Regulation and control method for realizing two-network balance and precise heat supply based on hydraulic decoupling and load prediction

Abstract

The invention discloses a regulation and control method for realizing two-network balance and precise heat supply based on hydraulic decoupling and load prediction, and relates to the technical field of centralized heat supply and smart energy, and the method comprises the steps: deploying a hydraulic decoupling device in each building of a target area, constructing an independent hydraulic unit, isolating user adjustment disturbance, and establishing a hydraulic decoupling platform; establishing a dynamic differential pressure maintaining system, and controlling frequency conversion operation of the circulating water pump through feedback of a differential pressure sensor. A pressure difference control valve is arranged at a unit inlet to cooperate with a pressure irrelevant valve at a user inlet, a pipe network coupled in the whole network is physically divided into a plurality of independent hydraulic units, and a built-in pressure compensation mechanism can sense and actively consume branch surplus pressure heads in real time; pressure fluctuation generated by user adjustment is limited in the unit, adjustment of all families is achieved, mutual interference is avoided, the dynamic hydraulic imbalance phenomenon that one family is adjusted and hundreds of families are tired is eradicated from the physical level, and reliable execution of control instructions and system convergence are ensured.

Description

Technical Field

[0001] This invention relates to the field of centralized heating and smart energy technology, specifically a control method for achieving balance between two power grids and precise heating based on hydraulic decoupling and load forecasting. Background Technology

[0002] With the acceleration of urbanization and the increasing demands of residents for heating quality, centralized heating systems are playing an increasingly important role in ensuring the comfort of winter heating, especially in cold regions. Heating systems are not only related to basic needs of people's livelihoods, but also closely related to energy consumption and environmental protection. Traditional centralized heating systems usually rely on high-flow operation or static balancing methods to maintain heating stability. However, in actual operation, due to factors such as the large scale of the system, the variability of user behavior, and the dynamic fluctuation of heat load, it is often difficult to achieve efficient, stable, and fair heat distribution.

[0003] Although existing heating regulation technologies have alleviated system imbalance to some extent, they still have several inherent defects. Traditional high-flow-rate operation, while barely meeting end-point heating demands, leads to near-end overheating and significantly increased pump energy consumption, representing a high-energy-consumption, low-efficiency, and extensive regulation mode. Meanwhile, while static balancing valves can alleviate initial hydraulic imbalances, they cannot adapt to dynamic changes during system operation. User adjustments easily trigger network-wide pressure fluctuations, creating a "one-stop-shop" coupling phenomenon. Furthermore, adding actuators to ordinary valves and relying on software algorithms for regulation schemes is difficult to execute stably in strongly coupled hydraulic environments, resulting in mutual interference of control commands, poor system convergence, and often failing to achieve the desired effect due to a lack of reliable physical execution foundations. Therefore, existing technologies lack a systematic solution that can fundamentally break dynamic hydraulic coupling and provide a stable and reliable hydraulic execution foundation for advanced intelligent control. To address these issues, this paper proposes a regulation method based on hydraulic decoupling and load prediction to achieve secondary network balancing and precise heating. Summary of the Invention

[0004] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction, comprising the following steps: S1. Deploy hydraulic decoupling devices in each building in the target area, that is, install differential pressure control valves at the inlet of each unit and configure pressure-independent valves at the user inlet to build independent hydraulic units, isolate user regulation disturbances, and establish a hydraulic decoupling platform. S2. Establish a dynamic differential pressure maintenance system, and control the variable frequency operation of the circulating water pump through differential pressure sensor feedback to maintain the set differential pressure of the main network, ensure the stability of the system set differential pressure, and eliminate the root cause of dynamic hydraulic imbalance. S3. Collect historical operating data including outdoor temperature, typical room temperature and water supply temperature, and generate a dynamic curve of outdoor temperature-water supply temperature through regression analysis to quantify the heat load characteristics of the building complex. S4. Based on the dynamic curve of outdoor temperature and water supply temperature, the weather forecast is used to predict future room temperature changes, and the water supply temperature prediction and adjustment curve is output to adjust the water supply temperature in advance to offset the building's thermal inertia and achieve precise heating matching on the heat source side. S5. Collect user-side thermal data, i.e. real-time data of each user, through room temperature sensors and heat meters, determine the individual load deviation between users, and determine the water supply temperature value that needs to be actively controlled by combining the water supply temperature prediction and adjustment curve, so that the total heat supply is dynamically matched with the heat load of the building group and avoids excessive heat supply. S6. Based on the user-side thermal data and the water supply temperature that needs to be actively controlled, the flow rate of the inlet valve is finely adjusted, and the heat is accurately distributed on the hydraulic decoupling platform to eliminate uneven heating caused by differences in apartment types and achieve accurate and fair heat distribution.

[0005] Preferably, in step S1, the process of deploying hydraulic decoupling devices in each building in the target area includes: At the entrance of each unit in each building of the secondary heating network in the target area, a hydraulic decoupling device with a differential pressure control valve as its core is installed to isolate user regulation disturbances from the source and build a stable hydraulic unit. At the user inlet downstream of the differential pressure control valve, a pressure-independent valve, i.e. a pressure-independent flow control valve, is installed in parallel to limit the user's initial flow, lock the user's design flow, and prevent local overflow and hydraulic competition. Through the synergistic effect of the differential pressure control valve and the pressure-independent valve, the original hydraulically coupled secondary heating network is divided into multiple independent hydraulic units, realizing the modularization of the hydraulic system, eliminating dynamic coupling imbalance, isolating pressure fluctuations caused by user self-adjustment behavior from propagating upstream, ensuring that user adjustments do not interfere with each other, maintaining the stability of the entire network pressure, integrating all independent hydraulic units in the target area, and forming a hydraulic decoupling platform by ID marking, realizing digital management of the system, and supporting precise monitoring and control.

[0006] Preferably, in step S1, constructing an independent hydraulic unit further includes: The differential pressure control valve uses a pressure compensator composed of an internal diaphragm and spring to sense and actively consume the excess pressure head in its branch in real time, eliminating the excess available pressure head at the near end and avoiding excessive heating from the source. The pressure compensator dynamically adjusts the valve core opening of the differential pressure control valve to limit the local pressure fluctuations caused by the valve action on the user side to the independent hydraulic unit where it is located, thus isolating user adjustment disturbances and ensuring the hydraulic stability of the main network of the system. By designing an isolation mechanism, the hydraulic regulation conditions of any user only affect its own unit, achieving localized control where "one user's regulation only affects its own unit," without disturbing the hydraulic stability of the main network and other users. This lays the physical foundation for the dynamic balance of the entire network, ensures that the hydraulic conditions of all users in the network do not interfere with each other, and improves system reliability.

