Intelligent prediction method and system for heat supply management of heating station

Abstract

The invention relates to the technical field of heat supply prediction, and discloses an intelligent prediction method and system for heat supply management of a heating station, and the method comprises the steps: collecting a plurality of groups of heat supply prediction influence data of the heating station based on a fixed sampling time period; performing data recombination on each group of heat supply prediction influence data to obtain a plurality of same-dimension heat supply prediction influence data groups, and determining the data fluctuation degree of each heat supply prediction influence data; calculating a sub-secondary water supply temperature prediction factor according to the data fluctuation degree, and calculating a comprehensive secondary water supply temperature prediction factor; time related characteristics are extracted from historical heat supply operation data, a secondary water supply prediction model of the heating station is constructed, the comprehensive secondary water supply temperature prediction factor is input into the secondary water supply prediction model of the heating station, the predicted secondary water supply temperature of the heating station is obtained, and the secondary water supply temperature prediction precision is improved by fusing time variables. Prediction errors are reduced, and energy waste is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of heat supply prediction, and in particular to an intelligent prediction method and system for heat supply management of a thermal power station. Background Art

[0002] The secondary water supply temperature at a heating station refers to the temperature of hot water delivered to buildings via the secondary pipe network (i.e., the user-side pipe network) after heat exchange at the heating station in a centralized heating system. It is a crucial parameter for heating system operation and regulation, directly impacting the user's indoor heating performance and system energy efficiency.

[0003] Current prediction technology for water supply temperature in secondary district heating networks for public buildings faces limitations, primarily due to the overreliance of prediction models on correlation analysis of meteorological conditions while neglecting the impact of personalized control strategies in actual operation. Traditional prediction methods typically only consider the static relationship between meteorological parameters such as outdoor temperature and wind speed and water supply temperature, failing to effectively incorporate the time-based control strategies implemented by heating station operators based on user behavior and building functional requirements. This technical shortcoming results in reduced prediction accuracy when faced with complex operating conditions involving manual temperature control. Summary of the Invention

[0004] In view of this, the present invention proposes an intelligent prediction method and system for heat supply management of a thermal power station. The present invention improves the prediction accuracy of secondary water supply temperature, reduces prediction error, and reduces energy waste by integrating time variables.

[0005] The present invention proposes an intelligent prediction method for heat supply management of a thermal power station, comprising:

[0006] receiving a heat supply management instruction from a heat supply station, presetting a fixed sampling time period, and collecting multiple sets of heat supply prediction impact data of the heat supply station based on the fixed sampling time period, wherein the fixed sampling time period includes multiple sub-fixed sampling time periods;

[0007] Reorganize each group of heat supply forecast impact data to obtain multiple heat supply forecast impact data groups with the same dimension, and determine the data fluctuation degree of each heat supply forecast impact data in the heat supply forecast impact data groups with the same dimension;

[0008] Calculating a sub-secondary water supply temperature prediction factor of the thermal power station according to all data fluctuation degrees, and calculating a comprehensive secondary water supply temperature prediction factor of the thermal power station according to all sub-secondary water supply temperature prediction factors;

[0009] Collect historical heating operation data, extract time-related features from the historical heating operation data, and construct a secondary water supply prediction model for the thermal power station. Input the comprehensive secondary water supply temperature prediction factor into the secondary water supply prediction model of the thermal power station to obtain the predicted secondary water supply temperature of the thermal power station.

[0010] Furthermore, before receiving the heating management instruction of the heating station and presetting the fixed sampling time period, the method further includes:

[0011] Obtaining a previous management instruction and determining an instruction category of the previous management instruction;

[0012] Matching the heating management instruction of the thermal power station with the instruction category of the previous management instruction, and determining whether the heating management instruction of the thermal power station is the same as the previous management instruction;

[0013] If the heating management instruction of the heating station matches the instruction category of the previous management instruction, it is determined that the heating management instruction of the heating station is the same as the previous management instruction, and the first time node of sending the heating management instruction of the heating station is collected, and the second time node of sending the previous management instruction is collected;

[0014] Calculating a time node difference between the first time node and the second time node, and determining whether the heating management instruction of the thermal power station can be received based on a relationship between the time node difference and a preset time node difference;

[0015] If the time node difference is greater than or equal to the preset time node difference, it is determined that the heating management instruction of the thermal power station can be received;

[0016] If the time node difference is less than the preset time node difference, it is determined that the heating management instruction of the thermal power station cannot be received, and a log reminder is generated and sent;

[0017] If the instruction category of the heating management instruction of the thermal power station does not match the instruction category of the previous management instruction, it is determined that the heating management instruction of the thermal power station is different from the previous management instruction, and the heating management instruction of the thermal power station is received.

[0018] Furthermore, when determining the data fluctuation degree of each heating supply prediction impact data in the heating supply prediction impact data group of the same dimension, it includes:

[0019] Sorting the heat supply forecast impact data group of the same dimension in time order based on the sub-fixed sampling time node, and determining the initial heat supply forecast impact data and the final heat supply forecast impact data;

[0020] Randomly extract a piece of heating forecast impact data from the heating forecast impact data group of the same dimension as the benchmark heating forecast impact data;

[0021] Calculating an initial data difference between the benchmark heating supply forecast impact data and the initial heating supply forecast impact data, wherein the initial data difference is an absolute value of a difference between the benchmark heating supply forecast impact data and the initial heating supply forecast impact data;

[0022] Calculating the end data difference between the baseline heating forecast impact data and the end heating forecast impact data, wherein the end data difference is the absolute value of the difference between the baseline heating forecast impact data and the end heating forecast impact data;

[0023] Calculating the data fluctuation degree of the benchmark heating forecast influencing data according to the initial data difference and the final data difference;

[0024] The remaining heating forecast impact data in the heating forecast impact data group of the same dimension are extracted and calculated to obtain the corresponding data fluctuation degree.

