Method for optimizing hot water circulation efficiency in a building heating system

Abstract

The application discloses a hot water circulation efficiency optimization method in a building heating system, and belongs to the technical field of building energy management and heating control. The method comprises the following steps: step 1, obtaining historical operation data and current system parameters of the building heating system; step 2, constructing a three-dimensional working condition characteristic library containing load characteristics, time dimensions and operation modes, and pre-calculating the occurrence probability and importance coefficient of each working condition; step 3, collecting current operation data of the building heating system in real time; step 4, identifying the operation working condition type of the current system, and obtaining the characteristic weight corresponding to the working condition; step 5, quantitatively evaluating the hydraulic balance, thermal distribution characteristics and energy consumption level of the system under the current working condition, and generating a working condition operation characteristic evaluation report; and step 6, judging whether the current operation state meets the preset efficiency standard according to the working condition operation characteristic evaluation report.

Description

Technical Field

[0001] This invention relates to the technical field of building energy management and heating control, and more particularly to a method for optimizing the hot water circulation efficiency in a building heating system. Background Technology

[0002] With the acceleration of urbanization and the continuous growth of building energy demand, centralized heating systems have become one of the important ways of utilizing energy in modern buildings. However, in traditional building heating systems, the efficiency of hot water circulation is generally affected by a variety of factors, such as hydraulic imbalance in the pipe network, uneven heat distribution, insufficient heating at the terminal, and high system energy consumption. Especially in complex building complexes or large-scale district heating systems, the system operating parameters are difficult to dynamically optimize due to the coupled effects of multiple factors such as ambient temperature fluctuations, changes in user load, and equipment performance degradation, making it difficult to balance heating comfort and energy utilization efficiency.

[0003] In existing technologies, optimization of building heating systems mainly focuses on single-level improvements, such as hydraulic balance regulation of the pipe network, control optimization of heat exchange stations, or frequency conversion control of circulating pumps. While these methods improve operational efficiency in specific areas, they lack a comprehensive identification and dynamic optimization mechanism for the overall system operating conditions, making it difficult to cope with complex operating environments involving multiple operating conditions and variables. Furthermore, traditional heating systems generally rely on manual experience or static parameter settings during regulation, lacking adaptive optimization capabilities based on real-time data, resulting in energy waste and decreased operational efficiency.

[0004] In recent years, with the development of the Internet of Things and intelligent control technologies, the data acquisition and analysis capabilities of building heating systems have been significantly enhanced, providing a foundation for system-level optimized control. However, how to fully utilize historical operating data to construct system characteristic models and combine them with real-time monitoring information to achieve the coordinated integration of operating condition identification, parameter optimization, and hierarchical control still faces challenges such as algorithm complexity, response lag, and insufficient adaptability.

[0005] In conclusion, how to dynamically optimize the hot water circulation efficiency in building heating systems while balancing system energy consumption, heating balance, and operational stability has become an urgent technical problem to be solved. Summary of the Invention

[0006] In view of the technical problems mentioned in the background section, a method for optimizing the hot water circulation efficiency in a building heating system is provided.

[0007] The technical means employed in this invention are as follows:

[0008] A method for optimizing hot water circulation efficiency in a building heating system includes the following steps:

[0009] Step 1: Obtain historical operating data and current system parameters of the building heating system; the historical operating data includes: load characteristic data, time dimension data, and operating mode data; the current system parameters include: pipeline topology, heat exchange equipment configuration, user load distribution, and design operating parameters.

[0010] Step 2: Based on the historical operating data, construct a three-dimensional operating condition feature library that includes load characteristics, time dimension and operating mode, and pre-calculate the occurrence probability and importance coefficient of different operating conditions;

[0011] Step 3: Collect the current operating data of the building heating system in real time; the current operating data includes: temperature of each node, flow rate of each node, pressure of each node, ambient temperature of each node, and user heat load parameters;

[0012] Step 4: Extract the feature vector of the current running data, perform similarity matching with the three-dimensional operating condition feature library, identify the current operating condition type of the system, and obtain the feature weight corresponding to the current operating condition.

[0013] Step 5: Based on the current operating condition type of the system and the current operating data, establish a three-domain coupled simulation model of hydraulic characteristics, thermal characteristics and control strategy; quantitatively evaluate the hydraulic balance, thermal distribution characteristics and energy consumption level of the current system, and generate an operating condition characteristic evaluation report.

[0014] Step 6: Determine whether the current operating status meets the preset efficiency standard based on the operating condition characteristic evaluation report;

[0015] Step 7: If satisfied, proceed to step 12 to continue real-time monitoring and adaptive adjustment; if not satisfied, construct a weighted multi-objective optimization function that includes hydraulic balance, system energy consumption, heating comfort, and operating cost, generate a candidate parameter set using a global search strategy, and optimize the candidate parameters using a local refinement strategy to obtain the optimal combination of operating parameters under the current operating conditions.

[0016] Furthermore, the historical operating data obtained in step 1 should cover no less than two consecutive complete heating seasons;

[0017] The load characteristic data includes: instantaneous heat load values ​​for each time period, peak load occurrence time, load change rate, and load distribution characteristics of different building functional areas;

[0018] The time dimension data includes multi-scale time labels at the hour, day, week, and month levels, and indicates the time attributes for holidays, weekdays, and special weather conditions;

[0019] The operating mode data includes: control strategies, equipment start-up and shutdown combinations, and historical set values ​​of adjustment parameters for each stage of the initial heating period, stable heating period, and final heating period.

[0020] Furthermore, the construction process of the three-dimensional working condition feature library in step 2 includes:

[0021] Historical operational data is cleaned and normalized to remove abnormal fluctuation data points and fill in missing data segments;

[0022] Operating conditions are classified in different dimensions: In terms of load characteristics, the operating data is divided into four typical intervals: light load, medium load, heavy load, and overload; in terms of time, four time periods are distinguished: weekday daytime, weekday nighttime, weekend, and holidays; and in terms of operating mode, three typical operating states are identified: energy-saving mode, standard mode, and emergency mode.

[0023] Cartesian product logic is used to combine different load ranges, time periods, and operating modes to generate a set of operating condition combinations;

[0024] For each working condition combination, calculate its frequency of occurrence in historical data, and determine the probability distribution characteristics of each working condition combination based on the frequency of occurrence.

[0025] Based on the degree of impact of each operating condition combination on system energy consumption and heating quality, a corresponding importance coefficient is assigned;

[0026] By integrating the characteristics, frequency of occurrence, probability distribution, and importance coefficients of various working conditions, a three-dimensional working condition feature library is finally constructed.

[0027] Furthermore, in step 3, the real-time acquisition of the current operating data of the building heating system is achieved by deploying a multi-level sensor network;

[0028] On the heat source side, supply and return water temperature sensors, flow meters, and pressure transmitters are installed, with measurement accuracies reaching ±0.5℃, ±0.5%, and ±0.25%, respectively. At key nodes along the pipeline network, including branch nodes, user access points, and pipeline ends, temperature and pressure monitoring units are deployed, with data acquisition intervals set to 1–5 minutes. On the user side, smart heat meters collect supply and return water temperatures, instantaneous flow rates, and cumulative heat consumption data for each user. Ambient temperature data, including outdoor dry-bulb temperature and meteorological parameters affecting heating load, is collected and updated using distributed weather stations.

[0029] Further, step 4 involves extracting the feature vector of the current operating data, performing similarity matching with the three-dimensional operating condition feature library, and identifying the current operating condition type of the system. This includes the following steps:

[0030] Based on the operational data, load characteristic parameters, time characteristic parameters, and operational status characteristic parameters are extracted. The load characteristic parameters are used to characterize the system load level, including: total heat load, load fluctuation amplitude, and load change trend. The time characteristic parameters are used to reflect the influence of the time dimension, including: current time, weekday attribute, and whether it is a holiday. The operational status characteristic parameters are used to describe the equipment operating status, including: circulating pump operating frequency, regulating valve opening, and heat exchanger heat exchange.

