Circulating pump optimization adjustment method based on big data

Abstract

The invention discloses a circulating pump optimization adjustment method based on big data, and the method comprises the steps: obtaining historical adjustment logs under different target demands, and the historical adjustment logs comprise historical operation data and feature historical adjustment data; according to the association degree of the historical operation data and the performance indexes under the same target demand, determining associated operation data of the plurality of performance indexes, and determining performance evaluation values of the corresponding performance indexes; generating a comprehensive evaluation value according to the plurality of performance evaluation values, setting an application evaluation value corresponding to the characteristic historical adjustment data in the historical adjustment log according to the comprehensive evaluation value, and screening out preferred adjustment data of the same target demand; the optimization adjustment model corresponding to the target requirement is constructed according to the optimization adjustment data, the real-time optimization adjustment data is determined, the optimization instruction is generated for the real-time adjustment data according to the real-time optimization adjustment data, optimization operation of the circulating pump is achieved, and the adjustment efficiency of the circulating pump and the operation efficiency of the heat exchange station are improved.

Description

Technical Field

[0001] The present application relates to the technical field of circulation pump regulation, and in particular to a circulation pump optimization regulation method based on big data. Background Art

[0002] Central heating with coal as the main fuel is the main form of winter heating in northern my country. Energy conservation and emission reduction in the heating industry have good social and economic benefits. At present, the circulating pump of the heat exchange station generally adopts fixed frequency or manual adjustment. There is no effective basis for scientifically adjusting the control parameters of the circulating pump, and the optimized operation of the circulating pump cannot be achieved, thereby reducing the adjustment efficiency of the circulating pump and the operation efficiency of the heat exchange station. Summary of the invention

[0003] In order to solve the above technical problems, the present application provides a circulation pump optimization and adjustment method based on big data, which determines the related operating data of multiple performance indicators, and determines the performance evaluation value and comprehensive evaluation value of each performance indicator. The optimization adjustment data for each target requirement is screened out according to the comprehensive evaluation value, and an optimization adjustment model is constructed to generate optimization instructions for real-time adjustment data, thereby realizing the optimized operation of the circulation pump and improving the adjustment efficiency of the circulation pump and the operation efficiency of the heat exchange station.

[0004] In some embodiments of the present application, a circulation pump optimization adjustment method based on big data is provided, comprising:

[0005] Obtaining historical adjustment logs under different target requirements, wherein the historical adjustment logs include historical operation data and characteristic historical adjustment data;

[0006] Determine the associated operating data of multiple performance indicators according to the degree of association between historical operating data and performance indicators under the same target demand, and determine the performance evaluation value of the corresponding performance indicator according to the corresponding associated operating data;

[0007] Generate a comprehensive evaluation value according to multiple performance evaluation values, set an application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log according to the comprehensive evaluation value, and screen out the preferred adjustment data for the same target requirement;

[0008] An optimization adjustment model corresponding to the target demand is constructed according to the optimization adjustment data, and the real-time optimization adjustment data is determined, and optimization instructions are generated for the real-time adjustment data according to the real-time optimization adjustment data.

[0009] In some embodiments of the present application, target operation data is selected from each historical adjustment log under the same target demand as a dependent variable, and historical adjustment data of the circulating pump in the corresponding historical adjustment log is selected as an independent variable, wherein the target operation data includes temperature, pressure, heating load and demand flow;

[0010] Construct a change relationship curve based on the independent variable and the dependent variable, and obtain a matching composite curve after piecewise curve fitting;

[0011] Screen out the first change feature of the change relationship curve and the second change feature of the composite curve, conduct a comprehensive analysis on the first change feature and the second change feature, and generate historical adjustment data that is strongly correlated with the target operation data in the corresponding historical adjustment log;

[0012] The historical adjustment data that are strongly correlated with the target operation data in multiple historical adjustment logs of the same target demand are compared, and the historical adjustment data whose appearance ratio is greater than a preset appearance ratio threshold is set as characteristic historical adjustment data.

