CN111612210A - Online optimization method for coal powder fineness of coal mill - Google Patents
Online optimization method for coal powder fineness of coal mill Download PDFInfo
- Publication number
- CN111612210A CN111612210A CN202010278769.5A CN202010278769A CN111612210A CN 111612210 A CN111612210 A CN 111612210A CN 202010278769 A CN202010278769 A CN 202010278769A CN 111612210 A CN111612210 A CN 111612210A
- Authority
- CN
- China
- Prior art keywords
- coal
- data
- fineness
- coal mill
- mill
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Molecular Biology (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Entrepreneurship & Innovation (AREA)
- Algebra (AREA)
- Development Economics (AREA)
- Mathematical Analysis (AREA)
- Game Theory and Decision Science (AREA)
- Feedback Control In General (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Pure & Applied Mathematics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Regulation And Control Of Combustion (AREA)
- Medical Informatics (AREA)
Abstract
The invention discloses an online optimization method for coal pulverizer coal dust fineness, which aims to solve the bottleneck problem of coal pulverizer operation optimization and provides an optimization method for coal pulverizer coal dust fineness, wherein optimization contents take all operation parameters and combustion states into consideration. The operation parameters and the coal powder fineness of the coal mill are optimized by acquiring the operation parameters and the corresponding coal powder fineness data in the production process of the coal mill and then applying a modeling algorithm and an optimization algorithm. The method is a path with better prediction precision and real-time performance in the optimization of the coal mill, can effectively improve the efficiency of the boiler unit, and can implement off-line optimization and on-line real-time optimization.
Description
Technical Field
The invention belongs to the technical field of information and control, relates to an automation technology, and particularly relates to an online optimization method for coal powder fineness of a coal mill.
Background
The coal powder fineness of the coal mill directly determines the combustion efficiency of the boiler and the power consumption of an auxiliary machine, and is an important technical key in the operation of a power station boiler system. The fineness of the coal powder has a complex nonlinear relation with a plurality of coal mill operating parameters, and mathematical analysis modeling is difficult to perform. Under certain equipment conditions and requirements, a data model between operation parameters and coal powder fineness is established for a coal mill, and the coal powder fineness is optimized by combining an optimization algorithm, which is very meaningful. However, it is not easy to build a model with accurate prediction capability, and it is also difficult to implement online optimization calculation.
Disclosure of Invention
The invention aims to provide a method for optimizing the coal powder fineness of a coal mill, aiming at the bottleneck problem of operation optimization of the coal mill.
The method comprises the steps of firstly acquiring operation parameters and corresponding coal powder fineness data in the production process of the coal mill, and then optimizing the operation parameters and the coal powder fineness of the coal mill by applying a modeling algorithm and an optimization algorithm. The method is a good path for optimizing coal mills in terms of prediction accuracy and real-time performance.
The method comprises the following specific steps:
step (1) collecting each operation parameter and corresponding coal powder fineness data in the production process of a coal mill, and establishing a coal mill operation characteristic database; the specific operating parameters include: the industrial analysis data of the coal quality, the coal feeding quantity, the coal mill air inlet quantity and the air inlet temperature, the coal mill current and the separator rotating speed. The coal mill operation parameters can be obtained by a data monitoring and controlling system in the production process of the coal mill or directly obtained by sampling and measuring through instrument equipment. The corresponding coal powder fineness can be obtained by collecting samples, analyzing and measuring, and the technology is an industry standard technology.
And (2) establishing a model between the coal mill operation parameters and the coal powder fineness, selecting training samples and inspection samples from the coal mill operation characteristic database established in the step (1), wherein the closer the acquisition time of the selected sample data to the modeling time is, the better the acquisition time is, so as to ensure the data consistency, and the specific time range can be adjusted according to the required quantity of the modeling data and the distribution condition of the data in the database. The amount of the test sample data is one third of that of the training sample data, the data are not completely the same, and different data account for one tenth to one fifth of the test sample;
step (3) modeling by adopting a data-based modeling algorithm, such as a Gaussian process algorithm, a neural network algorithm, a Bayesian algorithm and the like, and establishing a model between the coal mill operation parameters and the coal powder fineness;
the input parameters and output parameters for modeling the sample are represented as
Wherein xiRepresenting the ith group of coal mill operating parameters as input data, comprising: the industrial analysis data of the coal quality, the coal feeding quantity, the air inlet quantity and the air inlet temperature of the coal mill, the current quantity of the coal mill and the rotating speed of the separator. y isiAnd representing the coal powder fineness of the coal mill of the ith group as an output parameter, wherein N is the number of samples and is greater than 40 so as to ensure the prediction capability of the model, and establishing the model between the coal mill operation parameter and the corresponding coal powder fineness on the basis of actual data.