[0007] Preferably, in step S2, the process of establishing a dynamic differential pressure maintenance system includes: At the most unfavorable loop of the main network of the secondary heating pipe network, a differential pressure sensor is installed to monitor the actual differential pressure value of key nodes on the loop in real time. The most unfavorable loop of the main network is the complete hydraulic circulation path from the outlet of the circulating water pump, through the pipe network to the user with the greatest resistance and the longest path, and then back to the inlet of the water pump. The key node is the node between the supply and return water pipes at the last heat inlet at the end of the most unfavorable loop. This accurately locates the hydraulic bottleneck of the system and ensures that the most unfavorable user has the available pressure head. The signal monitored by the differential pressure sensor is fed back to the central controller, which compares the actual differential pressure value with the system's preset constant differential pressure setpoint to obtain the differential pressure deviation value. The differential pressure deviation is fed back in real time to provide accurate input for closed-loop control. Based on the comparison results of the differential pressure deviation, control commands are generated and the circulating water pump is driven to operate at variable frequency. By adjusting the pump speed, the set differential pressure of the main network is dynamically maintained, providing a stable power source for the hydraulic decoupling platform. The pump output is dynamically adjusted to maintain a constant system differential pressure, achieving energy saving and stability.

[0008] Preferably, in step S3, the process of quantifying the heat load characteristics of the building complex includes: Collect historical operating data of the secondary heating network in the target area during its historical operation period, including outdoor temperature, representative typical room temperature, and water supply temperature, to establish a comprehensive and reliable data foundation and support the accurate construction of the model; By using the central controller to fit and learn from the collected historical operating data through regression analysis, a dynamic adjustment curve of outdoor temperature and water supply temperature is generated, which reflects the overall thermal inertia and heat dissipation characteristics of the building complex. This dynamic adjustment curve serves as a digital model of the system's heat load characteristics, enabling the heating system to be intelligently controlled according to actual load characteristics, thereby improving energy efficiency.

[0009] Preferably, in step S3, the process of generating the outdoor temperature-water supply temperature dynamic curve further includes: The central controller continuously receives real-time operating data and incorporates it into the learning sample set of the outdoor temperature-water supply temperature dynamic adjustment curve to ensure the timeliness and comprehensiveness of the model training data and avoid model aging. The central controller dynamically optimizes and corrects the parameters of the outdoor temperature-water supply temperature dynamic adjustment curve by periodically refitting, dynamically correcting model deviations and improving the accuracy and adaptability of water supply temperature setting. Through a self-learning process, the outdoor temperature-water supply temperature dynamic adjustment curve adapts to the drift of system thermodynamic characteristics caused by changes in building envelope and user habits, maintaining the accuracy of the model, ensuring its long-term effectiveness, and responding to changes in building conditions and user habits.

[0010] Preferably, in step S4, the process of adjusting the water supply temperature in advance to counteract the building's thermal inertia includes: The central controller accesses authoritative weather forecast services for the target area to obtain outdoor temperature forecast data for the next 24 to 72 hours, and obtains the future outdoor temperature forecast sequence, providing the system with a forward-looking control basis and enhancing its ability to respond to sudden weather changes. The predicted outdoor temperature sequence is substituted into the pre-established dynamic adjustment curve of outdoor temperature and water supply temperature to achieve accurate matching between water supply temperature and future meteorological conditions, thereby improving the predictability of heating. Based on the outdoor temperature-water supply temperature dynamic adjustment curve, a predicted adjustment curve for water supply temperature in the future time series is calculated and output. This guides the heat source side to adjust the water temperature in advance, effectively offsetting the temperature lag caused by the building's thermal inertia. Accordingly, control commands are sent to the water temperature control device on the heat source side in advance to offset the building's thermal inertia effect, achieving a pre-match between heat supply and building demand, and avoiding excessive heating from the source.

[0011] Preferably, S5 specifically includes: By deploying room temperature sensors at each user terminal and installing heat meters at the user entrance, user-side thermal data, including the actual heating demand and consumption of users, are collected, i.e., real-time data of each user, to fully perceive the actual heating status of users and provide a data foundation for precise regulation. The collected real-time data from each user is uploaded to the central controller. Combined with the water supply temperature prediction and adjustment curve, the water supply temperature value that needs to be actively adjusted is determined, thereby realizing feedforward control of the heating system and matching the heat source output with the load demand in advance. Data fusion and calculation are performed within the central controller to assess the matching degree between the current and predicted total system heating supply and the total heat load of the building complex. The system heat output is dynamically optimized to avoid overheating and energy waste. The matching degree is calculated based on a weighted average of the heating deviation rate and the room temperature compliance rate. The weight of the heating deviation rate is set to 0.4, and the weight of the room temperature compliance rate is set to 0.6. This achieves a balance between energy saving and comfort, prioritizes user experience, provides a basis for decision-making in subsequent refined allocation, avoids overheating, improves system energy efficiency, and realizes on-demand heating and rational resource allocation.

[0012] Preferably, S5 further includes: The room temperature sensor continuously collects data at set time intervals, and the heat meter accumulates and calculates the user's heat consumption, thereby realizing continuous monitoring and accurate measurement of the user's heat consumption behavior. The central controller cleans, filters, and diagnoses outliers on the received user-side thermal data to improve data quality and ensure that heating control decisions are based on reliable, high-quality data. By utilizing processed user-side thermal data, we can identify personalized load deviations among users caused by differences in apartment type, orientation, heat dissipation equipment, and individual preferences. This allows us to accurately fine-tune target objects, pinpoint the root causes of uneven heating, and support the formulation of differentiated control strategies.

[0013] Preferably, in step S6, the process of precisely distributing heat on the hydraulic decoupling platform includes: On the established hydraulic decoupling platform, the central controller performs regulation analysis based on the determined individual load deviations between users and the water supply temperature values ​​that need to be actively regulated to determine the flow regulation scheme, thereby achieving accurate identification and dynamic response of user-side heat load and improving the targeting of system regulation. Fine-tuning commands are sent to the valves (electric regulating valves) at the corresponding user's inlet to precisely adjust their opening, achieving accurate flow regulation on demand. This avoids overheating and energy waste, altering the flow rate into the user's indoor heat dissipation equipment. By changing the flow rate, the heat allocated to the user is precisely controlled to correct individual load deviations and adapt to different users' temperature preferences. This corrects uneven heat distribution among users, improves heating fairness and comfort, meets the actual heating needs of different users, and enhances the personalization level of system services.

[0014] This invention provides a control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction. It has the following beneficial effects: (I) This regulation method for achieving balance and precise heating of two networks based on hydraulic decoupling and load prediction physically divides the entire coupled pipe network into multiple independent hydraulic units by deploying differential pressure control valves at the unit inlet and working in conjunction with pressure-independent valves at the user inlet. The built-in pressure compensation mechanism can sense and actively consume excess pressure head in the branches in real time, limiting pressure fluctuations caused by user regulation within the unit. This achieves regulation by each household without interference, eliminating the dynamic hydraulic imbalance phenomenon where regulation by one household affects all other households from a physical perspective, and ensuring reliable execution of control commands and system convergence.

[0015] (II) This regulation method for achieving balance and precise heating between the two networks based on hydraulic decoupling and load forecasting generates a dynamic adjustment curve of outdoor temperature and water supply temperature by collecting historical operating data and learning from it. It also integrates high-precision weather forecasts to generate a future water supply temperature prediction and adjustment curve. Based on this, the water supply temperature of the heat source is adjusted in advance, effectively offsetting the thermal inertia effect of the building. This allows the system to change from a passive response to an active prediction, achieving dynamic and forward-looking matching between the total heat supply of the system and the predicted total heat load of the building complex. This avoids overheating or underheating caused by regulation based on lagging feedback from the source, significantly reducing heat source energy consumption and transmission and distribution power consumption, and achieving source-grid coordinated energy saving. Attached Figure Description

[0016] Figure 1 This is a schematic diagram illustrating the workflow of a control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to the present invention. Figure 2 This is a flowchart illustrating the method of the present invention for achieving dual-network balance and precise heating based on hydraulic decoupling and load prediction. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1, please refer to Figure 1 , Figure 2 This invention provides a technical solution: a control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction, comprising the following steps: S1. Deploy hydraulic decoupling devices in each building within the target area. This involves installing differential pressure control valves at the inlet of each unit and pressure-independent valves at the user inlets, creating independent hydraulic units to isolate user regulation disturbances and establish a hydraulic decoupling platform. At the inlet of each unit in each building within the target area's secondary heating network, install hydraulic decoupling devices with differential pressure control valves as the core. This isolates user regulation disturbances at the source, creating stable hydraulic units. At the user inlets downstream of the differential pressure control valves, install pressure-independent valves (i.e., pressure-independent flow control valves) in parallel to limit the initial flow of users. The initial flow rate is locked to the user's design flow rate to avoid local overflow and hydraulic competition. Through the synergistic action of differential pressure control valves and pressure-independent valves, the original hydraulically coupled secondary heating network is divided into multiple independent hydraulic units, realizing the modularization of the hydraulic system, eliminating dynamic coupling imbalance, isolating pressure fluctuations caused by user self-adjustment behavior from propagating upstream, ensuring that user adjustments do not interfere with each other, maintaining stable pressure across the entire network, integrating independent hydraulic units in all target areas, and forming a hydraulic decoupling platform by ID marking, realizing digital management of the system and supporting precise monitoring and control. The specific work involves: when implementing hydraulic decoupling retrofitting of the secondary heating network in the target area, installing a differential pressure control valve (dynamic differential pressure balancing valve) as the core hydraulic decoupling device at the inlet of each unit in each building. The selection of this differential pressure control valve should meet the system design differential pressure range (30-80kPa) and pipe diameter (DN25-DN80) requirements. Its built-in diaphragm and spring pressure compensation mechanism can sense the pressure difference changes before and after the valve in real time. At the user inlet at the rear end of the valve, a pressure-independent flow control valve is installed in parallel. This pressure-independent flow control valve has a preset initial flow function, and its flow setting range is 0.3-1.With a capacity of 2 m³ / h, the flow rate can be precisely set according to the user's designed heat load. Through the coordinated configuration of two types of valves, when the user adjusts the indoor thermostatic valve, the pressure-independent flow control valve can maintain a constant flow rate through the user. The differential pressure control valve at the unit inlet dynamically adjusts the valve core opening to limit pressure fluctuations within the unit, thereby dividing the originally hydraulically coupled pipe network system into multiple independent hydraulic units, each forming an independent hydraulic regulation area. After the valve installation is completed, all independent hydraulic units are integrated into a system. Each unit inlet differential pressure control valve and the user inlet pressure-independent valve are equipped with... The data acquisition module monitors the operating parameters of the valve in real time, including the pressure difference across the valve (accuracy ±2kPa), flow rate (accuracy ±3%FS), and valve opening (0-100%). This data is transmitted to the central monitoring platform via wired communication (M-BUS / RS485). On the central monitoring platform, each independent hydraulic unit is assigned a unique ID, using a three-level coding structure of "region-building-unit," such as "Z1-B2-U3." Here, Z1 represents region one of the target area's secondary heating network, B2 represents building two within region one, and U3 represents unit three of building two. The central monitoring platform, through the integration of a SCADA system, centrally monitors the operational status of all independent hydraulic units across the network. It displays in real-time the inlet differential pressure (setpoint deviation controlled within ±5 kPa) and user flow rate (fluctuation range controlled within ±8% of the setpoint) for each independent hydraulic unit, forming a complete hydraulic decoupling platform. Before system commissioning, a debugging procedure is performed, setting the initial flow rate of the pressure-independent valves at each user inlet according to design data. This setpoint is determined based on the user's design heat load (calculated at 40-70 W / m²) and the system's design supply and return water temperature difference (15-25℃), and is verified through the central monitoring system. The central monitoring platform conducts individual tests on each independent hydraulic unit to verify that when any user adjusts the flow rate within an independent hydraulic unit, its inlet differential pressure control valve can respond within 3-8 seconds, controlling the differential pressure fluctuation within ±7% of the set value, and ensuring that the inlet differential pressure change between adjacent independent hydraulic units does not exceed ±3%. Furthermore, after the system is officially operational, a regular inspection system is established, with valve performance testing conducted at least once per heating season, including diaphragm sealing checks, spring elasticity coefficient verification, and sensor accuracy calibration, to ensure the hydraulic decoupling device operates continuously and stably throughout the entire heating season (typically 120-150 days). Furthermore, in S1, the construction of independent hydraulic units also includes: the differential pressure control valve, through its internal diaphragm and spring-based pressure compensator, senses and actively consumes the excess pressure head of its branch in real time, eliminating the excess available pressure head at the near end and preventing excessive heating from the source. The pressure compensator, by dynamically adjusting the valve core opening of the differential pressure control valve, limits the local pressure fluctuations caused by the valve action on the user side to its independent hydraulic unit, isolating user regulation disturbances and ensuring the hydraulic stability of the main network. Through the design of the isolation mechanism, the hydraulic regulation conditions of any user only affect its own unit, achieving localized control of "one user's regulation only affects itself," without disturbing the hydraulic stability of the main network and other users, laying the physical foundation for the dynamic balance of the entire network, ensuring that the hydraulic conditions of all users in the network do not interfere with each other, and improving system reliability. The specific work involves the following: During the hydraulic decoupling retrofit, the differential pressure control valve integrates a pressure compensation mechanism consisting of a special rubber diaphragm and a pre-compression spring. This mechanism directly senses the actual pressure difference across the valve. When the system is running, the power provided by the circulating water pump creates unevenly distributed available pressure heads in the pipe network. The differential pressure control valve can detect the excess pressure head at the inlet of its branch (i.e., the independent hydraulic unit) that exceeds the set value in real time. Upon detection, the pressure compensation mechanism immediately generates a counteracting mechanical force, driving the valve core to move towards the closing direction, thus actively consuming the excess pressure head by creating local resistance. When flow regulation occurs on the user side, if a user closes the indoor thermostatic valve, the local resistance of its branch increases instantaneously, causing the pressure before the user's pressure-independent valve to rise. At this time, the differential pressure control valve at the unit inlet instantly senses the increase in downstream pressure (i.e., the pressure difference across the valve decreases) through its diaphragm. (Trend), the pressure compensation mechanism responds immediately, driving the valve core to open wider to maintain its set constant differential pressure. Conversely, when the user opens the valve wider, the downstream pressure tends to decrease, and the valve core moves towards closing. The entire response time for valve core opening adjustment is required to be completed within 3 to 8 seconds to ensure that pressure fluctuations can be quickly suppressed. Through dynamic valve core opening adjustment, the flow changes and pressure fluctuations caused by user regulation are limited to the independent hydraulic unit where the regulation occurs, preventing disturbances from propagating to the upstream main network and other parallel units. Through the collaborative design of the isolation mechanism, each unit equipped with a differential pressure control valve becomes an independent hydraulic unit. The pressure fluctuations generated by any user's hydraulic regulation are effectively absorbed and isolated by the differential pressure control valve of this unit, and their influence is limited to the unit. The differential pressure at the inlet of the system's main network and other independent hydraulic units remains highly stable, with fluctuations controlled within ±3% of the set value. S2. Establish a dynamic differential pressure maintenance system. This system uses differential pressure sensors to control the variable frequency operation of the circulating water pumps, maintaining the set differential pressure in the main network and ensuring its stability. This eliminates the root causes of dynamic hydraulic imbalances. Differential pressure sensors are installed at the most unfavorable loop in the main network of the secondary heating pipe network to monitor the actual differential pressure at key nodes in that loop in real time. The most unfavorable loop in the main network is the complete hydraulic circulation path from the outlet of the circulating water pump, through the pipe network to the user with the greatest resistance and longest path, and back to the pump inlet. The key node is the supply and return water pipe at the last heat inlet on the most unfavorable loop. The system precisely locates hydraulic bottlenecks at key nodes, ensuring the most unfavorable head for users. Signals from differential pressure sensors are fed back to the central controller, which compares the actual differential pressure with the preset constant differential pressure setting to obtain the differential pressure deviation. This deviation is fed back in real-time, providing accurate input for closed-loop control. Based on the comparison results, control commands are generated to drive the circulating water pumps in variable frequency operation. By adjusting the pump speed, the system dynamically maintains the stability of the main network's set differential pressure, providing a stable power source for the hydraulic decoupling platform. Dynamically adjusting pump output maintains a constant system differential pressure, resulting in energy savings and stability. The specific work involves