[0031] A weighted fusion method is used to construct a comprehensive feature vector, and the weight coefficients of each feature parameter are dynamically adjusted according to the contribution of each feature parameter to the accuracy of the working condition identification.

[0032] Taking into account both the numerical differences and the similarity of the changing trends of the feature values, the constructed comprehensive feature vector is matched with the pre-established three-dimensional working condition feature library for similarity.

[0033] When the similarity exceeds a preset threshold, it is determined to be the same working condition type as the sample in the working condition feature library; if the similarity does not reach the threshold, a new working condition identification process is triggered, and the newly identified working condition features are included in the working condition feature library and the relevant parameters and weight coefficients are updated, thereby realizing the adaptive expansion and dynamic optimization of the feature library.

[0034] Furthermore, the weighted multi-objective optimization function constructed in step 7 is:

[0035] The objective function is equal to the hydraulic balance sub-objective multiplied by its weight coefficient, plus the system energy consumption sub-objective multiplied by its weight coefficient, plus the heating comfort sub-objective multiplied by its weight coefficient, plus the operating cost sub-objective multiplied by its weight coefficient.

[0036] The hydraulic balance sub-objective is characterized by the sum of squares of the flow deviations in each loop, with a weighting coefficient set at 0.25 under standard operating conditions. The system energy consumption sub-objective includes a weighted combination of heat source energy consumption and power consumption in the transmission and distribution system, with the weighting coefficient dynamically adjusted according to current energy prices and set between 0.30 and 0.40. The heating comfort sub-objective is comprehensively evaluated through indoor temperature deviation, temperature fluctuation range, and user complaint rate indicators, with a weighting coefficient set at 0.30 during severe cold periods and reduced to 0.20 during transitional seasons. The operating cost sub-objective comprehensively considers energy costs, labor costs, and equipment wear and tear, with a weighting coefficient of 0.15.

[0037] Furthermore, the hot water circulation efficiency optimization method further includes the following steps:

[0038] Step 8: Perform operating condition disturbance simulation based on the optimal combination of operating parameters. By introducing load fluctuation disturbance, external temperature change disturbance and equipment performance deviation disturbance, calculate the robustness score of the optimal operating parameters under actual complex operating conditions.

[0039] Step 9: Determine whether the stability of the optimal combination of operating parameters meets the preset robustness requirements based on the robustness score.

[0040] Step 10: If the stability of the optimal combination of operating parameters does not meet the robustness requirement, then adaptive optimization of the parameters is performed based on the robustness score, the weight coefficients or constraints in the optimization function are adjusted, and the optimal combination of operating parameters is solved again until the robustness requirement is met.

[0041] Step 11: If the stability of the optimal combination of operating parameters meets the robustness requirement, then establish a hierarchical control system including a system-level coordination layer, a regional-level adjustment layer, and a device-level execution layer based on the verified optimal operating parameters.

[0042] Step 12: Optimize the control parameters online, monitor the deviation between the system operating status and the target status in real time, adaptively switch the operating mode according to the changes in operating conditions, and send the optimized control commands to the execution units at each level.

[0043] Step 13: When a significant change in operating conditions or a deviation in operating efficiency is detected, return to the operating condition feature identification step and re-identify the operating conditions and optimize the parameters.

[0044] Furthermore, the control parameters are optimized online, the deviation between the system's operating status and the target status is monitored in real time, and the operating mode is adaptively switched according to changes in operating conditions, including the following steps:

[0045] A rolling optimization time-domain window is set, the length of which is 1 to 2 hours in the future. Based on historical operating data and real-time monitoring data, the load change trend and ambient temperature change are predicted to provide a time-domain prediction basis for the online optimization of control parameters.

[0046] Within each optimization cycle, the system status and load forecast results are updated based on the latest real-time data. The optimal control sequence within the current time window is re-solved, and only the optimal control action corresponding to the current moment is executed. When the next moment arrives, the time window is rolled forward and the optimization calculation is performed again to achieve dynamic rolling optimization of control parameters.

[0047] The system monitors the deviation between its operating status and the target status in real time. The deviation includes temperature deviation, flow rate deviation, and energy consumption deviation. When any deviation exceeds a preset threshold, the system immediately triggers a rapid adjustment of the control parameters.

[0048] By continuously identifying operating conditions, it determines whether the current operating condition has changed. When a change in operating condition is detected, it automatically calls the corresponding control strategy template and parameter settings from the operating condition feature library to achieve smooth switching and rapid response between different operating modes.

[0049] Furthermore, step 13 includes the following steps:

[0050] Significant Changes in Operating Conditions: A significant change in operating conditions is determined when any of the following conditions are met: The outdoor temperature changes by more than 4°C cumulatively within 1 hour or drops by more than 6°C continuously within 3 hours; the total system heat load changes by more than 15% within 30 minutes or by more than 25% cumulatively within 1 hour; the supply or return water temperature deviates from the set value by more than ±3°C for more than 15 minutes, or the pressure deviates from the set value by more than ±0.02MPa for more than 20 minutes; the number of user complaints exceeds three times the daily average level within 1 hour, or there are concentrated regional complaints; major equipment malfunctions and is taken out of operation, or the system operation mode needs to be switched between quality regulation and quantity regulation.

[0051] Determination of operational efficiency deviation: The comprehensive energy efficiency index is calculated at 5-minute intervals, and a statistical period is defined as 30 consecutive minutes. When the average energy efficiency value within the statistical period is continuously lower than 92% of the target energy efficiency value under the current operating condition, and the energy consumption increment exceeds 8% of the rated value, it is determined that there is a significant deviation in operational efficiency.

[0052] Anomaly recording and data saving: When the judgment conditions for changes in operating conditions or deviations in efficiency are met, the anomaly recording mechanism is automatically triggered after the current control cycle is completed, and the current operating data is saved first and the anomaly time node is marked.

[0053] Operating condition re-identification and feature extraction: Automatically return to the operating condition feature identification step, extract the feature vector of the operating data in the most recent 20 to 30 minutes, and perform similarity matching with the real-time updated three-dimensional operating condition feature library to re-identify the current operating condition type of the system.

[0054] Stability assessment of operating condition transition: Based on the re-identification results, the corresponding simulation model is called to assess the stability of the operating condition transition process and determine whether the fluctuation of the thermodynamic parameters of the system during the operating condition switching phase is within an acceptable range.

[0055] After the new operating conditions are identified and stability is assessed, the parameters are re-optimized and control commands are generated. The optimized commands are then issued through a hierarchical control system to achieve adaptive adjustment and smooth transition of the system's operating parameters.

[0056] Compared with the prior art, the present invention has the following advantages:

[0057] This invention constructs a three-dimensional operating condition feature library covering load characteristics, time dimension, and operation mode, and combines real-time data similarity matching and three-domain coupled simulation to achieve accurate identification and multi-objective optimization of building heating system operating conditions. Furthermore, through hierarchical control and rolling online optimization mechanisms, it achieves adaptive dynamic optimization of hot water circulation efficiency and improvement of operational stability. Attached Figure Description

[0058] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0059] Figure 1 This is a flowchart illustrating a method for optimizing hot water circulation efficiency in a building heating system according to the present invention. Detailed Implementation

[0060] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. 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 should fall within the scope of protection of the present invention.

[0061] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0062] like Figure 1 As shown, a method for optimizing hot water circulation efficiency in a building heating system includes the following steps:

[0063] Step 1: Obtain historical operating data and current system parameters of the building heating system. The historical operating data includes load characteristic data, time dimension data, and operating mode data. The current system parameters include pipeline topology, heat exchange equipment configuration, user load distribution, and design operating parameters.

