Real-time detection method and device for pressure data abnormity of heat supply network pipeline

Abstract

The invention discloses a real-time detection method for abnormal pressure data of a heat supply network pipeline, and the method comprises the steps: building a full-life-cycle management system of the heat supply network pipeline, carrying out the risk recognition and evaluation, and analyzing a key position where the risk of the heat supply network pipeline is liable to occur after a risk evaluation report of the whole heat supply network pipeline is formed; according to the difference between the real-time pressure data and the simulated pressure data of the key positions and the important nodes and the difference between the real-time pressure data and the pressure data predicted value, a pressure data comprehensive deviation value is obtained, and meanwhile the pressure data abnormal threshold range of each key position and each important node is configured; and the heat supply network pipeline carries out early warning based on the pressure data comprehensive deviation value and the configured pressure data abnormal threshold range, the abnormal condition of the heat supply network pipeline is displayed, and pressure abnormal positions and nodes are identified.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart heating systems, and specifically relates to a real-time detection method and device for abnormal pressure data of a heating network pipeline. Background Art

[0002] At present, the digital transformation has realized the comprehensive collection, real-time transmission and intelligent analysis of the monitoring data of the heat network pipeline, greatly improving the efficiency and accuracy of operation and maintenance management. At the same time, this transformation has also promoted the innovation of the operation and maintenance mode of the heat network pipeline, realizing the transition from passive response to active prevention, and providing a more solid guarantee for the safe operation of the heat network pipeline.

[0003] In the monitoring data of the heating network pipeline, online monitoring of the heating network pipeline pressure is one of the important means to ensure the safe and stable operation of the heating network. By monitoring the heating network pipeline pressure in real time through the pressure acquisition device, abnormal conditions can be discovered in time, preventive and emergency measures can be taken, and the risk of accidents can be minimized. However, the current heating network pipeline structure is complex and large in scale. It is difficult and costly to lay too many pressure acquisition devices, and the layout of the pressure acquisition device directly affects the pressure data detection effect of the heating network pipeline. In addition, the accurate analysis of abnormal pressure data plays a vital role in quickly locating the abnormal position of the heating network pipeline. Therefore, how to effectively distinguish which key positions and important nodes of the heating network pipeline are prone to risks, and accurately collect pressure data and detect abnormalities at these positions and nodes, and identify abnormal pressure data, is an urgent problem to be solved.

[0004] Based on the above technical problems, it is necessary to design a new real-time detection method for abnormal pressure data of heating network pipelines. Summary of the invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a real-time detection method for abnormal pressure data of a heating network pipeline, find out the pipelines with high risk levels as key positions where risks are prone to occur, and install pressure collection devices to monitor pressure data in real time, so as to ensure effective management of these key positions and reduce the possibility of accidents; in addition, heating network pipelines are usually complex in structure and large in number. By knowing the key positions where risks are prone to occur, the number and cost of laying pressure collection devices can also be reduced, and abnormal pressure data can be detected in time, and the positions and nodes where abnormalities occur can be identified to ensure the safe and stable operation of the heating network pipelines.

[0006] In order to solve the above technical problems, the technical solution of the present invention is:

[0007] The present invention provides a real-time detection method for abnormal pressure data of a heat network pipeline, which comprises:

[0008] S1. Based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, establish a full life cycle management system for the heat network pipeline, conduct risk identification and assessment, form a risk assessment report for the entire heat network pipeline, and analyze the key locations where risks are prone to occur in the heat network pipeline;

[0009] S2. Lay pressure collection devices at key locations where risks are prone to occur in the heat network pipeline and at important nodes of the heat network pipeline to obtain real-time pressure data at key locations and important nodes of the heat network pipeline;

[0010] S3. Based on the mechanism model and data model of the heat network pipeline, a digital twin model of the heat network pipeline is established, and online simulation deduction is performed under normal operating conditions to obtain simulated pressure data of key positions and important nodes; and based on the multi-dimensional factors affecting pipeline pressure under normal operating conditions of the heat network pipeline, a heat network pipeline pressure prediction model is constructed to output the predicted values ​​of pressure data of key positions and important nodes of the heat network pipeline;

[0011] S4. Obtain the comprehensive deviation value of the pressure data based on the difference between the real-time pressure data and the simulated pressure data at the key locations and important nodes, and the difference between the real-time pressure data and the predicted value of the pressure data, and configure the abnormal threshold range of the pressure data at each key location and important node;

[0012] S5. The heat network pipeline issues an early warning based on the comprehensive deviation value of the pressure data and the configured pressure data abnormal threshold range, displays the abnormal situation of the heat network pipeline, and identifies the abnormal pressure location and nodes.

[0013] Furthermore, in S1, a full life cycle management system for the heat network pipeline is established based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, including:

[0014] Obtain environmental data of heat network pipelines, including: geographic information, soil type, burial depth, and ground elevation;

[0015] Obtain basic attribute data of heat network pipelines, including: pipeline distance, pipe diameter, wall thickness, pipeline material, installation date, pipeline custom ID number, and pipeline structure layout;

[0016] Obtain maintenance data of heating network pipelines, including maintenance records, inspection results, and pipeline component replacement records;

[0017] Obtain historical operation data of the heat network pipeline, including supply and return water pressure, supply and return water temperature, and flow data under various operating conditions;

[0018] Based on the environmental data and basic attribute data of the heat network pipeline, a heat network pipeline construction period management database is established;

[0019] Establish a heat network pipeline operation management database based on the heat network pipeline maintenance data and historical operation data;

[0020] Based on the construction and operation management data of the heat network pipelines, a heat network pipeline scrapping management database is established, including the evaluation of pipelines that have reached the end of their service life, determining whether to continue to use or replace them, and the reasonable treatment of some pipelines that have been decided to be scrapped;

[0021] A full life cycle management system for heat network pipelines is established based on the heat network pipeline construction period management database, operation period management database and scrapping period management database.

