Intelligent heat supply integrated management and control method and system

Abstract

The invention discloses an intelligent heat supply integrated management and control method and system, and relates to the technical field of heat supply of heat supply networks. The method comprises the following steps: acquiring historical operation data of a heat supply network, preprocessing the historical operation data, screening out abnormal data in the historical operation data, generating a historical operation data table, constructing and generating a historical operation data set, dynamically generating a plurality of data learning groups for the historical operation data set, and calculating heat output ratio data of each data learning group; each data learning group takes the heat output ratio as a dependent variable, takes other data as independent variables, uses a multiple linear regression model to fit a plurality of independent variables and a dependent variable, constructs a historical operation data analysis model, adjusts the operation parameters of the heat supply network, constructs and generates a first heat supply network balance adjustment strategy, and stores the first heat supply network balance adjustment strategy; and real-time operation data of the heat supply network are obtained, a real-time operation data analysis model is constructed, the first heat supply network balance adjustment strategy is corrected, and a second heat supply network balance adjustment strategy is generated.

Description

Technical Field

[0001] The present invention relates to the field of heating network heating technology, and in particular to a smart heating integrated management and control method and system. Background Art

[0002] In recent years, with the continuous development and promotion of control and information technology, the heating network system has basically realized intelligent control, that is, the central control center can remotely measure the operation status of the heating network and control and adjust the basic operations of the heating network parameters, and has the basic conditions for intelligent control. However, in general, the heating network regulation still lacks scientific intelligent management and control methods and efficient regulation methods, and for the sake of "heating stability", it often chooses to sacrifice economic efficiency, resulting in a generally low heat output ratio, and heating companies are under great pressure to survive.

[0003] In order to solve the above problems, there is an urgent need for an intelligent integrated heating management and control method that can improve the heat output ratio of the heating network and perform real-time regulation of the heating network. This intelligent integrated heating management and control method is of great significance to the development of the field of heating network heating technology. Summary of the invention

[0004] The purpose of the present invention is to provide a smart integrated heating management and control method and system, which can effectively improve the heat output ratio and real-time control capability of the heating network during heating.

[0005] The technical solution adopted by the present invention is: a smart heating integrated control method, comprising: Obtain historical operation data of the heating network, pre-process the historical operation data, filter out abnormal data in the historical operation data, and generate a historical operation data table; According to the historical operation data table, the operation data collected at the same time node are integrated to construct a historical operation data set; For the historical operation data set, several data learning groups are dynamically generated, and the heat output ratio data of each data learning group is calculated. Each data learning group uses the heat output ratio as the dependent variable and other data as the independent variable. The multivariate linear regression model is used to fit multiple independent variables and one dependent variable to build a historical operation data analysis model; According to the historical operation data analysis model, the operation parameters of the heating network are adjusted to construct and generate the first heat network balance adjustment strategy; Acquire the real-time operation data of the heating network, build a real-time operation data analysis model, modify the first heating network balancing adjustment strategy according to the real-time operation data analysis model, and generate a second heating network balancing adjustment strategy.

[0006] In some embodiments of the present application, a method for preprocessing historical operation characteristic data, filtering out abnormal data in the historical operation characteristic data, and generating a historical operation characteristic data table includes: Use cluster analysis to filter out abnormal data in historical operation characteristic data; Conduct preliminary screening of the running parameters of the screened samples based on expert experience; Perform variance screening on the sample operating parameters after preliminary screening, and eliminate sample operating parameters whose variance is less than a preset variance threshold; The sample operating parameters after variance screening are subjected to correlation screening, and the sample operating parameters whose correlation coefficients are greater than a preset correlation coefficient threshold are determined as target operating parameters.

[0007] In some embodiments of the present application, a method for dynamically generating a plurality of data learning groups for a historical operation feature data set includes: Determine the number of data learning groups to be generated based on the historical operation feature data set, perform model training on a set of data in the historical operation feature data set, generate data learning groups, and evaluate the data learning groups; Retrain with multiple sets of data to generate new data learning sets.

[0008] In some embodiments of the present application, each data learning group uses the heat output ratio as a dependent variable and other data as independent variables, and uses a multivariate linear regression model to fit multiple independent variables and one dependent variable. The method for constructing a historical operation data analysis model includes: Using SPSS and applying the multiple regression equation, we selected variables based on the correlation between various data and the heat output ratio. The selected parameters are: heating network pressure, heating network flow, valve opening, and established a historical operation data analysis model. The historical operation data analysis model is solved to obtain the linear relationship between the heat output ratio and these three parameters.

