Electric load prediction method and system for cogeneration unit
By building mechanism models and extreme learning machine prediction models, and using historical data training, the problem of power generation prediction for cogeneration units is solved, and accurate prediction of electricity load and optimization of power plant operation is achieved.
Patent Information
- Application Number
- CN202411606582.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-12
- Publication Date
- 2025-04-11
AI Technical Summary
The prior art has not yet proposed an effective solution to accurately predict the power generation of cogeneration units.
By constructing a mechanism model that characterizes the correlation between the operation characteristics of cogeneration units and power generation, and constructs a correlation prediction model based on the limit learning machine algorithm, using historical operation data for training to achieve prediction of power generation.
A relatively accurate prediction of the electric load of cogeneration units has been achieved, and the power plant has been guided to complete load declaration and operation optimization under the coal-power capacity electricity price mechanism.
Smart Images
Figure CN119808521A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of electric load prediction, and in particular to an electric load prediction method and system for a cogeneration unit. Background Art
[0002] The introduction of the capacity price mechanism can effectively help coal-fired power companies change their profit model, promote coal-fired power companies to take the initiative to do peak and frequency regulation for the grid connection of new energy power generation, and promote coal-fired power to gradually transform from the main power source that provides power and electricity security to the basic security and system regulation power source. While ensuring the security of power supply in the medium and long term, it alleviates the problem of stranded power generation assets caused by market-oriented reforms, organically connects with power market-oriented reforms, and helps economic and social development and the safe and stable operation of the power system.
[0003] Therefore, under the power market system with efficient coordination of electric energy, capacity, spot or ancillary services, the internal and external environment and boundary constraints of coal-fired power, especially heating units, have undergone major changes. How to combine the power spot market and the coal-fired power capacity electricity price mechanism to intelligently manage the safe operation of the system, and reasonably predict the electric load, and guide power plants to complete load declaration and operation optimization under the coal-fired power capacity electricity price mechanism, is an issue that needs to be urgently addressed.
[0004] Currently, no effective solution has been proposed for the problem of how to accurately predict the power generation of a cogeneration unit in related technologies. Summary of the invention
[0005] The embodiments of the present application provide a method and system for predicting the electric load of a cogeneration unit, so as to at least solve the problem of how to accurately predict the power generation of the cogeneration unit in the related art.
[0006] In a first aspect, an embodiment of the present application provides a method for predicting electric load of a cogeneration unit, the method comprising:
[0007] Based on the operating characteristics of the cogeneration unit, a mechanism model is constructed to characterize the correlation between the operating characteristics and the power generation of the unit;
[0008] By using the mechanism model, a correlation prediction model based on the extreme learning machine algorithm is constructed;
[0009] Acquiring historical operation data of the cogeneration unit as training data to train the correlation prediction model to obtain a trained correlation prediction model;
[0010] The power generation of the cogeneration unit is predicted by using the trained correlation prediction model.
[0011] In some of the embodiments, based on the operating characteristics of the cogeneration unit, constructing a mechanism model characterizing the correlation between the operating characteristics and the power generation of the unit includes:
[0012] A mechanism model is constructed to characterize the correlation between the medium-pressure heating extraction steam flow, low-pressure heating extraction steam flow, turbine main steam flow, turbine last-stage overflow flow and the unit's power generation, wherein the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow and the turbine last-stage overflow flow are used to determine the turbine main steam flow.
[0013] In some embodiments, constructing a mechanism model to characterize the correlation between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the main steam flow of the steam turbine, the last-stage overflow flow of the steam turbine and the power generation of the cogeneration unit includes:
[0014] A mechanism model is constructed to characterize the correlation between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the turbine main steam flow and the power generation of the unit:
[0015] D MSF =G(D MHL ,D LHL ,D ES )
[0016] P e =F(D MSF ,D MHL ,D LHL )
[0017] Among them, D MSF is the main steam flow of the steam turbine, D MHL is the medium pressure heating extraction steam flow, D LHL is the low-pressure heating extraction steam flow rate, D ES is the overflow flow of the last stage of the steam turbine, P e is the electrical load generated by the unit; G is the functional relationship between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the turbine last-stage overflow flow and the turbine main steam flow; F is the functional relationship between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the turbine main steam flow and the electrical load.