[0022] Furthermore, in S1, after risk identification and assessment are performed to form a risk assessment report for the entire heat network pipeline, key locations where risks are prone to occur in the heat network pipeline are analyzed, including:

[0023] Based on the data in the full life cycle management system of the heat network pipeline, the damage pattern of the heat network pipeline is identified to determine whether the heat network pipeline is damaged; the pipeline damage pattern includes erosion corrosion, intermittent use fatigue, corrosion under insulation layer, and cracking due to original manufacturing defects;

[0024] Based on the data and damage patterns in the full life cycle management system of the heat network pipeline, a pipeline life prediction model is established to obtain pipeline life prediction results;

[0025] According to the damage mode of the heat network pipeline and the prediction results of the pipeline life, a pipeline risk assessment model is established, and each risk assessment result is dynamically updated and the risk level is ranked to form a risk assessment report for the entire heat network pipeline; the risk levels include low risk, medium risk, medium-high risk and high risk;

[0026] After emergency maintenance is carried out on the heating network pipelines at high risk, the risk level will be changed from high risk to medium-high risk and medium risk, and the medium-risk and medium-high risk heating network pipelines will be identified as key locations prone to risks.

[0027] Furthermore, in S2, the important nodes of the heat network pipeline include the pipeline inlet, outlet, branch point, and the vicinity of the valve.

[0028] Furthermore, in S3, a digital twin model of the heat network pipeline is established based on the mechanism model and data model of the heat network pipeline, and online simulation deduction is performed under normal operating conditions to obtain simulated pressure data of key positions and important nodes, including:

[0029] Obtain the relevant data of heat network pipeline modeling according to the full life cycle management system of the heat network pipeline, and establish the geometric model of the heat network pipeline based on the basic attribute data and environmental data of the heat network pipeline;

[0030] Using the heat transfer and fluid flow theory of the heat network pipeline and adding boundary condition constraints, the physical mechanism model of the heat network pipeline is established;

[0031] Based on the dynamic response of the heat network pipeline under different loads and different ambient temperature changes and the control principle of the heat network pipeline equipment components, the behavior mechanism model of the heat network pipeline is constructed;

[0032] According to the safe operation rules of the heat network pipeline and the change rules of pipeline operation data under different working conditions, the rule mechanism model of the heat network pipeline is constructed;

[0033] The geometric model, physical mechanism model, behavior mechanism model and rule mechanism model of the heat network pipeline are integrated to construct the mechanism model of the heat network pipeline;

[0034] Use the collected actual operation data to establish the data model of the heat network pipeline;

[0035] The mechanism model and data model of the heat network pipeline are integrated to establish a digital twin model of the heat network pipeline;

[0036] The pipeline simulation parameters under normal operating conditions are input into the digital twin model of the heat network pipeline, and the initial conditions of the pipeline that are suitable for the pipeline equipment adjustment strategy are set. After online simulation and deduction, the simulated pressure data of key positions and important nodes of the heat network pipeline are obtained.

[0037] Further, in S3, based on the multi-dimensional factors affecting the pipeline pressure under normal operation of the heat network pipeline, a heat network pipeline pressure prediction model is constructed to output the pressure data prediction values ​​of each key position and important node of the heat network pipeline, including:

[0038] Obtain multi-dimensional time series data that affects pipeline pressure under normal operating conditions of the heat network pipeline, including historical operation data, environmental data, and basic pipeline attribute data;

[0039] The multidimensional time series data is input into the ResNet-BiLSTM network. After the ResNet network is used to extract the features of the multidimensional time series data that affect the pipeline pressure, the extracted features are input into the BiLSTM network for training and learning, and a heat network pipeline pressure prediction model is constructed to output the pressure data prediction values ​​of each key position and important node of the heat network pipeline.

[0040] Furthermore, the ResNet-BiLSTM network structure includes two residual blocks ResNet1 and ResNet2, a BiLSTM unit and a fully connected layer;

[0041] Among them, an attention-based layer is added after the BiLSTM unit to calculate the attention weights of each feature at different times and rank the importance of different features.

[0042] Furthermore, in S4, based on the difference between the real-time pressure data and the simulated pressure data at the key positions and important nodes, and the difference between the real-time pressure data and the predicted pressure data, the following methods are included:

[0043] Get the real-time pressure data of key locations and important nodes at a preset time in the future, defined as X i,t , represents the real-time pressure data of the i-th pipeline point at the t-th moment;

[0044] Based on the digital twin model of the heat network pipeline, the actual operation status of the pipeline is simulated online to obtain the simulated pressure data of key locations and important nodes at a preset time in the future, which is defined as Represents the simulated pressure data of the i-th pipeline point at the t-th time;

[0045] Based on the heat network pipeline pressure prediction model, the pressure data prediction values ​​of key locations and important nodes of the heat network pipeline at the preset time in the future are output, which is defined as It represents the predicted value of pressure data at the i-th pipeline point at the t-th moment;

[0046] Calculate real-time pressure data X i,t With simulated pressure data The difference between

[0047] Calculate real-time pressure data X i,t Predicted value with pressure data The difference between

[0048] The difference δ i,t , Perform fusion calculation to obtain the comprehensive deviation value δ i ' ,t ; The fusion calculation includes weighted average calculation and weighted calculation;

[0049] Among them, the weighted average calculation comprehensive deviation value is expressed as:

[0050]

[0051] The weighted calculation comprehensive deviation value is expressed as:

[0052]

[0053] w 1 is the difference δ i,t The weight coefficient of 2 For the difference The weight coefficient of .

[0054] Further, S5 includes: when the comprehensive deviation value of the pressure data of the heating network pipeline exceeds the configured pressure data abnormal threshold range, an early warning is issued indicating that the pressure data is abnormal, and the abnormal situation of the heating network pipeline is highlighted, and the corresponding pipeline position or node of the heating network pipeline is screened and identified to have abnormal operating conditions.