[0025] Furthermore, when calculating the data fluctuation degree of the benchmark heating supply prediction influencing data according to the initial data difference and the final data difference, the method includes:

[0026] The degree of data fluctuation affecting the benchmark heating forecast data is calculated according to the following formula:

[0027]

[0028] Among them, q is the data fluctuation degree of the benchmark heating forecast impact data, w1 is the initial data difference, w2 is the final data difference, r is the number of heating forecast impact data in the heating forecast impact data group of the same dimension, y t+1 is the t+1th heating forecast impact data in the heating forecast impact data group of the same dimension, y t It is the tth heating forecast impact data in the heating forecast impact data group of the same dimension.

[0029] Furthermore, when calculating the sub-secondary water supply temperature prediction factor of the thermal power station according to all data fluctuation levels, it includes:

[0030] Determining a first standard data fluctuation degree corresponding to all data fluctuation degrees, wherein the first standard data fluctuation degree is an average of all data fluctuation degrees;

[0031] determining a maximum data fluctuation degree corresponding to all data fluctuation degrees, and calculating a first ratio of the first standard data fluctuation degree to the maximum data fluctuation degree as a first calculation factor;

[0032] Determining a second standard data fluctuation degree corresponding to all data fluctuation degrees, wherein the second standard data fluctuation degree is the variance of all data fluctuation degrees;

[0033] generating a first data identifier for all data fluctuation degrees greater than the second standard data fluctuation degree;

[0034] Generate a second data identifier for all data fluctuation levels that are less than or equal to the second standard data fluctuation level;

[0035] Counting the number of first identifiers of the generated first data identifiers, and counting the number of second identifiers of the generated second data identifiers;

[0036] Determine an exponential function template, construct a first exponential function based on the first number of identifiers and the exponential function template, and calculate a value of the first exponential function, wherein the constant of the first exponential function is the first number of identifiers, the base is the second standard data fluctuation degree, and the independent variable is the maximum data fluctuation degree corresponding to the first data identifier;

[0037] Constructing a second exponential function based on the second number of identifiers and the exponential function template, and calculating a second exponential function value, wherein the constant of the second exponential function is the second number of identifiers, the base is the second standard data fluctuation degree, and the independent variable is the maximum data fluctuation degree corresponding to the second data identifier;

[0038] calculating a second ratio of the first exponential function value to the second exponential function value as a second calculation factor;

[0039] The sum of the first calculation factor and the second calculation factor is determined as a sub-secondary water supply temperature prediction factor of the thermal power station.

[0040] Furthermore, when calculating the comprehensive secondary water supply temperature prediction factor of the thermal power station based on all the sub-secondary water supply temperature prediction factors, it includes:

[0041] extracting the same sub-secondary water supply temperature prediction factor from all sub-secondary water supply temperature prediction factors, and obtaining a plurality of sub-secondary water supply temperature prediction factor sets;

[0042] Counting the number of the first sub-secondary water supply temperature prediction factor set of the sub-secondary water supply temperature prediction factor set;

[0043] Extracting a sub-secondary water supply temperature prediction factor from all sub-secondary water supply temperature prediction factor sets respectively, and calculating a first sub-secondary water supply temperature prediction factor and value;

[0044] Obtaining a preset sub-secondary water supply temperature prediction factor, eliminating all sub-secondary water supply temperature prediction factor sets that are smaller than the preset sub-secondary water supply temperature prediction factor, and counting the number of second sub-secondary water supply temperature prediction factor sets in the remaining sub-secondary water supply temperature prediction factor sets;

[0045] extracting a sub-secondary water supply temperature prediction factor from each of the remaining sub-secondary water supply temperature prediction factor sets, and calculating a second sub-secondary water supply temperature prediction factor and value;

[0046] The comprehensive secondary water supply temperature prediction factor of the thermal power station is calculated according to the number of the first sub-secondary water supply temperature prediction factor sets, the number of the second sub-secondary water supply temperature prediction factor sets, the sum of the first sub-secondary water supply temperature prediction factors and the sum of the second sub-secondary water supply temperature prediction factors.

[0047] Furthermore, when calculating the comprehensive secondary water supply temperature prediction factor of the thermal power station according to the number of the first sub-secondary water supply temperature prediction factor sets, the number of the second sub-secondary water supply temperature prediction factor sets, the sum of the first sub-secondary water supply temperature prediction factors, and the sum of the second sub-secondary water supply temperature prediction factors, the method includes:

[0048] The comprehensive secondary water supply temperature prediction factor of the thermal power station is calculated according to the following formula:

[0049]

[0050] Among them, u is the comprehensive secondary water supply temperature prediction factor of the thermal power station, i1 is the number of the first sub-secondary water supply temperature prediction factor set, i2 is the number of the second sub-secondary water supply temperature prediction factor set, p1 is the sum of the first sub-secondary water supply temperature prediction factor, and p2 is the sum of the second sub-secondary water supply temperature prediction factor.

[0051] Furthermore, when collecting historical heating operation data, extracting time-related features from the historical heating operation data, and constructing a secondary water supply prediction model for a heating station, the following steps are included:

[0052] Extracting time-related features from historical heating operation data, wherein the time-related features include time period features, historical control mode features, and heating system response delay features;

[0053] The sliding window correlation analysis method is used to determine the time-varying correlation between each time-related feature and the secondary water supply temperature, and the feature subset is dynamically selected;

[0054] Construct a hybrid neural network structure based on the LSTM-attention mechanism, where the LSTM layer is used to capture temporal dependencies and the attention mechanism is used to identify key time nodes;

[0055] The feature subsets are divided according to the heating control period, and sub-models are trained for different time periods and hybrid neural network structures respectively. The sub-models are dynamically combined through the gating mechanism to obtain the secondary water supply prediction model of the heating station.