[0013] In some embodiments of the present application, determining associated operating data of a plurality of performance indicators includes:

[0014] A plurality of performance indicators are preset, and the historical adjustment log includes a historical evaluation value of each performance indicator;

[0015] Obtain historical operation data of different historical adjustment logs for the same target demand and historical evaluation values ​​of multiple performance indicators, establish a time reference line according to the target duration of the same target demand, and set analysis nodes according to preset time intervals;

[0016] Based on each analysis node on the time reference line, historical operation data of multiple historical adjustment logs corresponding to target requirements and historical evaluation values ​​of different performance indicators are collected;

[0017] Calculate the dependency change degree between the historical operation data and the historical evaluation values ​​of different performance indicators, and generate the correlation degree between the historical operation data and the corresponding performance indicators under the current target demand based on the dependency change degree difference value whose dependency change degree is greater than the preset dependency change degree threshold and the number of analysis nodes whose dependency change degree is greater than the preset dependency change degree threshold;

[0018] A correlation degree threshold is preset, and historical operation data with a correlation degree greater than the preset correlation degree threshold is set as the correlation operation data of the corresponding performance indicator.

[0019] In some embodiments of the present application, the calculation formula of the degree of association is:

[0020]

[0021] Among them, H is the degree of association, r is the degree of association conversion coefficient, n is the number of analysis nodes whose degree of dependency change is greater than the preset dependency change threshold, m is the total number of analysis nodes, Yi is the degree of dependency change at the i-th analysis node whose degree of dependency change is greater than the preset dependency change threshold, and y0 is the dependency change threshold.

[0022] In some embodiments of the present application, determining a performance evaluation value of a corresponding performance indicator according to corresponding associated operation data includes:

[0023] Presetting a plurality of standard associated operating data intervals of associated operating data of each performance indicator, and each standard associated operating data interval is configured with a corresponding preset operating state coefficient;

[0024] The associated operating data are compared with the corresponding standard associated operating data interval to obtain the standard associated operating data interval in which each associated operating data is located, and a preset operating state coefficient of the standard associated operating data interval is set as the operating state coefficient of the corresponding associated operating data, and a performance evaluation value of the corresponding performance indicator is generated according to the operating state coefficients of multiple associated operating data and the weight coefficients of the corresponding associated operating data.

[0025] In some embodiments of the present application, a comprehensive evaluation value is generated according to multiple performance evaluation values, including:

[0026] Analyze multiple performance indicators based on the hierarchical analysis method, and determine the first weight coefficient of each performance indicator according to the analysis results;

[0027] Constructing a first association structure diagram based on the logical relationship and influence relationship between the performance indicators, wherein the first association structure diagram takes the performance indicator with the greatest functional importance as the structure center, and sets a first connection distance based on the logical relationship and influence degree between the structure center and other performance indicators;

[0028] Preset multiple secondary performance indicators for each performance indicator;

[0029] Determine the importance coefficient of each secondary performance indicator based on the degree of influence of the secondary performance indicator of each performance indicator on the evaluation of the corresponding performance indicator, and construct a sub-association structure diagram of each performance indicator based on the internal dependency relationship of multiple secondary performance indicators of the same performance indicator, wherein the sub-association structure diagram takes the secondary performance indicator with the maximum importance coefficient as the sub-structure center, and sets the second connection distance according to the internal dependency degree of the secondary performance indicator;

[0030] Building a connection relationship of the sub-association structure graph based on the external dependency relationship between the secondary performance indicators of different performance indicators, and setting a third connection distance between the sub-association structure graphs according to the degree of external dependency;

[0031] Generate a compensation coefficient of the corresponding performance indicator according to the first connection distance, the second connection distance, the third connection distance and the number of nodes involved in each performance indicator;

[0032] Generate a comprehensive weight coefficient of the corresponding performance indicator according to the compensation coefficient and the first weight coefficient;

[0033] Generate a comprehensive evaluation value of the historical operation data in the corresponding historical adjustment log according to the comprehensive weight coefficients of the multiple performance indicators and the performance evaluation value;

[0034] The calculation formula of the comprehensive evaluation value is:

[0035]

[0036] Among them, Z is the comprehensive evaluation value, c is the total number of performance indicators, ks is the performance evaluation value of the sth performance indicator, and cs is the comprehensive weight coefficient of the sth performance indicator.

