CN116935985A - Sensitivity analysis method for experimental parameter change in coal gasification process - Google Patents
Sensitivity analysis method for experimental parameter change in coal gasification process Download PDFInfo
- Publication number
- CN116935985A CN116935985A CN202310877965.8A CN202310877965A CN116935985A CN 116935985 A CN116935985 A CN 116935985A CN 202310877965 A CN202310877965 A CN 202310877965A CN 116935985 A CN116935985 A CN 116935985A
- Authority
- CN
- China
- Prior art keywords
- sensitivity
- data point
- model
- infinite
- coal
- 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.)
- Granted
Links
- 239000003245 coal Substances 0.000 title claims abstract description 192
- 238000002309 gasification Methods 0.000 title claims abstract description 156
- 238000000034 method Methods 0.000 title claims abstract description 129
- 238000010206 sensitivity analysis Methods 0.000 title claims abstract description 96
- 230000035945 sensitivity Effects 0.000 claims abstract description 206
- 238000013499 data model Methods 0.000 claims abstract description 123
- 238000002474 experimental method Methods 0.000 claims abstract description 51
- 238000013528 artificial neural network Methods 0.000 claims abstract description 23
- 238000006243 chemical reaction Methods 0.000 claims description 137
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 68
- 229910052799 carbon Inorganic materials 0.000 claims description 68
- 239000012159 carrier gas Substances 0.000 claims description 47
- 238000013507 mapping Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 12
- 238000005457 optimization Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000007789 gas Substances 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000002068 genetic effect Effects 0.000 claims description 3
- 238000012512 characterization method Methods 0.000 claims description 2
- 238000012937 correction Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 239000002994 raw material Substances 0.000 description 3
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 101100532679 Caenorhabditis elegans scc-1 gene Proteins 0.000 description 1
- MYMOFIZGZYHOMD-UHFFFAOYSA-N Dioxygen Chemical compound O=O MYMOFIZGZYHOMD-UHFFFAOYSA-N 0.000 description 1
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 239000003795 chemical substances by application Substances 0.000 description 1
- 239000003034 coal gas Substances 0.000 description 1
- 239000000571 coke Substances 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 229930195733 hydrocarbon Natural products 0.000 description 1
- 150000002430 hydrocarbons Chemical class 0.000 description 1
- 239000001257 hydrogen Substances 0.000 description 1
- 229910052739 hydrogen Inorganic materials 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000004449 solid propellant Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a sensitivity analysis method for experimental parameter variation in a coal gasification process, which comprises the following steps: constructing an infinite sensitivity datamation model by using a BP neural network based on a finite amount of data points of sensitivity analysis parameters and a finite amount of data points of gasification performance indexes; and calculating gasification performance indexes of gasification experiments generated by any data point of the sensitivity analysis parameters in the coal gasification process by using an infinite sensitivity datamation model so as to realize infinite datamation reflection of experimental sensitivity in the coal gasification process. According to the application, the BP neural network is utilized to accumulate data samples based on a limited amount of experiments, an infinite sensitivity data model is constructed according to the limited amount of data samples, the sensitivity of the gasification experiment to any change of experimental parameters is measured and calculated by utilizing the infinite sensitivity data model, a large number of repeated experiments are avoided, the sensitivity analysis efficiency is improved, and the problem that the sensitivity analysis result caused by subjectivity of the experiment is unreliable is avoided.
Description
Technical Field
The application relates to the technical field of coal gasification, in particular to a sensitivity analysis method for experimental parameter change in the coal gasification process.
Background
The coal gasification technology is one of key technologies for efficient and clean utilization of coal in the future, and provides an important guarantee for sustainable development strategy of energy sources in China. The technology is characterized in that coal or coke is used as a raw material in specific equipment (such as a gasifier), oxygen (air, oxygen-enriched or pure oxygen) steam or hydrogen is used as a gasifying agent, raw material coal is converted into gas fuels such as COH2 and hydrocarbons from solid fuels through a series of chemical reactions at a certain temperature and pressure, and finally the generated high-heat-value gas can be used as high-quality gas for civil use or as raw material for gas turbine power generation, and can also be used as synthesis gas for processing and synthesizing chemical products and the like. Therefore, the main influencing factors in the coal gasification process are researched, and the method has remarkable significance for improving the coal gasification technology, improving the heat value of the coal gas, reducing the emission of pollutants and realizing the efficient clean utilization of the coal.
In the sensitivity analysis method for the experimental parameter change in the prior art, the sensitivity of the gasification experiment to the experimental parameter change can be obtained by continuously repeating the experiment, the workload of the sensitivity analysis is large, the subjectivity of the operation of the personnel of the experiment is easy, and the accuracy of the sensitivity analysis is further reduced.
Disclosure of Invention
The application aims to provide a sensitivity analysis method for experimental parameter change in a coal gasification process, which aims to solve the technical problems that in the prior art, the sensitivity of a gasification dynamic model can be obtained by repeated experiments, the workload of sensitivity analysis is large, experimental omission is easy to occur, and the accuracy of sensitivity analysis is further reduced.
In order to solve the technical problems, the application specifically provides the following technical scheme:
a sensitivity analysis method for experimental parameter variation in a coal gasification process comprises the following steps:
determining experimental parameters which can cause experimental sensitivity change in the coal gasification process as sensitivity analysis parameters, selecting limited data points of the sensitivity analysis parameters, and carrying out limited gasification experiments according to the limited data points of the sensitivity analysis parameters to obtain limited data points of gasification performance indexes, wherein the limited data points of the gasification performance indexes are used for reflecting experimental sensitivity in the coal gasification process in a limited data manner;
constructing an infinite sensitivity datamation model by using a BP neural network based on a finite amount of data points of sensitivity analysis parameters and a finite amount of data points of gasification performance indexes;
and calculating gasification performance indexes of gasification experiments generated by any data point of the sensitivity analysis parameters in the coal gasification process by using an infinite sensitivity datamation model so as to realize infinite datamation reflection of experimental sensitivity in the coal gasification process.
