Online Fault Diagnosis in Nonlinear Systems Using the Multiple Operating Regime Approach

Deshpande, Anjali; Patwardhan, Sachin C.

doi:10.1021/ie071593q

Cited by 22 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[5,16] However, the main purpose of this paper is to test the validation of the linear model in fault diagnosis, so only one linear perturbation model at the current operating point is used in this work. Decomposition of nonlinear transient systems into multiple linear modelling regimes has been proposed to arrest this problem.…”

Section: Update Linear Model Using Nonlinear Modelmentioning

confidence: 99%

“…The residual matrix r is presented in Equation (4). Its mean and standard deviation vector for each variable can be calculated by Equations (5) and (6):…”

Section: Fault Detection and Diagnosis Schemementioning

confidence: 99%

“…Decomposition of nonlinear transient systems into multiple linear modelling regimes has been proposed to arrest this problem. [5,16] However, the main purpose of this paper is to test the validation of the linear model in fault diagnosis, so only one linear perturbation model at the current operating point is used in this work. To make an accurate approximation of the nonlinear model, the linear model in this work is called with a period as small as possible (equal to measurement sampling interval), and its starting point is also corrected by the nonlinear model in this work.…”

Section: Controller Regulationmentioning

confidence: 99%

“…[1] Fault diagnosis methods proposed in the literature can be classified as quantitative model-based methods, qualitative model-based methods and process historybased methods. [4] A combination of several linear perturbation models is identified by a Bayesian approach in different operating regimes and is used by a nonlinear GLR method for fault identification in nonlinear systems, [5] whereas an artificial neural network is used to correlate plant input-output data by means of a nonlinear auto-regressive moving average model to capture the nonlinear system dynamics and to develop a cost-effective fault detection and diagnosis method. [3] A good understanding and a priori knowledge of observed processes would facilitate not only an accurate modelling but also an effective mapping from the measurement space to a discriminating fault feature space.…”

Section: Introductionmentioning

confidence: 99%

“…For example, a reduced order model is combined with a generalised likelihood ratio (GLR) method and integrated with fault tolerant control schemes to improve the diagnostic performance. [4] A combination of several linear perturbation models is identified by a Bayesian approach in different operating regimes and is used by a nonlinear GLR method for fault identification in nonlinear systems, [5] whereas an artificial neural network is used to correlate plant input-output data by means of a nonlinear auto-regressive moving average model to capture the nonlinear system dynamics and to develop a cost-effective fault detection and diagnosis method. [6] The modified model-based approaches for a distillation column have two features.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Fault detection and diagnosis for distillation column using two‐tier model

2013

View full text Add to dashboard Cite

In this paper, a two-tier model-based fault detection and diagnosis method for a distillation column is developed. It employs the nonlinear model developed earlier to monitor the distillation process and a corresponding linear model to identify an abnormal source when large deviations of measured values occur. The inner distillation fault parameters are estimated through linear least-square method based on the linear model. The proposed method is applied to the stripping tower in the Tennessee Eastman process simulator. Case studies demonstrate that the two-tier diagnosis structure effectively captures the variation of fault parameters and is more efficient than a pure nonlinear model-based structure.

show abstract

Section: Update Linear Model Using Nonlinear Modelmentioning

confidence: 99%

“…The residual matrix r is presented in Equation (4). Its mean and standard deviation vector for each variable can be calculated by Equations (5) and (6):…”

Section: Fault Detection and Diagnosis Schemementioning

confidence: 99%

Section: Controller Regulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fault detection and diagnosis for distillation column using two‐tier model

2013

View full text Add to dashboard Cite

show abstract

Nonstationary fault detection and diagnosis for multimode processes

Liu

Chen

2009

AIChE Journal

View full text Add to dashboard Cite

Fault isolation based on data-driven approaches usually assume the abnormal event data will be formed into a new operating region, measuring the differences between normal and faulty states to identify the faulty variables. In practice, operators intervene in processes when they are aware of abnormalities occurring. The process behavior is nonstationary, whereas the operators are trying to bring it back to normal states. Therefore, the faulty variables have to be located in the first place when the process leaves its normal operating regions. For an industrial process, multiple normal operations are common. On the basis of the assumption that the operating data follow a Gaussian distribution within an operating region, the Gaussian mixture model is employed to extract a series of operating modes from the historical process data. The local statistic T 2 and its normalized contribution chart have been derived for detecting abnormalities early and isolating faulty variables in this article. V

show abstract

Diagnosis of disturbance in distillation process based on inversion method

Tian

Liang

Zhang

2017

Asia-Pacific J Chem Eng

View full text Add to dashboard Cite

Many difficulties are encountered when analyzing hard-to-identify underlying causes of disturbances in distillation processes. Direct model-based fault diagnosis methods often prove to be time-consuming because they iteratively solve the direct model to obtain representative disturbance parameters. In this paper, an inversion method is proposed for identifying fault causes in the field of distillation diagnosis by mapping measured data against disturbance types. The proposed method consists of an offline phase and an online phase. In the offline phase, both normal and abnormal samples are simulated based on a simplified dynamic mechanistic model, and they are used to establish an inversion model for each disturbance with regard to each characteristic representation quantity using a genetic algorithm (GA). In the online phase, neural network, negative selection algorithm (NSA), and support vector machine (SVM) algorithms are used to determine the disturbance type, and the disturbance quantity is obtained by solving the corresponding inversion model. The proposed method is applied to high purity binary distillation column and benzene-toluene distillation column test cases. Case studies demonstrate that the inversion model-based diagnosis method can effectively identify disturbances and thus provide theoretical support for the application of quantitative fault diagnosis technology in the chemical industry.

show abstract

Online Fault Diagnosis in Nonlinear Systems Using the Multiple Operating Regime Approach

Cited by 22 publications

References 21 publications

Fault detection and diagnosis for distillation column using two‐tier model

Fault detection and diagnosis for distillation column using two‐tier model

Nonstationary fault detection and diagnosis for multimode processes

Diagnosis of disturbance in distillation process based on inversion method

Contact Info

Product

Resources

About