Heat supply network heat supply system control method based on prediction model

Abstract

The invention relates to the technical field of data processing, and discloses a heat supply network heat supply system control method based on a prediction model, and the method comprises the steps: S1, collecting historical operation data and real-time operation data of a heat supply network heat supply system, S2, carrying out the preprocessing of the historical operation data and the real-time operation data, and generating a standardized heat supply data set; by constructing a prediction model based on historical data and real-time data, the thermal load demand change in a future time period can be dynamically predicted, the problem of adjustment lag caused by dependence on a static model in a traditional control method is solved, the response ability of a heat supply system to extreme weather and user demand sudden change is improved, and the heat supply efficiency is improved. The stability and reliability of heat supply quality are guaranteed, the time hysteresis between a regulation and control instruction and the actual heat supply effect is reduced by analyzing the heat transmission characteristic and the delay effect of each node of the pipe network in real time, the phenomena of insufficient heat supply and energy waste caused by untimely regulation of the system are avoided, and the energy consumption is reduced. And the operation efficiency and the energy utilization rate of the heat supply system are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a heat supply network system control method based on a prediction model. BACKGROUND

[0002] The heat supply network is the main component of the central heating system, and is responsible for heat energy transportation. The system form of the heat supply network depends on the mutual position of the heat medium, heat source and heat user, the types of heat users in the heating area, the size and nature of the heat load, and the like. The principles to be followed in selecting the system form of the heat supply network are safe heating and economy.

[0003] At present, in the operation control process of the heat supply network system, due to the complex dynamic heat transfer characteristics of the heat supply pipe network and the randomness of the user heat demand, the traditional control method mainly relies on historical experience data and static models for heating adjustment, and cannot accurately predict the future heat load demand changes in real time according to the industrial big data of the heat supply network system influencing factors, especially in the face of extreme weather changes and user heat behavior mutations, the existing control method is difficult to respond in time, resulting in the problems of insufficient heating and energy waste of the heat supply system.

[0004] Therefore, the present application provides a heat supply network system control method based on a prediction model to solve the above problems. SUMMARY

[0005] (I) Technical problems to be solved

[0006] In view of the deficiencies of the prior art, the present application provides a heat supply network system control method based on a prediction model to solve the problems raised in the background art.

[0007] (II) Technical scheme

[0008] To achieve the above purpose, the present application provides the following technical scheme: a heat supply network system control method based on a prediction model, the method comprising the following steps:

[0009] S1, collecting historical operation data and real-time operation data of the heat supply network system;

[0010] S2, preprocessing the historical operation data and real-time operation data to generate a standardized heating data set;

[0011] S3, constructing a prediction model based on the standardized heating data set, and predicting future heating demand parameters and system efficiency parameters through the prediction model;

[0012] S4, generating a heating control instruction according to the prediction result, the heating control instruction comprising valve opening adjustment parameters, pump speed control parameters and heat source output parameters;

[0013] S5, execute the heating control instruction, dynamically adjust the operation state of the heat supply network;

[0014] S6, update the parameters of the prediction model based on the adjusted operation state data to optimize the prediction accuracy;

[0015] S7, real-time monitoring system response data, generate a heating control effect evaluation report;

[0016] S8, when the key indicators in the evaluation report are abnormal, trigger the early warning mechanism and generate the correction control instruction;

[0017] S9, the correction control instruction is fed back to the execution module for iterative control;

[0018] S10, output the final optimized heating control data, and store it in the heat network supervision platform database.

[0019] Preferably, the S1 comprises the following steps:

[0020] S11, collect the historical operation data of the heat supply network system through temperature sensors, flow meters and user terminals, the historical operation data including historical heating temperature data, historical user energy consumption data and historical environment temperature data;

[0021] S12, collect the real-time operation data of the heat supply network system through real-time monitoring equipment, the real-time operation data including real-time pipeline pressure data, real-time valve state data and real-time user demand feedback data;

[0022] S13, time series alignment processing is performed on the historical operation data and real-time operation data to generate an integrated heating data set;

[0023] S14, clean the abnormal values and missing values in the integrated heating data set to generate a preprocessed heating data package;

[0024] S15, transmit the preprocessed heating data package to the heat network supervision platform for preliminary analysis.

