Valve opening control method for user-side hydraulic balance

Abstract

The invention relates to the technical field of valve opening control, and discloses a valve opening control method for user-side hydraulic balance. The method comprises the following steps: carrying out parameter acquisition on the buried pipe cold storage system to obtain dynamic system parameter data; performing cold load fluctuation spectrum analysis and multi-scale decomposition based on the dynamic system parameter data to obtain a user demand prediction model and a hydraulic balance ideal flow distribution proportion; generating a comprehensive system state evaluation index according to the user demand prediction model and the hydraulic balance ideal flow distribution proportion; constructing a global optimization objective function based on the comprehensive system state evaluation index, and solving to obtain a time-phased valve adjustment strategy; and a valve flow characteristic model is constructed according to the time-phased valve adjusting strategy and the valve historical response data, the target opening degree of each adjusting valve is calculated, and a valve control execution instruction is output. The hydraulic balance strategy can be dynamically adjusted according to different working conditions, and flexible coordination of hydraulic balance and cooling requirements is achieved.

Description

Technical Field

[0001] This application relates to the technical field of valve opening control, and particularly to a valve opening control method for household-side hydraulic balance. Background Art

[0002] As an efficient and energy-saving temperature control technology, the buried pipe energy storage cooling system is widely used in green buildings and district energy systems. This system utilizes the relatively stable underground temperature characteristics, stores and releases thermal energy by circulating fluid in underground pipelines, and can effectively solve the peak-valley difference of energy, improving energy utilization efficiency. However, in practical applications, due to factors such as uneven distribution of cold user loads, complex and variable pipe networks, and external environmental disturbances, the buried pipe energy storage cooling system often exhibits hydraulic imbalance on the end-user side, resulting in insufficient cooling supply for some users while excessive cooling supply for others, not only reducing the overall energy efficiency of the system but also affecting user comfort and satisfaction.

[0003] Traditional household-side hydraulic balance adjustment methods mainly rely on manual experience to adjust static balance valves, unable to adapt to the dynamic changes in cooling loads. Although some improved solutions introduce dynamic automatic adjustment technologies, they often only consider a single parameter (such as differential pressure or flow rate) for local optimization, lacking a comprehensive analysis of the overall system operating state and multi-objective collaborative optimization. Especially in complex buried pipe energy storage cooling systems, due to multiple heat transfer links and large system inertia, the control accuracy and response speed of traditional methods cannot meet actual requirements. In addition, most existing technologies adopt fixed parameter control strategies and fail to make full use of system operation data and advanced data analysis technologies for adaptive optimization, resulting in low long-term operation efficiency of the system. Summary of the Invention

[0004] This application provides a valve opening control method for household-side hydraulic balance, which can dynamically adjust the hydraulic balance strategy according to different working conditions and achieve flexible coordination between hydraulic balance and cooling demand.

[0005] In a first aspect, this application provides a valve opening control method for household-side hydraulic balance, and the valve opening control method for household-side hydraulic balance includes: Collect parameters of the buried pipe energy storage cooling system to obtain dynamic system parameter data; Based on the dynamic system parameter data, perform cold load fluctuation spectrum analysis and multi-scale decomposition to obtain a user demand prediction model and an ideal flow distribution ratio for hydraulic balance; Generate a comprehensive system state evaluation index according to the user demand prediction model and the ideal flow distribution ratio for hydraulic balance; Based on the comprehensive system state evaluation index, construct a global optimization objective function and solve to obtain a valve adjustment strategy in sub-periods; Construct a valve flow characteristic model based on the time - segmented valve regulation strategy and valve historical response data, calculate the target opening degree of each regulating valve, and output valve control execution instructions.

[0006] In the technical solution provided by this application, a complete dynamic database of system parameters is constructed by setting multiple groups of sensors at the target nodes, providing a comprehensive and accurate data basis for hydraulic balance control; cold - load fluctuation spectrum analysis and multi - scale decomposition techniques are used to accurately grasp the load characteristics, users are classified according to the load stability index, and a differential prediction model is adopted to improve the load prediction accuracy; a comprehensive system state evaluation index is constructed to quantitatively characterize the degree of hydraulic imbalance, turning the control from qualitative judgment to quantitative control; a global optimization function is constructed based on the idea of multi - objective optimization, and the optimal regulation strategy that takes into account both system efficiency and user comfort is obtained by solving through a genetic algorithm; an adaptively corrected flow characteristic model is established to overcome the deviation of the actual valve characteristics, and a smoothing processing algorithm is adopted to avoid equipment wear caused by frequent regulation; a reinforcement learning algorithm is introduced to form a closed - loop feedback adaptive control mechanism to continuously optimize the regulation strategy; the system reliability is improved through valve health state evaluation, and the hydraulic balance strategy is dynamically adjusted according to different working conditions to achieve flexible coordination between hydraulic balance and cooling demand and meet diverse operation requirements. Brief Description of the Drawings

[0007] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0008] Figure 1 It is a schematic diagram of an embodiment of the valve opening control method for household - side hydraulic balance in the embodiments of this application. Detailed Embodiments

[0009] The embodiment of the present application provides a method for controlling the valve opening for hydropower balance at the user end. Terms such as "first", "second", "third", "fourth", etc. (if any) in the specification, claims and the above-mentioned drawings of the present application are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments described here can be implemented in an order other than that illustrated or described here. In addition, the term "comprising" or "having" and any variation thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or devices.

[0010] For ease of understanding, the specific process of the embodiment of the present application will be described below. Please refer to Figure 1 , an embodiment of the method for controlling the valve opening for hydropower balance at the user end in the embodiment of the present application includes: Step S101, collect parameters of the buried pipe cold storage system to obtain dynamic system parameter data; It can be understood that the execution subject of the present application can be a valve opening control system for hydropower balance at the user end, or a terminal or a server. Specifically, it is not limited here. The embodiment of the present application takes the server as the execution subject as an example for illustration.

[0011] Specifically, on the cold user side of the buried pipe cold storage system, temperature sensors and pressure sensors are installed on the branch pipelines to collect the supply water temperature, return water temperature, supply water pressure, and return water pressure of the chilled water respectively, reflecting the heat load and hydraulic state on the cold user side. Electromagnetic flowmeters are installed on the branch pipelines of each user to collect the flow data of the user branch pipelines, understand the cooling demand of each user, so as to ensure accurate adjustment of the system flow distribution and meet the needs of users. Through data collection on the cold user side, a parameter dataset of the cold user side is obtained, including key parameters such as the flow rate, temperature, and pressure of the chilled water. At the same time, temperature sensors are installed at the inlet and outlet of the buried pipe shell-and-tube heat exchanger to collect the temperature data at the inlet and outlet of the heat exchanger respectively, and reflect the operating state of the heat exchange system in real time and understand the heat exchange effect. Temperature sensors are installed at key parts of the precooled evaporative cooling chiller to collect the air temperature before and after the direct evaporative cooling filler and the water temperature in the chilled water tank. These temperature data help to monitor the efficiency of the heat exchange system, understand the heat exchange situation during the cooling process, and ensure that the system works efficiently. By collecting the temperature data of the heat exchange system, the cold load distribution is optimized, and the energy utilization efficiency of the system is improved. Inside the cold storage modular unit, pressure sensors and temperature sensors are installed to collect the pressure and temperature data of the refrigerant before and after the four-way reversing valve, as well as the pressure and temperature at the outlet of the fluorine pump. These data are key indicators for understanding the performance of the refrigeration system, which can reflect the flow state of the refrigerant, the efficiency of the compression process, and the system pressure change, so as to evaluate the operating condition of the refrigeration module. An electric control valve is installed on the main supply pipe of each cold user to monitor the opening and flow rate changes of the valve in real time. By collecting the operating parameters of these core components of the system, a parameter dataset of the operation of the core components of the system is obtained. The complete parameter dataset of the cold user side, the operation parameter dataset of the heat exchange system, and the operation parameter dataset of the core components of the system are subjected to data standardization processing to convert data from different sources and different types into comparable dynamic system parameter data.