[0056] On the other hand, the present application also provides a heating station heat supply management intelligent prediction system, including:

[0057] a data acquisition module, configured to receive a heat supply management instruction from a heat supply station, preset a fixed sampling time period, and acquire multiple sets of heat supply prediction impact data of the heat supply station based on the fixed sampling time period, wherein the fixed sampling time period includes multiple sub-fixed sampling time periods;

[0058] a data analysis module for reorganizing each group of heat supply forecast impact data to obtain multiple heat supply forecast impact data groups of the same dimension, and determining the data fluctuation degree of each heat supply forecast impact data in the heat supply forecast impact data groups of the same dimension;

[0059] a factor calculation module, configured to calculate a sub-secondary water supply temperature prediction factor of the thermal power station according to all data fluctuation degrees, and calculate a comprehensive secondary water supply temperature prediction factor of the thermal power station according to all sub-secondary water supply temperature prediction factors;

[0060] The temperature prediction module is used to collect historical heating operation data, extract time-related features from the historical heating operation data, and construct a secondary water supply prediction model for the thermal power station. The comprehensive secondary water supply temperature prediction factor is input into the secondary water supply prediction model of the thermal power station to obtain the predicted secondary water supply temperature of the thermal power station.

[0061] Furthermore, it also includes:

[0062] An instruction processing module, configured to obtain a previous management instruction and determine an instruction category of the previous management instruction;

[0063] Matching the heating management instruction of the thermal power station with the instruction category of the previous management instruction, and determining whether the heating management instruction of the thermal power station is the same as the previous management instruction;

[0064] If the heating management instruction of the heating station matches the instruction category of the previous management instruction, it is determined that the heating management instruction of the heating station is the same as the previous management instruction, and the first time node of sending the heating management instruction of the heating station is collected, and the second time node of sending the previous management instruction is collected;

[0065] Calculating a time node difference between the first time node and the second time node, and determining whether the heating management instruction of the thermal power station can be received based on a relationship between the time node difference and a preset time node difference;

[0066] If the time node difference is greater than or equal to the preset time node difference, it is determined that the heating management instruction of the thermal power station can be received;

[0067] If the time node difference is less than the preset time node difference, it is determined that the heating management instruction of the thermal power station cannot be received, and a log reminder is generated and sent;

[0068] If the instruction category of the heating management instruction of the thermal power station does not match the instruction category of the previous management instruction, it is determined that the heating management instruction of the thermal power station is different from the previous management instruction, and the heating management instruction of the thermal power station is received.

[0069] Compared with the prior art, the present invention has the following beneficial effects:

[0070] The present invention collects multiple groups of heating prediction impact data of a thermal power station based on a fixed sampling time period; reorganizes each group of heating prediction impact data to obtain multiple heating prediction impact data groups of the same dimension, and determines the data fluctuation degree of each heating prediction impact data; calculates a sub-secondary water supply temperature prediction factor according to the data fluctuation degree, and calculates a comprehensive secondary water supply temperature prediction factor; extracts time-related features from historical heating operation data, and constructs a secondary water supply prediction model for the thermal power station; inputs the comprehensive secondary water supply temperature prediction factor into the secondary water supply prediction model for the thermal power station to obtain the predicted secondary water supply temperature of the thermal power station; and by integrating the time variable, improves the secondary water supply temperature prediction accuracy, reduces the prediction error, and reduces energy waste. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0072] Figure 1 A schematic diagram of a flow chart of an intelligent prediction method for heat supply management of a thermal power station provided by an embodiment of the present invention;

[0073] Figure 2 This is a structural diagram of the intelligent prediction system for heat supply management of a thermal power station provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0074] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0075] like Figure 1As shown, in some embodiments of the present application, this embodiment provides an intelligent prediction method for heat supply management of a thermal power station, including:

[0076] S110: receiving a heat supply management instruction from a heat supply station, presetting a fixed sampling time period, and collecting multiple sets of heat supply prediction impact data of the heat supply station based on the fixed sampling time period, wherein the fixed sampling time period includes multiple sub-fixed sampling time periods;

[0077] In this embodiment, the fixed sampling time period is pre-set, such as 1 hour or 2 hours, and each fixed sampling time period includes multiple sub-fixed sampling time sections. Here, the number of sub-fixed sampling time sections is preferably 15, such as the 1st minute, the 4th minute, the 6th minute, etc., and the specific setting is 15.

[0078] In this embodiment, the heat supply prediction influencing data include secondary return water pressure, secondary supply water pressure, secondary return water pressure, secondary heat load, indoor temperature, outdoor temperature, solar radiation equivalent value and wind speed, etc., which are not shown here one by one.

[0079] In this embodiment, as described above, each sub-fixed sampling time segment corresponds to a plurality of heating supply prediction impact data.

[0080] In some embodiments of the present application, before receiving the heating management instruction of the thermal power station and presetting the fixed sampling time period, the method further includes:

[0081] Obtaining a previous management instruction and determining an instruction category of the previous management instruction;

[0082] Matching the heating management instruction of the thermal power station with the instruction category of the previous management instruction, and determining whether the heating management instruction of the thermal power station is the same as the previous management instruction;

[0083] If the heating management instruction of the heating station matches the instruction category of the previous management instruction, it is determined that the heating management instruction of the heating station is the same as the previous management instruction, and the first time node of sending the heating management instruction of the heating station is collected, and the second time node of sending the previous management instruction is collected;

[0084] Calculating a time node difference between the first time node and the second time node, and determining whether the heating management instruction of the thermal power station can be received based on a relationship between the time node difference and a preset time node difference;

[0085] If the time node difference is greater than or equal to the preset time node difference, it is determined that the heating management instruction of the thermal power station can be received;

[0086] If the time node difference is less than the preset time node difference, it is determined that the heating management instruction of the thermal power station cannot be received, and a log reminder is generated and sent;

[0087] If the instruction category of the heating management instruction of the thermal power station does not match the instruction category of the previous management instruction, it is determined that the heating management instruction of the thermal power station is different from the previous management instruction, and the heating management instruction of the thermal power station is received.

