A decision support tool for bi-objective risk-based maintenance scheduling of an LNG gas sweetening unit
Bibliographic record
Abstract
Purpose The purpose of this paper is to develop a decision support tool for risk-based maintenance scheduling for a large heavily equipped gas sweetening unit in a Liquefied Natural Gas (LNG) plant. Two conflicting objectives, i.e., total maintenance cost and the reliability, are considered in the tool. The tool is tested with the real plant data and suggests several Pareto-optimal schedules for a decision maker to choose from. The financial impacts are assessed. Design/methodology/approach A bi-objective scheduling optimization model is developed for maintenance scheduling using a risk-based framework. The model is developed integrating genetic algorithm and simulation-based optimization to find Pareto-optimal schedules. The model delivered true Pareto front optimal solutions for given plant-specific data. The two conflicting objectives: the minimization of total expenditures incurred on maintenance-related activities and improving the total reliability are considered. Findings For large and complex processing facilities such as LNG plant, a shutdown of facility generates a significant financial impact, resulting in millions of dollars in production loss. The developed risk-based equipment selection strategy helps to minimize such an event of production loss by generating a thorough maintenance strategy for inspection, repair, overhaul or replacement schedule of the unit without initiating the shutdown. The proposed model has been successfully applied to obtain an optimize maintenance schedule for a gas sweetening unit. Research limitations/implications A future work may consider the state-dependent models for various failure modes that will result in obtaining a better representation of the model. The proposed scheduling can further be extended to multi-criteria scheduling including availability, resource limitation and inflationary condition. A comparative analysis with other meta-heuristic techniques such as harmony search algorithm, tabu search, and simulated annealing will further help in confirming the schedule obtained from this application. Practical implications Maintenance scheduling using a conventional approach for special equipment generally does not consider the conflicting objectives. This research addresses this aspect using a bi-objective model. The usefulness of risk-based method is to assist in minimizing the financial and safety risk exposure to the operating companies, but some variation in results is expected due to varying risk matrix for different organizations. Social implications Managing two objectives, i.e., minimizing the cost of maintenance-related activities, while at the same time maximizing the overall reliability dramatically, helps in mitigating adverse safety and financial risk due to fires, explosions, fatality and excessive maintenance cost. Originality/value Research develops a decision support tool for managing conflicting objectives for an LNG process. This research highlights the impact of utilizing the simulation-based approach coupled with risk-based equipment selection for complex processing unit or plant maintenance scheduling optimization.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".