[0037] In some embodiments of the present application, setting the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log according to the comprehensive evaluation value includes:

[0038] Presetting a first preset comprehensive evaluation value interval, a second preset comprehensive evaluation value interval, a third preset comprehensive evaluation value interval and a fourth preset comprehensive evaluation value interval;

[0039] When the comprehensive evaluation value is within the first preset comprehensive evaluation value interval, the first preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log;

[0040] When the comprehensive evaluation value is within the second preset comprehensive evaluation value interval, the second preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log;

[0041] When the comprehensive evaluation value is within the third preset comprehensive evaluation value interval, the third preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log;

[0042] When the comprehensive evaluation value is in the fourth preset comprehensive evaluation value interval, the fourth preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log.

[0043] In some embodiments of the present application, building an optimization adjustment model corresponding to the target demand according to the optimization adjustment data, and determining the real-time optimization adjustment data, includes:

[0044] Setting the characteristic adjustment data corresponding to the fourth preset application evaluation value in each target requirement as the optimization adjustment data corresponding to the target requirement;

[0045] Obtain historical operation data corresponding to the target demand according to the optimized adjustment data, determine whether the data interval of the historical operation data corresponding to the target demand covers the preset data interval, and if so, generate a training data set according to the historical operation data corresponding to the target demand and the optimized adjustment data;

[0046] If not, determine the uncovered data interval according to the preset data interval and the data interval of the historical operation data, and select a corresponding correction scheme according to the interval length of the uncovered data interval to correct the optimized adjustment data of the adjacent data, wherein the correction scheme includes correction coefficients of different correction spans, and the correction coefficients include proportional coefficients, integral coefficients and differential coefficients;

[0047] According to a plurality of optimized adjustment data and historical operation data of the data interval not covered by the corresponding correction scheme, a training data set is constructed in combination with the optimized adjustment data and historical operation data of the data interval covered;

[0048] Construct an optimization adjustment model corresponding to the target requirements based on the training data set;

[0049] Obtain real-time target demand and corresponding real-time operation data, and input them into the optimization adjustment model corresponding to the target demand to obtain real-time optimization adjustment data.

[0050] In some embodiments of the present application, generating an optimization instruction for the real-time adjustment data according to the real-time optimization adjustment data includes:

[0051] Generating an optimization instruction for the corresponding real-time adjustment data according to the real-time optimization adjustment data, wherein the optimization instruction includes the optimization duration and the change amount of the operation data after optimization;

[0052] Determine the optimization efficiency of the corresponding optimization instruction according to the optimization time and the change in the running data after optimization;

[0053] If the optimization efficiency is less than the preset optimization efficiency threshold, the real-time optimization adjustment data and the optimization instructions are re-determined.

[0054] Compared with the prior art, the circulating pump optimization and adjustment method based on big data in the embodiment of the present application has the following beneficial effects:

[0055] By determining the associated operating data of multiple performance indicators, and determining the performance evaluation value and comprehensive evaluation value of each performance indicator, the optimized adjustment data for each target demand is screened out according to the comprehensive evaluation value, and an optimized adjustment model is constructed to generate optimization instructions for real-time adjustment data, thereby achieving optimized operation of the circulation pump and improving the adjustment efficiency of the circulation pump and the operation efficiency of the heat exchange station. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 It is a flow chart of a circulation pump optimization and adjustment method based on big data in the preferred embodiment of the present application. DETAILED DESCRIPTION

[0057] 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.

[0058] 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.

[0059] 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.

[0060] 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.

[0061] like Figure 1 As shown, a circulating pump optimization and adjustment method based on big data in a preferred embodiment of the present application includes:

[0062] Step S101: Acquire historical adjustment logs under different target requirements, wherein the historical adjustment logs include historical operation data and characteristic historical adjustment data;

[0063] Step S102: determining associated operating data of a plurality of performance indicators according to the degree of association between historical operating data and performance indicators under the same target requirement, and determining performance evaluation values ​​of corresponding performance indicators according to the corresponding associated operating data;

[0064] Step S103: Generate a comprehensive evaluation value according to the multiple performance evaluation values, set an application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log according to the comprehensive evaluation value, and screen out the preferred adjustment data for the same target requirement;

[0065] Step S104: construct an optimization adjustment model corresponding to the target demand according to the optimization adjustment data, determine the real-time optimization adjustment data, and generate optimization instructions for the real-time adjustment data according to the real-time optimization adjustment data.

