CN111612212A - On-line optimization model updating method for coal powder fineness of coal mill - Google Patents
On-line optimization model updating method for coal powder fineness of coal mill Download PDFInfo
- Publication number
- CN111612212A CN111612212A CN202010279286.7A CN202010279286A CN111612212A CN 111612212 A CN111612212 A CN 111612212A CN 202010279286 A CN202010279286 A CN 202010279286A CN 111612212 A CN111612212 A CN 111612212A
- Authority
- CN
- China
- Prior art keywords
- data
- coal
- model
- prediction
- coal 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Human Resources & Organizations (AREA)
- Databases & Information Systems (AREA)
- Computational Linguistics (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Medical Informatics (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Quality & Reliability (AREA)
- Feedback Control In General (AREA)
- Disintegrating Or Milling (AREA)
Abstract
The invention relates to an on-line optimization model updating method for coal powder fineness of a coal mill. The method comprises the steps of firstly collecting the prediction data of an original model of the coal mill, judging whether the original model needs to be updated or not, then selecting data meeting the requirements of model updating conditions from an original model prediction database, forming model updating sample data by combining the judgment data, and on the basis, establishing a new optimization model for the operation of the coal mill by applying a data-based silence algorithm to realize model updating. The method ensures the prediction precision and generalization capability of the model through data selection, and has higher reliability and feasibility.
Description
Technical Field
The invention belongs to the technical field of information control, relates to a machine learning self-adaptive technology, and particularly relates to an online optimization model updating method for coal powder fineness of a coal mill.
Background
The optimization of the operation of the coal mills is an important technical means for controlling the combustion and the power consumption of the boiler, and the aim is to obtain the required coal powder with ideal fineness by adjusting the operation parameters of each coal mill under certain production conditions and targets, so that the combustion of the boiler and the power consumption of the coal mills are in a good state, and the production benefit is maximized. The coal feeding quantity, the coal quality parameters, the air feeding condition and other operation parameters directly influence the distribution of the coal powder fineness, the combination of different parameters can directly cause different coal powder fineness distribution conditions, and especially under the condition that the operation parameters are disturbed, the coal powder fineness distribution is more unstable. For certain production conditions and product requirements, an optimal operating parameter configuration scheme exists for an ideal operating state required by a coal mill, so that characteristic indexes of corresponding combustion states can be optimized, but the coal powder fineness distribution and the operating parameters of the coal mill have a very complex coupling relation, and the optimal configuration of the operating parameters of each combustor is not easy to find.
By data mining, a machine learning method is applied in a large number of different production operation parameter combinations, a relation model between the operation parameters of each coal mill and the fineness distribution of the coal powder is excavated, and an optimization algorithm is combined to optimize the operation of the coal mills, so that the method is a very potential method.
The key problem of the method is how to ensure that the model can be updated quickly and efficiently to adapt to new conditions because the operation characteristics of the coal mill equipment are changed along with the increase of time or the reason of maintenance, namely the relationship between the coal powder fineness distribution and the operation parameters of each coal mill has time-varying property. The problem has a great relationship with a modeling method, sample data selection, an updating strategy and the like.
Disclosure of Invention
The invention aims to provide a model updating method considering both historical data and new change conditions aiming at the bottleneck problem in the operation optimization of coal mills, and the model can be effectively updated along with the change of the relationship between the coal powder fineness distribution and the operation parameters of each coal mill.
The method comprises the following steps:
and (1) establishing a prediction database of the original model. Collecting each operation parameter, corresponding coal powder fineness measurement data and prediction data of an original model in the production process of the coal mill, and establishing a prediction database of the original model; 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 the corresponding coal powder fineness raw model prediction data is obtained by taking the coal mill operation parameters as input vectors and predicting the coal powder fineness prediction model of the original coal mill. And storing the data into a prediction database of the original model for model updating.
And (2) judging the setting of the original model needing to be updated. Setting a prediction allowable error limit theta of the model, wherein the prediction allowable error limit theta can be set according to specific equipment and process running conditions, and 3% is generally recommended; setting the number m of times that the model continuous prediction error exceeds the allowable error, and setting according to the acquisition difficulty and the period of the pulverized coal fineness data, wherein the general proposal is 3; and when the prediction error of the model exceeds the allowable error limit theta for m times continuously, judging that the model needs to be updated, and recording the data of m times into a prediction database of the original model.