[0018] In some embodiments, constructing a correlation prediction model based on an extreme learning machine algorithm through the mechanism model includes:
[0019] Through the mechanism model, a correlation prediction model based on the extreme learning machine algorithm is constructed:
[0020]
[0021] Among them, M is the number of hidden units; N is the amount of training data; β is the weight vector between the i-th hidden layer and the output layer; w is the weight vector between the input layer and the output layer; g is the activation function; b is the bias vector; x is the input vector.
[0022] In some embodiments, obtaining the historical operation data of the cogeneration unit as training data includes:
[0023] Collecting historical operation data of the cogeneration unit within a preset time period, and preprocessing the historical operation data to establish a historical database of the unit, wherein the preprocessing includes missing data processing and abnormal data processing;
[0024] The historical operation data is obtained from the historical database as training data.
[0025] In some embodiments, performing abnormal data processing on the historical operation data includes:
[0026] Based on the operation boundary of the cogeneration unit, determining the location of abnormal data in the historical operation data, and removing the abnormal data at the location;
[0027] Perform missing data processing on the removed data in the historical operation data.
[0028] In some embodiments, determining the location of abnormal data in the historical operation data based on the operation boundary of the cogeneration unit includes:
[0029] Determining the operation boundary of the cogeneration unit, wherein the operation boundary includes a maximum main steam flow boundary surface, a minimum main steam flow boundary surface, a maximum heating steam quantity boundary surface, a minimum heating steam quantity boundary surface, a medium-pressure steam supply boundary surface, and a low-pressure steam supply boundary surface;
[0030] Based on the restriction constraints of the operating boundaries, the location of abnormal data in the historical operating data that exceeds the restriction constraints is determined, wherein the restriction constraints include that the sum of the medium-pressure heating extraction steam flow rate and the low-pressure heating extraction steam flow rate does not exceed 60% of the main steam flow rate of the turbine, and the sum of the medium-pressure heating extraction steam flow rate and the low-pressure heating extraction steam flow rate is not less than 25% of the main steam flow rate of the turbine.
[0031] In some embodiments, performing missing data processing on the historical operation data includes:
[0032] Determine the missing type of the missing data in the historical operation data. If the missing type is single-point data missing, fill in the missing data using the average value method; if the missing type is continuous data missing, fill in the missing data using the linear interpolation method.
[0033] In some embodiments, obtaining historical operation data from the historical database as training data includes:
[0034] Historical operation data is obtained from the historical database, and the historical operation data is divided into training data and test data according to a preset ratio, wherein the test data is used to perform accuracy test on the trained correlation prediction model.
[0035] In a second aspect, an embodiment of the present application provides an electric load prediction system for a cogeneration unit, the system being used to execute the method described in the first aspect above, the system comprising a mechanism model construction module, a prediction model construction module, a prediction model training module, and a prediction model application module;
[0036] The mechanism model building module is used to build a mechanism model that characterizes the correlation between the operating characteristics and the power generation of the cogeneration unit according to the operating characteristics of the cogeneration unit;
[0037] The prediction model building module is used to build a correlation prediction model based on an extreme learning machine algorithm according to the mechanism model;
[0038] The prediction model training module is used to obtain the historical operation data of the cogeneration unit as training data to train the correlation prediction model to obtain a trained correlation prediction model;
[0039] The prediction model application module is used to predict the power generation of the cogeneration unit through the trained correlation prediction model.
[0040] Compared with the related art, the embodiment of the present application provides a method and system for predicting the electric load of a cogeneration unit, wherein the method constructs a mechanism model that characterizes the correlation between the operating characteristics and the power generation of the unit based on the operating characteristics of the cogeneration unit; through the mechanism model, a correlation prediction model based on the extreme learning machine algorithm is constructed; the historical operating data of the cogeneration unit is obtained as training data to train the correlation prediction model to obtain a trained correlation prediction model; the power generation of the cogeneration unit is predicted through the trained correlation prediction model, thereby realizing an organic combination of the mechanism model of the cogeneration unit and the extreme learning machine algorithm, and only based on some physical quantity data related to the operating characteristics of the unit, the electric load of the unit can be predicted more accurately, thereby guiding the power plant to complete load declaration and operation optimization under the coal-fired power capacity electricity price mechanism, and solving the problem of how to accurately predict the power generation of the cogeneration unit. BRIEF DESCRIPTION OF THE DRAWINGS
[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0042] Figure 1 is a flowchart of the steps of a method for predicting electric load of a cogeneration unit according to an embodiment of the present application;
[0043] Figure 2 is a schematic diagram comparing the prediction results of ELM and ELM-SBOA according to an embodiment of the present application;
[0044] Figure 3 is a schematic diagram comparing prediction errors of ELM and ELM-SBOA according to an embodiment of the present application;
[0045] Figure 4 is a system schematic diagram of a double-extraction cogeneration unit according to an embodiment of the present application;
[0046] Figure 5 is a schematic diagram of changes in training data according to an embodiment of the present application;
[0047] Figure 6 is a schematic diagram of prediction results of test data according to an embodiment of the present application;
[0048] Figure 7 is a schematic diagram of prediction error of test data according to an embodiment of the present application;
[0049] Figure 8 It is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION
[0050] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.