[0066] In this embodiment, the target demand refers to the regulation demand instruction sent by the heat exchange system and received by the circulation pump, and the characteristic historical regulation data refers to the regulation data of the circulation pump associated with changes in the target operation data of the heat exchange system.

[0067] In this embodiment, by determining the associated operating data of multiple performance indicators, and determining the performance evaluation value and comprehensive evaluation value of each performance indicator, the optimized adjustment data for each target demand is screened out according to the comprehensive evaluation value, and an optimized adjustment model is constructed to generate optimization instructions for the real-time adjustment data, thereby realizing the optimized operation of the circulation pump and improving the adjustment efficiency of the circulation pump and the operating efficiency of the heat exchange station.

[0068] In some embodiments of the present application, target operation data is selected from each historical adjustment log under the same target demand as a dependent variable, and historical adjustment data of the circulating pump in the corresponding historical adjustment log is selected as an independent variable, wherein the target operation data includes temperature, pressure, heating load and demand flow;

[0069] Construct a change relationship curve based on the independent variable and the dependent variable, and obtain a matching composite curve after piecewise curve fitting;

[0070] Screen out the first change feature of the change relationship curve and the second change feature of the composite curve, conduct a comprehensive analysis on the first change feature and the second change feature, and generate historical adjustment data that is strongly correlated with the target operation data in the corresponding historical adjustment log;

[0071] The historical adjustment data that are strongly correlated with the target operation data in multiple historical adjustment logs of the same target demand are compared, and the historical adjustment data whose appearance ratio is greater than a preset appearance ratio threshold is set as characteristic historical adjustment data.

[0072] In this embodiment, the target operating data refers to the data used as a basis for adjusting the circulation pump in the heat exchange system, that is, an adjustment instruction is generated for the circulation pump according to the change of the target operating data. The first change feature and the second change feature are respectively used to represent the change trend of the correlation between the independent variable and the dependent variable in the change relationship curve and the composite curve, such as the degree of synchronous change, the direction of change and the time of synchronous change, so as to determine the characteristic adjustment data, reduce the amount of data analysis and processing, and screen out the adjustment data of the circulation pump that is strongly related to the operating efficiency and operating status of the heat exchange system, laying the foundation for the subsequent determination of the preferred adjustment data for the same target demand and the optimization of the adjustment model.

[0073] In some embodiments of the present application, determining associated operating data of a plurality of performance indicators includes:

[0074] A plurality of performance indicators are preset, and the historical adjustment log includes a historical evaluation value of each performance indicator;

[0075] Obtain historical operation data of different historical adjustment logs for the same target demand and historical evaluation values ​​of multiple performance indicators, establish a time reference line according to the target duration of the same target demand, and set analysis nodes according to preset time intervals;

[0076] Based on each analysis node on the time reference line, historical operation data of multiple historical adjustment logs corresponding to target requirements and historical evaluation values ​​of different performance indicators are collected;

[0077] Calculate the dependency change degree between the historical operation data and the historical evaluation values ​​of different performance indicators, and generate the correlation degree between the historical operation data and the corresponding performance indicators under the current target demand based on the dependency change degree difference value whose dependency change degree is greater than the preset dependency change degree threshold and the number of analysis nodes whose dependency change degree is greater than the preset dependency change degree threshold;

[0078] A correlation degree threshold is preset, and historical operation data with a correlation degree greater than the preset correlation degree threshold is set as the correlation operation data of the corresponding performance indicator.

[0079] In some embodiments of the present application, the calculation formula of the degree of association is:

[0080]

[0081] Among them, H is the degree of association, r is the degree of association conversion coefficient, n is the number of analysis nodes whose degree of dependency change is greater than the preset dependency change threshold, m is the total number of analysis nodes, Yi is the degree of dependency change at the i-th analysis node whose degree of dependency change is greater than the preset dependency change threshold, and y0 is the dependency change threshold.

