Intelligent heat supply method and system
By using intelligent heating methods and real-time data acquisition and machine learning models to optimize the heating system, the problems of lagging regulation and energy waste in traditional heating systems have been solved, and efficient and stable heating management has been achieved.
Patent Information
- Application Number
- CN202511580577.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-31
- Publication Date
- 2026-02-03
AI Technical Summary
Traditional centralized heating systems suffer from lagging regulation and cannot respond promptly to complex dynamic environmental factors and user needs, resulting in energy waste and poor user comfort. Furthermore, they lack the ability to optimize multiple heat sources in a coordinated manner.
The intelligent heating method is adopted, which realizes dynamic control command generation and adjustment through real-time data acquisition, preprocessing, heat load prediction and energy efficiency optimization, combined with LSTM model and particle swarm algorithm, and uses cloud platform for real-time feedback and optimization.
It enables the heating system to accurately match user needs, improves energy efficiency, reduces operating costs, and ensures the stability and adaptability of the heating process.
Smart Images
Figure CN121452591A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of heat supply engineering, in particular to an intelligent heat supply method and system. BACKGROUND
[0002] The operation and regulation of traditional centralized heat supply systems have long relied on manual experience and fixed operation and regulation curves, and are facing profound challenges. The regulation mode is essentially a kind of “lagging regulation” based on historical experience, which cannot respond to complex and dynamically changing environmental factors and actual user-side demands in a timely manner, and generally leads to excessive or insufficient heat supply, which not only affects the comfort experience of users, but also causes huge energy waste. At the same time, heat supply pipe networks, especially large and complex pipe networks, generally have serious hydraulic imbalance. In order to ensure the room temperature of users at unfavorable ends, the system has to adopt a “large flow and small temperature difference” extensive operation mode, which leads to high power consumption of circulating water pumps. On the user side, due to the lack of effective fine monitoring and management means, phenomena such as user window opening for heat dissipation and overheating cannot be curbed, and heat supply is continued during the unattended period of buildings, further exacerbating the invalid consumption of energy.
[0003] In addition, with the access of renewable energy and industrial waste heat and other heat sources, the traditional system lacks intelligent decision-making capabilities for online analysis and optimal allocation of the costs and efficiencies of various heat sources, and it is difficult to achieve multi-energy complementation and global economic operation. Therefore, the existing technical system has been difficult to meet the development requirements of modern smart cities and green buildings in terms of energy consumption, cost and user experience, and an intelligent heat supply method capable of realizing system perception, prediction, decision-making and execution is urgently needed. SUMMARY
[0004] The purpose of the present application is to provide an intelligent heat supply method which can solve the problems of lagging regulation, high energy consumption, poor comfort and difficulty in multi-heat source cooperation of traditional heat supply systems.
[0005] The present application provides an intelligent heat supply method, which comprises the following steps: S1. Real-time collection of outdoor meteorological parameters and multi-dimensional operation data of heat sources, heat supply pipe networks, heat stations and user ends; S2. Preprocessing of the collected data, performing outlier rejection and data standardization processing; S3. Heat load prediction based on the processed data, and energy efficiency optimization, generating control instructions according to time; S4. After the intelligent execution layer receives and executes the control instructions, it feeds back the execution effect, and the cloud-side intelligent analysis platform compares the deviation between the execution effect and the prediction result, and dynamically adjusts the control instructions.
[0006] Preferably, the multi-dimensional operation data includes temperature, pressure, flow and equipment status.
[0007] Preferably, the step of performing outlier rejection and data standardization processing includes rejecting outliers by threshold judgment or trend analysis, and converting data into standardized data recognizable by the cloud intelligent analysis platform.
[0008] Preferably, the heat load prediction adopts a machine learning model based on a long short-term memory network (LSTM), and calculates and outputs a heat load prediction value according to historical data, real-time data and a 72-hour weather forecast.
[0009] Preferably, the energy efficiency optimization specifically includes taking the minimum total operation cost and / or the maximum overall energy efficiency as an objective function, considering heat source efficiency, power transmission and distribution consumption, heat network loss and time-of-use electricity price factors, and calculating the heat source output proportion, circulating water pump frequency and pipe network valve opening degree through a particle swarm optimization algorithm.
[0010] Preferably, the control instruction in the step S3 includes a heat source output set value, a circulating water pump frequency set value, a pipe network regulating valve opening degree and a user end intelligent valve opening degree.
[0011] Preferably, the method further includes a fault handling step of automatically switching to a preset backup control mode and generating an alarm information when a device fault or communication interruption is detected.
[0012] The application provides an intelligent heating system, comprising: a data acquisition layer for acquiring multi-dimensional operation data of outdoor meteorological parameters and heat sources, heating pipe networks, heat stations and user ends in real time; an edge computing gateway for pre-processing the acquired data, performing outlier rejection and data standardization processing, and being in communication connection with the data acquisition layer; a cloud intelligent analysis platform for performing heat load prediction and energy efficiency optimization on the processed data, generating control instructions according to time, comparing the deviation between the execution effect and the prediction result, and dynamically adjusting the control instructions; the cloud intelligent analysis platform is in communication connection with the edge computing gateway; an intelligent execution layer for receiving and executing the control instructions and feeding back the execution effect; the intelligent execution layer is in communication connection with the cloud intelligent analysis platform and the edge computing gateway.
[0013] The application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions which, when executed, cause the processor to implement the steps of the above intelligent heating method.
[0014] The application also provides a storage medium for storing computer executable instructions, which, when executed, implement the steps of the intelligent heating method.
[0015] Advantages: The application can accurately match the actual heating demand of users through intelligent perception, analysis, decision-making and execution, can improve system energy efficiency and reduce operation cost while ensuring the stability and reliability of the heating process, and comprehensively improves the intelligent management level and comprehensive benefits of the heating system.
[0016] The application collects multi-dimensional operation data and meteorological parameters in real time, combines data preprocessing to ensure the reliability of input information, and provides a solid foundation for subsequent analysis. The heat load prediction based on the LSTM model can accurately grasp the trend of heating demand changes, and the optimization strategy with system total operation cost and energy efficiency as the target, combined with the particle swarm algorithm, can reasonably allocate the heat source output, pump frequency and valve opening, and realize efficient use of resources. The dynamic adjustment mechanism of the control instruction forms a closed loop from instruction execution to effect feedback, which can correct deviations in time and ensure the accuracy and adaptability of heating. The fault handling mechanism automatically switches to standby mode and alarms when the equipment or communication is abnormal, ensuring the stability of system operation. BRIEF DESCRIPTION OF DRAWINGS
[0017] In order to more clearly illustrate the specific embodiments of the application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.
[0018] Figure 1 A flow chart of an intelligent heating method is provided for one or more embodiments of the present specification; Figure 2 A module composition diagram of an intelligent heating system is provided for one or more embodiments of the present specification; Figure 3 A structural schematic diagram of an electronic device is provided for one or more embodiments of the present specification. DETAILED DESCRIPTION
[0019] The technical solutions of the application will be described below in conjunction with the embodiments, obviously, the described embodiments are part of the embodiments of the application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.
[0020] In the description of the present application, it should be understood that the terms "center", "longitudinal", "transverse", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", and the like indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and therefore cannot be understood as limiting the present application.
[0021] In addition, the terms "first" and "second" are only for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined with "first" and "second" can include one or more of the features explicitly or implicitly. In the description of the present application, "a plurality of" means two or more, unless otherwise specifically limited. In addition, the terms "mounting", "connecting", "connecting" should be broadly understood, for example, it can be fixedly connected, or it can be detachably connected, or integrally connected; it can be mechanically connected, or it can be electrically connected; it can be directly connected, or it can be indirectly connected through an intermediate medium, or it can be the communication between two elements. For those skilled in the art, the specific meaning of the above terms in the present application can be understood according to the specific circumstances.
[0022] Method embodiment An intelligent heating method, as shown in Figure 1 comprises the following steps: S1. Real-time acquisition of outdoor meteorological parameters and multi-dimensional operation data of heat sources, heating pipe networks, heat stations and user terminals; the multi-dimensional operation data includes temperature, pressure, flow and equipment state. The equipment state is collected in a state change trigger mode, and the temperature, pressure and flow are collected in a timing high-frequency mode by sensors; S2. Preprocessing the collected data, performing outlier rejection and data standardization processing; The outlier rejection and data standardization processing includes rejecting outliers by threshold judgment or trend analysis, and converting the data into standardized data recognizable by the cloud intelligent analysis platform.
[0023] Threshold judgment: set a reasonable data range (such as temperature 0-100°C, pressure 0-2.5MPa), and data outside the range is considered abnormal and automatically rejected; Trend analysis: use sliding window or exponential smoothing method to detect data mutation points, and data that does not match the historical trend is considered abnormal.
[0024] S3. Based on the processed data, heat load prediction is performed, and energy efficiency optimization is performed to generate control instructions according to time; The heat load prediction adopts a machine learning model based on a long short-term memory network (LSTM), and according to historical data, real-time data and 72h weather forecast, the heat load prediction value is calculated and output.
[0025] The energy efficiency optimization specific steps include taking the minimum total operation cost and / or the highest overall energy efficiency as the objective function, considering the heat source efficiency, power transmission and distribution consumption, heat network loss, time-of-use electricity price factor, and searching for the optimal solution through a particle swarm optimization algorithm. The particle represents the control variable (such as heat source output ratio, circulating water pump frequency, valve opening), and the fitness function is calculated based on the objective function. The heat source output ratio, circulating water pump frequency and pipe network valve opening are calculated.
[0026] The control instructions include heat source output set value, circulating water pump frequency set value, pipe network regulating valve opening, and user end intelligent valve opening.
[0027] S4. After the intelligent execution layer 740 receives and executes the control instructions, the execution effect is fed back, and the cloud intelligent analysis platform 730 compares the deviation between the execution effect and the prediction result, and dynamically adjusts the control instructions; The intelligent execution layer 740 receives the control instructions and executes, adjusts the equipment running state; after execution, the running effect data is collected in real time, and fed back to the cloud intelligent analysis platform 730; The cloud intelligent analysis platform 730 compares the deviation between the execution effect and the prediction result, if the deviation exceeds the preset tolerance, the adjustment mechanism is triggered: the heat load prediction and energy efficiency optimization model is re-run, and the corrected control instruction is generated; S5. When detecting equipment failure or communication interruption, automatically switch to the preset backup control mode, and generate alarm information; The backup control mode is maintained by the edge computing gateway 720 when the communication with the cloud intelligent analysis platform 730 is interrupted, according to the last received effective strategy or local preset strategy, and synchronizes the data after the communication is restored.
[0028] System embodiment An intelligent heating system, as shown in Figure 2 includes: The data acquisition layer 710 is used to collect multi-dimensional running data of outdoor meteorological parameters and heat sources, heating pipe networks, heat stations and user terminals in real time; The edge computing gateway 720 is used to pre-process the collected data, perform outlier rejection and data standardization processing, and the edge computing gateway 720 is in communication connection with the data acquisition layer 710; The cloud intelligent analysis platform 730 is configured to perform heat load prediction on the processed data, perform energy efficiency optimization, generate control instructions according to time, compare the deviation between the execution effect and the prediction result, and dynamically adjust the control instructions; the cloud intelligent analysis platform 730 is in communication connection with the edge computing gateway 720. The intelligent execution layer 740 is configured to receive and execute the control instructions and feed back the execution effect; the intelligent execution layer 740 is in communication connection with the cloud intelligent analysis platform 730 and the edge computing gateway 720.
[0029] The embodiment of the present application is a system embodiment corresponding to the above-mentioned method embodiment, and the specific operation of each module can be understood with reference to the description of the method embodiment, which will not be repeated here.
[0030] Device embodiment 1 The present application also provides an electronic device, such as Figure 3 as shown, comprising: a processor 1020; and a memory 1010 arranged to store computer executable instructions which, when executed, cause the processor 1010 to implement the following steps of the intelligent heating method: S1. Real-time collection of outdoor meteorological parameters and multi-dimensional operation data of heat sources, heating pipe networks, heat stations and user terminals; S2. Preprocessing of the collected data, performing outlier rejection and data standardization processing; S3. Heat load prediction based on the processed data, and energy efficiency optimization, generating control instructions according to time; S4. After the intelligent execution layer receives and executes the control instructions, it feeds back the execution effect, and the cloud intelligent analysis platform compares the deviation between the execution effect and the prediction result, and dynamically adjusts the control instructions.
[0031] Device embodiment 2 The present application also provides a storage medium for storing computer executable instructions which, when executed, implement the following steps of the intelligent heating method: S1. Real-time collection of outdoor meteorological parameters and multi-dimensional operation data of heat sources, heating pipe networks, heat stations and user terminals; S2. Preprocessing of the collected data, performing outlier rejection and data standardization processing; S3. Heat load prediction based on the processed data, and energy efficiency optimization, generating control instructions according to time; S4. After the intelligent execution layer receives and executes the control instructions, it feeds back the execution effect, and the cloud intelligent analysis platform compares the deviation between the execution effect and the prediction result, and dynamically adjusts the control instructions.
[0032] The computer readable storage medium in the embodiments includes, but is not limited to, ROM, RAM, magnetic or optical disk, etc.
[0033] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit the present application; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can still be modified, or some or all of the technical features can be replaced by equivalents; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.
Claims
1. A method of intelligent heating, characterized by, The method comprises the following steps: S1. Real-time acquisition of outdoor meteorological parameters and multi-dimensional operation data of heat sources, heat supply pipe networks, heat stations and user terminals; S2. Preprocessing of the collected data, performing outlier rejection and data standardization processing; S3. Heat load prediction based on the processed data, and energy efficiency optimization, generating control instructions according to time; S4. After the intelligent execution layer receives and executes the control instructions, it feeds back the execution effect, and the cloud intelligent analysis platform compares the deviation between the execution effect and the prediction result, and dynamically adjusts the control instructions.
2. The intelligent heating method according to claim 1, wherein, The multi-dimensional operation data includes temperature, pressure, flow and equipment state.
3. The intelligent heating method of claim 1, wherein, The execution of outlier rejection and data standardization processing includes outlier rejection through threshold judgment or trend analysis, and conversion of data into standardized data recognizable by the cloud intelligent analysis platform.
4. The intelligent heating method of claim 1, wherein, The heat load prediction adopts a machine learning model based on long short-term memory network LSTM, and calculates the heat load prediction value according to historical data, real-time data and future 72h weather forecast.
5. The intelligent heating method of claim 1, wherein, The specific steps of energy efficiency optimization include taking the minimum total operation cost and / or the highest overall energy efficiency as the objective function, considering heat source efficiency, power consumption, heat network loss, time-of-use electricity price factors, calculating the output proportion of each heat source, circulating water pump frequency and pipe network valve opening degree through particle swarm optimization algorithm.
6. The intelligent heating method of claim 1, wherein, The control instructions in step S3 include heat source output set value, circulating water pump frequency set value, pipe network regulating valve opening degree and user terminal intelligent valve opening degree.
7. The intelligent heating method of claim 1, wherein, The method further comprises a fault handling step: when a device fault or communication interruption is detected, automatically switch to a preset backup control mode and generate an alarm information.
8. An intelligent heating system, characterized by It comprises: A data acquisition layer for real-time acquisition of outdoor meteorological parameters and multi-dimensional operation data of heat sources, heat supply pipe networks, heat stations and user terminals; An edge computing gateway for preprocessing of the collected data, performing outlier rejection and data standardization processing, the edge computing gateway being in communication connection with the data acquisition layer; A cloud intelligent analysis platform for heat load prediction of the processed data, energy efficiency optimization, generation of control instructions according to time, comparison of the deviation between the execution effect and the prediction result, and dynamic adjustment of the control instructions; the cloud intelligent analysis platform being in communication connection with the edge computing gateway; An intelligent execution layer for receiving and executing control instructions and feeding back execution effect; the intelligent execution layer being in communication connection with the cloud intelligent analysis platform and the edge computing gateway.
9. An electronic device, comprising: It comprises: A processor; And A memory arranged to store computer executable instructions which, when executed, cause the processor to implement the steps of the intelligent heating method as claimed in any one of claims 1 to 7.
10. A storage medium, characterized by A memory arranged to store computer executable instructions which, when executed, cause the processor to implement the steps of the intelligent heating method as claimed in any one of claims 1 to 7.