Process Schedule Reconciliation Using Algebraic Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current process scheduling techniques in the refining and petrochemical industries do not adequately address the reconciliation step, which is essential for determining accurate operational activities and future scheduling, due to noisy plant data and manual, iterative reconciliation processes that consume significant time and effort.
Innovation Solution
A computer-implemented system using machine learning and statistical approaches, combined with mathematical optimization algorithms, automatically reconciles schedules by processing current and projected plant data to identify event boundaries and stream flowrates, reducing the need for human intervention and improving the accuracy of schedule adjustments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual iterative reconciliation process is used, then schedulers can adjust schedules step-by-step evaluating simulated values against plant data, but the process consumes significant time and effort
Solution Approach 1:
The patent replaces the manual mechanical reconciliation process with an automated computer-implemented system that uses algebraic model optimization. The system automatically imports plant data, identifies event boundaries, calculates stream flowrates, and reconciles schedules without manual trial-and-error iterations, thereby maintaining accuracy while dramatically reducing time consumption.
Solution Approach 2:
The reconciliation system performs self-service by automatically importing plant data, identifying event boundaries, calculating flowrates, and adjusting schedules without requiring scheduler intervention. The system independently evaluates simulated values against actual plant data and generates reconciled schedules, freeing schedulers from this time-consuming task.
2Reliability
If manual reconciliation process is used, then schedulers can evaluate and adjust schedules iteratively, but substantial effort is required consuming significant fraction of working time
Solution Approach 1:
The patent replaces manual scheduler effort with an automated computer system that performs all reconciliation tasks. The system imports plant data, processes it through algebraic optimization models, and generates reconciled schedules automatically, maintaining reliability while significantly improving scheduler productivity by eliminating manual iterative adjustments.
Solution Approach 2:
The patent introduces an intermediary computer-implemented system that acts as a mediator between plant data and schedule adjustments. This intermediary automatically processes raw plant data, reconciles it with simulated values, and produces adjusted schedules, thereby improving productivity while maintaining the reliability needed for accurate scheduling decisions.
3Extent of automation
If automatic reconciliation system is implemented, then manual effort is reduced, but the system requires complex mathematical optimization algorithms
Solution Approach 1:
The patent extracts the complex mathematical optimization algorithms into a separate computer-implemented system that operates independently. The core reconciliation logic, event boundary identification, and flowrate calculations are encapsulated in automated software modules, allowing the system to achieve high automation while managing complexity through modular design and automated computation.
Data Source
AI summary
A computer-implemented method and system for process schedule reconciliation receives a scheduling model and an initial schedule for reconciliation, where the initial schedule includes projected plant data. Current plant data is imported into the system. The current plant data and projected plant data is processed using mathematical modeling techniques to identify event boundaries, stream flowrates associated with tanks and process units. The system builds an optimization model applying identified event boundaries, stream flowrates and pre-determined constraints along a period of time that includes priority slots to reconcile the projected plant data of the initial schedule with the current plant data, and then solves the optimization model to develop a reconciled schedule.