阅读说明：本技术 一种煤粉燃烧特征参数智能预测方法、装置及存储介质 (Intelligent prediction method and device for pulverized coal combustion characteristic parameters and storage medium ) 是由 许扬 于 2021-08-06 设计创作，主要内容包括：本发明公开了一种煤粉燃烧特征参数智能预测方法,属于燃烧技术领域。首先建立单颗粒煤粉着火模型,根据模型计算结果,选取环境特征条件、煤粉颗粒特征参数作为输入参数,即自变量；选取关注的煤粉燃烧特征参数为因变量,通过数据分析,建立自变量与因变量之间的直接映射关系。基于各个单变量变化对煤粉燃烧特征参数的影响规律,选取回归变量,通过合理调整因变量的选取,优化回归结果。本发明将数据分析方法运用到复杂的煤粉燃烧过程,基于大量实验和模拟数据,建立统一的通用的回归模型,实现煤粉燃烧过程的快速准确预测,实现煤粉燃烧过程的数字化、智能化。(The invention discloses an intelligent prediction method for coal powder combustion characteristic parameters, and belongs to the technical field of combustion. Firstly, establishing a single-particle coal powder ignition model, and selecting environmental characteristic conditions and coal powder particle characteristic parameters as input parameters, namely independent variables, according to a model calculation result; and selecting concerned coal powder combustion characteristic parameters as dependent variables, and establishing a direct mapping relation between the independent variables and the dependent variables through data analysis. And selecting regression variables based on the influence rule of each univariate change on the pulverized coal combustion characteristic parameters, and optimizing the regression result by reasonably adjusting the selection of the dependent variables. The invention applies the data analysis method to the complicated pulverized coal combustion process, establishes a uniform and universal regression model based on a large amount of experimental and simulation data, realizes the rapid and accurate prediction of the pulverized coal combustion process, and realizes the digitization and the intellectualization of the pulverized coal combustion process.)

1. An intelligent prediction method for coal powder combustion characteristic parameters is characterized by comprising the following steps:

s1: establishing a single-particle coal powder ignition model;

s2: on the basis of a single-particle pulverized coal ignition model, characteristic parameters representing ignition stability are divided into dependent variables and independent variables through a research method of control variables, and the change rules of the dependent variables under different independent variables are respectively researched;

s3: based on the influence rule of each univariate change on the pulverized coal combustion characteristic parameters, selecting regression variables to reasonably reflect the change characteristics of the pulverized coal combustion characteristic parameters;

s4: performing linear regression analysis on the dependent variable and each independent variable through a linear regression analysis tool;

s5: reasonably adjusting the selection of the dependent variable, and optimizing a regression result to ensure that the regression P value of each variable is smaller than a preset value; and determining the weight parameters of the respective variables to obtain a regression relation.

2. The coal powder combustion characteristic parameter intelligent prediction method according to claim 1, wherein in S1, the single-particle coal powder ignition model is established by coupling a coal powder chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism.

3. The pulverized coal combustion characteristic parameter intelligent prediction method as claimed in claim 1, characterized in that in S1, after the single-particle pulverized coal ignition model is established, the single-particle pulverized coal ignition model is verified by using typical experimental research results.

4. The method for intelligently predicting the pulverized coal combustion characteristic parameters as claimed in claim 1, wherein in S2, the dependent variables comprise ignition delay time and ignition mode; independent variables include environmental variables and the characteristics of the coal dust particles themselves.

5. The intelligent prediction method for pulverized coal combustion characteristic parameters as claimed in claim 4, wherein the environmental variables include temperature, oxygen concentration, pressure, carbon dioxide concentration, water vapor concentration and turbulence intensity; the characteristics of the coal dust particles include volatile content and particle size.

6. The intelligent prediction method for pulverized coal combustion characteristic parameters as claimed in claim 5, wherein the turbulence intensity quantification adopts switching values of 0 and 1, and in the laminar flow working condition, the value of the turbulence intensity variable is 0; in the turbulent working condition, the value of the turbulent intensity variable is 1.