[0055] The present invention also provides a real-time detection device for abnormal pressure data of a heat network pipeline, comprising:

[0056] The risk identification and assessment module is used to establish a full life cycle management system for the heat network pipeline based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, conduct risk identification and assessment, form a risk assessment report for the entire heat network pipeline, and analyze the key locations where risks are prone to occur in the heat network pipeline;

[0057] The real-time data acquisition module is used to lay pressure acquisition devices at key locations where risks are prone to occur in the heat network pipeline and at important nodes of the heat network pipeline to obtain real-time pressure data at key locations and important nodes of the heat network pipeline;

[0058] The simulation data acquisition module is used to establish a digital twin model of the heat network pipeline based on the mechanism model and data model of the heat network pipeline, and to perform online simulation deduction under normal operating conditions to obtain simulated pressure data at key locations and important nodes;

[0059] The prediction data acquisition module is used to construct a heat network pipeline pressure prediction model based on the multi-dimensional factors that affect the pipeline pressure under normal operating conditions of the heat network pipeline, and output the pressure data prediction values ​​of each key position and important node of the heat network pipeline;

[0060] A deviation calculation module is used to obtain a comprehensive deviation value of pressure data based on the difference between the real-time pressure data and the simulated pressure data at key locations and important nodes, and the difference between the real-time pressure data and the predicted value of the pressure data;

[0061] The anomaly identification module is used to issue early warnings for the heat network pipeline based on the comprehensive deviation value of pressure data and the configured abnormal threshold range of pressure data at each key position and important node, display the abnormal situation of the heat network pipeline, and identify the abnormal pressure positions and nodes.

[0062] The beneficial effects of the present invention are:

[0063] (1) The present invention establishes a full life cycle management system for the heat network pipeline based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, conducts risk identification and assessment, forms a risk assessment report for the entire heat network pipeline, and then analyzes the key positions of the heat network pipeline where risks are prone to occur; lays pressure collection devices at the key positions of the heat network pipeline where risks are prone to occur and at the important nodes of the heat network pipeline, and obtains real-time pressure data of each key position and important node of the heat network pipeline; can manage the heat network pipeline throughout its life cycle, establish an equipment ledger for each pipeline, facilitate intuitive and clear knowledge of the attributes, current status and operating status of each pipeline, and conduct risk assessment considering multiple potential abnormal modes, find out pipelines with high risk levels as key positions prone to risks, and install pressure collection devices to monitor pressure data in real time, which can ensure effective management of these key positions and reduce the possibility of accidents; in addition, the heat network pipelines are usually complex in structure and large in number. By knowing the key positions prone to risks, the number and cost of laying pressure collection devices can also be reduced;

[0064] (2) The present invention establishes a digital twin model of the heat network pipeline based on the mechanism model and data model of the heat network pipeline, and performs online simulation under normal operating conditions to obtain simulated pressure data of key positions and important nodes; and, based on the multidimensional factors affecting the pipeline pressure under normal operating conditions of the heat network pipeline, constructs a heat network pipeline pressure prediction model, and outputs the predicted values ​​of pressure data of each key position and important node of the heat network pipeline; based on the difference between the real-time pressure data and the simulated pressure data of the key positions and important nodes, and the difference between the real-time pressure data and the predicted values ​​of the pressure data, obtains the comprehensive deviation value of the pressure data, and configures the abnormal threshold range of the pressure data of each key position and important node; the heat network pipeline is based on the comprehensive deviation value of the pressure data and the configured abnormal threshold range of the pressure data The digital twin model of the heating network pipeline is used to calculate the pressure data of the preset time period in the future under specific working conditions, so as to intuitively analyze the behavior of the heating network pipeline under different working conditions. Pressure data prediction refers to the use of machine learning algorithms to build a prediction model based on the data of the heating network pipeline to predict the pressure data of the preset time period in the future. Both can be used to assist the operation management and maintenance of the heating network pipeline, comprehensively consider the differences between the two, and dynamically configure the abnormal threshold range of pressure data at each key position and important node, so as to detect abnormal pressure data in time, identify the abnormal positions and nodes, and ensure the safe and stable operation of the heating network pipeline.

[0065] Other features and advantages will be described in the following description, and partly become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0066] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0068] Figure 1 This is a flow chart of a real-time detection method for abnormal pressure data of a heat network pipeline according to the present invention;

[0069] Figure 2 The present invention is a schematic diagram of a real-time detection device for abnormal pressure data of a heat network pipeline. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0071] Example 1

[0072] like Figure 1 As shown, this embodiment 1 provides a real-time detection method for abnormal pressure data of a heat network pipeline, which includes:

[0073] S1. Based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, establish a full life cycle management system for the heat network pipeline, conduct risk identification and assessment, form a risk assessment report for the entire heat network pipeline, and analyze the key locations where risks are prone to occur in the heat network pipeline;

[0074] S2. Lay pressure collection devices at key locations where risks are prone to occur in the heat network pipeline and at important nodes of the heat network pipeline to obtain real-time pressure data at key locations and important nodes of the heat network pipeline;

[0075] S3. Based on the mechanism model and data model of the heat network pipeline, a digital twin model of the heat network pipeline is established, and online simulation deduction is performed under normal operating conditions to obtain simulated pressure data of key positions and important nodes; and based on the multi-dimensional factors affecting pipeline pressure under normal operating conditions of the heat network pipeline, a heat network pipeline pressure prediction model is constructed to output the predicted values ​​of pressure data of key positions and important nodes of the heat network pipeline;

[0076] S4. Obtain the comprehensive deviation value of the pressure data based on the difference between the real-time pressure data and the simulated pressure data at the key locations and important nodes, and the difference between the real-time pressure data and the predicted value of the pressure data, and configure the abnormal threshold range of the pressure data at each key location and important node;

[0077] S5. The heat network pipeline issues an early warning based on the comprehensive deviation value of the pressure data and the configured pressure data abnormal threshold range, displays the abnormal situation of the heat network pipeline, and identifies the abnormal pressure location and nodes.

[0078] In actual applications, the pressure acquisition device usually uses a high-frequency dynamic pressure transmitter, which can quickly acquire sudden changes in pressure with high accuracy. In addition to laying and installing the pressure acquisition device on the pipeline, a data acquisition box for collecting pressure data is also required. The data acquisition box is powered by AC220. After entering the air switch, it provides power to the switching power supply. The switching power supply provides DC24V direct current to the acquisition module, pressure sensor, and gateway. After the acquisition module acquires the data from the pressure acquisition device, it provides the data to the gateway via the 485 interface and modbus protocol. The gateway supports wireless communication and transmits the data to the IoT platform via the MQTT protocol. The smart heating platform obtains the data from the IoT platform and analyzes the pressure. When pressure fluctuations occur, the smart heating platform issues an early warning.

