CN115600496A - Prediction method of multi-fuel combustion performance parameters, model training method and equipment - Google Patents
Prediction method of multi-fuel combustion performance parameters, model training method and equipment Download PDFInfo
- Publication number
- CN115600496A CN115600496A CN202211254267.4A CN202211254267A CN115600496A CN 115600496 A CN115600496 A CN 115600496A CN 202211254267 A CN202211254267 A CN 202211254267A CN 115600496 A CN115600496 A CN 115600496A
- Authority
- CN
- China
- Prior art keywords
- index
- sample
- combustion
- training
- preset
- 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
- 239000000446 fuel Substances 0.000 title claims abstract description 162
- 238000002485 combustion reaction Methods 0.000 title claims abstract description 161
- 238000012549 training Methods 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000002156 mixing Methods 0.000 claims abstract description 77
- 239000003245 coal Substances 0.000 claims abstract description 66
- 238000013528 artificial neural network Methods 0.000 claims abstract description 38
- 229910052799 carbon Inorganic materials 0.000 claims abstract description 34
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims abstract description 33
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 claims abstract description 32
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 claims abstract description 16
- 229910052757 nitrogen Inorganic materials 0.000 claims abstract description 16
- 229910052717 sulfur Inorganic materials 0.000 claims abstract description 16
- 239000011593 sulfur Substances 0.000 claims abstract description 16
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims abstract description 15
- 239000001257 hydrogen Substances 0.000 claims abstract description 15
- 229910052739 hydrogen Inorganic materials 0.000 claims abstract description 15
- 239000001301 oxygen Substances 0.000 claims abstract description 15
- 229910052760 oxygen Inorganic materials 0.000 claims abstract description 15
- 238000010438 heat treatment Methods 0.000 claims abstract description 4
- 125000004435 hydrogen atom Chemical class [H]* 0.000 claims abstract 3
- 239000002028 Biomass Substances 0.000 claims description 46
- 239000002910 solid waste Substances 0.000 claims description 31
- 230000006870 function Effects 0.000 claims description 30
- 238000004458 analytical method Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 24
- 238000012360 testing method Methods 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 6
- 239000002131 composite material Substances 0.000 claims description 3
- 238000013210 evaluation model Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 11
- 150000002431 hydrogen Chemical class 0.000 description 8
- 238000010248 power generation Methods 0.000 description 7
- 238000011160 research Methods 0.000 description 7
- 239000010802 sludge Substances 0.000 description 5
- 239000010902 straw Substances 0.000 description 5
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 4
- 230000008901 benefit Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 239000003814 drug Substances 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000003344 environmental pollutant Substances 0.000 description 4
- 231100000719 pollutant Toxicity 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000000921 elemental analysis Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- MWUXSHHQAYIFBG-UHFFFAOYSA-N nitrogen oxide Inorganic materials O=[N] MWUXSHHQAYIFBG-UHFFFAOYSA-N 0.000 description 3
- 230000004580 weight loss Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000008021 deposition Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 239000003039 volatile agent Substances 0.000 description 2
- UGFAIRIUMAVXCW-UHFFFAOYSA-N Carbon monoxide Chemical compound [O+]#[C-] UGFAIRIUMAVXCW-UHFFFAOYSA-N 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 229910052783 alkali metal Inorganic materials 0.000 description 1
- 229910001514 alkali metal chloride Inorganic materials 0.000 description 1
- 229910052936 alkali metal sulfate Inorganic materials 0.000 description 1
- 150000001340 alkali metals Chemical class 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 150000001805 chlorine compounds Chemical class 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000006477 desulfuration reaction Methods 0.000 description 1
- 230000023556 desulfurization Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000003546 flue gas Substances 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 235000021190 leftovers Nutrition 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 229910052751 metal Inorganic materials 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000010813 municipal solid waste Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XTQHKBHJIVJGKJ-UHFFFAOYSA-N sulfur monoxide Chemical class S=O XTQHKBHJIVJGKJ-UHFFFAOYSA-N 0.000 description 1
- 229910052815 sulfur oxide Inorganic materials 0.000 description 1
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"
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Tourism & Hospitality (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention provides a prediction method of multi-fuel combustion performance parameters, a model training method and equipment, wherein the method comprises the following steps: acquiring data of a preset characteristic parameter combination of a multi-fuel blending sample to be detected; inputting data of a preset characteristic parameter combination into a trained fire coal performance prediction model to obtain a flammability index and a comprehensive combustion characteristic index of a multi-fuel blending sample to be tested; the fire coal performance prediction model is obtained by training a pre-constructed neural network based on data combined by preset characteristic parameters of training samples, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function; the preset characteristic parameter combination comprises at least two of low-grade heating value, moisture, ash content, volatile matter, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of the multi-fuel blending sample to be detected. The invention can accurately predict the combustion characteristics of multiple fuels.
Description
Technical Field
The invention relates to the technical field of fire coal, in particular to a prediction method of multi-fuel combustion performance parameters, a model training method and equipment.
Background
With the increasing severity of the phenomenon of relative shortage of coal, great attention is paid to the development and utilization of biomass fuel which is rich in resources, strong in reproducibility, beneficial to improving the environment and sustainable development in the power generation industry, the biomass fuel is actively developed, the biomass power generation technology is developed in order, and the biomass power generation technology becomes a research hotspot at present.
Compared with the traditional fossil energy, the biomass fuel has low sulfur content and nitrogen content, and the discharge amount of sulfur oxides and nitrogen oxides after combustion is low, so that the biomass fuel is an environment-friendly fuel, and the flue gas after combustion generally does not need to be provided with desulfurization equipment. However, biomass fuel has a high alkali metal content and a low ash melting point, and may be in a molten state in a high-temperature environment in a furnace, and easily adhere to the surface of a heated surface. In addition, the alkali metal sulfates and chlorides attack the metal walls at high temperatures, potentially resulting in shortened service life of the pipe walls. Therefore, the co-combustion proportion of the biomass fuel must be controlled.