7. The pulverized coal combustion characteristic parameter intelligent prediction method according to claim 1, characterized in that in S4, after linear regression analysis, regression effect is detected by regression test parameters.

8. The intelligent prediction method for coal powder combustion characteristic parameters as claimed in claim 1, wherein in S5, the preset value is 5%.

9. A computer device, characterized by comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor when executing the computer program implements the steps of the intelligent prediction method for pulverized coal combustion characteristic parameters according to 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, implements the steps of the intelligent prediction method for pulverized coal combustion characteristic parameters according to any one of claims 1 to 8.

Technical Field

The invention belongs to the technical field of combustion, and particularly relates to an intelligent prediction method and device for coal powder combustion characteristic parameters and a storage medium.

Background

The acquisition of the characteristic parameters of the pulverized coal combustion process plays a key role in further understanding the stability of the combustion process. On one hand, the development of the measurement technology provides a more advanced and reliable means for monitoring the coal powder combustion process, and on the other hand, the advanced numerical simulation calculation technology also provides a digital prediction way for coal powder combustion.

However, since the pulverized coal combustion process is a transient, high-temperature, multi-phase, multi-component process, high computational cost is often required to achieve high prediction accuracy for the process.

Disclosure of Invention

In order to solve the above problems, the present invention provides a method, an apparatus, and a storage medium for intelligently predicting a characteristic parameter of pulverized coal combustion, which can simplify a process of predicting the stability of pulverized coal combustion and realize intelligentization and digitization of pulverized coal combustion.

The invention is realized by the following technical scheme:

an intelligent prediction method for coal powder combustion characteristic parameters comprises the following steps:

s1: establishing a single-particle coal powder ignition model;

s2: on the basis of a single-particle pulverized coal ignition model, characteristic parameters representing ignition stability are divided into dependent variables and independent variables through a research method of control variables, and the change rules of the dependent variables under different independent variables are respectively researched;

s3: based on the influence rule of each univariate change on the pulverized coal combustion characteristic parameters, selecting regression variables to reasonably reflect the change characteristics of the pulverized coal combustion characteristic parameters;

s4: performing linear regression analysis on the dependent variable and each independent variable through a linear regression analysis tool;

s5: reasonably adjusting the selection of the dependent variable, and optimizing a regression result to ensure that the regression P value of each variable is smaller than a preset value; and determining the weight parameters of the respective variables to obtain a regression relation.

Preferably, in S1, the ignition model of the single-particle pulverized coal is established by coupling a chemical infiltration pyrolysis model of the pulverized coal and a gas-phase chemical reaction mechanism.

Preferably, in S1, after the single-particle pulverized coal ignition model is established, the single-particle pulverized coal ignition model is verified by using typical experimental research results.

Preferably, in S2, the dependent variables include an ignition delay time and an ignition pattern; independent variables include environmental variables and the characteristics of the coal dust particles themselves.

Further preferably, the environmental variables include temperature, oxygen concentration, pressure, carbon dioxide concentration, water vapor concentration, and turbulence intensity; the characteristics of the coal dust particles include volatile content and particle size.

Further preferably, the turbulence intensity quantification adopts switching values of 0 and 1, and in the laminar flow working condition, the value of the turbulence intensity variable is 0; in the turbulent working condition, the value of the turbulent intensity variable is 1.

Preferably, in S4, after performing linear regression analysis, the regression effect is detected by regression test parameters.

Preferably, in S5, the preset value is 5%.

The invention also discloses computer equipment which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor realizes the steps of the intelligent prediction method for the coal powder combustion characteristic parameters when executing the computer program.

The invention also discloses a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to realize the steps of the intelligent prediction method for the pulverized coal combustion characteristic parameters.