[0064] The acquired historical operational data should cover at least two consecutive complete heating seasons. This includes: load characteristic data such as instantaneous heat load values ​​for each time period, peak load occurrence times, load change rates, and load distribution characteristics of different building functional areas; time dimension data such as hourly, daily, weekly, and monthly multi-scale time labels, indicating time attributes for holidays, weekdays, and special weather conditions; and operational mode data such as control strategies, equipment start-up and shutdown combinations, and historical setpoints of adjustment parameters for each stage of the heating season (initial heating period, stable heating period, and final heating period).

[0065] This embodiment acquires historical operating data and current system parameters of building heating systems covering at least two complete heating seasons, enabling a comprehensive understanding of system load characteristics, temporal patterns, and operating modes. It allows for precise analysis of instantaneous heat load, peak load times, load change rates, and load distribution across different building functional areas at various time periods. Furthermore, by combining multi-scale time tags (hourly, daily, weekly, monthly, etc.) and information on holidays, weekdays, and special weather conditions, it systematically evaluates control strategies, equipment start-up / shutdown combinations, and adjustment parameters during the initial, stable, and final stages of the heating season. This provides a scientific basis for optimizing network operating efficiency, rationally configuring heat exchange equipment, accurately allocating user loads, and improving the overall energy efficiency of the heating system, ensuring more precise heating regulation, more timely response, lower energy consumption, and more reliable operation.

[0066] Step 2: Based on historical operating data, construct a three-dimensional operating condition feature library that includes load characteristics, time dimension, and operating mode, and pre-calculate the occurrence probability and importance coefficient of each operating condition.

[0067] The construction process of the 3D working condition feature library includes:

[0068] Historical operational data is cleaned and normalized to remove abnormal fluctuation data points and fill in missing data segments;

[0069] Operating conditions are classified in different dimensions: In terms of load characteristics, the operating data is divided into four typical intervals: light load, medium load, heavy load, and overload; in terms of time, four time periods are distinguished: weekday daytime, weekday nighttime, weekend, and holidays; and in terms of operating mode, three typical operating states are identified: energy-saving mode, standard mode, and emergency mode.

[0070] Cartesian product logic is used to combine different load ranges, time periods, and operating modes to generate a set of operating condition combinations;

[0071] For each combination of operating conditions, calculate its frequency of occurrence in historical data, and determine its probability distribution characteristics accordingly.

[0072] Based on the degree of impact of each operating condition combination on system energy consumption and heating quality, a corresponding importance coefficient is assigned;

[0073] By integrating the characteristics, frequency of occurrence, probability distribution, and importance coefficients of various working conditions, a three-dimensional working condition feature library containing hundreds of typical working conditions and their characteristic parameters is finally constructed.

[0074] This embodiment constructs a three-dimensional operating condition feature library based on historical operating data, which can systematically characterize the typical operating states of a building heating system and achieve fine classification and combined management of load characteristics, time dimensions, and operating modes. In this process, historical data is first cleaned and normalized to remove abnormal fluctuations and fill in missing data, ensuring the reliability of operating condition analysis. Then, the load is divided into four categories: light load, medium load, heavy load, and overload; the time dimension is divided into weekday daytime, weekday nighttime, weekends, and holidays; and the operating mode is divided into energy-saving mode, standard mode, and emergency mode, forming a multi-dimensional classification basis. The dimensions are combined using Cartesian product logic to generate an operating condition set, and the frequency of each operating condition in historical data is statistically analyzed to form a probability distribution feature. Simultaneously, an importance coefficient is assigned to each operating condition based on its impact on system energy consumption and heating quality. Finally, by integrating various operating condition characteristics, occurrence probabilities, and importance, a three-dimensional operating condition feature library containing hundreds of typical operating conditions and their key parameters is constructed, thus providing a quantitative basis for heating system operation optimization, energy efficiency assessment, and strategy formulation.

[0075] Step 3: Collect real-time operating data of the building heating system, including temperature, flow rate, pressure at each node, as well as ambient temperature and user heat load parameters;

[0076] The real-time acquisition of current operating data of the building heating system is achieved through the deployment of a multi-level sensor network. Specifically: on the heat source side, supply and return water temperature sensors, flow meters, and pressure transmitters are installed, with measurement accuracies reaching ±0.5℃, ±0.5%, and ±0.25%, respectively; at key nodes along the pipeline network, including branch nodes, user access points, and pipeline ends, temperature and pressure monitoring units are deployed, with data acquisition intervals set to 1–5 minutes; on the user side, smart heat meters collect supply and return water temperatures, instantaneous flow rates, and cumulative heat consumption data for each user; ambient temperature data, including outdoor dry-bulb temperature and meteorological parameters affecting the heating load, is collected and updated using distributed weather stations.

[0077] This embodiment, by collecting real-time operational data of the building heating system, comprehensively understands the system's operating status and supports dynamic control and optimization decisions. A multi-level sensor network is deployed at the heat source side, key nodes in the pipeline network, and the user side to ensure high-precision acquisition of key parameters such as temperature, flow rate, pressure, and user heat load. The measurement accuracy at the heat source side reaches ±0.5℃, ±0.5%, and ±0.25%, respectively. Data at key nodes along the pipeline network is updated every 1-5 minutes. Smart heat meters at the user side record supply and return water temperatures, instantaneous flow rates, and cumulative heat consumption in real time. Simultaneously, distributed weather stations collect outdoor dry-bulb temperatures and meteorological parameters affecting the heating load, enabling real-time monitoring of environmental conditions. This data acquisition system provides highly timely and accurate operational information, providing a reliable basis for load allocation, equipment adjustment, and operational strategy optimization of the heating system. It improves the stability and responsiveness of system operation, ensuring that the temperature and flow rate at each operating node accurately match user needs, while reducing energy consumption fluctuations and resource waste. This enhances the reliability and energy efficiency of heating services, achieving refined management and efficient operation of the heating system in dynamic environments.

[0078] Step 4: Extract the feature vector of the current running data, perform similarity matching with the three-dimensional operating condition feature library, identify the current operating condition type of the system, and obtain the feature weight corresponding to the operating condition.

[0079] The process of extracting feature vectors from the current operating data, performing similarity matching with a three-dimensional operating condition feature library, and identifying the current operating condition type of the system includes the following steps:

[0080] Based on the operational data, load characteristic parameters, time characteristic parameters, and operational status characteristic parameters are extracted. Among them, the load characteristic parameters are used to characterize the system load level, including total heat load, load fluctuation amplitude, and load change trend; the time characteristic parameters are used to reflect the impact of the time dimension, including the current time, weekday attribute, and whether it is a holiday; the operational status characteristic parameters are used to describe the equipment operating status, including the operating frequency of the circulating pump, the opening degree of the regulating valve, and the heat exchanger heat exchange capacity.

[0081] A weighted fusion method is used to construct a comprehensive feature vector. The weight coefficients of each feature parameter are dynamically adjusted according to their contribution to the accuracy of working condition identification, so as to achieve unified expression and optimized representation of multi-source feature information.

[0082] Taking into account both the numerical differences and the similarity of the changing trends of the feature values, the constructed comprehensive feature vector is matched with the pre-established three-dimensional working condition feature library for similarity.

[0083] When the similarity exceeds a preset threshold, it is determined to be the same working condition type as the sample in the working condition feature library; if the similarity does not reach the threshold, a new working condition identification process is triggered, and the newly identified working condition features are included in the working condition feature library and the relevant parameters and weight coefficients are updated, thereby realizing the adaptive expansion and dynamic optimization of the feature library.