And (3) selecting data. When the model needs to be updated, selecting data meeting the following conditions in the original model prediction database as model updating data: 1, Euclidean distances between the coal mill operation parameter vectors and the m coal mill operation parameter vectors in the step (2) are respectively greater than a set value L, the L can be set according to data conditions and operation condition distribution conditions in a database, and the general proposal is 2; and 2, the data acquisition time is not more than T time from the earliest time point in the m groups of data in the step (2), T can be set according to the data acquisition time condition and the quantity distribution condition in the database, and the general proposal is within half a year. Not less than 30 groups of data are selected according to the above conditions, and if the data meeting the above conditions is less than 30 groups, the time limit of the condition 2 can be properly relaxed, or new data can be collected to complement the 30 groups of data meeting the conditions. And (3) adding the m data in the step (2) to the 30 groups of data to form model updating data.
And (4) updating the model. Using the data selected in step (3) asFor the sample, modeling is performed by using a data-based modeling algorithm, such as a support vector machine algorithm, a neural network algorithm, etc., and input parameters and output parameters of the sample for modeling are expressed 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 taking the ith group as an output parameter, wherein N is the number of samples, and establishing a model between a new coal mill operation parameter and the corresponding coal powder fineness on the basis of training sample data.
Under the condition of modeling data samples, the data modeling method is used for establishing a data-based prediction model in a mature and popular mode, which is not described herein, and the prediction error of the established model is controlled within 2%. And updating of the on-line optimization model of the coal powder fineness of the coal mill is realized.
The model updating method provided by the invention fully utilizes the existing historical data, greatly reduces the workload of model updating, improves the efficiency of model updating, meets the actual requirement of the operation optimization of the coal mill, and ensures the real-time performance and the accuracy of the operation optimization of the coal mill.
Detailed Description
An updating method of an online optimization model of coal powder fineness of a coal mill comprises the following specific steps:
(1) and establishing a prediction database of the original model. Collecting each operation parameter, corresponding coal powder fineness measurement data and prediction data of an original model in the production process of the coal mill, and establishing a prediction database of the original model; 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 the corresponding coal powder fineness raw model prediction data is obtained by taking the coal mill operation parameters as input vectors and predicting the coal powder fineness prediction model of the original coal mill. And storing the data into a prediction database of the original model for model updating.
(2) And judging the setting of the original model needing to be updated. Setting a prediction allowable error limit theta of the model, wherein the prediction allowable error limit theta can be set according to specific equipment and process running conditions, and 3% is generally recommended; setting the number m of times that the model continuous prediction error exceeds the allowable error, and setting according to the acquisition difficulty and the period of the pulverized coal fineness data, wherein the general proposal is 3; and when the prediction error of the model exceeds the allowable error limit theta for m times continuously, judging that the model needs to be updated, and recording the data of m times into a prediction database of the original model.
(3) And (6) selecting data. When the model needs to be updated, selecting data meeting the following conditions in the original model prediction database as model updating data: 1, Euclidean distances between the coal mill operation parameter vectors and the m coal mill operation parameter vectors in the step (2) are respectively greater than a set value L, the L can be set according to data conditions and operation condition distribution conditions in a database, and the general proposal is 2; and 2, the data acquisition time is not more than T time from the earliest time point in the m groups of data in the step (2), T can be set according to the data acquisition time condition and the quantity distribution condition in the database, and the general proposal is within half a year. Not less than 30 groups of data are selected according to the above conditions, and if the data meeting the above conditions is less than 30 groups, the time limit of the condition 2 can be properly relaxed, or new data can be collected to complement the 30 groups of data meeting the conditions. And (3) adding the m data in the step (2) to the 30 groups of data to form model updating data.
(4) And updating the model. Taking the data selected in the step (3) as a sample, modeling by adopting a data-based modeling algorithm, such as a support vector machine algorithm, a neural network algorithm and the like, and expressing input parameters and output parameters of the sample for modeling as
Wherein xiRepresenting the ith group as input dataThe coal pulverizer operating parameters of (1), 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 taking the ith group as an output parameter, wherein N is the number of samples, and establishing a model between a new coal mill operation parameter and the corresponding coal powder fineness on the basis of training sample data.
Under the condition of modeling data samples, the data modeling method is used for establishing a data-based prediction model in a mature and popular mode, which is not described herein, and the prediction error of the established model is controlled within 2%. And updating of the on-line optimization model of the coal powder fineness of the coal mill is realized.
