Data reconciliation and gross error detection in crude oil pre-heat trains undergoing shell-side and tube-side fouling deposition

Loyola-Fuentes, José; Smith, Robin

doi:10.1016/j.energy.2019.06.119

Cited by 26 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With respect to (a), missing values, sensor failure and gross errors are expected to reduce the performance of the ranking provided by relief, and, therefore, affect the identification of the critical components. In such situations, missing data imputation [30] and reconciliation techniques [31] can be used to enhance data quality. With respect to (b), the main criticality is that data collected when the CTI is in a failed state, which, given the high reliability of CTIs, can be insufficient for analysis.…”

Section: Discussionmentioning

confidence: 99%

“…It is worth mentioning that with respect to the quality of the monitoring data collected from industrial systems, the performance of the classification method could be reduced by: (i) missing measurements resulting from the failure to collect or store signal values at few time instances [30] and (ii) gross errors due to sensor faults, such as freezing, drifting and miscalibration [31,32]. To address these problems, missing data imputation and data reconciliation methods have been developed and successfully applied for improving the quality of the data collected from industrial systems.…”

Section: Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Identification of Critical Components in the Complex Technical Infrastructure of the Large Hadron Collider Using Relief Feature Ranking and Support Vector Machines

et al. 2021

View full text Add to dashboard Cite

This work proposes a data-driven methodology for identifying critical components in Complex Technical Infrastructures (CTIs), for which the functional logic and/or the system structure functions are not known due the CTI’s complexity and evolving nature. The methodology uses large amounts of CTI monitoring data acquired over long periods of time and under different operating conditions. The critical components are identified as those for which the condition monitoring signals permit the optimal classification of the CTI functioning or failed state. The methodology includes two stages: in the first stage, a feature selection filter method based on the Relief technique is used to rank the monitoring signals according to their importance with respect to the CTI functioning or failed state; the second stage identifies the subset of signals among those highlighted by the Relief technique that are most informative with respect to the CTI state. This identification is performed on the basis of evaluating the performance of a Cost-Sensitive Support Vector Machine (CS-SVM) classifier trained with several subsets of the candidate signals. The capabilities of the methodology proposed are assessed through its application to different benchmarks of highly imbalanced datasets, showing performances that are competitive to those obtained by other methods presented in the literature. The methodology is finally applied to the monitoring signals of the Large Hadron Collider (LHC) of the European Organization for Nuclear Research (CERN), a CTI for experiments of physics; the criticality of the identified components has been confirmed by CERN experts.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Problem Statementmentioning

confidence: 99%

Identification of Critical Components in the Complex Technical Infrastructure of the Large Hadron Collider Using Relief Feature Ranking and Support Vector Machines

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The threshold model was originally developed for crude oil streams flowing in the tube-side. 17,18 Loyola-Fuentes and Smith 42,43 suggested the use of linear fouling for wax deposits, which is not amenable for threshold modeling as it does not exhibit finite longterm behavior. However, Diaz-Bejarano et al 44 proposed the utilization of a threshold model for the modeling of the fouling rate in the shell-side.…”

Section: Shell-side Fouling Modelmentioning

confidence: 99%

Design of shell and tube heat exchangers considering the interaction of fouling and hydraulics

2022

View full text Add to dashboard Cite

We extend a formulation of the heat exchanger design optimization with fouling modeling to consider the effect of fouling on hydraulics. A shell-side fouling model was added so the optimization can consider cases with fouling in the tube and shell sides. The focus is the design of heat exchangers with fouling behavior associated with a threshold model, like in crude preheat trains. We solve the optimization problem by using a newly proposed Set Trimming technique. We compare our results with the traditional approach of using fixed fouling factors and the previous approach of not considering the hydraulic impact of fouling. We conclude that considering the deposit thickness leads to more realistic results that are different than the ones obtained using the previous approaches. Moreover, we show that previous approaches can render designs with larger pressure drops than the maximum imposed by the constraints, as well as exchangers with higher areas.

show abstract

“…Therefore, a constant fouling model, eq 15, is used to represent the deposition of waxes that occurs on both shell side and tube side, whereas the chemical reaction fouling tends to occur due to the nature of the crude oil. 21 Even though the linear assumption for shell-side deposition is simpler than the actual fouling behavior, it is an acceptable approximation when it is not the dominant resistance to heat transfer. The wellestablished Polley et al 27 model, eq 16, is used to represent the chemical reaction fouling deposition which is considered predominantly in the side where the crude oil flows.…”

Section: ■ Introductionmentioning

confidence: 99%

“…On the other hand, the calculations related to the shell-side fouling are very complex. Loyola-Fuentes and Smith used a data reconciliation method to estimate fouling models for both shell and tube sides undergoing different fouling mechanisms. Costa et al have shown that a parameter estimation problem may be a workable option for conclusive fouling models.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Flow Rate Distribution in a Crude Oil Preheat Train Considering Fouling Deposition in Shell and Tube Sides

Carvalho

Ravagnani

2022

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

The deposition of an undesired material on the heat transfer surfaces is a recurrent problem that affects the overall performance of heat exchanger networks (HENs). A wide variety of empirical and semiempirical models are available for predicting the fouling behavior. In this work, there are considered different predominant fouling mechanisms at each side of the shell and tube heat exchangers used to preheat crude oil from a refinery. Adopting the mass flow rates at the parallel branches of the HEN as optimization variables, an optimization model is proposed to find the minimum total annual cost for 12 months of uninterrupted operation. The model was coded in MATLAB and solved using a simulated annealing algorithm. The results showed that fouling accumulation in both heat exchanger sides significantly impacted the heat recovery and increased operating costs. The proposed methodology was able to decrease the total annual cost in $4.6516 × 10 4 when compared to the base case.

show abstract

Data reconciliation and gross error detection in crude oil pre-heat trains undergoing shell-side and tube-side fouling deposition

Cited by 26 publications

References 33 publications

Identification of Critical Components in the Complex Technical Infrastructure of the Large Hadron Collider Using Relief Feature Ranking and Support Vector Machines

Identification of Critical Components in the Complex Technical Infrastructure of the Large Hadron Collider Using Relief Feature Ranking and Support Vector Machines

Design of shell and tube heat exchangers considering the interaction of fouling and hydraulics

Optimization of Flow Rate Distribution in a Crude Oil Preheat Train Considering Fouling Deposition in Shell and Tube Sides

Contact Info

Product

Resources

About