[0082] In some embodiments of the present application, determining a performance evaluation value of a corresponding performance indicator according to corresponding associated operation data includes:

[0083] Presetting a plurality of standard associated operating data intervals of associated operating data of each performance indicator, and each standard associated operating data interval is configured with a corresponding preset operating state coefficient;

[0084] The associated operating data are compared with the corresponding standard associated operating data interval to obtain the standard associated operating data interval in which each associated operating data is located, and a preset operating state coefficient of the standard associated operating data interval is set as the operating state coefficient of the corresponding associated operating data, and a performance evaluation value of the corresponding performance indicator is generated according to the operating state coefficients of multiple associated operating data and the weight coefficients of the corresponding associated operating data.

[0085] In this embodiment, the performance evaluation value is obtained by summing up multiple operating status coefficients and corresponding weight coefficients. The larger the operating status coefficient, the better the operating status of the corresponding associated operating data, and the larger the performance evaluation value of the corresponding performance indicator.

[0086] In this embodiment, the performance evaluation value of the corresponding performance indicator is comprehensively determined according to the operating status coefficient of the associated operating data in each performance indicator, thereby improving the accuracy of the performance evaluation value of each performance indicator, laying a foundation for the subsequent determination of the comprehensive evaluation value and the setting of the application evaluation value, and improving the accuracy of determining the optimization instructions for the circulation pump, thereby ensuring the efficient and stable operation of the heat exchange system and improving the regulation efficiency of the circulation pump.

[0087] In some embodiments of the present application, a comprehensive evaluation value is generated according to multiple performance evaluation values, including:

[0088] Analyze multiple performance indicators based on the hierarchical analysis method, and determine the first weight coefficient of each performance indicator according to the analysis results;

[0089] A first association structure diagram is constructed based on the logical relationship and influence relationship between the performance indicators, wherein the first association structure diagram takes the performance indicator with the greatest functional importance as the structure center, and sets the first connection distance based on the logical relationship and influence degree between the structure center and other performance indicators;

[0090] Preset multiple secondary performance indicators for each performance indicator;

[0091] Determine the importance coefficient of each secondary performance indicator based on the degree of influence of the secondary performance indicator of each performance indicator on the evaluation of the corresponding performance indicator, and construct a sub-association structure diagram of each performance indicator based on the internal dependency relationship of multiple secondary performance indicators of the same performance indicator, wherein the sub-association structure diagram takes the secondary performance indicator with the maximum importance coefficient as the sub-structure center, and sets the second connection distance according to the internal dependency degree of the secondary performance indicator;

[0092] Building a connection relationship of the sub-association structure graph based on the external dependency relationship between the secondary performance indicators of different performance indicators, and setting a third connection distance between the sub-association structure graphs according to the degree of external dependency;

[0093] Generate a compensation coefficient of the corresponding performance indicator according to the first connection distance, the second connection distance, the third connection distance and the number of nodes involved in each performance indicator;

[0094] Generate a comprehensive weight coefficient of the corresponding performance indicator according to the compensation coefficient and the first weight coefficient;

[0095] Generate a comprehensive evaluation value of the historical operation data in the corresponding historical adjustment log according to the comprehensive weight coefficients of the multiple performance indicators and the performance evaluation value;

[0096] The calculation formula of the comprehensive evaluation value is:

[0097]

[0098] Among them, Z is the comprehensive evaluation value, c is the total number of performance indicators, ks is the performance evaluation value of the sth performance indicator, and cs is the comprehensive weight coefficient of the sth performance indicator.

[0099] In this embodiment, the internal dependency relationship refers to the dependency relationship between the secondary performance indicators of each performance indicator, and the internal dependency degree refers to the dependency degree between the secondary performance indicators of the same performance indicator. For example, if the secondary performance indicator A changes with the change of the secondary performance indicator B, then the secondary performance indicator A and the secondary performance indicator B have an internal dependency association, and the dependency degree is generated according to the degree of change. The external dependency degree refers to the dependency degree of the secondary performance indicators of different performance indicators.

[0100] In this embodiment, by constructing a correlation structure diagram between performance indicators, the correlation relationship between performance indicators and the importance of each performance indicator are determined, thereby improving the accuracy of the weight coefficient of each performance indicator, and subsequently determining the application evaluation value of the characteristic historical adjustment data, screening out the preferred adjustment data, and improving the adjustment efficiency of the circulation pump and the operating efficiency of the heat exchange system.

