A deep learning-based energy loss optimization method and system

Abstract

The application discloses an energy consumption optimization method and system based on deep learning, and relates to the technical field of machine learning.The application calculates a circulation period by obtaining secondary pipe network data and circulating water flow data, calibrates user topological positions in combination with heating completion drawings, and stores in association, and clearly defines the time reference and spatial topological relationship of the heating system; temperature data is collected based on the circulation period to construct a heating image, historical images are integrated to form a data analysis set, a time series prediction model is used to obtain a predicted heating image, and forward-looking prediction of heating demand is realized; a mapping relationship model of circulating water temperature, flow rate and indoor pipe temperature change is trained through deep learning, and an advance regulation time point is calculated in combination with the user topological positions and the circulating water flow data, so that the problems of heating imbalance of downstream users and increased energy consumption during low-temperature anti-freezing to heating are solved, while ensuring standard heating and maintaining system balance, heat dissipation is reduced, and energy consumption optimization is realized.

Description

Technical Field

[0001] This invention relates to the field of machine learning technology, specifically to a method and system for optimizing energy loss based on deep learning. Background Technology

[0002] Heating systems heat circulating water through heat exchange stations, which is then transported to users via a secondary pipeline network to release heat. The cooled circulating water then flows back to the heat exchange stations for reheating, forming a closed-loop heating cycle. As a key infrastructure in frigid winter regions, it directly ensures comfortable indoor temperatures for residents, maintaining normal living order and quality of life.

[0003] The topology of the secondary pipeline network directly affects the stability of heating supply. Remote users are prone to energy loss due to increased pipeline transmission distance. In scenarios such as shopping malls, low-temperature anti-freeze operation is often used late at night to prevent pipeline freezing and avoid unnecessary energy consumption. However, when these users switch to normal heating, changes in the temperature and flow rate of the circulating water in the secondary pipeline network are gradually transmitted along the topological path, disrupting the original heating balance of downstream users. To maintain demand, downstream users will further increase the heating adjustment range, forcing heat exchange stations to adjust output parameters to increase circulating water temperature and flow rate, thereby exacerbating unorganized heat dissipation and indirectly increasing overall energy loss. Therefore, there is an urgent need for an energy loss optimization method and system based on deep learning. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for optimizing energy loss based on deep learning, so as to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an energy loss optimization method based on deep learning, the energy loss optimization method comprising the following steps:

[0006] Step S1: Obtain the secondary pipeline network data information connected to the heat exchange station and the circulating water flow data information of the secondary pipeline network interface, and perform analysis and calculation to obtain the circulation cycle of the circulating water in the secondary pipeline network;

[0007] Step S1-1: Obtain the pipe diameter data and corresponding pipe length data of each pipe section of the secondary pipe network connected to the heat exchange station through the heating as-built drawings; calculate the cross-sectional area of ​​the corresponding pipe section based on the pipe diameter, and calculate the volume of a single pipe section filled with circulating water based on the length of the pipe section; sum up the volumes of all pipe sections filled with circulating water in the secondary pipe network to obtain the total volume of circulating water in the secondary pipe network.

[0008] The formula for calculating the cross-sectional area of ​​a pipe section is as follows:

[0009] S i =π×(d i ÷2)2 ;

[0010] In the formula, S i d represents the cross-sectional area of ​​the i-th pipe segment; i This represents the pipe diameter of the i-th pipe segment;

[0011] The formula for calculating the volume of a single pipe section filled with circulating water is as follows:

[0012] V i =S i ×L i ;

[0013] In the formula, V i L represents the volume of circulating water filling the i-th pipe segment; i This represents the length of the i-th pipe segment;

[0014] The formula for calculating the total volume of circulating water in a secondary pipe network is as follows:

[0015] ;

[0016] In the formula, V all The total volume of circulating water in the secondary pipe network is represented by n; n represents the number of pipe segments in the secondary pipe network.

[0017] Step S1-2: Obtain circulating water flow data at the secondary pipe network interface using a flow sensor. The secondary pipe network interface includes a secondary pipe network supply end interface and a secondary pipe network return end interface. Calculate the average circulating water flow rate at the secondary pipe network supply end interface and the secondary pipe network return end interface. Divide the total volume of circulating water in the secondary pipe network obtained in step S1-1 by the average circulating water flow rate to obtain the circulation cycle of the circulating water in the secondary pipe network.

[0018] The formula for calculating the average circulating water flow rate at the supply end interface and the return end interface of the secondary water supply network is as follows:

[0019] Q avg = (Q) out +Q in )÷2;

[0020] In the formula, Q avg Q represents the average circulating water flow rate at the supply and return water interfaces of the secondary water supply network; out This represents the circulating water flow rate at the secondary water supply interface; Q in This represents the circulating water flow rate at the return water interface of the secondary pipeline network;

[0021] The formula for calculating the circulation period of circulating water in a secondary pipe network is as follows:

[0022] T=V all ÷Q avg;

[0023] In the formula, T represents the circulation cycle of the secondary pipe network circulating water;

[0024] The diameter and length data of each section of the secondary pipeline network are obtained from the heating as-built drawings to calculate the total volume of circulating water. The flow rate of circulating water at the interface between the supply and return ends of the secondary network is obtained through flow sensors and the average value is calculated. Thus, the circulation cycle of circulating water in the secondary pipeline network is obtained. This circulation cycle provides an accurate time reference for subsequent steps such as heating service area detection, setting the time interval for collecting temperature of user inlet pipes, and building heating profiles, ensuring that all subsequent heating-related data collection and analysis are carried out based on a unified time dimension.

[0025] Step S2: Detect the heating service area of ​​the secondary pipeline network according to the cycle, and perform topology location calibration and topology location association storage for users in the heating service area based on the heating as-built drawings;

[0026] Step S2-1: Using the cycle period obtained in step S1 as a benchmark, detect the heating service area of ​​the secondary pipeline network to determine the connection relationship between users and branches of the secondary pipeline network within the heating service area and the pipeline branch segments corresponding to each user. The heating service area refers to the area where the secondary pipeline network connected to the heat exchange station transports circulating water for heating.

[0027] Step S2-2: Based on the heating as-built drawings, extract the geographical coordinates of each user in the heating service area and the corresponding secondary pipeline branch node number, and mark the topological location of each user in the secondary pipeline; associate the marked user topological location with user identification information and store it in the database.

