CN115481815A - Thermal power plant load distribution system and method based on neural network - Google Patents
Thermal power plant load distribution system and method based on neural network Download PDFInfo
- Publication number
- CN115481815A CN115481815A CN202211242130.7A CN202211242130A CN115481815A CN 115481815 A CN115481815 A CN 115481815A CN 202211242130 A CN202211242130 A CN 202211242130A CN 115481815 A CN115481815 A CN 115481815A
- Authority
- CN
- China
- Prior art keywords
- data
- real
- neural network
- power plant
- thermal power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 97
- 238000009826 distribution Methods 0.000 title claims abstract description 80
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000012545 processing Methods 0.000 claims abstract description 29
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims description 26
- MWUXSHHQAYIFBG-UHFFFAOYSA-N Nitric oxide Chemical compound O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 claims description 24
- 239000003245 coal Substances 0.000 claims description 16
- 238000007621 cluster analysis Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 8
- 238000013480 data collection Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 abstract description 3
- 230000008901 benefit Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
- H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Power Engineering (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Feedback Control In General (AREA)
Abstract
The application discloses a thermal power plant load distribution system and method based on a neural network. The system may include: the device comprises a standard curve acquisition module, a data processing module and a fitting iteration module; the standard curve acquisition module is used for acquiring a standard curve according to historical data; the data acquisition module is used for acquiring real-time load data of the operation of the thermal power plant and transmitting the real-time load data to the data processing module; the data processing module is used for preprocessing the real-time load data acquired by the data acquisition module and sending the real-time load data to the fitting iteration module; and the fitting iteration module is used for performing fitting iteration through a neural network according to the real-time load data subjected to data processing by taking the standard curve as output to obtain a load distribution result of the thermal power plant. Aiming at the characteristics of the parameters of the thermal power plant, the invention adopts a neural network model to carry out distribution optimization on the unit load.
Description
Technical Field
The invention relates to the field of thermal power plant control, in particular to a thermal power plant load distribution system and method based on a neural network.
Background
In the production process of a thermal power plant, the load is one of the important parameters for operating the unit. The method has the advantages that the load can be quickly, effectively and accurately predicted, the important guiding effect is realized on the production operation scheduling of the thermal power plant, the raw material saving and the power generation cost reduction of a production enterprise are facilitated, and meanwhile, the auxiliary monitoring and early warning effects on the fault diagnosis of equipment can be realized.
Because the power load of the power grid is constantly changing data, the load of the thermal power plant also needs to be synchronously adjusted in order to ensure the balance of the power grid load. In the actual production process, the numerical value change of the load of the thermal power plant unit is influenced by factors such as power grid dispatching, unit equipment operation conditions, water vapor quality, different working conditions and the like, the load integrally fluctuates within a period of time, and certain difficulty is brought to the mining and prediction of load data.
In the past, most of the load prediction problems of the thermal power plant are realized by establishing mathematical models for data, such as a gray model based on a differential equation, an auto-regressive and moving average (ARMA) model based on autoregressive moving average and a neural network model based on nonlinear mapping, and then modeling, predicting and analyzing the data. However, because the operation parameters of the thermal power plant units are complex and dynamically change all the time, the existing data modeling method cannot achieve optimal distribution of loads of different thermal power plant units, and the optimization effect is limited.
Therefore, there is a need to develop a neural network-based load distribution system and method for a thermal power plant.
The information disclosed in this background section is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art.
Disclosure of Invention
The invention provides a thermal power plant load distribution system and method based on a neural network, which aim at the characteristics of thermal power plant parameters and adopt a neural network model to carry out distribution optimization on unit loads.
In a first aspect, an embodiment of the present disclosure provides a thermal power plant load distribution system based on a neural network, including a standard curve obtaining module, a data acquisition module, a data processing module, and a fitting iteration module;
the standard curve acquisition module is used for acquiring a standard curve according to historical data;
the data acquisition module is used for acquiring real-time load data of the operation of the thermal power plant and transmitting the real-time load data to the data processing module;
the data processing module is used for preprocessing the real-time load data acquired by the data acquisition module and sending the real-time load data to the fitting iteration module;
and the fitting iteration module is used for performing fitting iteration through a neural network according to the real-time load data after data processing by taking the standard curve as output to obtain a load distribution result of the thermal power plant.
