Methods, internet of things (IoT) systems, and mediums for pipeline repair based on smart gas

Patent metadata

Field	Value
Publication number	US-12499418-B2
Application number	US-202519008585-A
Country	US
Kind code	B2
Filing date	Jan 2, 2025
Priority date	Oct 28, 2024
Publication date	Dec 16, 2025
Grant date	Dec 16, 2025

Abstract

Embodiments of the present disclosure provide a method, an Internet of Things (IoT) system, and a medium for pipeline repair based on smart gas. The method is executed based on a government supervision and management platform of the IoT system for pipeline repair based on smart gas. The method includes: obtaining pipeline repair equipment information and pipeline data to be repaired; determining a pipeline repair sequence based on the pipeline repair equipment information and the pipeline data to be repaired; based on the repair commands, performing at least one of the following operations: receiving feedback information; determining an updated collection frequency for a pressure regulating equipment and a gas metering device deployed on a target gas pipeline based on the feedback information; and generating a repair update command based on the pipeline data to be repaired, a pressure regulating parameter, a gas supply parameter, and a monitoring data.

First claim

What is claimed is:

1 . A method for pipeline repair based on smart gas, performed by a government supervision and management platform of an Internet of Things (IoT) system for pipeline repair based on smart gas, the IoT system including a citizen user platform, a government supervision service platform, the government supervision and management platform, a gas company management platform and a gas equipment object platform, and the method comprising:
obtaining pipeline repair equipment information and pipeline data to be repaired through the gas company management platform; determining a pipeline repair sequence based on the pipeline repair equipment information and the pipeline data to be repaired, wherein
the pipeline repair sequence includes a plurality of repair commands,
each of the plurality of repair commands is performed by at least one target pipeline repair equipment,
the target pipeline repair equipment is a pipeline repair equipment that performs repair for at least one target repair pipeline,
the pipeline repair equipment includes a pipeline filling machine, a pipeline internal coating equipment, a trenchless pipeline repair equipment, a pipeline rapid repair kit, and an endoscopic inspection equipment, and
each of the plurality of repair commands includes the at least one target repair pipeline and repair parameters corresponding to the at least one target repair pipeline;
based on the repair commands, performing at least one of the following operations:
receiving feedback information captured by the citizen user platform through the government supervision service platform;
determining an updated collection frequency for a pressure regulating equipment and a gas metering device deployed on a target gas pipeline based on the feedback information, and sending the updated collection frequency to the pressure regulating equipment and the gas metering device to control the pressure regulating equipment and the gas metering device to perform collection;
obtaining a pressure regulating parameter during a repair process captured by the pressure regulating equipment and a gas supply parameter during the repair process captured by the gas metering device;
obtaining monitoring data captured by monitoring components deployed on remaining target repair pipelines through the gas company management platform;
determining a pipeline map to be repaired based on the pipeline data to be repaired, wherein
each of nodes of the pipeline map to be repaired correspond to a pipeline to be repaired, and
a node attribute includes a fault type, a location, a length of the pipeline to be repaired, a pipeline operation parameter captured at a preset time period, a total number of gas residents in a surrounding area and downstream of the pipeline to be repaired, and a historical gas usage of downstream gas residents;

determining a repair urgency for each pipeline to be repaired based on the pipeline map to be repaired by a repair prediction model, the repair prediction model being a machine learning model;
determining an updated repair urgency of the remaining target repair pipelines based on the pipeline map to be repaired, the pressure regulating parameter, the gas supply parameter, the monitoring data, and the repair urgency for each pipeline to be repaired by a repair update model, the repair update model being a machine learning model, wherein
the repair prediction model and the repair update model is obtained by a joint training process,
parameters of the repair prediction model and the repair update model are updated simultaneously at each iteration,
wherein the joint training process includes:
noting a training sample corresponding to the repair prediction model as a first training sample, and noting a training label corresponding to the first training sample as a first training label, wherein
the first training sample includes a historical sample pipeline map to be repaired,
there exist a plurality of historical sample pipelines to be repaired on the historical sample pipeline map to be repaired, and
the first training label includes a plurality of first sub-training labels, each of the first sub-training labels corresponding to a historical sample pipeline to be repaired;

noting a training sample corresponding to the repair update model as a second training sample, and noting a training label corresponding to the second training sample as a second training label, wherein
the second training sample includes the historical sample pipeline map to be repaired,
a plurality of remaining historical sample target repair pipelines exist on the historical sample pipeline map to be repaired, and
the second training label includes a plurality of second sub-training labels, each of the second sub-training labels corresponds to one of the plurality of remaining historical sample target repair pipelines;

noting a difference between a result obtained by a prediction of the repair prediction model and the first training label as a first loss term, the first loss term including a plurality of first sub-loss terms, each of the plurality of first sub-loss terms corresponding to a difference between a predicted value of the repair urgency of the pipeline to be repaired and the corresponding first sub-training label;
noting a difference between the result obtained by the prediction of the repair update model and the second training label as a second loss term, the second loss term including a plurality of second sub-loss terms, each of the plurality of second sub-loss terms corresponding to a difference between a predicted value of the updated repair urgency and the corresponding second sub-training label, the predicted value of the updated repair urgency corresponding to the remaining target repair pipeline;
obtaining a loss function value based on a weighted sum of the first loss term and the second loss term, wherein
the first loss term corresponds to a first weight,
the first weight includes a plurality of first sub-weights, and each of the plurality of first sub-weights corresponds to one of the plurality of first sub-loss terms,
the plurality of first sub-weights are determined based on a fault type corresponding to the historical sample pipeline to be repaired,
the second loss term corresponds to a second weight,
the second weight includes a plurality of second sub-weights, and each of the plurality of second sub-weights corresponds to one of the plurality of second sub-loss terms, and
the plurality of second sub-weights are determined based on a fault type of the remaining historical sample target repair pipeline; and
generating a repair update command of the remaining target repair pipelines based on the updated repair urgency, wherein the repair update command is used to control and update the repair commands that have not yet been executed in the pipeline repair sequence to determine a reasonable pipeline repair sequence for repairing the gas pipeline, repair a malfunctioning gas pipeline, and ensure a gas supply demand of citizen users.

2 . The method of claim 1 , wherein the IoT system further includes a government supervision sensor network platform, a government supervision object platform, and a gas company sensor network platform;
the government supervision service platform includes a citizen cloud service sub-platform and a government safety supervision service sub-platform, the government supervision and management platform includes a government gas management sub-platform and a government safety management sub-platform, and the government supervision sensor network platform includes a government gas management sensor network sub-platform and a government safety management sensor network sub-platform, the government supervision object platform including the gas company management platform; the citizen user platform is configured to int

Assignees

• Chengdu Qinchuan Iot Tech Co Ltd

Inventors

• Shao Zehua
• Li Yong
• Wei Xiaojun
• Wang Feng
• Zhou Junyan

Classifications

• G06Q50/26

  Government or public services (business processes related to the transportation industry G06Q50/40) · CPC title

• G06Q50/06 Primary

  Energy or water supply · CPC title

• G06Q10/20 Primary

  Administration of product repair or maintenance · CPC title

• F17D5/005 Primary

  of gas pipelines, e.g. alarm · CPC title