CN109492322A - A kind of coal storage silo inside coal body spontaneous combustion position predicting method - Google Patents
A kind of coal storage silo inside coal body spontaneous combustion position predicting method Download PDFInfo
- Publication number
- CN109492322A CN109492322A CN201811409958.0A CN201811409958A CN109492322A CN 109492322 A CN109492322 A CN 109492322A CN 201811409958 A CN201811409958 A CN 201811409958A CN 109492322 A CN109492322 A CN 109492322A
- Authority
- CN
- China
- Prior art keywords
- storage silo
- coal storage
- coal
- temperature
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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 coal body spontaneous combustion position predicting methods inside a kind of coal storage silo, comprising: establishes coal storage silo computation model, carries out gridding point；Parametric boundary condition is set；Entire operating condition is initialized, max calculation step-length is set, starts to calculate；After obtaining calculated result, it establishes using the position coordinates of coal storage silo inner wall temperature point and temperature value as input, using the coordinate of self-ignition point and temperature value as three layers of BP nerve training network of output, using in obtained grid lines area inner layer node temperature 90% data as training sample, the data of residue 10% obtain the prediction result of spontaneous combustion position as test sample；Three layers of BP neural network after training are applied to carry out coal body spontaneous combustion point prediction inside practical power plant's coal storage silo.Beneficial effects of the present invention: by neural network method, predicting coal storage silo coal position self-ignition point, and self-ignition point position can be found before temperature monitoring early warning, guarantees power plant's coal storage system safety operation.
Description
Technical field
The present invention relates to coal storage silo technical fields, in particular to coal body spontaneous combustion position inside a kind of coal storage silo
Prediction technique.
Background technique
In current coal-burning power plant, China tubular coal store using more and more extensive, but due to loose coal in tubular coal store
The accumulation of heat condition of body is good, and it is big to store heat, and is difficult to discharge, and causes high temperature range big, while in the low-temperature oxidation of coal, heat
Under the conditions of excessively waiting dieseling easily occurs for accumulation.Mainly coal temperature in silo is carried out in terms of preventing spontaneous combustion at present
Monitoring, however, some monitoring systems can only monitor in silo close to barrel coal temperature；In addition there is the arrangement inside silo more
Cable for measuring temperature, but significantly damaged with constantly having into coal, coal breakage to the cable, need irregular inspection more
It changes, is unfavorable for the application of Practical Project.Currently, easily causing the prediction in spontaneous combustion region for coal body in coal store, there are no essences
Quasi- effective method.
Summary of the invention
To solve the above problems, the purpose of the present invention is to provide coal body spontaneous combustion position prediction sides inside a kind of coal storage silo
Method predicts coal storage silo coal position self-ignition point, self-ignition point position can be found before temperature monitoring early warning, is conducive to shift to an earlier date
It takes measures to prevent the expansion in spontaneous combustion region, guarantees power plant's coal storage system safety operation.
The present invention provides coal body spontaneous combustion position predicting methods inside a kind of coal storage silo, comprising:
Step 1, coal storage silo computation model is established according to the structure size of actual coal storage silo, coal storage silo is calculated
Model carries out gridding point, and is that temperature point is arranged at coal storage silo inner wall on the outermost node layer in grid lines region, passes through
Temperature sensor on temperature point obtains the temperature value of each temperature point；
Step 2, parametric boundary condition is arranged to coal storage silo computation model；
Step 3, the entire operating condition of coal storage silo computation model is initialized, max calculation step-length is set, starts to count
It calculates, obtains the grid lines area inner layer node temperature of coal storage silo computation model；
Step 4, it after obtaining calculated result, establishes and is made with the position coordinates of coal storage silo inner wall temperature point and temperature value
Network, the grid lines region that will be obtained are trained as three layers of BP nerve of output for input, using the coordinate of self-ignition point and temperature value
90% data utilize three layers of BP mind as test sample as training sample, the data of residue 10% in underlay nodes temperature
The self-ignition point in coal storage silo computation model is predicted through network, obtains the prediction result of spontaneous combustion position；
Step 5, three layers of BP neural network after training are applied to carry out coal body spontaneous combustion inside practical power plant's coal storage silo
Point prediction.
It is further improved as of the invention, in step 1, the structure size of the coal storage silo includes silo radius, height
Degree, bevel radius, cone nut line length and coning angle.
It is further improved as of the invention, in step 1, gridding point method particularly includes: on coal storage silo inner wall edge
Radial direction is divided into n-layer interface, is divided into the bed boundary m along axial direction, and the interface in both direction forms grid lines, grid lines intersection
Point is node, is respectively arranged temperature point on i.e. outermost node at the coal storage silo inner wall, is distinguished by temperature sensor
Measure the temperature value of each node on temperature point.
It is further improved as of the invention, in step 2, sets stable state for coal storage silo model, the parameter of coal is set
Including density, specific heat and thermal coefficient, self-ignition point temperature range and coal storage silo surrounding wall surface temperature are set, coal storage silo is set
The temperature point position coordinate of inner wall.
It is further improved as of the invention, in step 3, calculates the specific method of grid lines area inner layer node temperature
Are as follows: energy conservation equation is established according to control volume of the thermally conductive differential difference equation to outermost layer node on behalf, and according to measuring most
The temperature value of outer node layer and these energy conservation equations solve the temperature value of node layer second from the bottom；According to thermally conductive micro- side
Journey establishes energy conservation equation to the control volume that node layer second from the bottom represents, and according to the temperature value of node layer second from the bottom
And these energy conservation equations solve the temperature value of node layer third from the bottom；It is pushed away in successively, until finding out innermost layer node
Temperature value.
The invention has the benefit that
By neural network method, coal storage silo coal position self-ignition point is predicted, can be looked for before temperature monitoring early warning
To self-ignition point position, be conducive to the expansion for taking measures to prevent spontaneous combustion region in advance, guarantee power plant's coal storage system safety operation.
Detailed description of the invention
Fig. 1 is a kind of process signal of coal storage silo inside coal body spontaneous combustion position predicting method described in the embodiment of the present invention
Figure.
Specific embodiment
The present invention is described in further detail below by specific embodiment and in conjunction with attached drawing.
As shown in Figure 1, a kind of coal storage silo inside coal body spontaneous combustion position predicting method described in the embodiment of the present invention, specifically
Include:
Step 1, according to the structure size of actual coal storage silo (including silo radius, height, bevel radius, cone nut wire length
Degree and coning angle) coal storage silo computation model is established, gridding point is carried out to coal storage silo computation model, and in grid lines area
It is to arrange temperature point at coal storage silo inner wall on the outermost node layer in domain, is obtained by the temperature sensor on temperature point each
The temperature value of temperature point.
Wherein, gridding divides method particularly includes: is radially divided into n-layer interface in coal storage silo inner wall, draws along axial
It is divided into the bed boundary m, the interface in both direction forms grid lines, and the point of grid lines intersection is node, at coal storage silo inner wall
It is respectively arranged temperature point on i.e. outermost node, measures the temperature of each node on temperature point respectively by temperature sensor
Angle value.
Step 2, parametric boundary condition is arranged to coal storage silo computation model.
Wherein, since the spontaneous combustion of coal in coal storage silo is an extremely very long process, and coal body can be approximately considered
For isotropic pure solid, therefore stable state is set by coal storage silo model, the parameter that coal is arranged includes density, specific heat and thermally conductive
Self-ignition point temperature range and coal storage silo surrounding wall surface temperature is arranged in coefficient, and the temperature point of coal storage silo inner wall is arranged
Position coordinates.
Step 3, the entire operating condition of coal storage silo computation model is initialized, max calculation step-length is set, starts to count
It calculates, obtains the grid lines area inner layer node temperature of coal storage silo computation model.
Wherein, grid lines area inner layer node temperature is calculated method particularly includes: according to thermally conductive differential difference equation to outermost layer section
The control volume that point represents establishes energy conservation equation, and according to the temperature value and these energy of the outermost node layer measured
Conservation equation solves the temperature value of node layer second from the bottom；The control that node layer second from the bottom is represented according to thermally conductive differential difference equation
Volume establishes energy conservation equation, and is solved down according to the temperature value of node layer second from the bottom and these energy conservation equations
The temperature value of number third node layer；It is pushed away in successively, until finding out the temperature value of innermost layer node.
Step 4, it after obtaining calculated result, establishes and is made with the position coordinates of coal storage silo inner wall temperature point and temperature value
Network, the grid lines that will be obtained are trained as three layers of BP nerve of output for input, using the position coordinates of self-ignition point and temperature value
90% data utilize three layers as test sample as training sample, the data of residue 10% in area inner layer node temperature
BP neural network predicts the self-ignition point in coal storage silo computation model, obtains the prediction result of spontaneous combustion position.
It is required to meet the training and prediction of three layers of BP neural network, self-ignition point position should cover entire coal storage silo area
Domain, overall data are greater than 100 groups.
Data format is as shown in the table:
Wherein, X, Y, Z indicate the position coordinates in coal storage silo (in three-dimensional space).
Based on neural network theory, neural metwork training is carried out to data with existing and uses reversed error in the training process
Propagate, multiple adjusting training, constantly diminution error, to approach desired value, save network weight and deviation, network training it is good it
Afterwards, implicit function number of nodes, learning rate, factor of momentum, the connection weight of a node and iteration frequency are obtained, it can be to unknown sample
This is that spontaneous combustion position is predicted.By carrying out numerical simulation to the coal storage silo containing self-ignition point, it is available for verifying BP
The data of neural network correctness.It finally can be by the Application of Neural Network in the practical coal-fired self-ignition point in power plant's coal storage silo inside
Prediction.
Specific network training process is as follows:
(1) neural network initializes, and assigns initial weight to neural network with one group of random number, training pace η is arranged, allows
Error e and network structure (i.e. network number of plies L and every node layer number n1)；
(2) one group of training sample (i.e. 90% data in grid lines area inner layer node temperature) are provided for neural network；
(3) each training sample p is recycled:
It is successively positive to calculate outputting and inputting for each node of neural network；
Calculate the error E p of the output of p-th of training sample and the overall error E of neural network；
When E is less than allowable error e or reaches specified the number of iterations, training process terminates, and otherwise, it is anti-to carry out error
To propagation；
It is reversed successively to calculate each node error of neural network
Correct the connection weight of neural network.
Step 5, three layers of BP neural network after training are applied to carry out coal body spontaneous combustion inside practical power plant's coal storage silo
Point prediction.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (5)
1. coal body spontaneous combustion position predicting method inside a kind of coal storage silo characterized by comprising
Step 1, coal storage silo computation model is established according to the structure size of actual coal storage silo, to coal storage silo computation model
Gridding point is carried out, and is to arrange temperature point at coal storage silo inner wall on the outermost node layer in grid lines region, passes through temperature
Temperature sensor on measuring point obtains the temperature value of each temperature point；
Step 2, parametric boundary condition is arranged to coal storage silo computation model；
Step 3, the entire operating condition of coal storage silo computation model is initialized, max calculation step-length is set, starts to calculate, obtain
To the grid lines area inner layer node temperature of coal storage silo computation model；
Step 4, it after obtaining calculated result, establishes using the position coordinates of coal storage silo inner wall temperature point and temperature value as defeated
Enter, using the coordinate of self-ignition point and temperature value as three layers of BP nerve training network of output, the grid lines area inner layer that will be obtained
90% data utilize three layers of BP nerve net as test sample as training sample, the data of residue 10% in node temperature
Network predicts the self-ignition point in coal storage silo computation model, obtains the prediction result of spontaneous combustion position；
Step 5, three layers of BP neural network after training are pre- applied to coal body self-ignition point is carried out inside practical power plant's coal storage silo
It surveys.
2. coal body spontaneous combustion position predicting method inside coal storage silo according to claim 1, which is characterized in that in step 1,
The structure size of the coal storage silo includes silo radius, height, bevel radius, cone nut line length and coning angle.
3. coal body spontaneous combustion position predicting method inside coal storage silo according to claim 1, which is characterized in that in step 1,
Gridding point method particularly includes: it is radially divided into n-layer interface in coal storage silo inner wall, is divided into the bed boundary m along axial direction, two
Interface on a direction forms grid lines, and the point of grid lines intersection is node, the i.e. outermost node at coal storage silo inner wall
On be respectively arranged temperature point, measure the temperature value of each node on temperature point respectively by temperature sensor.
4. coal body spontaneous combustion position predicting method inside coal storage silo according to claim 2, which is characterized in that in step 2,
Stable state is set by coal storage silo computation model, the parameter that coal is arranged includes density, specific heat and thermal coefficient, and self-ignition point temperature is arranged
Range and coal storage silo surrounding wall surface temperature are spent, the position coordinates of the temperature point of coal storage silo inner wall are set.
5. coal body spontaneous combustion position predicting method inside coal storage silo according to claim 3, which is characterized in that in step 3,
Calculate grid lines area inner layer node temperature method particularly includes: hold to the control of outermost layer node on behalf according to thermally conductive differential difference equation
Product establishes energy conservation equation, and is solved according to the temperature value and these energy conservation equations of the outermost node layer measured
The temperature value of node layer second from the bottom；Energy is established to the control volume that node layer second from the bottom represents according to thermally conductive differential difference equation to keep
Permanent equation, and node layer third from the bottom is solved according to the temperature value of node layer second from the bottom and these energy conservation equations
Temperature value；It is pushed away in successively, until finding out the temperature value of innermost layer node.
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 true CN109492322A (en) | 2019-03-19 |
| CN109492322B 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) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027257A (en) * | 2019-11-19 | 2020-04-17 | 中国矿业大学 | Method for predicting safe storage time of pulverized coal covered coal pile by using neural network |
| CN113820211A (en) * | 2021-09-16 | 2021-12-21 | 马鞍山钢铁股份有限公司 | Method for measuring coal hardening period under silo process condition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050246088A1 (en) * | 1995-06-08 | 2005-11-03 | Doherty John A | Surface condition sensing and treatment systems, and associated methods |
| US20060053970A1 (en) * | 2003-11-24 | 2006-03-16 | Dreizin Edward L | Nano-composite energetic powders prepared by arrested reactive milling |
| 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 |
-
2018
- 2018-11-23 CN CN201811409958.0A patent/CN109492322B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050246088A1 (en) * | 1995-06-08 | 2005-11-03 | Doherty John A | Surface condition sensing and treatment systems, and associated methods |
| US20060053970A1 (en) * | 2003-11-24 | 2006-03-16 | Dreizin Edward L | Nano-composite energetic powders prepared by arrested reactive milling |
| 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 |
|---|
| GONGZHUANGPENG ET AL.: "Intelligent management of coal stockpiles using improved grey spontaneous combustion forecasting models", 《ENERGY》 * |
| 陈敏等: "基于分布式光纤的煤仓火灾监测***的研究", 《物联网技术》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111027257A (en) * | 2019-11-19 | 2020-04-17 | 中国矿业大学 | Method for predicting safe storage time of pulverized coal covered coal pile by using neural network |
| 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 |
| CN113820211A (en) * | 2021-09-16 | 2021-12-21 | 马鞍山钢铁股份有限公司 | Method for measuring coal hardening period under silo process condition |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109492322B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110009037B (en) | Short-term engineering wind speed prediction method and system based on physical information coupling | |
| CN108805350A (en) | Search and rescue horizon prediction method based on multidimensional Monte Carlo theory | |
| CN109492322A (en) | A kind of coal storage silo inside coal body spontaneous combustion position predicting method | |
| KR101742537B1 (en) | Multi model operating system for improved tracking accuracy | |
| CN110489777A (en) | A kind of array hole electric spark ultrasonic Compound Machining flow field simulation method | |
| CN112733363B (en) | Simulation method for three-dimensional full-space plasma response in EAST tokamak | |
| CN105699849A (en) | Voltage sag estimation method based on quantum-behaved particle swarm optimization algorithm | |
| CN103631995A (en) | Method and system for simulating temperature field inside carriage | |
| Catarelli et al. | Automated terrain generation for precise atmospheric boundary layer simulation in the wind tunnel | |
| Vickers et al. | Formulation of the sea surface friction velocity in terms of the mean wind and bulk stability | |
| CN114647985A (en) | Training method of frontal crossing prediction model and frontal crossing prediction method | |
| Moreira et al. | Numerical study of the neutral atmospheric boundary layer over complex terrain | |
| CN107222169A (en) | A kind of photovoltaic array based on outlier detection is monitored and fault detection method in real time | |
| Fang et al. | Numerical and experimental study of the aerodynamic characteristics around two-dimensional terrain with different slope angles | |
| Dalpé et al. | Numerical study of fully developed turbulent flow within and above a dense forest | |
| Guo et al. | Numerical and wind tunnel simulation studies of the flow field and pollutant diffusion around a building under neutral and stable atmospheric stratifications | |
| CN105808845A (en) | Structural damage identification method based on glowworm group intelligent algorithm | |
| Iacovides et al. | Alternative strategies for modelling flow over in-line tube banks | |
| Thuburn | Vertical discretizations: some basic ideas | |
| Nandi | Effects of Blade Boundary Layer Transition and Daytime Atmospheric Turbulence on Wind Turbine Performance Analyzed with Blade-Resolved Simulation and Field Data | |
| Nemec et al. | Uncertainty Estimates for Sonic-Boom Pressure Signatures and Loudness Carpets | |
| Zhang et al. | A novel particle swarm neural network model to optimize aircraft fuel consumption | |
| Reda et al. | Towards developing an idealised city model with realistic aerodynamic features | |
| CN107145471B (en) | Calculation method for long-distance migration trajectory of airborne radionuclide | |
| Mahmoodilari | The effect of turbulent flow on wind turbine loading and performance |
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 |