[0084] This embodiment extracts load features, time features, and operating status features from current operating data and constructs a weighted and fused comprehensive feature vector to achieve accurate identification of the operating conditions of a building heating system. Load features reflect the total heat load, fluctuation amplitude, and trend; time features cover the current time, weekday attributes, and holiday information; and operating status features characterize key equipment parameters such as the operating frequency of circulating pumps, the opening degree of regulating valves, and the heat exchanger's heat exchange capacity. Each feature is assigned a dynamic weight according to its importance to the accuracy of operating condition identification, achieving a unified expression of multi-source information. This comprehensive feature vector is matched with a pre-constructed three-dimensional operating condition feature library for similarity. When the similarity reaches a preset threshold, the system is determined to be in the corresponding typical operating condition, and the feature weight of that condition is obtained for subsequent operation analysis and optimization. If the threshold is not reached, a new operating condition identification mechanism is triggered, incorporating the new operating condition features into the feature library and updating the weights, achieving adaptive expansion and dynamic optimization of the feature library. This process can accurately reflect the actual state of the system under different loads, time periods, and operating modes, support the real-time adjustment and strategy optimization of the heating system, improve the accuracy of operating condition identification and system response capability, and at the same time ensure the reliability and energy efficiency of heating regulation.

[0085] Step 5: Based on the current operating condition type of the system and the current operating data, establish a three-domain coupled simulation model of hydraulic characteristics, thermal characteristics and control strategy, quantitatively evaluate the hydraulic balance, thermal distribution characteristics and energy consumption level of the current system, and generate an operating condition characteristic evaluation report.

[0086] The hydraulic characteristics domain uses graph theory to describe the pipe network topology, establishing pressure balance equations based on the node method and flow distribution equations based on the loop method, considering the influence of pipe friction resistance, local resistance, and the head characteristic curve of the circulating pump on hydraulic conditions. The thermal characteristics domain establishes a temperature field distribution model of the heating medium in the pipe network, calculating the heat loss of each pipe section, the heat exchange process on the user side, and the matching relationship between the heating capacity of the heat source and the load demand. The control strategy domain simulates the action logic and control effect of the regulating equipment under quality regulation, quantity regulation, and quality regulation modes. By building a unified data interface and solution framework in the simulation software platform, parameter transfer and iterative calculation between the three domains are realized, enabling the simulation model to accurately reflect the complex coupling relationship between hydraulic conditions, thermal conditions, and control behavior in the actual system.

[0087] The quantitative assessment of hydraulic balance includes the following steps:

[0088] Calculate the actual pressure drop value of each parallel loop and compare it with the average pressure drop. When the pressure drop difference between any two loops exceeds 12% of the average pressure drop, extract the pressure drop imbalance index as a characteristic component reflecting the difference in hydraulic distribution between loops.

[0089] The deviation rate between the actual traffic and the designed traffic for each user terminal is statistically analyzed, and the traffic imbalance index is calculated. When the traffic deviation rate of more than 50% of users is greater than 10%, the user traffic deviation characteristics are extracted to characterize the overall traffic distribution status.

[0090] Based on the supply and return water temperatures and user-end flow distribution, we analyze whether there is excessive flow for near-end users and insufficient flow for far-end users, and extract heating uniformity characteristic parameters to reflect the spatial balance of heat distribution.

[0091] Based on the flow rate, head, and power curves of the circulating pump, determine whether the pump's operating point is in the high-efficiency operating range. If the operating efficiency under the current conditions is lower than 85% of the rated efficiency, then extract the pump efficiency deviation parameter as an energy efficiency characteristic quantity.

[0092] The system is used to detect whether there are flow short circuits, backflows, or local eddies, and to extract abnormal flow frequency and disturbance intensity indices to reflect the flow stability of the system.

[0093] The pressure drop imbalance, flow imbalance, heating uniformity, pump efficiency deviation, and abnormal flow characteristics are normalized and then weighted according to preset weights to form a multidimensional feature vector characterizing the hydraulic balance state of the system.

[0094] The evaluation of heat distribution characteristics includes the following steps:

[0095] Calculate the deviation between the actual supply and return water temperature difference and the design temperature difference for each user. When the deviation exceeds ±10% of the design value, extract the temperature difference deviation index to reflect the heat transfer stability and regulation rationality of individual users.

[0096] The indoor temperature compliance rate of users in different locations was statistically analyzed to determine whether there were any users who were overheated or underheated. The room temperature uniformity index was extracted to characterize the uniformity of heating in the spatial dimension of the system.

[0097] Based on the total system heat supply and total heat load demand data, the matching degree between the two is calculated, and the heat supply redundancy or heat supply gap ratio is determined to assess the coordination between heat source output and actual load demand.

[0098] Calculate the proportion of heat loss during pipeline transmission to the total heat supply, determine whether this proportion is within the reasonable range specified in the design, and thus evaluate the heat transfer efficiency and thermal insulation performance of the pipeline network.

[0099] The decay patterns of the heat source outlet temperature, the pipe network water supply temperature, and the terminal water supply temperature are detected, and their temperature change curves are analyzed to determine whether they meet the design expectations, in order to identify any local heat loss or abnormal temperature control phenomena.

[0100] A comprehensive thermal performance evaluation index system is established, and the indices of temperature difference deviation, room temperature uniformity, supply and demand matching degree and heat loss ratio are standardized and weighted to form a comprehensive score result that characterizes the rationality of heat distribution.

[0101] This embodiment constructs a three-domain coupled simulation model of hydraulics, thermals, and control strategies to quantitatively assess the hydraulic balance, thermal distribution characteristics, and energy consumption level of a building heating system under current operating conditions. The hydraulic domain, based on the pipe network topology, calculates pressure drop in each loop, user flow deviation, and pump operating efficiency, extracting pressure drop imbalance, flow imbalance, pump efficiency deviation, and abnormal flow characteristics to form a hydraulic balance feature vector. The thermal domain calculates the deviation of user supply and return water temperature difference, room temperature uniformity, supply-demand matching degree, and pipe network heat loss to form a thermal distribution score. The control strategy domain simulates the equipment operating logic under quality regulation, quantity regulation, and comprehensive regulation to ensure that control actions match system responses. Through iterative calculation and weighted integration of parameters from the three domains, an operating condition characteristic assessment report is generated, achieving a comprehensive quantification of system flow distribution, heat balance, energy efficiency, and operational stability.

[0102] Step 6: Determine whether the current operating status meets the preset efficiency standard based on the operating condition characteristic evaluation report;

[0103] The preset efficiency standards include multiple judgment criteria: energy consumption per unit building area or power transmission and distribution ratio is lower than the value specified in the local energy-saving design standard; the indoor temperature compliance rate of main rooms is not less than 92% and the temperature fluctuation range is controlled within ±2℃ of the design temperature; the deviation rate between the actual flow and the design flow of the most unfavorable loop user is less than 15%, and the flow imbalance index of the whole system is less than 0.20; the boiler thermal efficiency reaches more than 88% of the rated operating efficiency, or the COP value of the heat pump system reaches more than 85% of the design value; the heat loss rate does not exceed 8% when the heating radius is within the design range; and the comprehensive operating cost per unit of heat supply is controlled within the budget.

[0104] This embodiment analyzes the operational characteristic assessment report to determine whether the current operating status of the building heating system meets the preset efficiency standards, thereby achieving operational optimization and energy-saving control. The judgment criteria cover multiple indicators: energy consumption per unit building area or power transmission and distribution ratio should be lower than the local energy-saving design standard to ensure energy efficiency; the indoor temperature compliance rate of main rooms should not be less than 92%, and temperature fluctuations should be controlled within ±2℃ of the design temperature to ensure comfort and temperature stability; the actual flow deviation rate of the most unfavorable loop users should be less than 15%, and the overall system flow imbalance should be less than 0.20 to ensure balanced hydraulic distribution; the boiler thermal efficiency should reach more than 88% of the rated operating condition or the COP of the heat pump system should reach more than 85% of the design value to ensure efficient operation of the heat source; the heat loss rate within the heating radius should not exceed 8% to optimize the heat transmission and distribution process; and the comprehensive operating cost per unit of heat supply should be controlled within the budget to achieve economic constraints. This multidimensional efficiency assessment can comprehensively reflect the system's energy consumption, heat distribution, flow balance, heat source efficiency, and operating costs, providing a quantitative basis for subsequent adjustment measures and ensuring that the heating system achieves a balance between safety, comfort, energy saving, and economic goals.