Preferably, the historical data includes a characteristic curve of the coal consumption and the unit load of each unit of the thermal power plant, a characteristic curve of the nitrogen oxide emission and the coal consumption of each unit of the thermal power plant, and a load adjustment rate of each unit of the thermal power plant.
Preferably, the preprocessing the real-time load data collected by the data collection module includes:
performing cluster analysis on the P real-time load data to obtain K real-time load data sets, wherein K is a positive integer;
classifying any one of the K real-time load data sets in a pairwise matching manner to obtain Q target real-time load data sets, wherein Q is an integer greater than or equal to K;
and selecting a group of real-time load data with the best data quality from each of the Q target real-time load data sets to obtain the Q real-time load data.
Preferably, the obtaining of the load distribution result of the thermal power plant by using the standard curve as an output and performing fitting iteration through a neural network according to the real-time load data after data processing comprises:
training the neural network through the historical data and a standard curve;
determining initial load distribution data according to the real-time load data;
inputting the initial load distribution data to a trained neural network, and fitting to obtain a fitting curve;
and comparing the fitted curve with the standard curve, and adjusting the initial load distribution data to iterate if the error is greater than a set threshold value until the error between the fitted curve and the standard curve is less than the set threshold value, wherein the corresponding load distribution data is the load distribution result.
Preferably, training the neural network by the historical data and a standard curve comprises:
respectively inputting multiple groups of historical data into the neural network to obtain an output result after first iteration;
inputting the output result after the first iteration to the neural network again, performing n iterations, and adjusting the weight information of the neural network in each iteration process;
and when the deviation rates of the output results corresponding to different groups of historical data and the standard curve are smaller than a set threshold value, finishing training and acquiring a trained neural network.
In a second aspect, an embodiment of the present disclosure further provides a thermal power plant load distribution method based on a neural network, including:
training the neural network according to historical data to obtain the trained neural network;
acquiring real-time load data of operation of a thermal power plant and preprocessing the real-time load data;
and inputting the real-time load data subjected to data processing into the trained neural network to obtain a load distribution result of the thermal power plant.
Preferably, the historical data includes a characteristic curve of the coal consumption and the unit load of each unit of the thermal power plant, a characteristic curve of the nitrogen oxide emission and the coal consumption of each unit of the thermal power plant, and a load adjustment rate of each unit of the thermal power plant.
Preferably, the preprocessing the real-time load data comprises:
performing cluster analysis on the P real-time load data to obtain K real-time load data sets, wherein K is a positive integer;
classifying any real-time load data set in the K real-time load data sets in a pairwise matching manner to obtain Q target real-time load data sets, wherein Q is an integer greater than or equal to K;
and selecting a group of real-time load data with the best data quality from each of the Q target real-time load data sets to obtain the Q real-time load data.
Preferably, the obtaining of the load distribution result of the thermal power plant by using the standard curve as an output and performing fitting iteration through a neural network according to the real-time load data after data processing comprises:
training the neural network through the historical data and a standard curve;
determining initial load distribution data according to the real-time load data;
inputting the initial load distribution data to a trained neural network, and fitting to obtain a fitting curve;
and comparing the fitted curve with the standard curve, and adjusting the initial load distribution data to iterate if the error is greater than a set threshold value until the error between the fitted curve and the standard curve is less than the set threshold value, wherein the corresponding load distribution data is the load distribution result.
Preferably, training the neural network by the historical data and a standard curve comprises:
respectively inputting multiple groups of historical data into the neural network to obtain an output result after first iteration;
inputting the output result after the first iteration into the neural network again, performing n iterations, and adjusting the weight information of the neural network in each iteration process;
and when the deviation rates of the output results corresponding to different groups of historical data and the standard curve are smaller than a set threshold value, finishing training and acquiring a trained neural network.
The method and apparatus of the present invention have other features and advantages which will be apparent from or are set forth in detail in the accompanying drawings and the following detailed description, which are incorporated herein, and which together serve to explain certain principles of the invention.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail exemplary embodiments thereof with reference to the attached drawings, in which like reference numerals generally represent like parts.
FIG. 1 illustrates a block diagram of a neural network based thermal power plant load distribution system, according to an embodiment of the present invention.
FIG. 2 shows a flow chart of steps of a neural network based thermal power plant load distribution method according to one embodiment of the present invention.
Description of the reference numerals:
1. a standard curve acquisition module; 2. a data acquisition module; 3. a data processing module; 4. and fitting an iteration module.