analyzing the complete hydraulic circulation path in the secondary heating network system, starting from the outlet of the circulating water pump, flowing through the network to the user with the greatest resistance and longest path, and then returning to the pump inlet. This path is marked as the most unfavorable loop in the main network. Simultaneously, the node between the supply and return water pipes at the last heating inlet of this most unfavorable loop is defined as a critical node. High-precision differential pressure sensors are deployed at each critical node. These sensors have a range covering the expected differential pressure fluctuation range of the system (0~100 kPa), a measurement accuracy of no less than ±1.0% FS, and good temperature stability to adapt to environmental conditions of 0~80℃. Based on hydraulic calculations and actual commissioning, a preset constant differential pressure setpoint is determined, with a range between 30~50 kPa, sufficient to ensure that the user in the most unfavorable loop receives sufficient usable pressure head under design conditions. The differential pressure sensors are tested at 4~20 kPa. The mA analog signal continuously uploads the actual differential pressure value of the nodes monitored in real time to the central controller of the system. After receiving the actual differential pressure value from the most unfavorable loop, the central controller continuously compares it with the internally stored constant differential pressure setpoint to calculate the differential pressure deviation value. The PID (proportional-integral-derivative) control algorithm built into the central controller calculates based on the differential pressure deviation value and outputs a corresponding control command. This control command is a standard 4~20 mA analog signal, which is directly transmitted to the frequency converter of the circulating water pump. The frequency converter dynamically adjusts its output frequency according to this control command, thereby changing the operating speed of the water pump motor. Its adjustment range is between 30~50 Hz to ensure that the circulating water pump always works in the high-efficiency range. S3. Collect historical operating data including outdoor temperature, typical room temperature, and water supply temperature. Generate a dynamic curve of outdoor temperature-water supply temperature through regression analysis to quantify the heat load characteristics of the building complex. Collect historical operating data of the secondary heating network in the target area during its historical operation period, including outdoor temperature, representative typical room temperature, and water supply temperature, to establish a comprehensive and reliable data foundation to support accurate model construction. Use the central controller to fit and learn from the collected historical operating data using regression analysis methods, thereby generating a dynamic adjustment curve of outdoor temperature-water supply temperature that reflects the overall thermal inertia and heat dissipation characteristics of the building complex. This dynamic adjustment curve serves as a digital model of the system's heat load characteristics, enabling intelligent control of the heating system according to actual load characteristics and improving energy efficiency. The specific work involves: systematically collecting historical operational data of the secondary heating network in the target area. Data sources include outdoor temperature sensors installed at least 1.5 meters above the ground in shady areas of buildings, with a measurement accuracy of at least ±0.3℃; water supply temperature collected from the system's heat inlet, measured by a PT1000 platinum resistance temperature sensor with an accuracy of ±0.2℃; and indoor temperature data collected from representative users in each building (residents on middle floors and / or those not against the gable wall), with a room temperature sensor measurement accuracy of ±0.5℃. The data collection frequency is set to once every 15 minutes, continuously collecting data for at least one complete heating season (November 15th of the previous year to March 15th of the following year) to ensure coverage of different outdoor conditions throughout the heating season. Before being stored in the central controller's historical database, the collected raw historical operational data undergoes a preprocessing procedure to automatically remove null values ​​caused by sensor communication interruptions, and a moving average filtering algorithm is used to smooth and correct abnormal data that significantly exceeds the physically reasonable range, forming a comprehensive data set. High-quality historical datasets suitable for model training are required. After obtaining sufficient and reliable historical datasets, the central controller calls its embedded regression analysis algorithm module to perform nonlinear regression fitting with outdoor temperature as the independent variable and the average supply and return water temperature as the dependent variable. Among them, a polynomial regression based on the least squares method is used to autonomously establish a dynamic adjustment curve of outdoor temperature and supply water temperature. The mathematical form of this dynamic adjustment curve is a continuous function, which includes key parameters such as the reference supply water temperature (corresponding to the outdoor design temperature), the slope of the curve (characterizing the overall heat dissipation coefficient of the building), and the inflection point temperature (reflecting the nonlinear region caused by the thermal inertia of the building). All of these parameters are learned by the regression analysis algorithm from historical operating data. For example, a typical dynamic adjustment curve is as follows: when the outdoor temperature is higher than 8℃, the supply water temperature is set below 45℃; when the outdoor temperature drops to -5℃, the supply water temperature is gradually increased to the range of 65℃ to 70℃. This dynamic adjustment curve of outdoor temperature and supply water temperature is the digital model of the heat load characteristics of the building complex. The expression for the dynamic adjustment curve of outdoor temperature versus water supply temperature is as follows: ; In the formula: The water supply temperature setpoint is a function of the outdoor temperature, and its value varies with... The changes are continuous and smooth; The outdoor temperature is the model's input; a decrease in its value will lead to... Increase; The reference water supply temperature corresponds to the water supply temperature at the outdoor design temperature (or higher), representing the highest water supply temperature the system needs to provide in the coldest weather. At very low levels, Approaching ; This is the maximum water supply temperature offset, and... They jointly define the adjustment range of the water supply temperature; The inflection point temperature reflects the center of the nonlinear zone caused by the building's thermal inertia. Near this temperature, the supply water temperature rises at the fastest rate as the outdoor temperature decreases. k is the curve slope coefficient, determining the steepness of the transition zone and comprehensively characterizing the building's overall heat dissipation coefficient and the system's regulation characteristics. The larger the value, the steeper the curve, meaning a faster transition from high temperature and low load to low temperature and high load. The smaller the value, the flatter the curve and the smoother the transition; when When it is very high (above the inflection point). The term becomes very large, therefore, At the beginning or end of the heating season, when the weather is warmer, the system maintains a lower water supply temperature; when At very low levels (below the inflection point) The term approaches 0. During periods of severe cold, when the outdoor temperature reaches the design temperature, the system outputs the highest water supply temperature. At the turning point When the value is near the nearest integer, the "1" in the denominator plays a crucial role, making... exist and Rapid, non-linear changes occur between these points. The system responds to the building's thermal inertia and requires dynamic adjustment of the water supply temperature in the core region, where the curve has the steepest slope. In S3, the process of generating the outdoor temperature-water supply temperature dynamic curve also includes: the central controller continuously receives real-time operating data and incorporates the real-time operating data into the learning sample set of the outdoor temperature-water supply temperature dynamic adjustment curve to ensure the timeliness and comprehensiveness of the model training data and avoid model aging. The central controller dynamically optimizes and corrects the parameters of the outdoor temperature-water supply temperature dynamic adjustment curve by periodically refitting, dynamically corrects model deviations, and improves the accuracy and adaptability of water supply temperature setting. Through the self-learning process, the outdoor temperature-water supply temperature dynamic adjustment curve adapts to the drift of system thermal characteristics caused by changes in building envelope structure and user habits, maintains the accuracy of the model, maintains the long-term effectiveness of the model, and responds to changes in building status and user habits. The specific tasks are as follows: The central controller continuously receives real-time operating data from the PT1000 platinum resistance temperature sensor installed at the heat inlet and the outdoor temperature sensor at the shaded area of ​​the building, at a fixed interval of once every 15 minutes via its communication interface. Before being stored in the historical database, newly acquired real-time operating data undergoes a data validity verification process: the system verifies the integrity of data packets and automatically discards null values ​​or invalid frames caused by communication interruptions; it applies outlier diagnosis logic based on the Raida criterion to mark and remove data points that clearly exceed the physically reasonable range. Verified real-time operating data is automatically added to a continuously updated learning sample set. The total capacity of this learning sample set is set to cover the most recent 3 to 5 complete heating seasons (i.e., approximately 15,000 to 25,000 valid data points), and it is managed according to the first-in, first-out principle to ensure the quality of the learning sample set. It can both carry long-term historical patterns and focus on recent system characteristics. The system is set to automatically start a model refit task every 24 hours (i.e., a complete calendar day) during the off-peak business period (02:00 to 04:00). This refit task calls the regression analysis algorithm embedded in the central controller, using outdoor temperature as the independent variable and the average supply and return water temperature as the dependent variable. It performs a nonlinear polynomial regression calculation based on the least squares method on the updated entire learning sample set. The refit process is used to dynamically optimize the key parameters of the dynamic adjustment curve. Specifically, it recalculates and outputs the benchmark supply water temperature, curve slope, and inflection point temperature of the outdoor temperature-supply water temperature dynamic adjustment curve, so that the dynamic adjustment curve can track and fit the actual operating trajectory of the system, correct the cumulative error caused by long-term sensor drift, and maintain the accuracy of the dynamic adjustment curve under static conditions. S4. Based on the dynamic curve of outdoor temperature and water supply temperature, the weather forecast is used to predict future room temperature changes, and the water supply temperature prediction and adjustment curve is output to adjust the water supply temperature in advance to offset the building's thermal inertia and achieve precise heating matching on the heat source side. S5. Collect user-side thermal data, i.e. real-time data of each user, through room temperature sensors and heat meters, determine the individual load deviation between users, and determine the water supply temperature value that needs to be actively controlled by combining the water supply temperature prediction and adjustment curve, so that the total heat supply is dynamically matched with the heat load of the building group and avoids excessive heat supply. S6. Based on the user-side thermal data and the water supply temperature that needs to be actively controlled, the flow rate of the inlet valve is finely adjusted, and the heat is accurately distributed on the hydraulic decoupling platform to eliminate uneven heating caused by differences in apartment types and achieve accurate and fair heat distribution.

