CN109492322B - Prediction method for spontaneous combustion position of coal body in coal storage silo - Google Patents
Prediction method for spontaneous combustion position of coal body in coal storage silo Download PDFInfo
- Publication number
- CN109492322B CN109492322B CN201811409958.0A CN201811409958A CN109492322B CN 109492322 B CN109492322 B CN 109492322B CN 201811409958 A CN201811409958 A CN 201811409958A CN 109492322 B CN109492322 B CN 109492322B
- Authority
- CN
- China
- Prior art keywords
- storage silo
- coal storage
- coal
- temperature
- layer
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- 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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
Abstract
The invention discloses a method for predicting the spontaneous combustion position of a coal body in a coal storage silo, which comprises the following steps: establishing a coal storage silo calculation model, and performing gridding division; setting parameter boundary conditions; initializing the whole working condition, setting the maximum calculation step length, and starting calculation; after the calculation result is obtained, a three-layer BP neural training network taking the position coordinates and the temperature values of the temperature measuring points of the inner wall surface of the coal storage silo as input and taking the coordinates and the temperature values of the self-ignition points as output is established, 90% of the obtained data in the node temperature of the inner layer of the grid line area are used as training samples, and the rest 10% of the data are used as test samples, so that the prediction result of the spontaneous combustion position is obtained; and applying the trained three-layer BP neural network to the inside of a coal storage silo of an actual power plant to predict the self-ignition point of the coal body. The invention has the beneficial effects that: the method has the advantages that the self-ignition point of the coal position of the coal storage silo is predicted by a neural network method, the self-ignition point position can be found before temperature monitoring and early warning, and the safe operation of the coal storage system of the power plant is ensured.
Description
Technical Field
The invention relates to the technical field of coal storage silos, in particular to a method for predicting spontaneous combustion positions of coal bodies in the coal storage silos.
Background
The application of the cylindrical coal storage bin in the coal-fired power plant in China is more and more widespread at present, but because the heat storage condition of loose coal bodies in the cylindrical coal storage bin is good, the heat storage quantity is large, and the release is difficult, the high-temperature range is large, and the spontaneous combustion phenomenon is easy to occur under the conditions of low-temperature oxidization of coal, excessive heat accumulation and the like. At present, the temperature of the coal in the silo is mainly monitored in the aspect of preventing spontaneous combustion, however, some monitoring systems can only monitor the temperature of the coal close to the wall of the silo; in addition, a plurality of temperature measuring cables are arranged in the silo, but the cables are damaged to a great extent along with continuous coal feeding and coal dropping, so that the cables need to be inspected and replaced at an unscheduled period, and the application of actual engineering is not facilitated. At present, no accurate and effective method is available for predicting the area where spontaneous combustion is easily caused by the coal in the coal storage bin.
Disclosure of Invention
In order to solve the problems, the invention aims to provide the method for predicting the spontaneous combustion position of the coal body in the coal storage silo, which predicts the spontaneous combustion point of the coal position of the coal storage silo, can find the spontaneous combustion point position before temperature monitoring and early warning, is favorable for taking measures in advance to prevent the spontaneous combustion area from expanding and ensures the safe operation of a coal storage system of a power plant.
The invention provides a method for predicting the spontaneous combustion position of a coal body in a coal storage silo, which comprises the following steps:
step 1, building a coal storage silo calculation model according to the structure size of an actual coal storage silo, gridding the coal storage silo calculation model, arranging temperature measuring points on the outermost layer nodes of the gridline areas, namely the inner wall of the coal storage silo, and acquiring the temperature value of each temperature measuring point through a temperature sensor on the temperature measuring point;
step 2, setting parameter boundary conditions for a coal storage silo calculation model;
step 3, initializing the whole working condition of the coal storage silo calculation model, setting the maximum calculation step length, and starting calculation to obtain the node temperature of the inner layer of the grid line area of the coal storage silo calculation model;
step 4, after a calculation result is obtained, a three-layer BP neural training network taking the position coordinates and the temperature values of temperature measuring points on the inner wall surface of the coal storage silo as input and taking the coordinates and the temperature values of the self-ignition points as output is established, 90% of data in the node temperature of the inner layer of the obtained grid line area is taken as a training sample, the rest 10% of data is taken as a test sample, and the self-ignition points in the calculation model of the coal storage silo are predicted by utilizing the three-layer BP neural network, so that a prediction result of the self-ignition position is obtained;
and 5, applying the trained three-layer BP neural network to the interior of a coal storage silo of an actual power plant to predict the self-ignition point of the coal body.