[0012] Step S102: Based on the dynamic system parameter data, perform cold load fluctuation spectrum analysis and multi-scale decomposition to obtain a user demand prediction model and an ideal flow distribution ratio for hydraulic balance; Specifically, the real-time cooling load of each user branch is extracted from the dynamic system parameter data. The calculation of the cooling load depends on the temperature difference between the supply and return water and the flow rate data of each user branch. The temperature difference between the supply and return water and the flow rate data are collected by the installed temperature sensors and flow meters, so as to obtain the real-time cooling load. All the real-time cooling load data are used to construct a three-dimensional matrix according to the user identification and time dimension, forming a cooling load distribution matrix, which effectively describes the cooling load changes of different user branches at different time periods. According to the cooling load distribution matrix, the spectral analysis of the cooling load time series is carried out to reveal the periodic characteristics of the load fluctuation. Through Fourier transform, the periodic law existing in the load fluctuation is identified, and the periodic characteristics are decomposed at multiple scales by wavelet transform. The load fluctuation is decomposed into three different types of loads: basic load, periodic load and random load, so as to more accurately understand the change trend of user demand. The basic load represents the constant demand of users, the periodic load reflects the load fluctuation caused by daily life or seasonal changes, and the random load reflects the unpredictable demand changes. Based on the decomposed load types, the historical load mean and standard deviation of each user branch are calculated to obtain the load stability index. The load stability index is an important parameter to measure the stability of user demand changes. By calculating the ratio of the standard deviation to the mean of each branch, users are divided into three categories: high stability, medium stability and low stability. High-stability users have smaller load fluctuations, while low-stability users face larger fluctuations. According to the stability of different users, different models are used for demand prediction. For high-stability users, a linear regression model is used for prediction, and their load changes are relatively regular; for medium-stability users, a seasonal ARIMA model is adopted to effectively capture seasonal fluctuations; for low-stability users, a long short-term memory network (LSTM) model is used to obtain the highly nonlinear characteristics of load fluctuations. Based on the temperature difference between the supply and return water, the flow rate data and the pipeline characteristics of each user, the ideal flow distribution ratio under the hydraulic balance state is calculated through a series of hydraulic models, and this ratio is used as the reference basis for subsequent hydraulic balance adjustment.

[0013] Step S103: Generate a comprehensive system state evaluation index according to the user demand prediction model and the ideal flow distribution ratio of hydraulic balance; Specifically, the deviation rate is calculated between the actual flow rate of each user branch and the ideal flow rate calculated according to the ideal flow rate distribution ratio of hydraulic balance, so as to obtain the global hydraulic imbalance index, which reflects the difference between the actual flow rate and the ideal flow rate of each branch, and further provides a basis for valve opening adjustment. When this index deviates greatly, it indicates that there is an obvious deviation in hydraulic balance and adjustment is needed. Based on the data of the pressure sensors on the user side, the pressure distribution of the chilled water supply and return pipe network is analyzed to obtain the weight coefficient of the pipe network pressure distribution. This coefficient helps to determine which areas have a greater impact on hydraulic balance during the system adjustment process, so as to pay more attention when adjusting the valves and ensure the overall stability of the system during the adjustment process. Based on the pressure difference and flow rate of the supply and return water of each user branch, the flow resistance coefficient of each branch is calculated and compared with the average flow resistance coefficient of the entire pipe network to obtain the flow resistance anomaly coefficient, which reflects the deviation of the flow resistance of some user branches from the overall system, helps the system identify which branches have hydraulic imbalance or poor flow, and serves as the key area for subsequent adjustment. In order to improve the accuracy of cooling capacity distribution, the cooling capacity distribution deviation index is corrected and calculated by combining the load prediction data output by the user demand prediction model and the actual flow rate of each branch. The correction process combines the flow resistance anomaly coefficient to improve the accuracy of cooling capacity distribution, ensure that each user receives a reasonable cooling capacity distribution according to its actual demand, and avoid uneven heating and cooling or over-regulation in the system. While correcting the cooling capacity distribution deviation, the working effect of the buried pipe shell and tube heat exchanger is calibrated. By collecting the inlet and outlet temperature data of the buried pipe heat exchanger and combining the weight coefficient of the pipe network pressure distribution, the efficiency of the heat exchange process is evaluated to obtain the heat exchange efficiency of the buried pipe. The global hydraulic imbalance index, the cooling capacity distribution deviation index and the buried pipe heat exchange efficiency are weighted and combined to obtain a comprehensive system state evaluation index, which reflects the overall operation state of the system. Through the comprehensive evaluation of these indexes, it is judged whether the current operation state reaches the best, whether valve opening adjustment is needed, and the priority and strategy of the adjustment, so as to achieve precise hydraulic balance control and ensure the efficient and stable operation of the buried pipe cold storage system under various load conditions.

[0014] Step S104: Construct a global optimization objective function based on the comprehensive system state evaluation index, and solve to obtain the valve adjustment strategy for each time period; Specifically, the current regulation urgency is classified by comprehensively considering system status evaluation indicators. During the classification process, based on the numerical values of indicators such as the global hydraulic imbalance index, the cooling capacity distribution deviation index, and the ground heat exchanger heat transfer efficiency, the current operating state of the system is determined. If the global hydraulic imbalance index is high, it indicates uneven hydraulic distribution and the system is in a relatively urgent regulation state; if the cooling capacity distribution deviation index is large, it means there is a significant error in cooling capacity distribution and priority adjustment is required. Through this assessment, the priorities of different regulation states are given. According to the assessment result of the regulation priority level, a global optimization objective function is constructed. This objective function includes three main factors: the user load demand weight, the pressure difference balance degree, and the temperature uniformity. The user load demand weight reflects the differences in cooling load demands of different users, helping the system to prioritize meeting the users with larger loads; the pressure difference balance degree reflects the pressure distribution in the cold water pipe network, ensuring that the system will not cause excessive pressure in some areas or too low pressure during regulation, and guaranteeing the overall stability of the system; the temperature uniformity measures the temperature distribution of each user in the system, ensuring uniform distribution of the cooling load and avoiding discomfort for some users due to excessive temperature differences. By setting these weights, the objective function comprehensively considers the requirements of all aspects to achieve the global optimal hydraulic balance. Parameter configuration is performed on the global optimization objective function, adjusting the weights and solution parameters of different variables to obtain a set of solution parameter sets suitable for the current system state. According to the load prediction data output by the user demand prediction model, it is divided into time periods, and combined with the load change amplitude to generate the load period characteristic classification result. By analyzing the periodicity and volatility of the load changes, the load demands in different time periods are classified, providing time-periodized load information for the formulation of the valve regulation strategy. The load period characteristic classification result helps the system identify which time periods have large load changes and which time periods have relatively stable loads, so as to decide to provide a larger regulation margin during the time periods with large load changes and perform fine regulation during the time periods with small load changes. Based on the load period characteristic classification result, the constraint conditions for valve regulation are set. The constraint conditions include the regulation range, regulation speed, and regulation frequency of the valve, etc., ensuring that during the regulation process, the valve will not cause system instability due to excessive regulation. Combining the boundary constraint conditions with the objective function forms an optimization problem. After inputting the global optimization objective function, the solution parameter set, and the boundary constraint conditions for valve regulation into the solver, calculations are performed to obtain the time-periodized valve regulation strategy. This strategy will guide the system on how to adjust the valve opening in different time periods to ensure hydraulic balance and maximize the overall efficiency and energy-saving effect of the system.