[0019] Example 2, as Figure 1 , Figure 2 As shown, based on Embodiment 1, the present invention provides a technical solution: In S4, the process of adjusting the water supply temperature in advance to offset the building's thermal inertia includes: the central controller accesses the authoritative weather forecast service of the target area, obtains outdoor temperature prediction data for the next 24 to 72 hours, obtains the future outdoor temperature prediction sequence, provides the system with a forward-looking control basis, enhances the response capability to sudden weather changes, substitutes the future outdoor temperature prediction sequence into the pre-established outdoor temperature-water supply temperature dynamic adjustment curve, realizes the accurate matching of water supply temperature with future meteorological conditions, improves the predictability of heating, and calculates and outputs a water supply temperature prediction adjustment curve on the future time series based on the outdoor temperature-water supply temperature dynamic adjustment curve, guides the heat source side to adjust the water temperature in advance, effectively offsets the temperature lag caused by the building's thermal inertia, and sends a control command to the water temperature control device on the heat source side in advance to offset the building's thermal inertia effect, realizes the pre-matching of heat supply and building demand, and avoids excessive heating from the source; The specific tasks are as follows: The central controller accesses authoritative weather forecast services provided by the meteorological department through a standardized data interface (RESTful API or OPC UA). It automatically acquires high-precision, gridded weather forecast data for the target area for the next 24 to 72 hours every 6 hours, focusing on outdoor temperature. The time resolution of the acquired forecast data is no less than 1 hour, and the temperature prediction accuracy is required to be better than ±1.0℃. The central controller performs validity verification and time alignment processing on the received raw weather forecast data, removing obvious outliers and synchronizing it with the system's internal clock to form a continuous and reliable future outdoor temperature prediction sequence. Its time range covers the typical thermal response cycle (6 to 24 hours) corresponding to the building's thermal inertia, ensuring the effectiveness of the prediction. After obtaining the processed future outdoor temperature prediction sequence, the central controller inputs it into the system's autonomously established and continuously optimized outdoor temperature-water supply temperature dynamic adjustment curve, using outdoor temperature as the independent variable. The corresponding water supply temperature setpoint is calculated in real time using an embedded regression function. The calculation process is performed point by point according to the predicted time series, and finally a water supply temperature prediction and adjustment curve corresponding to the outdoor meteorological conditions for the next 24 to 72 hours is generated. This water supply temperature prediction and adjustment curve clearly defines the target water supply temperature value that should be maintained at the system heat inlet at each time point in the future (with an interval of 1 hour). Its value range is set between 35℃ and 75℃ according to the system design, ensuring accurate matching between heat supply and building predicted load. Based on the generated water supply temperature prediction and adjustment curve, the central controller sends control instructions to the water temperature control device on the heat source side in advance. The control instructions are sent through a 4-20mA analog signal to adjust the system water supply temperature to the future value set by the prediction curve, compensating for the thermal inertia caused by the building envelope and indoor heat capacity, so that the indoor temperature can still be maintained within the set range when actual meteorological changes occur. The expression for the water supply temperature prediction and adjustment curve is as follows: ; In the formula: The predicted water supply temperature setpoint for future time t is a function of future time t, forming a curve that changes with time; t is a future time point, representing the number of hours calculated from the current time. The predicted outdoor temperature at time t is derived from a processed weather forecast sequence; The reference water supply temperature; R represents the maximum water supply temperature offset; R is the curve adjustment slope. The inflection point temperature; when predicting a certain period in the future. When there is a significant decrease, for each decrease , The number will decrease, resulting in Accordingly, the water supply temperature is gradually increased several hours in advance to counteract the building's thermal inertia and ensure that the indoor temperature remains stable when a cold wave arrives; when a certain period in the future is predicted... When there is a significant increase, for each increase , The item increases, leading to Accordingly, the water supply temperature is reduced slowly several hours in advance to avoid overheating indoors when the weather warms up, thus achieving energy conservation; S5 specifically includes: collecting user-side thermal data, including actual heating demand and consumption, through room temperature sensors deployed at each user terminal and heat meters installed at the user entrance, i.e., real-time data of each user, to comprehensively perceive the actual heating status of users and provide a data foundation for precise control. The collected real-time data of each user is uploaded to the central controller, and the water supply temperature prediction and adjustment curve is combined to determine the water supply temperature value that needs to be actively controlled, realizing feedforward control of the heating system, matching the heat source output and load demand in advance, and performing data fusion and calculation in the central controller to evaluate the matching degree between the current and predicted total system heat supply and the total heat load of the building complex, dynamically optimizing the system heat output, and avoiding overheating and energy waste. The matching degree is obtained by weighted calculation based on the heat supply deviation rate and the room temperature compliance rate. The weight of the heat supply deviation rate is set to 0.4, and the weight of the room temperature compliance rate is set to 0.6, to achieve a balance between energy saving and comfort, prioritize user experience, provide a decision basis for subsequent refined allocation, avoid overheating, improve system energy efficiency, and achieve on-demand heating and rational resource allocation. The specific work involves collecting user-side thermal data, i.e., real-time data from each user. Specifically, a room temperature sensor with wireless communication capabilities (LoRaWAN or NB-IoT) is installed in the living room or main room of each household. Its measurement range is 5℃ to 30℃, with an accuracy of no less than ±0.3℃. The data acquisition interval is set to 15 minutes. Simultaneously, an ultrasonic heat meter is installed on the water supply pipe at each user's inlet. Its flow measurement accuracy is ±2%, and its temperature measurement accuracy is ±0.1℃. This meter measures the user's heat data in real time, including instantaneous flow and cumulative heat consumption. The collected user room temperature and heat data are then initially aggregated through a data concentrator within the building, and subsequently uploaded to the central controller via a wireless network using the Modbus protocol. TCP is used, and the data transmission delay is required to be less than 10 seconds to ensure the real-time performance and integrity of the data. After receiving the thermal data from all users on the network, the central controller performs data cleaning and standardization, eliminating invalid data caused by communication interruptions or equipment malfunctions. The central controller integrates the processed user data with the current and future predicted operating status, and combines it with the generated water supply temperature prediction and adjustment curve (the curve is at 1-hour intervals, and the temperature setpoint range is 35℃ to 75℃). The central controller calculates the theoretical heat load of the building complex in real time through the heat balance model, and compares it with the actual total heat supply of the system (calculated based on the total supply and return water temperature difference and total flow rate). It calculates the heat supply deviation rate (the percentage of the difference between the actual heat supply and the predicted load to the predicted load, with a target control within ±8%) and the room temperature compliance rate (the proportion of all network users whose room temperature is within the range of 18℃-22℃, with a target ≥95%), and evaluates the matching degree between the current and predicted total system heat supply and the total heat load of the building complex. This ensures the dynamic matching between the total system heat supply and the total heat load of the building complex, avoiding energy waste caused by excessive heating from the source. The expression for the matching degree between the total heat supply of the system and the total heat load of the building complex is as follows: ; ; ; In the formula: M represents the matching degree between the total heat supply of the system and the total heat load of the building complex. The higher the value of M, the better the matching degree between the total heat supply of the system and the total heat load of the building complex; E represents the heat supply deviation rate. The smaller the value, the more accurate the heat matching. The actual total heat supply of the system (calculated from the total supply and return water temperature difference and total flow rate); To predict the total heat load of a building complex using a heat balance model; The target value for the heat supply deviation rate; For the room temperature compliance rate, The higher the value, the better the user comfort. This refers to the number of users whose room temperature is within the comfortable range of 18℃-22℃. The total number of users monitored across the entire network; the target value for the room temperature compliance rate; Let be the weight coefficient, and satisfy... When the system is running and hour, To achieve the best match; any deterioration in either aspect (energy consumption or comfort) will lead to a decrease in the M value. Due to the characteristics of the logarithmic function, the penalty for slightly falling below 95% is far greater than the penalty for slightly rising above 8% in E. This is reflected in the priority of the control strategy to achieve energy saving while ensuring comfort. In addition, S5 also includes: a room temperature sensor that continuously collects data at set time intervals, a heat meter that accumulates and calculates the user's heat consumption, realizing continuous monitoring and accurate metering of the user's heating behavior, and a central controller that cleans, filters, and diagnoses outliers on the received user-side thermal data to improve data quality and ensure that heating control decisions are based on reliable and high-quality