[0028] By using a cyclical approach as a benchmark, the connection relationship between users and secondary pipeline branches within the heating service area, as well as the corresponding pipe sections, are determined. Based on the heating as-built drawings, the geographic coordinates of users and the node numbers of pipeline branches are extracted. The topological location of users is then calibrated and associated with user identification information and stored in the database. This clarifies the spatial distribution and connection relationship of users in the secondary pipeline network, providing accurate spatial topological data support for subsequent operations such as precisely locating pipeline branches and pipe sections corresponding to users in low-temperature anti-freezing operation, calculating pipeline path length, and associating user locations with heating data.

[0029] Step S3: Based on the cycle, the circulating water temperature of the inlet pipes of each user in the heating service area is detected. Combined with the circulating water temperature analysis in the secondary pipe network interface of the heat exchange station, a cycle heating profile of the heating service area is constructed.

[0030] Step S3-1: Based on the cycle obtained in Step S1, the circulating water temperature in the inlet pipes of each user in the heating service area is collected at preset time intervals within the cycle, wherein the preset time interval does not exceed the cycle; simultaneously, the circulating water temperature at the water supply end interface of the secondary pipe network of the heat exchange station is collected to obtain the density and specific heat capacity data of the circulating water in the secondary pipe network; the ratio of the circulating water temperature in the inlet pipe of each user to the circulating water temperature at the water supply end interface of the secondary pipe network is calculated and recorded as the single-user inlet pipe circulating water temperature ratio; the heating capacity of the circulating water in the inlet pipe of each user is calculated, wherein the heating capacity of the circulating water in the inlet pipe of each user is equal to the product of the circulating water density, specific heat capacity, the corresponding user's inlet pipe circulating water flow rate, and the single-user inlet pipe circulating water temperature ratio; the single-user inlet pipe circulating water temperature ratios of all users are added together and divided by the total number of users in the heating service area to obtain the average inlet pipe circulating water temperature ratio corresponding to the time interval; the heating capacity of the circulating water in the inlet pipes of all users is added together to obtain the total heating capacity of the circulating water in the inlet pipes of the heating service area corresponding to the time interval.

[0031] The formula for calculating the heating capacity of a single-user household inlet pipe circulating water is as follows:

[0032] ;

[0033] In the formula, Q j，out ρ represents the heat supply of circulating water in the inlet pipe for the j-th user; ρ represents the density of circulating water in the secondary pipe network; c represents the specific heat capacity of circulating water in the secondary pipe network.

[0034] Q j，two Let k represent the circulating water flow rate of the inlet pipe for the j-th user; j This is represented as the inlet pipe circulating water temperature ratio for the j-th user;

[0035] Step S3-2: Record and store the collection time for each preset time interval, and associate the collection time with the total heat supply of the circulating water in the inlet pipe of the heating service area in the corresponding time interval to form a dataset showing the change of the total heat supply of the circulating water in the inlet pipe of the heating service area over time within the cycle; construct a cycle heating profile of the heating service area based on this dataset, wherein the cycle heating profile includes the mapping relationship between each collection time in the cycle and the total heat supply of the circulating water in the inlet pipe of the corresponding heating service area, as well as the cumulative value of the total heat supply of the circulating water in the inlet pipe of the heating service area within the cycle;

[0036] Based on the cycle, the temperature of the circulating water in the user's inlet pipe and the temperature of the secondary pipe network water supply interface are collected at preset time intervals. The water temperature ratio and heating capacity of a single user, as well as the total heating capacity and average water temperature ratio of the service area, are calculated. The data is formed by associating the collection time with the total heating capacity and constructing a cycle heating profile. This profile fully presents the changing pattern and cumulative value of the total heating capacity of the circulating water in the inlet pipe of the heating service area at each time within the cycle. It provides basic data including time, temperature, heating capacity and other dimensions for subsequent historical heating data analysis and deep learning model training.

[0037] Step S4: Acquire the historical heating profiles of the heat exchange station for multiple cycles and construct a heating data analysis set for the heating service area; process the data based on the heating data analysis set and the time series prediction model to predict the heating profile of the heating service area in the next cycle, which is denoted as the predicted cycle heating profile.

[0038] Step S4-1: Obtain multiple cycle heating profiles generated during the historical operation of the heat exchange station, and extract the collection time, total heat supply of the household inlet pipe circulating water in the heating service area, and the cumulative total heat supply within the cycle from each historical cycle heating profile; associate and organize all the extracted historical cycle-related data according to the cycle number to construct a heating data analysis set for the heating service area.

[0039] Step S4-2: Input the constructed heating service area heating data analysis set into the time series prediction model for data processing. The time series prediction model learns the time variation pattern and cumulative value variation pattern of the total heating supply of the household inlet circulating water in the heating service area within the historical cycle. The output is the heating profile of the heating service area in the next cycle, denoted as the predicted cycle heating profile. The predicted cycle heating profile includes the mapping relationship between each preset collection time in the next cycle and the corresponding predicted total heating supply of the household inlet circulating water in the heating service area, as well as the predicted cumulative value of the total heating supply of the household inlet circulating water in the heating service area in the next cycle.

[0040] The system acquires historical heating profiles for multiple cycles of the heat exchange station, extracts data such as collection time, total heat supply, and cumulative value, and organizes them into a heating data analysis set according to the cycle number. It inputs the data into a time series prediction model to learn the historical heating change patterns and outputs a predicted heating profile for the next cycle. This predicted profile clearly defines the predicted total heat supply and cumulative value for each preset collection time in the next cycle, providing a forward-looking heating demand data basis for the prediction and adjustment of subsequent heat exchange station control parameters.

[0041] Step S5: Based on the user topology location in the heating service area and the real-time flow data of circulating water at the secondary pipeline interface of the heat exchange station, analyze and calculate the advance control time for the low-temperature antifreeze to heating switch of the heat exchange station when the low-temperature antifreeze operation status changes in the heating service area.

[0042] Step S5-1: Retrieve user identification information for users in the heating service area who are in low-temperature anti-freeze operation from the database, and determine the secondary pipeline branch section corresponding to the user in low-temperature anti-freeze operation based on the user topology location marked in step S2; extract from the heating data analysis set the timestamp when the circulating water in the inlet pipe of the user in the low-temperature anti-freeze operation state transitions to normal heating state from the low-temperature anti-freeze operation state to the normal heating state, and the timestamp when the secondary pipeline water supply end interface of the heat exchange station starts regulation in the corresponding historical cycle. The regulation refers to the adjustment operation of the circulating water temperature and circulating water flow rate of the secondary pipeline water supply end interface of the heat exchange station.