Compared with the prior art, the invention has the following beneficial technical effects:

the invention discloses an intelligent prediction method of pulverized coal combustion characteristic parameters, which comprises the steps of firstly establishing a single-particle pulverized coal ignition model, and selecting environmental characteristic conditions and pulverized coal particle characteristic parameters as input parameters, namely independent variables, according to a model calculation result; and selecting concerned coal powder combustion characteristic parameters as dependent variables, and establishing a direct mapping relation between the independent variables and the dependent variables through data analysis. And selecting regression variables based on the influence rule of each univariate change on the pulverized coal combustion characteristic parameters, and optimizing the regression result by reasonably adjusting the selection of the dependent variables. The invention applies the data analysis method to the complicated pulverized coal combustion process, establishes a uniform and universal regression model based on a large amount of experimental and simulation data, realizes the rapid and accurate prediction of the pulverized coal combustion process, and realizes the digitization and the intellectualization of the pulverized coal combustion process.

Furthermore, the single-particle coal powder ignition model is obtained by coupling a coal powder chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism, and the model fully considers the coupling relation between a particle phase and a gas phase, so that the model is closer to the actual process. In addition, the coal powder chemical infiltration pyrolysis model is the most detailed coal powder pyrolysis model which is closest to the actual process at present, and the prediction precision of the coal powder chemical infiltration pyrolysis model is higher than that of other pyrolysis models.

Further, after the single-particle coal powder ignition model is established, the single-particle coal powder ignition model is verified by adopting typical experimental research results so as to verify the accuracy and the effectiveness of the model prediction result.

Further, based on a single-particle pulverized coal ignition model, key variables (including environmental variables and pulverized coal particle characteristics) influencing the pulverized coal combustion characteristics are respectively researched to obtain the influence rule of the single variables on the pulverized coal combustion characteristics.

Further, selecting appropriate dependent variables and independent variables, selecting the independent variables based on the single variable research result, and performing relevant combination on the single variables. The selection of dependent variables mainly selects relevant parameters influencing the combustion stability of the pulverized coal, such as an ignition mode, ignition time and the like.

Furthermore, because detailed research on the influence of turbulence intensity on the ignition characteristics of the pulverized coal is lacked at present, only part of work compares the difference of the ignition behaviors under laminar flow and turbulent flow conditions, and the influence of the turbulence degree on the ignition behaviors is not deeply discussed, so that the switching values of 0 and 1 are adopted for the quantification of the turbulence intensity.

Further, after linear regression analysis, regression effect is detected through regression test parameters to detect whether the selection of regression independent variables is proper or not.

Further, from a statistical point of view, when P < 5%, the regression coefficient was considered significant, and there was a clear linear relationship between the selected variables, so the preset value was set to 5%.

Drawings

FIG. 1 is a schematic flow chart of an intelligent prediction method for coal powder combustion characteristic parameters according to the present invention;

FIG. 2 is a direct mapping of a plurality of independent variables to pulverized coal combustion characteristic parameters.

Detailed Description

The invention will now be described in further detail with reference to the drawings and specific examples, which are given by way of illustration and not by way of limitation.

The method is used for simplifying the coal powder combustion stability prediction process and realizing the intellectualization and digitization of the coal powder combustion. Referring to fig. 2, a direct mapping from a plurality of independent variables to the pulverized coal combustion characteristic parameter is realized through a simple mapping relation.

Selecting characteristic parameters representing ignition stability: the ignition delay time and the ignition mode are used as dependent variables, and the environmental variables are selected as follows: temperature T (K), oxygen concentration f_O2Pressure p (atm), carbon dioxide concentration f_CO2Water vapor concentration f_H2OTurbulence intensity I, and particle self characteristics: volatile content V (%), particle size d (. mu.m), as independent variables.

Referring to fig. 1, the intelligent prediction method for coal powder combustion characteristic parameters of the present invention includes:

(1) firstly, a coal powder chemical infiltration pyrolysis model and a gas phase chemical reaction mechanism are coupled, a single particle ignition model is established, and the model is verified by adopting typical experimental research results.