[0105] Step 7: If satisfied, proceed to step 12 to continue real-time monitoring and adaptive adjustment; if not satisfied, construct a weighted multi-objective optimization function that includes hydraulic balance, system energy consumption, heating comfort and operating cost, generate a candidate parameter set using a global search strategy, and optimize the candidate parameters using a local refinement strategy to obtain the optimal combination of operating parameters under the current operating conditions.

[0106] The constructed weighted multi-objective optimization function takes the following form: the objective function equals the hydraulic balance sub-objective multiplied by its weight coefficient, plus the system energy consumption sub-objective multiplied by its weight coefficient, plus the heating comfort sub-objective multiplied by its weight coefficient, plus the operating cost sub-objective multiplied by its weight coefficient. The hydraulic balance sub-objective is represented by the sum of squares of the flow deviations in each loop, with a weight coefficient set to 0.25 under standard operating conditions. The system energy consumption sub-objective includes a weighted combination of heat source energy consumption and transmission and distribution system power consumption, with a weight coefficient dynamically adjusted based on current energy prices, set between 0.30 and 0.40. The heating comfort sub-objective is comprehensively evaluated through indoor temperature deviation, temperature fluctuation amplitude, and user complaint rate indicators, with a weight coefficient set to 0.30 during severe cold periods and reduced to 0.20 during transitional seasons. The operating cost sub-objective comprehensively considers energy costs, labor costs, and equipment wear and tear, with a weight coefficient of 0.15.

[0107] The global search strategy is based on an improved particle swarm optimization algorithm, specifically including: initializing the particle swarm size to 50 to 100 individuals, with each particle representing a set of possible operating parameter combinations, including heat source outlet water temperature, circulating pump frequency, and the opening degree of each regulating valve; setting the search space boundary for the particles to ensure that the search range covers all feasible operating parameter regions while excluding unreasonable parameter combinations; introducing an adaptive inertia weight strategy during the iteration process, initially using a larger inertia weight to enhance global exploration capabilities, and gradually reducing the inertia weight in the later stages to improve local search accuracy; introducing a mutation operator to randomly perturb the positions of some particles to avoid the algorithm getting trapped in local optima; and setting a convergence criterion, terminating the search when the improvement of the optimal solution for several consecutive generations is less than a set threshold or the maximum number of iterations is reached.

[0108] Among them, the local refinement strategy uses a sequential quadratic programming method to finely optimize the candidate parameter set obtained from the global search.

[0109] Step 8: Perform operating condition disturbance simulation based on the optimal combination of operating parameters. By introducing load fluctuation disturbance, external temperature change disturbance and equipment performance deviation disturbance, calculate the robustness score of the optimal operating parameters under actual complex operating conditions.

[0110] The load fluctuation disturbance simulates user behavior uncertainty and load forecasting error, superimposing random fluctuations of ±15% to ±25% on the current forecast load, with a fluctuation frequency set to 1 to 3 times per hour to reflect the dynamic characteristics of the load in actual operation; the external temperature change disturbance considers weather forecast deviations and local climate differences, setting a scenario where the actual outdoor temperature deviates from the forecast value by ±2℃ to ±4℃; the equipment performance deviation disturbance includes a 3% to 8% efficiency reduction in circulating pumps due to wear, and an 8% to 15% decrease in heat transfer coefficient in heat exchangers due to fouling. The regulating valves have a dead zone of 2% to 5% and a response lag of 30 seconds to 2 minutes, while the temperature sensors have a measurement drift of ±0.3℃ to ±0.8℃. For each disturbance, three intensity levels of mild, moderate and severe are designed, and no less than 150 representative disturbance scenario combinations are generated using the Latin hypercube sampling method. The disturbance scenarios are simulated one by one in the three-domain coupled simulation model, and the dynamic response characteristics of the system under the optimal operating parameters are recorded, including the fluctuation range of heating quality, energy consumption increment, parameter adjustment margin and the time required to reach a new steady state.

[0111] The calculation of the robustness score of the optimal operating parameters under actual complex operating conditions includes the following steps:

[0112] The worst-case deterioration of the objective function is calculated under each disturbance scenario. The worst-case deterioration is the ratio of the maximum deviation of the objective function under all disturbance scenarios to the optimal value under the no-disturbance condition. It is used to characterize the performance retention capability of the thermal distribution scheme under extremely unfavorable conditions.

[0113] The variance or standard deviation of the objective function under various disturbance scenarios is statistically analyzed to assess the volatility of heat distribution performance.

[0114] Calculate the constraint violation rate, which is the proportion of the number of scenarios in the disturbance scenario that cause the system to operate outside the range of safety constraints or performance constraints to the total number of scenarios, so as to reflect the safety and reliability of thermal distribution parameters;

[0115] Calculate the robustness index, which is the percentage of disturbance scenarios that meet the design performance requirements out of the total number of disturbance scenarios, and use it to evaluate the feasibility of the heat distribution scheme under complex operating conditions.

[0116] Calculate the average performance loss, which is the average difference between the objective function value and the optimal value under each perturbation scenario, and is used to measure the degree of overall performance degradation.

[0117] The worst-case deterioration, performance volatility, constraint violation rate, robustness index, and average performance loss are weighted and combined according to preset weights to obtain a comprehensive robustness score.

[0118] In this embodiment, when the system's operating state does not meet the preset efficiency standard, a weighted multi-objective optimization function incorporating hydraulic balance, energy consumption, heating comfort, and operating costs is constructed. A global search combined with local refinement strategies is used to generate the optimal combination of operating parameters, thereby optimizing system performance. The global search is based on an improved particle swarm optimization algorithm. Within a reasonable parameter range, the particle swarm is initialized and iteratively searched using adaptive inertia weights and mutation operators. Local refinement uses sequential quadratic programming to optimize candidate solutions. Subsequently, a disturbance simulation is introduced, incorporating load fluctuations, external temperature changes, and equipment performance deviations. The robustness of the optimal operating parameters is evaluated, including worst-case deterioration, performance volatility, constraint violation rate, robustness index, and average performance loss. These parameters are then weighted and synthesized according to preset weights to generate a comprehensive robustness score, thereby ensuring the stability, comfort, and energy efficiency of the heating system under complex operating conditions.

[0119] Step 9: Determine whether the stability of the optimal combination of operating parameters meets the preset robustness requirements based on the robustness score.

[0120] Step 10: If the stability of the optimal combination of operating parameters does not meet the robustness requirement, then adaptive optimization of the parameters is performed based on the robustness score, the weight coefficients or constraints in the optimization function are adjusted, and the optimal combination of operating parameters is solved again until the robustness requirement is met.

[0121] Specifically, the adaptive optimization of parameters based on robustness scores includes: when the robustness assessment finds that the performance of the optimal parameters deteriorates significantly under load fluctuations, increasing the weight coefficients of hydraulic balance and heating comfort in the multi-objective optimization function, and correspondingly reducing the weight of energy consumption optimization, so that the optimization results are more inclined to a conservative strategy; when the external temperature change disturbance has a significant impact, adding requirements for the heat source adjustment margin to the constraints to ensure that the heat source has sufficient output adjustment space to cope with sudden changes in meteorological conditions; when equipment performance deviations lead to insufficient robustness, considering equipment degradation factors in the optimization solution, and using the actual performance curve of the equipment as the constraint boundary.