However, because the types of biomass fuels are many and the properties of each biomass fuel are different, the existing analysis means often has the conditions of data loss, hysteresis and the like, the optimal proportion of the fire coal, the biomass fuel and the combustible solid waste fuel cannot be reasonably determined, and the operation requirement of a boiler cannot be met. However, the existing methods for determining the combustion characteristics of fuels cannot accurately predict the combustion characteristics of multiple fuels, so a method for predicting the combustion characteristics of multiple fuels is needed, which is convenient for adjusting the ratio of the fire coal to the biomass fuel and the combustible solid waste fuel according to the combustion characteristics of the fuels before the multiple fuels are mixed and combusted.
Disclosure of Invention
The embodiment of the invention provides a multi-fuel combustion performance parameter prediction method, a model training method and equipment, and aims to solve the problem that the multi-fuel combustion characteristics cannot be accurately predicted at present.
In a first aspect, an embodiment of the present invention provides a method for predicting a multi-fuel combustion performance parameter, including:
acquiring data of a preset characteristic parameter combination of a multi-fuel blending sample to be detected;
inputting data of preset characteristic parameter combinations into a trained fire coal performance prediction model to obtain the flammability index and the comprehensive combustion characteristic index of a multi-fuel blending sample to be tested;
the fire coal performance prediction model is obtained by training a pre-constructed neural network based on data combined by preset characteristic parameters of training samples, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function; the preset characteristic parameter combination comprises at least two of low calorific value, moisture, ash content, volatile matter, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of the multi-fuel blending sample to be tested, and the first flammability index and the first comprehensive combustion characteristic index are obtained based on a weight and temperature change curve of the training sample.
In one possible implementation mode, the training sample comprises a plurality of experimental samples formed by mixing coal, a plurality of biomass fuels and a plurality of combustible solid waste fuels according to different mixing ratios;
the data of the preset characteristic parameter combination of each experimental sample is obtained based on industrial analysis and element analysis, and the first flammability index and the first comprehensive combustion characteristic index of each experimental sample are obtained based on a weight and temperature change curve of the experimental sample;
the fire coal performance prediction model is obtained by training for multiple times based on data of preset characteristic parameter combinations of each experimental sample, a second flammability index, a second comprehensive combustion characteristic index, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function; and the second flammability index and the second comprehensive combustion characteristic index are obtained by inputting data of a preset characteristic parameter combination of each experimental sample into a pre-constructed neural network.
In one possible implementation, the weight versus temperature curve includes a thermogravimetric curve and a thermogravimetric differential curve;
the first flammability index of each experimental sample is obtained from the maximum burning rate and the ignition temperature determined by the thermogravimetric curve and the thermogravimetric differential curve of the experimental sample;
the first composite burn characteristic index for each test sample is obtained from the maximum burn rate, the ignition temperature, the burnout temperature, and the average burn rate determined from the thermogravimetric curve and the thermogravimetric differential curve of that test sample.
In one possible implementation manner, the obtaining data of the preset characteristic parameter combination of the multi-fuel blending sample to be tested includes:
respectively carrying out industrial analysis and element analysis on the multi-fuel blending sample to be detected to obtain data of a preset characteristic parameter combination of the multi-fuel blending sample to be detected;
and carrying out standardization processing on the data of the preset characteristic parameter combination.
In one possible implementation, the multi-fuel blending sample to be tested comprises at least two of raw coal, biomass fuel or combustible solid waste fuel.
In a second aspect, an embodiment of the present invention provides a method for training a prediction model of multiple fuel combustion performance parameters, including:
acquiring data of a preset characteristic parameter combination of a training sample, a first flammability index and a first comprehensive combustion characteristic index; the preset characteristic parameter combination comprises at least two of low-grade calorific value, moisture, ash content, volatile components, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of a multi-fuel blending sample to be tested, and the first flammability index and the first comprehensive combustion characteristic index are obtained based on a weight and temperature change curve of a training sample;
and training a pre-constructed neural network based on the data of the preset characteristic parameter combination, the first flammability index, the first comprehensive combustion characteristic index and a preset loss function to obtain a trained coal-fired performance prediction model.
In one possible implementation mode, the training sample comprises a plurality of experimental samples formed by mixing coal, a plurality of biomass fuels and a plurality of combustible solid waste fuels according to different mixing ratios;
the data of the preset characteristic parameter combination of each experimental sample is obtained based on industrial analysis and element analysis, and the first flammability index and the first comprehensive combustion characteristic index of each experimental sample are obtained based on the weight and temperature change curve of the experimental sample;
training a pre-constructed neural network based on data of a preset characteristic parameter combination, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function, comprising:
inputting the data of the preset characteristic parameter combination of each experimental sample into a pre-constructed neural network to obtain a second flammability index and a second comprehensive combustion characteristic index;
training a pre-constructed neural network based on data of a preset characteristic parameter combination, a second flammability index, a second comprehensive combustion characteristic index, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function of each experimental sample, testing a plurality of candidate trained neural networks based on a preset performance evaluation model, and determining a fire coal performance prediction model.
In one possible implementation, the weight versus temperature curve includes a thermogravimetric curve and a thermogravimetric differential curve;
determining the maximum burning rate, the peak temperature, the ignition temperature, the burnout temperature and the average burning rate of each experimental sample based on the thermogravimetric curve and the thermogravimetric differential curve;
the flammability index and the comprehensive combustion characteristic index of each experimental sample were determined based on the maximum combustion rate, peak temperature, ignition temperature, burnout temperature, and average combustion rate, respectively.
In a third aspect, an embodiment of the present invention provides a device for predicting a multi-fuel combustion performance parameter, including:
the data acquisition module is used for acquiring data of a preset characteristic parameter combination of a multi-fuel blending sample to be detected;
the prediction performance module is used for inputting data of the preset characteristic parameter combination into the trained coal combustion performance prediction model so as to obtain the flammability index and the comprehensive combustion characteristic index of the multi-fuel blending sample to be detected;
the fire coal performance prediction model is obtained by training a pre-constructed neural network based on data combined by preset characteristic parameters of training samples, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function; the preset characteristic parameter combination comprises at least two of low calorific value, moisture, ash content, volatile matter, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of the multi-fuel blending sample to be tested, and the first flammability index and the first comprehensive combustion characteristic index are obtained based on a weight and temperature change curve of the training sample.
In a fourth aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the method according to the first aspect or any possible implementation manner of the first aspect when executing the computer program.
In a fifth aspect, an embodiment of the present invention provides another electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the processor implements the steps of the method according to the second aspect or any one of the possible implementation manners of the second aspect.
In a sixth aspect, the present invention provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the steps of the method according to the first aspect or the first aspect, and any possible implementation manner of the second aspect or the second aspect.
The embodiment of the invention provides a method for predicting multi-fuel combustion performance parameters, a model training method and equipment. And then, inputting the data of the preset characteristic parameter combination of the multi-fuel blending sample to be detected into the fire coal performance prediction model, so as to obtain the flammability index and the comprehensive combustion characteristic index of the multi-fuel blending sample to be detected.
Therefore, when the mixed fuel formed by mixing the fire coal, the biomass fuel and the combustible solid waste is adopted for combustion, the flammability index and the comprehensive combustion characteristic index of the mixed fuel can be accurately predicted through the fire coal performance prediction model provided by the invention, so that a scientific basis can be provided for selecting a proper mixing combustion ratio, and the effects of reducing pollutant emission and ensuring normal operation of a boiler can be achieved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
FIG. 1 is a flow chart of an implementation of a method for training a predictive model of multi-fuel combustion performance parameters according to an embodiment of the present invention;
FIG. 2 is a block diagram of a training process for the neural network provided in FIG. 1;
FIG. 3 is a flowchart illustrating an implementation of a method for predicting multi-fuel combustion performance parameters according to an embodiment of the present invention;
FIG. 4 is a schematic structural diagram of a multi-fuel combustion performance parameter prediction device provided by an embodiment of the invention;
fig. 5 is a schematic diagram of an electronic device provided in an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
To make the objects, technical solutions and advantages of the present invention more apparent, the following description will be made by way of specific embodiments with reference to the accompanying drawings.
Along with the rapid increase of the power demand, the mixed combustion of coal, biomass fuel and combustible solid waste fuel is a low-carbon development direction of coal power, the mixed combustion power generation of the biomass fuel and the combustible solid waste fuel can directly utilize the advantage of high power generation efficiency of a large-capacity high-parameter coal-fired power generator set, the coal consumption is reduced, the carbon emission is reduced, the problem of treatment of the biomass and combustible solid waste is solved, and the coal-fired power generation system has good social benefit and environmental benefit.
For the biomass co-combustion boiler, because the coal quality characteristics and combustion performance of biomass and conventional coal are greatly different, and the coal quality characteristics of different biomasses are also greatly different, reasonable adjustment measures need to be taken in time to ensure that the boiler always runs in an optimal state. However, due to frequent change of the type and the property of the biomass fuel, the existing analysis means often has the conditions of data loss, hysteresis and the like, and can not meet the operation requirement of the boiler.
When biomass or combustible solid waste is co-combusted at a high proportion, unplanned furnace shutdown accidents such as unstable boiler combustion occur, which are closely related to unreasonable co-combustion proportion. Moreover, the existing blending combustion technology mostly aims at blending combustion of coal, or blending combustion of a single biomass and coal, or blending combustion of a single combustible solid waste and coal, but is insufficient in research and development of simultaneous blending combustion technology for various types of biomass and combustible solid waste. When various biomass fuels and combustible solid waste fuels are simultaneously mixed with coal, effective operation suggestions of the boiler cannot be correspondingly given due to the difficulty in obtaining the combustion characteristics of the fuels by common means.
At present, a weighted average method is mostly adopted for the research of the mixed combustion performance of coal and biomass, linear optimization models with different co-combustion proportions are established on the basis of the weighted average method, and a linear programming method is adopted to solve the models so as to obtain an optimized co-combustion scheme. However, the combustion performance of coal and biomass fuel species is far from each other, the coal and biomass mixed combustion and the single-component combustion have obvious difference, many combustion performance parameters cannot simply represent the weighted average of corresponding indexes of the single component, and the combustion process of the coal and biomass mixed combustion has interaction of different degrees and often presents nonlinear characteristics. Therefore, intensive research and research on the mixed combustion of coal and various biomass fuels and intensive research on the prediction of the combustion performance parameters of the mixed combustion are required, and a more accurate prediction method of the combustion performance parameters of the mixed fuels of coal, various biomass and combustible solid waste is needed.
In order to solve the problems in the prior art, the embodiment of the invention provides a prediction method of multi-fuel combustion performance parameters, a model training method and equipment. The following first describes a training method of a prediction model of multi-fuel combustion performance parameters provided by the embodiment of the present invention.
Referring to fig. 1, it shows a flowchart for implementing the training method of the prediction model of the multi-fuel combustion performance parameters provided by the embodiment of the present invention, and the details are as follows:
step S110, data of a preset characteristic parameter combination of the training samples, the first flammability index and the first comprehensive combustion characteristic index are obtained.
The preset characteristic parameter combination comprises at least two of low-grade heating value, moisture, ash content, volatile component, fixed carbon, carbon ratio, hydrogen ratio, oxygen ratio, nitrogen ratio and sulfur ratio of the multi-fuel blending sample to be detected. The first flammability index and the first integrated combustion characteristic index are based on a weight versus temperature curve of the training sample.
Along with the increase of the power demand and the requirements on low carbon and environmental protection, various biomass fuels and various combustible solid waste fuels can be mixed with fire coal to form blended fuels, so that the requirements on low carbon and environmental protection can be met, and the requirements on power generation can also be met.
In some embodiments, in order to achieve a predictable combustion performance of multiple blended fuels, multiple elements or mixtures may be selected as training samples.
In this embodiment, the training sample includes a plurality of experimental samples obtained by mixing coal, a plurality of biomass fuels, and a plurality of combustible solid waste fuels according to a plurality of different mixing ratios.