(2) Based on a single-particle pulverized coal ignition model, different environmental temperatures T (K) and oxygen concentrations f are respectively researched through a research method of control variables_O2Pressure p (atm), carbon dioxide concentration f_CO2Water vapor concentration f_H2OTurbulence intensity I, and particle self characteristics: the volatile content V (%), the particle size d (mum), the ignition delay time of the coal powder particles and the change rule of the characteristic parameters of the ignition mode.

(3) Based on the influence rule of each univariate (single independent variable) change on the pulverized coal combustion characteristic parameters, regression variables are selected, so that the change characteristics of the pulverized coal combustion characteristic parameters can be reasonably reflected.

(4) And (3) carrying out linear regression analysis on the dependent variable and each independent variable through a linear regression analysis tool, and detecting the regression effect through regression test parameters.

(5) And the regression result is optimized by reasonably adjusting the selection of the dependent variable, so that the regression P value of each variable is less than 5%.

Specifically, 1500K, 0.2O₂Concentration, 1atm, 0% CO₂，0％H₂O, the turbulence intensity is 0, the volatile content is 30 percent, and the particle size is 70 mu m, which is the standard working condition. Calculating different environmental temperatures (1200-1800K), different oxygen concentrations (0.1-0.3), different pressures (1-3atm) and different CO through a single-particle ignition model₂Concentration (0% -80%), different H₂Selecting several working conditions from 0-20% of O concentration, 0 or 1% of different turbulence intensity, 10-30% of different volatile component content and 60-90 μm of different particle size, and respectively calculating ignition delay time (t) by using single particle ignition model_ig) And the ignition mode (delta t), and taking the obtained data set as the data set of the intelligent prediction training model. Selecting dependent variables for regression analysis, e.g. t_ig＝f(T^-1,f_O2 ^-1,p^-1,V,d,f_CO2·f_O2 ²,f_CO2·f_O2,f_H2O ²,f_H2O,I/f_O2)，Δt＝f(T^-1,f_O2 ^0.5,p^0.5,V,d,f_CO2,I/f_O2). And obtaining the weight parameters of the respective variables through regression analysis, and verifying that the regression P value of each variable is less than 5%, so that the variables are properly selected and the regression result is credible.

The invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored in the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the intelligent prediction method for the pulverized coal combustion characteristic parameters.

The intelligent prediction method for the pulverized coal combustion characteristic parameters can adopt the forms of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. If the intelligent prediction method for the pulverized coal combustion characteristic parameters is realized in the form of a software functional unit and is sold or used as an independent product, the intelligent prediction method can be stored in a computer readable storage medium.

Based on such understanding, in the exemplary embodiment, a computer readable storage medium is also provided, all or part of the processes in the method of the above embodiments of the present invention can be realized by a computer program to instruct related hardware, the computer program can be stored in the computer readable storage medium, and when the computer program is executed by a processor, the steps of the above method embodiments can be realized. 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. Computer-readable storage media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice. The computer storage medium may be any available medium or data storage device that can be accessed by a computer, including but not limited to magnetic memory (e.g., floppy disk, hard disk, magnetic tape, magneto-optical disk (MO), etc.), optical memory (e.g., CD, DVD, BD, HVD, etc.), and semiconductor memory (e.g., ROM, EPROM, EEPROM, nonvolatile memory (NANDFLASH), Solid State Disk (SSD)), etc.

In an exemplary embodiment, a computer device is further provided, 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 coal powder combustion characteristic parameter intelligent prediction method when executing the computer program. The processor may be a Central Processing Unit (CPU), other general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, etc.

It should be noted that the above description is only a part of the embodiments of the present invention, and equivalent changes made to the system described in the present invention are included in the protection scope of the present invention. Persons skilled in the art to which this invention pertains may substitute similar alternatives for the specific embodiments described, all without departing from the scope of the invention as defined by the claims.