data. Using the processed user-side thermal data, it identifies personalized load deviations between users caused by differences in apartment type, orientation, heat dissipation equipment, and personal preferences, so as to accurately fine-tune the target object, accurately locate the root cause of uneven heating, and support the formulation of differentiated control strategies. The specific work involves: a room temperature sensor continuously collecting indoor temperature data from the user at fixed intervals of 15 minutes. Its installation location follows industry standards, situated in the living room or main room at a height of 1.5 meters above the ground to avoid interference from local cold or heat sources and direct sunlight, ensuring that the measured temperature is a representative dry-bulb temperature. Simultaneously, an ultrasonic heat meter installed on the user's inlet water supply pipe collects instantaneous flow rate and supply and return water temperatures at a frequency of no less than once per second, and applies standard thermodynamic formulas... (in For density, For specific heat capacity, To account for the temperature difference between supply and return water, The system calculates and accumulates users' heat consumption in real time (using volumetric flow rate). The collected room temperature and heat data are encapsulated and cached in a building-level data concentrator. Data is then uploaded to the central controller in batches every 15 minutes via LoRaWAN or NB-IoT wireless networks using the Modbus TCP protocol. The end-to-end communication latency from data acquisition to delivery to the central controller is controlled within 10 seconds to ensure the real-time and continuous nature of the data stream. Upon receiving the raw data stream, the central controller executes a standardized data cleaning and quality improvement procedure. The data cleaning module automatically identifies and removes data packet loss (null values) or frame errors caused by communication interruptions. Data filtering and anomaly diagnosis logic are activated: For room temperature data, a sliding window detection method based on the Raida criterion is used to scan five consecutive data points (i.e., a 75-minute window), marking and removing instantaneous jumps that clearly exceed the physically reasonable range; for heat data, the continuity of instantaneous power is verified, and sudden changes exceeding three standard deviations of the historical mean are identified and removed. The values ​​are smoothed and corrected, and valid data that passes the verification is timestamped and stored in the real-time database. Based on the high-quality data, the process of identifying personalized load deviations is initiated using the processed user-side thermal data. The central controller creates a scatter plot for each user with room temperature as the vertical axis and outdoor temperature as the horizontal axis. Through cluster analysis, the room temperature-outdoor temperature relationship curve for each user is identified. The user's heat consumption data is normalized with the corresponding indoor and outdoor temperature difference, and the heat consumption index per unit area (W / ㎡·℃) under unit temperature difference is calculated. By comparing this index with users across the entire network, the static load deviation caused by the inherent physical attribute differences of apartment type (top floor, corner, and middle units), orientation (south and north), thermal insulation performance of building envelope, and efficiency of heat dissipation equipment (radiators, underfloor heating) is accurately identified. At the same time, by analyzing the long-term preference deviation of user room temperature relative to the set value, the dynamic personalized adjustment preference of users is identified, and a target object list containing labels for high-demand users, low-demand users, and users who prefer high temperatures is generated. The expression for the heat consumption per unit area under a unit temperature difference is as follows: ; ; In the formula: This is the heat consumption per unit area of ​​user i under a unit temperature difference. The higher the value, the worse the thermal insulation performance of the building space to which the user belongs or the higher the heat dissipation demand, and the user belongs to the category of high static load user. For a certain calculation period Within, the cumulative heat consumption of user i; Let be the average thermal power of user i during the calculation period; For user i, the internal heating area; The indoor temperature for user i; Outdoor temperature; high A value indicating that a user needs to expend more heat to maintain the same indoor-outdoor temperature difference as others indicates a user with a large static load deviation, and is a target for which the flow rate needs to be appropriately increased in the fine-tuning strategy; low The value indicates that the user's building space has good thermal insulation performance or high heat gain, which is the target in the fine-tuning strategy that allows for a suitable reduction in flow without affecting comfort; The user dynamic preference tag list identifies behavioral preferences and defines dynamic personalized adjustment preferences by analyzing users' long-term room temperature data: The expression for the user tag indicating preference for high / low temperatures is as follows: ; ; In the formula: The average room temperature preference bias for user i; Let be the average indoor temperature of user i during the statistical period; Set the system's reference temperature ; Label the user's temperature preference; The temperature deviation threshold for triggering preference labels; For users who prefer high temperatures; For users who prefer low temperatures; For users with no particular preferences; The expressions for high / low demand user tags are as follows: ; ; In the formula: The overall needs score for user i; The average indoor temperature for all users across the network; , These are the weighting coefficients, and ; , The scoring thresholds for determining high and low demand; User needs and preferences tags; For high-demand users; For users with low demand; For users with ordinary needs; In S6, the process of precise heat distribution on the hydraulic decoupling platform includes: On the established hydraulic decoupling platform, the central controller performs control analysis based on the determined individual load deviations between users and the water supply temperature values ​​that need to be actively controlled to determine the flow control scheme, realize the accurate identification and dynamic response of user-side heat load, improve the system control targeting, issue fine-tuning commands to the valves (electric regulating valves) at the corresponding user inlet, finely adjust their valve openings, realize precise flow adjustment on demand, avoid overheating and energy waste, change the flow rate flowing into the user's indoor heat dissipation equipment, and precisely control the heat allocated to the user by changing the flow rate to correct its individual load deviation, adapt to the temperature preferences of different users, correct uneven heat distribution among users, improve the fairness and comfort of heating, meet the actual heating needs of different users, enhance the personalization level of system services, and substantially control the share of heat allocated to specific users through flow fine-tuning, thereby correcting the uneven heating in the "last mile", realizing precise and fair distribution of user-side heat on the basis of total heat matching, eliminating end-point heating differences, and achieving overall system thermal balance and energy efficiency optimization. The specific work involves the central controller, on the established hydraulic decoupling platform, performing control analysis based on pre-processed thermal data of all network users and predicted water supply temperature adjustment curves. It calls the central controller's built-in optimization algorithm, whose core input parameters include: heat consumption per unit area for each user, dynamic preference tags, and current and predicted water supply temperature values. With a room temperature compliance rate ≥95% as the primary constraint and a heat supply deviation rate controlled within ±8% as the energy-saving target, a personalized flow control scheme is calculated for the target user list (not exceeding 15% of the total number of network users). This control scheme is quantified into specific opening adjustment values ​​for the electric regulating valves at the inlet of each target user, and a fine-tuning instruction set is generated. The adjustment range is controlled between ±5% and ±15% of the current opening to avoid over-adjustment. The fine-tuning instruction set is transmitted through the system's control network using Modbus. The TCP protocol, with a control cycle of 15 minutes, sends batches of data to the corresponding building data concentrators, which then distribute them via the M-BUS bus to the actuators of the indoor electric regulating valves. Upon receiving a fine-tuning command, the electric regulating valve at the user's inlet (its diameter is DN15 or DN20 based on the design flow rate, with a preset valve authority of not less than 0.3) is driven by its actuator to actuate the valve core, precisely adjusting the valve opening. Changes in opening directly alter the flow rate of circulating water into the user's indoor cooling equipment; its design flow range is 0.3-1.2. According to the laws of thermodynamics, by increasing the flow rate for users with high heat consumption per unit area or those who prefer high temperatures, the actual heat gain is increased; correspondingly, the flow rate for users with low heat consumption per unit area or those who prefer low temperatures is reduced, gently suppressing their heat gain. The entire adjustment process requires the valve's full-stroke response time to be between 20-60 seconds to ensure the stability and accuracy of the adjustment, avoid hydraulic shock and sudden changes in room temperature, and ensure that the system pressure fluctuations caused by this flow rate fine-tuning for a single user are limited to this independent hydraulic unit and will not interfere with the hydraulic conditions of the main system network or other users. Through continuous, data-driven flow rate fine-tuning, macroscopic matching between total heat supply and total building load is achieved. Under the premise of adequate distribution, the precise redistribution of heat in the "last mile" involves dynamically weighting the limited total heat source according to the actual static load demand and dynamic comfort preferences of each user. After several hours to several adjustment cycles of operation, the room temperature data of all users in the network is collected again and fed back to the central controller. This corrects systemic room temperature deviations caused by apartment type and orientation, improving and maintaining the room temperature compliance rate above 95%. At the same time, the flow is precisely directed to the users who need it most, avoiding excessive heating for nearby users or users with low demand. Overall, on-demand heating is achieved, improving heating comfort and fairness while promoting the optimization of system operating energy efficiency, completing a precise closed-loop control of the entire chain from heat source to end.

[0020] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0021] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load forecasting, characterized in that, Includes the following steps: S1. Deploy hydraulic decoupling devices in each building in the target area to construct independent hydraulic units, isolate user regulation disturbances, and establish a hydraulic decoupling platform; S2. Establish a dynamic differential pressure maintenance system, and use the differential pressure sensor to control the variable frequency operation of the circulating water pump to maintain the set differential pressure of the main network. S3. Collect historical operating data including outdoor temperature, typical room temperature and water supply temperature, and generate a dynamic curve of outdoor temperature-water supply temperature through regression analysis to quantify the heat load characteristics of the building complex. S4. Based on the outdoor temperature-water supply temperature dynamic curve, incorporate weather forecasts to predict future room temperature changes and output a predicted adjustment curve for water supply temperature. S5. Collect user-side thermal data through room temperature sensors and heat meters, and determine the water supply temperature value that needs to be actively controlled by combining the water supply temperature prediction and adjustment curve, so as to dynamically match the total heat supply with the heat load of the building complex. S6. Based on the user-side thermal data and the water supply temperature that needs to be actively controlled, the flow rate of the inlet valve is finely adjusted, and the heat is accurately distributed on the hydraulic decoupling platform.

2. The control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to claim 1, characterized in that: In step S1, the process of deploying hydraulic decoupling devices in each building in the target area includes: At the entrance of each unit in each building of the secondary heating network in the target area, a hydraulic decoupling device with a differential pressure control valve as its core is installed. At the user inlet downstream of the differential pressure control valve, a pressure-independent valve, i.e. a pressure-independent flow control valve, is installed in parallel to limit the user's initial flow. Through the synergistic effect of the differential pressure control valve and the pressure-independent valve, the original hydraulically coupled secondary heating network is divided into multiple independent hydraulic units, isolating the upstream propagation of pressure fluctuations caused by user self-adjustment behavior, integrating the independent hydraulic units in all target areas, and forming a hydraulic decoupling platform by ID marking.