The training sample can be a single type of biomass fuel, a single type of combustible solid waste and a single fire coal, or a mixed sample formed by the fire coal and the biomass fuel according to different mixing ratios, or a mixed sample formed by the fire coal and the combustible solid waste according to different mixing ratios, or a mixed sample formed by the fire coal, the biomass fuel and the combustible solid waste according to different mixing ratios. The training samples can be one or more of the above, and the more the types of the experimental samples contained in the training samples, the more the model finally obtained can test the samples to be tested.
For example, the biomass fuel may be straw, herb residue, etc., and the combustible solid waste may be sludge, combustible general solid waste, combustible garbage, leftovers, etc.
In this embodiment, after the training sample is obtained, the training sample needs to be processed, so as to obtain data of the preset feature parameter combination of the training sample.
In some embodiments, it is desirable to first perform an industrial analysis and an elemental analysis on the training samples to determine the components in the training samples.
In this example, the industrial analysis of the training sample resulted in the proportions of moisture (Mad), ash (Aad), volatile (Vad), fixed carbon (FCad) in the training sample, and the lower calorific value (qnet. And performing element analysis on the training sample to obtain the carbon ratio, the hydrogen ratio, the oxygen ratio, the nitrogen ratio and the sulfur ratio of the training sample.
The preset characteristic parameter combinations comprise at least two of low calorific value, moisture, ash content, volatile matter, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of the multi-fuel blending sample to be tested, and the preset characteristic parameter combinations can be selected according to a subsequent test result of a pre-constructed neural network.
In some embodiments, the flammability index and the integrated combustion characteristic index of the training sample may be obtained from the weight versus temperature curve of the training sample. And keeping the temperature rising rate of the training sample unchanged, and obtaining a thermogravimetric curve (TG) and a thermogravimetric differential curve (DTG) representing the weight and temperature change of the training sample by using a thermal weight difference-thermal comprehensive thermal analyzer.
Illustratively, the flammability index and the integrated combustion behavior index of the training sample may be determined by the following methods.
Step S1110, the maximum burning rate (d) of each experimental sample may be determined based on the thermogravimetric curve and the thermogravimetric differential curve m /d t ) max Peak temperature T max Ignition temperature T i Burnout temperature T h Average burning Rate (d) m /d t ) mean 。
Specifically, most preferablyHigh combustion rate (d) m /d t ) max And is the longitudinal coordinate value corresponding to the maximum weightlessness peak on the DTG curve. Maximum burning rate (d) m /d t ) max The larger the amount of volatiles released by the fuel per unit time, the easier it is to achieve the minimum concentration of volatiles required for a fire. Peak temperature T max The smaller the peak temperature is, the larger the amount of volatile components released by the fuel at a lower temperature, and the peak temperature is an important index for measuring the difficulty of ignition of the fuel.
Drawing a vertical line at the maximum burning rate point on the DTG curve, drawing a tangent line of the TG curve at the intersection point of the vertical line and the TG curve, wherein the temperature corresponding to the intersection point of the tangent line and a weight loss starting parallel line is the ignition temperature T i (ii) a The ignition temperature characterizes how easily the fuel ignites. The higher the ignition temperature, the more difficult the deposition of the volatile matter and the ignition of the fuel, and the lower the ignition temperature, the more difficult the deposition of the volatile matter and the easier the ignition of the fuel. The corresponding temperature when the weight loss of the fuel sample reaches 98 percent of the total weight loss is the burnout temperature T h 。
The average burn rate is calculated as:
wherein beta is the rate of temperature rise and alpha i Is the mass fraction, alpha, of the fuel sample on ignition h The higher the average burn rate, which is the mass fraction of the fuel sample as it burns off, indicates that the fuel burns off faster.
Step S1120, respectively determining the flammability index and the comprehensive combustion characteristic index of each experimental sample based on the maximum combustion rate, the peak temperature, the ignition temperature, the burnout temperature, and the average combustion rate.
Specifically, the combustion performance parameters include a flammability index and a comprehensive combustion performance index.
The flammability index C characterizes the ease of ignition of the fuel, with the greater the flammability index, the better the combustion and ignition stability of the fuel.
The flammability index C is calculated as:
the comprehensive combustion characteristic index S represents the ignition and burnout performance of the fuel, the larger the comprehensive combustion characteristic index is, the better the comprehensive combustion performance of the fuel is, and the calculation formula of the comprehensive combustion characteristic index S is as follows:
in order to make the data of the preset characteristic parameter combination, the flammability index of the training sample and the comprehensive combustion characteristic index comparable and eliminate the dimensional relationship among variables, before training the model, the data needs to be standardized.
For example, the data of the preset characteristic parameter combination, the flammability index of the training sample and the comprehensive combustion characteristic index are normalized, that is, the data are mapped to the value in the interval [ -1,1], and the normalization method formula is as follows:
wherein x is i As the original data, it is the original data,
for normalized data, x min Is the minimum value of the selected column, x max Is the maximum value of the selected column.
The data of the preset characteristic parameter combination, the flammability index and the comprehensive combustion characteristic index of the training sample are determined through the steps, and the pre-constructed neural network can be trained.
And S120, training a pre-constructed neural network based on data of a preset characteristic parameter combination, the first flammability index, the first comprehensive combustion characteristic index and a preset loss function to obtain a trained coal-burning performance prediction model.
In some embodiments, the pre-constructed neural network is a three-layer neural network comprising an input layer, an intermediate layer, and an output layer, and the activation function uses a Sigmoid function. The loss function uses a mean square error loss function (MSE), and the performance index evaluation uses a Mean Absolute Error (MAE) function.
Specifically, a mean square error loss function (MSE) value is calculated:
where n is the number of samples of the data set,
as a model output value, y i Are measured values.
The Mean Absolute Error (MAE) function value is calculated as follows:
where n is the number of samples of the data set, a i And b i And respectively representing the true value and the predicted value of each prediction task under different blending proportions.
In this example, the data of the preset characteristic parameter combinations for each experimental sample were input into a neural network constructed in advance to obtain a second flammability index and a second comprehensive combustion characteristic index.
