Kriging based Fault Detection and Diagnosis Approach for Nonlinear Noisy Dynamic Processes

Shokry, Ahmed; Ardakani, Mohammad Hamed; Escudero, Gerard; Graells, Moisès; Espuña, Antonio

doi:10.1016/b978-0-444-63428-3.50014-x

Cited by 5 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is defined by the following relation: The polarization index represents the rate of moisture absorption by the insulation. It is defined as the ratio of the insulation resistance measured at 10 minutes to the insulation resistance measured at 1 minute [15][16][17][18][19][20][21].…”

Section: Ris (Min) = 506 ωmentioning

confidence: 99%

Diagnosis and Protection of Alternators Against Mass Faults

Ali¹,

Allal²,

Mahi³

2020

MMC_B

View full text Add to dashboard Cite

Generator protection system is one of the complicated industrial systems incorporating many group elements; measurement transformer, relays, circuit breakers and wiring connectors. Generally, protection systems are described using four characteristics; dependability, Sensitivity, rapidity and selectivity. The stator earth fault is a relatively common type of fault. The generators normally have grounded high impedance, that is to say, a ground via a neutral point resistor. This resistance is normally dimensioned to give a ground fault current of the order of 5 to 15 A in the event of permanent earth fault in high voltage terminals of the alternator. Relatively low ground fault currents cause. The new protection technique, it is called an intermittent defect, this type of defect usually has the following characteristics, A very short earth current pulse of high intensity (up to several hundred amps), lasting less than 1 ms. It occurs / disappears automatically over half a period, possibly over several periods, depending on the state of the power grid and the characteristics of the fault. Over longer periods (from several seconds to several minutes), it can evolve into a permanent fault.

show abstract

Section: Ris (Min) = 506 ωmentioning

confidence: 99%

Diagnosis and Protection of Alternators Against Mass Faults

Ali¹,

Allal²,

Mahi³

2020

MMC_B

View full text Add to dashboard Cite

show abstract

“…However, accurate and reliable FPMs of chemical processes are often unobtainable, especially for complex highly nonlinear ones (Jain et al, 2007;Jin et al, 2015;Shokry et al, 2014): in many cases, the details required to build the models needed to describe such processes are limited, because of the involved highly nonlinear behaviors, sophisticated mechanisms and complex phenomena as reaction kinetics, thermodynamics etc. (Shokry et al, 2016;Shokry et al, 2017a). Even more, the existing FPMs of many processes have been developed under the assumption of the most favorable/ideal experimental and laboratory conditions, which make them sensitive to parameter variations, uncontrolled disturbances and distinct reactors geometries (Kadlec et al, 2009;Jin et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

“…Ordinary Kriging has shown outperforming characteristics, as high prediction accuracy with relatively small number of training data, and relatively high tuning flexibility . The use of OK metamodels was introduced to the chemical process engineering area by Davis and Ierapetritou (2007), and Caballero and Grossmann (2008), and since that time it is gaining growing interest mainly for surrogate based optimization and analysis of complex nonlinear chemical systems (Shokry et al, 2014;Quirante et al, 2015;Rogers & Ierapetritou, 2015), and later on for multivariate dynamic modelling (Shokry et al, 2016;Shokry & Espuña, 2017a). However, the use of OK metamodels -as a specific implantation/formulation of Gaussian Process models -has never been introduced to the area of the soft-sensing of batch chemical processes yet.…”

Section: Introductionmentioning

confidence: 99%

Data-driven soft-sensors for online monitoring of batch processes with different initial conditions

Shokry

Vicente

Escudero

et al. 2018

Computers & Chemical Engineering

Self Cite

View full text Add to dashboard Cite

A soft-sensing methodology applicable to batch processes operated under changeable initial conditions is presented. These cases appear when the raw materials specifications differ from batch to batch, different production scenarios should be managed, etc. The proposal exploits the capabilities of the machine learning techniques to provide practical soft-sensing approach with minimum tuning effort in spite of the fact that the inherent dynamic behavior of batch systems are tracked through other online indirect measurements. Current data modelling techniques have been also tested within the proposed methodology to demonstrate its advantages. Two simulation casestudies and a pilot-plant case-study involving a complex batch process for wastewater treatment are used to illustrate the problem, to assess the modelling approach and to compare the modelling techniques. The results reflect a promising accuracy even when the training information is scarce, allowing significant reductions in the cost associated to batch processes monitoring and control.

show abstract