Detailed Description
Preferred embodiments of the present invention will be described in more detail below. While the following describes preferred embodiments of the present invention, it should be understood that the present invention may be embodied in various forms and should not be limited by the embodiments set forth herein.
To facilitate understanding of the aspects of the embodiments of the present invention and their effects, two specific application examples are given below. It will be appreciated by persons skilled in the art that this example is merely for the purpose of facilitating understanding of the invention, and that any specific details thereof are not intended to limit the invention in any way.
Example 1
The embodiment discloses a thermal power plant load distribution system based on a neural network, which comprises a standard curve acquisition module, a data processing module and a fitting iteration module;
the standard curve acquisition module is used for acquiring a standard curve according to historical data;
the data acquisition module is used for acquiring real-time load data of the operation of the thermal power plant and transmitting the real-time load data to the data processing module;
the data processing module is used for preprocessing the real-time load data acquired by the data acquisition module and sending the real-time load data to the fitting iteration module;
and the fitting iteration module is used for performing fitting iteration through a neural network according to the real-time load data subjected to data processing by taking the standard curve as output to obtain a load distribution result of the thermal power plant.
In one example, the historical data includes a characteristic curve of the coal consumption and the unit load of each unit of the thermal power plant, a characteristic curve of the nitrogen oxide emission and the coal consumption of each unit of the thermal power plant, and a load adjustment rate of each unit of the thermal power plant.
In one example, the preprocessing the real-time load data collected by the data collection module comprises:
performing cluster analysis on the P real-time load data to obtain K real-time load data sets, wherein K is a positive integer;
classifying any real-time load data set in the K real-time load data sets in a pairwise matching manner to obtain Q target real-time load data sets, wherein Q is an integer greater than or equal to K;
and selecting a group of real-time load data with the best data quality from each of the Q target real-time load data sets to obtain Q real-time load data.
In one example, the obtaining of the load distribution result of the thermal power plant by using the standard curve as an output and performing fitting iteration through a neural network according to the real-time load data after data processing comprises:
training a neural network through historical data and a standard curve;
determining initial load distribution data according to the real-time load data;
inputting initial load distribution data to a trained neural network, and fitting to obtain a fitting curve;
and comparing the fitted curve with the standard curve, adjusting the initial load distribution data to iterate if the error is greater than a set threshold value, and determining the corresponding load distribution data as the load distribution result if the error of the fitted curve and the standard curve is less than the set threshold value.
In one example, training a neural network with historical data and a standard curve includes:
respectively inputting multiple groups of historical data into a neural network to obtain an output result after first iteration;
inputting the output result after the first iteration into the neural network again, performing n iterations, and adjusting weight information of the neural network in each iteration process;
and when the deviation rates of the output results corresponding to different groups of historical data and the standard curve are smaller than a set threshold value, finishing training and acquiring a trained neural network.
FIG. 1 shows a schematic diagram of a neural network based thermal power plant load distribution system, according to an embodiment of the invention.
Specifically, as shown in fig. 1, the system for distributing load of a thermal power plant based on a neural network includes:
the system comprises a standard curve acquisition module 1, a load adjustment module and a data processing module, wherein the standard curve acquisition module is used for acquiring a standard curve according to historical data, and the historical data comprises a characteristic curve of the coal consumption and the unit load of each unit of the thermal power plant, a characteristic curve of the nitrogen oxide emission and the coal consumption of each unit of the thermal power plant, and a load adjustment rate of each unit of the thermal power plant;
the data acquisition module 2 is used for acquiring real-time load data of the operation of the thermal power plant and transmitting the real-time load data to the data processing module 3;
the data processing module 3 is configured to perform preprocessing on the real-time load data acquired by the data acquisition module 2 according to cluster analysis, perform preprocessing on training data, and form a plurality of data sets using the real-time load as an associated target, specifically: performing cluster analysis on the P real-time load data to obtain K real-time load data sets, wherein K is a positive integer, and the cluster analysis has certain limitation, so that certain errors exist in classification, and further, classifying any one real-time load data set of the K real-time load data sets in a pairwise matching manner to obtain Q target real-time load data sets, wherein Q is an integer greater than or equal to K; selecting a group of real-time load data with the best data quality from each target real-time load data set in the Q target real-time load data sets to obtain Q real-time load data; sending the preprocessed real-time load data to a fitting iteration module 4;
the fitting iteration module 4 trains the neural network through the historical data and the standard curve, and respectively inputs a plurality of groups of historical data into the neural network to obtain an output result after the first iteration; inputting the output result after the first iteration into the neural network again, performing n iterations, and adjusting weight information of the neural network in each iteration process; when the deviation rates of the output results corresponding to different groups of historical data and the standard curve are smaller than a set threshold value, finishing training and acquiring a trained neural network; determining initial load distribution data according to the real-time load data; inputting the initial load distribution data to a trained neural network, and fitting to obtain a fitting curve; and comparing the fitted curve with the standard curve, and adjusting the initial load distribution data to iterate if the error is greater than a set threshold value until the error between the fitted curve and the standard curve is less than the set threshold value, wherein the corresponding load distribution data is the load distribution result.