[0051] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.
[0052] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
[0053] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.
[0054] The present application provides a method for predicting the electric load of a cogeneration unit. Figure 1 is a flowchart of the steps of the method for predicting the electric load of a cogeneration unit according to an embodiment of the present application, such as Figure 1As shown, the method comprises the following steps:
[0055] Step S102, based on the operating characteristics of the cogeneration unit, construct a mechanism model that characterizes the correlation between the operating characteristics and the power generation of the unit;
[0056] Step S102 specifically constructs a mechanism model that characterizes the correlation between the medium-pressure heating extraction steam flow, low-pressure heating extraction steam flow, turbine main steam flow, turbine last-stage overflow flow and the unit's power generation, wherein the medium-pressure heating extraction steam flow, low-pressure heating extraction steam flow, and turbine last-stage overflow flow are used to determine the turbine main steam flow.
[0057] In step S102, preferably, a mechanism model is constructed to characterize the correlation between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the turbine main steam flow and the power generation of the unit:
[0058] D MSF =G(D MHL ,D LHL ,D ES )
[0059] P e =F(D MSF ,D MHL ,D LHL )
[0060] Among them, D MSF is the main steam flow of the steam turbine, D MHL is the medium pressure heating extraction steam flow, D LHL is the low-pressure heating extraction steam flow rate, D ES is the overflow flow of the last stage of the steam turbine, P e is the electrical load generated by the unit; G is the functional relationship between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the turbine last-stage overflow flow and the turbine main steam flow; F is the functional relationship between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the turbine main steam flow and the electrical load.
[0061] Step S104, constructing a correlation prediction model based on an extreme learning machine algorithm through a mechanism model;
[0062] Specifically, step S104 constructs a correlation prediction model based on the extreme learning machine algorithm through the mechanism model:
[0063]
[0064] Among them, M is the number of hidden units; N is the amount of training data; β is the weight vector between the i-th hidden layer and the output layer; w is the weight vector between the input layer and the output layer; g is the activation function; b is the bias vector; x is the input vector. The input vector x is specifically the medium-pressure heating extraction steam flow rate, low-pressure heating extraction steam flow rate and turbine last-stage overflow flow rate of the unit.
[0065] It should be noted that the extreme learning machine algorithm (ELM) is an algorithm for solving a single hidden layer neural network. Compared with the traditional neural network, it is faster than the traditional neural network algorithm while ensuring the learning accuracy. Preferably, the extreme learning machine algorithm can introduce the egret eagle algorithm for further optimization, that is, the extreme learning machine-egret eagle optimization algorithm (ELM-SBOA), so that it can obtain the optimal weight threshold and reduce the prediction error. Figure 2 is a schematic diagram comparing the prediction results of ELM and ELM-SBOA according to an embodiment of the present application, Figure 3 is a schematic diagram comparing the prediction errors of ELM and ELM-SBOA according to an embodiment of the present application, such as Figure 2 and Figure 3 As shown in the figure, for the historical data of a certain period of the unit, the prediction error of the extreme learning machine algorithm (ELM) is within ±1.5%, and after further optimization by introducing the Heron Eagle algorithm, the mismeasurement error can be reduced to ±0.5%
[0066] Step S106, acquiring historical operation data of the cogeneration unit as training data to train the correlation prediction model, and obtaining a trained correlation prediction model;
[0067] Step S106 specifically includes the following steps:
[0068] Step S1061, collecting historical operation data of the cogeneration unit within a preset time period, and preprocessing the historical operation data to establish a historical database of the unit, wherein the preprocessing includes missing data processing and abnormal data processing;
[0069] Specifically, step S1061 determines the location of abnormal data in the historical operation data based on the operation boundary of the cogeneration unit, and removes the abnormal data at the location; and performs missing data processing on the removed data in the historical operation data.