In the case of a modeling sample, establishing a data-based prediction model by using a data modeling method is a mature and popular mode, which is not described herein again. The prediction error of the established model is controlled within 2 percent.
And (4) optimizing coal mill parameter configuration according to different coal powder fineness requirements by utilizing a particle swarm optimization algorithm in combination with the coal mill coal powder fineness model established in the step (3) so as to achieve the aims of optimizing coal powder fineness and further improving the operation efficiency of the boiler unit, and the method specifically comprises the following steps:
a. defining each dimensional component of the particle swarm position vector x as each operation parameter of the coal mill respectively;
b. setting a search target and iteration times of the particle swarm, wherein the search target is set as follows: min | di-ddL where diPredicted coal fines fineness for coal pulverizer coal fines fineness model, ddThe fineness of the pulverized coal is set according to the combustion requirement; the number of iterations can be set between 20-100, taking into account the requirements of online application and production.
c. Setting the optimizing range of each operation parameter according to the design and operation requirements of an actual coal mill, initializing a position vector x, then performing iterative computation by using a particle swarm algorithm and combining the pulverized coal fineness model established in the step (3) according to the search target set in the previous step, predicting the corresponding pulverized coal fineness of the pulverized coal fineness model according to the position vector of the particle swarm algorithm by using the pulverized coal fineness model, and then performing the computation of the search target so as to search the optimal position of the particle swarm in the operation parameter vector space of the coal mill;
d. and when the particle swarm algorithm finishes the iteration times or finds the optimal set requirement, stopping calculating to obtain the corresponding optimal position vector, namely obtaining the optimal coal mill operation parameter combination and the corresponding coal powder fineness.
The method can be optimized on line or off line; according to the method, a relational model of coal mill operation parameters and coal powder fineness is obtained by data modeling and applying a modeling algorithm in different production operation parameter combinations, and the coal powder fineness of the coal mill is optimized on line by combining a particle swarm algorithm. The key to the technology is how to really meet the actual production requirement of the method, and the main problems comprise how to select modeling data, improve the prediction capability and generalization capability of a model, improve the online optimization calculation capability and the like.
Detailed Description
A predictive modeling method for coal powder fineness of a coal mill specifically comprises the following steps:
(1) collecting each operation parameter and corresponding coal powder fineness data in the production process of the coal mill, and establishing a coal mill operation characteristic database; the specific operating parameters include: the industrial analysis data of the coal quality, the coal feeding quantity, the coal mill air inlet quantity and the air inlet temperature, the coal mill current and the separator rotating speed. The coal mill operation parameters can be obtained by a data monitoring and controlling system in the production process of the coal mill or directly obtained by sampling and measuring through instrument equipment. The corresponding coal powder fineness can be obtained by collecting samples, analyzing and measuring, and the technology is an industry standard technology.
(2) In order to establish a model between the coal mill operation parameters and the coal powder fineness, training samples and inspection samples are selected from the coal mill operation characteristic database established in the step (1), the closer the acquisition time of the selected sample data to the modeling time is, the better the data consistency is ensured, and the specific time range can be adjusted according to the required quantity of the modeling data and the distribution condition of the data in the database. The amount of the test sample data is one third of that of the training sample data, the data are not completely the same, and different data account for one tenth to one fifth of the test sample;
(3) modeling by adopting a data-based modeling algorithm, such as a Gaussian process algorithm, a neural network algorithm, a Bayesian algorithm and the like, and establishing a model between the coal mill operation parameters and the coal powder fineness;
the input parameters and output parameters for modeling the sample are represented as
Wherein xiRepresenting the ith group of coal mill operating parameters as input data, comprising: the industrial analysis data of the coal quality, the coal feeding quantity, the air inlet quantity and the air inlet temperature of the coal mill, the current quantity of the coal mill and the rotating speed of the separator. y isiAnd representing the coal powder fineness of the coal mill of the ith group as an output parameter, wherein N is the number of samples and is greater than 40 so as to ensure the prediction capability of the model, and establishing the model between the coal mill operation parameter and the corresponding coal powder fineness on the basis of actual data.