[0015] Step S105: Construct a valve flow characteristic model based on the time-periodized valve regulation strategy and the valve historical response data, calculate the target opening of each regulating valve, and output a valve control execution instruction.

[0016] Specifically, the flow characteristics of each control valve are classified. Each type of valve has different flow characteristics, and the valve types include equal percentage characteristic valves, linear characteristic valves, quick opening characteristic valves, etc. The flow characteristics are classified according to the valve type, and the flow characteristic models of different types of valves are established. These models reflect the relationship between the valve opening and the flow rate, and each type of valve has its specific flow response law. Regression analysis is performed on the historical response data of the valves. By analyzing the deviation between the actual flow response and the theoretical flow response of each valve, the characteristic correction coefficient of the valve is calculated. Regression analysis can reveal the response relationship between the valve and the flow rate in the actual adjustment process, and calculate a correction coefficient, which can compensate for the error between the valve characteristic model and the actual operation, so that the flow characteristic model is more in line with the actual situation. According to the target flow distribution determined by the time-segmented valve adjustment strategy and the current pressure difference data, combined with the flow characteristic model of the valve, reverse calculation is performed to obtain the target opening of each control valve. The target flow distribution is obtained based on user demand prediction and system load analysis. Through reverse calculation, it is determined what opening each valve should be in to ensure that the flow rate reaches the expected target value. The target opening is compared with the current opening of the valve, and the difference between them is calculated. Threshold judgment is performed on the difference to ensure that the change in the valve opening will not be too drastic. If the difference between the target opening and the current opening exceeds the set threshold, appropriate adjustment is made to ensure the smooth adjustment process of the valve and avoid system instability caused by frequent adjustment. Through this judgment, the target opening value of the valve is determined and over-adjustment is avoided. According to the determined target opening value of the valve and the adjustment time window in the time-segmented valve adjustment strategy, a valve control execution instruction is generated, specifying the opening value to be adjusted, the adjustment rate, and the adjustment time period for each valve, ensuring that the valve can be adjusted according to the precise adjustment strategy to achieve the optimization of global hydraulic balance.

[0017] Prioritize the valve control execution instructions according to the urgency of hydraulic balance. The urgency of hydraulic balance is judged by calculating the global hydraulic imbalance index and the cooling capacity distribution deviation index. When these indexes are large, it indicates that the hydraulic balance state of the system is not ideal and adjustment is required immediately. On this basis, according to the adjustment priority of each valve and the sorting priority, determine the execution order of the adjustment instructions. Transmit the valve control execution instructions to the field controller through the Modbus protocol or the BACnet protocol. The field controller drives the electric actuator according to the instructions to adjust the valve opening, so as to achieve the required hydraulic balance adjustment. Compare and analyze the system state after the adjustment of each valve, and calculate the change rates of the hydraulic imbalance index, the cooling capacity distribution deviation index and the comprehensive system state evaluation index before and after the adjustment. By monitoring the changes of these indexes, quantify the adjustment effect and obtain the adjustment effect index. This index can reflect whether the adjustment action is effective. If the change rate of the index is large, it indicates that the adjustment effect is significant and the hydraulic balance of the system has been effectively improved; if the change rate is small, it indicates that the adjustment effect is not obvious and the control strategy needs to be further optimized. Collect data on the adjustment response characteristics of each valve. Reflect the dynamic response characteristics of the valve by recording the time delay and response gain required from issuing the control instruction to the flow stabilization. These data are modeled by a first-order lag model to reflect the lag phenomenon existing in the valve adjustment process. This model can help the system better predict the time characteristics of the valve response, ensure that the subsequent adjustment can take this delay effect into account, and thus improve the accuracy and response speed of the system adjustment. Based on the adjustment effect index and the first-order lag model, calculate the valve adaptive correction parameter set for adjusting the valve flow characteristics to compensate for the errors or lags generated during the adjustment process. Through adaptive correction, dynamically adjust the control strategy to ensure that the valve adjustment can always be in the best state under different operating conditions, and improve the accuracy of hydraulic balance and the stability of the system. Construct the valve adaptive correction parameter set, the system state during the hydraulic balance control process, the valve adjustment action and the environmental feedback into a state-action-reward sequence, and input it into the reinforcement learning algorithm for optimization analysis. The reinforcement learning algorithm optimizes the valve adjustment strategy under different environmental conditions through continuous learning and adjustment, and generates the valve opening control execution plan.

[0018] In the embodiments of the present application, a complete dynamic database of system parameters is constructed by setting multiple groups of sensors at the target nodes, providing a comprehensive and accurate data basis for hydraulic balance control; cold load fluctuation spectrum analysis and multi-scale decomposition techniques are adopted to accurately grasp the load characteristics, and users are classified according to the load stability index, and a differential prediction model is used to improve the load prediction accuracy; a comprehensive system state evaluation index is constructed to quantitatively characterize the degree of hydraulic imbalance, enabling the control to change from qualitative judgment to quantitative control; a global optimization function is constructed based on the idea of multi-objective optimization, and the optimal regulation strategy that takes into account both system efficiency and user comfort is obtained by solving through the genetic algorithm; an adaptive corrected flow characteristic model is established to overcome the deviation of the actual valve characteristics, and a smoothing processing algorithm is adopted to avoid equipment wear caused by frequent regulation; a reinforcement learning algorithm is introduced to form a closed-loop feedback adaptive control mechanism to continuously optimize the regulation strategy; the system reliability is improved by evaluating the valve health state, and the hydraulic balance strategy is dynamically adjusted according to different working conditions to achieve flexible coordination of hydraulic balance and cooling demand, meeting diverse operation requirements.

