Multi-batch liquid long-distance pipeline scheduling method, equipment and storage medium

By using pressure drop estimator and neural network optimization scheduling model in liquid fuel long-distance long-distance pipeline systems, the problems of low accuracy and potential risks in the prior art are solved, and more efficient energy saving and consumption reduction effects are achieved.

CN118761183BActive Publication Date: 2025-03-18HUAZHONG UNIV OF SCI & TECH
2 Cites 0 Cited by

Patent Information

Application Number
CN202410949671.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-16
Publication Date
2025-03-18
Estimated Expiration
2044-07-16

AI Technical Summary

Technical Problem

The existing long-distance long-distance liquid fuel pipeline systems have problems of low accuracy and potential risks in energy saving and consumption reduction, mainly because the model lacks accuracy when dealing with pressure drop parameters, and key components such as outbound pressure reducing valves are ignored.

Method used

A multi-batch liquid long-distance long-distance pipeline scheduling method is proposed. By obtaining the technical parameters and real-time operating status of each component of the pipeline system, the pressure drop estimator is used to predict the pressure drop of the pipeline, and the neural network is trained in combination with the particle swarm algorithm and the Levenberg-Marquardt algorithm to establish an optimized scheduling model to minimize the total power consumption of the system.

Benefits of technology

It improves the accuracy of the pipeline system regulation model, reduces potential risks, improves the energy saving effect of the system, and optimizes the energy efficiency of the system through event-triggered scheduling.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The present invention belongs to the technical field related to energy optimization, and discloses a method, device and storage medium for scheduling long-distance pipelines of multiple batches of liquids. The method includes: using a pressure drop estimator to predict the pipeline pressure drop and performing interpolation processing to obtain the pipeline pressure drop at the start and end of the time step to be optimized; establishing an optimization scheduling model, the objective function is to minimize the total power consumption of all main pumps in the system, and the constraints include: pipeline pressure safety constraints, main pump safety operation constraints, outbound pressure reducing valve safety operation constraints and component coupling relationship constraints; in the pipeline pressure safety constraints, the pressure difference at the beginning and end of the pipeline at the same time is equal to the pipeline pressure drop calculated based on the pressure drop estimator; solving the scheduling model to obtain a control strategy. The present invention combines the pressure drop estimator with the scheduling model to make the scheduling model more accurate, ensure the reliability of scheduling, and reduce potential risks while improving the energy saving of the pipeline system.
Need to check novelty before this filing date? Find Prior Art