[0101] In some embodiments of the present application, setting the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log according to the comprehensive evaluation value includes:

[0102] Presetting a first preset comprehensive evaluation value interval, a second preset comprehensive evaluation value interval, a third preset comprehensive evaluation value interval and a fourth preset comprehensive evaluation value interval;

[0103] When the comprehensive evaluation value is within the first preset comprehensive evaluation value interval, the first preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log;

[0104] When the comprehensive evaluation value is within the second preset comprehensive evaluation value interval, the second preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log;

[0105] When the comprehensive evaluation value is within the third preset comprehensive evaluation value interval, the third preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log;

[0106] When the comprehensive evaluation value is in the fourth preset comprehensive evaluation value interval, the fourth preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log.

[0107] In this embodiment, the first preset comprehensive evaluation value interval < the second preset comprehensive evaluation value interval < the third preset comprehensive evaluation value interval < the fourth preset comprehensive evaluation value interval, and the first preset application evaluation value < the second preset application evaluation value < the third preset application evaluation value < the fourth preset application evaluation value.

[0108] In this embodiment, the larger the comprehensive evaluation value is, the greater the comprehensive performance index of the heat exchange system is, that is, the better the application effect of the characteristic adjustment data corresponding to the circulating pump is, and the larger the application evaluation value is, the foundation is laid for the subsequent screening of optimized adjustment data.

[0109] In some embodiments of the present application, building an optimization adjustment model corresponding to the target demand according to the optimization adjustment data, and determining the real-time optimization adjustment data, includes:

[0110] Setting the characteristic adjustment data corresponding to the fourth preset application evaluation value in each target requirement as the optimization adjustment data corresponding to the target requirement;

[0111] Obtain historical operation data corresponding to the target demand according to the optimized adjustment data, determine whether the data interval of the historical operation data corresponding to the target demand covers the preset data interval, and if so, generate a training data set according to the historical operation data corresponding to the target demand and the optimized adjustment data;

[0112] If not, determine the uncovered data interval according to the preset data interval and the data interval of the historical operation data, and select a corresponding correction scheme according to the interval length of the uncovered data interval to correct the optimized adjustment data of the adjacent data, wherein the correction scheme includes correction coefficients of different correction spans, and the correction coefficients include proportional coefficients, integral coefficients and differential coefficients;

[0113] According to a plurality of optimized adjustment data and historical operation data of the data interval not covered by the corresponding correction scheme, a training data set is constructed in combination with the optimized adjustment data and historical operation data of the data interval covered;

[0114] Construct an optimization adjustment model corresponding to the target requirements based on the training data set;

[0115] Obtain real-time target demand and corresponding real-time operation data, and input them into the optimization adjustment model corresponding to the target demand to obtain real-time optimization adjustment data.

[0116] In some embodiments of the present application, generating an optimization instruction for the real-time adjustment data according to the real-time optimization adjustment data includes:

[0117] Generating an optimization instruction for the corresponding real-time adjustment data according to the real-time optimization adjustment data, wherein the optimization instruction includes the optimization duration and the change amount of the operation data after optimization;

[0118] Determine the optimization efficiency of the corresponding optimization instruction according to the optimization time and the change in the running data after optimization;

[0119] If the optimization efficiency is less than the preset optimization efficiency threshold, the real-time optimization adjustment data and the optimization instructions are re-determined.

[0120] In this embodiment, the changes in the optimized multiple performance indicators are determined based on the changes in the optimized operating data. When the performance indicator is better, the change is positive and larger, and when the performance indicator is worse, the change is negative and smaller. The optimization efficiency is generated based on the changes in the multiple performance indicators and the optimization time.

[0121] In this embodiment, the real-time optimization adjustment data is determined by optimizing the adjustment model and the real-time adjustment data is optimized, thereby improving the operation efficiency of the heat exchange system and the adjustment efficiency of the circulation pump.

[0122] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and substitutions can be made without departing from the technical principles of the present application. These improvements and substitutions should also be regarded as the scope of protection of the present application.