Training a pre-constructed neural network based on data of a preset characteristic parameter combination, a second flammability index, a second comprehensive combustion characteristic index, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function of each experimental sample, testing a plurality of candidate trained neural networks based on a preset performance evaluation model, and determining the fire coal performance prediction model.
Specifically, as shown in fig. 2, the training process of the neural network is as follows: and repeatedly training the pre-constructed neural network by using the acquired data of the preset characteristic parameter combination of the training sample, the flammability index and the comprehensive combustion characteristic index of the training sample. And obtaining a predicted value through forward propagation, and modifying an updated variable through backward propagation until a proper mapping result is obtained. However, the more times of non-training, the more accurately the mapping relationship between input and output is reflected as a result. The collected sample data contains measurement noise, the training times are too many, and the neural network copies the noise, thereby affecting the generalization capability of the neural network. During the training process, the selection of the initial weight of the network can be generated by a random method. In order to avoid generating local extreme values, a plurality of groups of initial weights can be selected, and then a group of more ideal initial weights can be selected by checking test errors.
The method comprises the steps of training a neural network by adopting data of various preset characteristic parameter combinations of each experimental sample, obtaining various different neural networks by different training times, calculating the average absolute error of each neural network by using the predicted value of the neural network of each experimental sample, namely the second flammability index and the second comprehensive combustion characteristic index, and the first flammability index and the first comprehensive combustion characteristic index determined by a weight and temperature change curve, and determining the neural network with the minimum average absolute error as a fire coal performance prediction model.
After the fire coal performance prediction model is determined, the combustion performance of the multi-fuel blending sample to be tested can be predicted.
As shown in fig. 3, it shows a flowchart for implementing the method for predicting the multi-fuel combustion performance parameters provided by the embodiment of the present invention, and the detailed description is as follows:
and S310, acquiring data of a preset characteristic parameter combination of the multi-fuel blending sample to be detected.
The preset characteristic parameter combination comprises at least two of low-grade heating value, moisture, ash content, volatile matter, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of the multi-fuel blending sample to be detected.
The multi-fuel blending sample to be tested comprises at least two fuels of raw coal, biomass fuel or combustible solid waste fuel.
In some embodiments, in order to obtain data of the preset characteristic parameter combination of the multi-fuel blending sample to be tested, the multi-fuel blending sample to be tested needs to be subjected to industrial analysis and elemental analysis, respectively.
Specifically, the proportion of moisture (Mad), ash (Aad), volatile component (Vad) and fixed carbon (FCad) in the multi-fuel blending sample to be tested and the lower calorific value (qnet. And performing element analysis on the multi-fuel blending sample to be detected to obtain the carbon ratio, the hydrogen ratio, the oxygen ratio, the nitrogen ratio and the sulfur ratio of the multi-fuel blending sample to be detected.
In some embodiments, in order to make the data of the preset feature parameter combination comparable and eliminate the dimensional relationship between the variables, it is also required to perform a normalization process on the data of the preset feature parameter combination, and map the data into values in the interval [ -1,1 ].
For example, the preset characteristic parameter combination may be a low calorific value, moisture, ash, volatile matter, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of the multi-fuel blending sample to be tested.
And S320, inputting data of the preset characteristic parameter combination into the trained coal-fired performance prediction model to obtain the flammability index and the comprehensive combustion characteristic index of the multi-fuel blending sample to be tested.
The fire coal performance prediction model is obtained by training a pre-constructed neural network based on data combined by preset characteristic parameters of training samples, the first flammability index, the first comprehensive combustion characteristic index and a preset loss function. The first flammability index and the first integrated combustion characteristic index are based on a weight versus temperature curve of the training sample. The training process of the coal-fired performance prediction model is described in detail above and will not be described in detail here.
And inputting the data of the preset characteristic parameter combination after the standardization treatment into a trained fire coal performance prediction model, so as to accurately obtain the flammability index and the comprehensive combustion characteristic index of the multi-fuel blending sample to be detected.
Through the flammability index and the comprehensive combustion characteristic index of the obtained multi-fuel blending sample, the proper mixing proportion of the blended fuel can be conveniently selected, a theoretical basis is provided for the aspect of energy utilization, a proposal is provided for the effective operation of a boiler, and the method has great scientific research and practical significance for the reasonable comprehensive utilization of biomass fuel and combustible solid waste fuel and the reduction of pollutant emission.
According to the prediction method provided by the invention, before the combustion performance parameters of the multi-fuel blending sample to be tested are predicted, firstly, a pre-constructed network is trained by selecting data of a proper preset characteristic parameter combination from training samples, so that a trained coal combustion performance prediction model is obtained. Then, the flammability index and the comprehensive combustion characteristic index of the multi-fuel blending sample to be detected can be obtained by inputting the data of the preset characteristic parameter combination of the multi-fuel blending sample to be detected into the fire coal performance prediction model.
Therefore, when the mixed fuel formed by mixing the fire coal, the biomass fuel and the combustible solid waste is adopted for combustion, the flammability index and the comprehensive combustion characteristic index of the mixed fuel can be accurately predicted through the fire coal performance prediction model provided by the invention, so that a scientific basis can be provided for selecting a proper mixing combustion ratio, and the effects of reducing pollutant emission and ensuring normal operation of a boiler can be achieved.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by functions and internal logic of the process, and should not limit the implementation process of the embodiments of the present invention in any way.
The method for predicting the multi-fuel combustion performance parameter provided by the invention is explained in detail by using a specific embodiment as follows:
in this embodiment, lean coal, straw, sludge and medicine residue are used as a mixed fuel, and the combustion performance parameters of the mixed fuel are predicted.
The model used for prediction in this embodiment is the model for predicting the coal-fired performance, which is constructed by the present invention, and the model is directly used for prediction without further describing the training process of the model, and the accuracy of the model for predicting the coal-fired performance provided by the present invention is verified by comparing the flammability index and the comprehensive combustion characteristic index determined by using the weight and temperature change curve with the data obtained by using the model prediction.
And S410, crushing and grinding the lean coal, the straw, the sludge and the medicine dregs, and screening a sample with the particle size of 75-96 mu m.
Step S420, then carrying out industrial analysis and element analysis on the lean coal, the straws, the sludge and the medicine dregs to obtain the low calorific value, the moisture, the ash content, the volatile matter, the fixed carbon, the carbon proportion, the hydrogen proportion, the oxygen proportion, the nitrogen proportion and the sulfur proportion of the mixed fuel as shown in Table 1,
TABLE 1 Industrial and elemental analysis results of blended fuels
And S420, mixing the lean coal, the straws, the sludge and the medicine dregs according to the proportion in the table 2, and putting about 10mg of sample into a thermogravimetric-differential thermal comprehensive thermal analyzer for experiment.
The test conditions were: the gas flow is 100ml/min, the atmosphere is air, the temperature rise interval is from room temperature to 1000 ℃, and the temperature rise rate is 20 ℃/min.
TABLE 2 mixing ratio of each test sample
And calculating the flammability index and the comprehensive combustion characteristic index of each group of experimental samples according to the weight and temperature change curve.
Step S430, comprehensively calculating the data of the preset characteristic parameter combinations of each group of the experimental samples, namely the data of the lower calorific value, the moisture content, the ash content, the volatile components, the fixed carbon, the carbon ratio, the hydrogen ratio, the oxygen ratio, the nitrogen ratio and the sulfur ratio of the upper 23 groups of the experimental samples according to the proportions in the table 2 and the content in the table 1, standardizing the data of the preset characteristic parameter combinations, and inputting the data into a coal-fired performance prediction model respectively, so that the flammability index and the comprehensive combustion characteristic index of each group of the experimental samples can be predicted respectively. As shown in the table 3 below, the following examples,
TABLE 3 Experimental and predicted values for each experimental sample
As can be seen from Table 3, the maximum error between the prediction result obtained by using the coal-fired performance prediction model provided by the invention and the experimental result obtained by using the weight and temperature change curve is 5%, which indicates that the coal-fired performance prediction model provided by the invention has higher accuracy.
According to the invention, through researching and analyzing the mixed combustion performance of various different biomasses, different combustible solid wastes and fire coal, and calculating the combustion characteristics such as the flammability index and comprehensive combustion characteristic index of the mixed combustion fuel by using the trained neural network, a theoretical basis is provided for the aspect of energy utilization, a suggestion is provided for the effective operation of a boiler, and the method has great scientific research and practical significance for the reasonable comprehensive utilization of the biomasses and the combustible solid wastes and the reduction of pollutant emission.
Based on the multi-fuel combustion performance parameter prediction method provided by the embodiment, correspondingly, the invention also provides a specific implementation mode of the multi-fuel combustion performance parameter prediction device applied to the multi-fuel combustion performance parameter prediction method. Please see the examples below.
As shown in fig. 4, there is provided a multi-fuel combustion performance parameter prediction apparatus 400, comprising:
the data acquiring module 410 is used for acquiring data of a preset characteristic parameter combination of a multi-fuel blending sample to be detected;
the prediction performance module 420 is used for inputting data of preset characteristic parameter combinations into the trained coal-fired performance prediction model so as to obtain the flammability index and the comprehensive combustion characteristic index of the multi-fuel blending sample to be detected;
the fire coal performance prediction model is obtained by training a pre-constructed neural network based on data combined by preset characteristic parameters of training samples, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function; the preset characteristic parameter combination comprises at least two of low calorific value, moisture, ash content, volatile matter, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of the multi-fuel blending sample to be tested, and the first flammability index and the first comprehensive combustion characteristic index are obtained based on a weight and temperature change curve of the training sample.
In one possible implementation mode, the training sample comprises a plurality of experimental samples formed by mixing coal, a plurality of biomass fuels and a plurality of combustible solid waste fuels according to different mixing ratios;
the data of the preset characteristic parameter combination of each experimental sample is obtained based on industrial analysis and element analysis, and the first flammability index and the first comprehensive combustion characteristic index of each experimental sample are obtained based on the weight and temperature change curve of the experimental sample;
the fire coal performance prediction model is obtained by training for multiple times based on data of preset characteristic parameter combinations of each experimental sample, a second flammability index, a second comprehensive combustion characteristic index, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function; and the second flammability index and the second comprehensive combustion characteristic index are obtained by inputting data of a preset characteristic parameter combination of each experimental sample into a pre-constructed neural network.
In one possible implementation, the weight versus temperature curve includes a thermogravimetric curve and a thermogravimetric differential curve;
the first flammability index of each test sample is obtained from the maximum burn rate and ignition temperature determined from the thermogravimetric curve and the thermogravimetric differential curve of that test sample;
the first composite burn characteristic index for each test sample is obtained from the maximum burn rate, the ignition temperature, the burnout temperature, and the average burn rate determined from the thermogravimetric curve and the thermogravimetric differential curve of that test sample.
In a possible implementation manner, the acquiring data of the preset characteristic parameter combination of the multi-fuel blending sample to be detected includes:
respectively carrying out industrial analysis and element analysis on the multi-fuel blending sample to be detected to obtain data of a preset characteristic parameter combination of the multi-fuel blending sample to be detected;
and carrying out standardization processing on the data of the preset characteristic parameter combination.
In one possible implementation, the multi-fuel blending sample to be tested comprises at least two of raw coal, biomass fuel or combustible solid waste fuel.
Fig. 5 is a schematic diagram of an electronic device provided in an embodiment of the present invention. As shown in fig. 5, the electronic apparatus 5 of this embodiment includes: a processor 50, a memory 51 and a computer program 52 stored in said memory 51 and executable on said processor 50. The processor 50, when executing the computer program 52, implements the steps in the various multi-fuel combustion performance parameter prediction method embodiments described above, such as steps 310-320 shown in FIG. 3. Alternatively, the processor 50, when executing the computer program 52, implements the functions of the modules in the above device embodiments, such as the functions of the modules 410 to 420 shown in fig. 4.
Illustratively, the computer program 52 may be partitioned into one or more modules that are stored in the memory 51 and executed by the processor 50 to implement the present invention. The one or more modules may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 52 in the electronic device 5. For example, the computer program 52 may be divided into the modules 410 to 420 shown in fig. 4.