Example 2
FIG. 2 shows a flow chart of steps of a neural network based thermal power plant load distribution method according to one embodiment of the present invention.
As shown in fig. 2, the method for distributing load of a thermal power plant based on a neural network includes: 101, training a neural network according to historical data to obtain the trained neural network; step 102, collecting real-time load data of operation of a thermal power plant and preprocessing the real-time load data; and 103, inputting the real-time load data subjected to data processing into the trained neural network to obtain a load distribution result of the thermal power plant.
In one example, the historical data includes a characteristic curve of the coal consumption and the unit load of each unit of the thermal power plant, a characteristic curve of the nitrogen oxide emission and the coal consumption of each unit of the thermal power plant, and a load adjustment rate of each unit of the thermal power plant.
In one example, preprocessing the real-time load data includes:
performing cluster analysis on the P real-time load data to obtain K real-time load data sets, wherein K is a positive integer;
classifying any real-time load data set in the K real-time load data sets in a pairwise matching manner to obtain Q target real-time load data sets, wherein Q is an integer greater than or equal to K;
and selecting a group of real-time load data with the best data quality from each target real-time load data set in the Q target real-time load data sets to obtain Q real-time load data.
In one example, the obtaining of the load distribution result of the thermal power plant by using the standard curve as an output and performing fitting iteration through a neural network according to the real-time load data after data processing comprises:
training a neural network through historical data and a standard curve;
determining initial load distribution data according to the real-time load data;
inputting the initial load distribution data to a trained neural network, and fitting to obtain a fitting curve;
and comparing the fitted curve with the standard curve, adjusting the initial load distribution data to iterate if the error is greater than a set threshold value, and determining the corresponding load distribution data as the load distribution result if the error of the fitted curve and the standard curve is less than the set threshold value.
In one example, training a neural network with historical data and a standard curve includes:
respectively inputting multiple groups of historical data into a neural network to obtain an output result after first iteration;
inputting the output result after the first iteration into the neural network again, performing n iterations, and adjusting weight information of the neural network in each iteration process;
and when the deviation rates of the output results corresponding to different groups of historical data and the standard curve are smaller than a set threshold value, finishing training and acquiring a trained neural network.
Specifically, a standard curve is obtained according to historical data, wherein the historical data comprises a characteristic curve of the coal consumption and the unit load of each unit of the thermal power plant, a characteristic curve of the nitrogen oxide emission and the coal consumption of each unit of the thermal power plant, and a load adjustment rate of each unit of the thermal power plant;
the method comprises the following steps of collecting real-time load data of operation of a thermal power plant, preprocessing the real-time load data according to clustering analysis, preprocessing training data, and forming a plurality of data sets taking the real-time load as a correlation target, wherein the method specifically comprises the following steps: performing cluster analysis on the P real-time load data to obtain K real-time load data sets, wherein K is a positive integer, and due to certain limitation of the cluster analysis, certain errors exist in classification, so that any one real-time load data set in the K real-time load data sets is further classified in a pairwise matching manner to obtain Q target real-time load data sets, and Q is an integer greater than or equal to K; selecting a group of real-time load data with the best data quality from each target real-time load data set in the Q target real-time load data sets to obtain Q real-time load data;
training a neural network through historical data and a standard curve, and respectively inputting multiple groups of historical data into the neural network to obtain an output result after first iteration; inputting the output result after the first iteration into the neural network again, performing n iterations, and adjusting weight information of the neural network in each iteration process; when the deviation rates of the output results corresponding to different groups of historical data and the standard curve are smaller than a set threshold value, finishing training and acquiring a trained neural network; determining initial load distribution data according to the real-time load data; inputting the initial load distribution data to a trained neural network, and fitting to obtain a fitting curve; and comparing the fitted curve with the standard curve, adjusting the initial load distribution data to iterate if the error is greater than a set threshold value, and determining the corresponding load distribution data as the load distribution result if the error of the fitted curve and the standard curve is less than the set threshold value.
It will be appreciated by persons skilled in the art that the above description of embodiments of the invention is intended only to illustrate the benefits of embodiments of the invention and is not intended to limit embodiments of the invention to any examples given.
While embodiments of the present invention have been described above, the above description is illustrative, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments.
Claims (10)
1. A thermal power plant load distribution system based on a neural network is characterized by comprising a standard curve acquisition module, a data processing module and a fitting iteration module;
the standard curve acquisition module is used for acquiring a standard curve according to historical data;
the data acquisition module is used for acquiring real-time load data of the operation of the thermal power plant and transmitting the real-time load data to the data processing module;
the data processing module is used for preprocessing the real-time load data acquired by the data acquisition module and sending the real-time load data to the fitting iteration module;
and the fitting iteration module is used for performing fitting iteration through a neural network according to the real-time load data after data processing by taking the standard curve as output to obtain a load distribution result of the thermal power plant.
2. The neural network-based load distribution system for a thermal power plant as claimed in claim 1, wherein the historical data comprises a characteristic curve of fire coal consumption and unit load of each unit of the thermal power plant, a characteristic curve of nitrogen oxide emission and fire coal consumption of each unit of the thermal power plant, and a load adjustment rate of each unit of the thermal power plant.
3. The neural network-based load distribution system of a thermal power plant as claimed in claim 1, wherein preprocessing the real-time load data collected by the data collection module comprises:
performing cluster analysis on the P real-time load data to obtain K real-time load data sets, wherein K is a positive integer;
classifying any real-time load data set in the K real-time load data sets in a pairwise matching manner to obtain Q target real-time load data sets, wherein Q is an integer greater than or equal to K;
and selecting a group of real-time load data with the best data quality from each target real-time load data set in the Q target real-time load data sets to obtain the Q real-time load data.
4. The thermal power plant load distribution system based on the neural network as claimed in claim 1, wherein the obtaining of the thermal power plant load distribution result by performing fitting iteration through the neural network according to the real-time load data after data processing with the standard curve as an output comprises:
training the neural network through the historical data and a standard curve;
determining initial load distribution data according to the real-time load data;
inputting the initial load distribution data to a trained neural network, and fitting to obtain a fitting curve;
and comparing the fitted curve with the standard curve, and adjusting the initial load distribution data for iteration if the error is greater than a set threshold value until the error between the fitted curve and the standard curve is less than the set threshold value, wherein the corresponding load distribution data is a load distribution result.
5. A thermal power plant load distribution system as recited in claim 4 wherein training said neural network with said historical data versus a standard curve comprises:
respectively inputting multiple groups of historical data into the neural network to obtain an output result after first iteration;
inputting the output result after the first iteration into the neural network again, performing n iterations, and adjusting the weight information of the neural network in each iteration process;
and when the deviation rates of the output results corresponding to different groups of historical data and the standard curve are smaller than a set threshold value, finishing training and acquiring a trained neural network.
6. A thermal power plant load distribution method based on a neural network, using the thermal power plant load distribution system based on the neural network of any one of claims 1 to 5, comprising:
training the neural network according to historical data to obtain the trained neural network;
acquiring real-time load data of the operation of a thermal power plant and preprocessing the real-time load data;
and inputting the real-time load data subjected to data processing into the trained neural network to obtain a load distribution result of the thermal power plant.
7. The neural network-based load distribution method for the thermal power plant as claimed in claim 6, wherein the historical data comprises a characteristic curve of fire coal consumption and unit load of each unit of the thermal power plant, a characteristic curve of nitrogen oxide emission and fire coal consumption of each unit of the thermal power plant, and a load adjustment rate of each unit of the thermal power plant.
8. The neural network-based thermal power plant load distribution method as recited in claim 6, wherein preprocessing the real-time load data comprises:
performing cluster analysis on the P real-time load data to obtain K real-time load data sets, wherein K is a positive integer;
classifying any real-time load data set in the K real-time load data sets in a pairwise matching manner to obtain Q target real-time load data sets, wherein Q is an integer greater than or equal to K;
and selecting a group of real-time load data with the best data quality from each of the Q target real-time load data sets to obtain the Q real-time load data.
9. The thermal power plant load distribution method based on the neural network as claimed in claim 6, wherein the obtaining of the thermal power plant load distribution result by performing fitting iteration through the neural network according to the real-time load data after data processing with the standard curve as an output comprises:
training the neural network through the historical data and a standard curve;
determining initial load distribution data according to the real-time load data;
inputting the initial load distribution data to a trained neural network, and fitting to obtain a fitting curve;
and comparing the fitted curve with the standard curve, and adjusting the initial load distribution data to iterate if the error is greater than a set threshold value until the error between the fitted curve and the standard curve is less than the set threshold value, wherein the corresponding load distribution data is the load distribution result.
10. A thermal power plant load distribution method as recited in claim 9 wherein training said neural network with said historical data versus a standard curve comprises:
respectively inputting multiple groups of historical data into the neural network to obtain an output result after first iteration;
inputting the output result after the first iteration to the neural network again, performing n iterations, and adjusting the weight information of the neural network in each iteration process;
and when the deviation rates of the output results corresponding to different groups of historical data and the standard curve are smaller than a set threshold value, finishing training and acquiring a trained neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211242130.7A CN115481815A (en) | 2022-10-11 | 2022-10-11 | Thermal power plant load distribution system and method based on neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211242130.7A CN115481815A (en) | 2022-10-11 | 2022-10-11 | Thermal power plant load distribution system and method based on neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115481815A true CN115481815A (en) | 2022-12-16 |
Family
ID=84394417
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211242130.7A Pending CN115481815A (en) | 2022-10-11 | 2022-10-11 | Thermal power plant load distribution system and method based on neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115481815A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574780A (en) * | 2024-01-15 | 2024-02-20 | 华北电力大学 | Intelligent thermal power plant load online modeling method and system |
-
2022
- 2022-10-11 CN CN202211242130.7A patent/CN115481815A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117574780A (en) * | 2024-01-15 | 2024-02-20 | 华北电力大学 | Intelligent thermal power plant load online modeling method and system |
| CN117574780B (en) * | 2024-01-15 | 2024-03-29 | 华北电力大学 | Intelligent thermal power plant load online modeling method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113255795B (en) | Equipment state monitoring method based on multi-index cluster analysis | |
| US11755976B2 (en) | Method for predicting oxygen load in iron and steel enterprises based on production plan | |
| CN108304941A (en) | A kind of failure prediction method based on machine learning | |
| CN111237988B (en) | Control method and system for subway vehicle-mounted air conditioning unit | |
| CN110571792A (en) | Analysis and evaluation method and system for operation state of power grid regulation and control system | |
| CN114580291B (en) | LSTM-VAE-based dynamic equipment health condition assessment method | |
| CN113240184B (en) | Building space unit cold load prediction method and system based on federal learning | |
| CN113837464A (en) | Load prediction method of cogeneration boiler based on CNN-LSTM-Attention | |
| CN115481815A (en) | Thermal power plant load distribution system and method based on neural network | |
| CN106682159A (en) | Threshold configuration method | |
| CN110991776A (en) | Method and system for realizing water level prediction based on GRU network | |
| CN117852896B (en) | Construction supervision risk control early warning system and method | |
| CN111598328A (en) | Power load prediction method considering epidemic situation events | |
| CN112734141B (en) | Diversified load interval prediction method and device | |
| CN109978396A (en) | A kind of early screening system and method for risk case | |
| CN111623905B (en) | Wind turbine generator bearing temperature early warning method and device | |
| CN117595231A (en) | Intelligent power grid distribution management system and method thereof | |
| CN116976862A (en) | Factory equipment informatization management system and method | |
| CN108090241A (en) | trend variable identification method and system of continuous process | |
| CN116225102A (en) | Mobile energy storage communication temperature rise automatic monitoring system and device | |
| CN108134687B (en) | Gray model local area network peak flow prediction method based on Markov chain | |
| CN113408764B (en) | Product online technical state management and control system based on digital twins | |
| CN112131069B (en) | Equipment operation monitoring method and system based on clustering | |
| CN111027719B (en) | Multi-component system state opportunity maintenance optimization method | |
| CN113688973A (en) | Water supply pump station scheduling method based on deep neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |