Intelligent heat supply and water return control system and method

Abstract

The invention relates to the technical field of heat supply, and discloses an intelligent heat supply and water return control system and method.The control method comprises the steps that the historical operation state of a past heat supply system is obtained and evaluated, historical heat supply and water return feature sets meeting user requirements are screened, and a heat supply and water return feature prediction model is constructed and trained based on the heat supply and water return feature sets; a first heat supply and water return characteristic is obtained, a first water outlet characteristic is predicted based on the first heat supply and water return characteristic, and then a first control strategy is determined to control the heat supply system to operate; after a first preset time period after operation based on the first control strategy, obtaining a current operation state to determine a current heat supply and water return characteristic, and judging a first difference characteristic between the current heat supply and water return characteristic and a heat supply and water return characteristic corresponding to the predicted heat supply and water outlet characteristic; and based on the first difference characteristic, an optimization control strategy of the heat supply system is determined, and the first control strategy is adjusted. According to the invention, centralized intelligent control and adjustment of the heat supply system can be effectively realized.

Description

Technical Field

[0001] The present invention relates to the field of heating technology, and in particular to an intelligent heating return water control system and method. Background Art

[0002] The control signals of existing heating return water equipment are not integrated into a system, and intelligent management and control cannot be achieved. Manual intervention is required, resulting in different parameter control of each heating equipment, low operating efficiency of the heating system, and failure to promptly detect and handle differences in heating return water during the operation of the heating system, resulting in high maintenance costs.

[0003] Therefore, how to provide a systematic and intelligent intelligent heating return water control system and method that can identify the differences in heating return water during the operation of the heating system and automatically adjust it is an issue that technical personnel in this field urgently need to solve. Summary of the invention

[0004] In view of this, the present invention provides an intelligent heating return water control system and method to solve the technical problems that the heating system cannot achieve centralized intelligent control and cannot timely discover and handle the heating return water differences during equipment operation.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] On the one hand, the present invention provides an intelligent heating return water control method, comprising:

[0007] Obtain the historical operating status of the heating system and the historical heating return water characteristics of its corresponding generator group;

[0008] Evaluate the historical operating status of the heating system and select the historical heating return water feature group whose historical operating status meets the needs of users;

[0009] Based on the heating return water feature group of the generator group, a heating return water feature prediction model is constructed and trained to predict the heating water outlet features of the corresponding heating system;

[0010] Acquire a first heating return water characteristic of the current generator group, and predict a first outlet water characteristic of the generator group based on the first heating return water characteristic and the heating return water characteristic prediction model; the first outlet water characteristic includes a heating outlet water temperature parameter and a heating outlet water flow parameter at different time nodes;

[0011] Determining a first control strategy for controlling the heating system based on the first water output characteristic, and controlling the operation of the heating system based on the first control strategy;

[0012] After a first preset time period after the heating system has been running according to the first control strategy, a current operating state of the heating system is obtained, and based on the current operating state, current heating return water characteristics of the generator group are determined, wherein the heating return water characteristics include heating return water temperature parameters and heating return water flow parameters at different time nodes;

[0013] Analyze the current heating return water characteristics of the generator group to determine the first difference characteristics of the heating return water characteristics corresponding to the current heating return water characteristics and the predicted heating outlet water characteristics;

[0014] Based on the first difference feature, an optimal control strategy for the heating system is determined, and the first control strategy is adjusted based on the optimal control strategy.

[0015] Preferably, in the above-mentioned intelligent heating return water control method, the method of screening out the historical heating return water feature group whose historical operating status of the heating system meets the user's needs includes:

[0016] Obtain the historical operation data of the heating system and preprocess the historical operation data to remove abnormal values, missing values ​​and duplicate values;

[0017] Extracting the pre-treated heating return water temperature parameters, heating return water flow parameters, heating outlet water temperature parameters and heating outlet water flow parameters;

[0018] The heating outlet water temperature parameters and heating outlet water flow parameters as well as the corresponding heating return water temperature parameters and heating return water flow parameters are analyzed, and the heating return water characteristics that meet user needs are classified to obtain a historical heating return water characteristic group.