Claims

1. A circulation pump optimization and adjustment method based on big data, characterized in that: include: Obtaining historical adjustment logs under different target requirements, wherein the historical adjustment logs include historical operation data and characteristic historical adjustment data; Determine the associated operating data of multiple performance indicators according to the degree of association between historical operating data and performance indicators under the same target demand, and determine the performance evaluation value of the corresponding performance indicator according to the corresponding associated operating data; Generate a comprehensive evaluation value according to multiple performance evaluation values, set an application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log according to the comprehensive evaluation value, and screen out the preferred adjustment data for the same target requirement; An optimization adjustment model corresponding to the target demand is constructed according to the optimization adjustment data, and the real-time optimization adjustment data is determined, and optimization instructions are generated for the real-time adjustment data according to the real-time optimization adjustment data.

2. The circulating pump optimization and adjustment method based on big data according to claim 1, characterized in that: Selecting target operation data from each historical adjustment log under the same target demand as a dependent variable, and using historical adjustment data of the circulating pump in the corresponding historical adjustment log as an independent variable, wherein the target operation data includes temperature, pressure, heating load and demand flow; Construct a change relationship curve based on the independent variable and the dependent variable, and obtain a matching composite curve after piecewise curve fitting; Screen out the first change feature of the change relationship curve and the second change feature of the composite curve, conduct a comprehensive analysis on the first change feature and the second change feature, and generate historical adjustment data that is strongly correlated with the target operation data in the corresponding historical adjustment log; The historical adjustment data that are strongly correlated with the target operation data in multiple historical adjustment logs of the same target demand are compared, and the historical adjustment data whose appearance ratio is greater than a preset appearance ratio threshold is set as characteristic historical adjustment data.

3. The circulating pump optimization and adjustment method based on big data according to claim 2, characterized in that: Determine the associated operational data for multiple performance indicators, including: A plurality of performance indicators are preset, and the historical adjustment log includes a historical evaluation value of each performance indicator; Obtain historical operation data of different historical adjustment logs for the same target demand and historical evaluation values ​​of multiple performance indicators, establish a time reference line according to the target duration of the same target demand, and set analysis nodes according to preset time intervals; Based on each analysis node on the time reference line, historical operation data of multiple historical adjustment logs corresponding to target requirements and historical evaluation values ​​of different performance indicators are collected; Calculate the dependency change degree between the historical operation data and the historical evaluation values ​​of different performance indicators, and generate the correlation degree between the historical operation data and the corresponding performance indicators under the current target demand based on the dependency change degree difference value whose dependency change degree is greater than the preset dependency change degree threshold and the number of analysis nodes whose dependency change degree is greater than the preset dependency change degree threshold; A correlation degree threshold is preset, and historical operation data with a correlation degree greater than the preset correlation degree threshold is set as the correlation operation data of the corresponding performance indicator.

4. The method for optimizing and adjusting a circulating pump based on big data according to claim 3, characterized in that: The calculation formula of the degree of association is: Among them, H is the degree of association, r is the degree of association conversion coefficient, n is the number of analysis nodes whose degree of dependency change is greater than the preset dependency change threshold, m is the total number of analysis nodes, Yi is the degree of dependency change at the i-th analysis node whose degree of dependency change is greater than the preset dependency change threshold, and y0 is the dependency change threshold.

5. The method for optimizing and adjusting a circulating pump based on big data according to claim 3, characterized in that: Determine the performance evaluation value of the corresponding performance indicator according to the corresponding associated operation data, including: Presetting a plurality of standard associated operating data intervals of associated operating data of each performance indicator, and each standard associated operating data interval is configured with a corresponding preset operating state coefficient; The associated operating data are compared with the corresponding standard associated operating data interval to obtain the standard associated operating data interval in which each associated operating data is located, and a preset operating state coefficient of the standard associated operating data interval is set as the operating state coefficient of the corresponding associated operating data, and a performance evaluation value of the corresponding performance indicator is generated according to the operating state coefficients of multiple associated operating data and the weight coefficients of the corresponding associated operating data.