[0088] In this embodiment, the heating station heat supply management instruction refers to the start instruction of the intelligent prediction of the heating station heat supply management. When the heating station heat supply management instruction is received, the secondary water supply temperature prediction is started.

[0089] In this embodiment, the previous management instruction also includes a heating control instruction, a load regulation instruction, and the like.

[0090] In this embodiment, the preset time node difference is preferably 5 hours.

[0091] The beneficial effect of the above technical solution is: when the time node difference is less than the preset time node difference, the present invention may indicate that there is a staff error in operation. If the heating station heating management instruction is issued again within the preset time node difference, it may not be a staff error in operation. It is necessary to perform a secondary water supply temperature prediction again within the preset time node difference. Therefore, a log reminder is generated and confirmed by relevant staff to avoid missed operations or repeated operations. This can not only ensure the normal prediction of the secondary water supply temperature, but also avoid repeated predictions and waste of manpower and material resources.

[0092] S120: Reorganize each group of heat supply prediction impact data to obtain multiple heat supply prediction impact data groups with the same dimension, and determine the data fluctuation degree of each heat supply prediction impact data in the heat supply prediction impact data groups with the same dimension;

[0093] In this embodiment, when data is reorganized for each set of heat supply prediction impact data, all heat supply prediction impact data of the same type are combined. For example, the secondary return water pressure corresponding to each sub-fixed sampling time node is combined to obtain a heat supply prediction impact data set of the same dimension for the secondary return water pressure. The secondary water supply pressure corresponding to each sub-fixed sampling time node is combined to obtain a heat supply prediction impact data set of the same dimension for the secondary water supply pressure.

[0094] In some embodiments of the present application, when determining the data fluctuation degree of each heating forecast impact data in the heating forecast impact data group of the same dimension, the process includes:

[0095] Sorting the heat supply forecast impact data group of the same dimension in time order based on the sub-fixed sampling time node, and determining the initial heat supply forecast impact data and the final heat supply forecast impact data;

[0096] Randomly extract a piece of heating forecast impact data from the heating forecast impact data group of the same dimension as the benchmark heating forecast impact data;

[0097] Calculating an initial data difference between the benchmark heating supply forecast impact data and the initial heating supply forecast impact data, wherein the initial data difference is an absolute value of a difference between the benchmark heating supply forecast impact data and the initial heating supply forecast impact data;

[0098] Calculating the end data difference between the baseline heating forecast impact data and the end heating forecast impact data, wherein the end data difference is the absolute value of the difference between the baseline heating forecast impact data and the end heating forecast impact data;

[0099] Calculating the data fluctuation degree of the benchmark heating forecast influencing data according to the initial data difference and the final data difference;

[0100] The remaining heating forecast impact data in the heating forecast impact data group of the same dimension are extracted and calculated to obtain the corresponding data fluctuation degree.

[0101] In this embodiment, each heat supply prediction impact data corresponds to a sub-fixed sampling time node, and therefore, time sequence can be sorted based on the sub-fixed sampling time nodes.

[0102] In this embodiment, the above steps are repeated to obtain the data fluctuation degree corresponding to each heat supply prediction impact data.

[0103] The beneficial effect of the above technical solution is: the present invention calculates the data fluctuation degree of the benchmark heating forecast influencing data based on the initial data difference and the final data difference. The data fluctuation degree can characterize the fluctuation of each heating forecast influencing data relative to all heating forecast influencing data, thereby ensuring the accuracy of the intelligent prediction of the heating management of the thermal power station.

[0104] In some embodiments of the present application, when calculating the data fluctuation degree of the benchmark heating supply prediction influencing data according to the initial data difference and the final data difference, the method includes:

[0105] The degree of data fluctuation affecting the benchmark heating forecast data is calculated according to the following formula:

[0106]

[0107] Among them, q is the data fluctuation degree of the benchmark heating forecast impact data, w1 is the initial data difference, w2 is the final data difference, r is the number of heating forecast impact data in the heating forecast impact data group of the same dimension, y t+1 is the t+1th heating forecast impact data in the heating forecast impact data group of the same dimension, y t It is the tth heating forecast impact data in the heating forecast impact data group of the same dimension.

[0108] S130: Calculating a sub-secondary water supply temperature prediction factor of the thermal power station according to all data fluctuation degrees, and calculating a comprehensive secondary water supply temperature prediction factor of the thermal power station according to all sub-secondary water supply temperature prediction factors;

[0109] In some embodiments of the present application, when calculating the sub-secondary water supply temperature prediction factor of the thermal power station according to all data fluctuation degrees, it includes:

[0110] Determining a first standard data fluctuation degree corresponding to all data fluctuation degrees, wherein the first standard data fluctuation degree is an average of all data fluctuation degrees;

[0111] determining a maximum data fluctuation degree corresponding to all data fluctuation degrees, and calculating a first ratio of the first standard data fluctuation degree to the maximum data fluctuation degree as a first calculation factor;

[0112] Determining a second standard data fluctuation degree corresponding to all data fluctuation degrees, wherein the second standard data fluctuation degree is the variance of all data fluctuation degrees;

[0113] generating a first data identifier for all data fluctuation degrees greater than the second standard data fluctuation degree;

