Pipe network heat supply planning transformation and scheduling method based on AI and digital twinning

Abstract

The invention discloses a pipe network heat supply planning transformation and scheduling method based on AI and digital twinning, and belongs to the technical field of pipe network optimization, and the method comprises the following steps: S1, obtaining heat supply pipe network operation data; s2, constructing a digital twinborn model of the first heat supply pipe network; s3, acquiring real-time heat distribution data of the heat supply pipe network; s4, clustering is carried out; s5, a real-time high-temperature area, a medium-temperature area and a low-temperature area of the heat supply pipe network are divided; s6, calculating the participation rate of each pipeline; s7, planning a transformation and scheduling scheme of the heat supply pipe network; s8, new heat supply pipe network laying data are generated, and a second heat supply pipe network digital twinborn model is locally modified and constructed with the first heat supply pipe network digital twinborn model as the reference; s9, visually knowing the layout and scheduling result of the heat supply pipe network after planning and transformation; according to the system, pipelines can be additionally arranged to meet the requirements of users, part of heat supply pipelines can be omitted, and the energy utilization rate is increased while the modification cost is reduced.

Description

Technical Field

[0001] This invention belongs to the field of pipeline network optimization technology, specifically relating to a pipeline heating planning, renovation and scheduling method based on AI and digital twins. Background Technology

[0002] With the acceleration of urbanization and the improvement of residents' living standards, the planning, renovation and scheduling methods of heating pipe network systems, as an important part of urban infrastructure, are particularly important.

[0003] Current methods for planning, upgrading, and optimizing pipeline heating systems generally involve increasing pipelines based on user frequency. This approach not only increases upgrade costs but also leads to underutilization of some heating pipelines within the network, resulting in energy waste.

[0004] In view of this, a method for planning, upgrading and scheduling pipeline heating based on AI and digital twins is designed to solve the above problems. Summary of the Invention

[0005] To address the problems mentioned in the background section, this invention provides a method for planning, upgrading, and scheduling pipeline heating systems based on AI and digital twins. This method not only allows for the addition of pipelines to meet user needs but also enables the reduction of some heating pipelines, thereby decreasing upgrade costs while improving energy efficiency.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for planning, upgrading, and scheduling pipeline heating systems based on AI and digital twins, comprising the following steps:

[0007] S1: Obtain operational data of the heating network;

[0008] S2: Construct a digital twin model of the first heating network based on the operation data of the heating network;

[0009] S3: Obtain real-time heat distribution data of the heating network;

[0010] S4: Clustering of real-time thermal distribution data based on the K-Means algorithm;

[0011] S5: Based on the average value of the clustering results, compare it with the preset thermal values ​​to divide the heating network into real-time high temperature zone, medium temperature zone and low temperature zone;

[0012] S6: Calculate the participation rate of each pipeline in the real-time high temperature zone, medium temperature zone, and low temperature zone of the heating network;

[0013] S7: Based on the participation rate of each pipeline in the heating network, plan the renovation and scheduling scheme of the heating network;

[0014] S8: Generate new heating network laying data based on the planned heating network renovation and scheduling scheme. Using the first heating network digital twin model as a benchmark, construct the second heating network digital twin model by partially modifying the generated new heating network laying data.

[0015] S9: Based on the constructed digital twin models of the first and second heating network, we can intuitively understand the layout and scheduling results of the planned and renovated heating network.

[0016] Furthermore, the specific steps of step S4 include:

[0017] Set the number of clusters for the thermal distribution data;

[0018] K thermal distribution data points are randomly selected as the initial cluster centers;

[0019] Calculate the distance between each thermal distribution data point and the K thermal distribution data points, and assign each thermal distribution data point to the cluster containing the nearest cluster center;

[0020] Recalculate the center position of each cluster and iterate until the cluster center no longer changes significantly, at which point the clustering is complete.

[0021] Furthermore, the specific steps of step S6 include:

[0022] Obtain real-time pipeline data for high-temperature, medium-temperature, and low-temperature zones of the heating network. Calculate the pipeline participation rate within these zones based on the thermal distribution data. The expression is:

[0023]

[0024] Where: φ i Let f represent the participation of the i-th pipe, N represent the set of pipe thermal distribution data, S represent the thermal distribution data, M represent the sum of thermal distribution data of all pipes, and f x (S∪{i}) represents the thermal distribution result including the i-th pipe, f x (S) represents the thermal distribution result excluding the i-th pipe.

[0025] Furthermore, the specific steps of step S7 include:

[0026] Based on the participation rate of each pipeline in the heating network, and compared with the preset pipeline participation rate threshold, if the pipeline participation rate of the heating network is lower than the preset minimum pipeline participation rate, it is determined whether there is a substitute pipeline for that pipeline. If there is no substitute pipeline, the pipeline is retained. If there is a substitute pipeline, the pipeline is removed from the planned renovation scheme. If the pipeline participation rate of the heating network is higher than the preset maximum pipeline participation rate, the pipeline is added.

[0027] Among them, the alternative pipeline is a pipeline in the heating network that is adjacent to the pipeline, whose beginning and end are connected to the same pipeline, and whose preset heating flow rate has not been reached after the pipeline is replaced.

[0028] After the renovation, the heating supply from the removed pipelines will be replaced by alternative pipelines.

[0029] Furthermore, the specific steps of step S8 include:

[0030] New heating network laying data is generated based on the removed or added pipeline data and scheduling data;

[0031] Copy the digital twin model of the first heating network, add or remove pipeline data and scheduling data to the first heating network digital twin model, and construct the second heating network digital twin model.

[0032] Compared with the prior art, the beneficial effects of the present invention are:

[0033] 1. This invention determines the real-time high-temperature zone, medium-temperature zone, and low-temperature zone based on the thermal distribution data of the heating network. Then, it determines the participation rate of each pipeline based on the real-time high-temperature zone, medium-temperature zone, and low-temperature zone. Finally, it plans, adds, modifies, and schedules the heating network based on the participation rate of each pipeline. Compared with the prior art, this invention can not only add pipelines to meet the needs of users, but also delete some heating pipelines, reducing modification costs while improving energy utilization.

[0034] 2. This invention simultaneously constructs two digital twin models of heating pipe networks, enabling an intuitive understanding of the existing and planned renovation and scheduling layouts of heating pipe networks. Furthermore, for optimizations in planning, renovation, and scheduling, existing model data can be directly used for local modifications, avoiding the complexity of model construction. Attached Figure Description

[0035] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0036] 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. 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.

[0037] See appendix Figure 1 This invention provides the following technical solution: a method for planning, upgrading, and scheduling pipeline heating based on AI and digital twins, comprising the following steps:

[0038] S1: Obtain operational data of the heating network;

[0039] S2: Construct a digital twin model of the first heating network based on the operation data of the heating network;

[0040] A digital twin model is a virtual model of a physical entity created digitally, which can reflect the state, behavior and performance of the entity in real time.

[0041] The first digital twin model of the heating network refers to a digital twin of the heating network. Data is acquired through sensors and simulated in a virtual space to reflect the entire life cycle of the heating network for analysis.

[0042] S3: Obtain real-time heat distribution data of the heating network;

[0043] Thermal distribution data refers to data used to describe and display the distribution of heat or temperature in a space or area;

[0044] S4: Clustering of real-time thermal distribution data based on the K-Means algorithm;

[0045] K-Means algorithm is an unsupervised learning clustering analysis method. Choosing K-Means algorithm to cluster real-time thermal distribution data is characterized by its simplicity, intuitiveness and high computational efficiency.

[0046] S5: Based on the average value of the clustering results, compare it with the preset thermal values ​​to divide the heating network into real-time high temperature zone, medium temperature zone and low temperature zone;

[0047] The preset thermal values ​​are based on expert presets;

[0048] S6: Calculate the participation rate of each pipeline in the real-time high temperature zone, medium temperature zone, and low temperature zone of the heating network;

[0049] If a certain area of ​​the heating network is divided into a real-time high temperature zone, a medium temperature zone, and a low temperature zone at different time periods, then the pipeline participation rate in the real-time high temperature zone, medium temperature zone, and low temperature zone is calculated simultaneously. That is, the participation rate of one pipeline is calculated for three zones. If there are multiple participation rates, the average of the multiple participation rates is used as the final participation rate.

[0050] S7: Based on the participation rate of each pipeline in the heating network, plan the renovation and scheduling scheme of the heating network;

[0051] S8: Generate new heating network laying data based on the planned heating network renovation and scheduling scheme. Using the first heating network digital twin model as a benchmark, construct the second heating network digital twin model by partially modifying the generated new heating network laying data.

[0052] S9: Based on the constructed digital twin models of the first and second heating network, we can intuitively understand the layout and scheduling results of the planned and renovated heating network.

[0053] Specifically, step S4 includes the following steps:

[0054] Set the number of clusters for the thermal distribution data;

[0055] K thermal distribution data points are randomly selected as the initial cluster centers;

[0056] Calculate the distance between each thermal distribution data point and the K thermal distribution data points, and assign each thermal distribution data point to the cluster containing the nearest cluster center;

[0057] Recalculate the center position of each cluster and iterate until the cluster center no longer changes significantly, at which point the clustering is complete.

[0058] Specifically, step S6 includes the following steps:

[0059] Obtain real-time pipeline data for high-temperature, medium-temperature, and low-temperature zones of the heating network. Calculate the pipeline participation rate within these zones based on the thermal distribution data. The expression is:

[0060]

[0061] Where: φ i Let f represent the participation of the i-th pipe, N represent the set of pipe thermal distribution data, S represent the thermal distribution data, M represent the sum of thermal distribution data of all pipes, and f x (S∪{i}) represents the thermal distribution result including the i-th pipe, f x (S) represents the thermal distribution result excluding the i-th pipe.