[0079] In this embodiment, in S1, a full life cycle management system of the heat network pipeline is established based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, including:

[0080] Obtain environmental data of heat network pipelines, including: geographic information, soil type, burial depth, and ground elevation;

[0081] Obtain basic attribute data of heat network pipelines, including: pipeline distance, pipe diameter, wall thickness, pipeline material, installation date, pipeline custom ID number, and pipeline structure layout;

[0082] Obtain maintenance data of heating network pipelines, including maintenance records, inspection results, and pipeline component replacement records;

[0083] Obtain historical operation data of the heat network pipeline, including supply and return water pressure, supply and return water temperature, and flow data under various operating conditions;

[0084] Based on the environmental data and basic attribute data of the heat network pipeline, a heat network pipeline construction period management database is established;

[0085] Establish a heat network pipeline operation management database based on the heat network pipeline maintenance data and historical operation data;

[0086] Based on the construction and operation management data of the heat network pipelines, a heat network pipeline scrapping management database is established, including the evaluation of pipelines that have reached the end of their service life, determining whether to continue to use or replace them, and the reasonable treatment of some pipelines that have been decided to be scrapped;

[0087] A full life cycle management system for heat network pipelines is established based on the heat network pipeline construction period management database, operation period management database and scrapping period management database.

[0088] In this embodiment, in S1, after risk identification and assessment are performed to form a risk assessment report for the entire heat network pipeline, key locations where risks are prone to occur in the heat network pipeline are analyzed, including:

[0089] Based on the data in the full life cycle management system of the heat network pipeline, the damage pattern of the heat network pipeline is identified to determine whether the heat network pipeline is damaged; the pipeline damage pattern includes erosion corrosion, intermittent use fatigue, corrosion under insulation layer, and cracking due to original manufacturing defects;

[0090] Based on the data and damage patterns in the full life cycle management system of the heat network pipeline, a pipeline life prediction model is established to obtain pipeline life prediction results;

[0091] According to the damage mode of the heat network pipeline and the prediction results of the pipeline life, a pipeline risk assessment model is established, and each risk assessment result is dynamically updated and the risk level is ranked to form a risk assessment report for the entire heat network pipeline; the risk levels include low risk, medium risk, medium-high risk and high risk;

[0092] After emergency maintenance is carried out on the heating network pipelines at high risk, the risk level will be changed from high risk to medium-high risk and medium risk, and the medium-risk and medium-high risk heating network pipelines will be identified as key locations prone to risks.

[0093] In this embodiment, in S2, the important nodes of the heat network pipeline include the pipeline inlet, outlet, branch point, and the vicinity of the valve.

[0094] In this embodiment, in S3, a digital twin model of the heat network pipeline is established based on the mechanism model and data model of the heat network pipeline, and online simulation deduction is performed under normal operating conditions to obtain simulated pressure data of key positions and important nodes, including:

[0095] Obtain the relevant data of heat network pipeline modeling according to the full life cycle management system of the heat network pipeline, and establish the geometric model of the heat network pipeline based on the basic attribute data and environmental data of the heat network pipeline;

[0096] Using the heat transfer and fluid flow theory of the heat network pipeline and adding boundary condition constraints, the physical mechanism model of the heat network pipeline is established;

[0097] Based on the dynamic response of the heat network pipeline under different loads and different ambient temperature changes and the control principle of the heat network pipeline equipment components, the behavior mechanism model of the heat network pipeline is constructed;

[0098] According to the safe operation rules of the heat network pipeline and the change rules of pipeline operation data under different working conditions, the rule mechanism model of the heat network pipeline is constructed;

[0099] The geometric model, physical mechanism model, behavior mechanism model and rule mechanism model of the heat network pipeline are integrated to construct the mechanism model of the heat network pipeline;

[0100] Use the collected actual operation data to establish the data model of the heat network pipeline;

[0101] The mechanism model and data model of the heat network pipeline are integrated to establish a digital twin model of the heat network pipeline;

[0102] The pipeline simulation parameters under normal operating conditions are input into the digital twin model of the heat network pipeline, and the initial conditions of the pipeline that are suitable for the pipeline equipment adjustment strategy are set. After online simulation and deduction, the simulated pressure data of key positions and important nodes of the heat network pipeline are obtained.

[0103] It should be noted that building a digital twin model of the heat network pipeline requires comprehensive consideration of multiple aspects, including geometric models, physical models, behavioral models and rule models.

[0104] Geometry Model:

[0105] The geometric model describes the physical structure and layout of the heat network pipeline system, including the size, shape, direction of the pipeline and the location of each node. The main steps of building the geometric model include:

[0106] 1) Surveying and design: Obtain the size and location information of the pipeline through on-site measurement or drawing data;

[0107] 2) 3D model: Use computer-aided design software to draw a 3D model of the pipeline;

[0108] 3) Geometry parameterization: parameterize the key geometry of the pipeline so that it can be adjusted in the subsequent simulation and optimization process;

[0109] Physical Model:

[0110] The physical model mainly deals with the heat transfer and fluid flow phenomena in the heating network piping system. This includes the mathematical description of processes such as convection, heat conduction, and radiation. The steps to build a physical model include:

[0111] 1) Thermodynamic model: Establish a heat exchange model of the medium in the pipeline based on thermodynamic principles;

[0112] 2) Fluid mechanics model: Use the fluid mechanics equations (such as the Navier-Stokes equations) to simulate the flow of fluid in the pipe;

[0113] 3) Boundary conditions: Determine the temperature, pressure and other boundary conditions of the inlet, outlet and other important nodes of the heat network pipeline;

[0114] 4) Numerical solution: numerical methods (such as finite element method, finite volume method, etc.) are used to solve the partial differential equations of the above model;