[0009] In some embodiments of the present application, the heating network operating parameters include: The pressure, flow, valve opening data of the heating network, these operating parameters are used as the control parameters of the system.

[0010] In some embodiments of the present application, the method of adjusting the operation parameters of the heating network according to the historical operation data analysis model and constructing and generating the first heating network balance adjustment strategy includes: According to the historical operation data analysis model, based on the linear relationship between the heat output ratio and the heating network pressure, heating network flow, and valve opening, these three parameters are adjusted up and down, and the adjustment amount is used as the first heating network balance adjustment strategy.

[0011] In some embodiments of the present application, according to the historical operation data analysis model, the expression for adjusting the operation parameters of the heating network is: ; in, is the heat output ratio demand value, is the heat network pressure parameter, is the heat network flow parameter, is the valve opening parameter, , , The weight conversion coefficient is artificially configured based on the linear relationship between the heat output ratio and the three parameters of heat network pressure, heat network flow, and valve opening. The weight conversion coefficients of the three parameters are adjusted up and down to make the heat output ratio When the demand value is reached, the adjustment amount is used as the first heat network balance regulation strategy.

[0012] In some embodiments of the present application, it also includes: Based on the current operating data analysis model of the heating network, the balancing adjustment strategy of the second heating network is optimized in real time.

[0013] In some embodiments of the present application, the method for optimizing the second heat network balance adjustment strategy in real time according to the current operation data analysis model of the heat supply network includes: Obtain the current operation data of the heating network, build an analysis model for the current operation data, and optimize the balance adjustment strategy of the second heating network in real time based on the current operation data analysis model; When the second heating network balancing regulation strategy is optimized in real time, the heating network pressure, flow rate and valve opening of the second heating network balancing regulation strategy are adjusted up and down.

[0014] In some embodiments of the present application, a smart heating integrated management and control system is also disclosed, including: A historical operation data table generation module is used to obtain historical operation data of the heating network, pre-process the historical operation data, filter out abnormal data in the historical operation data, and generate a historical operation data table; The historical operation data analysis model generation module is used to integrate the operation data collected at the same time node according to the historical operation data table, build a historical operation data set, and dynamically generate several data learning groups for the historical operation data set, and calculate the heat output ratio data of each data learning group. Each data learning group uses the heat output ratio as the dependent variable and other data as the independent variable. The multivariate linear regression model is used to fit multiple independent variables and one dependent variable to build a historical operation data analysis model; A first heat network balance adjustment strategy generation module is used to adjust the heat supply network operation parameters according to the historical operation data analysis model, and construct and generate the first heat network balance adjustment strategy; The second heat network balancing adjustment strategy generation module is used to obtain the real-time operation data of the heat supply network, build a real-time operation data analysis model, and modify the first heat network balancing adjustment strategy according to the real-time operation data analysis model to generate the second heat network balancing adjustment strategy; The real-time optimization module is used to optimize the second heating network balance adjustment strategy in real time according to the current operating data analysis model of the heating network.

[0015] The beneficial effects of the present invention are: 1. By using the multivariate linear regression model to fit multiple independent variables and one dependent variable, a historical operation data analysis model is constructed, and various parameters are adjusted up and down to generate the first heat network balance adjustment strategy, so that the heating network can quickly achieve energy-saving goals.

[0016] 2. By acquiring the current operating data of the heating network, building a current operating data analysis model, and optimizing the balance adjustment strategy of the second heating network in real time, the real-time regulation capability of the heating network is effectively improved.

[0017] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the steps of a smart heating integrated control method in an embodiment of the present application; Figure 2 This is a schematic diagram of the module connections of an intelligent integrated heating management and control system in an embodiment of the present application. DETAILED DESCRIPTION

[0019] The technical solution of the present invention is further described below through the accompanying drawings and embodiments.

[0020] The following will be combined with the accompanying drawings and specific embodiments to clearly and completely describe the technical solution of the present invention. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and cannot be understood as limiting the scope of protection of the present invention. Those skilled in the art in this field can make some non-essential improvements and adjustments based on the content of the present invention described below. In the present invention, unless otherwise clearly specified and limited, the technical terms used in this application should be the common meanings understood by the technical personnel of the present invention.

[0021] Example: The purpose of the present invention is to provide a smart heating integrated control method and system.

[0022] A smart heating integrated control method, see Figure 1 ,include: S1: Obtain historical operation data of the heating network, pre-process the historical operation data, filter out abnormal data in the historical operation data, and generate a historical operation data table.

[0023] It should be understood that the historical operation data of the heating network refers to the heating network pressure, heating network flow, valve opening and other heating network operation parameters in the historical operation of the heating network. These parameters can intuitively reflect the historical operation of the heating network, and the heat output ratio data can be calculated based on these parameters.

[0024] S2: According to the historical operation data table, the operation data collected at the same time node are integrated to construct a historical operation data set; For the historical operation data set, several data learning groups are dynamically generated, and the heat output ratio data of each data learning group is calculated. Each data learning group uses the heat output ratio as the dependent variable and other data as independent variables. A multivariate linear regression model is used to fit multiple independent variables and one dependent variable to construct a historical operation data analysis model.

[0025] It is important to understand that the heat output ratio data refers to the ratio of the heat output of the heating network to the heat input of the heating network, usually expressed as a percentage, which can be used to measure the energy efficiency of the heating network. The multiple regression equation is a statistical model used to describe the relationship between two or more independent variables and a dependent variable. It can be used to predict the value of the dependent variable or to test whether the independent variable has a significant impact on the dependent variable.

[0026] S3: According to the historical operation data analysis model, the operation parameters of the heating network are adjusted to construct and generate the first heat network balance adjustment strategy.

[0027] It needs to be understood that adjusting the operating parameters of the heating network refers to adjusting the heating network pressure, heating network flow, and valve opening parameters. These parameters will affect the output heat ratio of the heating network. By adjusting these parameters to increase the output heat ratio, the energy-saving goal can be achieved.

[0028] S4: Acquire the real-time operation data of the heating network, construct a real-time operation data analysis model, and modify the first heating network balancing adjustment strategy according to the real-time operation data analysis model to generate a second heating network balancing adjustment strategy.

[0029] In some embodiments of the present application, a method for preprocessing historical operation characteristic data, filtering out abnormal data in the historical operation characteristic data, and generating a historical operation characteristic data table includes: Use cluster analysis to filter out abnormal data in historical operation characteristic data; Conduct preliminary screening of the running parameters of the screened samples based on expert experience; Perform variance screening on the sample operating parameters after preliminary screening, and eliminate sample operating parameters whose variance is less than a preset variance threshold; The sample operating parameters after variance screening are subjected to correlation screening, and the sample operating parameters whose correlation coefficients are greater than a preset correlation coefficient threshold are determined as target operating parameters.

[0030] In some embodiments of the present application, a method for dynamically generating a plurality of data learning groups for a historical operation feature data set includes: Determine the number of data learning groups to be generated based on the historical operation feature data set, perform model training on a set of data in the historical operation feature data set, generate data learning groups, and evaluate the data learning groups; Retrain with multiple sets of data to generate new data learning sets.

[0031] In some embodiments of the present application, each data learning group uses the heat output ratio as a dependent variable and other data as independent variables, and uses a multivariate linear regression model to fit multiple independent variables and one dependent variable. The method for constructing a historical operation data analysis model includes: Using SPSS and applying the multiple regression equation, we selected variables based on the correlation between various data and the heat output ratio. The selected parameters are: heating network pressure, heating network flow, valve opening, and established a historical operation data analysis model. The historical operation data analysis model is solved to obtain the linear relationship between the heat output ratio and these three parameters.

[0032] In some embodiments of the present application, the heating network operating parameters include: The pressure, flow, valve opening data of the heating network, these operating parameters are used as the control parameters of the system.

[0033] In some embodiments of the present application, the method of adjusting the operation parameters of the heating network according to the historical operation data analysis model and constructing and generating the first heating network balance adjustment strategy includes: According to the historical operation data analysis model, based on the linear relationship between the heat output ratio and the heating network pressure, heating network flow, and valve opening, these three parameters are adjusted up and down, and the adjustment amount is used as the first heating network balance adjustment strategy.

[0034] In some embodiments of the present application, according to the historical operation data analysis model, the expression for adjusting the operation parameters of the heating network is: ; in, is the heat output ratio demand value, is the heat network pressure parameter, is the heat network flow parameter, is the valve opening parameter, , , The weight conversion coefficient is artificially configured based on the linear relationship between the heat output ratio and the three parameters of heat network pressure, heat network flow, and valve opening. The weight conversion coefficients of the three parameters are adjusted up and down to make the heat output ratio When the demand value is reached, the adjustment amount is used as the first heat network balance regulation strategy.

[0035] In some embodiments of the present application, it also includes: Based on the current operating data analysis model of the heating network, the balancing adjustment strategy of the second heating network is optimized in real time.

[0036] In some embodiments of the present application, the method for optimizing the second heat network balance adjustment strategy in real time according to the current operation data analysis model of the heat supply network includes: Obtain the current operation data of the heating network, build an analysis model for the current operation data, and optimize the balance adjustment strategy of the second heating network in real time based on the current operation data analysis model; When the second heating network balancing regulation strategy is optimized in real time, the heating network pressure, flow rate and valve opening of the second heating network balancing regulation strategy are adjusted up and down.

[0037] In some embodiments of the present application, a smart heating integrated management and control system is also disclosed, see Figure 2 , including: a historical operation data table generation module, a historical operation data analysis model generation module, a first heat network balance adjustment strategy generation module, a second heat network balance adjustment strategy generation module, and a real-time optimization module.

[0038] The historical operation data table generation module is used to obtain the historical operation data of the heating network, pre-process the historical operation data, filter out abnormal data in the historical operation data, and generate a historical operation data table; The historical operation data analysis model generation module is used to integrate the operation data collected at the same time node according to the historical operation data table, construct and generate a historical operation data set, and dynamically generate a number of data learning groups for the historical operation data set, and calculate the heat output ratio data of each data learning group. Each data learning group uses the heat output ratio as a dependent variable and other data as independent variables, and uses a multivariate linear regression model to fit multiple independent variables and one dependent variable to construct a historical operation data analysis model; The first heat network balance adjustment strategy generation module is used to adjust the heat supply network operation parameters according to the historical operation data analysis model to construct and generate the first heat network balance adjustment strategy; The second heat network balancing adjustment strategy generating module is used to obtain the real-time operation data of the heat supply network, build a real-time operation data analysis model, and modify the first heat network balancing adjustment strategy according to the real-time operation data analysis model to generate the second heat network balancing adjustment strategy; The real-time optimization module is used to optimize the second heating network balance adjustment strategy in real time according to the current operation data analysis model of the heating network.

[0039] The beneficial effects of the present invention are: 1. By using the multivariate linear regression model to fit multiple independent variables and one dependent variable, a historical operation data analysis model is constructed, and various parameters are adjusted up and down to generate the first heat network balance adjustment strategy, so that the heating network can quickly achieve energy-saving goals.

[0040] 2. By acquiring the current operating data of the heating network, building a current operating data analysis model, and optimizing the balance adjustment strategy of the second heating network in real time, the real-time regulation capability of the heating network is effectively improved.

[0041] Finally, it should be noted that 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 preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

Claims

1. A smart heating integrated management and control method, characterized in that: include: Obtain historical operation data of the heating network, pre-process the historical operation data, filter out abnormal data in the historical operation data, and generate a historical operation data table; According to the historical operation data table, the operation data collected at the same time node are integrated to construct a historical operation data set; For the historical operation data set, several data learning groups are dynamically generated, and the heat output ratio data of each data learning group is calculated. Each data learning group uses the heat output ratio as the dependent variable and other data as the independent variable. The multivariate linear regression model is used to fit multiple independent variables and one dependent variable to build a historical operation data analysis model; According to the historical operation data analysis model, the operation parameters of the heating network are adjusted to construct and generate the first heat network balance adjustment strategy; Acquire the real-time operation data of the heating network, build a real-time operation data analysis model, modify the first heating network balancing adjustment strategy according to the real-time operation data analysis model, and generate a second heating network balancing adjustment strategy.

2. A smart heating integrated management and control method according to claim 1, characterized in that: The method of preprocessing the historical operation characteristic data, filtering out abnormal data in the historical operation characteristic data, and generating a historical operation characteristic data table includes: Use cluster analysis to filter out abnormal data in historical operation characteristic data; Conduct preliminary screening of the running parameters of the screened samples based on expert experience; Perform variance screening on the sample operating parameters after preliminary screening, and eliminate sample operating parameters whose variance is less than a preset variance threshold; The sample operating parameters after variance screening are subjected to correlation screening, and the sample operating parameters whose correlation coefficients are greater than a preset correlation coefficient threshold are determined as target operating parameters.