As a preferred embodiment of the present application, the sensitivity analysis parameters include temperature, water-to-coal ratio, coal feeding rate, carrier gas N 2 Flow and RPC height.
And (3) carrying out limited adjustment on experimental parameters in the coal gasification process by using a gradient change method.
As a preferred aspect of the present application, the gasification performance index includes a carbon conversion rate, an energy upgrade factor, and a solar energy conversion rate.
As a preferred embodiment of the present application, selecting a limited number of data points for the sensitivity analysis parameter includes:
selecting a group of temperature data values as limited data points of the temperature within the allowable range of the experimental temperature in the coal gasification process;
selecting a group of water-coal ratio data values as limited data points of the water-coal ratio in the water-coal ratio allowable range in the coal gasification process;
selecting a group of coal feeding rate data values as limited data points of the coal feeding rate within the allowable range of the coal feeding rate in the coal gasification process;
carrier gas N in coal gasification process 2 Selecting a group of carrier gases N within the flow allowable range 2 Flow data value as the carrier gas N 2 Limited amount of data points of the flow;
and selecting a group of RPC height data values as a limited data point of the RPC height within the range of the RPC height allowance in the coal gasification process.
As a preferable scheme of the application, the limited amount of gasification experiments are carried out according to the limited amount of data points of the sensitivity analysis parameters to obtain the limited amount of data points of the gasification performance index, which comprises the following steps:
performing gasification experiments based on each limited data point of the temperature to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar conversion rate corresponding to each limited data point of the temperature;
carrying out gasification experiments based on each limited data point of the water-coal ratio to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the water-coal ratio;
carrying out gasification experiments based on each limited data point of the coal feeding rate to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the coal feeding rate;
respectively based on carrier gas N 2 Carrying out gasification experiments on each limited data point of the flow to obtain carrier gas N 2 Each limited data point of carbon conversion rate, each limited data point of energy upgrading factor and each limited data point of solar energy conversion rate corresponding to each limited data point of flow;
and carrying out gasification experiments based on each limited data point of the RPC height to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the RPC height.
As a preferred scheme of the application, the construction of the infinite sensitivity data model comprises the following steps:
training and learning each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the temperature by using a BP neural network to obtain a temperature change infinite sensitivity datamation model representing the change mapping relation among the temperature, the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate;
training and learning each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the water-coal ratio and each limited data point of the water-coal ratio by using the BP neural network to obtain a water-coal ratio change infinite sensitivity datamation model representing the change mapping relation among the water-coal ratio, the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate;
training and learning each limited data point of the coal feeding rate and each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar conversion rate corresponding to each limited data point of the coal feeding rate by using a BP neural network to obtain a coal feeding rate variation infinite sensitivity datamation model representing a variation mapping relation between the coal feeding rate and the carbon conversion rate, and between the energy upgrading factor and the solar conversion rate;
carrier gas N using BP neural network 2 Each limited amount of data point of flow and carrier gas N 2 Each limited data point of the flow rate corresponding to each limited data point of the carbon conversion rateTraining and learning each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate to obtain a characteristic carrier gas N 2 Carrier gas N in a varying mapping relationship between flow and carbon conversion, energy upgrade factor and solar energy conversion 2 A flow change infinite sensitivity datamation model;
training and learning each limited data point of the RPC height and each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar conversion rate corresponding to each limited data point of the RPC height by using a BP neural network to obtain an RPC height variation infinite sensitivity datamation model representing the variation mapping relation between the RPC height and the carbon conversion rate, the energy upgrading factor and the solar conversion rate;
setting a sensitivity data expected model, quantifying a temperature change infinite sensitivity data model, a water-coal ratio change infinite sensitivity data model, a coal feeding rate change infinite sensitivity data model and a carrier gas N 2 The method comprises the steps of calculating a sensitivity data expected model by taking the minimum discreteness as an optimization target, and taking the sensitivity data expected model as an infinite sensitivity data model by taking the minimum discreteness as the variability between the flow variation infinite sensitivity data model and the RPC height variation infinite sensitivity data model and the sensitivity data expected model;
the solving of the sensitivity datamation expectation model comprises:
quantifying an optimization target with minimum discreteness, wherein an objective function of the optimization target is as follows:
wherein, minF is the minimum discreteness, min is the minimum operator, Y1, Y2, Y3 and Y4, Y5 are respectively the temperature, the water-coal ratio, the coal feeding rate and the carrier gas N 2 Flow and RPC height, BP (X i ) An infinite sensitivity data model for X variation at the ith data value within the X allowable range of the coal gasification processMeasuring and calculating the obtained carbon conversion rate, energy upgrading factor and solar energy conversion rate, BP E (X i ) Calculating the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate at the ith data value within the X allowable range of the coal gasification process for the sensitivity datamation expected model, and n X Is the total number of data values within the X allowed range, |BP (X i )-BP E (X i ) The I is BP (X) i ) And BP E (X i ) A Euclidean distance between the two;
solving an objective function of an optimization target by utilizing a genetic algorithm to obtain a function expression BP of a sensitivity data expected model E (X i ) To complete the solution of the sensitivity datamation desired model.
As a preferred embodiment of the present application, the method further comprises: utilizing a temperature change infinite sensitivity data model, a water-coal ratio change infinite sensitivity data model, a coal feeding rate change infinite sensitivity data model and a carrier gas N 2 The flow change infinite sensitivity data model and the RPC height change infinite sensitivity data model correct the infinite sensitivity data model;
the correction of the infinite sensitivity datamation model comprises the following steps:
the method comprises the steps that an infinite sensitivity data model is applied to an X allowable range of a coal gasification process to calculate carbon conversion rate, energy upgrading factor and solar energy conversion rate, and the accuracy of the infinite sensitivity data model is quantified based on the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate obtained by calculation and the X variable infinite sensitivity data model in the X allowable range of the coal gasification process;
comparing the accuracy of the infinite sensitivity datamation model within the X allowable range of the coal gasification process with a preset threshold, wherein,
when the accuracy of the infinite sensitivity data model in the X allowable range of the coal gasification process is smaller than a preset threshold, retraining the infinite sensitivity data model in the X allowable range of the coal gasification process by utilizing the carbon conversion rate, the energy upgrading factor and the solar conversion rate which are obtained by measuring and calculating the X variable infinite sensitivity data model in the X allowable range of the coal gasification process so as to update the infinite sensitivity data model;
and when the accuracy of the infinite sensitivity data model in the X allowable range of the coal gasification process is greater than or equal to a preset threshold value, the infinite sensitivity data model is not updated.