[0019] In a specific embodiment, the process of executing step S101 may specifically include the following steps: Install temperature sensors and pressure sensors on the branch pipelines on the cold user side of the ground-coupled energy storage cooling system to collect the cold water supply temperature and return water temperature, supply pressure and return pressure, and install electromagnetic flowmeters on each user branch to collect the user branch flow, obtaining a complete parameter data set on the cold user side; Install temperature sensors at the inlet and outlet of the ground-coupled energy storage tube-in-tube heat exchanger to collect the inlet temperature and outlet temperature, and install temperature sensors at the target parts of the precooled evaporative cooling chiller to collect the air temperatures before and after the direct evaporative cooling packing and the water temperature in the cold water tank, obtaining an operating parameter data set of the heat exchange system; Install pressure sensors and temperature sensors in the energy storage modular unit to collect the pressure and temperature of the refrigerant before and after the four-way reversing valve and the pressure and temperature at the outlet of the fluorine pump, and install electric control valves on the water supply main pipes of each cold user, obtaining an operating parameter data set of the core components of the system; Perform data standardization processing on the complete parameter data set on the cold user side, the operating parameter data set of the heat exchange system, and the operating parameter data set of the core components of the system to obtain dynamic system parameter data.

[0020] Specifically, temperature sensors and pressure sensors are installed on the branch pipelines on the cold user side to collect the cold water supply temperature, return water temperature, supply pressure, and return pressure. The temperature sensors reflect the change trend of the cooling load by monitoring the temperature changes of the supply water and return water in real time, helping the system understand the cooling load requirements of each cold user; the pressure sensors help analyze the operation status of the pipe network and identify existing hydraulic imbalance problems by collecting the pressure data of the supply and return water pipelines. On each cold user branch, an electromagnetic flowmeter is installed to collect the flow data of each user branch in real time. The cooling capacity of each user is obtained through the flow data measured by the flowmeter to ensure the reasonable distribution of the cooling capacity. The data collected by these sensors and flowmeters form the parameter dataset on the cold user side. To monitor the operation status of the heat exchange system, temperature sensors are installed at the inlet and outlet of the buried pipe shell-and-tube heat exchanger to collect the inlet temperature and outlet temperature of the heat exchanger. These temperature data can reflect the working efficiency and performance of the heat exchanger. If the temperature difference of the heat exchanger is large, it means that the heat exchange efficiency is high, while a small temperature difference means that the heat exchange effect is not ideal and further optimization is required. At the key parts of the pre-cooled evaporative cooling chiller, temperature sensors are installed to collect the air temperature before and after the direct evaporative cooling filler and the water temperature in the cold water tank. By monitoring these temperature data, the cooling effect and the efficiency of the heat exchange process are understood to ensure that the chiller can maintain an efficient operation status and avoid adverse effects on the system caused by too high or too low temperatures. All the data collection results from the heat exchange system form the operation parameter dataset of the heat exchange system. Pressure sensors and temperature sensors are installed inside the cold storage modular unit to collect the pressure and temperature data of the refrigerant before and after the four-way reversing valve. By analyzing these data, the flow state and working state of the refrigerant in the cold storage module are understood, and the overall operation efficiency of the refrigeration system is judged. At the same time, the pressure and temperature at the outlet of the fluorine pump are collected. The fluorine pump is an important part of the system, and the performance of the pump is directly related to the refrigeration effect and energy efficiency of the system. On the main supply pipe of each cold user, an electric control valve is installed to accurately adjust the cold water flow. By monitoring these core components, the operation status of the cold storage system is grasped, and faults or performance degradation that occur are detected in a timely manner. The monitoring data from the cold storage module and the system core components form the operation parameter dataset of the system core components. The complete parameter dataset on the cold user side, the operation parameter dataset of the heat exchange system, and the operation parameter dataset of the system core components are subjected to data standardization processing to convert data from different sources and in different formats into a data set with a unified unit and format, ensuring that all data can be analyzed and calculated on the same platform. The standardized data forms a dynamic system parameter dataset, including the temperature, pressure, and flow data on the cold user side, the temperature data of the heat exchange system, and the pressure and temperature data of the cold storage module and the system core components.

[0021] In a specific embodiment, the process of executing step S102 may specifically include the following steps: Calculate the temperature difference between supply and return water and the flow rate of each user branch in the dynamic system parameter data to obtain the real-time cooling load, and construct a three-dimensional matrix for the real-time cooling load according to the user identification and time dimension to obtain the cooling load distribution matrix; Perform Fourier transform on the cooling load time series data in the cooling load distribution matrix to obtain the periodic characteristics of load fluctuations, and perform multi-scale decomposition on the periodic characteristics of load fluctuations through wavelet transform to obtain the basic load type, periodic load type, and random load type; Calculate the historical load mean and standard deviation of each user branch according to the basic load type, periodic load type, and random load type to obtain the load stability index, and classify users into high stability, medium stability, and low stability according to the load stability index; For high-stability users, use a linear regression model, for medium-stability users, use a seasonal ARIMA model, and for low-stability users, use a long short-term memory network model. Taking the load data at the current time t and the historical data of the previous n time windows as inputs, obtain the user demand prediction model; Based on the temperature difference between supply and return water, flow rate data, and pipeline characteristics of each user, calculate the ideal flow distribution ratio under the hydraulic balance state to obtain the ideal flow distribution ratio of hydraulic balance.

[0022] Specifically, the supply-return water temperature difference and flow rate of each user branch in the system are calculated in real time to obtain the real-time cooling load of the branch, reflecting the cooling demand of each branch and providing data support for subsequent load distribution and hydraulic balance adjustment. A three-dimensional matrix is constructed for the cooling load data according to the user identification and time dimension, forming a cooling load distribution matrix. The three-dimensional structure of the matrix consists of user identification, time dimension, and cooling load value, showing the cooling load changes on different user branches at different time periods. Through this matrix, the cooling load fluctuations of each user branch can be effectively analyzed, and the cooling load distribution of the system can be optimized more precisely. After the construction of the cooling load distribution matrix is completed, Fourier transform is performed on the cooling load time series data therein to extract the periodic characteristics of the load fluctuations. Fourier transform converts the cooling load time series from the time domain to the frequency domain, thus revealing the frequency components of the cooling load fluctuations. This analysis helps to identify the regular characteristics of the load fluctuations, such as the periodicity of the peaks and valleys of the cooling load, and provides a reference basis for system adjustment. The periodic characteristics obtained through Fourier transform help the system identify which time periods have larger cooling load fluctuations and which have smaller fluctuations, so as to adjust the valve opening and flow distribution strategies according to the actual load fluctuations. Wavelet transform is used to perform multi-scale decomposition on the periodic characteristics of the load fluctuations. Wavelet transform is a method that can analyze signals at different scales and extract different levels of information from the load data. By performing wavelet transform on the cooling load fluctuations, three components of the load fluctuations are decomposed: the base load, the periodic load, and the random load. The base load represents the stable load demand of the system during long-term operation, the periodic load represents the load fluctuations caused by seasonal changes or other periodic factors, and the random load represents the load fluctuations caused by unpredictable factors (such as equipment failures or sudden demands). According to the base load, periodic load, and random load types obtained from the multi-scale decomposition, the historical load mean and standard deviation of each user branch are calculated to obtain the load stability index. The load mean reflects the average level of the cooling load demand of the user, while the standard deviation reflects the fluctuation range of the cooling load demand. By calculating the load stability index of each user branch, the load stability of the user is determined, and then the users are divided into three categories: high-stability users, medium-stability users, and low-stability users. High-stability users have smaller load fluctuations and relatively stable load demands, while low-stability users have larger load fluctuations and unstable demands. According to the load stability of the users, different prediction models are adopted to more accurately predict the cooling load demand of the users. Different load prediction models are selected for users with different stabilities. For high-stability users, a linear regression model is used for prediction. The linear regression model is suitable for users with relatively stable load changes and obvious trends, and this model can better capture the linear change trend of the load demand over time. For medium-stability users, a seasonal ARIMA (Autoregressive Integrated Moving Average) model is used.The seasonal ARIMA model can handle time series data with seasonal fluctuations and is suitable for users whose load demands have regular fluctuations within certain periods. For users with low stability, the long short-term memory network (LSTM) model is used for prediction. The LSTM model can capture complex patterns in non-linear, long time series and is applicable to users with complex and difficult-to-predict load changes. Through these different prediction models, more accurate demand predictions are provided according to the load stability characteristics of each user. Based on the supply and return water temperature difference, flow rate data, and pipeline characteristics of each user, the ideal flow rate distribution ratio under the hydraulic balance state is calculated. Hydraulic balance means that the flow rates of each branch in the system can achieve the stable operation of the pipe network while meeting the load demands of each user. By calculating the supply and return water temperature difference, flow rate, and pipeline characteristics of each branch, the ideal flow rate distribution ratio, that is, the flow rate share that each user should obtain, is determined.