[0114] Generate a second data identifier for all data fluctuation levels that are less than or equal to the second standard data fluctuation level;

[0115] Counting the number of first identifiers of the generated first data identifiers, and counting the number of second identifiers of the generated second data identifiers;

[0116] Determine an exponential function template, construct a first exponential function based on the first number of identifiers and the exponential function template, and calculate a value of the first exponential function, wherein the constant of the first exponential function is the first number of identifiers, the base is the second standard data fluctuation degree, and the independent variable is the maximum data fluctuation degree corresponding to the first data identifier;

[0117] Constructing a second exponential function based on the second number of identifiers and the exponential function template, and calculating a second exponential function value, wherein the constant of the second exponential function is the second number of identifiers, the base is the second standard data fluctuation degree, and the independent variable is the maximum data fluctuation degree corresponding to the second data identifier;

[0118] calculating a second ratio of the first exponential function value to the second exponential function value as a second calculation factor;

[0119] The sum of the first calculation factor and the second calculation factor is determined as a sub-secondary water supply temperature prediction factor of the thermal power station.

[0120] In this embodiment, the exponential function template is f(x)=ab x , a is a constant, b is the base, and x is the independent variable.

[0121] In this embodiment, the corresponding constants, bases, and independent variables are substituted into the above formula to obtain the first exponential function and the second exponential function, and then the first exponential function value and the second exponential function value are calculated.

[0122] The beneficial effect of the above technical solution is: the present invention determines the sum of the first calculation factor and the second calculation factor as the sub-secondary water supply temperature prediction factor of the thermal power station. The sub-secondary water supply temperature prediction factor can be used to characterize the impact of the secondary water supply temperature of the thermal power station on one data dimension, further ensuring the accuracy and comprehensiveness of the intelligent prediction of the thermal power station's heating management.

[0123] In some embodiments of the present application, when calculating the comprehensive secondary water supply temperature prediction factor of the thermal power station based on all the sub-secondary water supply temperature prediction factors, the method includes:

[0124] extracting the same sub-secondary water supply temperature prediction factor from all sub-secondary water supply temperature prediction factors, and obtaining a plurality of sub-secondary water supply temperature prediction factor sets;

[0125] Counting the number of the first sub-secondary water supply temperature prediction factor set of the sub-secondary water supply temperature prediction factor set;

[0126] Extracting a sub-secondary water supply temperature prediction factor from all sub-secondary water supply temperature prediction factor sets respectively, and calculating a first sub-secondary water supply temperature prediction factor and value;

[0127] Obtaining a preset sub-secondary water supply temperature prediction factor, eliminating all sub-secondary water supply temperature prediction factor sets that are smaller than the preset sub-secondary water supply temperature prediction factor, and counting the number of second sub-secondary water supply temperature prediction factor sets in the remaining sub-secondary water supply temperature prediction factor sets;

[0128] extracting a sub-secondary water supply temperature prediction factor from each of the remaining sub-secondary water supply temperature prediction factor sets, and calculating a second sub-secondary water supply temperature prediction factor and value;

[0129] The comprehensive secondary water supply temperature prediction factor of the thermal power station is calculated according to the number of the first sub-secondary water supply temperature prediction factor sets, the number of the second sub-secondary water supply temperature prediction factor sets, the sum of the first sub-secondary water supply temperature prediction factors and the sum of the second sub-secondary water supply temperature prediction factors.

[0130] In this embodiment, the preset sub-secondary water supply temperature prediction factor is the variance corresponding to all sub-secondary water supply temperature prediction factors.

[0131] The beneficial effect of the above technical solution is: the present invention calculates the comprehensive secondary water supply temperature prediction factor of the thermal power station based on the number of first sub-secondary water supply temperature prediction factor sets, the number of second sub-secondary water supply temperature prediction factor sets, the sum of the first sub-secondary water supply temperature prediction factor and the sum of the second sub-secondary water supply temperature prediction factor, realizes the fusion of time variables, and at the same time realizes multi-dimensional data analysis, ensures the accuracy of the comprehensive secondary water supply temperature prediction factor, and lays the foundation for secondary water supply temperature prediction.

[0132] In some embodiments of the present application, when calculating the comprehensive secondary water supply temperature prediction factor of the thermal power station according to the number of the first sub-secondary water supply temperature prediction factor sets, the number of the second sub-secondary water supply temperature prediction factor sets, the sum of the first sub-secondary water supply temperature prediction factors, and the sum of the second sub-secondary water supply temperature prediction factors, the calculation includes:

[0133] The comprehensive secondary water supply temperature prediction factor of the thermal power station is calculated according to the following formula:

[0134]

[0135] Among them, u is the comprehensive secondary water supply temperature prediction factor of the thermal power station, i1 is the number of the first sub-secondary water supply temperature prediction factor set, i2 is the number of the second sub-secondary water supply temperature prediction factor set, p1 is the sum of the first sub-secondary water supply temperature prediction factor, and p2 is the sum of the second sub-secondary water supply temperature prediction factor.

[0136] S140: Collect historical heating operation data, extract time-related features from the historical heating operation data, and construct a secondary water supply prediction model for the thermal power station. Input the comprehensive secondary water supply temperature prediction factor into the secondary water supply prediction model for the thermal power station to obtain the predicted secondary water supply temperature of the thermal power station.

[0137] In some embodiments of the present application, when collecting historical heating operation data, extracting time-related features from the historical heating operation data, and constructing a secondary water supply prediction model for a thermal power station, the following steps are included:

[0138] Extracting time-related features from historical heating operation data, wherein the time-related features include time period features, historical control mode features, and heating system response delay features;

[0139] The sliding window correlation analysis method is used to determine the time-varying correlation between each time-related feature and the secondary water supply temperature, and the feature subset is dynamically selected;

[0140] Construct a hybrid neural network structure based on the LSTM-attention mechanism, where the LSTM layer is used to capture temporal dependencies and the attention mechanism is used to identify key time nodes;

[0141] The feature subsets are divided according to the heating control period, and sub-models are trained for different time periods and hybrid neural network structures respectively. The sub-models are dynamically combined through the gating mechanism to obtain the secondary water supply prediction model of the heating station.