[0122] In this embodiment, when the stability of the optimal combination of operating parameters fails to meet the robustness requirements, the optimization function weights or constraints are adjusted through adaptive optimization based on robustness scores, and the optimal parameters are re-solved until the requirements are met. When load fluctuations lead to performance degradation, the weights of hydraulic balance and heating comfort are increased, while the weight of energy consumption is decreased, making the optimization results biased towards a conservative strategy. When external temperature disturbances have a significant impact, the heat source adjustment margin constraint is increased to ensure adjustable output space. When equipment performance deviations affect robustness, the actual equipment performance curves are included in the constraint boundaries to account for degradation factors and ensure the stability and reliability of the system under complex operating conditions.

[0123] Step 11: If the stability of the optimal combination of operating parameters meets the robustness requirement, then establish a hierarchical control system including a system-level coordination layer, a regional-level adjustment layer, and a device-level execution layer based on the verified optimal operating parameters.

[0124] The hierarchical control system employs a tiered control architecture to achieve coordinated optimization across different time and spatial scales: the system-level coordination layer, located at the top of the control system, is responsible for formulating optimization objectives and macro-control strategies for the entire system. Its decision-making cycle is set to 10 to 30 minutes depending on the system size. Its main tasks include determining the total heat supply of the heat source, the setpoints for the primary network supply and return water temperatures, the heat distribution schemes for each region or heating station, and the number and frequency range of circulating pumps based on load forecasts and operating condition identification results for the next 1 to 2 hours; the regional-level regulation layer, located in the middle of the control system, is responsible for decomposing system-level commands into specific instructions for each heating zone. The specific control parameters of the domain or secondary network have a decision cycle of 3 to 10 minutes. They mainly complete the dynamic adjustment of the frequency of circulating pumps in each area, the fine control of the regional water supply temperature, the matching adjustment of the primary and secondary flow rates of the heat exchange station, and the heat coordination and balance between adjacent areas. The equipment-level execution layer is located at the bottom of the control system and directly drives the action of the field actuators. The control cycle is 10 seconds to 3 minutes, ensuring rapid response and accurate execution of control commands. The three levels exchange information through a standardized communication protocol. The upper layer sends control commands and target setpoints to the lower layer, and the lower layer provides real-time feedback on equipment operating status, execution deviations, and fault alarm information to the upper layer.

[0125] The system-level coordination layer is configured to: determine the optimal output allocation and start-stop combination based on the efficiency characteristic curve of the heat source, current load demand, and economic considerations; calculate the optimal water supply temperature curve under the current operating conditions by comprehensively considering outdoor temperature, load level, pipeline characteristics, and user demand; determine the head setpoint of the circulating pump based on the pressure demand at the most unfavorable point of the pipeline network; and compare the matching relationship between the total heat supply and the total heat load of the system in real time, and promptly trigger control strategy adjustments when a significant imbalance is detected.

[0126] The regional-level regulation layer is configured to: receive regional heat allocation indicators and temperature and pressure setpoints from the system-level coordination layer; dynamically adjust the speed of the circulating pump based on the actual demand flow and supply-return water pressure difference feedback of users within the region to achieve on-demand supply of regional flow; correct the temperature by adjusting the primary flow of the mixing device or heat exchanger when the regional water supply temperature deviates from the setpoint; automatically adjust the opening of the dynamic balancing valve or electric regulating valve by monitoring the flow distribution of each branch within the region to eliminate hydraulic imbalance; and achieve mutual allocation of heat through connecting pipes and regulating valves when there is heating redundancy or insufficiency in adjacent areas.

[0127] The equipment-level execution layer is configured to: implement variable frequency speed control for circulating water pumps, while monitoring their status parameters and triggering fault warnings when an anomaly is detected; implement opening control for electric regulating valves and electric ball valves; control the regulating devices of heat exchangers; perform edge computing and preliminary processing on the data collected by heat metering and temperature sensors, remove outliers and smooth the data; and automatically take protective measures when the equipment operating parameters are detected to exceed the safe range.

[0128] In this embodiment, after the optimal combination of operating parameters passes robustness verification, a hierarchical control system is established based on it to achieve multi-scale collaborative optimization of the building heating system. This system includes a system-level coordination layer, a regional-level regulation layer, and an equipment-level execution layer. The system-level coordination layer has a decision cycle of 10–30 minutes and is responsible for formulating the overall system optimization goals and macro-control strategies, including heat source output allocation, primary network supply and return water temperature settings, regional heat allocation, and circulating pump start / stop and head settings. It also compares the total heat supply with the total load in real time and triggers strategy adjustments. The regional-level regulation layer has a decision cycle of 3–10 minutes and translates system-level commands into specific regional control parameters, dynamically adjusting the circulating pump frequency, regional water supply temperature, and heat exchange station flow matching. It also achieves hydraulic balance and inter-regional heat coordination through regulating valves. The equipment-level execution layer has a control cycle of 10 seconds to 3 minutes and directly drives the circulating pumps, regulating valves, and heat exchangers. It performs real-time data acquisition, edge computing, and anomaly handling to ensure rapid command response and accurate execution. The three layers exchange information through a standardized communication protocol. The upper layer sends out targets and instructions, while the lower layer provides feedback on operating status, deviations, and fault information. This hierarchical control architecture can balance overall system optimization, regional regulation accuracy, and equipment response speed, achieving precise load matching, stable and balanced temperature, rational hydraulic distribution, and simultaneous optimization of heating efficiency and economy.

[0129] Step 12: Optimize the control parameters online, monitor the deviation between the system operating status and the target status in real time, adaptively switch the operating mode according to the changes in operating conditions, and send the optimized control commands to the execution units at each level.

[0130] This includes online optimization of control parameters, real-time monitoring of the deviation between the system's operating status and the target status, and adaptive switching of operating modes based on changes in operating conditions. The steps include:

[0131] A rolling optimization time-domain window is set, the length of which is 1 to 2 hours in the future. Based on historical operating data and real-time monitoring data, the load change trend and ambient temperature change are predicted to provide a time-domain prediction basis for the online optimization of control parameters.

[0132] Within each optimization cycle, the system status and load forecast results are updated based on the latest real-time data. The optimal control sequence within the current time window is re-solved, and only the optimal control action corresponding to the current moment is executed. When the next moment arrives, the time window is rolled forward and the optimization calculation is performed again to achieve dynamic rolling optimization of control parameters.

[0133] The system monitors the deviation between its operating status and the target status in real time. The deviation includes temperature deviation, flow rate deviation, and energy consumption deviation. When any deviation exceeds a preset threshold, the system immediately triggers a rapid adjustment of the control parameters.

[0134] By continuously identifying operating conditions, it determines whether the current operating condition has changed. When a change in operating condition is detected, it automatically calls the corresponding control strategy template and parameter settings from the operating condition feature library to achieve smooth switching and rapid response between different operating modes.

[0135] This embodiment dynamically adjusts the building heating system through a rolling time-domain window, achieving adaptive switching and refined control of operating modes. A rolling optimization window of 1-2 hours is set, combining historical operating data and real-time monitoring data to predict load and ambient temperature changes, providing a time-domain prediction basis for control parameter optimization. Within each optimization cycle, the system status and load forecast are updated in real time, solving for the optimal control sequence for the current window. Only the control action corresponding to the current moment is executed, and the system is re-optimized over time to achieve dynamic rolling control. The system continuously monitors temperature, flow rate, and energy consumption deviations. When the deviation exceeds a preset threshold, rapid adjustments are made immediately to maintain the operating state matching the target state. Simultaneously, by continuously identifying changes in system operating modes, the system automatically calls the corresponding control strategies and parameter templates from the operating condition feature library, achieving smooth switching and rapid response under different operating conditions. This ensures that the system maintains efficient, stable, and energy-saving operation under complex loads and environmental conditions.