[0023] In a specific embodiment, the process of executing step S103 may specifically include the following steps: Calculate the deviation rate between the actual flow rate of each user branch and the ideal flow rate calculated according to the ideal flow rate distribution ratio of hydraulic balance to obtain the global hydraulic imbalance index; Analyze the pressure distribution of the chilled water supply and return pipe network based on the data of the user-side pressure sensors to obtain the pressure distribution weight coefficient of the pipe network; Based on the supply and return water pressure difference and flow rate of each user branch, calculate the flow resistance coefficient of each user branch and compare it with the average flow resistance coefficient of the pipe network to obtain the flow resistance anomaly coefficient; According to the load prediction data output by the user demand prediction model and the actual flow rate of each branch, combined with the flow resistance anomaly coefficient, perform correction calculations to obtain the cooling capacity distribution deviation index; Based on the collected data of the inlet temperature and outlet temperature of the buried pipe shell-and-tube heat exchanger, combined with the pressure distribution weight coefficient of the pipe network, correct the heat exchange process to obtain the buried pipe heat exchange efficiency; Perform weighted combination on the global hydraulic imbalance index, the cooling capacity distribution deviation index, and the buried pipe heat exchange efficiency to obtain the comprehensive system state evaluation index.

[0024] Specifically, analyze the actual operating conditions of each user branch. During the operation of the system, chilled water continuously circulates in the user-side pipe network, and the actual flow rate of each branch deviates due to changes in cooling demand or differences in pipe network structure. Compare the actual flow rate of each user branch with the ideal flow rate calculated according to the principle of hydraulic balance, and measure the current hydraulic balance status of the system through the degree of deviation between the two. After summarizing the deviation data of all branches, an index representing the overall hydraulic imbalance degree of the system is formed. The larger this index, the more the water flow distribution of the system deviates from the ideal state, and the more serious the hydraulic balance problem; on the contrary, it indicates that the system operation is closer to the design condition. Use the pressure sensor data arranged on the user side to analyze the pressure distribution of the water supply pipe and the return water pipe. Through a series of spatial distribution calculations, construct a pressure gradient map to reveal which areas have uneven pressure, abnormal flow velocity changes or sudden changes in local resistance. Quantify the analysis results of the pressure distribution into a weight coefficient, which is used in subsequent comprehensive judgments to represent the pressure sensitivity of different users' locations, that is, if a certain branch is located in a region with a steep pressure gradient, the hydraulic disturbance it bears will be more intense, and this situation needs to be given priority consideration during adjustment. At the same time, by analyzing the pressure difference between the water supply and return water of each branch and the corresponding flow rate, calculate the strength of the flow resistance of each branch, reflecting the internal characteristics of the pipeline, such as the degree of inhibition of factors such as length, diameter, and local elbow loss on the water flow. Then compare these branch resistance values with the average level of the whole system to determine which branches are in a high-resistance abnormal state. These abnormal branches have problems such as blockage, scaling or unreasonable pipeline design, thus becoming the key influencing factors for the hydraulic imbalance of the whole system. Combine the user's load prediction results and the actual flow rate of each branch to conduct chilled water matching analysis. Correct the flow rate of each branch to make it closer to the water volume corresponding to the actual load demand. After the correction process, calculate the overall chilled water distribution rationality index to reflect whether there are problems such as excessive concentration of chilled water or insufficient chilled water supply in the system. At the same time, evaluate the heat exchange efficiency. Through long-term monitoring of the inlet and outlet temperatures of the buried pipe shell-and-tube heat exchanger, analyze whether its heat exchange performance is at the design level. Since pressure also affects the heat exchange efficiency, especially when the flow rate of the heat exchanger fluctuates violently, combine the pressure distribution weight coefficient obtained above to correct the performance index of the heat exchanger to obtain a more accurate heat exchange efficiency evaluation result. If the heat exchange efficiency is low, it means that there are problems such as energy waste or fouling deposition on the surface of the heat exchanger. Weightedly combine the global hydraulic imbalance index, the chilled water distribution deviation index and the buried pipe heat exchange efficiency. By setting weights for each index, combine them into a comprehensive evaluation index reflecting the overall operating state. According to the value of the comprehensive evaluation index, judge whether the current operating state is in a stable, slightly unbalanced or severely unbalanced state, and select different levels of valve adjustment strategies accordingly.

[0025] In a specific embodiment, the process of executing step S104 may specifically include the following steps: Classify the adjustment urgency according to the comprehensive system status evaluation index to obtain the adjustment priority rating result; Based on the adjustment priority rating result, construct a global optimization objective function including the user load demand weight, pressure difference balance degree, and temperature uniformity; Configure the solution parameters for the global optimization objective function to obtain a set of solution parameters; Divide the load prediction data output according to the user demand prediction model by time period and generate a load period characteristic classification result in combination with the load change amplitude; Set the valve adjustment constraint conditions based on the load period characteristic classification result to obtain the boundary constraint conditions for valve adjustment; Input the global optimization objective function, the set of solution parameters, and the boundary constraint conditions for valve adjustment into a solver for calculation to obtain a time-segmented valve adjustment strategy.