[0062] Specifically, step S7 includes the following steps:

[0063] Based on the participation rate of each pipeline in the heating network, and compared with the preset pipeline participation rate threshold, if the pipeline participation rate of the heating network is lower than the preset minimum pipeline participation rate, it is determined whether there is a substitute pipeline for that pipeline. If there is no substitute pipeline, the pipeline is retained. If there is a substitute pipeline, the pipeline is removed from the planned renovation scheme. If the pipeline participation rate of the heating network is higher than the preset maximum pipeline participation rate, the pipeline is added.

[0064] Among them, the alternative pipeline is a pipeline in the heating network that is adjacent to the pipeline, whose beginning and end are connected to the same pipeline, and whose preset heating flow rate has not been reached after the pipeline is replaced.

[0065] After the renovation, the heating supply from the removed pipelines will be replaced by alternative pipelines.

[0066] Specifically, step S8 includes the following steps:

[0067] New heating network laying data is generated based on the removed or added pipeline data and scheduling data;

[0068] Copy the digital twin model of the first heating network, add or remove pipeline data and scheduling data to the first heating network digital twin model, and construct the second heating network digital twin model.

[0069] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An AI and digital twin based heating network planning and reconstruction and scheduling method, characterized in that, The method comprises the following steps: S1: obtaining operation data of a heat supply pipe network; S2: constructing a first heat supply pipe network digital twin model based on the operation data of the heat supply pipe network; S3: obtaining real-time heat distribution data of the heat supply pipe network; S4: clustering the real-time heat distribution data based on a K-Means algorithm; S5: comparing the average value of the clustering result with a preset heat value to divide the heat supply pipe network into a real-time high-temperature zone, a medium-temperature zone and a low-temperature zone; S6: calculating the participation rates of pipes in the real-time high-temperature zone, the medium-temperature zone and the low-temperature zone of the heat supply pipe network; S7: planning a reconstruction and dispatching scheme for the heat supply pipe network based on the participation rates of the pipes of the heat supply pipe network; S8: generating new heat supply pipe network laying data based on the planned reconstruction and dispatching scheme for the heat supply pipe network, modifying the first heat supply pipe network digital twin model based on the generated new heat supply pipe network laying data to construct a second heat supply pipe network digital twin model; S9: intuitively understanding the layout of the heat supply pipe network after the planned reconstruction and the dispatching result based on the constructed first heat supply pipe network digital twin model and the second heat supply pipe network digital twin model.

2. The AI and digital twin-based pipe network heating planning reconstruction and scheduling method according to claim 1, characterized in that: The specific steps of the step S4 comprise: setting the number of clusters of the heat distribution data; randomly selecting K heat distribution data points as initial cluster centers; calculating the distances between each heat distribution data point and the K heat distribution data points, and assigning each heat distribution data point to the cluster where the nearest cluster center is located; recalculating the center positions of each cluster and iterating until the cluster centers do not change significantly to stop, and the clustering is completed.

3. The AI and digital twin-based pipe network heating planning reconstruction and scheduling method according to claim 2, characterized in that: The specific steps of the step S6 comprise: obtaining pipe data of the heat supply pipe network in the real-time high-temperature zone, the medium-temperature zone and the low-temperature zone, and calculating the pipe participation rates of the pipes in the real-time high-temperature zone, the medium-temperature zone and the low-temperature zone of the heat supply pipe network based on the heat distribution data, with the expression being: where: φ i represents the participation of the i-th pipe, N represents a set of pipe heat distribution data, S represents a heat distribution data, and M represents the sum of all pipe heat distribution data f x (S∪{i}) denotes a heat distribution result including the i-th pipe, f x (S) denotes a heat distribution result not including the i-th pipe.

4. The AI and digital twin-based pipe network heating planning reconstruction and scheduling method according to claim 3, characterized in that: The specific steps of the step S7 comprise: comparing the participation rates of the pipes of the heat supply pipe network with preset pipe participation rate thresholds, if the participation rate of the pipe of the heat supply pipe network is lower than the preset minimum pipe participation rate, determining whether there is a replaceable pipe for the pipe, if there is no replaceable pipe, retaining the pipe, if there is a replaceable pipe, removing the pipe in the planned reconstruction scheme, and if the participation rate of the pipe of the heat supply pipe network is higher than the preset maximum pipe participation rate, adding the pipe; wherein the replaceable pipe is a pipe in the heat supply pipe network that is adjacent to the pipe, connected at the same end of the pipe and has not reached the preset heat supply flow after pipe replacement; after the reconstruction, the heat supply of the removed pipe is dispatched to the replaced pipe.

5. The AI and digital twin-based pipe network heating planning reconstruction and scheduling method according to claim 4, characterized in that: The specific steps of the step S8 comprise: generating new heat supply pipe network laying data based on the removed or added pipe data and the dispatching data; copying the first heat supply pipe network digital twin model, adding the removed or added pipe data and the dispatching data in the first heat supply pipe network digital twin model, and constructing the second heat supply pipe network digital twin model.

Images