Condition Monitoring using Machine Learning: A Review of Theory, Applications, and Recent Advances

Surucu, Onur; Gadsden, S. Andrew; Yawney, John

doi:10.1016/j.eswa.2023.119738

Cited by 44 publications

(4 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advances in the field of machine learning continuously motivate novel methods for data-driven process monitoring. [8][9][10] With the help of kernel function mapping, the aforementioned typical linear algorithms such as PCA, ICA, and PLS can be easily extended to model the nonlinear characteristics of a given dataset. [11][12][13] Because of the salient nonlinear feature extraction capability, artificial neural network models such as auto-encoder, 14,15 convolutional neural network, 16 and longshort-term memory neural network, 17 have also demonstrated their powerful ability to fault detection.…”

Section: Introductionmentioning

confidence: 99%

“…Different from first‐principle‐model‐based methods that generate residuals to indicate a fault, 7 data‐driven process monitoring approaches mainly focus on modeling normal variation in a dataset given from the NOC. The advances in the field of machine learning continuously motivate novel methods for data‐driven process monitoring 8–10 . With the help of kernel function mapping, the aforementioned typical linear algorithms such as PCA, ICA, and PLS can be easily extended to model the nonlinear characteristics of a given dataset 11–13 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Distributed statistical process monitoring based on block‐wise residual generator

Tong,

Zhou,

Qian

et al. 2023

Journal of Chemometrics

View full text Add to dashboard Cite

The increasing scale of modern chemical plants keeps popularizing investigation as well as application of distributed process monitoring approaches. With a goal of directly quantifying the normal relations between different blocks divided from the whole process, a novel multi‐block modeling strategy called block‐wise residual generator is proposed, which trains a residual generator for each block through using the partial least squares algorithm with single one output, so that the relation between the corresponding block and the others is quantified as a regression model in a block‐wise manner. The deviations caused by the abnormal samples to the normal relations quantified for different blocks could thus be efficiently captured by the residuals generated from the block regression models, which then provide sensitive information for fault detection and contribution‐based fault diagnosis. Moreover, the proposed method is applicable for both disjoint and overlapped block divisions, and the direct consideration of individually quantifying relations between different blocks can always guarantee its salient monitoring performance, as validated through comparisons with classical distributed process monitoring methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Distributed statistical process monitoring based on block‐wise residual generator

Tong,

Zhou,

Qian

et al. 2023

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…The solid requirement of production safety and sustainable operation keeps motivating novel approaches for effectively monitoring the operating condition of modern industrial processes 1–4 . Nowadays, the great achievements in Industry 4.0 have been popularizing wider application of data‐driven process monitoring techniques 3–5 .…”

Section: Introductionmentioning

confidence: 99%

Just‐in‐time latent autoregressive residual generation for dynamic process monitoring

Hu,

Chang

2023

Journal of Chemometrics

View full text Add to dashboard Cite

With a goal of timely and adaptively exploiting the inconsistency inherited in the monitored samples of current interest, a novel dynamic process monitoring method based on just‐in‐time latent autoregressive residual generation (JITLAR2G) model is proposed. Different from the mainstream dynamic modeling and monitoring methods which usually train a signature generating mechanism and then repeatedly apply it for online monitored samples, the proposed JITLAR2G‐based approach provides a JITLAR2G model for the online monitored samples after data augmentation, so that the corresponding inconsistency within the given consecutive samples could be timely and adaptively uncovered. Instead of expressing the time‐serial relationship that generally accepted by the normal samples in the given dataset, solving the objective function designed for JITLAR2G in a just‐in‐time manner can adaptively and correspondingly seek but only one projecting vector as well as coefficient vector to generate residual, which points to the potential inconsistency inherited in the monitored samples, for the sole purpose of fault detection. As demonstrated through comparisons, the proposed JITLAR2G model can consistently guarantee its effectiveness, in terms of reducing both false alarm rate and missed alarm rate, for dynamic process monitoring, the salient performance achieved by the proposed JITLAR2G‐based method in contrast to the counterparts can be always confirmed.

show abstract

“…The basic model is a linear classifier and a nonlinear classifier can also be obtained by kernel methods [2], which can be used for regression analysis and classifying the data. SVM is now widely used in many fields [3][4][5], can improve the performance of classification and fully embodies the essence of statistical learning theory. However, TBSVM uses L 2 -norm as the loss function.…”

Section: Introductionmentioning

confidence: 99%

Twin Bounded Support Vector Machine with Capped Pinball Loss

Wang,

Hong,

Zhang

2023

Preprint

View full text Add to dashboard Cite

In this paper, we propose a novel classifier termed as twin bounded support vector machine with capped pinball loss (CPin-TBSVM), which has the excellent properties of being insensitive to noise. Given that the proposed model is non-convex, we use the convex-concave procedure algorithm (CCCP) to solve a series of two smaller-sized quadratic programming problems to find the optimal solution. In the process of solving the iterative sub-problem, the dual coordinate descent method (DCDM) is used for speeding up solving optimization problems. Moreover, we analyze its theoretical properties, including that the capped pinball loss satisfies Bayes’ rule and CPin-TBSVM has certain noise insensitivity and sparsity. The properties are verified on an artificial dataset as well. The numerical experiment is conducted on 24 UCI datasets and the results are compared with four other models which include SVM, TSVM, Pin-GTSVM and TPin-TSVM. The results show that the proposed CPin-TBSVM has a better classification effect and noise insensitivity.

show abstract

Condition Monitoring using Machine Learning: A Review of Theory, Applications, and Recent Advances

Cited by 44 publications

References 101 publications

Distributed statistical process monitoring based on block‐wise residual generator

Distributed statistical process monitoring based on block‐wise residual generator

Just‐in‐time latent autoregressive residual generation for dynamic process monitoring

Twin Bounded Support Vector Machine with Capped Pinball Loss

Contact Info

Product

Resources

About