[0026] Specifically, the hydraulic balance status is quantitatively judged according to the index value obtained by the evaluation. This index has combined multiple key factors such as hydraulic imbalance, cooling capacity distribution error and heat exchange efficiency, and has the ability to fully reflect the urgency of system regulation needs. A series of grading standards are set according to the numerical range of this index. For example, when the index is high, it means that the system deviates far from the designed operating state, which is an emergency state of regulation; when the index value is medium or low, it corresponds to moderate and mild imbalance states respectively. According to the grading rules, the classification of the regulation urgency is output, and the regulation priority assessment results are generated accordingly. Based on the regulation priority assessment results, a global optimization objective function including user load demand weight, pressure difference balance and temperature uniformity is constructed. The user load demand weight reflects the importance of the cooling load of different users at the current moment or in the future cycle. For example, for users in high load periods or with severe load fluctuations, their corresponding weights will be relatively increased to ensure that they are given priority in the regulation plan. As an important dimension to measure the rationality of the hydraulic transmission path, the pressure difference balance aims to make the supply and return water pressure difference between each branch consistent through optimization and regulation, thereby improving the system stability and response speed. The goal of temperature uniformity is to ensure that the water supply temperature difference of each user end in the system is small, so as to avoid the phenomenon of uneven cold and hot, and improve the terminal comfort and energy efficiency utilization. Taking the above factors into consideration, a global optimization objective function covering the rationality of heat distribution, the balance of hydraulic paths and the coordination of thermal response is constructed. According to the control requirements under different priorities, the solution parameters of the objective function are configured. The solution parameter configuration process includes the adjustment rate coefficient, the optimization accuracy requirement, the iteration range setting, the constraint processing method, etc., which provides a set of technical parameters that can adapt to the current system state for the operation of the solver. For example, in the state of higher adjustment priority, the system tends to accelerate the convergence speed and adopt a larger adjustment range in order to quickly reduce the system deviation; while in the state of lower priority, it pays more attention to the smooth operation of the system and the minimization of energy consumption, and the parameter setting will tend to fine-grained adjustment and high-precision solution. These solution parameters are combined into a parameter set and input into the solution module together with the objective function structure. At the same time, in order to improve the dynamic adaptability of the control strategy, the data output by the user demand prediction model is combined to identify the change trend of the cooling load in the future time period. The forecast data is divided according to the time dimension, divided into multiple time periods, and the amplitude and fluctuation frequency of the load changes in each time period are calculated. Based on this analysis, different time periods are divided into high-load variation period, medium-load variation period and stable load period to form the load period characteristic classification results. The classification results will serve as the time basis for determining the system regulation intensity, frequency and valve response priority. Periods with large load fluctuations will be given a larger adjustment space, allowing the valve to have a wider adjustment range and a shorter adjustment interval; while periods with relatively stable loads will give priority to maintaining system stability, appropriately compressing the adjustment range and reducing system disturbances.After obtaining the classification results of the time period characteristics, the boundary constraint conditions for valve regulation are set accordingly. These constraint conditions include the maximum allowable opening change range for each valve regulation, the minimum time interval between two regulations, the minimum water supply flow rate lower limit for each branch, and the flow safety threshold agreed upon according to the characteristics of the pipe network, etc. These boundary constraints play a role in protecting on-site equipment and preventing over-regulation of the system, and ensure the continuity of the regulation process and the execution stability. For example, during the low-load stable period, even if the objective function suggests adjusting certain valves to improve energy efficiency, the system determines whether the adjustment is necessary based on the boundary conditions, thus avoiding mechanical wear and increased energy consumption caused by frequent fine-tuning. The globally optimized objective function that has been constructed, the set of solution parameters, and the boundary constraint conditions for valve regulation corresponding to the load characteristic classification results are input into the solver for unified calculation. The solver uses iterative algorithms (such as genetic algorithms, particle swarm algorithms, or adaptive variable-step gradient descent, etc.) to find the solution that minimizes the optimized objective function under the premise of satisfying the constraint conditions, and generates a set of optimal time-based valve regulation strategies. This strategy specifically defines the target opening, regulation rate, and execution timing of each regulating valve within each time period, and continuously adjusts the optimization direction according to the real-time feedback mechanism to adapt to the non-linear interference and load fluctuations in actual operation, so as to ensure that the entire system can maintain the optimal hydraulic distribution state under various operating conditions.

[0027] In a specific embodiment, the process of executing step S105 may specifically include the following steps: Classify the flow characteristics of each regulating valve according to the valve type to obtain the valve flow characteristic model; Conduct a regression analysis on the historical response data of the valve, calculate the deviation between the actual flow response and the theoretical flow response of each valve, and obtain the valve characteristic correction coefficient; Based on the target flow distribution determined by the time-based valve regulation strategy and the current pressure difference data, perform reverse calculation in combination with the valve flow characteristic model to obtain the target opening of each regulating valve; Judge the difference between the target opening and the current opening by a threshold to obtain the valve target opening value; Generate a valve control execution instruction according to the valve target opening value and the regulation time window in the time-based valve regulation strategy.

[0028] Specifically, classify the flow characteristics of each control valve and establish a valve flow characteristic model. Different types of valves have different flow characteristics, such as equal percentage characteristic valves, linear characteristic valves, and quick opening characteristic valves. These different types of valves will exhibit different response characteristics in flow control and are classified according to the valve structure and working principle. The valve flow characteristic model is a mathematical model that describes the relationship between the valve opening and the flow rate, helping the system understand the flow rate range that the valve can regulate at a given opening. Through this classification, a corresponding flow regulation model is designed for each type of valve. Conduct a regression analysis on the historical response data of the valves. Through the actual operation data, evaluate the deviation between the actual flow response and the theoretical flow response of each valve. In actual operation, the valve is affected by various factors, such as valve aging, pipeline pressure changes, fluid characteristics, etc. These factors will cause an error between the flow response of the valve and the theoretical model. Through regression analysis, quantify this deviation and calculate the characteristic correction coefficient for each valve. The correction coefficient is an important parameter for adjusting the theoretical flow model according to the actual situation, ensuring the accuracy of flow regulation and compensating for the difference between the theoretical model and the actual operation. The introduction of the correction coefficient makes the control strategy of each valve more in line with the actual operating conditions, thereby improving the regulation effect and operating efficiency of the entire system. According to the target flow distribution determined by the time-segmented valve regulation strategy and the current pressure difference data, perform a reverse calculation in combination with the valve flow characteristic model to determine the target opening of each valve. The target flow distribution is the flow rate required for each user branch obtained by the system based on load prediction and hydraulic balance analysis, and the current pipeline pressure difference reflects the hydraulic state of the system at different time periods. Combining these two data, perform a reverse calculation according to the valve flow characteristic model, that is, deduce the required valve opening from the target flow rate and the pipeline pressure difference. This reverse calculation process is carried out based on the hydraulic balance requirements of the system to ensure that the opening adjustment of each valve can meet the cold load demand and hydraulic balance conditions, thereby achieving global optimal control. Perform a threshold judgment on the difference between the target opening and the current opening. Set a threshold to ensure that when the difference between the target opening and the current opening is small, the valve is not adjusted or only slightly adjusted. Through the threshold judgment, meaningless fine-tuning and over-regulation are avoided. If the difference between the target opening and the current opening exceeds the set threshold, the system issues a regulation instruction to make appropriate adjustments to gradually adjust the valve opening to the target value. Based on the calculated valve target opening value and the adjustment time window in the time-segmented valve regulation strategy, generate valve control execution instructions. These instructions include the valve target opening value, as well as the specific time and adjustment rate of the regulation. The setting of the adjustment time window takes into account the change in the user's load demand and the hydraulic balance of the system, ensuring that the adjustment process of the valve is not too hasty or delayed and can complete the necessary adjustments within a suitable time period.By controlling the execution instructions, the field controller accurately drives the electric actuator to adjust the valve opening, ensuring that the cooling load requirements of each user are met and the hydraulic balance of the entire system is optimized.