[0025] Preferably, the S2 comprises the following steps:

[0026] S21, obtain the preprocessed heating data package;

[0027] S22, normalize the preprocessed heating data package to generate a normalized heating data matrix; the normalization processing adopts the following formula:

[0028] ;

[0029] Wherein The normalized data value, The original data value, data mean, data standard deviation and greater than 0;

[0030] S23, extracting key features in the normalized heating data matrix based on a feature selection algorithm, generating a feature optimized data set;

[0031] S24, performing dimensionality reduction processing on the feature optimized data set, generating a standardized heating data set;

[0032] S25, verifying the data integrity of the standardized heating data set, outputting a data verification report.

[0033] Preferably, the S3 comprises the following steps:

[0034] S31, dividing the training set and the test set based on the standardized heating data set;

[0035] S32, constructing an initial prediction model using a machine learning algorithm, the machine learning algorithm including a random forest algorithm and a neural network algorithm;

[0036] S33, training the initial prediction model through the training set, generating a preliminary prediction result;

[0037] S34, cross-validating the preliminary prediction result using the test set, generating model precision evaluation data;

[0038] S35, adjusting model hyperparameters according to model precision evaluation data, optimizing the initial prediction model and outputting a final prediction model;

[0039] S36, predicting future heating demand parameters and system efficiency parameters through the final prediction model, the prediction model outputting heating demand parameters using the following formula:

[0040] ;

[0041] wherein predicted heating demand, outdoor temperature, is the number of users, temperature coefficient, user coefficient, constant term.

[0042] Preferably, the S4 comprises the following steps:

[0043] S41, obtaining the future heating demand parameters and system efficiency parameters;

[0044] S42, generating an initial heating control instruction based on a rule engine, the rule engine including an energy saving priority rule and a user comfort rule;

[0045] S43, simulate the initial heating control instruction to generate simulation response data;

[0046] S44, analyze the deviation of the simulation response data and the target parameter to generate instruction optimization parameters;

[0047] S45, correct the initial heating control instruction according to the instruction optimization parameters, and output the final heating control instruction.

[0048] Preferably, the S5 comprises the following steps:

[0049] S51, send the final heating control instruction to the actuator module;

[0050] S52, the actuator module controls the valve opening adjustment parameter to adjust the pipe hot water flow;

[0051] S53, the actuator module controls the pump speed control parameter to optimize the water pump operation efficiency;

[0052] S54, the actuator module controls the heat source output parameter to adjust the output power of the boiler and the heat pump;

[0053] S55, real-time acquisition of feedback data in the execution process to generate execution log data package.

[0054] Preferably, the S6 comprises the following steps:

[0055] S61, obtain the execution log data package and system response data;

[0056] S62, calculate the actual error rate of the prediction model to generate an error analysis report;

[0057] S63, update the weight parameters of the prediction model based on the error analysis report;

[0058] S64, retrain the prediction model through the incremental learning algorithm to generate the updated prediction model;

[0059] S65, store the updated prediction model to the heat network supervision platform model library.

[0060] Preferably, the S7 comprises the following steps:

[0061] S71, deploy the monitoring sensor network to collect system response data;

[0062] S72, calculate the key performance indicators, including energy consumption rate and user satisfaction index;

[0063] S73, generate a heating control effect evaluation report based on the threshold comparison algorithm;

[0064] S74, marking abnormal state data when the key performance indicator exceeds the preset threshold;

[0065] S75, outputting an evaluation report to a heat network supervision platform control center at regular intervals.

[0066] Preferably, the S8 comprises the following steps:

[0067] S81, triggering a warning mechanism when abnormal state data is marked in the evaluation report;

[0068] S82, identifying the source of the anomaly through a root cause analysis algorithm to generate an anomaly analysis report;

[0069] S83, generating a revised control instruction draft based on the anomaly analysis report;

[0070] S84, reviewing the revised control instruction draft through an expert system and outputting a final revised control instruction;

[0071] S85, recording the warning and revision process in a system log.

[0072] Preferably, the S9 comprises the following steps:

[0073] S91, inputting the final revised control instruction into an execution module;

[0074] S92, the execution module scheduling control tasks according to the instruction priority;

[0075] S93, implementing closed-loop adjustment through an iterative control algorithm to generate adjusted running data;

[0076] S94, verifying the effectiveness of the adjusted running data and outputting an iterative control report;

[0077] S95, comparing the iterative control report with the initial target parameters to optimize subsequent control strategies.

[0078] (Three) beneficial effects

[0079] Compared with the prior art, the present application provides a heat supply system control method based on a prediction model, which has the following beneficial effects:

[0080] 1. In the present application, during the operation control of the heat supply system, by constructing a prediction model based on historical data and real-time data, through the collection, processing and processing of industrial big data, the future period of heat load demand change can be dynamically predicted, the adjustment lag problem caused by the dependence of traditional control methods on static models is solved, the response ability of the heat supply system to extreme weather and sudden changes in user demand is improved, and the stability and reliability of the heat supply quality are guaranteed.

[0081] 2. In the heat supply parameter adjustment process of the present application, by analyzing the heat transfer characteristics and delay effects of each node in the pipe network in real time, the output timing and amplitude of the control instruction are dynamically optimized, the time lag between the control instruction and the actual heat supply effect is reduced, the insufficient heat supply and energy waste caused by untimely adjustment of the system are avoided, and the operation efficiency and energy utilization rate of the heat supply system are improved.

[0082] 3. In the multi-heat source collaborative regulation process of the present application, through intelligent decision support algorithm, the matching relationship between heat source output distribution and pipe network hydraulic working condition is balanced in real time, the hydraulic imbalance problem caused by uneven heat source output is avoided, the heat supply temperature of each node in the pipe network is balanced, the occurrence probability of local overheating and underheating is reduced, and the overall regulation precision and stability of the heat supply system are improved. BRIEF DESCRIPTION OF DRAWINGS

[0083] Figure 1 The flowchart of the heat supply system control method based on the prediction model of the present application. DETAILED DESCRIPTION

[0084] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0085] Embodiment: The heat supply system control method based on the prediction model, the method comprising the following steps:

[0086] S1, collecting historical operation data and real-time operation data of the heat supply system;

[0087] S2, preprocessing the historical operation data and real-time operation data to generate a standardized heat supply data set;

[0088] S3, constructing a prediction model based on the standardized heat supply data set, and predicting future heat supply demand parameters and system efficiency parameters through the prediction model;

[0089] S4, generating a heat supply control instruction according to the prediction result, the heat supply control instruction including valve opening adjustment parameters, pump speed control parameters and heat source output parameters;

[0090] S5, executing the heat supply control instruction to dynamically adjust the operation state of the heat supply system;

[0091] S6, updating the parameters of the prediction model based on the adjusted operation state data to optimize the prediction accuracy;

[0092] S7, real-time monitoring system response data, generating heating control effect evaluation report;

[0093] S8, when the key indicators in the evaluation report are abnormal, trigger the early warning mechanism and generate correction control instructions;

[0094] S9, the modified control instructions are fed back to the execution module for iterative control;

[0095] S10, output the final optimized heating control data, and store it in the heat network supervision platform database.

[0096] S1 includes the following steps:

[0097] S11, through the temperature sensor, flow meter and user terminal to collect the historical operation data of heat supply system, including historical heating temperature data, historical user energy consumption data, historical environment temperature data;

[0098] S12, through the real-time monitoring equipment to collect the real-time operation data of heat supply system, including real-time pipeline pressure data, real-time valve state data, real-time user demand feedback data;

[0099] S13, time series alignment processing is carried out on the historical operation data and real-time operation data, and integrated heating data set is generated;

[0100] S14, cleaning the integrated heating data set of abnormal value and missing value, generating pre-processing heating data package;

[0101] S15, the pre-processing heating data package is transmitted to the heat network supervision platform for preliminary analysis.

[0102] S2 includes the following steps:

[0103] S21, obtaining the pre-processing heating data package;

[0104] S22, the pre-processing heating data package is normalized to generate normalized heating data matrix; the normalization processing adopts the following formula:

[0105] ;

[0106] Among them, The normalized data value, The original data value, The data mean, The data standard deviation is greater than 0;

[0107] S23, based on the feature selection algorithm, the key features in the normalized heating data matrix are extracted, and the feature optimization data set is generated;

[0108] S24, dimensionality reduction is performed on the feature optimization dataset to generate a standardized heating dataset;

[0109] S25, verifying the data integrity of the standardized heating dataset, and outputting a data verification report.

[0110] S3 includes the following steps:

[0111] S31, dividing the training set and the test set based on the standardized heating dataset;

[0112] S32, constructing an initial prediction model using a machine learning algorithm, which includes a random forest algorithm and a neural network algorithm;

[0113] S33, training the initial prediction model through the training set to generate a preliminary prediction result;

[0114] S34, cross-validating the preliminary prediction result using the test set to generate model precision evaluation data;

[0115] S35, adjusting the model hyperparameters according to the model precision evaluation data, optimizing the initial prediction model, and outputting a final prediction model;

[0116] S36, predicting future heating demand parameters and system efficiency parameters through the final prediction model, and the heating demand parameters output by the prediction model are calculated using the following formula:

[0117] ;

[0118] wherein predicted heating demand, outdoor temperature, the number of users, temperature coefficient, user coefficient, constant term;

[0119] S37, the heat loss of the heating pipe network during the transportation process provides the basic data of the pipe network efficiency parameters for the prediction model:

[0120] ;

[0121] wherein:

[0122] heat loss of the pipe network per unit time, comprehensive heat transfer coefficient of the pipe, pipe length, average temperature of the medium in the pipe, soil temperature around the pipe.

[0123] S4 includes the following steps:

[0124] S41, acquire future heat supply demand parameters and system efficiency parameters;

[0125] S42, generate initial heat supply control instructions based on a rule engine, the rule engine including energy saving priority rules and user comfort rules;

[0126] S43, simulate the initial heat supply control instructions to generate simulation response data;

[0127] S44, analyze deviations of the simulation response data from target parameters to generate instruction optimization parameters;

[0128] S45, correct the initial heat supply control instructions according to the instruction optimization parameters to output final heat supply control instructions;

[0129] S46, calculate hydraulic working conditions of each branch of the pipe network to provide a theoretical basis for valve opening adjustment:

[0130] ;

[0131] wherein is the pipe pressure drop, is the pipe resistance characteristic coefficient, is the pipe flow rate, is the flow index, usually 1.75-2.0.

[0132] S5 includes the following steps:

[0133] S51, send the final heat supply control instructions to an executor module;

[0134] S52, control valve opening adjustment parameters by the executor module to adjust hot water flow rate of the pipe;

[0135] S53, control pump speed control parameters by the executor module to optimize water pump operating efficiency;

[0136] S54, control heat source output parameters by the executor module to adjust output power of the boiler and the heat pump;

[0137] S55, collect feedback data in the execution process in real time to generate execution log data packets.

[0138] S6 includes the following steps:

[0139] S61, acquire execution log data packets and system response data;

[0140] S62, calculate actual error rate of the prediction model to generate an error analysis report;

[0141] S63, update weight parameters of the prediction model based on the error analysis report;

[0142] S64, retrain the prediction model through the incremental learning algorithm to generate an updated prediction model:

[0143] ;

[0144] wherein the updated model weight, the current model weight, the learning rate, and , the partial derivative of the error with respect to the weight, which describes the mathematical process of parameter updating of the prediction model through gradient descent method, supporting the continuous optimization of the model;

[0145] S65, store the updated prediction model in the heat network regulatory platform model library.

[0146] S7 includes the following steps:

[0147] S71, deploy the monitoring sensor network acquisition system to collect system response data;

[0148] S72, calculate key performance indicators, including energy consumption rate and user satisfaction index;

[0149] S73, generate a heating control effect evaluation report based on a threshold comparison algorithm:

[0150] ;

[0151] wherein the heat source comprehensive efficiency, the effective output heat of the heat source, the input energy of the heat source, the formula is applicable to evaluate the operation efficiency of heat source equipment such as boilers and heat pumps, which is a key indicator for system energy efficiency analysis;

[0152] S74, when the key performance indicators exceed the preset threshold, mark the abnormal state data;

[0153] S75, output the evaluation report to the heat network regulatory platform control center regularly.

[0154] S8 includes the following steps:

[0155] S81, when the evaluation report marks the abnormal state data, trigger the early warning mechanism:

[0156] ;

[0157] wherein user comfort index, indoor measured temperature, user set temperature, temperature change rate, Weight coefficient, the formula quantifies the impact of heating quality on user comfort, providing a quantitative basis for anomaly early warning;

[0158] S82, identify the source of the anomaly through root cause analysis algorithm, generate anomaly analysis report;

[0159] S83, generate revision control instruction draft based on anomaly analysis report;

[0160] S84, review the revision control instruction draft through expert system, output the final revision control instruction;

[0161] S85, record the warning and revision process to the system log.

[0162] S9 includes the following steps:

[0163] S91, input the final revision control instruction into the execution module;

[0164] S92, the execution module schedules control tasks according to instruction priority;

[0165] S93, realize closed-loop adjustment through iterative control algorithm, generate adjusted running data;

[0166] S94, verify the validity of the adjusted running data, output the iterative control report;

[0167] S95, compare the iterative control report with the initial target parameters, optimize the subsequent control strategy.

[0168] The steps of the method are as follows:

[0169] Data acquisition and preprocessing stage:

[0170] The method first collects the historical running data of the heat supply system through temperature sensors, flow meters and user terminals, including historical heating temperature, user energy consumption and environmental temperature and other key parameters. At the same time, real-time monitoring equipment will collect pipeline pressure, valve state and user demand feedback and other real-time running data. After time series alignment processing, a complete integrated heating data set is formed. The system will clean the data set, remove outliers and fill in missing values, and generate a preprocessed heating data package.

[0171] Data standardization and feature engineering:

[0172] The preprocessed data package will be normalized to convert data of different dimensions and ranges to a unified standard, generating a normalized heating data matrix. Subsequently, the system uses feature selection algorithms to extract key features from the data matrix, removes redundant information, and further optimizes the data structure through dimension reduction techniques, finally forming a standardized heating data set. This step ensures the data quality and efficiency of subsequent model training.

[0173] Prediction model construction and training:

[0174] The system divides the training set and test set based on the standardized data set, and uses machine learning algorithms such as random forest and neural network to construct the initial prediction model. During the training process, the model continuously adjusts the parameters to minimize the prediction error, and evaluates the model accuracy through cross-validation. After hyperparameter optimization, the system outputs the final prediction model, which can accurately predict future heating demand parameters and system efficiency parameters, providing decision basis for heating control.

[0175] Control instruction generation and optimization:

[0176] According to the prediction results, the system generates initial heating control instructions based on energy saving priority and user comfort rules, including valve opening, pump speed and heat source output, etc. These instructions will be verified through simulation analysis, and the deviation from the actual target parameters will be analyzed and corrected through optimization algorithm, and finally the optimized heating control instructions will be output.

[0177] Execution and feedback closed loop:

[0178] The final control instructions are sent to the actuator module to adjust the operating parameters such as pipe flow, pump efficiency and heat source power in real time. The system will collect feedback data during execution to form an execution log. Based on these real-time data, the system calculates the actual error rate of the prediction model, and continuously updates the model weight parameters through incremental learning algorithm to dynamically improve the prediction accuracy.

[0179] Monitoring and evaluation and abnormal processing:

[0180] The system deploys a comprehensive monitoring sensor network to collect system response data and calculate key performance indicators such as energy consumption rate and user satisfaction in real time. When the indicators exceed the preset threshold, the system will trigger the early warning mechanism, identify the source of the anomaly through root cause analysis, and generate correction control instructions. These correction instructions are reviewed by the expert system and fed back to the execution module for iterative adjustment to form a complete closed-loop control system.

[0181] Result output and storage:

[0182] The system finally outputs the optimized heating control data and stores it in the heat network supervision platform database, providing data support for subsequent analysis and management decisions. The whole process realizes the full-process automatic control from data collection, prediction analysis to execution feedback, improving the response speed, running efficiency and energy utilization rate of the heating system.

[0183] It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting; it is not intended to exclude myriad other embodiments of the present application that other inventors can develop based on the same general inventive concepts embodied by the described embodiments. That is, although the present application is described in terms of particular embodiments and implementations, it is to be understood that the terminology used is for the purpose of descriptive clarity and that it should be taken in a descriptive sense and not a limiting sense.

[0184] While the embodiments of the application have been shown and described herein, it is to be understood that the application is not limited to these embodiments. Rather, many modifications, changes, substitutions, and alterations can be made to the embodiments of the application without departing from the spirit and scope of the application as defined by the appended claims and their equivalents.

Claims

1. A control method for a heating network system based on a predictive model, characterized in that: The method includes the following steps: S1. Collect historical and real-time operating data of the heating network system; S2. Preprocess the historical and real-time operating data to generate a standardized heating dataset; S3. Construct a prediction model based on the standardized heating dataset, and use the prediction model to predict future heating demand parameters and system efficiency parameters; S4. Generate heating control commands based on the prediction results. The heating control commands include valve opening adjustment parameters, pump speed control parameters, and heat source output parameters. S5. Execute the heating control command to dynamically adjust the operating status of the heating network system; S6. Based on the adjusted operating status data, update the parameters of the prediction model to optimize the prediction accuracy; S7. Monitor system response data in real time and generate a heating control effect evaluation report; S8. When a key indicator in the assessment report is abnormal, an early warning mechanism is triggered and a correction control instruction is generated. S9. Feed the correction control command back to the execution module for iterative control; S10. Output the final optimized heating control data and store it in the heating network monitoring platform database.

2. The control method for a heating network system based on a predictive model according to claim 1, characterized in that: S1 includes the following steps: S11. Collect historical operating data of the heating network system through temperature sensors, flow meters and user terminals. The historical operating data includes historical heating temperature data, historical user energy consumption data and historical ambient temperature data. S12. Collect real-time operating data of the heating network system through real-time monitoring equipment. The real-time operating data includes real-time pipeline pressure data, real-time valve status data, and real-time user demand feedback data. S13. Perform time series alignment processing on the historical operating data and real-time operating data to generate an integrated heating dataset; S14. Clean outliers and missing values ​​in the integrated heating data set to generate a preprocessed heating data package; S15. The pre-processed heating data package is transmitted to the heating network monitoring platform for preliminary analysis.

3. The control method for a heating network system based on a predictive model according to claim 1, characterized in that: S2 includes the following steps: S21. Obtain the preprocessed heating data packet; S22. Normalize the preprocessed heating data package to generate a normalized heating data matrix; the normalization process uses the following formula: ； in Normalized data values, Original data values, Data mean The data standard deviation is greater than 0; S23. Extract key features from the normalized heating data matrix based on the feature selection algorithm to generate a feature-optimized dataset; S24. Perform dimensionality reduction processing on the feature optimization dataset to generate a standardized heating dataset; S25. Verify the data integrity of the standardized heating dataset and output a data verification report.

4. The control method for a heating network system based on a predictive model according to claim 1, characterized in that: S3 includes the following steps: S31. Divide the standardized heating dataset into a training set and a test set; S32. An initial prediction model is constructed using machine learning algorithms, including random forest algorithm and neural network algorithm; S33. Train the initial prediction model using the training set to generate preliminary prediction results; S34. Cross-validate the primary prediction results using the test set to generate model accuracy evaluation data; S35. Adjust the model hyperparameters based on the model accuracy evaluation data, optimize the initial prediction model, and output the final prediction model; S36. Predict future heating demand parameters and system efficiency parameters using the final prediction model. The heating demand parameters output by the prediction model are given by the following formula: ； in Predicting heating demand, Outdoor temperature, For the number of users, Temperature coefficient User coefficient, Constant term.

5. The control method for a heating network system based on a predictive model according to claim 1, characterized in that: S4 includes the following steps: S41. Obtain the future heating demand parameters and system efficiency parameters; S42. Generate initial heating control instructions based on a rule engine, wherein the rule engine includes energy-saving priority rules and user comfort rules; S43. Simulate the initial heating control command to generate simulation response data; S44. Analyze the deviation between the simulation response data and the target parameters, and generate instruction optimization parameters; S45. Based on the instruction, optimize the parameters to correct the initial heating control instruction and output the final heating control instruction.

6. The control method for a heating network system based on a predictive model according to claim 1, characterized in that: S5 includes the following steps: S51. Send the final heating control command to the actuator module; S52, the actuator module controls the valve opening adjustment parameters to regulate the hot water flow in the pipeline; S53, the actuator module controls the pump speed control parameters to optimize the pump operating efficiency; S54, the actuator module controls the output parameters of the heat source and adjusts the output power of the boiler and heat pump; S55. Collect feedback data during the execution process in real time and generate execution log data packets.

7. The control method for a heating network system based on a predictive model according to claim 1, characterized in that: S6 includes the following steps: S61. Obtain the execution log data packet and system response data; S62. Calculate the actual error rate of the prediction model and generate an error analysis report; S63. Update the weight parameters of the prediction model based on the error analysis report; S64. Retrain the prediction model using the incremental learning algorithm to generate an updated prediction model; S65. Store the updated prediction model in the model library of the heating network monitoring platform.

8. The control method for a heating network system based on a predictive model according to claim 1, characterized in that: S7 includes the following steps: S71. Deploy and monitor the sensor network to collect system response data; S72. Calculate key performance indicators, including energy consumption rate and user satisfaction index; S73. Generate a heating control effect evaluation report based on a threshold comparison algorithm; S74. When a key performance indicator exceeds a preset threshold, mark the abnormal state data. S75. Regularly output assessment reports to the control center of the heating network supervision platform.

9. The control method for a heating network system based on a predictive model according to claim 1, characterized in that: S8 includes the following steps: S81. When abnormal data is marked in the assessment report, an early warning mechanism is triggered; S82. Identify the source of anomalies using the root cause analysis algorithm and generate an anomaly analysis report; S83. Generate a draft of corrective control instructions based on the anomaly analysis report; S84. Review the draft of the revised control instruction through the expert system and output the final revised control instruction; S85. Record the warning and correction process to the system log.

10. The control method for a heating network system based on a predictive model according to claim 1, characterized in that: S9 includes the following steps: S91. Input the final correction control command into the execution module; S92. The execution module schedules and controls tasks according to instruction priority; S93. Closed-loop adjustment is achieved through iterative control algorithm to generate adjusted operating data; S94. Verify the validity of the adjusted running data and output an iteration control report; S95. Compare the iterative control report with the initial target parameters and optimize the subsequent control strategy.

Images