6. The method for optimizing and adjusting a circulating pump based on big data according to claim 4, characterized in that: Generate a comprehensive evaluation value based on multiple performance evaluation values, including: Analyze multiple performance indicators based on the hierarchical analysis method, and determine the first weight coefficient of each performance indicator according to the analysis results; A first association structure diagram is constructed based on the logical relationship and influence relationship between the performance indicators, wherein the first association structure diagram takes the performance indicator with the greatest functional importance as the structure center, and sets the first connection distance based on the logical relationship and influence degree between the structure center and other performance indicators; Preset multiple secondary performance indicators for each performance indicator; Determine the importance coefficient of each secondary performance indicator based on the degree of influence of the secondary performance indicator of each performance indicator on the evaluation of the corresponding performance indicator, and construct a sub-association structure diagram of each performance indicator based on the internal dependency relationship of multiple secondary performance indicators of the same performance indicator, wherein the sub-association structure diagram takes the secondary performance indicator with the maximum importance coefficient as the sub-structure center, and sets the second connection distance according to the internal dependency degree of the secondary performance indicator; Building a connection relationship of the sub-association structure graph based on the external dependency relationship between the secondary performance indicators of different performance indicators, and setting a third connection distance between the sub-association structure graphs according to the degree of external dependency; Generate a compensation coefficient of the corresponding performance indicator according to the first connection distance, the second connection distance, the third connection distance and the number of nodes involved in each performance indicator; Generate a comprehensive weight coefficient of the corresponding performance indicator according to the compensation coefficient and the first weight coefficient; Generate a comprehensive evaluation value of the historical operation data in the corresponding historical adjustment log according to the comprehensive weight coefficients of the multiple performance indicators and the performance evaluation value; The calculation formula of the comprehensive evaluation value is: Among them, Z is the comprehensive evaluation value, c is the total number of performance indicators, ks is the performance evaluation value of the sth performance indicator, and cs is the comprehensive weight coefficient of the sth performance indicator.

7. The method for optimizing and adjusting a circulating pump based on big data according to claim 6, characterized in that: The application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log is set according to the comprehensive evaluation value, including: Presetting a first preset comprehensive evaluation value interval, a second preset comprehensive evaluation value interval, a third preset comprehensive evaluation value interval and a fourth preset comprehensive evaluation value interval; When the comprehensive evaluation value is within the first preset comprehensive evaluation value interval, the first preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log; When the comprehensive evaluation value is within the second preset comprehensive evaluation value interval, the second preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log; When the comprehensive evaluation value is within the third preset comprehensive evaluation value interval, the third preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log; When the comprehensive evaluation value is in the fourth preset comprehensive evaluation value interval, the fourth preset application evaluation value is selected as the application evaluation value of the characteristic historical adjustment data in the corresponding historical adjustment log.

8. The method for optimizing and adjusting a circulating pump based on big data according to claim 7, characterized in that: Build an optimization adjustment model corresponding to the target demand based on the optimization adjustment data, and determine the real-time optimization adjustment data, including: Setting the characteristic adjustment data corresponding to the fourth preset application evaluation value in each target requirement as the optimization adjustment data corresponding to the target requirement; Obtain historical operation data corresponding to the target demand according to the optimized adjustment data, determine whether the data interval of the historical operation data corresponding to the target demand covers the preset data interval, and if so, generate a training data set according to the historical operation data corresponding to the target demand and the optimized adjustment data; If not, determine the uncovered data interval according to the preset data interval and the data interval of the historical operation data, and select a corresponding correction scheme according to the interval length of the uncovered data interval to correct the optimized adjustment data of the adjacent data, wherein the correction scheme includes correction coefficients of different correction spans, and the correction coefficients include proportional coefficients, integral coefficients and differential coefficients; According to a plurality of optimized adjustment data and historical operation data of the data interval not covered by the corresponding correction scheme, a training data set is constructed in combination with the optimized adjustment data and historical operation data of the data interval covered; Construct an optimization adjustment model corresponding to the target requirements based on the training data set; Obtain real-time target demand and corresponding real-time operation data, and input them into the optimization adjustment model corresponding to the target demand to obtain real-time optimization adjustment data.

9. The method for optimizing and adjusting a circulating pump based on big data according to claim 8, characterized in that: Generating optimization instructions for the real-time adjustment data according to the real-time optimization adjustment data, including: Generating an optimization instruction for the corresponding real-time adjustment data according to the real-time optimization adjustment data, wherein the optimization instruction includes the optimization duration and the change amount of the operation data after optimization; Determine the optimization efficiency of the corresponding optimization instruction according to the optimization time and the change in the running data after optimization; If the optimization efficiency is less than the preset optimization efficiency threshold, the real-time optimization adjustment data and the optimization instructions are re-determined.

Images