[0019] Preferably, in the above-mentioned intelligent heating return water control method, the historical operation status includes historical heating return water characteristics and historical heating water outlet characteristics, and the method for constructing and training the heating return water characteristic prediction model based on the heating return water characteristic group of the generator group includes:

[0020] Acquire the historical heating return water characteristics as model input data;

[0021] Acquiring the historical heating water outlet characteristics as model output data;

[0022] Constructing a heating return water characteristic prediction model based on the model input data, the model output data and a preset neural network model;

[0023] A plurality of groups of the model input data and the model output data are obtained as model training data, and the heating return water characteristic prediction model is trained to obtain the heating return water characteristic prediction model.

[0024] Preferably, in the above-mentioned intelligent heating return water control method, the method for predicting the first water output characteristic of the generator group based on the first heating return water characteristic and the heating return water characteristic prediction model includes:

[0025] Acquire a first heating return water characteristic of the generator group according to a first operating state of the heating system, wherein the first heating return water characteristic comprises a first heating return water temperature parameter and a first heating return water flow parameter of the generator group;

[0026] The first heating return water temperature parameter and the first heating return water flow parameter are input into the heating return water characteristic prediction model as model input data to obtain the first heating outlet water characteristic of the generator group, wherein the first heating outlet water characteristic includes the first heating outlet water temperature parameter and the first heating outlet water flow parameter of the generator group, and the first heating outlet water temperature parameter and the first heating outlet water flow parameter of each unit in the generator group are the same.

[0027] Preferably, in the above-mentioned intelligent heating return water control method, the method for determining the first control strategy for controlling the heating system based on the first water outlet characteristic includes:

[0028] A plurality of valve opening-heating water flow parameter interval correspondence relationships are preset, and the plurality of valve opening-heating water flow parameter interval correspondence relationships are associated with a plurality of valve openings for each heating water flow parameter interval of the heating system;

[0029] The first heating outlet water flow parameter predicted by the heating return water characteristic prediction model is obtained, and based on the mapping relationship between the heating outlet water flow parameter interval to which the first heating outlet water flow parameter belongs and the corresponding relationship between the valve opening and the heating outlet water flow parameter interval, the opening of the current valves of the heating system is determined.

[0030] Preferably, in the above-mentioned intelligent heating return water control method, the method for determining the first difference characteristic of the heating return water characteristic corresponding to the current heating return water characteristic and the predicted heating outlet water characteristic comprises:

[0031] Acquire predicted water discharge characteristics, and determine the current control strategy for controlling the heating system based on the predicted water discharge characteristics, and after controlling the operation of the heating system for a first preset time period based on the current control strategy, determine the corresponding heating return water characteristics of the heating system at this time according to the overall performance state of the heating system, and determine the heating return water temperature parameters at different time points based on the heating return water characteristics;

[0032] Obtain the optimal historical heating return water characteristics corresponding to the predicted water outlet characteristics, and determine the historical heating return water temperature parameters at different time points based on the historical heating return water characteristics;

[0033] Compare and analyze the current heating return water temperature parameter with the historical heating return water temperature parameter to obtain several first parameter differences;

[0034] Determining a first degree of difference based on a plurality of first parameter differences;

[0035] If the first difference degree = 0, continue to control the operation of the heating system based on the current control strategy;

[0036] If the first difference degree is greater than 0, the second water outlet temperature parameter is determined based on the current heating return water temperature parameter, and then the second control strategy is determined and the operation of the heating system is controlled based on the second control strategy.

[0037] Preferably, in the above intelligent heating return water control method, the expression for determining the first difference degree based on the first parameter differences is:

[0038]

[0039] Among them, is the first difference degree of the current heating return water temperature parameter relative to the optimal historical heating return water temperature parameter, is the weight coefficient of the parameter difference between the heating return water temperature parameter at the nth time point and the historical heating return water temperature parameter, is the current heating return water temperature parameter at the nth time point, and is the historical heating return water temperature parameter at the nth time point.