[0029] In a specific embodiment, the method for controlling the valve opening for the hydraulic balance at the user end further includes the following steps: Sort the priorities of the valve control execution instructions according to the urgency of the hydraulic balance, and transmit the valve control execution instructions to the field controller through the Modbus protocol or the BACnet protocol to drive the electric actuator to adjust the valve opening; Compare and analyze the system states after each valve control execution instruction is completed, calculate the change rates of the hydraulic imbalance index, the cooling capacity distribution deviation index, and the comprehensive system state evaluation index before and after adjustment, and obtain the adjustment effect index; Collect data on the adjustment response characteristics of each valve, record the time delay and response gain required from the issuance of the instruction to the flow stabilization, and construct a first-order lag model; Calculate the valve adaptive correction parameter set according to the adjustment effect index and the first-order lag model; Construct the state-action-reward sequence with the valve adaptive correction parameter set, the system state, the valve adjustment actions, and the environmental feedback during the hydraulic balance control process, and input it into the reinforcement learning algorithm for optimization analysis to generate the valve opening control execution plan.

[0030] Specifically, the valve control execution instructions are prioritized according to the urgency of hydraulic balance. The urgency of hydraulic balance is determined by the global hydraulic imbalance index, the cooling capacity distribution deviation index, and other key performance indicators. When the values of these indicators are high, it indicates that there is a large hydraulic imbalance or cooling capacity distribution deviation in the system, and the system preferentially adjusts the relevant valves to restore balance. Therefore, first evaluate the current hydraulic balance status of the areas controlled by each valve, and determine the adjustment priority of each valve according to the evaluation results. For example, user branches located in the hydraulic imbalance area or with cooling capacity distribution deviation will be given a higher priority to ensure that the adjustment can act on these areas first. The valve with a higher adjustment priority will have its control instructions processed first during the adjustment execution, ensuring that the system responds quickly and restores hydraulic balance. After determining the adjustment priority, the valve control execution instructions are transmitted to the field controller through the Modbus protocol or the BACnet protocol. The Modbus protocol and the BACnet protocol can perform efficient and reliable data transmission between different devices. After receiving the instructions, the field controller precisely adjusts the valve opening by controlling the electric actuator. This process is the core of automatic control, ensuring that the system can respond in real time according to the adjustment instructions and adjust the valve opening according to different hydraulic balance requirements, thereby affecting the distribution of flow and pressure and ensuring the reasonable distribution of cooling capacity. After the adjustment execution is completed, a comparative analysis is carried out on the system state after the control execution instructions of each valve are completed. Calculate the change rates of the hydraulic imbalance index, the cooling capacity distribution deviation index, and the comprehensive system state evaluation index before and after the adjustment. These change rates can reflect the actual impact of valve adjustment on the system operation state. If the change rates of the hydraulic imbalance index and the cooling capacity distribution deviation index are large, it indicates that the valve adjustment effectively improves the hydraulic balance and cooling capacity distribution of the system; if the change rates are small, it indicates that the adjustment effect is not obvious and further adjustment or optimization of the control strategy is required. The adjustment effect index is a comprehensive index that can reflect the actual effect of valve adjustment and guide the optimization of subsequent adjustment schemes. Data collection is carried out on the adjustment response characteristics of each valve. Record the time delay and response gain required from the issuance of the adjustment instruction to the flow stabilization. The time delay and response gain are important indicators to measure the valve response speed and adjustment accuracy, revealing problems such as hysteresis or uneven response during the valve adjustment process. By collecting these data, a first-order lag model of the valve is constructed. This model is used to describe the dynamic characteristics during the valve adjustment process, especially the changes in time delay and response gain. Establishing a first-order lag model can help the system understand the adjustment efficiency of the valve and the valve's response ability to flow changes, thereby providing a parameter basis for future adjustment strategies. According to the adjustment effect index and the first-order lag model, calculate the adaptive correction parameter set of the valve. The adaptive correction parameter set of the valve aims to compensate for the errors that occur during the adjustment process, especially when the valve response is slow or there is a large lag.The adaptive correction parameter set is adjusted according to historical data and real-time feedback to optimize the accuracy and responsiveness of the valve adjustment strategy. By continuously adjusting and optimizing these correction parameters, it is ensured that the valve responds more precisely in future adjustments and can adapt to environmental changes and load fluctuations. Information such as the valve adaptive correction parameter set, the current system state, valve adjustment actions, and environmental feedback is constructed into a state-action-reward sequence and input into a reinforcement learning algorithm for optimization analysis. Reinforcement learning is a machine learning method that optimizes the decision-making process by interacting with the environment. In this process, the current system state is regarded as the "state", the adjustment action of each valve as the "action", and the effect after adjustment as the "reward". Through the training of the reinforcement learning algorithm, the system can continuously optimize the valve opening control strategy, making each adjustment action bring the optimal system performance. The reinforcement learning algorithm automatically selects the most suitable valve adjustment scheme under different hydraulic imbalance states through multiple iterations and feedback adjustments, thus achieving the optimal control of the system.

[0031] Among them, the valve adaptive correction parameter set, the system state, valve adjustment actions, and environmental feedback in the hydraulic balance control process are constructed into a state-action-reward sequence and input into a reinforcement learning algorithm for optimization analysis to generate a valve opening control execution plan, including: extracting and normalizing the system key parameters such as the hydraulic imbalance index, cooling capacity distribution deviation index, ground heat exchanger heat transfer efficiency, user load demand, and valve response characteristics to obtain a state vector representing the current state of the system; discretizing the adjustable opening range of all valves, dividing the adjustment amplitude of each valve into three basic operations: increasing, decreasing, and maintaining, and constructing a multi-dimensional action space in combination with the adjustment step size to obtain the action set of valve adjustment; designing a multi-objective reward function based on three objectives of hydraulic balance degree, user comfort, and system energy efficiency, and conducting positive and negative incentive evaluations on the system state changes after valve adjustment to obtain a reward signal representing the quality of the adjustment effect; associating and organizing the state vector, action set, and reward signal in the historical adjustment process according to the time series to form a state-action-reward triple sequence, obtaining the training data set for reinforcement learning; inputting the training data set into a deep Q network for model training, using the experience replay mechanism and the target network separation technology to reduce sample correlation, and balancing exploration and exploitation by gradually reducing the exploration rate to obtain an optimized valve adjustment strategy network; analyzing and evaluating the current system state based on the optimized valve adjustment strategy network, generating an optimal valve adjustment action sequence and converting it into a standard control instruction format to obtain a valve opening control execution plan with adaptive learning ability.

[0032] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, systems, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0033] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a valve opening control device for client-side hydraulic balance (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0034] As mentioned above, the above embodiments are only used to illustrate the technical solution of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of various embodiments of the present invention.

Claims

1. A method for controlling the valve opening for household end hydraulic balance, characterized in that, Including: Collecting parameter data of the buried pipe cold storage system to obtain dynamic system parameter data; Performing cold load fluctuation spectrum analysis and multi-scale decomposition based on the dynamic system parameter data to obtain a user demand prediction model and an ideal flow distribution ratio for hydraulic balance; Generating a comprehensive system status evaluation index according to the user demand prediction model and the ideal flow distribution ratio for hydraulic balance; Constructing a global optimization objective function based on the comprehensive system status evaluation index and solving to obtain a time-segmented valve regulation strategy; Constructing a valve flow characteristic model according to the time-segmented valve regulation strategy and valve historical response data, calculating the target opening degree of each regulating valve, and outputting a valve control execution instruction.

