Artificial intelligence for monitoring and supervisory control of process systems

Uraikul, V.; Chan, Christine W.; Tontiwachwuthikul, Paitoon

doi:10.1016/j.engappai.2006.07.002

Cited by 177 publications

(68 citation statements)

References 107 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…32 There are three general solution approaches for supporting the tasks of monitoring, control, and diagnosis: (1) data driven, for which the most popular techniques are principal component analysis, Fisher discriminant analysis, and partial least-squares analysis; (2) analytical, an approach founded on first principles or other mathematical models; and (3) KB founded on AI, specifically expert systems, fuzzy logic, ML, and PR. 32,33 Due to the explosion of industrial big data, KB ISCSs have received great attention. Since the scale of the data generated from manufacturing systems cannot be efficiently managed by traditional process monitoring and quality control methods, a KB scheme might be an advantageous approach.…”

Section: Iscsmentioning

confidence: 99%

Machine learning techniques for quality control in high conformance manufacturing environment

Escobar

Morales-Menéndez

2018

Advances in Mechanical Engineering

109

View full text Add to dashboard Cite

In today's highly competitive global market, winning requires near-perfect quality. Although most mature organizations operate their processes at very low defects per million opportunities, customers expect completely defect-free products. Therefore, the prompt detection of rare quality events has become an issue of paramount importance and an opportunity for manufacturing companies to move quality standards forward. This article presents the learning process and pattern recognition strategy for a knowledge-based intelligent supervisory system, in which the main goal is the detection of rare quality events. Defect detection is formulated as a binary classification problem. The l 1 -regularized logistic regression is used as the learning algorithm for the classification task and to select the features that contain the most relevant information about the quality of the process. The proposed strategy is supported by the novelty of a hybrid feature elimination algorithm and optimal classification threshold search algorithm. According to experimental results, 100% of defects can be detected effectively.

show abstract

Section: Iscsmentioning

confidence: 99%

Machine learning techniques for quality control in high conformance manufacturing environment

Escobar

Morales-Menéndez

2018

Advances in Mechanical Engineering

109

View full text Add to dashboard Cite

show abstract

“…In this regard, Zhang and Morris [31] presented an excellent extension of the work using fuzzy neural network. A more recent work towards such knowledge based systems in process control and fault identification can be found in [32][33][34].…”

Section: Future Work and Directionsmentioning

confidence: 99%

An integrated qualitative trend analysis approach to identify process abnormalities: A case of oil export pumps in an offshore oil and gas production facility

Raza

Liyanage

2009

Proceedings of the Institution of Mechanical Engineers, Part E:

View full text Add to dashboard Cite

Abstract:Oil & gas production can be largely benefited by minimizing unwanted production losses. This can be done by effective identification of system anomalies and faults. In standard control systems these abnormalities can be observed as gradually deviating trends from the norms. Available tools for monitoring these trends, in some cases, may not be enough to reveal hidden faulty features. In order to interpret these changes accurately, measured data must be visualized as a combination of multiple sensor signals within a particular domain. This paper suggests an approach to effectively utilize integrated data from multiple sources, and defines a set of 12 fault features. The approach, in principle, encodes real plant data in the form of logical IF-THEN rules in Microsoft Excel. Confidence values are set based on these interpretations to differentiate between normal and abnormal conditions exhibited by the system. This is to provide an opportunity for the process and maintenance engineers to effectively identify the equipment"s health based on the early identification of developing abnormalities.

show abstract

“…The first class is based on a signal analysis [12,13] that uses spectra in a frequency domain, time domain, time-frequency domain, and high-order harmonics. The second approach is based on analytical modeling [14] that involves mathematical models to measure input and output feature such as residuals, state estimation, and parameter estimation that incorporate the artificial intelligence (AI) to online automate analyze the health of induction motor through measured signals [15]. In engineering the AI tools are of great significance to solve various complex problems [16,17].…”

Section: Introductionmentioning

confidence: 99%

Noninvasive Methods for Condition Monitoring and Electrical Fault Diagnosis of Induction Motors

Sheikh¹,

Nor²,

Ibrahim³

et al. 2017

Fault Diagnosis and Detection

View full text Add to dashboard Cite

This chapter provides a comprehensive analysis of noninvasive methods to diagnose stator winding insulation faults of an induction motor. Further, a novel noninvasive method is proposed to diagnose the root cause of winding failure due to unbalanced voltage to avoid catastrophic failure. Therefore, a winding function approach is utilized to derive an analytical expression for stator winding distribution and magnetomotive force (MMF). This tactic qualifies the conductor segment that generates MMF, and it also helps to analyze a healthy current spectrum. One can easily observe higher order harmonics in current spectrum; therefore, a new series of rotor harmonics is introduced to diagnose unbalanced supply. The locus of these harmonics is dependent on the poles, rotor bars, and slip. Due to the rapid complexity in industrial plants, it is inconceivable to continue human inspection to diagnose the faults. Thus, to avoid human inspection, in addition to new series of rotor harmonic, a fully automatic method based on neural network is proposed. This method not only diagnoses unbalanced voltage but it also recognize the percentage of unbalanced voltage by use of feed-forward multilayer perceptron (MLP) trained by back propagation. Finally, the experimental results shows the validation of this research work proposed method.

show abstract

Artificial intelligence for monitoring and supervisory control of process systems

Cited by 177 publications

References 107 publications

Machine learning techniques for quality control in high conformance manufacturing environment

Machine learning techniques for quality control in high conformance manufacturing environment

An integrated qualitative trend analysis approach to identify process abnormalities: A case of oil export pumps in an offshore oil and gas production facility

Noninvasive Methods for Condition Monitoring and Electrical Fault Diagnosis of Induction Motors

Contact Info

Product

Resources

About