In the case of a modeling sample, establishing a data-based prediction model by using a data modeling method is a mature and popular mode, which is not described herein again. The prediction error of the established model is controlled within 2 percent.
(4) And (3) optimizing coal mill parameter configuration according to the requirements of different coal powder fineness by utilizing a particle swarm optimization algorithm in combination with the coal mill coal powder fineness model established in the step (3) so as to achieve the aims of optimizing the coal powder fineness and further improving the operation efficiency of the boiler unit, and the method specifically comprises the following steps:
a. defining each dimensional component of the particle swarm position vector x as each operation parameter of the coal mill respectively;
b. setting a search target and iteration times of the particle swarm, wherein the search target is set as follows: min | di-ddL where diPredicted coal fines fineness for coal pulverizer coal fines fineness model, ddThe fineness of the pulverized coal is set according to the combustion requirement; the number of iterations can be set between 20-100, taking into account the requirements of online application and production.
c. Setting the optimizing range of each operation parameter according to the design and operation requirements of an actual coal mill, initializing a position vector x, then performing iterative computation by using a particle swarm algorithm and combining the pulverized coal fineness model established in the step (3) according to the search target set in the previous step, predicting the corresponding pulverized coal fineness of the pulverized coal fineness model according to the position vector of the particle swarm algorithm by using the pulverized coal fineness model, and then performing the computation of the search target so as to search the optimal position of the particle swarm in the operation parameter vector space of the coal mill;
d. and when the particle swarm algorithm finishes the iteration times or finds the optimal set requirement, stopping calculating to obtain the corresponding optimal position vector, namely obtaining the optimal coal mill operation parameter combination and the corresponding coal powder fineness.
And adjusting the actual combustion of each combustor according to the obtained optimal parameter combination to achieve the purpose of combustion optimization.
Claims (3)
1. An on-line optimization method for coal powder fineness of a coal mill is characterized by comprising the following steps:
step (1): collecting each operation parameter and corresponding coal powder fineness data in the production process of the coal mill, and establishing a coal mill operation characteristic database;
step (2): in order to establish a model between the coal mill operation parameters and the coal powder fineness, a training sample and a test sample are selected from the coal mill operation characteristic database established in the step (1), the closer the acquisition time of the selected sample data to the modeling time is, the better the acquisition time is, so as to ensure the data consistency, and the specific time range is adjusted according to the required quantity of the modeling data and the distribution condition of the data in the database; the amount of the test sample data is one third of that of the training sample data, the data are not completely the same, and different data account for one tenth to one fifth of the test sample;
modeling by adopting a data-based modeling algorithm, and establishing a model between the operating parameters of the coal mill and the fineness of the pulverized coal;
the input parameters and output parameters for modeling the sample are represented as
Wherein xiRepresenting the ith group of coal mill operating parameters as input data, comprising: the method comprises the following steps of (1) industrial analysis data of coal quality, coal feeding quantity, coal mill air inlet quantity and air inlet temperature, coal mill current quantity and separator rotating speed; y isiRepresenting the coal mill coal powder fineness of the ith group as an output parameter, wherein N is the number of samples and is more than 40 so as to ensure the prediction capability of the model, and establishing a model between the coal mill operation parameter and the corresponding coal powder fineness on the basis of actual data;
under the condition of a modeling sample, establishing a prediction model based on data by using a data modeling method is a mature and popular mode, which is not described herein any more; the prediction error of the established model is controlled within 2 percent;
and (4) optimizing coal mill parameter configuration according to different coal powder fineness requirements by utilizing a particle swarm optimization algorithm in combination with the coal mill coal powder fineness model established in the step (3) so as to achieve the aims of optimizing coal powder fineness and further improving the operation efficiency of the boiler unit, and the method specifically comprises the following steps:
a. defining each dimensional component of the particle swarm position vector x as each operation parameter of the coal mill respectively;
b. setting a search target and iteration times of the particle swarm, wherein the search target is set as follows: min | di-ddL where diPredicted coal fines fineness for coal pulverizer coal fines fineness model, ddThe fineness of the pulverized coal is set according to the combustion requirement; the iteration number is set to be between 20 and 100 times in consideration of the requirements of online application and production;
c. setting the optimizing range of each operation parameter according to the design and operation requirements of an actual coal mill, initializing a position vector x, then performing iterative computation by using a particle swarm algorithm and combining the pulverized coal fineness model established in the step (3) according to the search target set in the previous step, predicting the corresponding pulverized coal fineness of the pulverized coal fineness model according to the position vector of the particle swarm algorithm by using the pulverized coal fineness model, and then performing the computation of the search target so as to search the optimal position of the particle swarm in the operation parameter vector space of the coal mill;
d. and when the particle swarm algorithm finishes the iteration times or finds the optimal set requirement, stopping calculating to obtain the corresponding optimal position vector, namely obtaining the optimal coal mill operation parameter combination and the corresponding coal powder fineness.
2. The on-line optimization method for coal powder fineness of the coal mill as claimed in claim 1, characterized in that: the operating parameters include: the method comprises the following steps of (1) industrial analysis data of coal quality, coal feeding quantity, coal mill air inlet quantity and air inlet temperature, coal mill current and separator rotating speed; the coal mill operation parameters are obtained by a data monitoring control system in the production process of the coal mill or directly obtained by sampling and measuring samples by instrument equipment; the corresponding coal powder fineness is obtained by collecting samples, analyzing and measuring, and the technology is an industry standard technology.
3. The on-line optimization method for coal powder fineness of the coal mill as claimed in claim 1, characterized in that: and (3) adopting a modeling algorithm in the data-based modeling algorithm modeling to comprise a Gaussian process algorithm, a neural network algorithm or a Bayesian algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010278769.5A CN111612210A (en) | 2020-04-10 | 2020-04-10 | Online optimization method for coal powder fineness of coal mill |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010278769.5A CN111612210A (en) | 2020-04-10 | 2020-04-10 | Online optimization method for coal powder fineness of coal mill |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111612210A true CN111612210A (en) | 2020-09-01 |
Family
ID=72195716
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010278769.5A Pending CN111612210A (en) | 2020-04-10 | 2020-04-10 | Online optimization method for coal powder fineness of coal mill |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111612210A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112130538A (en) * | 2020-09-22 | 2020-12-25 | 京东城市(北京)数字科技有限公司 | Method, device, equipment and medium for control optimization and model training of coal mill |
| CN113743672A (en) * | 2021-09-09 | 2021-12-03 | 西安热工研究院有限公司 | Coal mill economic coal powder fineness on-line analysis and operation optimization guidance method |
| CN114054191A (en) * | 2021-11-17 | 2022-02-18 | 西安热工研究院有限公司 | Coal mill pulverized coal optimal fineness evaluation method based on cost change |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104374675A (en) * | 2014-10-15 | 2015-02-25 | 国家电网公司 | Coal mill pulverized coal fineness online monitoring method |
| CN104634706A (en) * | 2015-01-23 | 2015-05-20 | 国家电网公司 | Neural network-based soft measurement method for pulverized coal fineness |
| CN107016176A (en) * | 2017-03-24 | 2017-08-04 | 杭州电子科技大学 | A kind of hybrid intelligent overall boiler burning optimization method |