Claims (6)
1. An on-line optimization model updating method for coal powder fineness of a coal mill is characterized by comprising the following steps:
step (1), establishing a prediction database of an original model
Collecting each operation parameter, corresponding coal powder fineness measurement data and prediction data of an original model in the production process of the coal mill, and establishing a prediction database of the original model;
step (2) determining the settings of the original model that need to be updated
Setting a prediction allowable error limit theta of the model, and setting the number m of times that the model continuous prediction error exceeds the allowable error; when the prediction error of the model exceeds the allowable error limit theta for m times continuously, judging that the model needs to be updated, and recording the data of m times into a prediction database of the original model;
step (3) data selection
When the model needs to be updated, selecting data meeting the following conditions in the original model prediction database as model updating data:
firstly, enabling Euclidean distances between the coal mill operation parameter vectors and the m coal mill operation parameter vectors in the step (2) to be respectively larger than a set value L;
secondly, the data acquisition time is not more than T time from the earliest time point in the m groups of data in the step (2);
selecting no less than 30 groups of data according to the conditions, if the data meeting the conditions is less than 30 groups, relaxing the time limit of the condition II, or collecting new data to complement the 30 groups of data meeting the conditions; adding the 30 groups of data to the m data in the step (2) to form model updating data;
step (4) updating the model
Taking the data selected in the step (3) as a sample, modeling by adopting a data-based modeling algorithm, and expressing input parameters and output parameters of the sample for modeling 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 powder fineness of the coal mill of the ith group as an output parameter, wherein N is the number of samples, and establishing a model between a new coal mill operation parameter and the corresponding coal powder fineness on the basis of training sample data;
under the condition of modeling data samples, the prediction error of a model established by establishing a prediction model based on data by using a data modeling method is controlled within 2 percent; and updating of the on-line optimization model of the coal powder fineness of the coal mill is realized.
2. The on-line optimization model updating method for coal pulverizer coal powder fineness according to claim 1, characterized by comprising the following steps: the specific operation parameters in the first step comprise: 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 through a data monitoring control system in the production process of the coal mill or directly obtained through sample collection and measurement of instrument equipment.
3. The on-line optimization model updating method for coal pulverizer coal powder fineness according to claim 1, characterized by comprising the following steps: the corresponding coal powder fineness in the step one is obtained by collecting samples, analyzing and measuring, and the technology is an industry standard technology.
4. The on-line optimization model updating method for coal pulverizer coal powder fineness according to claim 1, characterized by comprising the following steps: and (4) corresponding coal powder fineness raw model prediction data in the step one is obtained by taking the coal mill operation parameters as input vectors and predicting the coal powder fineness prediction model of the original coal mill.
5. The on-line optimization model updating method for coal pulverizer coal powder fineness according to claim 1, characterized by comprising the following steps: and in the second step, the prediction allowable error limit of the model is 3%, and the number of times that the model continuous prediction error exceeds the allowable error is 3.
6. The on-line optimization model updating method for coal pulverizer coal powder fineness according to claim 1, characterized by comprising the following steps: and in the fourth step, modeling is carried out by adopting a data-based modeling algorithm, wherein the modeling algorithm is a support vector machine algorithm and a neural network algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010279286.7A CN111612212A (en) | 2020-04-10 | 2020-04-10 | On-line optimization model updating method for coal powder fineness of coal mill |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010279286.7A CN111612212A (en) | 2020-04-10 | 2020-04-10 | On-line optimization model updating method for coal powder fineness of coal mill |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111612212A true CN111612212A (en) | 2020-09-01 |
Family
ID=72201425
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010279286.7A Pending CN111612212A (en) | 2020-04-10 | 2020-04-10 | On-line optimization model updating method for coal powder fineness of coal mill |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111612212A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| JP7142752B1 (en) * | 2021-07-08 | 2022-09-27 | 住友化学株式会社 | Powder production method, information processing method, program, information processing device, model generation method, data structure, trained model, and powder |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101038277A (en) * | 2007-04-19 | 2007-09-19 | 东北大学 | Soft measurement method for coal power fineness in powdering producer |
| CN102252342A (en) * | 2011-05-05 | 2011-11-23 | 衢州远景资源再生科技有限公司 | Model updating method for online combustion optimization of porous medium combustor |