[0115] Behavioral Model:

[0116] The behavioral model focuses on the dynamic response of the heat network pipeline system under different working conditions. It not only takes into account the physical characteristics, but also the influence of external factors, such as load changes, ambient temperature changes, etc. The steps to build a behavioral model include:

[0117] 1) Load model: simulates the impact of changes in heat user demand on the heat network;

[0118] 2) Control system model: describes the working principle of the heating network control system, such as valve opening, pump speed, etc.;

[0119] 3) Dynamic simulation: Use numerical simulation methods to simulate the behavior of the heating network under different operating conditions;

[0120] Rule Model:

[0121] The rule model is mainly a series of rules based on empirical rules, operating procedures, and safety standards. These rules ensure the safe operation of the heat network pipeline and meet regulatory requirements. The steps to build a rule model include:

[0122] 1) Safety standards: Ensure that all designs and operations comply with relevant safety standards and specifications;

[0123] 2) Operating procedures: Develop detailed operating procedures for startup, shutdown and emergency situations;

[0124] 3) Fault detection: Define fault detection and diagnosis rules to promptly detect and handle potential problems.

[0125] In this embodiment, in S3, based on the multi-dimensional factors affecting the pipeline pressure under normal operation of the heat network pipeline, a heat network pipeline pressure prediction model is constructed to output the predicted values ​​of pressure data at key locations and important nodes of the heat network pipeline, including:

[0126] Obtain multi-dimensional time series data that affects pipeline pressure under normal operating conditions of the heat network pipeline, including historical operation data, environmental data, and basic pipeline attribute data;

[0127] The multidimensional time series data is input into the ResNet-BiLSTM network. After the ResNet network is used to extract the features of the multidimensional time series data that affect the pipeline pressure, the extracted features are input into the BiLSTM network for training and learning, and a heat network pipeline pressure prediction model is constructed to output the pressure data prediction values ​​of each key position and important node of the heat network pipeline.

[0128] It should be noted that the pressure value of the heating network pipeline has a certain relationship with environmental factors. Although the main purpose of the heating network is to transport heat through the pipeline system, environmental factors will affect the operating status of the heating network and thus affect the pressure value. The following is an explanation of how some environmental factors affect the pressure of the heating network:

[0129] 1. Ambient temperature

[0130] Thermal expansion and contraction: Changes in ambient temperature will cause the thermal expansion and contraction of the pipeline material, which may affect the size and shape of the pipeline, thereby indirectly affecting the pressure inside the pipeline;

[0131] Heat loss: When the ambient temperature is low, the speed at which the pipe dissipates heat will increase, causing the fluid temperature in the pipe to drop, and a higher pressure may be required to maintain the required heat transfer efficiency;

[0132] 2. Atmospheric pressure

[0133] External pressure: Changes in atmospheric pressure will have some effect on the pressure inside the pipe, especially in an open system. For example, when atmospheric pressure drops, the relative pressure inside the pipe may appear higher;

[0134] Tightness: In some systems, if the pipe is not sealed well, changes in atmospheric pressure may affect the pressure inside the pipe;

[0135] 3. Terrain and altitude

[0136] Terrain changes: When a pipeline passes through undulating terrain, the pressure at different heights will be different due to gravity. The pressure at higher locations is lower, and the pressure at lower locations is higher;

[0137] Altitude changes: As altitude increases, atmospheric pressure decreases, which may indirectly affect the pressure inside the pipe;

[0138] 4. Seasonal changes

[0139] User demand: Seasonal changes can cause user demand for heat to change, especially in winter and summer. Higher demand will cause the system to require greater pressure to meet the heat supply;

[0140] Ambient temperature: Seasonal changes are accompanied by changes in ambient temperature, which will affect the heat loss of the heating network system and thus the pressure in the system;

[0141] 5. Humidity

[0142] Condensation: In high humidity environments, condensation may occur on the pipe surface, which may affect the insulation effect of the pipe and thus affect the pressure of the system;

[0143] The pressure value of the heating network pipeline is related to environmental factors, especially ambient temperature, atmospheric pressure, topography, seasonal changes and humidity. These factors will affect the heat loss of the heating network, user demand and the physical characteristics of the pipeline, which in turn affects the pressure value of the heating network.

[0144] In this embodiment, the ResNet-BiLSTM network structure includes two residual blocks ResNet1 and ResNet2, a BiLSTM unit and a fully connected layer;

[0145] Among them, an attention-based layer is added after the BiLSTM unit to calculate the attention weights of each feature at different times and rank the importance of different features.

[0146] It should be noted that the ResNet residual neural network structure introduces jump connections to solve the gradient vanishing and gradient exploding problems in the deep neural network training process, avoiding the gradient attenuation during the back propagation process, so that the network can easily learn deeper features. BiLSTM is composed of forward and backward LSTM, which are often used to model and extract contextual semantic information in time series prediction tasks. It can simultaneously use the sequence information before and after the current time step, and integrate the current input with the past and future information to obtain more comprehensive contextual semantic information. The two residual blocks ResNet1 and ResNet2 in the ResNet-BiLSTM network structure are used to extract features first, and then output to the BiLSTM network and the fully connected layer for pipeline pressure prediction to obtain the final pipeline pressure prediction value.

[0147] The attention-based layer calculates the attention weight at each moment, allowing the model to focus more on those features that contribute more to the prediction of pipeline pressure, identify the relationship between different features, and assign corresponding weights according to the degree of contribution, thereby improving the accuracy of model prediction. The attention weight vector is expressed as:

[0148] u t =tanh(w h h t +b h );

[0149] w h is the weight matrix; h t is the hidden vector; b h is the bias vector;

[0150] The normalized attention weight is expressed as:

[0151]

[0152] v is the weight vector;

[0153] The weighted output vector of the attention layer is expressed as: s = ∑ t α t h t .

