Fault diagnosis of a benchmark fermentation process: a comparative study of feature extraction and classification techniques

Monroy, Isaac; Villez, Kris; Graells, Moisès; Venkatasubramanian, Venkat

doi:10.1007/s00449-011-0649-1

Cited by 22 publications

(15 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A total of 150 Pensim batches (50 of each of three types of process upsets) was used by Monroy et al [59] to test fault identification via Artificial Neural Networks (ANN) and Support Vector Machines (SVM). Information on the types of upset and their (fixed) magnitude is provided, but not on onset time.…”

Section: Introductionmentioning

confidence: 99%

An extensive reference dataset for fault detection and identification in batch processes

Impe¹,

Gins²

2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

Close process monitoring (i.e., detection and identification of disturbances) is important to achieve high process efficiency and safety. The Tennessee Eastman process is an extensive benchmark dataset for fault detection and identification, but it is only representative for continuous processes because it does not contain the inherent nonstationarity that complicates monitoring of batch processes. Nevertheless, batch processes also play an important role in many types of industry. This paper therefore presents an extensive reference dataset for benchmarking data-driven methodologies for fault detection and identification in batch processes. The original Pensim model [10] is expanded with sensor noise. By changing the properties of the initial conditions and/or model parameters, four subsets of different complexity are generated, each containing 400 batches with normal operation. To correctly assess the fault detection and identification in batch processes, 15 faults are simulated with various amplitudes and onset times for a total of 22,200 faulty batches for each subset, or 90,400 batches in total. Analysis of the data indicates that the presented types of process faults and their various amplitudes in each of the four subsets present a suitable benchmark for fault detection and identification in batch processes. The dataset is freely available at http://cit.kuleuven.be/biotec/batchbenchmark.

show abstract

Section: Introductionmentioning

confidence: 99%

An extensive reference dataset for fault detection and identification in batch processes

Impe¹,

Gins²

2015

Chemometrics and Intelligent Laboratory Systems

View full text Add to dashboard Cite

show abstract

“…Dimensionality reduction is a first possible pretreatment step. Monroy et al [20] reduced the data of each batch to a score vector using PCA or ICA and use the resulting scores as input for the classifier. To train the PCA or ICA model, Monroy et al [20] generated artificial data sets containing an equal number of normal and faulty batches.…”

Section: Data Selection and Pretreatmentmentioning

confidence: 99%

“…The aforementioned methods [16][17][18][19][20] are essentially offline diagnosis methods since the classifier is trained on entire faulty batches, not faulty episodes. Hence, before fault classification, the new (faulty) batch needs to be completed or its future variable trajectories estimated.…”

Section: Introductionmentioning

confidence: 99%

“…Li and Cui [19] further reduced the need for pseudo-batch generation. Recently, Support Vector Machines (SVMs) were utilized as a learning algorithm for fault classification of batch processes [20]. SVMs are based on statistical learning theory developed by Vapnik [21] and have shown to exhibit a large generalization performance, especially when the number of training samples is small [22].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving classification-based diagnosis of batch processes through data selection and appropriate pretreatment

Gins

Kerkhof

Vanlaer

et al. 2015

Journal of Process Control

View full text Add to dashboard Cite

a b s t r a c tThis work considers the application of classification algorithms for data-driven fault diagnosis of batch processes. A novel data selection methodology is proposed which enables online classification of detected disturbances without requiring the estimation of unknown (future) process behavior, as is the case in previously reported approaches.The proposed method is benchmarked in two case studies using the Pensim process model of Birol et al. (2002) implemented in RAYMOND. Both a simple k Nearest Neighbors (k-NN) and complex Least Squares Support Vector Machine (LS-SVM) are employed for classification to demonstrate the generic nature of the proposed approach. In addition, the influence of different data pretreatment methods on the classification performance is discussed, together with a motivation for selecting the correct pretreatment steps. Finally, the influence of the number of available training batches is studied.The results demonstrate that a good classification performance can be achieved with the proposed data selection method even with a low number of faulty training batches by exploiting knowledge on the nature of the to-be-diagnosed faults in the data pretreatment. This provides a proof of concept for classification-based batch diagnosis and demonstrates the importance of incorporating process insight in the construction of data-driven process monitoring and diagnosis tools.

show abstract

“…In this order, FD outcomes are arranged in a validation confusion matrix (Monroy, Villez, Graells, & Venkatasubramanian, 2012) presented in Table 1. …”

Section: Key Performance Indicatorsmentioning

confidence: 99%

Data-based fault detection in chemical processes: Managing records with operator intervention and uncertain labels

Askarian

Benítez

Graells

et al. 2016

Expert Systems with Applications

Self Cite

View full text Add to dashboard Cite

Developing data-driven fault detection systems for chemical plants requires managing uncertain data labels and dynamic attributes due to operator-process interactions.Mislabeled data is a known problem in computer science that has received scarce attention from the process systems community. This work introduces and examines the effects of operator actions in records and labels, and the consequences in the development of detection models. Using a state space model, this work proposes an iterative relabeling scheme for retraining classifiers that continuously refines dynamic attributes and labels.Three case studies are presented: a reactor as a motivating example, flooding in a simulated de-Butanizer column, as a complex case, and foaming in an absorber as an industrial challenge. For the first case, detection accuracy is shown to increase by 14% while operating costs are reduced by 20%. Moreover, regarding the de-Butanizer column, the performance of the proposed strategy is shown to be 10% higher than the filtering strategy. Promising results are finally reported in regard of efficient strategies to deal with the presented problem.

show abstract

Fault diagnosis of a benchmark fermentation process: a comparative study of feature extraction and classification techniques

Cited by 22 publications

References 45 publications

An extensive reference dataset for fault detection and identification in batch processes

An extensive reference dataset for fault detection and identification in batch processes

Improving classification-based diagnosis of batch processes through data selection and appropriate pretreatment

Data-based fault detection in chemical processes: Managing records with operator intervention and uncertain labels

Contact Info

Product

Resources

About