3. The control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to claim 2, characterized in that: In S1, constructing an independent hydraulic unit also includes: The differential pressure control valve senses and actively consumes the excess pressure head of its branch in real time through a pressure compensator composed of a diaphragm and a spring inside it. The pressure compensator limits the local pressure fluctuations caused by the valve action on the user side to the independent hydraulic unit by dynamically adjusting the valve core opening of the differential pressure control valve. Through the design of the isolation mechanism, the hydraulic regulation conditions of any user only affect its own unit.

4. The control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to claim 1, characterized in that: In step S2, the process of establishing a dynamic differential pressure maintenance system includes: At the most unfavorable loop of the main network of the secondary heating network, a differential pressure sensor is installed to monitor the actual differential pressure value of the key nodes on the loop in real time. The most unfavorable loop of the main network is the complete hydraulic circulation path from the outlet of the circulating water pump, through the network to the user with the greatest resistance and the longest path, and then back to the inlet of the water pump. The key node is the node between the supply and return water pipes at the last heat inlet of the most unfavorable loop. The signal monitored by the differential pressure sensor is fed back to the central controller, which compares the actual differential pressure value with the system's preset constant differential pressure setting value to obtain the differential pressure deviation value. Based on the comparison results of the differential pressure deviation, control commands are generated and the circulating water pump is driven to operate at variable frequency. The set differential pressure of the main network is dynamically maintained by adjusting the pump speed.

5. The control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to claim 1, characterized in that: In S3, the process of quantifying the heat load characteristics of the building complex includes: Collect historical operating data of the secondary heating network in the target area during its historical operation period, including outdoor temperature, representative typical room temperature, and water supply temperature; By using the central controller to fit and learn from the collected historical operating data through regression analysis, a dynamic adjustment curve of outdoor temperature and water supply temperature is generated, which reflects the overall thermal inertia and heat dissipation characteristics of the building complex.

6. The control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to claim 5, characterized in that: In step S3, the process of generating the outdoor temperature-water supply temperature dynamic curve also includes: The central controller continuously receives real-time operating data and incorporates the real-time operating data into the learning sample set of the outdoor temperature-water supply temperature dynamic adjustment curve. The central controller dynamically optimizes and corrects the parameters of the outdoor temperature-water supply temperature dynamic adjustment curve by periodically refitting. Through a self-learning process, the outdoor temperature-water supply temperature dynamic adjustment curve adapts to the drift in system thermodynamic characteristics caused by changes in building envelope and user habits.

7. The control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to claim 1, characterized in that: In step S4, the process of adjusting the water supply temperature in advance to counteract the building's thermal inertia includes: The central controller accesses authoritative weather forecast services for the target area to obtain outdoor temperature forecast data for the next 24 to 72 hours and obtains the future outdoor temperature forecast sequence. The predicted sequence of future outdoor temperatures is substituted into the pre-established dynamic adjustment curve of outdoor temperature and water supply temperature. Based on the outdoor temperature-water supply temperature dynamic adjustment curve, a predicted adjustment curve for water supply temperature in the future time series is calculated and output. Accordingly, control commands are sent to the water temperature control device on the heat source side in advance to counteract the thermal inertia effect of the building.

8. The control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to claim 1, characterized in that: S5 specifically includes: By deploying room temperature sensors at each user terminal and installing heat meters at the user entrance, user-side thermal data, including the user's actual heating demand and consumption, is collected, i.e., real-time data for each user. The collected real-time data from each user is uploaded to the central controller, and the water supply temperature prediction and adjustment curve is used to determine the water supply temperature value that needs to be actively controlled. Data fusion and calculation are performed within the central controller to assess the matching degree between the current and predicted total system heating supply and the total heat load of the building complex. The matching degree is calculated by weighting the heating supply deviation rate and the room temperature compliance rate. The weight of the heating supply deviation rate is set to 0.4, and the weight of the room temperature compliance rate is set to 0.

6.

9. The control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to claim 8, characterized in that: The S5 also includes: The room temperature sensor continuously collects data at set time intervals, and the heat meter accumulates and calculates the user's heat consumption. The central controller cleans, filters, and diagnoses outliers in the received user-side thermal data. By utilizing processed user-side thermal data, we can identify personalized load deviations among users caused by differences in apartment type, orientation, heat dissipation equipment, and individual preferences, in order to accurately fine-tune the target objects.

10. The control method for achieving secondary network balance and precise heating based on hydraulic decoupling and load prediction according to claim 1, characterized in that: In step S6, the process of precisely distributing heat on the hydraulic decoupling platform includes: On the established hydraulic decoupling platform, the central controller performs regulation analysis and determines the flow regulation scheme based on the determined individual load deviations between users and the water supply temperature value that needs to be actively regulated. A fine-tuning command is sent to the valve at the corresponding user's entrance to precisely adjust its opening degree, thereby changing the flow rate into the user's indoor heat dissipation equipment. By changing the flow rate, the heat allocated to the user is precisely controlled to correct individual load deviations and adapt to different users' temperature preferences.

Images