3. The intelligent integrated heating management and control method according to claim 1 is characterized in that: For the historical operation feature data set, the method of dynamically generating several data learning groups includes: Determine the number of data learning groups to be generated based on the historical operation feature data set, perform model training on a set of data in the historical operation feature data set, generate data learning groups, and evaluate the data learning groups; Retrain with multiple sets of data to generate new data learning sets.

4. The intelligent integrated heating management and control method according to claim 1 is characterized in that: Each data learning group uses the heat output ratio as the dependent variable and other data as the independent variables. The multivariate linear regression model is used to fit multiple independent variables and one dependent variable. The method of constructing the historical operation data analysis model includes: Using SPSS and applying the multiple regression equation, we selected variables based on the correlation between various data and the heat output ratio. The selected parameters are: heating network pressure, heating network flow, valve opening, and established a historical operation data analysis model. The historical operation data analysis model is solved to obtain the linear relationship between the heat output ratio and these three parameters.

5. The intelligent integrated heating management and control method according to claim 1 is characterized in that: The heating network operation parameters include: The pressure, flow, valve opening data of the heating network, these operating parameters are used as the control parameters of the system.

6. The intelligent integrated heating management and control method according to claim 1 is characterized in that: According to the historical operation data analysis model, the method for adjusting the operation parameters of the heating network and constructing and generating the first heat network balance adjustment strategy includes: According to the historical operation data analysis model, based on the linear relationship between the heat output ratio and the heating network pressure, heating network flow, and valve opening, these three parameters are adjusted up and down, and the adjustment amount is used as the first heating network balance adjustment strategy.

7. The intelligent integrated heating management and control method according to claim 1 is characterized in that: According to the historical operation data analysis model, the expression for adjusting the operation parameters of the heating network is: ； in, is the heat output ratio demand value, is the heat network pressure parameter, is the heat network flow parameter, is the valve opening parameter, , , The weight conversion coefficient is artificially configured based on the linear relationship between the heat output ratio and the three parameters of heat network pressure, heat network flow, and valve opening. The weight conversion coefficients of the three parameters are adjusted up and down to make the heat output ratio When the demand value is reached, the adjustment amount is used as the first heat network balance regulation strategy.

8. The intelligent integrated heating management and control method according to claim 1 is characterized in that: Also includes: Based on the current operating data analysis model of the heating network, the balancing adjustment strategy of the second heating network is optimized in real time.

9. The intelligent integrated heating management and control method according to claim 8, characterized in that: According to the current operation data analysis model of the heating network, the method for real-time optimization of the balance adjustment strategy of the second heating network includes: Obtain the current operation data of the heating network, build an analysis model for the current operation data, and optimize the balance adjustment strategy of the second heating network in real time based on the current operation data analysis model; When the second heating network balancing regulation strategy is optimized in real time, the heating network pressure, flow rate and valve opening of the second heating network balancing regulation strategy are adjusted up and down.

10. A smart integrated heating management and control system, characterized in that: include: A historical operation data table generation module is used to obtain historical operation data of the heating network, pre-process the historical operation data, filter out abnormal data in the historical operation data, and generate a historical operation data table; The historical operation data analysis model generation module is used to integrate the operation data collected at the same time node according to the historical operation data table, build a historical operation data set, and dynamically generate several data learning groups for the historical operation data set, and calculate the heat output ratio data of each data learning group. Each data learning group uses the heat output ratio as the dependent variable and other data as the independent variable. The multivariate linear regression model is used to fit multiple independent variables and one dependent variable to build a historical operation data analysis model; A first heat network balance adjustment strategy generation module is used to adjust the heat supply network operation parameters according to the historical operation data analysis model, and construct and generate the first heat network balance adjustment strategy; The second heat network balancing adjustment strategy generation module is used to obtain the real-time operation data of the heat supply network, build a real-time operation data analysis model, and modify the first heat network balancing adjustment strategy according to the real-time operation data analysis model to generate the second heat network balancing adjustment strategy; The real-time optimization module is used to optimize the second heating network balance adjustment strategy in real time according to the current operating data analysis model of the heating network.

Images