| CN109615084A (en) * | 2017-09-30 | 2019-04-12 | 中电华创电力技术研究有限公司 | Positive-pressure type medium-speed pulverizer fuel pulverizing plant fineness of pulverized coal real-time monitoring system |
-
2020
- 2020-04-10 CN CN202010278769.5A patent/CN111612210A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104374675A (en) * | 2014-10-15 | 2015-02-25 | 国家电网公司 | Coal mill pulverized coal fineness online monitoring method |
| CN104634706A (en) * | 2015-01-23 | 2015-05-20 | 国家电网公司 | Neural network-based soft measurement method for pulverized coal fineness |
| CN107016176A (en) * | 2017-03-24 | 2017-08-04 | 杭州电子科技大学 | A kind of hybrid intelligent overall boiler burning optimization method |
| CN109615084A (en) * | 2017-09-30 | 2019-04-12 | 中电华创电力技术研究有限公司 | Positive-pressure type medium-speed pulverizer fuel pulverizing plant fineness of pulverized coal real-time monitoring system |
Non-Patent Citations (1)
| Title |
|---|
| 刘定平等: "基于煤粉细度反馈控制的制粉系统优化", vol. 35, no. 6, pages 34 - 42 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112130538A (en) * | 2020-09-22 | 2020-12-25 | 京东城市(北京)数字科技有限公司 | Method, device, equipment and medium for control optimization and model training of coal mill |
| CN113743672A (en) * | 2021-09-09 | 2021-12-03 | 西安热工研究院有限公司 | Coal mill economic coal powder fineness on-line analysis and operation optimization guidance method |
| CN113743672B (en) * | 2021-09-09 | 2024-04-05 | 西安热工研究院有限公司 | Online analysis and operation optimization guiding method for economic coal fines fineness of coal mill |
| CN114054191A (en) * | 2021-11-17 | 2022-02-18 | 西安热工研究院有限公司 | Coal mill pulverized coal optimal fineness evaluation method based on cost change |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111612210A (en) | Online optimization method for coal powder fineness of coal mill | |
| CN109541168B (en) | Coal powder economic fineness on-line monitoring and adjusting method | |
| CN101863088B (en) | Method for forecasting Mooney viscosity in rubber mixing process | |
| CN108564204B (en) | Least square support vector machine electricity quantity prediction method based on maximum correlation entropy criterion | |
| CN109935280B (en) | Blast furnace molten iron quality prediction system and method based on ensemble learning | |
| CN112433507B (en) | LSO-LSSVM (least squares support vector machine) -based five-axis numerical control machine tool thermal error comprehensive modeling method | |
| Li et al. | Dynamic time features expanding and extracting method for prediction model of sintering process quality index | |
| CN111617876B (en) | Method for optimizing online comprehensive operation of coal mill | |
| CN102540879A (en) | Multi-target evaluation optimization method based on group decision making retrieval strategy | |
| CN110782067B (en) | Sintering end point fluctuation range prediction method based on fuzzy information granulation | |
| Hu et al. | Multi-model ensemble prediction model for carbon efficiency with application to iron ore sintering process | |
| CN116377370A (en) | Plasma spraying control system and method based on digital twin | |
| Zhou et al. | A new Co/Co $ _2 $ prediction model based on labeled and unlabeled process data for sintering process | |
| Takalo-Mattila et al. | Explainable steel quality prediction system based on gradient boosting decision trees | |
| CN104263960B (en) | On-line prediction method for replacement rate and gold mud grade in gold hydrometallurgy replacement process | |
| Liang et al. | A transfer predictive control method based on inter-domain mapping learning with application to industrial roasting process | |
| Li et al. | Multi-agent evolution reinforcement learning method for machining parameters optimization based on bootstrap aggregating graph attention network simulated environment | |
| CN111612212A (en) | On-line optimization model updating method for coal powder fineness of coal mill | |
| CN112541296A (en) | SO2 prediction method based on PSO-LSSVM | |
| CN111612211A (en) | Predictive modeling method for coal powder fineness of coal mill | |
| CN108709426B (en) | Sintering machine air leakage fault online diagnosis method based on frequency spectrum characteristic bilateral detection method | |
| CN114740713A (en) | Multi-objective optimization control method for wet flue gas desulfurization process | |
| Qiang et al. | The combination prediction of BTP in sintering process based on Bayesian framework and LS-SVM | |
| Zhang et al. | Design of a prediction and optimization system for plate shape in roller quenching process | |
| Zhang et al. | Attention-based stacked supervised poisson autoencoders for defects prediction in casting-rolling process |
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 |