[0040] On the other hand, the present invention provides an intelligent heating return water control system, including: a prediction module, a data acquisition and communication module, a control center and an execution module;

[0041] The prediction module is used to obtain historical operation data of the heating system, build and train a heating return water characteristic prediction model based on the historical operation data, and predict corresponding heating return water outlet parameters;

[0042] The data acquisition and communication module is used to collect data in real time, obtain the current operating status of the heating system, determine the current heating return water characteristics of each unit based on the current operating status, and send the current operating status to the control center through the communication module;

[0043] The control center includes an intelligent algorithm platform, which optimizes the heating water outlet characteristics based on the current heating return water characteristics and the heating return water characteristics prediction model, determines the optimized heating water outlet temperature parameters, and then determines the optimized control strategy to control the operation of the heating system;

[0044] The execution module includes several valves and heat exchangers. Based on the control strategy, the opening of the several valves is controlled to adjust the flow rate of heating return water of each unit, and the heat exchanger is controlled to adjust the heat exchange between hot water and cold water in the heating system to adjust the heating return water temperature of each unit.

[0045] The present invention provides an intelligent heating return water control system and method. Compared with the prior art, the beneficial effects thereof are:

[0046] The intelligent heating return water control system and method of the present invention evaluates the historical operation status through a prediction module to select the corresponding historical heating return water feature group, and constructs and trains a heating return water feature prediction model based on the heating return water feature group of the generator group, predicts the best heating outlet water feature by acquiring the current heating return water feature, determines the first control strategy based on the best heating outlet water feature, and the execution module adjusts the opening of several valves based on the first control strategy to adjust the heating outlet water flow rate. After a period of operation, the data acquisition and communication module intelligently monitors the heating return water feature of the heating system and compares and analyzes it with the optimal historical heating return water feature to obtain several first parameter differences. Based on the several first parameter differences, the first difference degree is determined. If the first difference degree = 0, the operation of the heating system is continued to be controlled based on the current control strategy; if the first difference degree is greater than 0, the second outlet water temperature parameter is determined based on the current heating return water temperature parameter, and then the second control strategy is determined and the operation of the heating system is controlled based on the second control strategy, thereby realizing centralized intelligent control of the heating system and achieving the technical effect of timely discovery and timely adjustment of the heating return water difference during the operation of the heating system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flow chart of an intelligent heating return water control method in the preferred embodiment of the present application. DETAILED DESCRIPTION

[0048] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0049] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0050] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0051] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0052] like Figure 1 As shown, an intelligent heating return water control method according to a preferred embodiment of the present application includes:

[0053] Obtain the historical operating status of the heating system and the historical heating return water characteristics of its corresponding generator group;

[0054] Evaluate the historical operating status of the heating system and select the historical heating return water feature group whose historical operating status meets the needs of users;

[0055] Based on the heating return water feature group of the generator group, a heating return water feature prediction model is constructed and trained to predict the heating water outlet features of the corresponding heating system;

[0056] In this embodiment, the historical operating status of the heating system includes several historical heating return water characteristics and several historical heating water outlet characteristics. The historical operating status of the heating system is evaluated, that is, several historical heating return water characteristics and several historical heating water outlet characteristics are evaluated. If the historical heating water outlet characteristics meet the user's heating needs, the historical heating water outlet characteristics are associated with their corresponding historical heating return water characteristics, and several historical heating water outlet characteristics that meet the user's heating needs and their corresponding historical heating return water characteristics are obtained. A heating return water characteristic prediction model is constructed and trained to achieve accurate prediction of the heating water outlet characteristics of the heating system, so that the heating system can operate stably and normally.

[0057] Acquire a first heating return water characteristic of the current generator group, and predict a first outlet water characteristic of the generator group based on the first heating return water characteristic and the heating return water characteristic prediction model; the first outlet water characteristic includes a heating outlet water temperature parameter and a heating outlet water flow parameter at different time nodes;

[0058] Determining a first control strategy for controlling the heating system based on the first water output characteristic, and controlling the operation of the heating system based on the first control strategy;

[0059] In this embodiment, the heating water outlet characteristics include the heating water outlet temperature parameters and the heating water outlet flow parameters at different time nodes, and the heating return water characteristics include the heating return water temperature parameters and the heating return water flow parameters at different time nodes; the current heating return water characteristics are obtained, and the current heating return water characteristics are substituted into the heating return water characteristic prediction model to predict the current heating water outlet characteristics, and the first control strategy is determined based on the predicted heating water outlet characteristics. The first control strategy analyzes the valve opening and closing degree and heating conditions corresponding to the current generator group as the main purpose to achieve more efficient and reasonable control.

