CN116127843A - Method, system, equipment and storage medium for predicting gas consumption - Google Patents
Method, system, equipment and storage medium for predicting gas consumption Download PDFInfo
- Publication number
- CN116127843A CN116127843A CN202310075854.5A CN202310075854A CN116127843A CN 116127843 A CN116127843 A CN 116127843A CN 202310075854 A CN202310075854 A CN 202310075854A CN 116127843 A CN116127843 A CN 116127843A
- Authority
- CN
- China
- Prior art keywords
- sample data
- gas
- gas consumption
- model
- furnace
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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"
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The embodiment of the invention discloses a method, a system, equipment and a storage medium for predicting the gas consumption, which are characterized in that firstly, temperature detection is carried out on a blast furnace hot blast stove, and the current stove heat deviation of the hot blast stove is calculated according to the detection result; taking the current furnace heat deviation and the next furnace gas demand as sample data pairs, and generating a training data set and a testing data set by utilizing the sample data pairs subjected to data screening; constructing a first gas consumption prediction model by using a training data set, and performing model training based on a lifting decision tree algorithm to obtain a trained second gas consumption prediction model; performing model verification processing on the second gas consumption prediction model by using the test data set to obtain a third gas consumption prediction model passing verification; and finally, carrying out weighted combination treatment by using a third gas consumption prediction model to obtain a gas consumption prediction combination model. The embodiment of the invention realizes the prediction of the gas consumption of the blast furnace hot blast stove, and effectively improves the accuracy of the gas consumption prediction.
Description
Technical Field
The embodiment of the invention relates to the field of machine learning, in particular to a method, a system, equipment and a storage medium for predicting gas consumption.
Background
When the hot blast stove provides air temperature for a blast furnace, the conditions of unstable air temperature and unstable time exist, so that the gas quantity required by the hot blast stove when the hot blast stove is changed from air supply to burning furnace is uncertain, and when the gas pressure is small, the use of the gas quantity is reduced by the hot blast stove, so that the waste gas temperature of the furnace for burning the furnace to reduce the gas quantity is difficult to burn to the set requirement when the furnace is changed; meanwhile, the difference of the physical characteristics of different hot blast stoves, the air permeability of a heat accumulator and the heat dissipation of the heat accumulator can also cause the different gas amounts required by different hot blast stoves under the same blast furnace; in addition, in the burning process, the gas quantity of the hot blast stove is frequently increased and decreased, so that the heat accumulation quantity is unstable due to the change of the contact area between the flue gas and the heat accumulator, the maximum heat accumulation of the unit gas quantity is difficult to ensure, the maintenance period of the hot blast stove is shortened, and the service life of hardware is unfavorable.
The existing gas consumption calculation method calculates the thermal efficiency value according to the gas composition of the hot blast stove and the parameter requirements during the design of the hot blast stove, and calculates the gas consumption required by the compensation heat according to the air supply temperature and the cold air quantity of the hot blast stove.
Disclosure of Invention
Therefore, the embodiment of the invention provides a method, a system, equipment and a storage medium for predicting the gas consumption, so as to solve the problem of low accuracy of the existing gas consumption prediction technology.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
according to a first aspect of an embodiment of the present invention, there is provided a gas usage prediction method, the method including:
temperature detection is carried out on the burning process and the air supply process of the blast furnace hot blast stove to obtain detection results, the detection results are input into a thermal deviation model, and the current furnace thermal deviation of the hot blast stove is calculated;
using the current furnace heat deviation and the next furnace gas demand as first sample data pairs, carrying out data screening on all the first sample data pairs to obtain second sample data pairs, and obtaining a training data set and a testing data set by using the second sample data pairs;
constructing a first gas consumption prediction model aiming at each training data set, wherein the first gas consumption prediction model predicts a gas demand predicted value by utilizing the training data set based on a lifting decision tree algorithm, and carries out model iterative training according to the error of the gas demand predicted value and a corresponding true value to obtain a trained second gas consumption prediction model;
And performing model cross validation processing on the second gas consumption prediction model by using the test data set to obtain a third gas consumption prediction model which passes validation, and performing weighted combination processing on all the third gas consumption prediction models to obtain a gas consumption prediction combination model.
Further, temperature detection is performed on a burning process and an air supply process of the blast furnace hot blast stove to obtain a detection result, the detection result is input into a thermal deviation model, and a current furnace thermal deviation of the hot blast stove is obtained through calculation, and the method comprises the following steps:
in the burning process of the hot blast stove, carrying out first temperature detection on the hot blast stove according to a preset period to obtain the temperature of a vault of the hot blast stove and the temperature of waste gas of the hot blast stove;
inputting the temperature of the vault of the burning furnace and the waste temperature of the burning furnace into a preset heat storage soft measurement model, and calculating to obtain the total heat Q absorbed by the burning furnace of the hot blast stove in the burning furnace time xr The furnace absorbs the total heat Q xr The calculation formula of (2) is as follows:
wherein t is n Representing the duration time of the burning process of the hot blast stove; t (T) g Indicating the temperature of the furnace vault; t (T) f Representing the waste temperature of the burning furnace;
in the air supply process of the hot blast stove, carrying out second temperature detection on the hot blast stove according to the preset period to obtain cold air temperature before entering the stove and hot air temperature after entering the stove;
Calculating an air supply temperature difference T by using the cold air temperature and the hot air temperature pc ；
Temperature difference T of the air supply pc And air supply quantity V lf Inputting the total heat quantity into a preset heat release soft measurement model, and calculating to obtain total heat quantity Q released by the air supply of the hot air furnace in the air supply time fr The air supply releases the total heat Q fr The calculation formula of (2) is as follows:
wherein t is m The duration time of the air supply process of the hot blast stove is represented;
the total heat quantity Q is absorbed by the burning furnace xr And the total heat released by the air supply Q fr Calculating to obtain the heat deviation Q of the hot blast stove pc The thermal deviation Q pc The calculation formula of (2) is as follows: q (Q) pc ＝Q xr -Q fr 。
Further, using the current furnace heat deviation and the next furnace gas demand as a first sample data pair, performing data screening on all the first sample data pairs to obtain a second sample data pair, including:
using the current furnace heat deviation and the next furnace gas demand as a first sample data pair;
judging whether the burning time of the hot blast stove corresponding to each first sample data pair is within a preset burning time range or not;
if the stove burning time of the hot blast stove corresponding to the first sample data pair is not within the preset stove burning time range, discarding the first sample data pair;
If the burning time of the hot blast stove corresponding to the first sample data pair is within the preset burning time range, judging whether the temperature of the burning waste gas corresponding to the first sample data pair is within the preset burning waste gas temperature range;
discarding the first sample data pair if the temperature of the corresponding furnace burning waste gas of the first sample data pair is not within the preset furnace burning waste gas temperature range;
if the temperature of the furnace burning waste gas corresponding to the first sample data pair is within the preset furnace burning waste gas temperature range, judging whether the average value of the furnace burning vault temperatures corresponding to the first sample data pair is larger than a preset vault temperature threshold value;
discarding the first sample data pair if the average value of the furnace vault temperatures corresponding to the first sample data pair is smaller than or equal to a preset vault temperature threshold;
and if the average value of the furnace vault temperatures corresponding to the first sample data pair is larger than a preset vault temperature threshold value, the first sample data pair is used as a second sample data pair to be stored in the sample database.