As a further improvement of the invention, in step 1, the structural dimensions of the coal storage silo include silo radius, height, cone radius, cone bus length and cone angle.
As a further improvement of the invention, in the step 1, the specific method of gridding division is as follows: the method comprises the steps of dividing the inner wall of a coal storage silo into n layers of interfaces along the radial direction, dividing the inner wall of the coal storage silo into m layers of interfaces along the axial direction, forming grid lines on the interfaces in two directions, wherein the crossing points of the grid lines are nodes, respectively arranging temperature measuring points on the inner wall of the coal storage silo, namely the nodes on the outermost layer, and respectively measuring the temperature values of all the nodes on the temperature measuring points through temperature sensors.
In step 2, setting the coal storage silo model to be steady, setting parameters of coal including density, specific heat and heat conductivity coefficient, setting a self-ignition temperature range and the temperature of the peripheral wall surface of the coal storage silo, and setting the position coordinates of temperature measuring points of the inner wall surface of the coal storage silo.
As a further improvement of the invention, in the step 3, the specific method for calculating the node temperature of the inner layer of the grid line area is as follows: establishing an energy conservation equation for the control volume represented by the outermost layer node according to the heat conduction micro equation, and solving the temperature value of the penultimate layer node according to the measured temperature value of the outermost layer node and the energy conservation equation; establishing an energy conservation equation for the control volume represented by the penultimate layer node according to the heat conduction micro equation, and solving the temperature value of the penultimate layer node according to the temperature value of the penultimate layer node and the energy conservation equation; pushing the nodes layer by layer until the temperature value of the innermost node is obtained.
The beneficial effects of the invention are as follows:
the method has the advantages that the self-ignition point of the coal position of the coal storage silo is predicted by a neural network method, the self-ignition point position can be found before temperature monitoring and early warning, measures can be taken in advance to prevent the expansion of the spontaneous combustion area, and the safe operation of the coal storage system of the power plant is ensured.
Drawings
Fig. 1 is a schematic flow chart of a method for predicting spontaneous combustion positions of coal bodies in a coal storage silo according to an embodiment of the invention.
Detailed Description
The invention will now be described in further detail with reference to specific examples thereof in connection with the accompanying drawings.
As shown in fig. 1, the method for predicting the spontaneous combustion position of the coal body in the coal storage silo according to the embodiment of the invention specifically includes:
step 1, a coal storage silo calculation model is established according to the structure size (comprising silo radius, height, cone radius, cone bus length and cone angle) of an actual coal storage silo, the coal storage silo calculation model is subjected to gridding division, temperature measuring points are arranged on the outermost layer nodes of the gridline areas, namely the inner wall of the coal storage silo, and the temperature value of each temperature measuring point is obtained through a temperature sensor on each temperature measuring point.
The specific method for gridding division comprises the following steps: the method comprises the steps of dividing the inner wall of a coal storage silo into n layers of interfaces along the radial direction, dividing the inner wall of the coal storage silo into m layers of interfaces along the axial direction, forming grid lines on the interfaces in two directions, wherein the crossing points of the grid lines are nodes, respectively arranging temperature measuring points on the inner wall of the coal storage silo, namely the nodes on the outermost layer, and respectively measuring the temperature values of all the nodes on the temperature measuring points through temperature sensors.
And 2, setting parameter boundary conditions for the coal storage silo calculation model.
The spontaneous combustion of the coal in the coal storage silo is an extremely long process, and the coal body can be approximately regarded as isotropic pure solid, so that the coal storage silo model is set to be stable, parameters of the coal comprise density, specific heat and heat conductivity coefficient, a self-combustion point temperature range and the temperature of the peripheral wall surface of the coal storage silo are set, and the position coordinates of temperature measuring points of the inner wall surface of the coal storage silo are set.