[0060] After a first preset time period after the heating system has been running according to the first control strategy, a current operating state of the heating system is obtained, and based on the current operating state, current heating return water characteristics of the generator group are determined, wherein the heating return water characteristics include heating return water temperature parameters and heating return water flow parameters at different time nodes;

[0061] Analyze the current heating return water characteristics of the generator group to determine the first difference characteristics of the heating return water characteristics corresponding to the current heating return water characteristics and the predicted heating outlet water characteristics;

[0062] In this embodiment, the valve opening is adjusted through the first control strategy. After the heating has been running for a period of time, the heating return water characteristics of the current heating system are monitored and obtained, and it is determined whether the heating return water characteristics of the current heating system are consistent with the heating return water characteristics corresponding to the predicted heating water outlet characteristics to determine whether the current heating system has returned to a good state. If the current heating system has returned to a good state, the heating system operation is continued to be controlled based on the current control strategy. If the current heating system has not returned to a good state, the first difference feature is determined based on the current heating return water characteristics.

[0063] Based on the first difference feature, an optimal control strategy for the heating system is determined, and the first control strategy is adjusted based on the optimal control strategy.

[0064] In this embodiment, the difference between the current heating outlet water temperature parameter and the standard outlet water temperature parameter is determined through the first difference feature, and then the optimized heating outlet water temperature parameter is determined to adjust the first control strategy, thereby realizing real-time adjustment and centralized control of system operating parameters and improving the flexibility of the intelligent heating return water control method.

[0065] In some embodiments of the present invention, the method for screening out a historical heating return water feature group whose historical operating status of the heating system meets the user's needs comprises:

[0066] Obtain the historical operation data of the heating system and preprocess the historical operation data to remove abnormal values, missing values ​​and duplicate values;

[0067] Extracting the pre-treated heating return water temperature parameters, heating return water flow parameters, heating outlet water temperature parameters and heating outlet water flow parameters;

[0068] The heating outlet water temperature parameters and heating outlet water flow parameters as well as the corresponding heating return water temperature parameters and heating return water flow parameters are analyzed, and the heating return water characteristics that meet user needs are classified to obtain a historical heating return water characteristic group.

[0069] In this embodiment, screening the historical heating return water feature groups that have performed well in the historical operating status helps to improve the prediction accuracy and heating efficiency of the heating system, thereby helping to ensure the stable operation of the heating system.

[0070] In some embodiments of the present invention, the method for constructing and training a heating return water feature prediction model based on a heating return water feature group of a generator group includes:

[0071] Acquire the historical heating return water characteristics as model input data;

[0072] Acquiring the historical heating water outlet characteristics as model output data;

[0073] Constructing a heating return water characteristic prediction model based on the model input data, the model output data and a preset neural network model;

[0074] A plurality of groups of the model input data and the model output data are obtained as model training data, and the heating return water characteristic prediction model is trained to obtain the heating return water characteristic prediction model.

[0075] In this embodiment, the heating return water characteristic prediction model is trained to more accurately predict the heating water outlet characteristics, which helps to reduce energy waste and reduce maintenance difficulty.

[0076] In some embodiments of the present invention, the method for predicting the first water output characteristic of the generator group based on the first heating return water characteristic and the heating return water characteristic prediction model includes:

[0077] Acquire a first heating return water characteristic of the generator group according to a first operating state of the heating system, wherein the first heating return water characteristic comprises a first heating return water temperature parameter and a first heating return water flow parameter of the generator group;

[0078] The first heating return water temperature parameter and the first heating return water flow parameter are input into the heating return water characteristic prediction model as model input data to obtain the first heating outlet water characteristic of the generator group, wherein the first heating outlet water characteristic includes the first heating outlet water temperature parameter and the first heating outlet water flow parameter of the generator group, and the first heating outlet water temperature parameter and the first heating outlet water flow parameter of each unit in the generator group are the same.

