Process Monitoring and Fault Diagnosis Based on a Regular Vine and Bayesian Network

Jia, Qiong; Li, Shaojun

doi:10.1021/acs.iecr.0c01474

Cited by 13 publications

(5 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A conditional dependence model (e.g., Bayesian network (BN)) may provide a viable solution in this context since it can better present the local qualitative dependence structure. 16 One of the limitations of all of these works is their inability to quantify the risk in a financial term. Loss functions (LFs) can be utilized in this context.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Dynamic Process Safety Assessment Using Adaptive Bayesian Network with Loss Function

Amin

Khan

2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

Fault detection and diagnosis (FDD) is crucial for dynamic process safety analysis. Integrated with failure prediction models, it enables us to realize how a deviation in process variable(s) can affect system safety (measured as risk). This work aims to overcome the challenges of nonlinear, non-Gaussian, and multimodal behavior of the processing systems to detect abnormal process operations, predict dynamic operational risk, and diagnose root cause of the abnormal situation. A methodology is proposed here by integrating different techniques. The artificial neural network (ANN) is used to identify process modes, while the Bayesian network (BN) is used for fault detection. How a fault will lead to a process failure is modeled using the event tree (ET), whereas time-dependent losses associated with the failure scenarios are assessed using the inverted normal loss function (INLF). A probability adaption mechanism is used to estimate the conditional probabilities in each time slice. The complexity of estimating conditional probabilities is handled using the copula theory. The proposed framework is validated using numerical, simulated, and industrial datasets. The results suggest that the developed framework can provide greater flexibility and wider applications.

show abstract

Section: Introductionmentioning

confidence: 99%

“…However, the overall dependence structure may not be suitable for precise diagnosis. A conditional dependence model (e.g., Bayesian network (BN)) may provide a viable solution in this context since it can better present the local qualitative dependence structure …”

Section: Introductionmentioning

confidence: 99%

Dynamic Process Safety Assessment Using Adaptive Bayesian Network with Loss Function

Amin

Khan

2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

show abstract

“…In modern coal-fired power plants, benefiting from the development of sensor measurements and large database storage technology, massive data are generated and collected . Compared with that for a mechanism-based model, the internal information associated with operational data can be explored by a data-driven model without mechanism knowledge. , Well-developed data-driven models are verified to exhibit good behavior in parameter prediction, process monitoring, and fault identification . Thus, these data-driven models in the field of power plants are receiving attention.…”

Section: Introductionmentioning

confidence: 99%

“…2,3 Welldeveloped data-driven models are verified to exhibit good behavior in parameter prediction, 4 process monitoring, 5 and fault identification. 6 Thus, these data-driven models in the field of power plants are receiving attention.…”

Section: Introductionmentioning

confidence: 99%

Data Enhancement for Data-Driven Modeling in Power Plants Based on a Conditional Variational-Adversarial Generative Network

Peng

Shao

et al. 2021

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The quality of data directly affects the performance of data-driven models that are developed to monitor the operation of power plants. Constrained by external instructions and other factors, the operational data of a power plant generally present an irregular distribution, which leads to data imbalance. In this paper, a novel data generation method called a conditional variational autoencoder and generative adversarial networks (CVAE-GAN) is proposed. The original samples are first mapped to the latent variables by the encoder network in the CVAE. On combining with the conditional variables, the latent variables are then mapped to a new sample space by the generation network of the proposed model. The CVAE-GAN model trained with the original imbalanced dataset can generate a uniformly distributed dataset under the guidance of incremental L 2 -discrepancy. A numerical simulation case is given to validate the superiority of the proposed model over other common generative models. Then, the proposed model is applied for NO x emission prediction in a coal-fired power plant. The results demonstrate that the accuracy of NO x emission predictions is improved by training the model with the dataset generated by the proposed method.

show abstract

“…Fault diagnosis methods include a linear PCA‐based method 10 and a nonlinear SOM‐based method 9 . Additionally, there exist fault diagnosis methods based on process fault databases using dynamic simulators 11 and R vine and Bayesian networks 12 . Yin and Jiang reviewed recent advances in key performance indicator oriented prognosis and diagnosis, 13 and developed a MATLAB toolbox, which is data‐based key performance indicator oriented fault detection toolbox (DB‐KIT) (https://www.mathworks.com/matlabcentral/fileexchange/65348-db-kit).…”

Section: Introductionmentioning

confidence: 99%

Estimation and visualization of process states using latent variable models based on Gaussian process

Kaneko

2021

Analytical Science Advances

View full text Add to dashboard Cite

The estimation and visualization of process states are important for process control in chemical and industrial plants. Since industrial processes are related to Gaussian distributions theoretically, this study focused on Gaussian process latent variable models. Process state estimation and visualization methods are proposed using two latent variables based on the Bayesian Gaussian process latent variable model (BGPLVM), infinite warped mixture model (iWMM), and Gaussian process dynamical models (GPDM). The Tennessee Eastman process dataset was analyzed and it was confirmed that the performance of estimating the process states was highest in the order of GPDM, iWMM, and BGPLVM. Moreover, time‐delayed process variables were added to the process variables to consider the process dynamics, which further improved the performance of estimating the process states. Particularly in the case of GPDM, only two latent variables could estimate the process states, with approximately 100% accuracy for four process states. Additionally, even 10 process states could be estimated with approximately 90% accuracy, and it was confirmed that the process state estimation and process state visualization could be achieved simultaneously.

show abstract

Process Monitoring and Fault Diagnosis Based on a Regular Vine and Bayesian Network

Cited by 13 publications

References 53 publications

Dynamic Process Safety Assessment Using Adaptive Bayesian Network with Loss Function

Dynamic Process Safety Assessment Using Adaptive Bayesian Network with Loss Function

Data Enhancement for Data-Driven Modeling in Power Plants Based on a Conditional Variational-Adversarial Generative Network

Estimation and visualization of process states using latent variable models based on Gaussian process

Contact Info

Product

Resources

About