And step 3, initializing the whole working condition of the coal storage silo calculation model, setting the maximum calculation step length, and starting calculation to obtain the node temperature of the inner layer of the grid line area of the coal storage silo calculation model.
The specific method for calculating the temperature of the inner layer node of the grid line area comprises the following steps: establishing an energy conservation equation for the control volume represented by the outermost layer node according to the heat conduction micro equation, and solving the temperature value of the penultimate layer node according to the measured temperature value of the outermost layer node and the energy conservation equation; establishing an energy conservation equation for the control volume represented by the penultimate layer node according to the heat conduction micro equation, and solving the temperature value of the penultimate layer node according to the temperature value of the penultimate layer node and the energy conservation equation; pushing the nodes layer by layer until the temperature value of the innermost node is obtained.
And 4, after a calculation result is obtained, establishing a three-layer BP neural training network taking the position coordinates and the temperature values of the temperature measuring points of the inner wall surface of the coal storage silo as input and taking the position coordinates and the temperature values of the self-ignition points as output, taking 90% of data in the node temperature of the inner layer of the obtained grid line area as a training sample, taking the rest 10% of data as a test sample, and predicting the self-ignition points in the calculation model of the coal storage silo by utilizing the three-layer BP neural network to obtain a prediction result of the self-ignition position.
In order to meet the training and prediction requirements of the three-layer BP neural network, the self-ignition point position should cover the whole coal storage silo area, and the whole data is more than 100 groups.
The data format is shown in the following table:
wherein X, Y, Z represents the position coordinates within the coal storage silo (within the three-dimensional space).
Based on the neural network theory, the existing data are trained by the neural network, reverse error propagation is used in the training process, the training is adjusted for multiple times, the error is continuously reduced, the expected value is approximated, the network weight and the deviation are saved, after the network training is finished, the number of hidden function nodes, the learning rate, the momentum factors, the connection weight of each node and the iteration frequency are obtained, and the unknown sample, namely the spontaneous combustion position, can be predicted. By carrying out numerical simulation on the coal storage silo with the self-ignition point, data for verifying the correctness of the BP neural network can be obtained. Finally, the neural network can be applied to prediction of the self-ignition point of the fire coal in the coal storage silo of the actual power plant.
The specific network training process is as follows:
(1) Initializing a neural network, weighting the neural network with a set of random numbers, setting training step length eta, allowing error e and network structure (i.e. network layer number L and node number n of each layer 1 )；
(2) Providing a set of training samples (i.e., 90% of the data in the node temperature in the inner layer of the gridline region) to the neural network;
(3) For each training sample p-cycle:
forward computing the input and output of each node of the neural network layer by layer;
calculating an error Ep of the output of the p-th training sample and a total error E of the neural network;
when E is smaller than the allowable error E or reaches the appointed iteration times, the training process is ended, otherwise, error back propagation is carried out;
reverse layer-by-layer calculation of errors of nodes of neural network
And correcting the connection weight of the neural network.
And 5, applying the trained three-layer BP neural network to the interior of a coal storage silo of an actual power plant to predict the self-ignition point of the coal body.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. The method for predicting the spontaneous combustion position of the coal body in the coal storage silo is characterized by comprising the following steps:
step 1, building a coal storage silo calculation model according to the structure size of an actual coal storage silo, gridding the coal storage silo calculation model, arranging temperature measuring points on the outermost layer nodes of the gridline areas, namely the inner wall of the coal storage silo, and acquiring the temperature value of each temperature measuring point through a temperature sensor on the temperature measuring point;
step 2, setting parameter boundary conditions for a coal storage silo calculation model, setting the coal storage silo calculation model to be steady-state, setting parameters of coal including density, specific heat and heat conductivity coefficient, setting a self-ignition point temperature range and the temperature of the peripheral wall surface of the coal storage silo, and setting position coordinates of temperature measuring points of the inner wall surface of the coal storage silo;
step 3, initializing the whole working condition of the coal storage silo calculation model, setting the maximum calculation step length, and starting calculation to obtain the node temperature of the inner layer of the grid line area of the coal storage silo calculation model;
step 4, after a calculation result is obtained, a three-layer BP neural training network taking the position coordinates and the temperature values of temperature measuring points on the inner wall surface of the coal storage silo as input and taking the coordinates and the temperature values of the self-ignition points as output is established, 90% of data in the node temperature of the inner layer of the obtained grid line area is taken as a training sample, the rest 10% of data is taken as a test sample, and the self-ignition points in the calculation model of the coal storage silo are predicted by utilizing the three-layer BP neural network, so that a prediction result of the self-ignition position is obtained;
and 5, applying the trained three-layer BP neural network to the interior of a coal storage silo of an actual power plant to predict the self-ignition point of the coal body.