[0079] In some embodiments of the present invention, the method for determining a first control strategy for controlling a heating system based on a first water outlet characteristic includes:

[0080] A plurality of valve opening-heating water flow parameter interval correspondence relationships are preset, and the plurality of valve opening-heating water flow parameter interval correspondence relationships are associated with a plurality of valve openings for each heating water flow parameter interval of the heating system;

[0081] The first heating outlet water flow parameter predicted by the heating return water characteristic prediction model is obtained, and based on the mapping relationship between the heating outlet water flow parameter interval to which the first heating outlet water flow parameter belongs and the corresponding relationship between the valve opening and the heating outlet water flow parameter interval, the opening of the current valves of the heating system is determined.

[0082] In this embodiment, the correspondence between several valve openings and heating water flow parameter intervals is set in advance. The corresponding valve opening can be obtained according to the heating water flow parameter in the first water outlet feature, which is convenient for identifying and extracting corresponding control data to form control signals for centralized control of valves, thereby improving the operating efficiency of the heating system.

[0083] In some embodiments of the present invention, the method for determining the first difference characteristic of the heating return water characteristic corresponding to the current heating return water characteristic and the predicted heating outlet water characteristic comprises:

[0084] Acquire predicted water discharge characteristics, and determine the current control strategy for controlling the heating system based on the predicted water discharge characteristics, and after controlling the operation of the heating system for a first preset time period based on the current control strategy, determine the corresponding heating return water characteristics of the heating system at this time according to the overall performance state of the heating system, and determine the heating return water temperature parameters at different time points based on the heating return water characteristics;

[0085] Obtain the optimal historical heating return water characteristics corresponding to the predicted water outlet characteristics, and determine the historical heating return water temperature parameters at different time points based on the historical heating return water characteristics;

[0086] Compare and analyze the current heating return water temperature parameter with the historical heating return water temperature parameter to obtain several first parameter differences;

[0087] Determining a first degree of difference based on a plurality of first parameter differences;

[0088] If the first difference degree = 0, continue to control the operation of the heating system based on the current control strategy;

[0089] If the first difference degree is greater than 0, the second water outlet temperature parameter is determined based on the current heating return water temperature parameter, and then the second control strategy is determined and the operation of the heating system is controlled based on the second control strategy.

[0090] In this embodiment, the heating return water temperature parameters at different time points determined by the current heating return water characteristics are compared with the historical heating return water temperature parameters of the historical heating return water characteristics corresponding to the historical optimal heating water outlet characteristics. If there is no difference, it means that the current control strategy is feasible and the current heating system is operating well; if there is a difference, it means that the current control strategy needs to be adjusted until the heating system operates well.

[0091] In some embodiments of the present invention, the expression for determining the first degree of difference based on the first parameter differences is:

[0092]

[0093] Among them, η1 is the first difference degree of the current heating return water temperature parameter relative to the optimal historical heating return water temperature parameter, λ n is the weight coefficient of the parameter difference between the heating return water temperature parameter at the nth time point and the historical heating return water temperature parameter, t l--n is the current heating return water temperature parameter at the nth time point, t h-n It is the historical heating return water temperature parameter at the nth time point.

[0094] In this embodiment, the parameter difference between the heating return water temperature parameters at different time points after the heating system has been running for a period of time and the heating return water temperature parameters at different time points of the historical heating return water characteristics corresponding to the optimal historical heating water outlet characteristics is calculated, and the first degree of difference between the current heating return water temperature parameter and the optimal historical heating return water temperature parameter is judged according to the cumulative value of the parameter difference at each time point, and then it is determined whether the current control strategy needs to be adjusted, thereby realizing the system self-diagnosis function, being able to discover differences and make adjustments in time, which is beneficial to improving the operating efficiency of the system and reducing maintenance costs.

[0095] In some embodiments of the present application, an intelligent heating return water control system is also included, including a prediction module, a data acquisition and communication module, a control center and an execution module:

[0096] The prediction module is used to obtain the historical operation data of the heating system, build and train the heating return water characteristic prediction model based on the historical operation data, and predict the corresponding heating return water outlet parameters;

[0097] The data acquisition and communication module is used to collect data in real time, obtain the current operating status of the heating system, determine the current heating return water characteristics of each unit based on the current operating status, and send the current operating status to the control center through the communication module;

[0098] The control center includes an intelligent algorithm platform, which optimizes the heating water outlet characteristics based on the current heating return water characteristics and the heating return water characteristics prediction model, determines the optimized heating water outlet temperature parameters, and then determines the optimized control strategy to control the operation of the heating system;

[0099] The execution module includes several valves and heat exchangers. Based on the control strategy, the opening of the several valves is controlled to adjust the flow rate of the heating return water of each unit, and the heat exchanger is controlled to adjust the heat exchange between hot water and cold water in the heating system to adjust the heating return water temperature of each unit.

[0100] In summary, the present invention discloses an intelligent heating return water control system and method, the method comprising: first, a prediction module screens past historical operation data, and constructs and trains a heating return water feature prediction model based on the screened historical heating return water feature group; when in use, a data acquisition and communication module collects a first heating return water feature and sends it to a control center; a first outlet water feature is predicted by the first heating return water feature and the heating return water feature prediction model; and a first control strategy for controlling valve opening and heating outlet water temperature parameters is determined according to the first outlet water feature; an execution module controls the valve opening and the outlet water temperature based on the first control strategy; and then obtains the operating status of the heating system after running for a period of time and performs heating return water feature analysis and comparison to obtain a first difference degree; if the first difference degree is greater than 0, the first control strategy is adjusted, thereby effectively solving the problem that the existing intelligent heating return water control system cannot realize centralized intelligent control and cannot timely discover and handle the heating return water difference during the operation of the equipment.

[0101] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0102] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention without departing from the principles and intent of the present invention.

Claims

1. An intelligent heating return water control method, characterized in that: include: Obtain the historical operating status of the heating system and the historical heating return water characteristics of its corresponding generator group; Evaluate the historical operating status of the heating system and select the historical heating return water feature group whose historical operating status of the heating system meets the needs of users; Based on the heating return water feature group of the generator group, a heating return water feature prediction model is constructed and trained to predict the heating water outlet features of the corresponding heating system; Acquire a first heating return water characteristic of the current generator group, and predict a first water outlet characteristic of the generator group based on the first heating return water characteristic and the heating return water characteristic prediction model; The first outlet water characteristics include outlet heating water temperature parameters and outlet heating water flow parameters at different time nodes; Determining a first control strategy for controlling the heating system based on the first water outlet characteristic, and controlling the operation of the heating system based on the first control strategy; After a first preset time period after the heating system has been running according to the first control strategy, a current operating state of the heating system is obtained, and based on the current operating state, current heating return water characteristics of the generator group are determined, wherein the heating return water characteristics include heating return water temperature parameters and heating return water flow parameters at different time nodes; Analyze the current heating return water characteristics of the generator group to determine the first difference characteristics of the heating return water characteristics corresponding to the current heating return water characteristics and the predicted heating water outlet characteristics; Based on the first difference feature, an optimal control strategy for the heating system is determined, and the first control strategy is adjusted based on the optimal control strategy.

2. The intelligent heating return water control method according to claim 1 is characterized in that: The method for screening out a historical heating return water feature group whose historical operating state of the heating system meets the user's needs comprises: Obtain historical operation data of the heating system and preprocess the historical operation data to remove abnormal values, missing values ​​and duplicate values; Extracting the pre-treated heating return water temperature parameters, heating return water flow parameters, heating outlet water temperature parameters and heating outlet water flow parameters; The heating outlet water temperature parameters and heating outlet water flow parameters as well as the corresponding heating return water temperature parameters and heating return water flow parameters are analyzed, and the heating return water characteristics that meet user needs are classified to obtain a historical heating return water characteristic group.

3. The intelligent heating return water control method according to claim 1 is characterized in that: The historical operation status includes historical heating return water characteristics and historical heating water outlet characteristics. The method for constructing and training a heating return water characteristic prediction model based on the heating return water characteristic group of the generator group includes: Acquire the historical heating return water characteristics as model input data; Acquiring the historical heating water outlet characteristics as model output data; Constructing a heating return water characteristic prediction model based on the model input data, the model output data and a preset neural network model; A plurality of groups of the model input data and the model output data are obtained as model training data, and the heating return water characteristic prediction model is trained to obtain the heating return water characteristic prediction model.