As a preferred scheme of the application, the gasification performance index of the gasification experiment generated by any data point of the sensitivity analysis parameters in the gasification process is calculated by utilizing an infinite sensitivity datamation model, and the method comprises the following steps:
inputting any data point of the sensitivity analysis parameters in the coal gasification process into the infinite sensitivity data model, and outputting gasification performance indexes at any data point of the sensitivity analysis parameters by the infinite sensitivity data model.
As a preferable scheme of the application, the temperature change infinite sensitivity data model, the water-coal ratio change infinite sensitivity data model, the coal feeding rate change infinite sensitivity data model and the carrier gas N 2 The variable flow infinite sensitivity data model, the variable RPC height infinite sensitivity data model and the variable infinite sensitivity data model both adopt mean square error as damage functions.
As a preferable scheme of the application, when an infinite sensitivity data model is constructed, each sensitivity analysis parameter is normalized to eliminate dimension errors.
Compared with the prior art, the application has the following beneficial effects:
according to the application, the BP neural network is utilized to accumulate data samples based on a limited amount of experiments, an infinite sensitivity data model is constructed according to the limited amount of data samples, the sensitivity of the gasification experiment to any change of experimental parameters is measured and calculated by utilizing the infinite sensitivity data model, a large number of repeated experiments are avoided, the sensitivity analysis efficiency is improved, and the problem that the sensitivity analysis result caused by subjectivity of the experiment is unreliable is avoided.
Drawings
In order to more clearly illustrate the embodiments of the present application 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.
FIG. 1 is a flow chart of a sensitivity analysis method for experimental parameter variation in a coal gasification process according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
In the sensitivity analysis method for the experimental parameter change in the prior art, the sensitivity of the gasification experiment to the experimental parameter change can be obtained by continuously repeating the experiment, the workload of the sensitivity analysis is large, the subjectivity of the operation of the personnel of the experiment is easy, and the accuracy of the sensitivity analysis is further reduced. Therefore, the application provides a sensitivity analysis method for experimental parameter change in the coal gasification process, which utilizes a limited amount of experiments to construct an unlimited sensitivity datamation model, carries out unlimited measurement and calculation on the sensitivity of experimental parameter change, improves the measurement and calculation efficiency and ensures the measurement and calculation accuracy.
As shown in FIG. 1, the application provides a sensitivity analysis method for experimental parameter variation in a coal gasification process, which comprises the following steps:
determining experimental parameters which can cause experimental sensitivity change in the coal gasification process as sensitivity analysis parameters, selecting limited data points of the sensitivity analysis parameters, and carrying out limited gasification experiments according to the limited data points of the sensitivity analysis parameters to obtain limited data points of gasification performance indexes, wherein the limited data points of the gasification performance indexes are used for reflecting experimental sensitivity in the coal gasification process in a limited datamation manner;
constructing an infinite sensitivity datamation model by using a BP neural network based on a finite amount of data points of sensitivity analysis parameters and a finite amount of data points of gasification performance indexes;
and calculating gasification performance indexes of gasification experiments generated by any data point of the sensitivity analysis parameters in the coal gasification process by using an infinite sensitivity datamation model so as to realize infinite datamation reflection of experimental sensitivity in the coal gasification process.
The sensitivity analysis parameters comprise temperature, water-coal ratio, coal feeding rate and carrier gas N 2 Flow and RPC height.
And (3) carrying out limited adjustment on experimental parameters in the coal gasification process by using a gradient change method.
Gasification performance metrics include carbon conversion, energy upgrade factor, and solar energy conversion.
In order to avoid the sensitivity analysis which can only rely on gasification experiments to realize the change of experimental parameters in the coal gasification process, the sensitivity analysis results obtained by limited experiments are subjected to machine learning by utilizing the BP neural network to construct a sensitivity data model, the sensitivity analysis can be completed by utilizing the data model, the sensitivity analysis of experimental operation is converted into the sensitivity analysis of digital measurement and calculation, the experimental steps of the sensitivity analysis are lightened, the efficiency of the sensitivity analysis is improved, the number of experimental operations is limited, and the digital measurement and calculation is infinite, so that the sensitivity analysis of the experimental operation is converted into the sensitivity analysis of digital measurement and calculation, the analysis range of the sensitivity analysis is further widened, and the breadth of the sensitivity analysis is improved.
According to the application, the sample accumulation of the sensitivity data model training is carried out by utilizing the experimental operation of the gasification experiment in the initial stage, so that the learning training of the sensitivity data model has practical significance, namely, the mapping relation between the learned sensitivity analysis parameters and gasification performance indexes accords with practical rules, thereby ensuring that the accuracy of sensitivity analysis is maintained when the sensitivity analysis breadth is expanded, and the method specifically comprises the following steps:
the method for selecting the limited data points of the sensitivity analysis parameters comprises the following steps:
selecting a group of temperature data values as limited data points of temperature within the allowable range of the experimental temperature in the coal gasification process;
selecting a group of water-coal ratio data values as a limited quantity of data points of the water-coal ratio in the water-coal ratio allowable range in the coal gasification process;
selecting a group of coal feeding rate data values as limited data points of the coal feeding rate within the allowable range of the coal feeding rate in the coal gasification process;
carrier gas N in coal gasification process 2 Selecting a group of carrier gases N within the flow allowable range 2 Flow data value as carrier gas N 2 Limited amount of data points of the flow;
and selecting a group of RPC height data values as a limited number of data points of the RPC height within the range of the RPC height allowance in the coal gasification process.
Carrying out a limited amount of gasification experiments according to the limited amount of data points of the sensitivity analysis parameters to obtain the limited amount of data points of the gasification performance index, wherein the limited amount of data points comprise:
performing gasification experiments based on each limited data point of the temperature to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar conversion rate corresponding to each limited data point of the temperature;
carrying out gasification experiments based on each limited data point of the water-coal ratio to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the water-coal ratio;
carrying out gasification experiments based on each limited data point of the coal feeding rate to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the coal feeding rate;
respectively based on carrier gas N 2 Carrying out gasification experiments on each limited data point of the flow to obtain carrier gas N 2 Each limited data point of carbon conversion rate, each limited data point of energy upgrading factor and each limited data point of solar energy conversion rate corresponding to each limited data point of flow;
and carrying out gasification experiments based on each limited data point of the RPC height to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the RPC height.
The construction of an infinite sensitivity datamation model comprises the following steps:
training and learning each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the temperature by using a BP neural network to obtain a temperature change infinite sensitivity datamation model representing the change mapping relation among the temperature, the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate;
training and learning each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the water-coal ratio and each limited data point of the water-coal ratio by using the BP neural network to obtain a water-coal ratio change infinite sensitivity datamation model representing the change mapping relation among the water-coal ratio, the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate;
training and learning each limited data point of the coal feeding rate and each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar conversion rate corresponding to each limited data point of the coal feeding rate by using a BP neural network to obtain a coal feeding rate variation infinite sensitivity datamation model representing a variation mapping relation between the coal feeding rate and the carbon conversion rate, and between the energy upgrading factor and the solar conversion rate;
carrier gas N using BP neural network 2 Each limited amount of data point of flow and carrier gas N 2 Training and learning each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the flow to obtain a characterization carrier gas N 2 Carrier gas N in a varying mapping relationship between flow and carbon conversion, energy upgrade factor and solar energy conversion 2 A flow change infinite sensitivity datamation model;
training and learning each limited data point of the RPC height and each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar conversion rate corresponding to each limited data point of the RPC height by using a BP neural network to obtain an RPC height variation infinite sensitivity datamation model representing the variation mapping relation between the RPC height and the carbon conversion rate, the energy upgrading factor and the solar conversion rate;
setting a sensitivity data expected model, quantifying a temperature change infinite sensitivity data model, a water-coal ratio change infinite sensitivity data model, a coal feeding rate change infinite sensitivity data model and a carrier gas N 2 The method comprises the steps of calculating a sensitivity data expected model by taking the minimum discreteness as an optimization target, and taking the sensitivity data expected model as an infinite sensitivity data model by taking the minimum discreteness as the variability between the flow variation infinite sensitivity data model and the RPC height variation infinite sensitivity data model and the sensitivity data expected model;
solving the sensitivity datamation expectation model comprises:
quantifying an optimization target with minimum discreteness, wherein the objective function of the optimization target is as follows:
wherein, minF is the minimum discreteness, min is the minimum operator, Y1, Y2, Y3 and Y4, Y5 are respectively the temperature, the water-coal ratio, the coal feeding rate and the carrier gas N 2 Flow and RPC height, BP (X i ) Carbon conversion rate, energy upgrading factor and solar energy conversion rate measured and calculated for X-variation infinite sensitivity datamation model at ith data value within X allowable range of coal gasification process, BP E (X i ) Calculating the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate at the ith data value within the X allowable range of the coal gasification process for the sensitivity datamation expected model, and n X Is the total number of data values within the X allowed range, |BP (X i )-BP E (X i ) The I is BP (X) i ) And BP E (X i ) A Euclidean distance between the two;
solving an objective function of an optimization target by utilizing a genetic algorithm to obtain a function expression BP of a sensitivity data expected model E (X i ) To complete the solution of the sensitivity datamation desired model.
The application builds a temperature change infinite sensitivity data model, a water-coal ratio change infinite sensitivity data model, a coal feeding rate change infinite sensitivity data model and a carrier gas N 2 The flow change infinite sensitivity data model and the RPC height change infinite sensitivity data model respectively obtain the mapping relation between the temperature and the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate, the mapping relation between the water-coal ratio and the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate, the mapping relation between the coal feeding rate and the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate, and the carrier gas N 2 The mapping relation between the flow and the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate, the mapping relation between the RPC height and the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate can obtain the temperature, the water-coal ratio, the coal feeding rate and the carrier gas N 2 Flow and RPC height these single sensitivity analysis parameters vary the sensitivity produced during coal gasification.
The method is used for respectively obtaining the temperature change infinite sensitivity data model, the water-coal ratio change infinite sensitivity data model, the coal feeding rate change infinite sensitivity data model and the carrier gas N 2 After the flow change infinite sensitivity data model and the RPC height change infinite sensitivity data model, the sensitivity generated in the coal gasification process of single sensitivity analysis parameter change can be obtained, but the sensitivity generated in the coal gasification process of a plurality of sensitivity analysis parameter mixed changes is difficult to obtain, so that the applicability of sensitivity analysis is weaker, and in order to solve the problem of weaker applicability, the application utilizes the temperature change infinite sensitivity data model, the water-coal ratio change infinite sensitivity data model, the coal feeding rate change infinite sensitivity data model and the carrier gas N 2 Performing discrete analysis on the flow rate change infinite sensitivity data model and the RPC height change infinite sensitivity data model, and performing discrete analysis on the temperature change infinite sensitivity data model, the water-coal ratio change infinite sensitivity data model, the coal feeding rate change infinite sensitivity data model and the carrier gas N 2 The optimal model with the minimum dispersion of the single-parameter sensitivity analysis model is found from the flow change infinite sensitivity data model and the RPC height change infinite sensitivity data model, and the smaller the dispersion is, the higher the measurement similarity between the infinite sensitivity data model and the single-parameter sensitivity analysis model is, namely the more accurate the sensitivity analysis result of the infinite sensitivity data model is on the change of a plurality of sensitivity analysis parameters, thereby realizing the sensitivity analysis applied to the mixed change of a plurality of sensitivity analysis parameters in the coal gasification process.
In order to further improve the accuracy of the sensitivity analysis of the infinite sensitivity data model, the infinite sensitivity data model is modified, and the method comprises the following steps of:
further comprises: utilizing a temperature change infinite sensitivity data model, a water-coal ratio change infinite sensitivity data model, a coal feeding rate change infinite sensitivity data model and a carrier gas N 2 Unlimited sensitivity to flow rate variationThe data model and the RPC height change infinite sensitivity data model correct the infinite sensitivity data model;
modifying the infinite sensitivity databased model includes:
the method comprises the steps that an infinite sensitivity data model is applied to an X allowable range of a coal gasification process to calculate carbon conversion rate, energy upgrading factor and solar energy conversion rate, and the accuracy of the infinite sensitivity data model is quantified based on the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate obtained by calculation and the X variable infinite sensitivity data model in the X allowable range of the coal gasification process;
comparing the accuracy of the infinite sensitivity datamation model within the X allowable range of the coal gasification process with a preset threshold, wherein,
when the accuracy of the infinite sensitivity data model in the X allowable range of the coal gasification process is smaller than a preset threshold, retraining the infinite sensitivity data model in the X allowable range of the coal gasification process by utilizing the carbon conversion rate, the energy upgrading factor and the solar conversion rate which are obtained by measuring and calculating the X variable infinite sensitivity data model in the X allowable range of the coal gasification process so as to update the infinite sensitivity data model;
and when the accuracy of the infinite sensitivity data model in the X allowable range of the coal gasification process is greater than or equal to a preset threshold value, the infinite sensitivity data model is not updated.
Calculating gasification performance indexes of gasification experiments generated by any data point of sensitivity analysis parameters in the coal gasification process by using an infinite sensitivity datamation model, wherein the method comprises the following steps:
inputting any data point of the sensitivity analysis parameters in the coal gasification process into the infinite sensitivity data model, and outputting gasification performance indexes at any data point of the sensitivity analysis parameters by the infinite sensitivity data model.
Temperature change infinite sensitivity data model and water-coal ratio change infinite sensitivity dataModel, coal feed rate variation infinite sensitivity datamation model and carrier gas N 2 The variable flow infinite sensitivity data model, the variable RPC height infinite sensitivity data model and the variable infinite sensitivity data model both adopt mean square error as damage functions.
When an infinite sensitivity datamation model is constructed, each sensitivity analysis parameter is normalized, and dimension errors are eliminated.
According to the application, the BP neural network is utilized to accumulate data samples based on a limited amount of experiments, an infinite sensitivity data model is constructed according to the limited amount of data samples, the sensitivity of the gasification experiment to any change of experimental parameters is measured and calculated by utilizing the infinite sensitivity data model, a large number of repeated experiments are avoided, the sensitivity analysis efficiency is improved, and the problem that the sensitivity analysis result caused by subjectivity of the experiment is unreliable is avoided.
The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this application will occur to those skilled in the art, and are intended to be within the spirit and scope of the application.
Claims (10)
1. A sensitivity analysis method for experimental parameter change in coal gasification process is characterized in that: the method comprises the following steps:
determining experimental parameters which can cause experimental sensitivity change in the coal gasification process as sensitivity analysis parameters, selecting limited data points of the sensitivity analysis parameters, and carrying out limited gasification experiments according to the limited data points of the sensitivity analysis parameters to obtain limited data points of gasification performance indexes, wherein the limited data points of the gasification performance indexes are used for reflecting experimental sensitivity in the coal gasification process in a limited data manner;
constructing an infinite sensitivity datamation model by using a BP neural network based on a finite amount of data points of sensitivity analysis parameters and a finite amount of data points of gasification performance indexes;
and calculating gasification performance indexes of gasification experiments generated by any data point of the sensitivity analysis parameters in the coal gasification process by using an infinite sensitivity datamation model so as to realize infinite datamation reflection of experimental sensitivity in the coal gasification process.
2. The method for sensitivity analysis of experimental parameter variation in coal gasification process according to claim 1, wherein: the sensitivity analysis parameters comprise temperature, water-coal ratio, coal feeding rate and carrier gas N 2 Flow and RPC height.
And (3) carrying out limited adjustment on experimental parameters in the coal gasification process by using a gradient change method.
3. The method for sensitivity analysis of experimental parameter variation in coal gasification process according to claim 2, wherein: the gasification performance metrics include carbon conversion, energy upgrade factor, and solar energy conversion.
4. The method for sensitivity analysis of experimental parameter variation in coal gasification process according to claim 2, wherein: and selecting a limited number of data points for the sensitivity analysis parameters, including:
selecting a group of temperature data values as limited data points of the temperature within the allowable range of the experimental temperature in the coal gasification process;
selecting a group of water-coal ratio data values as limited data points of the water-coal ratio in the water-coal ratio allowable range in the coal gasification process;
selecting a group of coal feeding rate data values as limited data points of the coal feeding rate within the allowable range of the coal feeding rate in the coal gasification process;
carrier gas N in coal gasification process 2 Selecting a group of carrier gases N within the flow allowable range 2 Flow data value as the carrier gas N 2 Limited amount of data points of the flow;
and selecting a group of RPC height data values as a limited data point of the RPC height within the range of the RPC height allowance in the coal gasification process.
5. A method for sensitivity analysis of experimental parameter variations in a coal gasification process according to claim 3, wherein: the limited amount of gasification experiments are carried out according to the limited amount of data points of the sensitivity analysis parameters to obtain the limited amount of data points of the gasification performance index, and the method comprises the following steps:
performing gasification experiments based on each limited data point of the temperature to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar conversion rate corresponding to each limited data point of the temperature;
carrying out gasification experiments based on each limited data point of the water-coal ratio to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the water-coal ratio;
carrying out gasification experiments based on each limited data point of the coal feeding rate to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the coal feeding rate;
respectively based on carrier gas N 2 Carrying out gasification experiments on each limited data point of the flow to obtain carrier gas N 2 Each limited data point of carbon conversion rate, each limited data point of energy upgrading factor and each limited data point of solar energy conversion rate corresponding to each limited data point of flow;
and carrying out gasification experiments based on each limited data point of the RPC height to obtain each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the RPC height.