[0142] In this embodiment, the time period feature is: a day is divided into multiple heating control periods, such as morning peak, noon trough, evening peak, etc., and each time period is encoded as a unique vector or sine / cosine cycle code.

[0143] In this embodiment, the historical control mode features: extracting the control parameters of the same period in the past N days, such as the statistics of valve opening and water pump frequency.

[0144] In this embodiment, the heating system response delay characteristic is to calculate the delay time from the issuance of the control instruction to the actual change of the secondary water supply temperature.

[0145] In this embodiment, the sliding window design is:

[0146] Window size: set according to the inertia characteristics of the heating network, usually 3-6 heating regulation cycles.

[0147] Step size: The window sliding step size is consistent with the prediction frequency, such as 15 minutes.

[0148] Time-varying correlation calculation: combining Pearson correlation coefficient (linear relationship) and maximum information coefficient (MIC, nonlinear relationship).

[0149] In this embodiment, the feature subset is a combination of high-value predictive variables dynamically screened from the original features through sliding window correlation analysis.

[0150] In this embodiment, the LSTM layer is designed as follows:

[0151] Structure: Double-layer stacked LSTM. The number of hidden layer neurons is set according to the complexity of the heating system (usually 32-64).

[0152] Input: Normalized time series data with shape (batch, time steps, number of features).

[0153] Attention Mechanism:

[0154] Function: Automatically identify key time nodes (such as the first 10 minutes of data after valve adjustment).

[0155] In this embodiment, the gating mechanism is implemented as follows: a fully connected network, the input is the time period code, and the output is the weight of each sub-model.

[0156] In this embodiment, the comprehensive secondary water supply temperature prediction factor is used as a single input feature and input into the secondary water supply prediction model of the thermal power station. The secondary water supply prediction model of the thermal power station outputs the predicted secondary water supply temperature of the thermal power station through linear calculation.

[0157] The beneficial effect of the above technical solution is: the present invention can provide reliable technical support for the intelligent prediction of the thermal power station by training the secondary water supply prediction model of the thermal power station, and obtain the predicted secondary water supply temperature of the thermal power station through the secondary water supply prediction model of the thermal power station, which effectively ensures the prediction accuracy and prediction efficiency of the secondary water supply temperature, eliminates the prediction error, and comprehensively considers the time variable.

[0158] like Figure 2 As shown, in another preferred embodiment based on the above embodiment, this embodiment provides an intelligent prediction system for heat supply management of a thermal power station, including:

[0159] a data acquisition module, configured to receive a heat supply management instruction from a heat supply station, preset a fixed sampling time period, and acquire multiple sets of heat supply prediction impact data of the heat supply station based on the fixed sampling time period, wherein the fixed sampling time period includes multiple sub-fixed sampling time periods;

[0160] a data analysis module for reorganizing each group of heat supply forecast impact data to obtain multiple heat supply forecast impact data groups of the same dimension, and determining the data fluctuation degree of each heat supply forecast impact data in the heat supply forecast impact data groups of the same dimension;

[0161] a factor calculation module, configured to calculate a sub-secondary water supply temperature prediction factor of the thermal power station according to all data fluctuation degrees, and calculate a comprehensive secondary water supply temperature prediction factor of the thermal power station according to all sub-secondary water supply temperature prediction factors;

[0162] The temperature prediction module is used to collect historical heating operation data, extract time-related features from the historical heating operation data, and construct a secondary water supply prediction model for the thermal power station. The comprehensive secondary water supply temperature prediction factor is input into the secondary water supply prediction model of the thermal power station to obtain the predicted secondary water supply temperature of the thermal power station.

[0163] In some embodiments of the present application, further comprising:

[0164] An instruction processing module, configured to obtain a previous management instruction and determine an instruction category of the previous management instruction;

[0165] Matching the heating management instruction of the thermal power station with the instruction category of the previous management instruction, and determining whether the heating management instruction of the thermal power station is the same as the previous management instruction;

[0166] If the heating management instruction of the heating station matches the instruction category of the previous management instruction, it is determined that the heating management instruction of the heating station is the same as the previous management instruction, and the first time node of sending the heating management instruction of the heating station is collected, and the second time node of sending the previous management instruction is collected;

[0167] Calculating a time node difference between the first time node and the second time node, and determining whether the heating management instruction of the thermal power station can be received based on a relationship between the time node difference and a preset time node difference;

[0168] If the time node difference is greater than or equal to the preset time node difference, it is determined that the heating management instruction of the thermal power station can be received;

[0169] If the time node difference is less than the preset time node difference, it is determined that the heating management instruction of the thermal power station cannot be received, and a log reminder is generated and sent;

[0170] If the instruction category of the heating management instruction of the thermal power station does not match the instruction category of the previous management instruction, it is determined that the heating management instruction of the thermal power station is different from the previous management instruction, and the heating management instruction of the thermal power station is received.

[0171] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0172] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0173] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0174] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0175] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be included in the scope of protection of the present invention.

Claims

1. An intelligent prediction method for heat supply management of a thermal power station, characterized in that: include: receiving a heat supply management instruction from a heat supply station, presetting a fixed sampling time period, and collecting multiple sets of heat supply prediction impact data of the heat supply station based on the fixed sampling time period, wherein the fixed sampling time period includes multiple sub-fixed sampling time periods; Reorganize each group of heat supply forecast impact data to obtain multiple heat supply forecast impact data groups with the same dimension, and determine the data fluctuation degree of each heat supply forecast impact data in the heat supply forecast impact data groups with the same dimension; Calculating a sub-secondary water supply temperature prediction factor of the thermal power station according to all data fluctuation degrees, and calculating a comprehensive secondary water supply temperature prediction factor of the thermal power station according to all sub-secondary water supply temperature prediction factors; Collect historical heating operation data, extract time-related features from the historical heating operation data, and construct a secondary water supply prediction model for the thermal power station. Input the comprehensive secondary water supply temperature prediction factor into the secondary water supply prediction model of the thermal power station to obtain the predicted secondary water supply temperature of the thermal power station.

2. The intelligent prediction method for heat supply management of a thermal power station according to claim 1 is characterized in that: Before receiving the heating management instruction from the heating station and setting the fixed sampling time period, the following steps are also included: Obtaining a previous management instruction and determining an instruction category of the previous management instruction; Matching the heating management instruction of the thermal power station with the instruction category of the previous management instruction, and determining whether the heating management instruction of the thermal power station is the same as the previous management instruction; If the heating management instruction of the heating station matches the instruction category of the previous management instruction, it is determined that the heating management instruction of the heating station is the same as the previous management instruction, and the first time node of sending the heating management instruction of the heating station is collected, and the second time node of sending the previous management instruction is collected; Calculating a time node difference between the first time node and the second time node, and determining whether the heating management instruction of the thermal power station can be received based on a relationship between the time node difference and a preset time node difference; If the time node difference is greater than or equal to the preset time node difference, it is determined that the heating management instruction of the thermal power station can be received; If the time node difference is less than the preset time node difference, it is determined that the heating management instruction of the thermal power station cannot be received, and a log reminder is generated and sent; If the instruction category of the heating management instruction of the thermal power station does not match the instruction category of the previous management instruction, it is determined that the heating management instruction of the thermal power station is different from the previous management instruction, and the heating management instruction of the thermal power station is received.

3. The intelligent prediction method for heat supply management of a thermal power station according to claim 1, characterized in that: When determining the data fluctuation degree of each heating forecast influencing data in the heating forecast influencing data group of the same dimension, it includes: Sorting the heat supply forecast impact data group of the same dimension in time order based on the sub-fixed sampling time node, and determining the initial heat supply forecast impact data and the final heat supply forecast impact data; Randomly extract a piece of heating forecast impact data from the heating forecast impact data group of the same dimension as the benchmark heating forecast impact data; Calculating an initial data difference between the benchmark heating supply forecast impact data and the initial heating supply forecast impact data, wherein the initial data difference is an absolute value of a difference between the benchmark heating supply forecast impact data and the initial heating supply forecast impact data; Calculating the end data difference between the baseline heating forecast impact data and the end heating forecast impact data, wherein the end data difference is the absolute value of the difference between the baseline heating forecast impact data and the end heating forecast impact data; Calculating the data fluctuation degree of the benchmark heating forecast influencing data according to the initial data difference and the final data difference; The remaining heating forecast impact data in the heating forecast impact data group of the same dimension are extracted and calculated to obtain the corresponding data fluctuation degree.

4. The intelligent prediction method for heat supply management of a thermal power station according to claim 3 is characterized in that: When calculating the data fluctuation degree of the benchmark heating supply prediction influencing data according to the initial data difference and the final data difference, the method includes: The degree of data fluctuation affecting the benchmark heating forecast data is calculated according to the following formula: Among them, q is the data fluctuation degree of the benchmark heating forecast impact data, w1 is the initial data difference, w2 is the final data difference, r is the number of heating forecast impact data in the heating forecast impact data group of the same dimension, y t+1 is the t+1th heating forecast impact data in the heating forecast impact data group of the same dimension, y t It is the tth heating forecast impact data in the heating forecast impact data group of the same dimension.

5. The intelligent prediction method for heat supply management of a thermal power station according to claim 1, characterized in that: When calculating the sub-secondary water supply temperature prediction factor of the thermal power station according to all data fluctuation levels, it includes: Determining a first standard data fluctuation degree corresponding to all data fluctuation degrees, wherein the first standard data fluctuation degree is an average of all data fluctuation degrees; determining a maximum data fluctuation degree corresponding to all data fluctuation degrees, and calculating a first ratio of the first standard data fluctuation degree to the maximum data fluctuation degree as a first calculation factor; Determining a second standard data fluctuation degree corresponding to all data fluctuation degrees, wherein the second standard data fluctuation degree is the variance of all data fluctuation degrees; generating a first data identifier for all data fluctuation degrees greater than the second standard data fluctuation degree; Generate a second data identifier for all data fluctuation levels that are less than or equal to the second standard data fluctuation level; Counting the number of first identifiers of the generated first data identifiers, and counting the number of second identifiers of the generated second data identifiers; Determine an exponential function template, construct a first exponential function based on the first number of identifiers and the exponential function template, and calculate a value of the first exponential function, wherein the constant of the first exponential function is the first number of identifiers, the base is the second standard data fluctuation degree, and the independent variable is the maximum data fluctuation degree corresponding to the first data identifier; Constructing a second exponential function based on the second number of identifiers and the exponential function template, and calculating a second exponential function value, wherein the constant of the second exponential function is the second number of identifiers, the base is the second standard data fluctuation degree, and the independent variable is the maximum data fluctuation degree corresponding to the second data identifier; calculating a second ratio of the first exponential function value to the second exponential function value as a second calculation factor; The sum of the first calculation factor and the second calculation factor is determined as a sub-secondary water supply temperature prediction factor of the thermal power station.