4. The intelligent heating return water control method according to claim 3 is characterized in that: The method for predicting the first water output characteristic of the generator group based on the first heating return water characteristic and the heating return water characteristic prediction model includes: Acquire a first heating return water characteristic of the generator group according to a first operating state of the heating system, wherein the first heating return water characteristic comprises a first heating return water temperature parameter and a first heating return water flow parameter of the generator group; The first heating return water temperature parameter and the first heating return water flow parameter are input into the heating return water characteristic prediction model as model input data to obtain the first heating outlet water characteristic of the generator group, wherein the first heating outlet water characteristic includes the first heating outlet water temperature parameter and the first heating outlet water flow parameter of the generator group, and the first heating outlet water temperature parameter and the first heating outlet water flow parameter of each unit in the generator group are the same.

5. The intelligent heating return water control method according to claim 1 is characterized in that: The method for determining a first control strategy for controlling a heating system based on a first water outlet characteristic comprises: A plurality of valve opening-heating water outlet flow parameter interval correspondence relationships are preset, and the plurality of valve opening-heating water outlet flow parameter interval correspondence relationships are associated with a plurality of valve openings for each heating water outlet flow parameter interval of the heating system; The first heating outlet water flow parameter predicted by the heating return water characteristic prediction model is obtained, and based on the mapping relationship between the heating outlet water flow parameter interval to which the first heating outlet water flow parameter belongs and the corresponding relationship between the valve opening and the heating outlet water flow parameter interval, the opening of the current valves of the heating system is determined.

6. The intelligent heating return water control method according to claim 1 is characterized in that: The method for determining the first difference characteristic of the heating return water characteristic corresponding to the current heating return water characteristic and the predicted heating outlet water characteristic comprises: Acquire predicted water discharge characteristics, and determine the current control strategy for controlling the heating system based on the predicted water discharge characteristics, and after controlling the operation of the heating system for a first preset time period based on the current control strategy, determine the corresponding heating return water characteristics of the heating system at this time according to the overall performance state of the heating system, and determine the heating return water temperature parameters at different time points based on the heating return water characteristics; Obtain the optimal historical heating return water characteristics corresponding to the predicted water outlet characteristics, and determine the historical heating return water temperature parameters at different time points based on the historical heating return water characteristics; Compare and analyze the current heating return water temperature parameter with the historical heating return water temperature parameter to obtain several first parameter differences; Determining a first degree of difference based on a plurality of first parameter differences; If the first difference degree = 0, continue to control the operation of the heating system based on the current control strategy; If the first difference degree is greater than 0, the second water outlet temperature parameter is determined based on the current heating return water temperature parameter, and then the second control strategy is determined and the operation of the heating system is controlled based on the second control strategy.

7. The intelligent heating return water control method according to claim 6 is characterized in that: The expression for determining the first difference degree based on the first parameter differences is: Among them, η1 is the first difference degree of the current heating return water temperature parameter relative to the optimal historical heating return water temperature parameter, λ n is the weight coefficient of the parameter difference between the heating return water temperature parameter at the nth time point and the historical heating return water temperature parameter, t l-n is the current heating return water temperature parameter at the nth time point, t h-n It is the historical heating return water temperature parameter at the nth time point.

8. An intelligent heating return water control system, characterized in that: It includes prediction module, data acquisition and communication module, control center and execution module; The prediction module is used to obtain historical operation data of the heating system, build and train a heating return water characteristic prediction model based on the historical operation data, and predict corresponding heating return water outlet parameters; The data acquisition and communication module is used to collect data in real time, obtain the current operating status of the heating system, determine the current heating return water characteristics of each unit based on the current operating status, and send the current operating status to the control center through the communication module; The control center includes an intelligent algorithm platform, which optimizes the heating return water outlet parameters predicted by the current heating return water characteristics and the heating return water characteristics prediction model, and determines the optimized heating return water outlet parameters, wherein the heating return water outlet parameters include the opening and closing degree of each valve and the temperature of each unit; The execution module includes a plurality of valves and a heat exchanger, which are used to control the opening of the plurality of valves to adjust the flow rate of the heating return water of each unit, and control the heat exchanger to adjust the heat exchange between hot water and cold water in the heating system to adjust the heating return water temperature of each unit.

Images