6. The method for sensitivity analysis of experimental parameter variation in coal gasification process according to claim 5, wherein: the construction of an infinite sensitivity datamation model comprises the following steps:
training and learning each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the temperature by using a BP neural network to obtain a temperature change infinite sensitivity datamation model representing the change mapping relation among the temperature, the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate;
training and learning each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the water-coal ratio and each limited data point of the water-coal ratio by using the BP neural network to obtain a water-coal ratio change infinite sensitivity datamation model representing the change mapping relation among the water-coal ratio, the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate;
training and learning each limited data point of the coal feeding rate and each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar conversion rate corresponding to each limited data point of the coal feeding rate by using a BP neural network to obtain a coal feeding rate variation infinite sensitivity datamation model representing a variation mapping relation between the coal feeding rate and the carbon conversion rate, and between the energy upgrading factor and the solar conversion rate;
carrier gas N using BP neural network 2 Each limited amount of data point of flow and carrier gas N 2 Training and learning each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar energy conversion rate corresponding to each limited data point of the flow to obtain a characterization carrier gas N 2 The flow rate and carbon conversion rate, energy upgrading factor and solar conversion rate are changed to be mappedCarrier gas N in jet relation 2 A flow change infinite sensitivity datamation model;
training and learning each limited data point of the RPC height and each limited data point of the carbon conversion rate, each limited data point of the energy upgrading factor and each limited data point of the solar conversion rate corresponding to each limited data point of the RPC height by using a BP neural network to obtain an RPC height variation infinite sensitivity datamation model representing the variation mapping relation between the RPC height and the carbon conversion rate, the energy upgrading factor and the solar conversion rate;
setting a sensitivity data expected model, quantifying a temperature change infinite sensitivity data model, a water-coal ratio change infinite sensitivity data model, a coal feeding rate change infinite sensitivity data model and a carrier gas N 2 The method comprises the steps of calculating a sensitivity data expected model by taking the minimum discreteness as an optimization target, and taking the sensitivity data expected model as an infinite sensitivity data model by taking the minimum discreteness as the variability between the flow variation infinite sensitivity data model and the RPC height variation infinite sensitivity data model and the sensitivity data expected model;
the solving of the sensitivity datamation expectation model comprises:
quantifying an optimization target with minimum discreteness, wherein an objective function of the optimization target is as follows:
wherein, minF is the minimum discreteness, min is the minimum operator, Y1, Y2, Y3 and Y4, Y5 are respectively the temperature, the water-coal ratio, the coal feeding rate and the carrier gas N 2 Flow and RPC height, BP (X i ) Carbon conversion rate, energy upgrading factor and solar energy conversion rate measured and calculated for X-variation infinite sensitivity datamation model at ith data value within X allowable range of coal gasification process, BP E (X i ) Calculating the carbon conversion rate of the expected model at the ith data value within the X allowable range of the coal gasification process for the sensitivity datamation,Energy upgrade factor and solar energy conversion, n X Is the total number of data values within the X allowed range, |BP (X i )-BP E (X i ) The I is BP (X) i ) And BP E (X i ) A Euclidean distance between the two;
solving an objective function of an optimization target by utilizing a genetic algorithm to obtain a function expression BP of a sensitivity data expected model E (X i ) To complete the solution of the sensitivity datamation desired model.
7. The method for sensitivity analysis of experimental parameter variation in coal gasification process according to claim 6, wherein: further comprises: utilizing a temperature change infinite sensitivity data model, a water-coal ratio change infinite sensitivity data model, a coal feeding rate change infinite sensitivity data model and a carrier gas N 2 The flow change infinite sensitivity data model and the RPC height change infinite sensitivity data model correct the infinite sensitivity data model;
the correction of the infinite sensitivity datamation model comprises the following steps:
the method comprises the steps that an infinite sensitivity data model is applied to an X allowable range of a coal gasification process to calculate carbon conversion rate, energy upgrading factor and solar energy conversion rate, and the accuracy of the infinite sensitivity data model is quantified based on the carbon conversion rate, the energy upgrading factor and the solar energy conversion rate obtained by calculation and the X variable infinite sensitivity data model in the X allowable range of the coal gasification process;
comparing the accuracy of the infinite sensitivity datamation model within the X allowable range of the coal gasification process with a preset threshold, wherein,
when the accuracy of the infinite sensitivity data model in the X allowable range of the coal gasification process is smaller than a preset threshold, retraining the infinite sensitivity data model in the X allowable range of the coal gasification process by utilizing the carbon conversion rate, the energy upgrading factor and the solar conversion rate which are obtained by measuring and calculating the X variable infinite sensitivity data model in the X allowable range of the coal gasification process so as to update the infinite sensitivity data model;
and when the accuracy of the infinite sensitivity data model in the X allowable range of the coal gasification process is greater than or equal to a preset threshold value, the infinite sensitivity data model is not updated.
8. The method for sensitivity analysis of experimental parameter variation in coal gasification process according to claim 1, wherein: calculating gasification performance indexes of gasification experiments generated by any data point of sensitivity analysis parameters in the coal gasification process by using an infinite sensitivity datamation model, wherein the method comprises the following steps:
inputting any data point of the sensitivity analysis parameters in the coal gasification process into the infinite sensitivity data model, and outputting gasification performance indexes at any data point of the sensitivity analysis parameters by the infinite sensitivity data model.
9. The method for sensitivity analysis of experimental parameter variation in coal gasification process according to claim 6, wherein: temperature change infinite sensitivity data model, water-coal ratio change infinite sensitivity data model, coal feeding rate change infinite sensitivity data model and carrier gas N 2 The variable flow infinite sensitivity data model, the variable RPC height infinite sensitivity data model and the variable infinite sensitivity data model both adopt mean square error as damage functions.
10. The method for sensitivity analysis of experimental parameter variation in coal gasification process according to claim 1, wherein: when an infinite sensitivity datamation model is constructed, each sensitivity analysis parameter is normalized, and dimension errors are eliminated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310877965.8A CN116935985B (en) | 2023-07-17 | 2023-07-17 | Sensitivity analysis method for experimental parameter change in coal gasification process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310877965.8A CN116935985B (en) | 2023-07-17 | 2023-07-17 | Sensitivity analysis method for experimental parameter change in coal gasification process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116935985A true CN116935985A (en) | 2023-10-24 |
| CN116935985B CN116935985B (en) | 2024-03-15 |
Family
ID=88387315
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310877965.8A Active CN116935985B (en) | 2023-07-17 | 2023-07-17 | Sensitivity analysis method for experimental parameter change in coal gasification process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116935985B (en) |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090276193A1 (en) * | 2006-04-13 | 2009-11-05 | Osaka University | Design support method, design support system, and design support program for heat convection field |
| CN108229721A (en) * | 2017-12-04 | 2018-06-29 | 西北大学 | The Forecasting Methodology of pyrolysis of coal product based on Speed Controlling Based on Improving BP Neural Network |
| CN110059803A (en) * | 2019-04-03 | 2019-07-26 | 东华大学 | A kind of temperature-compensation method of the optical fibre displacement sensor based on GA-BP |
| CN110083895A (en) * | 2019-04-12 | 2019-08-02 | 浙江大学 | A kind of surface heat flux three-dismensional effect modification method neural network based |
| CN110889495A (en) * | 2019-12-04 | 2020-03-17 | 河南中烟工业有限责任公司 | State maintenance analysis method for silk making equipment based on active parameters |
| US20200394494A1 (en) * | 2019-06-17 | 2020-12-17 | East China Jiaotong University | Method And System For Predicting Content Of Multiple Components In Rare Earth Extraction Process |
| CN112289392A (en) * | 2020-10-28 | 2021-01-29 | 广西贺州市桂东电子科技有限责任公司 | Method for predicting performance of anode aluminum foil for aluminum electrolytic capacitor |
| US20210282649A1 (en) * | 2019-10-31 | 2021-09-16 | Peach Intellihealth, Inc. | Systems and methods for predicting high frequency and low frequency patient parameters |
| CN113611114A (en) * | 2021-08-03 | 2021-11-05 | 长安大学 | Urban expressway traffic accident meteorological factor sensitivity analysis method |
| US20220129757A1 (en) * | 2020-10-26 | 2022-04-28 | Jiangxi University Of Science And Technology | Prediction method, device and system for rock mass instability stages |
| CN114529105A (en) * | 2022-03-24 | 2022-05-24 | 江苏真鹿科技有限公司 | Engine crankshaft high-temperature performance analysis processing method based on BP neural network |
| CN114611380A (en) * | 2022-02-14 | 2022-06-10 | 广西电网有限责任公司电力科学研究院 | Transformer fault diagnosis method based on genetic algorithm and BP neural network |
| CN114662406A (en) * | 2022-04-12 | 2022-06-24 | 中国科学院武汉岩土力学研究所 | Method for establishing rock joint peak shear strength prediction model with assistance of machine learning |
| US20220235279A1 (en) * | 2021-01-21 | 2022-07-28 | Shanghai Maritime University | Method of reducing octane loss in catalytic cracking of gasoline in S-zorb plant |
| US20220340827A1 (en) * | 2019-09-24 | 2022-10-27 | China Petroleum & Chemical Corporation | System and method for intelligent gasification blending |
| KR20220159762A (en) * | 2021-05-26 | 2022-12-05 | 인하대학교 산학협력단 | Construction method of artificial neural network model using genetic algorithm and variable optimization method using the same |
| WO2023005302A1 (en) * | 2021-07-26 | 2023-02-02 | 东南大学 | Method for predicting biomass coke gasification reaction characteristics |
| CN115762664A (en) * | 2022-09-21 | 2023-03-07 | 浙江大学 | Method for predicting gas production component in high-temperature gasification process of multi-component organic waste |
| US20230074074A1 (en) * | 2021-09-02 | 2023-03-09 | Southwest Petroleum University | Intelligent recognition method for while-drilling safety risk based on convolutional neural network |
-
2023
- 2023-07-17 CN CN202310877965.8A patent/CN116935985B/en active Active
Patent Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090276193A1 (en) * | 2006-04-13 | 2009-11-05 | Osaka University | Design support method, design support system, and design support program for heat convection field |
| CN108229721A (en) * | 2017-12-04 | 2018-06-29 | 西北大学 | The Forecasting Methodology of pyrolysis of coal product based on Speed Controlling Based on Improving BP Neural Network |
| CN110059803A (en) * | 2019-04-03 | 2019-07-26 | 东华大学 | A kind of temperature-compensation method of the optical fibre displacement sensor based on GA-BP |
| CN110083895A (en) * | 2019-04-12 | 2019-08-02 | 浙江大学 | A kind of surface heat flux three-dismensional effect modification method neural network based |
| US20200394494A1 (en) * | 2019-06-17 | 2020-12-17 | East China Jiaotong University | Method And System For Predicting Content Of Multiple Components In Rare Earth Extraction Process |
| US20220340827A1 (en) * | 2019-09-24 | 2022-10-27 | China Petroleum & Chemical Corporation | System and method for intelligent gasification blending |
| US20210282649A1 (en) * | 2019-10-31 | 2021-09-16 | Peach Intellihealth, Inc. | Systems and methods for predicting high frequency and low frequency patient parameters |
| CN110889495A (en) * | 2019-12-04 | 2020-03-17 | 河南中烟工业有限责任公司 | State maintenance analysis method for silk making equipment based on active parameters |
| US20220129757A1 (en) * | 2020-10-26 | 2022-04-28 | Jiangxi University Of Science And Technology | Prediction method, device and system for rock mass instability stages |
| CN112289392A (en) * | 2020-10-28 | 2021-01-29 | 广西贺州市桂东电子科技有限责任公司 | Method for predicting performance of anode aluminum foil for aluminum electrolytic capacitor |
| US20220235279A1 (en) * | 2021-01-21 | 2022-07-28 | Shanghai Maritime University | Method of reducing octane loss in catalytic cracking of gasoline in S-zorb plant |
| KR20220159762A (en) * | 2021-05-26 | 2022-12-05 | 인하대학교 산학협력단 | Construction method of artificial neural network model using genetic algorithm and variable optimization method using the same |
| WO2023005302A1 (en) * | 2021-07-26 | 2023-02-02 | 东南大学 | Method for predicting biomass coke gasification reaction characteristics |
| CN113611114A (en) * | 2021-08-03 | 2021-11-05 | 长安大学 | Urban expressway traffic accident meteorological factor sensitivity analysis method |
| US20230074074A1 (en) * | 2021-09-02 | 2023-03-09 | Southwest Petroleum University | Intelligent recognition method for while-drilling safety risk based on convolutional neural network |
| CN114611380A (en) * | 2022-02-14 | 2022-06-10 | 广西电网有限责任公司电力科学研究院 | Transformer fault diagnosis method based on genetic algorithm and BP neural network |
| CN114529105A (en) * | 2022-03-24 | 2022-05-24 | 江苏真鹿科技有限公司 | Engine crankshaft high-temperature performance analysis processing method based on BP neural network |
| CN114662406A (en) * | 2022-04-12 | 2022-06-24 | 中国科学院武汉岩土力学研究所 | Method for establishing rock joint peak shear strength prediction model with assistance of machine learning |
| CN115762664A (en) * | 2022-09-21 | 2023-03-07 | 浙江大学 | Method for predicting gas production component in high-temperature gasification process of multi-component organic waste |
Non-Patent Citations (8)
| Title |
|---|
| DONG-JIE LI等: "Gesture Recognition Based on BP Neural Network Improved by Chaotic Genetic Algorithm", INTERNATIONAL JOURNAL OF AUTOMATION AND COMPUTING, vol. 15, no. 03, 30 June 2018 (2018-06-30), pages 267 - 276 * |
| HAN WANG等: "Modelling and optimization of a pilot-scale entrained-flow gasifier using artificial neural networks", ENERGY, vol. 188, pages 2 * |
| 付波等: "基于粗糙集和AFSA-BP的水电机组故障诊断", 宁夏电力, no. 04, 30 August 2012 (2012-08-30), pages 31 - 35 * |
| 张冬至等: "基于模态辨识的原油含水率智能组合测量模型", 华南理工大学学报(自然科学版), vol. 37, no. 05, 15 May 2009 (2009-05-15), pages 73 - 78 * |
| 张青民: "太阳能驱动煤气化反应器设计及实验研究", 中国优秀硕士学位论文全文数据库工程科技Ⅰ辑, no. 03, pages 22 * |
| 杜旭鹏: "SE水煤浆气化炉内反应流动状态在线监控研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑, no. 02, pages 017 - 108 * |
| 王婷: "基于BP组合模型的燃气负荷预测的研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, no. 02, 15 February 2017 (2017-02-15), pages 038 - 2514 * |
| 黄捍东等: "基于灰关联和遗传算法的地震属性优化方法", 石油地球物理勘探, vol. 45, no. 03, 15 June 2010 (2010-06-15), pages 381 - 391 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116935985B (en) | 2024-03-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Örs et al. | A conceptual framework for AI-based operational digital twin in chemical process engineering | |
| CN113657591B (en) | Prediction method for biomass coke gasification reaction characteristics | |
| CN110413941B (en) | Similar principle analysis method for input and output characteristics of fuel cell | |
| CN107918368B (en) | The dynamic prediction method and equipment of iron and steel enterprise's coal gas yield and consumption | |
| CN116935985B (en) | Sensitivity analysis method for experimental parameter change in coal gasification process | |
| CN112686445A (en) | Photovoltaic power generation prediction method based on ARIMA-LSTM-DBN | |
| Chung et al. | Computer-aided identification and evaluation of technologies for sustainable carbon capture and utilization using a superstructure approach | |
| CN112651576A (en) | Long-term wind power prediction method and device | |
| CN110676852B (en) | Improved extreme learning machine rapid probability load flow calculation method considering load flow characteristics | |
| CN109934493B (en) | Method for rapidly determining coal consumption characteristic curve of thermal generator set | |
| Mütter et al. | Artificial intelligence for solid oxide fuel cells: Combining automated high accuracy artificial neural network model generation and genetic algorithm for time-efficient performance prediction and optimization | |
| CN112686447A (en) | Multi-energy flow coupling load prediction method for offshore oil and gas field development | |
| CN116823074A (en) | Cost accounting method and system for hydrogen system | |
| CN114091304B (en) | Intelligent decision-making method for processing hull plate by oxyhydrogen gas heat source | |
| CN113343589B (en) | Genetic-random constant-based acidic natural gas hydrate generation condition prediction method adopting genetic expression programming | |
| CN110824099B (en) | Method for predicting reaction performance in solid fuel chemical chain process based on GBRT | |
| CN103645633B (en) | Furnace temperature self-learning control method of conversion furnace system | |
| Chen et al. | Study on Model Evolution Method Based on the Hybrid Modeling Technology With Support Vector Machine for an SOFC-GT System | |
| Huo et al. | Nonlinear Hammerstein model identification of SOFC using improved GEO algorithm | |
| CN118070678B (en) | Intelligent optimization method of coal gasification device based on flow simulation and machine learning | |
| Devasahayam | Deep Learning Models for Hydrogen Production Prediction in Python: A Comparative Study | |
| CN116595824B (en) | Method for rapidly estimating parameters of thermal management system for hydrogen production by reforming methanol vapor | |
| Kim et al. | A comparative study of models for molten carbonate fuel cell (MCFC) processes | |
| CN118133694B (en) | Fuel cell bipolar plate flow channel structure design method | |
| CN118332828B (en) | Method for simulating sludge drying and carbonizing process and optimizing system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |