Operation and maintenance decision optimization method based on pipeline network dynamic analysis

By using multi-dimensional data collection and dynamic analysis models, the problem of inaccurate fault diagnosis in the operation and maintenance of heating pipe networks has been solved, achieving precise operation and maintenance and improving the operational stability and economy of heating pipe networks.

CN123118069APending Publication Date: 2026-11-17TIBET LONGSHENG ENERGY MANAGEMENT CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202611312087.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-08-27
Publication Date
2026-11-17

AI Technical Summary

Technical Problem

The operation and maintenance decisions of the existing heating network rely on manual inspections and basic data collection, which fail to effectively consider environmental factors and component aging rates, resulting in inaccurate fault diagnosis and an inability to meet the needs of refined operation and maintenance under complex operating conditions.

Method used

By collecting, preprocessing, dynamically analyzing, and iteratively optimizing data in a closed loop, a comprehensive dataset of pipeline network operating conditions is constructed. Combined with the installation location of components and environmental influences, a dynamic analysis model of operating conditions is built to achieve accurate fault point identification and optimized operation and maintenance decisions.

Benefits of technology

It enables accurate prediction and proactive protection against faults, reduces the frequency of faults, improves the stability and efficiency of pipeline operation and maintenance, and reduces operation and maintenance costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN123118069A_ABST
    Figure CN123118069A_ABST
Patent Text Reader

Abstract

This invention discloses an operation and maintenance decision optimization method based on dynamic analysis of pipeline network operating conditions, including the following steps: S1, Multi-dimensional data acquisition: collecting basic operation data, component installation location data, environmental status data, and current environment data of the heating pipeline network; This invention overcomes the limitations of existing technologies in acquiring single basic data by collecting basic operation data, component installation location data, environmental status data, and current environment data of the pipeline network. Combining the operating characteristics of components at different installation locations and incorporating influencing factors such as water accumulation, environmental corrosion, and stray current, a multi-dimensional dynamic analysis model of operating conditions is constructed. This model can comprehensively and accurately characterize the operating status and hidden deterioration trends of various components in the pipeline network, while providing reliable data support for subsequent operation and maintenance decisions; it achieves early fault prediction and proactive protection, reduces the frequency of fault occurrence, and improves the stability of pipeline network operation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This invention belongs to the field of pipeline operation and maintenance technology, specifically relating to an optimization method for operation and maintenance decisions based on dynamic analysis of pipeline operating conditions. Background Technology

[0002] In centralized heating systems, the heating pipeline network serves as the core carrier for heat transmission and distribution. Its operational stability directly determines the heating quality for end users and is also related to the energy efficiency, safety, and economy of the heating system. With the extension of the service life of heating pipeline networks and the expansion of network coverage due to urban development, the operating conditions of the networks are becoming increasingly complex. Various faults (such as pipeline leaks, valve jamming, compensator failure, and corrosion perforation) occur frequently, not only causing significant heat waste and increased maintenance costs but also potentially affecting residents' normal heating and triggering user complaints. Therefore, optimizing operation and maintenance decisions based on pipeline condition analysis is particularly important.

[0003] Current operational and maintenance decisions for heating networks primarily rely on manual inspections combined with the collection and monitoring of basic operational data such as water pressure and temperature within the network. By analyzing abnormal fluctuations in this data, fault location, prediction, and maintenance planning are achieved. However, this traditional approach to operational condition analysis and decision-making fails to consider the impact of environmental factors on component operating conditions, aging rates, and failure probabilities. This leads to significant biases in operational condition analysis results and inaccurate fault diagnosis, failing to meet the demands for refined and precise operation and maintenance of heating networks under complex conditions. Summary of the Invention

[0004] The purpose of this invention is to provide an operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions, so as to solve the problems in the prior art mentioned in the background.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions includes the following steps:

[0007] S1. Multi-dimensional Data Acquisition: This involves collecting basic operational data, component installation location data, environmental status data, and current environment data for the heating network. The basic operational data includes time-series data on water pressure, water temperature, and flow rate within the network. The component installation location data includes the installation type of each component, categorized into four types: open-air installation, buried installation, well installation, and trench installation. The environmental status data includes water accumulation and environmental corrosion parameters in the installation areas of each component. The current environment data includes stray current parameters and pipe-to-ground potential offset values ​​in the installation areas of each component.

[0008] S2. Multi-dimensional data preprocessing: Standardize, denoise, and perform spatiotemporal registration on the multi-dimensional data collected in step S1 to construct a comprehensive dataset of pipeline network operating conditions; among them, classify the water accumulation data into levels, quantify and calibrate the environmental corrosion parameters, classify stray current parameters and pipe-to-ground potential offset values ​​according to the degree of interference, and establish basic data correction coefficients corresponding to different installation types in combination with the differences in installation location types.

[0009] S3. Dynamic analysis and anomaly judgment of operating conditions: Based on the comprehensive dataset of pipeline operating conditions obtained in step S2, and combined with the operating characteristics of components of different installation types, the influence of water accumulation and environmental corrosion on component aging, and the stray current corrosion mechanism, a dynamic analysis model of operating conditions is constructed. The dynamic analysis model of operating conditions, combined with the correction coefficient of basic operating data, dynamically evaluates the operating conditions of each component of the pipeline network, accurately judges the location of the fault point, the fault type and the fault development trend, and predicts the aging rate and failure risk of each component.

[0010] S4. Operation and Maintenance Decision Optimization Generation: Based on the dynamic analysis results of the working conditions in step S3, and combined with the construction difficulty of each component installation location, the cost of water accumulation and environmental corrosion control, and the cost of stray current protection, a multi-objective operation and maintenance decision optimization model is constructed to output the optimal operation and maintenance decisions for inspection priority, maintenance plan, protection measures, and component replacement cycle.

[0011] S5. Closed-loop iterative optimization: Collect pipeline operating condition data, fault recurrence rate and protection effect data after the execution of operation and maintenance decisions, and iteratively optimize the parameters of the dynamic analysis model of operating conditions in step S3 and the basic data correction coefficients in step S2 to achieve continuous optimization of operation and maintenance decisions and adapt to the dynamic changes of pipeline operating status and environmental conditions.

[0012] Preferably, in step S1, the environmental corrosion parameters include soil corrosion level, soil moisture, soil resistivity, pipeline corrosion rate, and the degree of damage to the pipeline's outer anti-corrosion layer. For buried and trench-installed components, soil potential difference data is additionally collected, and for open-air-installed components, atmospheric corrosion level data is additionally collected. The stray current parameters include soil potential gradient and stray current intensity. The pipe-to-ground potential offset value is divided into three levels according to the positive offset amplitude: weak interference, medium interference, and strong interference.

[0013] Preferably, in step S1, the water accumulation status is supplemented by the water level sensor in the well, the humidity sensor in the trench, and manual inspection, and is divided into four levels: no water accumulation, slight water accumulation, moderate water accumulation, and severe water accumulation. Among them, the components installed in the well and the components installed in the trench focus on collecting the duration of water accumulation and the water quality parameters, which are used to evaluate the impact of water accumulation on the corrosion and sealing performance of the components.

[0014] Preferably, in step S2, the method for determining the basic data correction coefficient is as follows: for the four types of installation—open-air installation, buried installation, in-well installation, and trench installation—the method combines the environmental corrosion level, water accumulation level, and stray current interference level, and dynamically assigns values ​​using the analytic hierarchy process combined with the entropy weight method. The stray current correction coefficient for buried installation components has a weight ratio of not less than 25%, and the water accumulation correction coefficient for in-well and trench installation components has a weight ratio of not less than 30%.

[0015] Preferably, in step S3, the dynamic analysis model of the working condition integrates the LSTM time series algorithm and the random forest algorithm. The LSTM time series algorithm is used to analyze the time series change trend of basic operating data and current environment data, while the random forest algorithm is used to integrate multiple factors such as installation location, water accumulation, and environmental corrosion to achieve fault judgment and failure risk prediction.

[0016] Preferably, in step S3, the fault types include pipeline leakage, valve jamming, compensator failure, and pipeline corrosion perforation. Leakage faults are determined by combining water pressure change data, water accumulation data, and environmental corrosion data, while corrosion perforation faults are determined by combining corrosion rate, stray current parameters, and pipe-to-ground potential offset values.

[0017] Preferably, in step S4, the constraints of the multi-objective operation and maintenance decision optimization model include the scope of fault impact, operation and maintenance cost, construction difficulty, and impact on user heating. For buried installation components, stray current protection measures and trenchless maintenance schemes are given priority; for components installed in wells and trenches, water accumulation control and anti-corrosion treatment are given priority.

[0018] Preferably, in step S4, the protective measures include cathodic protection measures for buried installation components, anti-corrosion coating reinforcement measures for open-air installation components, water drainage and sealing protection measures for installation components in wells and trenches, and drainage protection measures for stray current interference areas.

[0019] Preferably, in step S5, the closed-loop iterative optimization cycle is 1-3 months. After each iteration, the fault judgment accuracy is improved by no less than 8%, and the comprehensive benefits of operation and maintenance decisions (fault reduction rate and cost reduction rate) are improved by no less than 10%.

[0020] Preferably, in step S1, the components of the pipeline network include pipes, valves, compensators, supports, and thermal inlet devices. Each component is bound to a unique installation location identifier, environmental parameter acquisition node, and current environment monitoring point, so as to realize a one-to-one correspondence between the component and multi-dimensional data.

[0021] Technical effects and advantages of the present invention: The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions proposed in this invention has the following advantages compared with the prior art:

[0022] This invention overcomes the limitations of existing technologies that rely on a single basic data source by collecting basic pipeline network operation data, component installation location data, environmental status data, and current environment data. By combining the operating characteristics of components at different installation locations with influencing factors such as water accumulation, environmental corrosion, and stray currents, a multi-dimensional dynamic analysis model of operating conditions is constructed. This model can comprehensively and accurately characterize the operating status and hidden deterioration trends of various pipeline network components, while providing reliable data support for subsequent operation and maintenance decisions. It also enables early fault prediction and proactive protection, reduces the frequency of fault occurrence, and improves the operational stability of the pipeline network. Attached Figure Description

[0023] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] This invention provides, for example Figure 1 The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions, as shown, includes the following steps:

[0026] Step S1: Multi-dimensional data collection

[0027] At the main pipes, branch pipes, heat inlets, and installation locations of various components in the heating network, corresponding data acquisition devices are deployed to simultaneously collect four types of data, as detailed below:

[0028] 1. Basic operating data: Time-series data of water pressure, water temperature and flow rate in the pipeline network are collected through pressure sensors, temperature sensors and flow sensors. The collection frequency is once every 5 minutes and the data is stored in the time-series database.

[0029] 2. Component installation location data: Through the GIS geographic information system, the installation type and specific location of each component of the pipeline network are entered, and each component is labeled as an open-air installation, buried installation, in-manhole installation or trench installation, and a unique identifier is bound to achieve a one-to-one correspondence between components and data;

[0030] 3. Environmental Status Data: Water accumulation is collected using in-well water level sensors and trench humidity sensors, categorized into four levels: no water accumulation, slight water accumulation, moderate water accumulation, and severe water accumulation. The duration of water accumulation and water quality parameters are recorded simultaneously. Soil corrosion level, soil moisture, soil resistivity, pipeline corrosion rate, and atmospheric corrosion level are collected using soil corrosion sensors and atmospheric corrosion monitors. For buried and trench-installed components, soil potential difference is additionally collected, while for open-air installed components, atmospheric corrosion data is the primary focus.

[0031] 4. Current environment data: Stray current intensity, soil potential gradient and pipe-to-ground potential offset value of each component installation area are collected by stray current monitor and pipe-to-ground potential tester. The interference is divided into three levels: weak interference, medium interference and strong interference.

[0032] Step S2: Multidimensional data preprocessing

[0033] The multi-dimensional data collected in step S1 is preprocessed. First, a filtering algorithm is used to remove data noise and outliers. Then, the data of different dimensions are standardized to unify the data units. Finally, spatiotemporal registration is performed to ensure that the data of the same component are consistent in time and space.

[0034] For the four installation types, and considering the environmental corrosion level, water accumulation level, and stray current interference level, the analytic hierarchy process (AHP) combined with the entropy weighting method is used to dynamically assign correction coefficients to the basic data: stray current correction coefficient weight 0.28 for buried installation components, soil corrosion correction coefficient weight 0.22; water accumulation correction coefficient weight 0.32 for in-well and trench installation components, corrosion correction coefficient weight 0.20; atmospheric corrosion correction coefficient weight 0.30 for open-air installation components, temperature fluctuation correction coefficient weight 0.25, used for accurate calibration in subsequent working condition analysis.

[0035] Step S3: Dynamic Analysis of Operating Conditions and Anomaly Judgment

[0036] Based on the preprocessed comprehensive dataset of pipeline network operating conditions, a dynamic analysis model integrating LSTM time series algorithm and random forest algorithm is constructed: LSTM time series algorithm is used to analyze the time series variation trend of stray current parameters such as water pressure, water temperature, and flow rate, and capture parameter mutation characteristics; random forest algorithm is used to integrate multiple factors such as installation location, water accumulation, and environmental corrosion, and combined with the correction coefficient of basic data to dynamically evaluate the operating conditions of each component.

[0037] This model accurately identifies the location and type of fault (pipeline leakage, valve jamming, compensator failure, corrosion perforation, etc.). Leakage faults are determined by combining sudden changes in water pressure, water accumulation data, and corrosion data. Corrosion perforation faults are determined by combining corrosion rate, stray current parameters, and pipe-to-ground potential offset. At the same time, it predicts the aging rate and failure risk of each component and automatically triggers early warnings for extremely high-risk components.

[0038] Step S4: Optimization and Generation of Operation and Maintenance Decisions

[0039] Based on the dynamic analysis results of step S3, a multi-objective operation and maintenance decision optimization model is constructed. Combining the construction difficulty of each component's installation location, the cost of controlling water accumulation and environmental corrosion, and the cost of stray current protection, the optimal operation and maintenance decision is output:

[0040] 1. Inspection priority: Components in areas with extremely high risk, severe water accumulation in the well, and strong stray current interference should be inspected first, with an inspection cycle of once a week; components in areas with medium to low risk, no water accumulation, and weak interference should be inspected once a month.

[0041] 2. Repair plan: Corrosion perforation of buried pipelines will be repaired using a trenchless repair plan; rust on valves installed in wells and trenches will be repaired using a rust removal and seal replacement plan; and anti-corrosion coating reinforcement will be used for components installed in the open air.

[0042] 3. Protective measures: For buried installation components, cathodic protection and stray current drainage devices shall be deployed; for installation components installed in wells and trenches, water drainage devices and sealing protection shall be added; and for outdoor installation components, anti-corrosion coatings shall be sprayed regularly.

[0043] 4. Component replacement cycle: Based on the aging rate prediction, pipes and compensators with severe corrosion and less than 2 years remaining service life will be included in the replacement plan for the next quarter.

[0044] Step S5: Closed-loop iterative optimization

[0045] After the operation and maintenance decision is implemented, pipeline operating condition data, fault recurrence rate and protection effect data are continuously collected. Every two months is a closed-loop iteration cycle. The algorithm parameters of the dynamic analysis model of operating conditions and the basic data correction coefficient in step S2 are adjusted in reverse. The fault judgment accuracy of the optimized model is improved to more than 95%, and the comprehensive benefits of operation and maintenance decision are improved by more than 12%, ensuring that the method can adapt to the dynamic changes of pipeline operating status and environmental conditions.

[0046] This embodiment effectively solves the shortcomings of existing technologies that only collect basic water pressure and water temperature data without considering installation location, water accumulation, environmental corrosion, and current environment. It achieves precise and proactive operation and maintenance of heating pipe networks, reduces the frequency of faults, lowers operation and maintenance costs, and extends the service life of pipe network components. This verifies the feasibility, practicality, and significant beneficial effects of the method of this invention.

[0047] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for optimizing operation and maintenance decisions based on dynamic analysis of pipeline network conditions, characterized in that, Includes the following steps: S1. Multi-dimensional Data Acquisition: This involves collecting basic operational data, component installation location data, environmental status data, and current environment data for the heating network. The basic operational data includes time-series data on water pressure, water temperature, and flow rate within the network. The component installation location data includes the installation type of each component, categorized into four types: open-air installation, buried installation, well installation, and trench installation. The environmental status data includes water accumulation and environmental corrosion parameters in the installation areas of each component. The current environment data includes stray current parameters and pipe-to-ground potential offset values ​​in the installation areas of each component. S2. Multi-dimensional data preprocessing: Standardize, denoise, and perform spatiotemporal registration on the multi-dimensional data collected in step S1 to construct a comprehensive dataset of pipeline network operating conditions; among them, classify the water accumulation data into levels, quantify and calibrate the environmental corrosion parameters, classify stray current parameters and pipe-to-ground potential offset values ​​according to the degree of interference, and establish basic data correction coefficients corresponding to different installation types in combination with the differences in installation location types. S3. Dynamic analysis and anomaly judgment of operating conditions: Based on the comprehensive dataset of pipeline operating conditions obtained in step S2, and combined with the operating characteristics of components of different installation types, the influence of water accumulation and environmental corrosion on component aging, and the stray current corrosion mechanism, a dynamic analysis model of operating conditions is constructed. The dynamic analysis model of operating conditions, combined with the correction coefficient of basic operating data, dynamically evaluates the operating conditions of each component of the pipeline network, accurately judges the location of the fault point, the fault type and the fault development trend, and predicts the aging rate and failure risk of each component. S4. Operation and maintenance decision optimization generation: Based on the dynamic analysis results of the working conditions in step S3, combined with the construction difficulty of each component installation location, the cost of water accumulation and environmental corrosion control, and the cost of stray current protection, a multi-objective operation and maintenance decision optimization model is constructed to output the optimal operation and maintenance decisions for inspection priority, maintenance plan, protection measures, and component replacement cycle. S5. Closed-loop iterative optimization: Collect pipeline operating condition data, fault recurrence rate and protection effect data after the execution of operation and maintenance decisions, and iteratively optimize the parameters of the dynamic analysis model of operating conditions in step S3 and the basic data correction coefficients in step S2 to achieve continuous optimization of operation and maintenance decisions and adapt to the dynamic changes of pipeline operating status and environmental conditions.

2. The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions according to claim 1, characterized in that, In step S1, the environmental corrosion parameters include soil corrosion level, soil moisture, soil resistivity, pipeline corrosion rate, and the degree of damage to the pipeline's outer anti-corrosion layer. For buried and trench-installed components, soil potential difference data is additionally collected, and for open-air installed components, atmospheric corrosion level data is additionally collected. The stray current parameters include soil potential gradient and stray current intensity. The pipe-to-ground potential offset value is divided into three levels: weak interference, medium interference, and strong interference, based on the positive offset amplitude.

3. The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions according to claim 1, characterized in that, In step S1, the water accumulation status is collected through the water level sensor in the well, the humidity sensor in the trench, and manual inspection. It is divided into four levels: no water accumulation, slight water accumulation, moderate water accumulation, and severe water accumulation. Among them, the water accumulation duration and water quality parameters of the components installed in the well and in the trench are collected in particular to assess the impact of water accumulation on the corrosion and sealing performance of the components.

4. The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions according to claim 1, characterized in that, In step S2, the method for determining the basic data correction coefficient is as follows: for the four types of installation, namely open-air installation, buried installation, in-well installation and trench installation, the analytic hierarchy process (AHP) combined with the entropy weight method is used to dynamically assign values ​​based on the environmental corrosion level, water accumulation level and stray current interference level. The stray current correction coefficient of buried installation components has a weight ratio of not less than 25%, and the water accumulation correction coefficient of in-well and trench installation components has a weight ratio of not less than 30%.

5. The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions according to claim 1, characterized in that, In step S3, the dynamic analysis model of the working condition integrates the LSTM time series algorithm and the random forest algorithm. The LSTM time series algorithm is used to analyze the time series change trend of basic operating data and current environment data, while the random forest algorithm is used to integrate multiple factors such as installation location, water accumulation, and environmental corrosion to achieve fault judgment and failure risk prediction.

6. The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions according to claim 1, characterized in that, In step S3, the fault types include pipeline leakage, valve jamming, compensator failure, and pipeline corrosion perforation. Leakage faults are determined by combining water pressure change data, water accumulation data, and environmental corrosion data. Corrosion perforation faults are determined by combining corrosion rate, stray current parameters, and pipe-to-ground potential offset values.

7. The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions according to claim 1, characterized in that, In step S4, the constraints of the multi-objective operation and maintenance decision optimization model include the scope of fault impact, operation and maintenance cost, construction difficulty, and impact on user heating. For buried installation components, stray current protection measures and trenchless maintenance schemes are given priority; for components installed in wells and trenches, water accumulation control and anti-corrosion treatment are given priority.

8. The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions according to claim 1, characterized in that, In step S4, the protective measures include cathodic protection measures for buried installation components, anti-corrosion coating reinforcement measures for open-air installation components, water drainage and sealing protection measures for installation components in wells and trenches, and drainage protection measures for stray current interference areas.

9. The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions according to claim 1, characterized in that, In step S5, the closed-loop iterative optimization cycle is 1-3 months. After each iteration, the fault judgment accuracy is improved by no less than 8%, and the comprehensive benefits of operation and maintenance decisions (fault reduction rate and cost reduction rate) are improved by no less than 10%.

10. The operation and maintenance decision optimization method based on dynamic analysis of pipeline network conditions according to claim 1, characterized in that, In step S1, the components of the pipeline network include pipes, valves, compensators, supports, and thermal inlet devices. Each component is bound to a unique installation location identifier, environmental parameter acquisition node, and current environment monitoring point, so as to realize a one-to-one correspondence between the component and multi-dimensional data.