The electronic device 5 may include, but is not limited to, a processor 50 and a memory 51. Those skilled in the art will appreciate that fig. 5 is merely an example of an electronic device 5 and does not constitute a limitation of the electronic device 5 and may include more or fewer components than shown, or some components may be combined, or different components, e.g., the electronic device may also include input-output devices, network access devices, buses, etc.
The Processor 50 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 51 may be an internal storage unit of the electronic device 5, such as a hard disk or a memory of the electronic device 5. The memory 51 may also be an external storage device of the electronic device 5, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like, provided on the electronic device 5. Further, the memory 51 may also include both an internal storage unit and an external storage device of the electronic device 5. The memory 51 is used for storing the computer program and other programs and data required by the electronic device. The memory 51 may also be used to temporarily store data that has been output or is to be output.
It should be clear to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional units and modules is only used for illustration, and in practical applications, the above function distribution may be performed by different functional units and modules as needed, that is, the internal structure of the apparatus may be divided into different functional units or modules to perform all or part of the above described functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only used for distinguishing one functional unit from another, and are not used for limiting the protection scope of the present application. For the specific working processes of the units and modules in the system, reference may be made to the corresponding processes in the foregoing method embodiments, which are not described herein again.
In the above embodiments, the description of each embodiment has its own emphasis, and reference may be made to the related description of other embodiments for parts that are not described or recited in any embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other ways. For example, the above-described apparatus/electronic device embodiments are merely illustrative, and for example, the division of the modules or units is only one type of logical function division, and other division manners may exist in actual implementation, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one position, or may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow of the method of the embodiment described above can be realized by the present invention, and the computer program can be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program can realize the steps of the embodiments of the method for predicting the multi-fuel combustion performance parameters described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein.
Claims (10)
1. A method of predicting a multi-fuel combustion performance parameter, comprising:
acquiring data of a preset characteristic parameter combination of a multi-fuel blending sample to be detected;
inputting the data of the preset characteristic parameter combination into a trained fire coal performance prediction model to obtain the flammability index and the comprehensive combustion characteristic index of the multi-fuel blending sample to be tested;
the fire coal performance prediction model is obtained by training a pre-constructed neural network based on data combined by preset characteristic parameters of training samples, a first flammability index, a first comprehensive combustion characteristic index and a preset loss function; the preset characteristic parameter combination comprises at least two of low-grade heating value, moisture, ash content, volatile components, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of a multi-fuel blending sample to be detected, and the first flammability index and the first comprehensive combustion characteristic index are obtained based on a weight and temperature change curve of the training sample.
2. The prediction method of claim 1, wherein the training samples comprise a plurality of experimental samples prepared by mixing coal, a plurality of biomass fuels, and a plurality of combustible solid waste fuels according to a plurality of different mixing ratios;
the data of the preset characteristic parameter combination of each experimental sample is obtained based on industrial analysis and element analysis, and the first flammability index and the first comprehensive combustion characteristic index of each experimental sample are obtained based on the weight and temperature change curve of the experimental sample;
the fire coal performance prediction model is obtained by training for multiple times based on data of a preset characteristic parameter combination of each experimental sample, a second flammability index, a second comprehensive combustion characteristic index, a first flammability index, a first comprehensive combustion characteristic index and the preset loss function; and the second flammability index and the second comprehensive combustion characteristic index are obtained by inputting data of a preset characteristic parameter combination of each experimental sample into a pre-constructed neural network.
3. The method of predicting according to claim 2, wherein the weight versus temperature curve comprises a thermogravimetric curve and a thermogravimetric differential curve;
the first flammability index of each of said test samples is derived from the maximum burn rate and ignition temperature determined from the thermogravimetric curve and the thermogravimetric differential curve of that test sample;
the first composite combustion characteristic index of each of the test samples is obtained from the maximum combustion rate, the ignition temperature, the burnout temperature and the average combustion rate determined from the thermogravimetric curve and the thermogravimetric differential curve of the test sample.
4. The prediction method of claim 1, wherein the obtaining data of the predetermined characteristic parameter combination of the multi-fuel blending sample to be tested comprises:
respectively carrying out industrial analysis and element analysis on a multi-fuel blending sample to be detected to obtain data of a preset characteristic parameter combination of the multi-fuel blending sample to be detected;
and carrying out standardization processing on the data of the preset characteristic parameter combination.
5. The prediction method of any one of claims 1 to 4, wherein the multi-fuel blending sample to be tested comprises at least two of raw coal, biomass fuel or combustible solid waste fuel.
6. A method for training a predictive model of multi-fuel combustion performance parameters, comprising:
acquiring data of a preset characteristic parameter combination of a training sample, a first flammability index and a first comprehensive combustion characteristic index; the preset characteristic parameter combination comprises at least two of low-grade calorific value, moisture, ash, volatile matters, fixed carbon, carbon proportion, hydrogen proportion, oxygen proportion, nitrogen proportion and sulfur proportion of a multi-fuel blending sample to be tested, and the first flammability index and the first comprehensive combustion characteristic index are obtained based on a weight and temperature change curve of the training sample;
and training a pre-constructed neural network based on the data of the preset characteristic parameter combination, the first flammability index, the first comprehensive combustion characteristic index and a preset loss function to obtain a trained coal-fired performance prediction model.
7. The training method according to claim 6, wherein the training sample comprises a plurality of experimental samples obtained by mixing coal, a plurality of biomass fuels, and a plurality of combustible solid waste fuels according to a plurality of different mixing ratios;
the data of the preset characteristic parameter combination of each experimental sample is obtained based on industrial analysis and element analysis, and the first flammability index and the first comprehensive combustion characteristic index of each experimental sample are obtained based on the weight and temperature change curve of the experimental sample;
the training of the pre-constructed neural network based on the data of the preset characteristic parameter combination, the first flammability index, the first comprehensive combustion characteristic index and the preset loss function comprises the following steps:
inputting the data of the preset characteristic parameter combination of each experimental sample into a pre-constructed neural network to obtain a second flammability index and a second comprehensive combustion characteristic index;
and training the pre-constructed neural network based on the data of the preset characteristic parameter combination of each experimental sample, the second flammability index, the second comprehensive combustion characteristic index, the first flammability index, the first comprehensive combustion characteristic index and the preset loss function, testing a plurality of candidate trained neural networks based on a preset performance evaluation model, and determining the fire coal performance prediction model.
8. The training method of claim 7, wherein the weight versus temperature curve comprises a thermogravimetric curve and a thermogravimetric differential curve;
determining a maximum burn rate, a peak temperature, an ignition temperature, a burnout temperature, and an average burn rate for each of the experimental samples based on the thermogravimetric curve and the thermogravimetric differential curve;
the flammability index and the comprehensive combustion characteristic index of each of the test samples were respectively determined based on the maximum combustion rate, peak temperature, ignition temperature, burnout temperature, and average combustion rate.
9. An electronic device, comprising a memory for storing a computer program and a processor for invoking and running the computer program stored in the memory, performing the method of any one of claims 1 to 8.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of a method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211254267.4A CN115600496A (en) | 2022-10-13 | 2022-10-13 | Prediction method of multi-fuel combustion performance parameters, model training method and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211254267.4A CN115600496A (en) | 2022-10-13 | 2022-10-13 | Prediction method of multi-fuel combustion performance parameters, model training method and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115600496A true CN115600496A (en) | 2023-01-13 |
Family
ID=84846058
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211254267.4A Pending CN115600496A (en) | 2022-10-13 | 2022-10-13 | Prediction method of multi-fuel combustion performance parameters, model training method and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115600496A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992289A (en) * | 2023-08-02 | 2023-11-03 | 浙江大学 | Model fine adjustment-based incinerator material mixing thermal characteristic prediction method |
| CN117474278A (en) * | 2023-11-20 | 2024-01-30 | 中国电力工程顾问集团有限公司 | Coal-fired power plant deep peak regulation method and device for dynamic coal types |
| CN118035693A (en) * | 2024-04-12 | 2024-05-14 | 东莞理工学院 | Mineral admixture activity rapid prediction method based on artificial intelligence |
| CN118130545A (en) * | 2024-04-30 | 2024-06-04 | 北京华能长江环保科技研究院有限公司 | Method for determining combustion characteristics of solid recovery fuel |
-
2022
- 2022-10-13 CN CN202211254267.4A patent/CN115600496A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116992289A (en) * | 2023-08-02 | 2023-11-03 | 浙江大学 | Model fine adjustment-based incinerator material mixing thermal characteristic prediction method |
| CN116992289B (en) * | 2023-08-02 | 2024-03-19 | 浙江大学 | Model fine adjustment-based incinerator material mixing thermal characteristic prediction method |
| CN117474278A (en) * | 2023-11-20 | 2024-01-30 | 中国电力工程顾问集团有限公司 | Coal-fired power plant deep peak regulation method and device for dynamic coal types |
| CN118035693A (en) * | 2024-04-12 | 2024-05-14 | 东莞理工学院 | Mineral admixture activity rapid prediction method based on artificial intelligence |
| CN118130545A (en) * | 2024-04-30 | 2024-06-04 | 北京华能长江环保科技研究院有限公司 | Method for determining combustion characteristics of solid recovery fuel |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115600496A (en) | Prediction method of multi-fuel combustion performance parameters, model training method and equipment | |
| Aydın et al. | Performance and emission prediction of a compression ignition engine fueled with biodiesel-diesel blends: A combined application of ANN and RSM based optimization | |
| Pohit et al. | Optimization of performance and emission characteristics of diesel engine with biodiesel using grey‐taguchi method | |
| Sharma | Gene expression programming-based model prediction of performance and emission characteristics of a diesel engine fueled with linseed oil biodiesel/diesel blends: An artificial intelligence approach | |
| Rushdi et al. | Mechanistic prediction of ash deposition in a pilot-scale test facility | |
| Wang et al. | Kinetics investigation on the combustion of biochar in O 2/CO 2 atmosphere | |
| Kim et al. | Modeling on combustion characteristics of biocoalbriquettes | |
| Gurusamy et al. | Experimental evaluation of cottonseed oil-camphor binary blends on diesel engine performance, combustion, exhaust and cyclic variance parameters | |
| Lazaroiu et al. | Innovative renewable waste conversion technologies | |
| Wang et al. | Effect of volatile-char interaction on nitrogen oxide emission during combustion of blended coal | |
| CN114239311A (en) | Coal blending and blending method, device and computer readable storage medium | |
| Wang et al. | Numerical study on the influence of gasoline properties and thermodynamic conditions on premixed laminar flame velocity at multiple conditions | |
| Lai et al. | Effects of ethanol-blended fuel on combustion characteristics, gaseous and particulate emissions in gasoline direct injection (GDI) engines | |
| CN116401948A (en) | Online prediction method and system for generating amount of power station boiler ash based on LSTM | |
| Chen et al. | Numerical simulation of bed combustion in biomass-briquette boiler | |
| Silva et al. | Characterization of the physicochemical and thermal properties of different forest residues | |
| Joseph et al. | Review on combustion optimization methods in pulverised coal fired boiler | |
| Drosatos et al. | Numerical investigation of a coal-fired power plant main furnace under normal and reduced-oxygen operating conditions | |
| Liu et al. | Optimization of combustion characteristics of blended coals based on TOPSIS method | |
| Zhou et al. | Study on the thermogravimetric and combustion of coal slime | |
| CN111859711A (en) | Method for calculating ignition temperature of mixed coal and pulverized coal airflow after two single coal types are mixed and burned | |
| Singh et al. | Optimization of performance and emission characteristics of CI engine fueled with waste safflower oil biodiesel and its blends | |
| CN115564119A (en) | Prediction method of multi-fuel ash fusion temperature, model training method and equipment | |
| CN114036833B (en) | Method and device for acquiring wall thinning rate of coal-fired boiler and electronic equipment | |
| Miles et al. | Alkalis in alternative biofuels |
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 |