[0043] Step S5-2: Based on the user's topology location in low-temperature antifreeze operation, determine the pipeline path length between the corresponding secondary pipeline branch section and the secondary pipeline water supply end interface of the heat exchange station. Combine the real-time flow data of circulating water at the secondary pipeline interface of the heat exchange station to calculate the transmission time of circulating water flowing through the pipeline path length. Subtract the transmission time from the difference between the extracted timestamp of the circulating water in the user's inlet pipe reaching the standard temperature and the timestamp of the heat exchange station's control start-up to obtain the advance control time of the heat exchange station when the low-temperature antifreeze operation status changes in the heating service area.

[0044] By retrieving user identification information of low-temperature antifreeze operation status and determining the corresponding pipeline branch section in combination with topological location, the timestamps of compliance and control start-up at historical switching states are extracted. The pipeline path transmission time is calculated and the advance control time for switching from low-temperature antifreeze to heating is derived. This time parameter accurately quantifies the time required to start control in advance to compensate for the transmission delay of circulating water, providing a key time reference for determining the start-up control time of the heat exchange station and avoiding the delay in temperature compliance during heating switching.

[0045] Step S6: The heating data analysis set of the heating service area is processed by deep learning to map the relationship between the temperature and flow rate of the circulating water in the secondary pipe network and the temperature change of the inlet pipe. Combined with the analysis of the early control time of low temperature antifreeze to heating, the time point of low temperature antifreeze to heating start control of the heat exchange station is obtained.

[0046] Step S6-1: Extract the temperature and flow rate data of circulating water in the secondary pipe network during historical cycles from the heating data analysis set, as well as the corresponding time-based circulating water temperature data of each user's inlet pipe within the heating service area; combine the extracted data with user topology location data and organize them according to circulating water temperature, circulating water flow rate, inlet pipe circulating water temperature, and user topology location to form a training dataset; input the training dataset into a preset deep learning model for training, and output a mapping relationship model between the temperature and flow rate of circulating water in the secondary pipe network and the changes in inlet pipe circulating water temperature;

[0047] Step S6-2: Obtain the initial temperature data of the circulating water in the user's inlet pipe under low-temperature anti-freeze operation and the target temperature data of the circulating water in the inlet pipe under the preset normal heating state within the heating service area, and calculate the temperature difference between the two; input the temperature difference into the mapping relationship model, and combine it with the topological location data of the corresponding user to output the heating time required for the circulating water in the user's inlet pipe to rise from the initial temperature to the target temperature; subtract the heating time from the low-temperature anti-freeze to heating advance control time to obtain the low-temperature anti-freeze to heating start control time of the heat exchange station, where the low-temperature anti-freeze to heating start control time is represented by the time when the heat exchange station starts to adjust the temperature of the user's inlet pipe. The circulating water temperature and flow rate at the secondary network water supply end interface are adjusted to ensure that the circulating water in the user's inlet pipe, which is in low-temperature antifreeze operation, reaches the target temperature of normal heating at a predetermined time. The total heat demand in the heating profile of the cycle is predicted, and the temperature rise demand output by the mapping relationship model is combined with the temperature rise demand. The circulating water temperature at the secondary network water supply end interface is gradually adjusted according to the predetermined time interval within the cycle. When adjusting the circulating water flow rate, based on the real-time flow data of the circulating water at the secondary network interface of the heat exchange station and the user topology location, the heat delivery demand after temperature adjustment is matched, and the circulating water flow rate is adjusted synchronously to maintain the balance of supply and return flow.

[0048] By controlling the circulating water in the secondary pipe network to operate at the same temperature but different flow rates, and combining this with user topology location data, the magnitude and rate of temperature change of the circulating water in the inlet pipe under different flow rates can be accurately determined, clarifying the influence of flow rate on the temperature transfer efficiency of the inlet pipe. By controlling the circulating water to operate at the same flow rate but different temperatures, and simultaneously combining this with user topology location data, the magnitude of temperature increase or decrease of the circulating water in the inlet pipe under different temperatures can be clearly determined, understanding the mechanism of temperature's effect on heat transfer in the inlet pipe. The analysis results of the above two control variables provide accurate variable correlation data for deep learning model training, further optimizing the accuracy of the mapping relationship model between circulating water temperature, flow rate, and inlet pipe temperature changes.

[0049] By extracting circulating water temperature, flow rate, inlet pipe temperature, and user topology location data from the heating data analysis set to construct a training dataset, a mapping relationship model between the three is obtained through deep learning model training. Combining the initial and target temperature difference of low-temperature antifreeze users and the topology location, the heating time is calculated, and the start-up control time point is obtained. Based on this, the circulating water temperature and flow rate at the secondary network water supply end are precisely adjusted, which not only ensures that low-temperature antifreeze users reach the normal heating temperature on time, but also maintains the balance of supply and return flow and the stability of heating for downstream users, effectively avoiding the additional heat dissipation caused by heating imbalance and achieving precise control of energy loss.

[0050] Furthermore, a deep learning-based energy loss optimization system is provided, which includes a cycle calculation module, a topology calibration and storage module, a heating profile construction module, a heating profile prediction module, an advance control time calculation module, and a control start point calculation module.

[0051] The cycle calculation module is used to acquire secondary pipe network data and secondary pipe network interface circulating water flow data to calculate the cycle of circulating water in the secondary pipe network. The topology calibration and storage module is used to detect the connection relationship between users in the heating service area and the secondary pipe network based on the cycle, and to calibrate and store the user topology location. The heating profile construction module is used to collect the circulating water temperature of the user's inlet pipe and the secondary network water supply end temperature of the heat exchange station based on the cycle to construct the cycle heating profile of the heating service area. The advance control time calculation module is used to calculate the advance control time for low-temperature anti-freezing to heating by combining the user topology location and the real-time circulating water flow data of the secondary pipe network interface. The control start point calculation module is used to train the mapping relationship between circulating water temperature, flow rate and inlet pipe temperature changes through deep learning, and to calculate the start control time point by combining the advance control time.

[0052] The circulation cycle calculation module includes a pipeline flow acquisition unit and a circulation cycle calculation unit; the pipeline flow acquisition unit is used to acquire the pipe diameter and length data of each pipe section of the secondary pipeline and the circulating water flow data of the secondary pipeline interface; the circulation cycle calculation unit is used to calculate the total volume of circulating water and the average value of circulating water flow in the secondary pipeline, and then obtain the circulation cycle.

[0053] The topology calibration and storage module includes a service area detection unit and a topology calibration unit. The service area detection unit is used to determine the connection relationship between users and secondary pipeline branches within the heating service area and the corresponding pipeline branch segments, based on the cycle period. The topology calibration unit is used to extract user geographic coordinates and pipeline branch node numbers based on the heating as-built drawings, calibrate the user topology location, and store it in association with user identification information.

[0054] The heating profile construction module includes a temperature and heat acquisition and calculation unit and a profile construction unit. The temperature and heat acquisition and calculation unit is used to acquire temperature data at preset time intervals within the cycle, calculate the temperature ratio of circulating water in the inlet pipe of a single user, the heat supply, and the total heat supply of the heating service area. The profile construction unit is used to associate the acquisition time with the total heat supply of circulating water in the inlet pipe of the heating service area, form a dataset of the total heat supply changing over time within the cycle, and construct a heating profile.

[0055] The heating profile prediction module includes a historical data processing unit and a prediction profile generation unit. The historical data processing unit is used to obtain historical cycle heating profiles, extract relevant data, and organize them into a heating data analysis set according to the cycle number. The prediction profile generation unit is used to input the heating data analysis set into a time series prediction model, learn historical patterns, and output the prediction heating profile for the next cycle.

[0056] The advance control time calculation module includes a conversion data extraction unit and a control time derivation unit. The conversion data extraction unit is used to retrieve the user identification information of the low temperature antifreeze operation status, and extract the timestamp of the inlet pipe meeting the standard when it switches from low temperature antifreeze to normal heating and the timestamp of the control start of the heat exchange station. The control time derivation unit is used to calculate the transmission time of the circulating water through the corresponding pipeline path, and derive the advance control time for switching from low temperature antifreeze to heating.

[0057] The control start-up point calculation module includes a mapping model training unit and a start-up point derivation unit. The mapping model training unit is used to extract data from the heating data analysis set and organize it into a training dataset, which is then input into a deep learning model to train and obtain a mapping relationship model. The start-up point derivation unit is used to calculate the difference between the initial temperature and the target temperature of the inlet pipe for low-temperature antifreeze users, and derive the start-up control time point by combining the mapping relationship model and the advance control time.

[0058] Compared with the prior art, the beneficial effects of the present invention are:

[0059] 1. This invention calculates the cycle period by acquiring secondary pipeline network data and circulating water flow data, and marks and stores the user topology location in conjunction with the heating as-built drawings. It clarifies the time reference and spatial topology relationship of the heating system, and solves the problem of lack of unified time dimension and accurate spatial positioning in the existing technology of heating data acquisition and analysis. It provides accurate data support for subsequent heating profile construction and control parameter calculation, and improves the accuracy and pertinence of heating data analysis.

[0060] 2. This invention constructs a heating profile based on temperature data collected in a cyclical manner, integrates historical profiles to form a data analysis set, and uses a time series prediction model to obtain a predicted heating profile for the next cyclical period. This enables forward-looking prediction of heating demand, overcomes the limitations of existing technologies that rely on real-time data and lack advance planning for heating regulation, provides a predictive basis for heat exchange station regulation decisions, and ensures the forward-looking nature and rationality of heating regulation.

[0061] 3. This invention trains a mapping model of circulating water temperature, flow rate and inlet pipe temperature changes through deep learning, and calculates advance control time and start control point by combining user topology location and circulating water flow data. It accurately adjusts circulating water parameters, solves the problem of downstream user heating imbalance and increased energy loss when switching from low temperature antifreeze to heating, maintains system balance while ensuring user heating meets standards, effectively reduces unorganized heat dissipation and energy waste, and improves energy utilization efficiency. Attached Figure Description

[0062] Figure 1 This is a flowchart illustrating an energy loss optimization method based on deep learning according to the present invention.

[0063] Figure 2 This is a schematic diagram of the structure of an energy loss optimization system based on deep learning according to the present invention. Detailed Implementation

[0064] 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.

[0065] Example 1: As Figure 1 As shown, the present invention provides a technical solution, an energy loss optimization method based on deep learning, the energy loss optimization method comprising the following steps:

[0066] Step S1: Obtain the secondary pipeline network data information connected to the heat exchange station and the circulating water flow data information of the secondary pipeline network interface, and perform analysis and calculation to obtain the circulation cycle of the circulating water in the secondary pipeline network;

[0067] Step S1-1: Obtain the pipe diameter data and corresponding pipe length data of each pipe section of the secondary pipe network connected to the heat exchange station through the heating as-built drawings; calculate the cross-sectional area of ​​the corresponding pipe section based on the pipe diameter, and calculate the volume of a single pipe section filled with circulating water based on the length of the pipe section; sum up the volumes of all pipe sections filled with circulating water in the secondary pipe network to obtain the total volume of circulating water in the secondary pipe network.

[0068] Step S1-2: Obtain circulating water flow data at the secondary pipe network interface using a flow sensor. The secondary pipe network interface includes a secondary pipe network supply end interface and a secondary pipe network return end interface. Calculate the average circulating water flow rate at the secondary pipe network supply end interface and the secondary pipe network return end interface. Divide the total volume of circulating water in the secondary pipe network obtained in step S1-1 by the average circulating water flow rate to obtain the circulation cycle of the circulating water in the secondary pipe network.

[0069] In practice, the structural parameters of each section of the secondary pipeline network are accurately extracted from the heating as-built drawings. Based on this, the total volume of circulating water is calculated. At the same time, flow sensors are used to obtain the flow data of the supply and return water interfaces of the secondary network in real time. The circulation cycle is determined by the ratio of volume to average flow. It is important to ensure the completeness of the extracted pipeline network section parameters and avoid missing branch sections. At the same time, it is necessary to ensure the stable operation of the flow sensors to obtain reliable flow data, so as to provide a reliable time reference for subsequent steps.

[0070] Step S2: Detect the heating service area of ​​the secondary pipeline network according to the cycle, and perform topology location calibration and topology location association storage for users in the heating service area based on the heating as-built drawings;

[0071] Step S2-1: Using the cycle period obtained in step S1 as a benchmark, detect the heating service area of ​​the secondary pipeline network to determine the connection relationship between users and branches of the secondary pipeline network within the heating service area and the pipeline branch segments corresponding to each user. The heating service area refers to the area where the secondary pipeline network connected to the heat exchange station transports circulating water for heating.

[0072] Step S2-2: Based on the heating as-built drawings, extract the geographical coordinates of each user in the heating service area and the corresponding secondary pipeline branch node number, and mark the topological location of each user in the secondary pipeline; associate the marked user topological location with user identification information and store it in the database.

[0073] In practice, the connection logic between users and secondary pipeline branches within the heating service area is clarified through detection. Then, based on the heating as-built drawings, the geographical coordinates of users and the corresponding pipeline node numbers are accurately extracted to complete the topology location calibration and associated storage. Attention should be paid to the uniqueness verification of the correspondence between users and pipeline branch segments to ensure the accuracy of the association between topology location and user identification information, and to avoid deviations in subsequent location-based data analysis.

[0074] Step S3: Based on the cycle, the circulating water temperature of the inlet pipes of each user in the heating service area is detected. Combined with the circulating water temperature analysis in the secondary pipe network interface of the heat exchange station, a cycle heating profile of the heating service area is constructed.

[0075] Step S3-1: Based on the cycle obtained in Step S1, the circulating water temperature in the inlet pipes of each user in the heating service area is collected at preset time intervals within the cycle, wherein the preset time interval does not exceed the cycle; simultaneously, the circulating water temperature at the water supply end interface of the secondary pipe network of the heat exchange station is collected to obtain the density and specific heat capacity data of the circulating water in the secondary pipe network; the ratio of the circulating water temperature in the inlet pipe of each user to the circulating water temperature at the water supply end interface of the secondary pipe network is calculated and recorded as the single-user inlet pipe circulating water temperature ratio; the heating capacity of the circulating water in the inlet pipe of each user is calculated, wherein the heating capacity of the circulating water in the inlet pipe of each user is equal to the product of the circulating water density, specific heat capacity, the corresponding user's inlet pipe circulating water flow rate, and the single-user inlet pipe circulating water temperature ratio; the single-user inlet pipe circulating water temperature ratios of all users are added together and divided by the total number of users in the heating service area to obtain the average inlet pipe circulating water temperature ratio corresponding to the time interval; the heating capacity of the circulating water in the inlet pipes of all users is added together to obtain the total heating capacity of the circulating water in the inlet pipes of the heating service area corresponding to the time interval.

[0076] Step S3-2: Record and store the collection time for each preset time interval, and associate the collection time with the total heat supply of the circulating water in the inlet pipe of the heating service area in the corresponding time interval to form a dataset showing the change of the total heat supply of the circulating water in the inlet pipe of the heating service area over time within the cycle; construct a cycle heating profile of the heating service area based on this dataset, wherein the cycle heating profile includes the mapping relationship between each collection time in the cycle and the total heat supply of the circulating water in the inlet pipe of the corresponding heating service area, as well as the cumulative value of the total heat supply of the circulating water in the inlet pipe of the heating service area within the cycle;

[0077] In practical implementation, a reasonable temperature acquisition interval is set based on the cycle period. The circulating water temperature at the user's inlet pipe and the secondary pipe network water supply interface is acquired simultaneously. The heat supply for a single user and the entire service area is calculated by combining the physical parameters of the circulating water. Then, a heating profile is constructed by associating the acquisition time with the total heat supply. It is important to note that the acquisition interval setting should be able to fully cover the temperature changes within the cycle period, while ensuring that the installation location of the temperature acquisition points is representative, so that the calculated heat supply data can truly reflect the heating status.

[0078] Step S4: Acquire the historical heating profiles of the heat exchange station for multiple cycles and construct a heating data analysis set for the heating service area; process the data based on the heating data analysis set and the time series prediction model to predict the heating profile of the heating service area in the next cycle, which is denoted as the predicted cycle heating profile.

[0079] Step S4-1: Obtain multiple cycle heating profiles generated during the historical operation of the heat exchange station, and extract the collection time, total heat supply of the household inlet pipe circulating water in the heating service area, and the cumulative total heat supply within the cycle from each historical cycle heating profile; associate and organize all the extracted historical cycle-related data according to the cycle number to construct a heating data analysis set for the heating service area.

[0080] Step S4-2: Input the constructed heating service area heating data analysis set into the time series prediction model for data processing. The time series prediction model learns the time variation pattern and cumulative value variation pattern of the total heating supply of the household inlet circulating water in the heating service area within the historical cycle. The output is the heating profile of the heating service area in the next cycle, denoted as the predicted cycle heating profile. The predicted cycle heating profile includes the mapping relationship between each preset collection time in the next cycle and the corresponding predicted total heating supply of the household inlet circulating water in the heating service area, as well as the predicted cumulative value of the total heating supply of the household inlet circulating water in the heating service area in the next cycle.

[0081] In practice, key data from historical heating cycle profiles are integrated to form an analysis set. Time series prediction models are used to learn the historical heating change patterns, and then the predicted profile for the next cycle is output. It is important to select continuous and complete historical profile data to avoid affecting the model's learning effect due to missing data. At the same time, attention should be paid to the model's adaptability to heating patterns under different seasons or special weather conditions to ensure the rationality of the prediction results.

[0082] Step S5: Based on the user topology location in the heating service area and the real-time flow data of circulating water at the secondary pipeline interface of the heat exchange station, analyze and calculate the advance control time for the low-temperature antifreeze to heating switch of the heat exchange station when the low-temperature antifreeze operation status changes in the heating service area.

[0083] Step S5-1: Retrieve user identification information for users in the heating service area who are in low-temperature anti-freeze operation from the database, and determine the secondary pipeline branch section corresponding to the user in low-temperature anti-freeze operation based on the user topology location marked in step S2; extract from the heating data analysis set the timestamp when the circulating water in the inlet pipe of the user in the low-temperature anti-freeze operation state transitions to normal heating state from the low-temperature anti-freeze operation state to the normal heating state, and the timestamp when the secondary pipeline water supply end interface of the heat exchange station starts regulation in the corresponding historical cycle. The regulation refers to the adjustment operation of the circulating water temperature and circulating water flow rate of the secondary pipeline water supply end interface of the heat exchange station.

[0084] Step S5-2: Based on the user's topology location in low-temperature antifreeze operation, determine the pipeline path length between the corresponding secondary pipeline branch section and the secondary pipeline water supply end interface of the heat exchange station. Combine the real-time flow data of circulating water at the secondary pipeline interface of the heat exchange station to calculate the transmission time of circulating water flowing through the pipeline path length. Subtract the transmission time from the difference between the extracted timestamp of the circulating water in the user's inlet pipe reaching the standard temperature and the timestamp of the heat exchange station's control start-up to obtain the advance control time of the heat exchange station when the low-temperature antifreeze operation status changes in the heating service area.

[0085] In practice, user information for low-temperature antifreeze is retrieved from the database, and the corresponding pipeline path is determined based on its topological location. By extracting the timestamps of historical switching states and calculating the transmission time, the advance control time is derived. Attention should be paid to the accuracy of historical timestamp extraction to ensure that it matches the control operation of the corresponding cycle. At the same time, the calculation of the pipeline path length should strictly follow the topological connection relationship to avoid errors in the calculation of transmission time due to path deviation.

[0086] Step S6: The heating data analysis set of the heating service area is processed by deep learning to map the relationship between the temperature and flow rate of the circulating water in the secondary pipe network and the temperature change of the inlet pipe. Combined with the analysis of the early control time of low temperature antifreeze to heating, the time point of low temperature antifreeze to heating start control of the heat exchange station is obtained.