| CN103400015A (en) * | 2013-08-15 | 2013-11-20 | 华北电力大学 | Composition modeling method for combustion system based on numerical simulation and test operation data |
| CN103728879A (en) * | 2014-01-20 | 2014-04-16 | 华北电力大学 | Power station boiler emission soft measuring method based on least squares support vector machine and on-line updating |
| CN104634706A (en) * | 2015-01-23 | 2015-05-20 | 国家电网公司 | Neural network-based soft measurement method for pulverized coal fineness |
| CN106594794A (en) * | 2016-12-22 | 2017-04-26 | 杭州电子科技大学 | Hybrid and intelligent updating method for boiler efficiency combustion optimization model |
| CN109101683A (en) * | 2018-06-29 | 2018-12-28 | 杭州电子科技大学 | Coal-fired sub-prime utilizes the model update method with cleaning pretreatment system pyrolysis kettle |
| CN110794782A (en) * | 2019-11-08 | 2020-02-14 | 中国矿业大学 | Batch industrial process online quality prediction method based on JY-MKPLS |
-
2020
- 2020-04-10 CN CN202010279286.7A patent/CN111612212A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101038277A (en) * | 2007-04-19 | 2007-09-19 | 东北大学 | Soft measurement method for coal power fineness in powdering producer |
| CN102252342A (en) * | 2011-05-05 | 2011-11-23 | 衢州远景资源再生科技有限公司 | Model updating method for online combustion optimization of porous medium combustor |
| CN103400015A (en) * | 2013-08-15 | 2013-11-20 | 华北电力大学 | Composition modeling method for combustion system based on numerical simulation and test operation data |
| CN103728879A (en) * | 2014-01-20 | 2014-04-16 | 华北电力大学 | Power station boiler emission soft measuring method based on least squares support vector machine and on-line updating |
| CN104634706A (en) * | 2015-01-23 | 2015-05-20 | 国家电网公司 | Neural network-based soft measurement method for pulverized coal fineness |
| CN106594794A (en) * | 2016-12-22 | 2017-04-26 | 杭州电子科技大学 | Hybrid and intelligent updating method for boiler efficiency combustion optimization model |
| CN109101683A (en) * | 2018-06-29 | 2018-12-28 | 杭州电子科技大学 | Coal-fired sub-prime utilizes the model update method with cleaning pretreatment system pyrolysis kettle |
| CN110794782A (en) * | 2019-11-08 | 2020-02-14 | 中国矿业大学 | Batch industrial process online quality prediction method based on JY-MKPLS |
Non-Patent Citations (3)
| Title |
|---|
| 张伟;熊伟丽;徐保国;: "基于实时学习的高斯过程回归多模型融合建模", no. 04 * |
| 杨耀权;张新胜;: "LSSVM动态软测量模型在磨煤机一次风量预测方面的应用", no. 03 * |
| 王高升;刘振娟;李宏光;: "加热炉缓变故障的预测监控方法", no. 09 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP7142752B1 (en) * | 2021-07-08 | 2022-09-27 | 住友化学株式会社 | Powder production method, information processing method, program, information processing device, model generation method, data structure, trained model, and powder |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107042234B (en) | Intelligent technique production method based on the acquisition of bar whole process big data | |
| CN111353656B (en) | Steel enterprise oxygen load prediction method based on production plan | |
| CN101995822A (en) | Grey active disturbance rejection control method of long time-delay system | |
| CN111612212A (en) | On-line optimization model updating method for coal powder fineness of coal mill | |
| CN209485669U (en) | A kind of hobboing cutter information monitoring device | |
| WO2021007871A1 (en) | Alumina production operation optimization system and method employing cloud-side collaboration | |
| CN104699050A (en) | Leaf-shred preparation segment on-line monitoring and fault diagnosing method for cigarette filament treatment driven by data | |
| CN112418538A (en) | Continuous casting billet inclusion prediction method based on random forest classification | |
| CN114418177B (en) | New product material distribution prediction method based on digital twin workshops for generating countermeasure network | |
| CN111612210A (en) | Online optimization method for coal powder fineness of coal mill | |
| CN105242660A (en) | Multi-modal cigarette primary processing process online monitoring and fault diagnosis method based on relative change analysis | |
| CN117114226B (en) | Intelligent dynamic optimization and process scheduling system of automation equipment | |
| CN111676365A (en) | LSTM-based method for predicting annealing temperature set value of transition steel coil | |
| CN109902871A (en) | A kind of intelligent optimization energy conserving system of combination enterprise production line differentiation feature | |
| CN113325819B (en) | Continuous annealing unit fault diagnosis method and system based on deep learning algorithm | |
| CN111617876A (en) | Method for optimizing online comprehensive operation of coal mill | |
| Mukherjee et al. | Real-time coal classification in thermal power plants | |
| CN201666923U (en) | Device for processing DSP failure diagnosis of electric power system by using immune genetic algorithm | |
| US20080004722A1 (en) | Process-related systems and methods | |
| CN108709426B (en) | Sintering machine air leakage fault online diagnosis method based on frequency spectrum characteristic bilateral detection method | |
| CN116822319A (en) | Industrial product manufacturing quality active prediction control method based on cloud edge cooperative computing | |
| CN113769880B (en) | Industrial big data-based optimization method for control index of cement production raw material grinding system | |
| Liu et al. | Research and application of the sintering whole process intelligent manufacturing system | |
| CN113138584A (en) | Bioreactor data management and remote control system and method | |
| Qiang et al. | The combination prediction of BTP in sintering process based on Bayesian framework and LS-SVM |
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 |