6. The intelligent prediction method for heat supply management of a thermal power station according to claim 1, characterized in that: When calculating the comprehensive secondary water supply temperature prediction factor of the thermal power station based on all the sub-secondary water supply temperature prediction factors, it includes: extracting the same sub-secondary water supply temperature prediction factor from all sub-secondary water supply temperature prediction factors, and obtaining a plurality of sub-secondary water supply temperature prediction factor sets; Counting the number of the first sub-secondary water supply temperature prediction factor set of the sub-secondary water supply temperature prediction factor set; Extracting a sub-secondary water supply temperature prediction factor from all sub-secondary water supply temperature prediction factor sets respectively, and calculating a first sub-secondary water supply temperature prediction factor and value; Obtaining a preset sub-secondary water supply temperature prediction factor, eliminating all sub-secondary water supply temperature prediction factor sets that are smaller than the preset sub-secondary water supply temperature prediction factor, and counting the number of second sub-secondary water supply temperature prediction factor sets in the remaining sub-secondary water supply temperature prediction factor sets; extracting a sub-secondary water supply temperature prediction factor from each of the remaining sub-secondary water supply temperature prediction factor sets, and calculating a second sub-secondary water supply temperature prediction factor and value; The comprehensive secondary water supply temperature prediction factor of the thermal power station is calculated according to the number of the first sub-secondary water supply temperature prediction factor sets, the number of the second sub-secondary water supply temperature prediction factor sets, the sum of the first sub-secondary water supply temperature prediction factors and the sum of the second sub-secondary water supply temperature prediction factors.

7. The intelligent prediction method for heat supply management of a thermal power station according to claim 6, characterized in that: When calculating the comprehensive secondary water supply temperature prediction factor of the thermal power station according to the number of the first sub-secondary water supply temperature prediction factor sets, the number of the second sub-secondary water supply temperature prediction factor sets, the sum of the first sub-secondary water supply temperature prediction factors, and the sum of the second sub-secondary water supply temperature prediction factors, the method includes: The comprehensive secondary water supply temperature prediction factor of the thermal power station is calculated according to the following formula: Among them, u is the comprehensive secondary water supply temperature prediction factor of the thermal power station, i1 is the number of the first sub-secondary water supply temperature prediction factor set, i2 is the number of the second sub-secondary water supply temperature prediction factor set, p1 is the sum of the first sub-secondary water supply temperature prediction factor, and p2 is the sum of the second sub-secondary water supply temperature prediction factor.

8. The intelligent prediction method for heat supply management of a thermal power station according to claim 1, characterized in that: When collecting historical heating operation data, extracting time-related features from the historical heating operation data, and constructing a secondary water supply prediction model for the heating station, the following steps are included: Extracting time-related features from historical heating operation data, wherein the time-related features include time period features, historical control mode features, and heating system response delay features; The sliding window correlation analysis method is used to determine the time-varying correlation between each time-related feature and the secondary water supply temperature, and the feature subset is dynamically selected; Construct a hybrid neural network structure based on the LSTM-attention mechanism, where the LSTM layer is used to capture temporal dependencies and the attention mechanism is used to identify key time nodes; The feature subsets are divided according to the heating control period, and sub-models are trained for different time periods and hybrid neural network structures respectively. The sub-models are dynamically combined through the gating mechanism to obtain the secondary water supply prediction model of the heating station.

9. An intelligent prediction system for heat supply management of a thermal power station, applied to the intelligent prediction method for heat supply management of a thermal power station according to any one of claims 1 to 8, characterized in that: include: a data acquisition module, configured to receive a heat supply management instruction from a heat supply station, preset a fixed sampling time period, and acquire multiple sets of heat supply prediction impact data of the heat supply station based on the fixed sampling time period, wherein the fixed sampling time period includes multiple sub-fixed sampling time periods; a data analysis module for reorganizing each group of heat supply forecast impact data to obtain multiple heat supply forecast impact data groups of the same dimension, and determining the data fluctuation degree of each heat supply forecast impact data in the heat supply forecast impact data groups of the same dimension; a factor calculation module, configured to calculate a sub-secondary water supply temperature prediction factor of the thermal power station according to all data fluctuation degrees, and calculate a comprehensive secondary water supply temperature prediction factor of the thermal power station according to all sub-secondary water supply temperature prediction factors; The temperature prediction module is used to collect historical heating operation data, extract time-related features from the historical heating operation data, and construct a secondary water supply prediction model for the thermal power station. The comprehensive secondary water supply temperature prediction factor is input into the secondary water supply prediction model of the thermal power station to obtain the predicted secondary water supply temperature of the thermal power station.

10. The intelligent prediction system for heat supply management of a thermal power station according to claim 9, characterized in that: Also includes: An instruction processing module, configured to obtain a previous management instruction and determine an instruction category of the previous management instruction; Matching the heating management instruction of the thermal power station with the instruction category of the previous management instruction, and determining whether the heating management instruction of the thermal power station is the same as the previous management instruction; If the heating management instruction of the heating station matches the instruction category of the previous management instruction, it is determined that the heating management instruction of the heating station is the same as the previous management instruction, and the first time node of sending the heating management instruction of the heating station is collected, and the second time node of sending the previous management instruction is collected; Calculating a time node difference between the first time node and the second time node, and determining whether the heating management instruction of the thermal power station can be received based on a relationship between the time node difference and a preset time node difference; If the time node difference is greater than or equal to the preset time node difference, it is determined that the heating management instruction of the thermal power station can be received; If the time node difference is less than the preset time node difference, it is determined that the heating management instruction of the thermal power station cannot be received, and a log reminder is generated and sent; If the instruction category of the heating management instruction of the thermal power station does not match the instruction category of the previous management instruction, it is determined that the heating management instruction of the thermal power station is different from the previous management instruction, and the heating management instruction of the thermal power station is received.

Images