[0070] Determine the missing type of missing data in the historical operation data. If the missing type is single-point data missing, fill in the missing data using the average value method; if the missing type is continuous data missing, fill in the missing data using the linear interpolation method.
[0071] Step S1062, obtaining historical operation data from a historical database as training data.
[0072] Specifically, step S1062 obtains historical operation data from a historical database, and divides the historical operation data into training data and test data according to a preset ratio, wherein the test data is used to perform accuracy test on the trained correlation prediction model.
[0073] Step S108, predicting the power generation of the cogeneration unit by using the trained correlation prediction model.
[0074] Specifically, step S108 determines the expected heating steam extraction volume based on the industrial steam usage of the enterprise's cogeneration unit and the overflow situation based on the current operating status of the unit, and inputs the actual medium-pressure heating steam extraction flow, low-pressure heating steam extraction flow and overflow flow to predict the electric load.
[0075] Through steps S102 to S108 in the embodiment of the present application, an organic combination of the mechanism model of the cogeneration unit and the extreme learning machine algorithm is achieved. The unit's electrical load can be more accurately predicted based on only some physical quantity data related to the unit's operating characteristics, thereby guiding the power plant to complete load declaration and operation optimization under the coal-fired power capacity price mechanism, solving the problem of how to accurately predict the power generation of the cogeneration unit.
[0076] In some embodiments, for the above step S102, the cogeneration unit is preferably a double-extraction cogeneration unit. Figure 4 is a system schematic diagram of a double-extraction cogeneration unit according to an embodiment of the present application, such as Figure 4 As shown in the figure, the maximum power of the steam turbine is 157MW, and it supplies steam of two pressures to external industrial heat users. The steam pressure and temperature required for the medium-pressure heat load are 5.0MPa and 453℃, respectively, and the steam pressure and temperature required for the low-pressure heat load are 1.8MPa and 330.9℃, respectively. According to the operating characteristics of the double-extraction high back-pressure cogeneration unit, the influence mechanism of the main steam flow of the steam turbine, the medium-pressure heating extraction flow, the low-pressure heating extraction flow and the overflow situation on the power generation of the unit is clarified to construct a mechanism model.
[0077] Specifically, the operating characteristics of the double-extraction high back-pressure cogeneration unit are as follows: the main steam flow and pressure of the unit are determined according to the unit's demand for external medium-pressure heating extraction steam and low-pressure heating extraction steam, as well as the overflow of the last stage of the low-pressure cylinder of the turbine, and the unit's power generation is then determined according to the medium-pressure heating extraction steam, low-pressure heating extraction steam and main steam flow.
[0078] In some embodiments, for determining the location of abnormal data in the historical operation data based on the operation boundary of the cogeneration unit in step S106, preferably:
[0079] Determine the operation boundary of the cogeneration unit, wherein the operation boundary includes a maximum main steam flow boundary surface, a minimum main steam flow boundary surface, a maximum heating steam quantity boundary surface, a minimum heating steam quantity boundary surface, a medium-pressure steam supply boundary surface, and a low-pressure steam supply boundary surface;
[0080] Based on the restriction constraints of the operating boundaries, the location of abnormal data that exceeds the restriction constraints in the historical operating data is determined, wherein the restriction constraints include that the sum of the medium-pressure heating extraction steam flow rate and the low-pressure heating extraction steam flow rate does not exceed 60% of the main steam flow rate of the turbine, and the sum of the medium-pressure heating extraction steam flow rate and the low-pressure heating extraction steam flow rate is not less than 25% of the main steam flow rate of the turbine.
[0081] In some embodiments, for the missing data completion by the average value method in the above step S1061, preferably:
[0082] The calculation formula for filling missing data using the mean value method is as follows:
[0083]
[0084] In the formula, x i is the missing data at a certain moment; x i-1 is the data of the previous moment; x i+1 The data for the next moment. If the data for the moments before and after this point are missing, the average value of the data for the moment before and after it, which is one day away, can be used to supplement it.
[0085] In some embodiments, for the missing data completion by linear interpolation in step S1061, preferably:
[0086] Based on the linear interpolation method, assuming that in the data [n l , x l ] and [n k , x k ], then the supplementary formula for the missing data x at a certain position n in the interval is:
[0087]
[0088] Among them, n l 、n k , n are data x l 、x k and the locations of the missing data x.