[0154] In this embodiment, in S4, based on the difference between the real-time pressure data and the simulated pressure data at the key positions and important nodes, and the difference between the real-time pressure data and the predicted value of the pressure data, the following are included:

[0155] Get the real-time pressure data of key locations and important nodes at a preset time in the future, defined as X i,t , represents the real-time pressure data of the i-th pipeline point at the t-th moment;

[0156] Based on the digital twin model of the heat network pipeline, the actual operation status of the pipeline is simulated online to obtain the simulated pressure data of key locations and important nodes at a preset time in the future, which is defined as Represents the simulated pressure data of the i-th pipeline point at the t-th time;

[0157] Based on the heat network pipeline pressure prediction model, the pressure data prediction values ​​of key locations and important nodes of the heat network pipeline at the preset time in the future are output, which is defined as It represents the predicted value of pressure data at the i-th pipeline point at the t-th moment;

[0158] Calculate real-time pressure data X i,t With simulated pressure data The difference between

[0159] Calculate real-time pressure data X i,t Predicted value with pressure data The difference between

[0160] The difference δ i,t , Perform fusion calculation to obtain the comprehensive deviation value δ i ' ,t ; The fusion calculation includes weighted average calculation and weighted calculation;

[0161] Among them, the weighted average calculation comprehensive deviation value is expressed as:

[0162]

[0163] The weighted calculation comprehensive deviation value is expressed as:

[0164]

[0165] w 1 is the difference δ i,t The weight coefficient of 2 For the difference The weight coefficient of .

[0166] In this embodiment, S5 includes: when the comprehensive deviation value of the pressure data of the heating network pipeline exceeds the configured pressure data abnormal threshold range, an early warning is issued indicating that the pressure data is abnormal, and the abnormal situation of the heating network pipeline is highlighted, and the corresponding pipeline position or node of the heating network pipeline is screened and identified to have abnormal operating conditions.

[0167] It should be noted that the threshold configuration is set based on historical data and statistical results, and the threshold needs to be optimized regularly to ensure the effectiveness of the threshold setting; for example, the threshold can be set to ±2δ or ±3δ, where δ is the standard deviation of the deviation value. According to the deviation between real-time data and simulation data, and the deviation between real-time data and predicted data, the abnormality of the comprehensive deviation value is judged, so as to timely discover and handle abnormal situations and ensure the safe and stable operation of the heat network pipeline.

[0168] In actual applications, after screening and identifying the abnormal operating conditions of the corresponding pipeline positions or nodes of the heat network pipeline, it also includes setting up an abnormal pattern recognition process: simulating the abnormal operating conditions of each key position and important node based on the digital twin model of the heat network pipeline, and analyzing the impact of abnormalities at different positions and nodes of the pipeline on the operating data of other positions and nodes, obtaining the operating data of each key position and important node under the abnormal mode as the simulated abnormal data sample, and using the machine learning algorithm for training and learning, establishing an abnormal pattern recognition model, and outputting the abnormal pattern of pressure data.

[0169] Abnormal patterns of heat network pipeline pressure data usually refer to situations in which the pressure data deviates from the normal range or shows unusual change trends during the operation of the heat network pipeline. These abnormal patterns can help operation and maintenance personnel to promptly discover potential problems in the system so that appropriate measures can be taken to avoid more serious failures. The following are several common abnormal patterns of heat network pipeline pressure data:

[0170] 1)Sudden pressure drop:

[0171] Causes: Pipeline leakage, accidental valve opening, pump station failure, etc.;

[0172] Performance: Pressure data drops rapidly in a short period of time;

[0173] Impact: May lead to insufficient heating and affect user comfort;

[0174] 2)Sudden pressure rise:

[0175] Cause: accidental valve closure, too fast increase in heat supply from heat source, etc.

[0176] Symptoms: Pressure data rises rapidly in a short period of time;

[0177] Impact: It may cause the pipeline to be subjected to excessive pressure, resulting in pipe burst or damage;

[0178] 3) Periodic pressure fluctuations:

[0179] Cause: improper control system parameter settings, fluctuations in user demand, etc.; Manifestation: pressure data shows obvious periodic changes;

[0180] Impact: May cause system instability and affect heating quality;

[0181] 4) Long-term low pressure:

[0182] Causes: Pipeline aging, insulation damage, system design defects, etc.

[0183] Symptoms: Pressure data is continuously below the normal range;

[0184] Impact: May lead to system inefficiency and increase energy consumption;

[0185] 5) Long-term high stress:

[0186] Cause: Excessive heat supply from the heat source, blockage in the system, etc.

[0187] Symptoms: Pressure data is continuously higher than the normal range;

[0188] Impact: May cause excessive wear or damage to system components;

[0189] 6) Pressure data mutation:

[0190] Cause: sensor failure, control system misoperation, etc.

[0191] Symptoms: Sudden jumps in pressure data;

[0192] Impact: May lead to misjudgment of system status and affect decision-making;

[0193] 7) Abnormal trend of pressure data:

[0194] Causes: scale accumulation inside the pipeline, changes in the external environment, etc.;

[0195] Symptoms: Pressure data gradually deviates from the normal range over time;

[0196] Impact: May cause system performance to degrade, requiring timely maintenance;

[0197] 8) Abnormal local pressure:

[0198] Cause: Partial blockage of pipeline, equipment failure, etc.

[0199] Symptoms: Pressure data in one area is significantly different from that in other areas;

[0200] Impact: May cause insufficient or overheating of local heating;

[0201] 9) Abnormal peak:

[0202] Cause: Short-term load surge, system failure, etc.

[0203] Symptoms: A brief spike in pressure data;

[0204] Impact: May cause damage to equipment or affect user comfort;

[0205] 10) Pressure data missing:

[0206] Cause: sensor failure, data acquisition system problem, etc.

[0207] Symptoms: Blank intervals appear in the pressure data;

[0208] Impact: It may make it impossible to monitor the system status in real time, affecting fault diagnosis.

[0209] Example 2

[0210] like Figure 2 As shown, this embodiment 2 provides a real-time detection device for abnormal pressure data of a heat network pipeline, including:

[0211] The risk identification and assessment module is used to establish a full life cycle management system for the heat network pipeline based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, conduct risk identification and assessment, form a risk assessment report for the entire heat network pipeline, and analyze the key locations where risks are prone to occur in the heat network pipeline;

[0212] The real-time data acquisition module is used to lay pressure acquisition devices at key locations where risks are prone to occur in the heat network pipeline and at important nodes of the heat network pipeline to obtain real-time pressure data at key locations and important nodes of the heat network pipeline;

[0213] The simulation data acquisition module is used to establish a digital twin model of the heat network pipeline based on the mechanism model and data model of the heat network pipeline, and to perform online simulation deduction under normal operating conditions to obtain simulated pressure data at key locations and important nodes;

[0214] The prediction data acquisition module is used to construct a heat network pipeline pressure prediction model based on the multi-dimensional factors that affect the pipeline pressure under normal operating conditions of the heat network pipeline, and output the pressure data prediction values ​​of each key position and important node of the heat network pipeline;

[0215] A deviation calculation module is used to obtain a comprehensive deviation value of pressure data based on the difference between the real-time pressure data and the simulated pressure data at key locations and important nodes, and the difference between the real-time pressure data and the predicted value of the pressure data;

[0216] The anomaly identification module is used to issue early warnings for the heat network pipeline based on the comprehensive deviation value of pressure data and the configured abnormal threshold range of pressure data at each key position and important node, display the abnormal situation of the heat network pipeline, and identify the abnormal pressure positions and nodes.

[0217] In several embodiments provided in the present application, it should be understood that the disclosed system and method can also be implemented in other ways. The system embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the systems, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0218] In addition, the functional modules in each embodiment of the present invention can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), disk or optical disk and other media that can store program codes.

[0219] Based on the above ideal embodiments of the present invention, the relevant staff can make various changes and modifications without departing from the technical concept of the present invention through the above description. The technical scope of the present invention is not limited to the contents of the specification, and its technical scope must be determined according to the scope of the claims.

Claims

1. A real-time detection method for abnormal pressure data of a heat network pipeline, characterized in that: It includes: S1. Based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, establish a full life cycle management system for the heat network pipeline, conduct risk identification and assessment, form a risk assessment report for the entire heat network pipeline, and analyze the key locations where risks are prone to occur in the heat network pipeline; S2. Lay pressure collection devices at key locations where risks are prone to occur in the heat network pipeline and at important nodes of the heat network pipeline to obtain real-time pressure data at key locations and important nodes of the heat network pipeline; S3. Based on the mechanism model and data model of the heat network pipeline, a digital twin model of the heat network pipeline is established, and online simulation deduction is performed under normal operating conditions to obtain simulated pressure data of key positions and important nodes; and based on the multi-dimensional factors affecting pipeline pressure under normal operating conditions of the heat network pipeline, a heat network pipeline pressure prediction model is constructed to output the predicted values ​​of pressure data of key positions and important nodes of the heat network pipeline; S4. Obtain the comprehensive deviation value of the pressure data based on the difference between the real-time pressure data and the simulated pressure data at the key locations and important nodes, and the difference between the real-time pressure data and the predicted value of the pressure data, and configure the abnormal threshold range of the pressure data at each key location and important node; S5. The heat network pipeline issues an early warning based on the comprehensive deviation value of the pressure data and the configured pressure data abnormal threshold range, displays the abnormal situation of the heat network pipeline, and identifies the abnormal pressure location and nodes.

2. The real-time detection method for abnormal pressure data of heat network pipeline according to claim 1 is characterized in that: In S1, a full life cycle management system for the heat network pipeline is established based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, including: Obtain environmental data of heat network pipelines, including: geographic information, soil type, burial depth, and ground elevation; Obtain basic attribute data of heat network pipelines, including: pipeline distance, pipe diameter, wall thickness, pipeline material, installation date, pipeline custom ID number, and pipeline structure layout; Obtain maintenance data of heating network pipelines, including maintenance records, inspection results, and pipeline component replacement records; Obtain historical operation data of the heat network pipeline, including supply and return water pressure, supply and return water temperature, and flow data under various operating conditions; Based on the environmental data and basic attribute data of the heat network pipeline, a heat network pipeline construction period management database is established; Establish a heat network pipeline operation management database based on the heat network pipeline maintenance data and historical operation data; Based on the construction and operation management data of the heat network pipelines, a heat network pipeline scrapping management database is established, including the evaluation of pipelines that have reached the end of their service life, determining whether to continue to use or replace them, and the reasonable treatment of some pipelines that have been decided to be scrapped; A full life cycle management system for heat network pipelines is established based on the heat network pipeline construction period management database, operation period management database and scrapping period management database.

3. The real-time detection method for abnormal pressure data of heat network pipeline according to claim 1 is characterized in that: In S1, after risk identification and assessment are performed to form a risk assessment report for the entire heat network pipeline, key locations where risks are prone to occur in the heat network pipeline are analyzed, including: Based on the data in the full life cycle management system of the heat network pipeline, the damage pattern of the heat network pipeline is identified to determine whether the heat network pipeline is damaged; the pipeline damage pattern includes erosion corrosion, intermittent use fatigue, corrosion under insulation layer, and cracking due to original manufacturing defects; Based on the data and damage patterns in the full life cycle management system of the heat network pipeline, a pipeline life prediction model is established to obtain pipeline life prediction results; According to the damage mode of the heat network pipeline and the prediction results of the pipeline life, a pipeline risk assessment model is established, and each risk assessment result is dynamically updated and the risk level is ranked to form a risk assessment report for the entire heat network pipeline; the risk levels include low risk, medium risk, medium-high risk and high risk; After emergency maintenance is carried out on the heating network pipelines at high risk, the risk level will be changed from high risk to medium-high risk and medium risk, and the medium-risk and medium-high risk heating network pipelines will be identified as key locations prone to risks.

4. The real-time detection method for abnormal pressure data of heat network pipeline according to claim 1 is characterized in that: In S2, the important nodes of the heat network pipeline include the pipeline inlet, outlet, branch point, and the vicinity of the valve.

5. The real-time detection method for abnormal pressure data of heat network pipeline according to claim 1 is characterized in that: In S3, a digital twin model of the heat network pipeline is established based on the mechanism model and data model of the heat network pipeline, and online simulation deduction is performed under normal operating conditions to obtain simulated pressure data of key locations and important nodes, including: Obtain the relevant data of heat network pipeline modeling based on the full life cycle management system of the heat network pipeline, and establish the geometric model of the heat network pipeline based on the basic attribute data and environmental data of the heat network pipeline; Using the heat transfer and fluid flow theory of the heat network pipeline and adding boundary condition constraints, the physical mechanism model of the heat network pipeline is established; Based on the dynamic response of the heat network pipeline under different loads and different ambient temperature changes and the control principle of the heat network pipeline equipment components, the behavior mechanism model of the heat network pipeline is constructed; According to the safe operation rules of the heat network pipeline and the change rules of pipeline operation data under different working conditions, the rule mechanism model of the heat network pipeline is constructed; The geometric model, physical mechanism model, behavioral mechanism model and rule mechanism model of the heat network pipeline are integrated to construct the mechanism model of the heat network pipeline; Use the collected actual operation data to establish the data model of the heat network pipeline; The mechanism model and data model of the heat network pipeline are integrated to establish a digital twin model of the heat network pipeline; The pipeline simulation parameters under normal operating conditions are input into the digital twin model of the heat network pipeline, and the initial conditions of the pipeline that are suitable for the pipeline equipment adjustment strategy are set. After online simulation and deduction, the simulated pressure data of key positions and important nodes of the heat network pipeline are obtained.

6. The real-time detection method for abnormal pressure data of heat network pipeline according to claim 1 is characterized in that: In S3, based on the multi-dimensional factors affecting the pipeline pressure under normal operation of the heat network pipeline, a heat network pipeline pressure prediction model is constructed to output the pressure data prediction values ​​of each key position and important node of the heat network pipeline, including: Obtain multi-dimensional time series data that affects pipeline pressure under normal operating conditions of the heat network pipeline, including historical operation data, environmental data, and basic pipeline attribute data; The multidimensional time series data is input into the ResNet-BiLSTM network. After the ResNet network is used to extract the features of the multidimensional time series data that affect the pipeline pressure, the extracted features are input into the BiLSTM network for training and learning, and a heat network pipeline pressure prediction model is constructed to output the pressure data prediction values ​​of each key position and important node of the heat network pipeline.

7. The real-time detection method for abnormal pressure data of heat network pipeline according to claim 6 is characterized in that: The ResNet-BiLSTM network structure includes two residual blocks ResNet1 and ResNet2, a BiLSTM unit and a fully connected layer; Among them, an attention-based layer is added after the BiLSTM unit to calculate the attention weights of each feature at different times and rank the importance of different features.

8. The real-time detection method for abnormal pressure data of heat network pipeline according to claim 1 is characterized in that: In S4, based on the difference between the real-time pressure data and the simulated pressure data at the key positions and important nodes, and the difference between the real-time pressure data and the predicted value of the pressure data, the following are included: Get the real-time pressure data of key locations and important nodes at a preset time in the future, defined as X i,t , represents the real-time pressure data of the i-th pipeline point at the t-th moment; Based on the digital twin model of the heat network pipeline, the actual operation status of the pipeline is simulated online to obtain the simulated pressure data of key locations and important nodes at a preset time in the future, which is defined as Represents the simulated pressure data of the i-th pipeline point at the t-th time; Based on the heat network pipeline pressure prediction model, the pressure data prediction values ​​of key locations and important nodes of the heat network pipeline at the preset time in the future are output, which is defined as It represents the predicted value of pressure data at the i-th pipeline point at the t-th moment; Calculate real-time pressure data X i,t With simulated pressure data The difference between Calculate real-time pressure data X i,t Predicted value with pressure data The difference between The difference δ i,t , Perform fusion calculation to obtain the comprehensive deviation value δ i ' ,t ; The fusion calculation includes weighted average calculation and weighted calculation; Among them, the weighted average calculation comprehensive deviation value is expressed as: The weighted calculation comprehensive deviation value is expressed as: w1 is the difference δ i,t The weight coefficient of The weight coefficient of .

9. The real-time detection method for abnormal pressure data of heat network pipeline according to claim 1 is characterized in that: The S5 includes: when the comprehensive deviation value of the pressure data of the heat network pipeline exceeds the configured pressure data abnormal threshold range, an early warning is issued indicating that the pressure data is abnormal, and the abnormal situation of the heat network pipeline is highlighted, and the corresponding pipeline position or node of the heat network pipeline is screened and identified to have abnormal operating conditions.

10. A real-time detection device for abnormal pressure data of a heat network pipeline, characterized in that: include: The risk identification and assessment module is used to establish a full life cycle management system for the heat network pipeline based on the environmental data, basic attribute data, maintenance data and historical operation data of the heat network pipeline, conduct risk identification and assessment, form a risk assessment report for the entire heat network pipeline, and analyze the key locations where risks are prone to occur in the heat network pipeline; The real-time data acquisition module is used to lay pressure acquisition devices at key locations where risks are prone to occur in the heat network pipeline and at important nodes of the heat network pipeline to obtain real-time pressure data at key locations and important nodes of the heat network pipeline; The simulation data acquisition module is used to establish a digital twin model of the heat network pipeline based on the mechanism model and data model of the heat network pipeline, and to perform online simulation deduction under normal operating conditions to obtain simulated pressure data at key locations and important nodes; The prediction data acquisition module is used to construct a heat network pipeline pressure prediction model based on the multi-dimensional factors that affect the pipeline pressure under normal operating conditions of the heat network pipeline, and output the pressure data prediction values ​​of each key position and important node of the heat network pipeline; A deviation calculation module is used to obtain a comprehensive deviation value of pressure data based on the difference between the real-time pressure data and the simulated pressure data at key locations and important nodes, and the difference between the real-time pressure data and the predicted value of the pressure data; The anomaly identification module is used to issue early warnings for the heat network pipeline based on the comprehensive deviation value of pressure data and the configured abnormal threshold range of pressure data at each key position and important node, display the abnormal situation of the heat network pipeline, and identify the abnormal pressure positions and nodes.

Images