[0136] Step 13: When a significant change in operating conditions or a deviation in operating efficiency is detected, return to the operating condition feature identification step and re-perform operating condition identification and parameter optimization, including the following steps:

[0137] Significant Changes in Operating Conditions: A significant change in operating conditions is determined when any of the following conditions are met: The outdoor temperature changes by more than 4°C cumulatively within 1 hour or drops by more than 6°C continuously within 3 hours; the total system heat load changes by more than 15% within 30 minutes or by more than 25% cumulatively within 1 hour; the supply or return water temperature deviates from the set value by more than ±3°C for more than 15 minutes, or the pressure deviates from the set value by more than ±0.02MPa for more than 20 minutes; the number of user complaints exceeds three times the daily average level within 1 hour, or there are concentrated regional complaints; major equipment malfunctions and is taken out of operation, or the system operation mode needs to be switched between quality regulation and quantity regulation.

[0138] Determination of operational efficiency deviation: The comprehensive energy efficiency index is calculated at 5-minute intervals, and a statistical period is defined as 30 consecutive minutes. When the average energy efficiency value within the statistical period is continuously lower than 92% of the target energy efficiency value under the current operating condition, and the energy consumption increment exceeds 8% of the rated value, it is determined that there is a significant deviation in operational efficiency.

[0139] Anomaly recording and data saving: When the judgment conditions for changes in operating conditions or deviations in efficiency are met, the anomaly recording mechanism is automatically triggered after the current control cycle is completed, and the current operating data is saved first and the anomaly time node is marked.

[0140] Operating condition re-identification and feature extraction: Automatically return to the operating condition feature identification step, extract the feature vector of the operating data in the most recent 20 to 30 minutes, and perform similarity matching with the real-time updated three-dimensional operating condition feature library to re-identify the current operating condition type of the system.

[0141] Stability assessment of operating condition transition: Based on the re-identification results, the corresponding simulation model is called to assess the stability of the operating condition transition process and determine whether the fluctuation of the thermodynamic parameters of the system during the operating condition switching phase is within an acceptable range.

[0142] After the new operating conditions are identified and stability is assessed, the parameters are re-optimized and control commands are generated. The optimized commands are then issued through a hierarchical control system to achieve adaptive adjustment and smooth transition of the system's operating parameters.

[0143] In this embodiment, when a significant change in operating conditions or a deviation in operating efficiency is detected, the system automatically returns to the operating condition feature identification and parameter optimization process to achieve adaptive adjustment and smooth transition of the operating state. Significant changes in operating conditions are determined by factors such as: short-term drastic fluctuations in outdoor temperature, rapid changes in total heat load, deviations in supply and return water temperature or pressure from set values, a concentrated increase in user complaints, and major equipment failures or operating mode switching requirements. Deviance in operating efficiency is determined based on energy efficiency indicators falling below target values ​​and abnormal energy consumption increases within a continuous statistical period. Once the trigger conditions are met, abnormal data is automatically recorded and time nodes are marked. Subsequently, the feature vectors of the operating data from the most recent 20-30 minutes are extracted and matched with a real-time updated three-dimensional operating condition feature library to re-identify the current operating condition type. A three-domain coupled simulation model is then used to evaluate the stability of the operating condition transition and determine whether the fluctuations in thermal parameters are acceptable. After re-identification and stability assessment, the optimal operating parameters are solved again and control commands are generated. Optimization commands are issued through a hierarchical control system to achieve adaptive adjustment, stable operation, and energy efficiency optimization under the new operating conditions.

[0144] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments. In the above embodiments of the present invention, the descriptions of each embodiment have their own emphasis; parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments. It should be understood that the disclosed technical content in the several embodiments provided in this application can be implemented in other ways.

[0145] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for optimizing hot water circulation efficiency in a building heating system, characterized in that, Includes the following steps: Step 1: Obtain historical operating data and current system parameters of the building heating system; The historical operating data includes: load characteristic data, time dimension data, and operating mode data; the current system parameters include: pipeline topology, heat exchange equipment configuration, user load distribution, and design operating parameters. Step 2: Based on the historical operating data, construct a three-dimensional operating condition feature library that includes load characteristics, time dimension and operating mode, and pre-calculate the occurrence probability and importance coefficient of different operating conditions; Step 3: Collect the current operating data of the building heating system in real time; the current operating data includes: temperature of each node, flow rate of each node, pressure of each node, ambient temperature of each node, and user heat load parameters; Step 4: Extract the feature vector of the current running data, perform similarity matching with the three-dimensional operating condition feature library, identify the current operating condition type of the system, and obtain the feature weight corresponding to the current operating condition. Step 5: Based on the current operating condition type of the system and the current operating data, establish a three-domain coupled simulation model of hydraulic characteristics, thermal characteristics and control strategy; quantitatively evaluate the hydraulic balance, thermal distribution characteristics and energy consumption level of the current system, and generate an operating condition characteristic evaluation report. Step 6: Determine whether the current operating status meets the preset efficiency standard based on the operating condition characteristic evaluation report; Step 7: If satisfied, proceed to step 12 to continue real-time monitoring and adaptive adjustment; if not satisfied, construct a weighted multi-objective optimization function that includes hydraulic balance, system energy consumption, heating comfort, and operating cost, generate a candidate parameter set using a global search strategy, and optimize the candidate parameters using a local refinement strategy to obtain the optimal combination of operating parameters under the current operating conditions.

2. The method for optimizing hot water circulation efficiency in a building heating system according to claim 1, characterized in that, The historical operating data obtained in step 1 should cover at least two consecutive complete heating seasons; The load characteristic data includes: instantaneous heat load values ​​for each time period, peak load occurrence time, load change rate, and load distribution characteristics of different building functional areas; The time dimension data includes multi-scale time labels at the hour, day, week, and month levels, and indicates the time attributes for holidays, weekdays, and special weather conditions; The operating mode data includes: control strategies, equipment start-up and shutdown combinations, and historical set values ​​of adjustment parameters for each stage of the initial heating period, stable heating period, and final heating period.

3. The method for optimizing hot water circulation efficiency in a building heating system according to claim 1, characterized in that, The construction process of the three-dimensional working condition feature library in step 2 includes: Historical operational data is cleaned and normalized preprocessed to remove abnormal fluctuation data points and fill in missing data segments; Operating conditions are classified in different dimensions: In terms of load characteristics, the operating data is divided into four typical intervals: light load, medium load, heavy load, and overload; in terms of time, four time periods are distinguished: weekday daytime, weekday nighttime, weekend, and holidays; and in terms of operating mode, three typical operating states are identified: energy-saving mode, standard mode, and emergency mode. Cartesian product logic is used to combine different load ranges, time periods, and operating modes to generate a set of operating condition combinations; For each working condition combination, calculate its frequency of occurrence in historical data, and determine the probability distribution characteristics of each working condition combination based on the frequency of occurrence. Based on the degree of impact of each operating condition combination on system energy consumption and heating quality, a corresponding importance coefficient is assigned; By integrating the characteristics, frequency of occurrence, probability distribution, and importance coefficients of various working conditions, a three-dimensional working condition feature library is finally constructed.

