A new fault classification approach applied to Tennessee Eastman benchmark process

D’Angelo, Marcos Flávio Silveira Vasconcelos; Palhares, Reinaldo M.; Camargos, Murilo Osorio; Maia, Renato Dourado; Mendes, Joo B.; Ekel, Petr

doi:10.1016/j.asoc.2016.08.040

Cited by 40 publications

(16 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The TE process is a classical representative in the chemical process. As a result, many scholars studied the process and used it as a driving source for process monitoring and fault diagnosis . Figure shows the approximate schema of the Tennessee Eastman process and there are five main units: reactor; condenser; compressor; stripper; and separator.…”

Section: Methodsmentioning

confidence: 99%

“…These methods eliminate the difficulties of using and developing detailed models and can enable appropriate process monitoring and fault detection tasks, especially for large chemical process systems. Therefore, data‐driven technologies include neural network methods, fuzzy theory, signed directed graph (SDG), support vector machines (SVM), and other machine learning methods have been widely used in process monitoring and fault diagnosis research. Hsu and Chen proposed a method for the fault diagnosis of the Tennessee Eastman (TE) process based on the SVM and verified the effectiveness of the method.…”

Section: Introductionmentioning

confidence: 99%

“…Subsequently, Zhang et al used the genetic algorithm (GA) to optimize the penalty parameter c in the SVM to improve the fault diagnosis accuracy of the SVM. D'Angelo et al proposed a fault diagnosis method based on fuzzy set theory, which combines the ClonALG algorithm with the Kohonen neural network. It is sensitive to changes in fault data in the sensor.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fault diagnosis in industrial chemical processes using optimal probabilistic neural network

Xie

Yang

et al. 2019

Can J Chem Eng

View full text Add to dashboard Cite

For fault detection and diagnosis in large‐scale industrial systems, traditional methods have a low classification accuracy, which is an issue. This paper proposes a fault diagnosis method based on the modified cuckoo search algorithm (MCS) to optimize the probabilistic neural network (PNN). The random forest treebagger (RFtb) is used to reduce the data feature and the PNN is trained for fault diagnosis and classification. However, in order to address the problem that the parameters of PNN easily fall into the local optimal value, the MCS algorithm is introduced to globally optimize the hidden layer element smoothing factor (σ) in the PNN. The MCS algorithm uses a parameters update and a better optimization mechanism to achieve excellent global convergence and to effectively improve the fault diagnosis capability of the model. During the testing process using the Tennessee Eastman (TE) process dataset, the performance of the proposed model is assessed by comparing the accuracy and the F1‐score of different methods. Graphs are presented that depict fault classification and diagnostic results for the different models. The results show that the MCS algorithm has a better optimization ability than the traditional optimization algorithm and the proposed combination method can significantly improve the accuracy of the TE process fault diagnosis.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fault diagnosis in industrial chemical processes using optimal probabilistic neural network

Xie

Yang

et al. 2019

Can J Chem Eng

View full text Add to dashboard Cite

show abstract

“…VA can be described as "the science of analytical reasoning facilitated by interactive visual interfaces" [7]. In the field of industrial processes, a combination of various methods is implemented for malfunction detection and incident detection [8,9], such as the use of the Tennessee Eastman process [10]. Alternative methods, such as vibration analysis have been developed to determine if a machine is functioning correctly or not [11] or the use of the Taguchi's method to explore potential multilevel state of damage in gearboxes [12].…”

Section: A Visual Analyticsmentioning

confidence: 99%

Malfunction diagnosis in industrial process systems using data mining for knowledge discovery

Lithoxoidou

Vafeiadis

Krinidis

et al. 2017

2017 International Conference on Engineering, Technology and Innovation (ICE/ITMC)

View full text Add to dashboard Cite

The determination of abnormal behavior at process industries gains increasing interest as strict regulations and highly competitive operation conditions are regularly applied at the process systems. A synergetic approach in exploring the behavior of industrial processes is proposed, targeting at the discovery of patterns and implement fault detection (malfunction) diagnosis. The patterns are based on highly correlated time series. The concept is based on the fact that if independent time series are combined based on rules, we can extract scenarios of functional and non-functional situations so as to monitor hazardous procedures occurring in workplaces. The selected methods combine and apply actions on historically stored, experimental data from a chemical pilot plant, located at CERTH/CPERI. The implementation of the clustering and classification methods showed promising results of determining with great accuracy (97%) the potential abnormal situations.

show abstract

“…Fault diagnosis technology has always been an important topic of investigation and it is widely used in industrial process systems . In addition, with multidisciplinary development and the expansion of network theory, network‐based fault diagnosis methods, such as fault diagnosis based on Bayesian networks, fault diagnosis based on neural networks, and fault diagnosis based on complex networks, have also received increasing attention. Fault detection based on complex networks regards the whole industrial system as a network structure and the devices or monitoring variables in industrial systems are regarded as the nodes in the network.…”

Section: Introductionmentioning

confidence: 99%

A fault detection method based on horizontal visibility graph‐integrated complex networks: Application to complex chemical processes

Geng

Wang

et al. 2018

Can J Chem Eng

View full text Add to dashboard Cite

With the trend towards large-scale structure and complexity in modern chemical processes, it is difficult to describe the system operating status and fault conditions via traditional approaches. In addition, there are obstacles to fault detection research in complex chemical processes due to the characteristics of the equipment hardware used in chemical systems, data collection and handling, strong internal correlations in chemical systems, factors affecting transmission, and randomness and cascade in process failures. Therefore, this paper presents a fault detection method based on horizontal visibility graph (HVG) analysis-integrated complex networks. The data for each variable in the system are regarded as a time series, each time series is modelled into a network by the horizontal visibility algorithm, and each single-layer network corresponding to a time series is abstracted as a node. Meanwhile, the correlation between two single-layer networks is used to characterize the correlation between the corresponding nodes. Moreover, a complex network structure representing the chemical system can be constructed from the correlations. In addition, according to the correlation ratio matrix obtained from the fault state and the normal state, the variance of each node determines the faulty node. Finally, we verify the validity and the effectiveness of the proposed method by applying it to the Tennessee Eastman (TE) process.

show abstract

A new fault classification approach applied to Tennessee Eastman benchmark process

Cited by 40 publications

References 59 publications

Fault diagnosis in industrial chemical processes using optimal probabilistic neural network

Fault diagnosis in industrial chemical processes using optimal probabilistic neural network

Malfunction diagnosis in industrial process systems using data mining for knowledge discovery

A fault detection method based on horizontal visibility graph‐integrated complex networks: Application to complex chemical processes

Contact Info

Product

Resources

About