2. The method for predicting the spontaneous combustion position of a coal body in a coal storage silo according to claim 1, wherein in step 1, the structural dimensions of the coal storage silo include silo radius, height, cone radius, cone bus length and cone angle.
3. The method for predicting the spontaneous combustion position of the coal body in the coal storage silo according to claim 1, wherein in the step 1, the specific method of gridding division is as follows: the method comprises the steps of dividing the inner wall of a coal storage silo into n layers of interfaces along the radial direction, dividing the inner wall of the coal storage silo into m layers of interfaces along the axial direction, forming grid lines on the interfaces in two directions, wherein the crossing points of the grid lines are nodes, respectively arranging temperature measuring points on the inner wall of the coal storage silo, namely the nodes on the outermost layer, and respectively measuring the temperature values of all the nodes on the temperature measuring points through temperature sensors.
4. The method for predicting the spontaneous combustion position of a coal body in a coal storage silo according to claim 3, wherein in the step 3, the specific method for calculating the node temperature of the inner layer of the grid line area is as follows: establishing an energy conservation equation for the control volume represented by the outermost layer node according to the heat conduction micro equation, and solving the temperature value of the penultimate layer node according to the measured temperature value of the outermost layer node and the energy conservation equation; establishing an energy conservation equation for the control volume represented by the penultimate layer node according to the heat conduction micro equation, and solving the temperature value of the penultimate layer node according to the temperature value of the penultimate layer node and the energy conservation equation; pushing the nodes layer by layer until the temperature value of the innermost node is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811409958.0A CN109492322B (en) | 2018-11-23 | 2018-11-23 | Prediction method for spontaneous combustion position of coal body in coal storage silo |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811409958.0A CN109492322B (en) | 2018-11-23 | 2018-11-23 | Prediction method for spontaneous combustion position of coal body in coal storage silo |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109492322A CN109492322A (en) | 2019-03-19 |
| CN109492322B true CN109492322B (en) | 2023-07-25 |
Family
ID=65696613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811409958.0A Active CN109492322B (en) | 2018-11-23 | 2018-11-23 | Prediction method for spontaneous combustion position of coal body in coal storage silo |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109492322B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027257B (en) * | 2019-11-19 | 2021-10-08 | 中国矿业大学 | Method for predicting safe storage time of pulverized coal covered coal pile by using neural network |
| CN113820211B (en) * | 2021-09-16 | 2024-01-30 | 马鞍山钢铁股份有限公司 | Method for measuring hardening period of coal under silo process condition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104089656A (en) * | 2014-07-17 | 2014-10-08 | 北京物资学院 | Storage yard coal spontaneous combustion detection method and device |
| CN107290068A (en) * | 2017-06-20 | 2017-10-24 | 华电电力科学研究院 | A kind of spontaneous combustion monitoring system and method for circular coal yard |
| CN108489546A (en) * | 2018-03-29 | 2018-09-04 | 大唐环境产业集团股份有限公司 | A kind of coal store monitoring system |
| CN108844651A (en) * | 2018-05-06 | 2018-11-20 | 北京工业大学 | A kind of ball storehouse temperature pre-warning method neural network based |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7839301B2 (en) * | 1995-06-08 | 2010-11-23 | Western Strategic Products, Llc | Surface condition sensing and treatment systems, and associated methods |
| US7524355B2 (en) * | 2003-11-24 | 2009-04-28 | New Jersey Institute Of Technology | Nano-composite energetic powders prepared by arrested reactive milling |