[0087] Step S6-1: Extract the temperature and flow rate data of circulating water in the secondary pipe network during historical cycles from the heating data analysis set, as well as the corresponding time-based circulating water temperature data of each user's inlet pipe within the heating service area; combine the extracted data with user topology location data and organize them according to circulating water temperature, circulating water flow rate, inlet pipe circulating water temperature, and user topology location to form a training dataset; input the training dataset into a preset deep learning model for training, and output a mapping relationship model between the temperature and flow rate of circulating water in the secondary pipe network and the changes in inlet pipe circulating water temperature;

[0088] Step S6-2: Obtain the initial temperature data of the circulating water in the user's inlet pipe under low-temperature anti-freeze operation and the target temperature data of the circulating water in the inlet pipe under the preset normal heating state within the heating service area, and calculate the temperature difference between the two; input the temperature difference into the mapping relationship model, and combine it with the topological location data of the corresponding user to output the heating time required for the circulating water in the user's inlet pipe to rise from the initial temperature to the target temperature; subtract the heating time from the low-temperature anti-freeze to heating advance control time to obtain the low-temperature anti-freeze to heating start control time of the heat exchange station, where the low-temperature anti-freeze to heating start control time is represented by the time when the heat exchange station starts to adjust the temperature of the user's inlet pipe. The circulating water temperature and flow rate at the secondary network water supply end interface are adjusted to ensure that the circulating water in the user's inlet pipe, which is in low-temperature antifreeze operation, reaches the target temperature of normal heating at a predetermined time. The total heat demand in the heating profile of the cycle is predicted, and the temperature rise demand output by the mapping relationship model is combined with the temperature rise demand. The circulating water temperature at the secondary network water supply end interface is gradually adjusted according to the predetermined time interval within the cycle. When adjusting the circulating water flow rate, based on the real-time flow data of the circulating water at the secondary network interface of the heat exchange station and the user topology location, the heat delivery demand after temperature adjustment is matched, and the circulating water flow rate is adjusted synchronously to maintain the balance of supply and return flow.

[0089] In practical implementation, multi-dimensional data is extracted from the heating data analysis set to construct a training set. A deep learning model is used to train the model to obtain the mapping relationship between circulating water parameters and the temperature change of the inlet pipe. Then, the temperature difference of users with low temperature and freeze protection and the topological location are combined to calculate the heating time. Finally, the start-up control time point is determined and the temperature rate is adjusted synchronously. Attention should be paid to the temporal correlation of each parameter in the training data to ensure that the model can accurately capture the dynamic change pattern. At the same time, the temperature rate adjustment should be carried out in a coordinated manner to avoid the imbalance of supply and return flow caused by unilateral adjustment, which will affect the overall heating stability.

[0090] Example 2, as Figure 2 As shown, the present invention provides an energy loss optimization system based on deep learning. The energy loss optimization system includes a cycle calculation module, a topology calibration and storage module, a heating profile construction module, a heating profile prediction module, an advance control time calculation module, and a control start point calculation module.

[0091] The cycle calculation module is used to acquire secondary pipe network data and secondary pipe network interface circulating water flow data to calculate the cycle of circulating water in the secondary pipe network. The topology calibration and storage module is used to detect the connection relationship between users in the heating service area and the secondary pipe network based on the cycle, and to calibrate and store the user topology location. The heating profile construction module is used to collect the circulating water temperature of the user's inlet pipe and the secondary network water supply end temperature of the heat exchange station based on the cycle to construct the cycle heating profile of the heating service area. The advance control time calculation module is used to calculate the advance control time for low-temperature anti-freezing to heating by combining the user topology location and the real-time circulating water flow data of the secondary pipe network interface. The control start point calculation module is used to train the mapping relationship between circulating water temperature, flow rate and inlet pipe temperature changes through deep learning, and to calculate the start control time point by combining the advance control time.

[0092] The circulation cycle calculation module includes a pipeline flow acquisition unit and a circulation cycle calculation unit; the pipeline flow acquisition unit is used to acquire the pipe diameter and length data of each pipe section of the secondary pipeline and the circulating water flow data of the secondary pipeline interface; the circulation cycle calculation unit is used to calculate the total volume of circulating water and the average value of circulating water flow in the secondary pipeline, and then obtain the circulation cycle.

[0093] The topology calibration and storage module includes a service area detection unit and a topology calibration unit. The service area detection unit is used to determine the connection relationship between users and secondary pipeline branches within the heating service area and the corresponding pipeline branch segments, based on the cycle period. The topology calibration unit is used to extract user geographic coordinates and pipeline branch node numbers based on the heating as-built drawings, calibrate the user topology location, and store it in association with user identification information.

[0094] The heating profile construction module includes a temperature and heat acquisition and calculation unit and a profile construction unit. The temperature and heat acquisition and calculation unit is used to acquire temperature data at preset time intervals within the cycle, calculate the temperature ratio of circulating water in the inlet pipe of a single user, the heat supply, and the total heat supply of the heating service area. The profile construction unit is used to associate the acquisition time with the total heat supply of circulating water in the inlet pipe of the heating service area, form a dataset of the total heat supply changing over time within the cycle, and construct a heating profile.

[0095] The heating profile prediction module includes a historical data processing unit and a prediction profile generation unit. The historical data processing unit is used to obtain historical cycle heating profiles, extract relevant data, and organize them into a heating data analysis set according to the cycle number. The prediction profile generation unit is used to input the heating data analysis set into a time series prediction model, learn historical patterns, and output the prediction heating profile for the next cycle.

[0096] The advance control time calculation module includes a conversion data extraction unit and a control time derivation unit. The conversion data extraction unit is used to retrieve the user identification information of the low temperature antifreeze operation status, and extract the timestamp of the inlet pipe meeting the standard when it switches from low temperature antifreeze to normal heating and the timestamp of the control start of the heat exchange station. The control time derivation unit is used to calculate the transmission time of the circulating water through the corresponding pipeline path, and derive the advance control time for switching from low temperature antifreeze to heating.

[0097] The control start-up point calculation module includes a mapping model training unit and a start-up point derivation unit. The mapping model training unit is used to extract data from the heating data analysis set and organize it into a training dataset, which is then input into a deep learning model to train and obtain a mapping relationship model. The start-up point derivation unit is used to calculate the difference between the initial temperature and the target temperature of the inlet pipe for low-temperature antifreeze users, and derive the start-up control time point by combining the mapping relationship model and the advance control time.

[0098] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, it is intended that all variations falling within the meaning and scope of equivalents of the claims be included within the present invention.

Claims

1. A deep learning-based method for optimizing energy loss, characterized in that: The energy loss optimization method includes the following steps: Step S1: Obtain the secondary pipeline network data information connected to the heat exchange station and the circulating water flow data information of the secondary pipeline network interface, and perform analysis and calculation to obtain the circulation cycle of the circulating water in the secondary pipeline network; Step S2: Detect the heating service area of ​​the secondary pipeline network according to the cycle, and perform topology location calibration and topology location association storage for users in the heating service area based on the heating as-built drawings; Step S3: Based on the cycle, the circulating water temperature of the inlet pipes of each user in the heating service area is detected. Combined with the circulating water temperature analysis in the secondary pipe network interface of the heat exchange station, a cycle heating profile of the heating service area is constructed. Step S4: Acquire the historical heating profiles of the heat exchange station for multiple cycles and construct a heating data analysis set for the heating service area; process the data based on the heating data analysis set and the time series prediction model to predict the heating profile of the heating service area in the next cycle, which is denoted as the predicted cycle heating profile. Step S5: Based on the user topology location in the heating service area and the real-time flow data of circulating water at the secondary pipeline interface of the heat exchange station, analyze and calculate the advance control time for the low-temperature antifreeze to heating switch of the heat exchange station when the low-temperature antifreeze operation status changes in the heating service area. Step S6: The heating data analysis set of the heating service area is processed by deep learning to map the relationship between the temperature and flow rate of the circulating water in the secondary pipe network and the temperature change of the inlet pipe. Combined with the analysis of the early control time of low temperature antifreeze to heating, the time point of low temperature antifreeze to heating start control of the heat exchange station is obtained. The specific steps of step S6 are as follows: Step S6-1: Extract the temperature and flow rate data of circulating water in the secondary pipe network during historical cycles from the heating data analysis set, as well as the corresponding time-based circulating water temperature data of each user's inlet pipe within the heating service area; combine the extracted data with user topology location data and organize them according to circulating water temperature, circulating water flow rate, inlet pipe circulating water temperature, and user topology location to form a training dataset; input the training dataset into a preset deep learning model for training, and output a mapping relationship model between the temperature and flow rate of circulating water in the secondary pipe network and the changes in inlet pipe circulating water temperature; Step S6-2: Obtain the initial temperature data of the circulating water in the user's inlet pipe under low-temperature antifreeze operation and the target temperature data of the circulating water in the inlet pipe under the preset normal heating state within the heating service area, and calculate the temperature difference between the two; input the temperature difference into the mapping relationship model, and combine it with the topological location data of the corresponding user to output the heating time required for the circulating water in the user's inlet pipe to rise from the initial temperature to the target temperature; subtract the heating time from the low-temperature antifreeze to heating advance control time to obtain the low-temperature antifreeze to heating start control time of the heat exchange station. The low-temperature antifreeze to heating start control time is represented by the specific time when the heat exchange station starts to adjust the circulating water temperature and flow rate at the secondary pipeline water supply end interface so that the circulating water in the user's inlet pipe under low-temperature antifreeze operation reaches the target temperature of the normal heating state within the preset time.

2. The energy loss optimization method based on deep learning according to claim 1, characterized in that: The specific steps of step S1 are as follows: Step S1-1: Obtain the pipe diameter data and corresponding pipe length data of each pipe section of the secondary pipe network connected to the heat exchange station through the heating as-built drawings; calculate the cross-sectional area of ​​the corresponding pipe section based on the pipe diameter, and calculate the volume of a single pipe section filled with circulating water based on the length of the pipe section; sum up the volumes of all pipe sections filled with circulating water in the secondary pipe network to obtain the total volume of circulating water in the secondary pipe network. Step S1-2: Obtain circulating water flow data of the secondary pipeline interface through a flow sensor. The secondary pipeline interface includes a secondary pipeline water supply end interface and a secondary pipeline water return end interface. Calculate the average circulating water flow rate at the water supply end interface and the water return end interface of the secondary pipe network; divide the total volume of circulating water in the secondary pipe network obtained in step S1-1 by the average circulating water flow rate to obtain the circulation cycle of circulating water in the secondary pipe network.

3. The energy loss optimization method based on deep learning according to claim 2, characterized in that: The specific steps of step S2 are as follows: Step S2-1: Using the cycle period obtained in step S1 as a benchmark, detect the heating service area of ​​the secondary pipeline network to determine the connection relationship between users and branches of the secondary pipeline network within the heating service area and the pipeline branch segments corresponding to each user. The heating service area refers to the area where the secondary pipeline network connected to the heat exchange station transports circulating water for heating. Step S2-2: Based on the heating as-built drawings, extract the geographical coordinates of each user in the heating service area and the corresponding secondary pipeline branch node number, and mark the topological location of each user in the secondary pipeline; associate the marked user topological location with the user identification information and store it in the database.

4. The energy loss optimization method based on deep learning according to claim 3, characterized in that: The specific steps of step S3 are as follows: Step S3-1: Based on the cycle obtained in Step S1, the circulating water temperature in the inlet pipes of each user in the heating service area is collected at preset time intervals within the cycle, wherein the preset time interval does not exceed the cycle; simultaneously, the circulating water temperature at the water supply end interface of the secondary pipe network of the heat exchange station is collected to obtain the density and specific heat capacity data of the circulating water in the secondary pipe network; the ratio of the circulating water temperature in the inlet pipe of each user to the circulating water temperature at the water supply end interface of the secondary pipe network is calculated and recorded as the single-user inlet pipe circulating water temperature ratio; the heating capacity of the circulating water in the inlet pipe of each user is calculated, wherein the heating capacity of the circulating water in the inlet pipe of each user is equal to the product of the circulating water density, specific heat capacity, the corresponding user's inlet pipe circulating water flow rate, and the single-user inlet pipe circulating water temperature ratio; the single-user inlet pipe circulating water temperature ratios of all users are added together and divided by the total number of users in the heating service area to obtain the average inlet pipe circulating water temperature ratio corresponding to the time interval; the heating capacity of the circulating water in the inlet pipes of all users is added together to obtain the total heating capacity of the circulating water in the inlet pipes of the heating service area corresponding to the time interval. Step S3-2: Record and store the collection time of each preset time interval, and associate the collection time with the total heat supply of the circulating water in the heating service area in the corresponding time interval to form a dataset showing the change of the total heat supply of the circulating water in the heating service area in the time interval over time. Based on this dataset, a cyclic heating profile of the heating service area is constructed. The cyclic heating profile includes the mapping relationship between each collection time in the cycle and the total heat supply of the circulating water in the inlet pipe of the corresponding heating service area, as well as the cumulative value of the total heat supply of the circulating water in the inlet pipe of the heating service area in the cycle.

5. The energy loss optimization method based on deep learning according to claim 4, characterized in that: The specific steps of step S4 are as follows: Step S4-1: Obtain multiple cycle heating images generated during the historical operation of the heat exchange station, and extract the collection time, total heat supply of the household inlet pipe in the heating service area, and cumulative total heat supply within the cycle contained in each historical cycle heating image. All extracted historical cycle-related data are linked and organized according to cycle number to construct a heating data analysis set for the heating service area. Step S4-2: Input the constructed heating service area heating data analysis set into the time series prediction model for data processing. The time series prediction model is used to learn the time variation pattern and cumulative value variation pattern of the total heating of the household circulating water in the heating service area within the historical cycle. The output is a heating profile of the heating service area in the next cycle, denoted as the predicted cycle heating profile. The predicted cycle heating profile includes the mapping relationship between each preset collection time in the next cycle and the total heat supply of the circulating water in the inlet pipe of the corresponding predicted heating service area, as well as the predicted cumulative value of the total heat supply of the circulating water in the inlet pipe of the heating service area in the next cycle.

6. The energy loss optimization method based on deep learning according to claim 5, characterized in that: The specific steps of step S5 are as follows: Step S5-1: Retrieve user identification information for users in the heating service area who are in low-temperature anti-freeze operation from the database, and determine the secondary pipeline branch section corresponding to the user in low-temperature anti-freeze operation based on the user topology location marked in step S2; extract from the heating data analysis set the timestamp when the circulating water in the inlet pipe of the user in the low-temperature anti-freeze operation state transitions to normal heating state from the low-temperature anti-freeze operation state to the normal heating state, and the timestamp when the secondary pipeline water supply end interface of the heat exchange station starts regulation in the corresponding historical cycle. The regulation refers to the adjustment operation of the circulating water temperature and circulating water flow rate of the secondary pipeline water supply end interface of the heat exchange station. Step S5-2: Based on the user topology location in low-temperature antifreeze operation, determine the pipeline path length between the corresponding secondary pipeline branch section and the secondary pipeline water supply end interface of the heat exchange station, and calculate the transmission time of the circulating water through the pipeline path length by combining the real-time flow data of the circulating water at the secondary pipeline interface of the heat exchange station. The difference between the timestamp of the extracted user's inlet pipe circulating water reaching the standard temperature and the timestamp of the heat exchange station's control start is subtracted from the transmission time to obtain the time when the heat exchange station makes advance control when the low temperature antifreeze operation status changes in the heating service area. This time is recorded as the advance control time for switching from low temperature antifreeze to heating.

7. A deep learning-based energy loss optimization system, applied to the deep learning-based energy loss optimization method according to any one of claims 1-6, characterized in that: The energy loss optimization system includes a cycle calculation module, a topology calibration and storage module, a heating profile construction module, a heating profile prediction module, an advance control time calculation module, and a control start point calculation module. The cycle calculation module is used to acquire secondary pipe network data information and secondary pipe network interface circulating water flow data information, and calculate the cycle of circulating water in the secondary pipe network; the topology calibration and storage module is used to detect the connection relationship between users in the heating service area and the secondary pipe network according to the cycle, and to calibrate and associate the user topology location; the heating profile construction module is used to collect the circulating water temperature of the user's inlet pipe and the water supply end temperature of the secondary pipe network of the heat exchange station based on the cycle, and to construct a cycle heating profile of the heating service area. The advance control time calculation module is used to calculate the advance control time for low temperature antifreeze to heating by combining the user topology location and the real-time flow data of circulating water at the secondary pipe network interface. The control start-up point calculation module is used to train the mapping relationship between circulating water temperature, flow rate and inlet pipe temperature changes through deep learning, and calculate the start-up control time point in combination with the advance control time.

8. The energy loss optimization system based on deep learning according to claim 7, characterized in that: The circulation cycle calculation module includes a pipeline flow acquisition unit and a circulation cycle calculation unit; the pipeline flow acquisition unit is used to acquire the pipe diameter and length data of each pipe section of the secondary pipeline network and the circulating water flow data of the secondary pipeline network interface; the circulation cycle calculation unit is used to calculate the total volume of circulating water and the average value of circulating water flow in the secondary pipeline network, and then obtain the circulation cycle. The topology calibration and storage module includes a service area detection unit and a topology calibration unit. The service area detection unit is used to determine the connection relationship between users and secondary pipeline branches within the heating service area and the corresponding pipeline branch segments, based on the cycle period. The topology calibration unit is used to extract user geographic coordinates and pipeline branch node numbers based on the heating as-built drawings, calibrate the user topology location, and store it in association with user identification information.

9. The energy loss optimization system based on deep learning according to claim 7, characterized in that: The heating profile construction module includes a temperature and heat acquisition and calculation unit and a profile construction unit. The temperature and heat acquisition and calculation unit is used to acquire temperature data at preset time intervals within the cycle, calculate the temperature ratio of circulating water in the inlet pipe of a single user, the heat supply, and the total heat supply of the heating service area. The profile construction unit is used to associate the acquisition time with the total heat supply of circulating water in the inlet pipe of the heating service area, form a dataset of the total heat supply changing over time within the cycle, and construct a heating profile. The heating profile prediction module includes a historical data processing unit and a prediction profile generation unit. The historical data processing unit is used to obtain historical cycle heating profiles, extract relevant data, and organize them into a heating data analysis set according to the cycle number. The prediction profile generation unit is used to input the heating data analysis set into a time series prediction model, learn historical patterns, and output the prediction heating profile for the next cycle.

10. The energy loss optimization system based on deep learning according to claim 7, characterized in that: The advance control time calculation module includes a conversion data extraction unit and a control time derivation unit; the conversion data extraction unit is used to retrieve the user identification information of the low temperature anti-freeze operation status, and extract the time stamp of the inlet pipe meeting the standard when it switches from low temperature anti-freeze to normal heating and the time stamp of the heat exchange station control start-up; The control time derivation unit is used to calculate the transmission time of circulating water through the corresponding pipeline path and derive the low temperature antifreeze to heating advance control time. The regulation initiation point calculation module includes a mapping model training unit and an initiation point derivation unit; The mapping model training unit is used to extract data from the heating data analysis set and associate and organize it into a training dataset, which is then input into a deep learning model to train and obtain a mapping relationship model. The start-up point derivation unit is used to calculate the difference between the initial temperature and the target temperature of the user's inlet pipe for low-temperature antifreeze, and derive the start-up control time point by combining the mapping relationship model and the advance control time.

Images