2. The valve opening control method for client-side hydraulic balance according to claim 1, wherein The collecting parameter data of the buried pipe cold storage system to obtain dynamic system parameter data includes: Installing temperature sensors and pressure sensors on the branch pipelines on the cold user side of the buried pipe cold storage system to collect the cold water supply temperature and return water temperature, supply pressure and return pressure, installing electromagnetic flowmeters on each user branch to collect the user branch flow, and obtaining a complete parameter data set on the cold user side; Installing temperature sensors at the inlet and outlet of the buried pipe shell-and-tube heat exchanger to collect the inlet temperature and outlet temperature, installing temperature sensors at the target parts of the precooling evaporative cooling chiller to collect the air temperatures before and after the direct evaporative cooling packing and the water temperature in the cold water tank, and obtaining an operation parameter data set of the heat exchange system; Installing pressure sensors and temperature sensors in the cold storage modular unit to collect the pressures and temperatures of the refrigerant before and after the four-way reversing valve and the pressure and temperature at the outlet of the fluorine pump, installing electric regulating valves on the water supply main pipes of each cold user, and obtaining an operation parameter data set of the core components of the system; Performing data standardization processing on the complete parameter data set on the cold user side, the operation parameter data set of the heat exchange system, and the operation parameter data set of the core components of the system to obtain dynamic system parameter data.

3. The valve opening control method for client-side hydraulic balance according to claim 1, characterized in that The performing cold load fluctuation spectrum analysis and multi-scale decomposition based on the dynamic system parameter data to obtain a user demand prediction model and an ideal flow distribution ratio for hydraulic balance includes: Calculating the temperature difference and flow rate between the supply and return water of each user branch in the dynamic system parameter data to obtain the real-time cold load, and constructing a three-dimensional matrix based on the user identification and time dimension for the real-time cold load to obtain a cold load distribution matrix; Performing Fourier transform on the cold load time series data in the cold load distribution matrix to obtain the periodic characteristics of the load fluctuation, and performing multi-scale decomposition on the periodic characteristics of the load fluctuation through wavelet transform to obtain the basic load type, periodic load type, and random load type; Calculating the historical load mean and standard deviation of each user branch according to the basic load type, the periodic load type, and the random load type to obtain a load stability index, and classifying users into high stability, medium stability, and low stability according to the load stability index; For high-stability users, a linear regression model is adopted; for medium-stability users, a seasonal ARIMA model is adopted; and for low-stability users, a long short-term memory network model is adopted. Using the load data at the current moment t and the historical data of the previous n time windows as inputs, a user demand prediction model is obtained. Based on the supply and return water temperature difference, flow rate data of each user, and pipeline characteristics, the ideal flow rate distribution ratio under the hydraulic balance state is calculated to obtain the ideal flow rate distribution ratio for hydraulic balance.

4. The valve opening control method for client-side hydraulic balance according to claim 1, wherein The comprehensive system state evaluation index is generated according to the user demand prediction model and the ideal flow rate distribution ratio for hydraulic balance, including: Calculate the deviation rate between the actual flow rate of each user branch and the ideal flow rate calculated according to the ideal flow rate distribution ratio for hydraulic balance to obtain the global hydraulic imbalance index. Analyze the pressure distribution of the chilled water supply and return pipe network based on the data of the pressure sensors on the user side to obtain the pressure distribution weight coefficient of the pipe network. Based on the supply and return water pressure difference and flow rate of each user branch, calculate the flow resistance coefficient of each user branch and compare it with the average flow resistance coefficient of the pipe network to obtain the flow resistance anomaly coefficient. According to the load prediction data output by the user demand prediction model and the actual flow rate of each branch, combined with the flow resistance anomaly coefficient, perform correction calculations to obtain the cooling capacity distribution deviation index. Based on the collected data of the inlet temperature and outlet temperature of the buried tube shell-and-tube heat exchanger, combined with the pressure distribution weight coefficient of the pipe network, correct the heat transfer process to obtain the heat transfer efficiency of the buried tube. Perform weighted combination on the global hydraulic imbalance index, the cooling capacity distribution deviation index, and the heat transfer efficiency of the buried tube to obtain the comprehensive system state evaluation index.

5. The valve opening control method for client-side hydraulic balance according to claim 1, characterized in that Based on the comprehensive system state evaluation index, construct a global optimization objective function and solve it to obtain the valve regulation strategy for each time period, including: Classify the adjustment urgency according to the comprehensive system state evaluation index to obtain the evaluation result of the adjustment priority level. Based on the evaluation result of the adjustment priority level, construct a global optimization objective function including the user load demand weight, pressure difference balance degree, and temperature uniformity. Configure the solution parameters for the global optimization objective function to obtain the solution parameter set. Divide the load prediction data output by the user demand prediction model according to time periods and combine the load change amplitude to generate the load period characteristic classification result. Based on the load period characteristic classification result, set the valve regulation constraint conditions to obtain the boundary constraint conditions for valve regulation. Input the global optimization objective function, the solution parameter set, and the boundary constraint conditions for valve regulation into the solver for calculation to obtain the valve regulation strategy for each time period.

6. The valve opening control method for client-side hydraulic balance according to claim 1, characterized in that According to the valve regulation strategy for each time period and the valve historical response data, construct a valve flow characteristic model, calculate the target opening degree of each regulating valve, and output the valve control execution instruction, including: Classify the flow characteristics of each regulating valve according to the valve type to obtain the valve flow characteristic model. Perform regression analysis on the valve historical response data, calculate the deviation between the actual flow rate response and the theoretical flow rate response of each valve to obtain the valve characteristic correction coefficient. Based on the target flow rate distribution and the current pressure difference data determined by the time - segmented valve regulation strategy, and combined with the valve flow characteristic model, perform reverse calculation to obtain the target opening degrees of each regulating valve; Perform threshold judgment on the difference between the target opening degree and the current opening degree to obtain the valve target opening degree value; Generate a valve control execution instruction according to the valve target opening degree value and the regulation time window in the time - segmented valve regulation strategy.

7. The valve opening control method for client-side hydraulic balance according to claim 1, characterized in that The valve opening degree control method for household - side hydraulic balance further includes: Rank the priorities of the valve control execution instructions according to the urgency of hydraulic balance, and transmit the valve control execution instructions to the field controller through the Modbus protocol or the BACnet protocol to drive the electric actuator to adjust the valve opening degree; Conduct comparative analysis on the system states after each valve control execution instruction is completed, calculate the change rates of the hydraulic imbalance index, the cooling capacity distribution deviation index, and the comprehensive system state evaluation index before and after regulation to obtain the regulation effect index; Collect data on the adjustment response characteristics of each valve, record the time delay and response gain required from issuing the instruction to the flow rate stabilizing, and construct a first - order lag model; Calculate the valve adaptive correction parameter set according to the regulation effect index and the first - order lag model; Construct the state - action - reward sequence with the valve adaptive correction parameter set, the system state, valve adjustment actions, and environmental feedback during the hydraulic balance control process, and input it into the reinforcement learning algorithm for optimization analysis to generate a valve opening degree control execution plan.

Images