-
2018
- 2018-11-23 CN CN201811409958.0A patent/CN109492322B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104089656A (en) * | 2014-07-17 | 2014-10-08 | 北京物资学院 | Storage yard coal spontaneous combustion detection method and device |
| CN107290068A (en) * | 2017-06-20 | 2017-10-24 | 华电电力科学研究院 | A kind of spontaneous combustion monitoring system and method for circular coal yard |
| CN108489546A (en) * | 2018-03-29 | 2018-09-04 | 大唐环境产业集团股份有限公司 | A kind of coal store monitoring system |
| CN108844651A (en) * | 2018-05-06 | 2018-11-20 | 北京工业大学 | A kind of ball storehouse temperature pre-warning method neural network based |
Non-Patent Citations (2)
| Title |
|---|
| Intelligent management of coal stockpiles using improved grey spontaneous combustion forecasting models;GongzhuangPeng et al.;《Energy》;20170831;全文 * |
| 基于分布式光纤的煤仓火灾监测系统的研究;陈敏等;《物联网技术》;20140930;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109492322A (en) | 2019-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107491608B (en) | Formation parameter optimization method and system for airplane formation flight | |
| Baker et al. | Experimental analysis of thick blunt trailing-edge wind turbine airfoils | |
| CN109492322B (en) | Prediction method for spontaneous combustion position of coal body in coal storage silo | |
| Gomez-Iradi et al. | Development and validation of a CFD technique for the aerodynamic analysis of HAWT | |
| Heng et al. | Transient thermal prediction methodology for parabolic trough solar collector tube using artificial neural network | |
| Jeon et al. | Comparison and verification of wake models in an onshore wind farm considering single wake condition of the 2 MW wind turbine | |
| Krzywanski et al. | Modeling of heat transfer coefficient in the furnace of CFB boilers by artificial neural network approach | |
| Wang et al. | Data-driven CFD modeling of turbulent flows through complex structures | |
| CN112685965B (en) | Method and system for monitoring risk of transmission tower in typhoon | |
| CN103364170A (en) | Ground simulation predicting method and system for aeroelasticity stability | |
| CN105181744A (en) | Coal pile ignition period calculation method and coal yard spontaneous combustion preventing and monitoring system | |
| CN104049000B (en) | The gas-liquid phase content migrating complex network based on mode is measured and verification method | |
| CN110059389B (en) | Solar cross-season soil heat storage POD (POD) rapid prediction method | |
| Gao et al. | Artificial neural network model research on effects of cross-wind to performance parameters of wet cooling tower based on level Froude number | |
| CN107222169A (en) | A kind of photovoltaic array based on outlier detection is monitored and fault detection method in real time | |
| CN114861279A (en) | Method and system for testing temperature simulation consistency of hydraulic concrete structure | |
| CN114462336A (en) | Method for calculating average temperature of coolant of main pipeline of nuclear reactor | |
| CN113990539A (en) | Ultrasonic measurement reconstruction method for temperature distribution of coolant in hot section of nuclear reactor main pipeline | |
| Al Asmi et al. | Thermocline thermal storage modeling towards its predictive optimal management | |
| CN103472343A (en) | High voltage equipment state predicting method | |
| CN114326772B (en) | Multi-source uncertain spacecraft attitude control reliability integrated modeling evaluation method | |
| Zhang et al. | Temperature Prediction for Ultra-Low Temperature Measurement System Based on Improved Extreme Learning Machine Algorithm | |
| Abdol-Hamid et al. | DPW-6 Results Using FUN3D With Focus on k-kL-MEAH2015 Turbulence Model | |
| Kao et al. | Investigation of plenum-to-plenum heat transfer and gas dynamics under natural circulation in a scaled-down dual channel module mimicking prismatic VHTR core using CFD | |
| Kling et al. | Geofit: Experimental investigations and numerical validation of shallow spiral collectors as a bases for development of a design tool for geothermal retrofitting of existing buildings |
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 |