Further, obtaining a training data set and a test data set by using the second sample data pair comprises:
randomly selecting a first preset number of second sample data pairs from the sample database as third sample data pairs;
Generating a second preset number of initial data sets;
randomly selecting a third sample data pair with a third preset number from all the third sample data pairs as a fourth sample data pair for each initial data set, and storing the fourth sample data pair into the initial data set to obtain a sample data set;
randomly selecting a sample data set with a preset proportion from all the sample data sets as a training data set, and taking the remaining unselected sample data sets as test data sets.
Further, for each training data set, a first gas consumption prediction model is constructed, the first gas consumption prediction model predicts a gas demand predicted value by using the training data set based on a lifting decision tree algorithm, and model iterative training is performed according to errors of the gas demand predicted value and a corresponding true value to obtain a trained second gas consumption prediction model, and the method comprises the following steps:
presetting an initialization function h for each sample data set in the training data set 0 (x) =0, wherein x represents the thermal bias in the fourth sample data pair;
calculating a residual error r by using each fourth sample data pair m The residual error r m The calculation formula of (2) is as follows:
r m ＝y m -h m-1 (x m )
wherein m is an integer greater than zero and less than or equal to a third preset number; y is m Representing a next furnace gas demand in an mth fourth sample data pair of the sample data set; x is x m Representing a thermal bias in an mth fourth sample data pair of the sample data set;
utilizing the residual error r m Fitting to obtain decision function T (x; θ) m ) Wherein θ m Representing decision function parameters;
according to the decision function T (x; θ) m ) Calculating to obtain a gas demand predicted value h m (x) The predicted value h of the gas demand m (x) The calculation formula of (2) is as follows:
h m (x)＝h m-1 (x)+T(x；θ m )
by using the gas demand predicted value h m (x) Calculating to obtain square loss error L (y m ，h m (x) And the square loss error L (y) m ，h m (x) The calculation formula of (c) is:
L(y m ，h m (x))＝(y m -h m (x)) 2 ＝[r m -T(x；θ m )] 2
determining the square loss error L (y m ，h m (x) Whether less than or equal to a preset error threshold;
if the square loss error L (y m ，h m (x) If the gas demand predicted value is larger than the preset error threshold value, circulating to recalculate the gas demand predicted value and the square loss error by using the next fourth sample data pair;
if the square loss error L (y m ，h m (x) Less than or equal to the preset error threshold, then using the decision function T (x; θ m ) Obtaining a second gas consumption prediction model h M (x) The saidSecond gas consumption prediction model h M (x) The calculation formula of (2) is as follows:
wherein M is the third preset number.
Further, performing a model cross validation process on the second gas usage prediction model using the test dataset to obtain a validated third gas usage prediction model, including:
for each second gas consumption prediction model h M (x) Inputting the thermal deviation in each fourth sample data pair in the test data set into the second gas usage prediction model h M (x) Calculating to obtain corresponding model test predicted values
Testing predicted values using all of the models
Calculating to obtain a model cross validation parameter R 2 The model cross-validation parameter R 2 The calculation formula of (2) is as follows:
wherein i is an integer greater than zero; y is i Representing a next furnace gas demand in an ith fourth sample data pair in the test data set;
representing y i Testing a predicted value by a corresponding model; />
A mean value of thermal deviations representing all fourth sample data pairs in the test dataset;
judging the model cross validation parameter R 2 Whether the verification value is larger than a preset verification threshold value or not;
if the model cross-verifies the parameter R 2 If the gas consumption is larger than the preset verification threshold, the second gas consumption prediction model is used as a third gas consumption prediction model;
if the model cross-verifies the parameter R 2 And if the gas consumption prediction model is smaller than or equal to the preset verification threshold value, discarding the second gas consumption prediction model.
Further, performing weighted combination processing on all the third gas consumption prediction models to obtain a gas consumption prediction combination model, including:
and carrying out weighted average treatment by using all the third gas consumption models, and calculating to obtain a gas consumption prediction combination model H (x), wherein the calculation formula of the gas consumption prediction combination model H (x) is as follows:
wherein k is an integer greater than zero; n is the total number of the third gas consumption prediction model; h is a k (x) Representing the kth model in all the third gas usage prediction models; w (w) k Represents h k (x) Corresponding preset weight parameters.
According to a second aspect of embodiments of the present invention, there is provided a gas usage prediction system, the system comprising:
the thermal deviation operation module is used for detecting the temperature of the burning process and the air supply process of the blast furnace hot blast stove to obtain a detection result, inputting the detection result into the thermal deviation model, and calculating to obtain the current stove thermal deviation of the hot blast stove;
The data processing module is used for taking the current furnace heat deviation and the next furnace gas demand as first sample data pairs, carrying out data screening on all the first sample data pairs to obtain second sample data pairs, and obtaining a training data set and a test data set by using the second sample data pairs;
the model training module is used for constructing a first gas consumption prediction model aiming at each training data set, the first gas consumption prediction model is based on a lifting decision tree algorithm, a gas demand predicted value is predicted by utilizing the training data set, and model iterative training is carried out according to errors of the gas demand predicted value and a corresponding true value, so that a trained second gas consumption prediction model is obtained;
and the model verification combination module is used for carrying out model cross verification processing on the second gas consumption prediction model by utilizing the test data set to obtain a verified third gas consumption prediction model, and carrying out weighted combination processing on all the third gas consumption prediction models to obtain a gas consumption prediction combination model.
Further, temperature detection is performed on a burning process and an air supply process of the blast furnace hot blast stove to obtain a detection result, the detection result is input into a thermal deviation model, and a current furnace thermal deviation of the hot blast stove is obtained through calculation, and the method comprises the following steps:
In the burning process of the hot blast stove, carrying out first temperature detection on the hot blast stove according to a preset period to obtain the temperature of a vault of the hot blast stove and the temperature of waste gas of the hot blast stove;
inputting the temperature of the vault of the burning furnace and the waste temperature of the burning furnace into a preset heat storage soft measurement model, and calculating to obtain the total heat Q absorbed by the burning furnace of the hot blast stove in the burning furnace time xr The furnace absorbs the total heat Q xr The calculation formula of (2) is as follows:
wherein t is n Representing the duration time of the burning process of the hot blast stove; t (T) g Indicating the temperature of the furnace vault; t (T) f Representing the waste temperature of the burning furnace;
in the air supply process of the hot blast stove, carrying out second temperature detection on the hot blast stove according to the preset period to obtain cold air temperature before entering the stove and hot air temperature after entering the stove;
using the cold air temperature and the hot air temperature, a meterCalculating to obtain the air supply temperature difference T pc ；
Temperature difference T of the air supply pc And air supply quantity V lf Inputting the total heat quantity into a preset heat release soft measurement model, and calculating to obtain total heat quantity Q released by the air supply of the hot air furnace in the air supply time fr The air supply releases the total heat Q fr The calculation formula of (2) is as follows:
wherein t is m The duration time of the air supply process of the hot blast stove is represented;
the total heat quantity Q is absorbed by the burning furnace xr And the total heat released by the air supply Q fr Calculating to obtain the heat deviation Q of the hot blast stove pc The thermal deviation Q pc The calculation formula of (2) is as follows: q (Q) pc ＝Q xr -Q fr 。
Further, using the current furnace heat deviation and the next furnace gas demand as a first sample data pair, performing data screening on all the first sample data pairs to obtain a second sample data pair, including:
using the current furnace heat deviation and the next furnace gas demand as a first sample data pair;
judging whether the burning time of the hot blast stove corresponding to each first sample data pair is within a preset burning time range or not;
if the stove burning time of the hot blast stove corresponding to the first sample data pair is not within the preset stove burning time range, discarding the first sample data pair;
if the burning time of the hot blast stove corresponding to the first sample data pair is within the preset burning time range, judging whether the temperature of the burning waste gas corresponding to the first sample data pair is within the preset burning waste gas temperature range;
discarding the first sample data pair if the temperature of the corresponding furnace burning waste gas of the first sample data pair is not within the preset furnace burning waste gas temperature range;
if the temperature of the furnace burning waste gas corresponding to the first sample data pair is within the preset furnace burning waste gas temperature range, judging whether the average value of the furnace burning vault temperatures corresponding to the first sample data pair is larger than a preset vault temperature threshold value;
Discarding the first sample data pair if the average value of the furnace vault temperatures corresponding to the first sample data pair is smaller than or equal to a preset vault temperature threshold;
and if the average value of the furnace vault temperatures corresponding to the first sample data pair is larger than a preset vault temperature threshold value, the first sample data pair is used as a second sample data pair to be stored in the sample database.
Further, obtaining a training data set and a test data set by using the second sample data pair comprises:
randomly selecting a first preset number of second sample data pairs from the sample database as third sample data pairs;
generating a second preset number of initial data sets;
randomly selecting a third sample data pair with a third preset number from all the third sample data pairs as a fourth sample data pair for each initial data set, and storing the fourth sample data pair into the initial data set to obtain a sample data set;
randomly selecting a sample data set with a preset proportion from all the sample data sets as a training data set, and taking the remaining unselected sample data sets as test data sets.
Further, for each training data set, a first gas consumption prediction model is constructed, the first gas consumption prediction model predicts a gas demand predicted value by using the training data set based on a lifting decision tree algorithm, and model iterative training is performed according to errors of the gas demand predicted value and a corresponding true value to obtain a trained second gas consumption prediction model, and the method comprises the following steps:
Presetting an initialization function h for each sample data set in the training data set 0 (x) =0, wherein x representsThermal bias in the fourth sample data pair;
calculating a residual error r by using each fourth sample data pair m The residual error r m The calculation formula of (2) is as follows:
r m ＝y m -h m-1 (x m )
wherein m is an integer greater than zero and less than or equal to a third preset number; y is m Representing a next furnace gas demand in an mth fourth sample data pair of the sample data set; x is x m Representing a thermal bias in an mth fourth sample data pair of the sample data set;
utilizing the residual error r m Fitting to obtain decision function T (x; θ) m ) Wherein θ m Representing decision function parameters;
according to the decision function T (x; θ) m ) Calculating to obtain a gas demand predicted value h m (x) The predicted value h of the gas demand m (x) The calculation formula of (2) is as follows:
h m (x)＝h m-1 (x)+T(x；θ m )
by using the gas demand predicted value h m (x) Calculating to obtain square loss error L (y m ，h m (x) And the square loss error L (y) m ，h m (x) The calculation formula of (c) is:
L(y m ，h m (x))＝(y m -h m (x)) 2 ＝[r m -T(x；θ m )] 2
determining the square loss error L (y m ，h m (x) Whether less than or equal to a preset error threshold;
if the square loss error L (y m ，h m (x) If the gas demand predicted value is larger than the preset error threshold value, circulating to recalculate the gas demand predicted value and the square loss error by using the next fourth sample data pair;
If the square loss error L (y m ，h m (x) Less than or equal to the preset error threshold, then using the decision function T (x; θ m ) Obtaining the productTo a second gas consumption prediction model h M (x) The second gas consumption prediction model h M (x) The calculation formula of (2) is as follows:
wherein M is the third preset number.
Further, performing a model cross validation process on the second gas usage prediction model using the test dataset to obtain a validated third gas usage prediction model, including:
for each second gas consumption prediction model h M (x) Inputting the thermal deviation in each fourth sample data pair in the test data set into the second gas usage prediction model h M (x) Calculating to obtain corresponding model test predicted values
Testing predicted values using all of the models
Calculating to obtain a model cross validation parameter R 2 The model cross-validation parameter R 2 The calculation formula of (2) is as follows:
wherein i is an integer greater than zero; y is i Representing a next furnace gas demand in an ith fourth sample data pair in the test data set;
representing y i Testing a predicted value by a corresponding model; />
Representing the test datasetA mean value of thermal deviations for all fourth sample data pairs;
Judging the model cross validation parameter R 2 Whether the verification value is larger than a preset verification threshold value or not;
if the model cross-verifies the parameter R 2 If the gas consumption is larger than the preset verification threshold, the second gas consumption prediction model is used as a third gas consumption prediction model;
if the model cross-verifies the parameter R 2 And if the gas consumption prediction model is smaller than or equal to the preset verification threshold value, discarding the second gas consumption prediction model.
Further, performing weighted combination processing on all the third gas consumption prediction models to obtain a gas consumption prediction combination model, including:
and carrying out weighted average treatment by using all the third gas consumption models, and calculating to obtain a gas consumption prediction combination model H (x), wherein the calculation formula of the gas consumption prediction combination model H (x) is as follows:
wherein k is an integer greater than zero; n is the total number of the third gas consumption prediction model; h is a k (x) Representing the kth model in all the third gas usage prediction models; w (w) k Represents h k (x) Corresponding preset weight parameters.
According to a third aspect of embodiments of the present invention, there is provided a gas usage prediction apparatus, the apparatus comprising: a processor and a memory;
the memory is used for storing one or more program instructions;
The processor is configured to execute one or more program instructions for performing the steps of a gas usage prediction method as defined in any one of the preceding claims.
According to a fourth aspect of embodiments of the present invention, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a gas usage prediction method as defined in any one of the above.
The embodiment of the invention has the following advantages:
the embodiment of the invention discloses a method, a system, equipment and a storage medium for predicting the gas consumption, which are characterized in that firstly, temperature detection is carried out on a blast furnace hot blast stove, and the current stove heat deviation of the hot blast stove is calculated according to the detection result; taking the current furnace heat deviation and the next furnace gas demand as sample data pairs, and generating a training data set and a testing data set by utilizing the sample data pairs subjected to data screening; constructing a first gas consumption prediction model by using a training data set, and performing model training based on a lifting decision tree algorithm to obtain a trained second gas consumption prediction model; performing model verification processing on the second gas consumption prediction model by using the test data set to obtain a third gas consumption prediction model passing verification; and finally, carrying out weighted combination treatment by using a third gas consumption prediction model to obtain a gas consumption prediction combination model. The embodiment of the invention realizes the prediction of the gas consumption of the blast furnace hot blast stove, and effectively improves the accuracy of the gas consumption prediction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
The structures, proportions, sizes, etc. shown in the present specification are shown only for the purposes of illustration and description, and are not intended to limit the scope of the invention, which is defined by the claims, so that any structural modifications, changes in proportions, or adjustments of sizes, which do not affect the efficacy or the achievement of the present invention, should fall within the ambit of the technical disclosure.
FIG. 1 is a schematic diagram of a logic structure of a gas consumption prediction system according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for predicting gas consumption according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a hot blast stove thermal deviation operation according to an embodiment of the present invention;
FIG. 4 is a schematic flow chart of screening sample data pairs according to an embodiment of the present invention;
FIG. 5 is a schematic flow chart of generating a training data set and a test data set according to an embodiment of the present invention;
FIG. 6 is a schematic flow chart of a gas consumption prediction model obtained by training with a training data set according to an embodiment of the present invention;
FIG. 7 is a schematic flow chart of verifying a gas consumption prediction model by using a test data set and generating a gas consumption prediction combined model according to an embodiment of the present invention.
Detailed Description
Other advantages and advantages of the present invention will become apparent to those skilled in the art from the following detailed description, which, by way of illustration, is to be read in connection with certain specific embodiments, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, an embodiment of the present invention provides a gas usage prediction system, which specifically includes: a thermal deviation operation module 1, a data processing module 2, a model training module 3 and a model verification combination module 4.
Further, the thermal deviation operation module 1 is used for detecting the temperature of the burning process and the air supply process of the blast furnace hot blast stove to obtain a detection result, inputting the detection result into the thermal deviation model, and calculating to obtain the current stove thermal deviation of the hot blast stove; the data processing module 2 is used for utilizing the current furnace heat deviation and the next furnace gas demand as first sample data pairs, carrying out data screening on all the first sample data pairs to obtain second sample data pairs, and utilizing the second sample data pairs to obtain a training data set and a test data set; the model training module 3 is used for constructing a first gas consumption prediction model aiming at each training data set, wherein the first gas consumption prediction model predicts a gas demand predicted value by utilizing the training data set based on a lifting decision tree algorithm, and carries out model iterative training according to the error of the gas demand predicted value and a corresponding true value to obtain a trained second gas consumption prediction model; and the model verification combination module 4 is used for carrying out model cross verification processing on the second gas consumption prediction model by using the test data set to obtain a verified third gas consumption prediction model, and carrying out weighted combination processing on all the third gas consumption prediction models to obtain a gas consumption prediction combination model.
The embodiment of the invention discloses a gas consumption prediction system, which comprises the steps of firstly, detecting the temperature of a blast furnace hot blast stove, and calculating to obtain the current stove heat deviation of the hot blast stove according to the detection result; taking the current furnace heat deviation and the next furnace gas demand as sample data pairs, and generating a training data set and a testing data set by utilizing the sample data pairs subjected to data screening; constructing a first gas consumption prediction model by using a training data set, and performing model training based on a lifting decision tree algorithm to obtain a trained second gas consumption prediction model; performing model verification processing on the second gas consumption prediction model by using the test data set to obtain a third gas consumption prediction model passing verification; and finally, carrying out weighted combination treatment by using a third gas consumption prediction model to obtain a gas consumption prediction combination model. The embodiment of the invention realizes the prediction of the gas consumption of the blast furnace hot blast stove, and effectively improves the accuracy of the gas consumption prediction.
Corresponding to the disclosed gas consumption prediction system, the embodiment of the invention also discloses a gas consumption prediction method. The following describes a gas usage prediction method disclosed in the embodiment of the present invention in detail in connection with a gas usage prediction system described above.
With reference to fig. 2, specific steps of a gas usage prediction method provided by an embodiment of the present invention are described below.
The temperature detection is carried out on the burning process and the air supply process of the blast furnace hot blast stove by the hot deviation operation module 1, a detection result is obtained, the detection result is input into a hot deviation model, and the current stove hot deviation of the hot blast stove is obtained through calculation.
Referring to fig. 3, the steps specifically include: the working principle of the blast furnace regenerative hot blast stove is that coal gas is combusted firstly to burn the furnace, the regenerative chamber is heated by the generated flue gas, and then the regenerative chamber is utilized to heat the fed cold air, so that high-temperature hot air is obtained; in the burning process of the hot blast stove, carrying out first temperature detection on the hot blast stove according to a preset period, for example, detecting the temperature of a burning dome and the temperature of burning waste gas in a period of one second to obtain the temperature of the burning dome and the temperature of burning waste gas; inputting the temperature of the vault of the burning furnace and the waste temperature of the burning furnace into a preset heat storage soft measurement model, and calculating to obtain the total heat absorbed by the burning furnace Q of the hot blast stove in the current burning furnace time xr The burning furnace absorbs the total heat Q xr The calculation formula of (2) is as follows:
wherein t is n Representing the duration time of the burning process of the hot blast stove; t (T) g The temperature of the furnace dome of the t-th preset period is represented; t (T) f The waste temperature of the burning furnace in the t preset period is represented;
then, in the air supply process of the hot blast stove, carrying out second temperature detection on the hot blast stove according to the preset period to obtain cold air temperature before entering the stove and hot air temperature after entering the stove and heating; the temperature difference T of the supplied air is calculated by using the cold air temperature and the hot air temperature pc ；
Temperature difference T of air supply pc And air supply amount V in air supply time l Inputting the total heat quantity into a preset heat release soft measurement model, and calculating to obtain total heat quantity Q released by the air supply of the hot air furnace in the air supply time fr The air supply releases the total heat Q fr The calculation formula of (2) is as follows:
wherein t is m The duration time of the air supply process of the hot blast stove is represented;
the total heat quantity Q absorbed by the burning furnace is reused xr And supply air to release total heat Q fr Calculating to obtain the heat deviation Q of the hot blast stove pc Thermal deviation Q pc The calculation formula of (2) is as follows: q (Q) pc ＝Q xr -Q fr 。
And the data screening module 2 uses the current furnace heat deviation and the next furnace gas demand as first sample data pairs, performs data screening on all the first sample data pairs to obtain second sample data pairs, and obtains a training data set and a test data set by using the second sample data pairs.
Referring to fig. 4 and 5, the steps specifically include: firstly, using the current furnace heat deviation and the next furnace gas demand as a first sample data pair; judging whether the burning time of the hot blast stove corresponding to each first sample data pair is within a preset burning time range or not; if the corresponding burning time of the hot blast stove of the first sample data pair is not within the preset burning time range, discarding the first sample data pair; if the corresponding burning time of the first sample data pair of the hot blast stove is within the preset burning time range, judging whether the corresponding burning waste gas temperature of the first sample data pair is within the preset burning waste gas temperature range; if the temperature of the corresponding burning furnace waste gas of the first sample data pair is not within the preset burning furnace waste gas temperature range, discarding the first sample data pair; if the temperature of the corresponding furnace burning waste gas of the first sample data pair is within the preset furnace burning waste gas temperature range, judging whether the average value of the temperature of the corresponding furnace burning vault of the first sample data pair is larger than a preset vault temperature threshold value or not; if the average value of the temperature of the corresponding furnace vault of the first sample data pair is smaller than or equal to a preset vault temperature threshold value, discarding the first sample data pair; and if the average value of the corresponding furnace vault temperatures of the first sample data pair is larger than the preset vault temperature threshold value, the first sample data pair is used as a second sample data pair to be stored in a sample database.
Randomly selecting a first preset number of second sample data pairs from the sample database as third sample data pairs; then generating a second preset number of initial data sets; randomly selecting a third preset number of third sample data pairs from all third sample data pairs as fourth sample data pairs aiming at each initial data set, and storing the fourth sample data pairs into the initial data set to obtain a sample data set; obtaining a second preset number of sample data sets, wherein each sample data set comprises a third preset number of fourth sample data pairs; and randomly selecting sample data sets with preset proportions from all sample data sets to serve as training data sets, and taking the remaining unselected sample data sets as test data sets.
The model training module 3 builds a first gas consumption prediction model aiming at each training data set, the first gas consumption prediction model predicts a gas demand predicted value by utilizing the training data set based on a lifting decision tree algorithm, and carries out model iterative training according to errors of the gas demand predicted value and a corresponding true value to obtain a trained second gas consumption prediction model.
Referring to fig. 6, the steps specifically include: constructing a first gas consumption prediction model aiming at each sample data set in the training data set; firstly, presetting an initialization function h 0 (x) =0, where x represents the thermal bias in the fourth sample data pair; then each fourth sample data pair is utilized to calculate and obtain residual error r m The residual error r m The calculation formula of (2) is as follows:
r m ＝y m -h m-1 (x m )
wherein m is an integer greater than zero and less than or equal to a third preset number; y is m Representing a next furnace gas demand in an mth fourth sample data pair of the sample data set; x is x m Representing a thermal bias in an mth fourth sample data pair of the sample data set;
utilizing residual error r m Fitting to obtain decision function T (x; θ) m ) Wherein θ m Representing decision function parameters; based on decision function T (x; θ) m ) Calculating to obtain a gas demand predicted value h m (x) The predicted value h of the gas demand m (x) The calculation formula of (2) is as follows:
h m (x)＝h m-1 (x)+T(x；θ m )
by using the predicted value h of the gas demand m (x) Calculating to obtain square loss error L (y m ，h m (x) Error of square loss L (y) m ，h m (x) The calculation formula of (c) is:
L(y m ，h m (x))＝(y m -h m (x)) 2 ＝[r m -T(x；θ m )] 2
determine the square loss error L (y) m ，h m (x) Whether less than or equal to a preset error threshold; if the square loss error L (y m ，h m (x) If the gas demand predicted value is greater than the preset error threshold value, the gas demand predicted value and the square loss error are circularly calculated again by using the next fourth sample data pair until all the fourth sample data pairs in the training data set are calculated; if the square loss error L (y m ，h m (x) Less than or equal to the preset error threshold, using a decision function T (x; θ m ) Obtaining a second gas consumption prediction model h M (x) Second gas consumption prediction model h M (x) The calculation formula of (2) is as follows:
wherein M is a third preset number.
The second gas consumption prediction model is obtained through training of the lifting decision tree algorithm adopted by the embodiment of the invention, and the trained prediction model can accurately predict the actual gas amount required by the next furnace firing according to the thermal deviation of the current furnace.
The model verification combination module 4 is used for carrying out model cross verification processing on the second gas consumption prediction model by using the test data set to obtain verified third gas consumption prediction models, and carrying out weighted combination processing on all the third gas consumption prediction models to obtain a gas consumption prediction combination model.
Referring to fig. 7, the steps specifically include: for each second gas consumption prediction model h M (x) Inputting the thermal deviation in each fourth sample data pair in the test data set into the second gas consumption prediction model h M (x) Obtaining a corresponding model test predicted value
Testing predictive value using all models->
Calculating to obtain a model cross validation parameter R 2 The above model cross-validation parameter R 2 The calculation formula of (2) is as follows:
wherein i is an integer greater than zero; y is i Representing the next furnace gas demand in the ith fourth sample data pair in the test data set;
representing y i Testing a predicted value by a corresponding model; />
Representing the mean value of thermal deviations for all fourth sample data pairs in the test dataset;
judging the cross validation parameter R of the model 2 Whether the verification value is larger than a preset verification threshold value or not; if the model cross-verifies the parameter R 2 If the gas consumption is larger than the preset verification threshold, the second gas consumption prediction model is used as a third gas consumption prediction model; if the model cross-verifies the parameter R 2 And if the gas consumption prediction model is smaller than or equal to the preset verification threshold value, discarding the second gas consumption prediction model.
And carrying out weighted average treatment by using all the third gas consumption models, and calculating to obtain a gas consumption prediction combination model H (x), wherein the calculation formula of the gas consumption prediction combination model H (x) is as follows:
wherein k is an integer greater than zero; n is the total number of the third gas consumption prediction model; h is a k (x) Representing a kth prediction model in all third gas consumption prediction models; w (w) k Represents h k (k) Corresponding preset weight parameters;
the above w k The calculation mode of (a) is as follows: firstly, inputting preset thermal deviation into each third gas consumption prediction model to obtain gas consumption prediction values, taking all the gas consumption prediction values as a set U, classifying data in the set U according to preset interval values, and obtaining w corresponding to each third gas consumption prediction model according to interval proportion of the gas consumption prediction values corresponding to each third gas consumption prediction model k 。
The embodiment of the invention discloses a gas consumption prediction method, which comprises the steps of firstly, detecting the temperature of a blast furnace hot blast stove, and calculating to obtain the current stove heat deviation of the hot blast stove according to the detection result; taking the current furnace heat deviation and the next furnace gas demand as sample data pairs, and generating a training data set and a testing data set by utilizing the sample data pairs subjected to data screening; constructing a first gas consumption prediction model by using a training data set, and performing model training based on a lifting decision tree algorithm to obtain a trained second gas consumption prediction model; performing model verification processing on the second gas consumption prediction model by using the test data set to obtain a third gas consumption prediction model passing verification; and finally, carrying out weighted combination treatment by using a third gas consumption prediction model to obtain a gas consumption prediction combination model. The embodiment of the invention realizes the prediction of the gas consumption of the blast furnace hot blast stove, and effectively improves the accuracy of the gas consumption prediction.
In addition, the embodiment of the invention also provides a gas consumption prediction device, which comprises: a processor and a memory; the memory is used for storing one or more program instructions; the processor is configured to execute one or more program instructions for performing the steps of a gas usage prediction method as defined in any one of the preceding claims.
In addition, the embodiment of the invention also provides a computer readable storage medium, wherein a computer program is stored on the computer readable storage medium, and the computer program realizes the steps of the gas consumption prediction method according to any one of the above steps when being executed by a processor.
In the embodiment of the invention, the processor may be an integrated circuit chip with signal processing capability. The processor may be a general purpose processor, a digital signal processor (Digital Signal Processor, DSP for short), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), a field programmable gate array (Field Programmable GateArray, FPGA for short), or other programmable logic device, discrete gate or transistor logic device, discrete hardware components.
The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present invention may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The processor reads the information in the storage medium and, in combination with its hardware, performs the steps of the above method.
The storage medium may be memory, for example, may be volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory.
The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable ROM (Electrically EPROM, EEPROM), or a flash Memory.
The volatile memory may be a random access memory (Random Access Memory, RAM for short) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous DRAM (SLDRAM), and direct memory bus RAM (Direct Rambus RAM, DRRAM).
The storage media described in embodiments of the present invention are intended to comprise, without being limited to, these and any other suitable types of memory.
Those skilled in the art will appreciate that in one or more of the examples described above, the functions described in the present invention may be implemented in a combination of hardware and software. When the software is applied, the corresponding functions may be stored in a computer-readable medium or transmitted as one or more instructions or code on the computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
While the invention has been described in detail in the foregoing general description and specific examples, it will be apparent to those skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.
Claims (10)
1. A method for predicting gas usage, the method comprising:
Temperature detection is carried out on the burning process and the air supply process of the blast furnace hot blast stove to obtain detection results, the detection results are input into a thermal deviation model, and the current furnace thermal deviation of the hot blast stove is calculated;
using the current furnace heat deviation and the next furnace gas demand as first sample data pairs, carrying out data screening on all the first sample data pairs to obtain second sample data pairs, and obtaining a training data set and a testing data set by using the second sample data pairs;
constructing a first gas consumption prediction model aiming at each training data set, wherein the first gas consumption prediction model predicts a gas demand predicted value by utilizing the training data set based on a lifting decision tree algorithm, and carries out model iterative training according to the error of the gas demand predicted value and a corresponding true value to obtain a trained second gas consumption prediction model;
and performing model cross validation processing on the second gas consumption prediction model by using the test data set to obtain a third gas consumption prediction model which passes validation, and performing weighted combination processing on all the third gas consumption prediction models to obtain a gas consumption prediction combination model.
2. The method for predicting the gas consumption according to claim 1, wherein the temperature detection is performed on the burning process and the air supply process of the blast furnace hot blast stove to obtain a detection result, the detection result is input into a thermal deviation model, and the current stove thermal deviation of the hot blast stove is calculated, comprising:
in the burning process of the hot blast stove, carrying out first temperature detection on the hot blast stove according to a preset period to obtain the temperature of a vault of the hot blast stove and the temperature of waste gas of the hot blast stove;
inputting the temperature of the vault of the burning furnace and the waste temperature of the burning furnace into a preset heat storage soft measurement model, and calculating to obtain the total heat Q absorbed by the burning furnace of the hot blast stove in the burning furnace time xr The furnace absorbs the total heat Q xr The calculation formula of (2) is as follows:
wherein t is n Representing the duration time of the burning process of the hot blast stove; t (T) g Indicating the temperature of the furnace vault; t (T) f Representing the waste temperature of the burning furnace;
in the air supply process of the hot blast stove, carrying out second temperature detection on the hot blast stove according to the preset period to obtain cold air temperature before entering the stove and hot air temperature after entering the stove;
calculating an air supply temperature difference T by using the cold air temperature and the hot air temperature pc ；
Temperature difference T of the air supply pc And air supply quantity V lf Inputting the total heat quantity into a preset heat release soft measurement model, and calculating to obtain total heat quantity Q released by the air supply of the hot air furnace in the air supply time fr The air supply releases the total heat Q fr The calculation formula of (2) is as follows:
wherein t is m The duration time of the air supply process of the hot blast stove is represented;
the total heat quantity Q is absorbed by the burning furnace xr And the total heat released by the air supply Q fr Calculating to obtain the heat deviation Q of the hot blast stove pc The thermal deviation Q pc The calculation formula of (2) is as follows: q (Q) pc ＝Q xr -Q fr 。
3. The method of predicting gas usage as set forth in claim 2, wherein the data screening all of the first sample data pairs using the current furnace heat deviation and the next furnace gas demand as first sample data pairs to obtain second sample data pairs, comprises:
using the current furnace heat deviation and the next furnace gas demand as a first sample data pair;
judging whether the burning time of the hot blast stove corresponding to each first sample data pair is within a preset burning time range or not;
if the stove burning time of the hot blast stove corresponding to the first sample data pair is not within the preset stove burning time range, discarding the first sample data pair;
if the burning time of the hot blast stove corresponding to the first sample data pair is within the preset burning time range, judging whether the temperature of the burning waste gas corresponding to the first sample data pair is within the preset burning waste gas temperature range;
Discarding the first sample data pair if the temperature of the corresponding furnace burning waste gas of the first sample data pair is not within the preset furnace burning waste gas temperature range;
if the temperature of the furnace burning waste gas corresponding to the first sample data pair is within the preset furnace burning waste gas temperature range, judging whether the average value of the furnace burning vault temperatures corresponding to the first sample data pair is larger than a preset vault temperature threshold value;
discarding the first sample data pair if the average value of the furnace vault temperatures corresponding to the first sample data pair is smaller than or equal to a preset vault temperature threshold;
and if the average value of the furnace vault temperatures corresponding to the first sample data pair is larger than a preset vault temperature threshold value, the first sample data pair is used as a second sample data pair to be stored in the sample database.
4. A gas usage prediction method according to claim 3, wherein obtaining training data sets and test data sets using the second sample data pairs comprises:
randomly selecting a first preset number of second sample data pairs from the sample database as third sample data pairs;
generating a second preset number of initial data sets;
Randomly selecting a third sample data pair with a third preset number from all the third sample data pairs as a fourth sample data pair for each initial data set, and storing the fourth sample data pair into the initial data set to obtain a sample data set;
randomly selecting a sample data set with a preset proportion from all the sample data sets as a training data set, and taking the remaining unselected sample data sets as test data sets.
5. The method for predicting gas consumption according to claim 4, wherein a first gas consumption prediction model is constructed for each training data set, the first gas consumption prediction model predicts a gas demand predicted value by using the training data set based on a lifting decision tree algorithm, and performs model iterative training according to errors of the gas demand predicted value and a corresponding true value, to obtain a trained second gas consumption prediction model, and the method comprises the steps of:
presetting an initialization function h for each sample data set in the training data set 0 (x) =0, wherein x represents the thermal bias in the fourth sample data pair;
calculating a residual error r by using each fourth sample data pair m The residual error r m The calculation formula of (2) is as follows:
r m ＝y m -h m-1 (x m )
wherein m is an integer greater than zero and less than or equal to a third preset number; y is m Representing a next furnace gas demand in an mth fourth sample data pair of the sample data set; x is x m Representing a thermal bias in an mth fourth sample data pair of the sample data set;
utilizing the residual error r m Fitting to obtain decision function T (x; θ) m ) Wherein θ m Representing decision function parameters;
according to the decision function T (x; θ) m ) Calculating to obtain a gas demand predicted value h m (x) The predicted value h of the gas demand m (x) The calculation formula of (2) is as follows:
h m (x)＝h m-1 (x)+T(x；θ m )
by using the gas demand predicted value h m (x)Calculating to obtain square loss error L (y m ，h m (x) And the square loss error L (y) m ，h m (x) The calculation formula of (c) is:
L(y m ，h m (x))＝(y m -h m (x)) 2 ＝[r m -T(x；θ m )] 2
determining the square loss error L (y m ，h m (x) Whether less than or equal to a preset error threshold;
if the square loss error L (y m ，h m (x) If the gas demand predicted value is larger than the preset error threshold value, circulating to recalculate the gas demand predicted value and the square loss error by using the next fourth sample data pair;
if the square loss error L (y m ，h m (x) Less than or equal to the preset error threshold, then using the decision function T (x; θ m ) Obtaining a second gas consumption prediction model h M (x) The second gas consumption prediction model h M (x) The calculation formula of (2) is as follows:
wherein M is the third preset number.
6. The method of claim 5, wherein performing a model cross-validation process on the second gas usage prediction model using the test dataset to obtain a validated third gas usage prediction model, comprising:
for each second gas consumption prediction model h M (x) Inputting the thermal deviation in each fourth sample data pair in the test data set into the second gas usage prediction model h M (x) Calculating to obtain corresponding model test predicted values
Testing predicted values using all of the models
Calculating to obtain a model cross validation parameter R 2 The model cross-validation parameter R 2 The calculation formula of (2) is as follows:
wherein i is an integer greater than zero; y is i Representing a next furnace gas demand in an ith fourth sample data pair in the test data set;
representing y i Testing a predicted value by a corresponding model; />
A mean value of thermal deviations representing all fourth sample data pairs in the test dataset;
judging the model cross validation parameter R 2 Whether the verification value is larger than a preset verification threshold value or not;
if the model cross-verifies the parameter R 2 If the gas consumption is larger than the preset verification threshold, the second gas consumption prediction model is used as a third gas consumption prediction model;
if the model cross-verifies the parameter R 2 And if the gas consumption prediction model is smaller than or equal to the preset verification threshold value, discarding the second gas consumption prediction model.
7. The method for predicting gas consumption according to claim 6, wherein the step of performing weighted combination processing on all the third gas consumption prediction models to obtain a gas consumption prediction combination model comprises the steps of:
and carrying out weighted average treatment by using all the third gas consumption models, and calculating to obtain a gas consumption prediction combination model H (x), wherein the calculation formula of the gas consumption prediction combination model H (x) is as follows:
wherein k is an integer greater than zero; n is the total number of the third gas consumption prediction model; h is a k (x) Representing the kth model in all the third gas usage prediction models; w (w) k Represents h k (x) Corresponding preset weight parameters.
8. A gas usage prediction system, the system comprising:
the thermal deviation operation module is used for detecting the temperature of the burning process and the air supply process of the blast furnace hot blast stove to obtain a detection result, inputting the detection result into the thermal deviation model, and calculating to obtain the current stove thermal deviation of the hot blast stove;
The data processing module is used for taking the current furnace heat deviation and the next furnace gas demand as first sample data pairs, carrying out data screening on all the first sample data pairs to obtain second sample data pairs, and obtaining a training data set and a test data set by using the second sample data pairs;
the model training module is used for constructing a first gas consumption prediction model aiming at each training data set, the first gas consumption prediction model is based on a lifting decision tree algorithm, a gas demand predicted value is predicted by utilizing the training data set, and model iterative training is carried out according to errors of the gas demand predicted value and a corresponding true value, so that a trained second gas consumption prediction model is obtained;
and the model verification combination module is used for carrying out model cross verification processing on the second gas consumption prediction model by utilizing the test data set to obtain a verified third gas consumption prediction model, and carrying out weighted combination processing on all the third gas consumption prediction models to obtain a gas consumption prediction combination model.
9. A gas usage prediction apparatus, the apparatus comprising: a processor and a memory;
The memory is used for storing one or more program instructions;
the processor is configured to execute one or more program instructions for performing the steps of a gas usage prediction method as claimed in any one of claims 1 to 7.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the gas usage prediction method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310075854.5A CN116127843A (en) | 2023-02-07 | 2023-02-07 | Method, system, equipment and storage medium for predicting gas consumption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310075854.5A CN116127843A (en) | 2023-02-07 | 2023-02-07 | Method, system, equipment and storage medium for predicting gas consumption |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116127843A true CN116127843A (en) | 2023-05-16 |
Family
ID=86304366
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310075854.5A Pending CN116127843A (en) | 2023-02-07 | 2023-02-07 | Method, system, equipment and storage medium for predicting gas consumption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116127843A (en) |
-
2023
- 2023-02-07 CN CN202310075854.5A patent/CN116127843A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20190019096A1 (en) | Estimator, estimation method, program and storage medium where program stored for model parameter estimation and model parameter estimation system | |
| CN102043877B (en) | Systems and methods for predicting heat transfer coefficients during quenching | |
| CN109086545B (en) | Engine bench calibration test optimization method, computer equipment and system | |
| WO2019196481A1 (en) | Multi-split air conditioning system communication matching method and apparatus | |
| CN110442974B (en) | Method and device for optimizing performance of regenerative chamber of horseshoe flame glass kiln | |
| CN112036100A (en) | Method for predicting hearth oxygen concentration by using regression algorithm based on numerical simulation | |
| Chong et al. | Uncertainty analysis and parameter estimation of HVAC systems in building energy models | |
| JP6776858B2 (en) | Air conditioning control programs, equipment, and methods | |
| CN111396979A (en) | Central hot water system and rapid preheating method thereof | |
| CN116127843A (en) | Method, system, equipment and storage medium for predicting gas consumption | |
| WO2023241682A1 (en) | Temperature prediction method and apparatus for engine cooling system, device, medium, and vehicle | |
| CN117081724A (en) | Estimation method for instance calculated amount of problem with error learning | |
| CN113158589A (en) | Simulation model calibration method and device of battery management system | |
| CN115290218A (en) | Soft measurement method and system for wall temperature of boiler water wall of thermal generator set | |
| CN114038513A (en) | Method, device and terminal for predicting mass concentration of hydrogen sulfide in coal-fired boiler | |
| CN110543108A (en) | Heating system measurement data correction method and system based on mechanism model prediction | |
| CN112082786B (en) | Method and device for predicting normal operation performance of air preheater of generator set | |
| CN110285444B (en) | Method and device for regulating and controlling gas boiler | |
| Peyton Jones et al. | A comparative study of fixed-gain classical knock control strategies | |
| Wohlthan et al. | Modular fault diagnosis system for engine test bed measurements | |
| CN1763478A (en) | Hot spot detection method for air preheater based on fuzzy kernel function support vector machine | |
| CN109635404B (en) | Steam pipeline pressure drop estimation method, device and system | |
| Jean et al. | Trustworthy estimation and control of engine knocking level for transient operation | |
| CN111967150A (en) | Cooling capacity calculation method and device, computer equipment and storage medium | |
| CN112504689B (en) | Engine knock detection method, device, equipment and storage medium |
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 |