4. The method for optimizing hot water circulation efficiency in a building heating system according to claim 1, characterized in that, In step 3, the real-time acquisition of the current operating data of the building heating system is achieved by deploying a multi-level sensor network. On the heat source side, supply and return water temperature sensors, flow meters, and pressure transmitters are installed, with measurement accuracies reaching ±0.5℃, ±0.5%, and ±0.25%, respectively. At key nodes along the pipeline network, including branch nodes, user access points, and pipeline ends, temperature and pressure monitoring units are deployed, with data acquisition intervals set to 1–5 minutes. On the user side, smart heat meters collect supply and return water temperatures, instantaneous flow rates, and cumulative heat consumption data for each user. Ambient temperature data, including outdoor dry-bulb temperature and meteorological parameters affecting heating load, is collected and updated using distributed weather stations.

5. The method for optimizing hot water circulation efficiency in a building heating system according to claim 1, characterized in that, Step 4 involves extracting the feature vector of the current operating data, performing similarity matching with the three-dimensional operating condition feature library, and identifying the current operating condition type of the system. This includes the following steps: Based on the current operating data, load characteristic parameters, time characteristic parameters, and operating status characteristic parameters are extracted. The load characteristic parameters are used to characterize the system load level, including: total heat load, load fluctuation amplitude, and load change trend. The time characteristic parameters are used to reflect the influence of the time dimension, including: current time, weekday attribute, and whether it is a holiday. The operating status characteristic parameters are used to describe the equipment operating status, including: circulating pump operating frequency, regulating valve opening, and heat exchanger heat exchange. A weighted fusion method is used to construct a comprehensive feature vector, and the weight coefficients of each feature parameter are dynamically adjusted according to the contribution of each feature parameter to the accuracy of working condition identification. Taking into account both the numerical differences and the similarity of the changing trends of the feature values, the constructed comprehensive feature vector is matched with the pre-established three-dimensional working condition feature library for similarity. When the similarity exceeds a preset threshold, it is determined to be the same working condition type as the sample in the working condition feature library; if the similarity does not reach the threshold, a new working condition identification process is triggered, and the newly identified working condition features are included in the working condition feature library and the relevant parameters and weight coefficients are updated, thereby realizing the adaptive expansion and dynamic optimization of the feature library.

6. The method for optimizing hot water circulation efficiency in a building heating system according to claim 1, characterized in that, The weighted multi-objective optimization function constructed in step 7 is: The weighted multi-objective optimization function is equal to the hydraulic balance sub-objective multiplied by its weight coefficient, plus the system energy consumption sub-objective multiplied by its weight coefficient, plus the heating comfort sub-objective multiplied by its weight coefficient, plus the operating cost sub-objective multiplied by its weight coefficient. Among them, the hydraulic balance sub-objective is characterized by the sum of squares of the flow deviations of each loop, with a weighting coefficient set at 0.25 under standard operating conditions; the system energy consumption sub-objective includes a weighted combination of heat source energy consumption and transmission and distribution system power consumption, with the weighting coefficient dynamically adjusted according to current energy prices and set between 0.30 and 0.40; the heating comfort sub-objective is comprehensively evaluated through indoor temperature deviation, temperature fluctuation range, and user complaint rate indicators, with a weighting coefficient set at 0.30 during severe cold periods and reduced to 0.20 during transitional seasons; the operating cost sub-objective comprehensively considers energy costs, labor costs, and equipment wear and tear, with a weighting coefficient of 0.

15.

7. A method for optimizing hot water circulation efficiency in a building heating system according to any one of claims 1-6, characterized in that, The hot water circulation efficiency optimization method also includes the following steps: Step 8: Perform operating condition disturbance simulation based on the optimal combination of operating parameters. By introducing load fluctuation disturbance, external temperature change disturbance and equipment performance deviation disturbance, calculate the robustness score of the optimal operating parameters under actual complex operating conditions. Step 9: Determine whether the stability of the optimal combination of operating parameters meets the preset robustness requirements based on the robustness score. Step 10: If the stability of the optimal combination of operating parameters does not meet the robustness requirement, then adaptive optimization of the parameters is performed based on the robustness score, the weight coefficients or constraints in the optimization function are adjusted, and the optimal combination of operating parameters is solved again until the robustness requirement is met. Step 11: If the stability of the optimal combination of operating parameters meets the robustness requirement, then establish a hierarchical control system including a system-level coordination layer, a regional-level adjustment layer, and a device-level execution layer based on the verified optimal operating parameters. Step 12: Optimize the control parameters online, monitor the deviation between the system operating status and the target status in real time, adaptively switch the operating mode according to the changes in operating conditions, and send the optimized control commands to the execution units at each level. Step 13: When a significant change in operating conditions or a deviation in operating efficiency is detected, return to the operating condition feature identification step and re-identify the operating conditions and optimize the parameters.

8. The method for optimizing hot water circulation efficiency in a building heating system according to claim 7, characterized in that, The control parameters are optimized online, the deviation between the system's operating status and the target status is monitored in real time, and the operating mode is adaptively switched according to changes in operating conditions. This includes the following steps: A rolling optimization time-domain window is set, the length of which is 1 to 2 hours in the future. Based on historical operating data and real-time monitoring data, the load change trend and ambient temperature change are predicted to provide a time-domain prediction basis for the online optimization of control parameters. Within each optimization cycle, the system status and load forecast results are updated based on the latest real-time data. The optimal control sequence within the current time window is re-solved, and only the optimal control action corresponding to the current moment is executed. When the next moment arrives, the time window is rolled forward and the optimization calculation is performed again to achieve dynamic rolling optimization of control parameters. The system monitors the deviation between its operating status and the target status in real time. The deviation includes temperature deviation, flow rate deviation, and energy consumption deviation. When any deviation exceeds a preset threshold, the system immediately triggers a rapid adjustment of the control parameters. By continuously identifying operating conditions, it determines whether the current operating condition has changed. When a change in operating condition is detected, it automatically calls the corresponding control strategy template and parameter settings from the operating condition feature library to achieve smooth switching and rapid response between different operating modes.

9. A method for optimizing hot water circulation efficiency in a building heating system according to claim 7, characterized in that, Step 13 includes the following steps: Determination of significant changes in operating conditions: A significant change in operating conditions is determined when any of the following conditions are met: the outdoor temperature changes by more than 4°C cumulatively within 1 hour or drops by more than 6°C continuously within 3 hours; the total system heat load changes by more than 15% within 30 minutes or by more than 25% cumulatively within 1 hour; the supply or return water temperature deviates from the set value by more than ±3°C for more than 15 minutes, or the pressure deviates from the set value by more than ±0.02MPa for more than 20 minutes; the number of user complaints exceeds three times the daily average level within 1 hour or there are concentrated regional complaints; major equipment fails and is taken out of operation, or the system operation mode needs to be switched between quality regulation and quantity regulation. Determination of operational efficiency deviation: The comprehensive energy efficiency index is calculated at 5-minute intervals, and a statistical period is defined as 30 consecutive minutes. When the average energy efficiency value within the statistical period is continuously lower than 92% of the target energy efficiency value under the current operating condition, and the energy consumption increment exceeds 8% of the rated value, it is determined that there is a significant deviation in operational efficiency. Anomaly recording and data saving: When the judgment conditions for changes in operating conditions or deviations in efficiency are met, the anomaly recording mechanism is automatically triggered after the current control cycle is completed, and the current operating data is saved first and the anomaly time node is marked. Operating condition re-identification and feature extraction: Automatically return to the operating condition feature identification step, extract the feature vector of the operating data in the most recent 20 to 30 minutes, and perform similarity matching with the real-time updated three-dimensional operating condition feature library to re-identify the current operating condition type of the system. Stability assessment of operating condition transition: Based on the re-identification results, the corresponding simulation model is called to assess the stability of the operating condition transition process and determine whether the fluctuation of the thermodynamic parameters of the system during the operating condition switching phase is within an acceptable range. After the new operating conditions are identified and stability is assessed, the parameters are re-optimized and control commands are generated. The optimized commands are then issued through a hierarchical control system to achieve adaptive adjustment and smooth transition of the system's operating parameters.

Images