[0089] In some embodiments, for the above step S1062 of dividing the historical operation data into training data and test data according to a preset ratio, preferably:
[0090] The historical operation data includes the unit's demand for external medium-pressure heating extraction steam, demand for low-pressure heating extraction steam, and the overflow condition of the last stage of the low-pressure cylinder of the turbine within a preset time. When the model is trained and tested based on the historical operation data, it is divided into training data and test data according to a preset ratio, and the model accuracy is measured based on the prediction results of the test data.
[0091] The ratio of training data to test data is about m:n, where m should be greater than n. When the total amount of historical data is Y data When , the total amount of training data is The total amount of data in the test set is Y test =Y data -Y train , where [·] represents the rounding function.
[0092] Assuming the historical operation data of the unit on a certain day, the ratio of training data to test data is 4:1. Figure 5 is a schematic diagram of changes in training data according to an embodiment of the present application, Figure 6 is a schematic diagram of prediction results of test data according to an embodiment of the present application, Figure 7 is a schematic diagram of prediction error of test data according to an embodiment of the present application, such as Figure 5-7 As shown, the relative error is within ±1.0%. When the historical operating data does not change much and there are no abnormal values, the prediction algorithm can predict the electric load more accurately.
[0093] It should be noted that the steps shown in the above process or the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0094] The embodiment of the present application provides an electric load prediction system for a cogeneration unit, the system comprising a mechanism model construction module, a prediction model construction module, a prediction model training module and a prediction model application module;
[0095] A mechanism model building module is used to build a mechanism model that characterizes the correlation between the operating characteristics and the power generation of the unit according to the operating characteristics of the cogeneration unit;
[0096] The prediction model building module is used to build a correlation prediction model based on the extreme learning machine algorithm according to the mechanism model;
[0097] The prediction model training module is used to obtain the historical operation data of the cogeneration unit as training data to train the correlation prediction model and obtain a trained correlation prediction model;
[0098] The prediction model application module is used to predict the power generation of the cogeneration unit through the trained correlation prediction model.
[0099] Through the mechanism model construction module, prediction model construction module, prediction model training module and prediction model application module in the embodiments of the present application, an organic combination of the mechanism model of the cogeneration unit and the extreme learning machine algorithm is achieved. Only based on some physical quantity data related to the operating characteristics of the unit, a relatively accurate prediction of the unit's electrical load can be made, thereby guiding the power plant to complete load declaration and operation optimization under the coal-fired power capacity electricity price mechanism, solving the problem of how to accurately predict the power generation of the cogeneration unit.
[0100] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.
[0101] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.
[0102] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.
[0103] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.
[0104] In addition, in combination with the electric load prediction method of the cogeneration unit in the above embodiment, the embodiment of the present application can provide a storage medium for implementation. The storage medium stores a computer program; when the computer program is executed by the processor, any one of the electric load prediction methods of the cogeneration unit in the above embodiment is implemented.
[0105] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for predicting the electric load of a cogeneration unit is implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.
[0106] In one embodiment, Figure 8 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application, such as Figure 8 As shown, an electronic device is provided, which may be a server, and its internal structure diagram may be as shown in Figure 8 As shown. The electronic device includes a processor, a network interface, an internal memory and a non-volatile memory connected through an internal bus, wherein the non-volatile memory stores an operating system, a computer program and a database. The processor is used to provide computing and control capabilities, the network interface is used to communicate with an external terminal through a network connection, the internal memory is used to provide an environment for the operation of the operating system and the computer program, the computer program is executed by the processor to implement a method for predicting the electric load of a cogeneration unit, and the database is used to store data.
[0107] Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the electronic device to which the scheme of the present application is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
[0108] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
[0109] Those skilled in the art should understand that the technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0110] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.
Claims
1. A method for predicting electric load of a cogeneration unit, characterized in that: The method comprises: Based on the operating characteristics of the cogeneration unit, a mechanism model is constructed to characterize the correlation between the operating characteristics and the power generation of the unit; By using the mechanism model, a correlation prediction model based on the extreme learning machine algorithm is constructed; Acquiring historical operation data of the cogeneration unit as training data to train the correlation prediction model to obtain a trained correlation prediction model; The power generation of the cogeneration unit is predicted by using the trained correlation prediction model.
2. The method according to claim 1, characterized in that Based on the operating characteristics of the cogeneration unit, a mechanism model is constructed to characterize the correlation between the operating characteristics and the power generation of the unit, including: A mechanism model is constructed to characterize the correlation between the medium-pressure heating extraction steam flow, low-pressure heating extraction steam flow, turbine main steam flow, turbine last-stage overflow flow and the unit's power generation, wherein the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow and the turbine last-stage overflow flow are used to determine the turbine main steam flow.
3. The method according to claim 2, characterized in that The mechanism model that characterizes the correlation between the medium-pressure heating extraction steam flow, low-pressure heating extraction steam flow, turbine main steam flow, turbine last-stage overflow flow and unit power generation of the cogeneration unit includes: A mechanism model is constructed to characterize the correlation between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the turbine main steam flow and the power generation of the unit: D MSF =G(D MHL ,D LHL ,D ES ) P e =F(D MSF ,D MHL ,D LHL ) Among them, D MSF is the main steam flow of the steam turbine, D MHL is the medium pressure heating extraction steam flow, D LHL is the low-pressure heating extraction steam flow rate, D ES is the overflow flow of the last stage of the steam turbine, P e is the electrical load generated by the unit; G is the functional relationship between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the turbine last-stage overflow flow and the turbine main steam flow; F is the functional relationship between the medium-pressure heating extraction steam flow, the low-pressure heating extraction steam flow, the turbine main steam flow and the electrical load.
4. The method according to claim 1, characterized in that: Through the mechanism model, a correlation prediction model based on the extreme learning machine algorithm is constructed, including: Through the mechanism model, a correlation prediction model based on the extreme learning machine algorithm is constructed: Among them, M is the number of hidden units; N is the amount of training data; β is the weight vector between the i-th hidden layer and the output layer; w is the weight vector between the input layer and the output layer; g is the activation function; b is the bias vector; x is the input vector.
5. The method according to claim 1, characterized in that: Acquiring the historical operation data of the cogeneration unit as training data includes: Collecting historical operation data of the cogeneration unit within a preset time period, and preprocessing the historical operation data to establish a historical database of the unit, wherein the preprocessing includes missing data processing and abnormal data processing; The historical operation data is obtained from the historical database as training data.
6. The method according to claim 5, characterized in that The abnormal data processing of the historical operation data includes: Based on the operation boundary of the cogeneration unit, determining the location of abnormal data in the historical operation data, and removing the abnormal data at the location; Perform missing data processing on the removed data in the historical operation data.
7. The method according to claim 6, characterized in that Based on the operation boundary of the cogeneration unit, determining the location of abnormal data in the historical operation data includes: Determining the operation boundary of the cogeneration unit, wherein the operation boundary includes a maximum main steam flow boundary surface, a minimum main steam flow boundary surface, a maximum heating steam quantity boundary surface, a minimum heating steam quantity boundary surface, a medium-pressure steam supply boundary surface, and a low-pressure steam supply boundary surface; Based on the restriction constraints of the operating boundaries, the location of abnormal data in the historical operating data that exceeds the restriction constraints is determined, wherein the restriction constraints include that the sum of the medium-pressure heating extraction steam flow rate and the low-pressure heating extraction steam flow rate does not exceed 60% of the main steam flow rate of the turbine, and the sum of the medium-pressure heating extraction steam flow rate and the low-pressure heating extraction steam flow rate is not less than 25% of the main steam flow rate of the turbine.
8. The method according to claim 5, characterized in that Processing missing data on the historical operation data includes: Determine the missing type of the missing data in the historical operation data. If the missing type is single-point data missing, fill in the missing data using the average value method; if the missing type is continuous data missing, fill in the missing data using the linear interpolation method.
9. The method according to claim 5, characterized in that Acquiring historical operation data from the historical database as training data includes: Historical operation data is obtained from the historical database, and the historical operation data is divided into training data and test data according to a preset ratio, wherein the test data is used to perform accuracy test on the trained correlation prediction model.
10. An electric load prediction system for a cogeneration unit, characterized in that: The system is used to execute the method according to any one of claims 1 to 9, and the system comprises a mechanism model construction module, a prediction model construction module, a prediction model training module and a prediction model application module; The mechanism model building module is used to build a mechanism model that characterizes the correlation between the operating characteristics and the power generation of the cogeneration unit according to the operating characteristics of the cogeneration unit; The prediction model building module is used to build a correlation prediction model based on an extreme learning machine algorithm according to the mechanism model; The prediction model training module is used to obtain the historical operation data of the cogeneration unit as training data to train the correlation prediction model to obtain a trained correlation prediction model; The prediction model application module is used to predict the power generation of the cogeneration unit through the trained correlation prediction model.