Online fault prognosis with relative deviation analysis and vector autoregressive modeling

Zhao, Chunhui; Gao, Furong

doi:10.1016/j.ces.2015.08.037

Cited by 40 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of plausible ways is to apply multi-step (MS) ahead prediction, which is able to predict the progress of the filamentous bulking for a long-term operation MS ahead prediction would also add further complexity of uncertainty description for a GPR model, as the propagation of uncertainties is calculated recursively as prediction moves ahead. So far, few studies have devoted to fault diagnosis and fault prognosis (fault prediction) with MS ahead prediction in bio-chemical processes 18 . In particular, few attempts based on MS ahead prediction are used for filamentous sludge bulking fault diagnosis and prognosis.…”

mentioning

confidence: 99%

Prediction of Filamentous Sludge Bulking using a State-based Gaussian Processes Regression Model

Liu

Guo

Wang

et al. 2016

Sci Rep

View full text Add to dashboard Cite

Activated sludge process has been widely adopted to remove pollutants in wastewater treatment plants (WWTPs). However, stable operation of activated sludge process is often compromised by the occurrence of filamentous bulking. The aim of this study is to build a proper model for timely diagnosis and prediction of filamentous sludge bulking in an activated sludge process. This study developed a state-based Gaussian Process Regression (GPR) model to monitor the filamentous sludge bulking related parameter, sludge volume index (SVI), in such a way that the evolution of SVI can be predicted over multi-step ahead. This methodology was validated with SVI data collected from one full-scale WWTP. Online diagnosis and prediction of filamentous bulking sludge with real-time SVI prediction was tested through a simulation study. The results showed that the proposed methodology was capable of predicting future SVIs with good accuracy, thus providing sufficient time for predicting and controlling filamentous sludge bulking.

show abstract

mentioning

confidence: 99%

Prediction of Filamentous Sludge Bulking using a State-based Gaussian Processes Regression Model

Liu

Guo

Wang

et al. 2016

Sci Rep

View full text Add to dashboard Cite

show abstract

“…ACCEPTED MANUSCRIPT 16 recursive counterpart, even though recursive multi-step-ahead method has the error accumulation problems. This mainly results from the fact that direct multi-step-ahead prediction strategy is always built regardless of recent correlated information.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

Development of multiple-step soft-sensors using a Gaussian process model with application for fault prognosis

Liu

Xiao

Huang

et al. 2016

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

Predicting the degradation of working conditions and trending of fault propagation before they reach the alarm or failure control limit is significantly important to optimize the operational capacity of a chemical process. However, traditional one-step-ahead (OS) soft-sensors render such benefits inadequate. Direct, Recursive and Direct-recursive strategies are proposed to generalize the Gaussian Process Regression (GPR) model for multi-step-ahead (MS) prediction, thereby supporting the A C C E P T E D M A N U S C R I P T ACCEPTED MANUSCRIPT 2 fault diagnosis and prognosis of the product qualities control for chemical processes.The proposed methodology was firstly demonstrated by applying the designed algorithm to a wastewater plant (WWTP) simulated with the well-established model, i.e., Benchmark Simulation Model 1 (BSM1), then extended to a full-scale WWTP with data collected from the field influenced by filamentous sludge bulking. Results showed that the proposed strategies significantly improved the prediction performance.

show abstract

“…These data-driven fault diagnosis methods have been widely used in the engineering field. If they are combined with data-driven RUL prediction technologies, fault prognosis approaches without physical models are developed [ 19 , 29 , 30 ]. Traditional fault diagnosis can only detect the failure moment of the system.…”

Section: Introductionmentioning

confidence: 99%

“…For the purpose of fault prognosis, it is expected to detect fault trends as early as possible, and we call it early fault detection. Early detection of slowly varying small faults is an essential step to develop an efficient fault prognosis method [ 2 , 29 , 30 ].…”

Section: Introductionmentioning

confidence: 99%

Average Accumulative Based Time Variant Model for Early Diagnosis and Prognosis of Slowly Varying Faults

Zhou

Park

Wen

et al. 2018

Sensors

View full text Add to dashboard Cite

Early detection of slowly varying small faults is an essential step for fault prognosis. In this paper, we first propose an average accumulative (AA) based time varying principal component analysis (PCA) model for early detection of slowly varying faults. The AA based method can increase the fault size as well as decrease the noise energy. Then, designated component analysis (DCA) is introduced for developing an AA-DCA method to diagnose the root cause of the fault, which is helpful for the operator to make maintenance decisions. Combining the advantage of the cumulative sum (CUSUM) based method and the AA based method, a CUSUM-AA based method is developed to detect faults at earlier times. Finally, the remaining useful life (RUL) prediction model with error correction is established by nonlinear fitting. Once online fault size defined by detection statistics is obtained by an early diagnosis algorithm, real-time RUL prediction can be directly estimated without extra recursive regression.

show abstract

Online fault prognosis with relative deviation analysis and vector autoregressive modeling

Cited by 40 publications

References 29 publications

Prediction of Filamentous Sludge Bulking using a State-based Gaussian Processes Regression Model

Prediction of Filamentous Sludge Bulking using a State-based Gaussian Processes Regression Model

Development of multiple-step soft-sensors using a Gaussian process model with application for fault prognosis

Average Accumulative Based Time Variant Model for Early Diagnosis and Prognosis of Slowly Varying Faults

Contact Info

Product

Resources

About