumption in buildings. The majority of fault detection research has neglected zone-level faults. In this study, the methodology of a quantitative model-based fault detection and diagnostics (FDD) system for the zone-level is presented. The creation of a basic model was completed using Matlab. Analyses were conducted, identifying five zone-level inefficiencies. The severity of these inefficiencies was analyzed and an excessive amount of air handling unit (AHU) fan energy consumption was detected. The redundancy of these faults in the building force the AHU to expend an unwarranted amount of energy, highlighting the importance of utilizing FDD. Benefits of this methodology include the detection of pre-existing faults originating from the initial design and the ability to apply this to new or existing buildings, improving the efficiency of the building.ii

show abstract

Section: Quantitative Model-based Fddmentioning

confidence: 99%

Section: Quantitative Model-based Fddmentioning

confidence: 99%

Section: Quantitative Model-based Fddmentioning

confidence: 99%

Section: Process History-based Fddmentioning

confidence: 99%

Section: Introduction To Fddmentioning

confidence: 99%

See 3 more Smart Citations

A Quantitative Model-Based Fault Detection & Diagnostics (FDD) System for Zone-Level Inefficiencies

Berquist¹

View full text Add to dashboard Cite

show abstract

Multi‐block principal component analysis based on variable weight information and its application to multivariate process monitoring

Wang

Deng

2017

Can J Chem Eng

View full text Add to dashboard Cite

The traditional principal component analysis (PCA)‐based process monitoring method builds a global statistical model and omits the mining of the local variable behaviours, which may degrade the fault detection performance. Considering this problem, this paper proposes a variable weight information‐based multi‐block PCA (VWI‐MBPCA) method. Firstly, a sequence hierarchical clustering algorithm is proposed to divide the full PCA component space into several sub‐blocks, where the components sharing similar variable weight information are gathered together and then the sub‐block T2 statistic is constructed for monitoring sub‐block components. Further, the variables with small weight information on each component sub‐block are extracted to build an additional sub‐PCA model, where the trueTˆ2 statistic is developed to compensate the sub‐block T2 statistic. In order to integrate the monitoring results of each sub‐block, Bayesian inference is applied to construct an overall T2 statistic. To identify the faulty variables, a multi‐block PCA contribution plot is designed by choosing some specific blocks to highlight fault information. Finally, simulations on a numerical example and the benchmark Tennessee Eastman (TE) process are used to demonstrate the strengths of the proposed method.

show abstract

Fault detection and diagnosis for chemical processes using dynamic global–local preserving projections

Chen,

Yang,

Bai

et al. 2023

Can J Chem Eng

View full text Add to dashboard Cite

Most traditional multivariate statistical monitoring methods require an assumption that the observation values at a certain moment and a past moment are statistically independent. However, in actual chemical and biological processes, the sample at a certain moment is often affected by the previous moment. Therefore, given the problem of more false alarms and poor detection ability based on the traditional principal component analysis, this article proposes a dynamic global–local preserving projections (DGLPP) algorithm. Unlike dynamic local preserving projections (DLPP) and dynamic principal component analysis (DPCA), DGLPP controls the global and local information retained in the dimensionality reduction data by introducing weight coefficients, which makes the algorithm applicable to more types of industrial processes. Moreover, new parameter determination methods are also proposed for improved detection and diagnosis. Through the improved contribution graph method, we can see the influence degree of each variable on the fault, to monitor and isolate the fault. Finally, by verifying the operation of the multivariable process and two practical cases, the results show that compared with DPCA, DLPP, and global local retained projection (GLPP) methods, the performance under this method has been significantly improved.

show abstract

Data-driven Fault Detection and Diagnosis for HVAC water chillers

Cited by 153 publications

References 46 publications

A Quantitative Model-Based Fault Detection & Diagnostics (FDD) System for Zone-Level Inefficiencies

A Quantitative Model-Based Fault Detection & Diagnostics (FDD) System for Zone-Level Inefficiencies

Multi‐block principal component analysis based on variable weight information and its application to multivariate process monitoring

Fault detection and diagnosis for chemical processes using dynamic global–local preserving projections

Contact Info

Product

Resources

About