CN112149912A - Coal mine working face mine pressure data prediction method based on reverse propagation neural network - Google Patents
Coal mine working face mine pressure data prediction method based on reverse propagation neural network Download PDFInfo
- Publication number
- CN112149912A CN112149912A CN202011062494.8A CN202011062494A CN112149912A CN 112149912 A CN112149912 A CN 112149912A CN 202011062494 A CN202011062494 A CN 202011062494A CN 112149912 A CN112149912 A CN 112149912A
- Authority
- CN
- China
- Prior art keywords
- working face
- mine
- neural network
- thickness
- propagation neural
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 54
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 title claims abstract description 23
- 230000008859 change Effects 0.000 claims abstract description 31
- 238000005065 mining Methods 0.000 claims abstract description 26
- 238000009933 burial Methods 0.000 claims abstract description 21
- 230000000737 periodic effect Effects 0.000 claims abstract description 14
- 238000003062 neural network model Methods 0.000 claims description 9
- 238000012549 training Methods 0.000 claims description 6
- 238000013473 artificial intelligence Methods 0.000 abstract description 7
- 238000005516 engineering process Methods 0.000 abstract description 7
- 238000004364 calculation method Methods 0.000 abstract description 5
- 230000006872 improvement Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
Images
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
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Agronomy & Crop Science (AREA)
- Primary Health Care (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a mine pressure data prediction method for a coal mine working face based on a reverse propagation neural network, which is characterized in that mine pressure data of any position of any working face can be predicted by the trained reverse propagation neural network according to requirements by utilizing periodic pressure steps and periodic pressure intensity parameters of mine pressure of a roof collected by a coal mine working face and a working face under mining and the burial depth, the change rate of the height of the burial depth, the thickness of a coal seam, the change rate of the thickness of the coal seam, the mining thickness, the inclination angle of the coal seam, the change rate of the inclination angle of the coal seam, the thickness of a direct roof, the basic thickness of the roof, the inclination length and the propulsion speed parameter of the corresponding position. Compared with the traditional mine pressure calculation, the method has the advantages of high prediction accuracy, simplicity, high efficiency and the like. Meanwhile, a new idea combined with an artificial intelligence technology is provided for the prediction of the mine pressure data of the working face.
Description
Technical Field
The invention belongs to the field of coal mine pressure, and particularly relates to a coal mine working face mine pressure data prediction method based on a reverse propagation neural network.
Background
The mine pressure and the display rule thereof are the core of the coal mining theory and are the central importance of coal mine research. When mine pressure research is carried out, analyzing and calculating the step distance and the pressure intensity of the roof plate of the working face are often the key points and the difficulty points of the research. In the existing theory, the elastic-plastic theory is mostly adopted to calculate the pressure of the top plate, but the error is often large. The working face top plate pressure step distance and pressure intensity are in nonlinear relation with mining factors, and an ideal functional relation is difficult to fit.
In recent years, artificial intelligence technology has been rapidly developed and applied. With the research and development of artificial intelligence technology becoming more mature, the application of the artificial intelligence technology to the field of coal mines is imminent. The basis of artificial intelligence technology is neural networks, and neural networks are well suited to handle non-linear problems. The neural network can realize the prediction of data through the training of a large amount of sample data, and is widely applied to the fields of pattern recognition, image recognition, natural language processing, real-time analysis tools, unmanned driving and the like at present.
Disclosure of Invention
In order to solve the practical problem that the working face roof pressure step distance and the pressure difference calculation error are large in the prior art, the invention aims to provide a coal mine working face mine pressure data prediction method based on a reverse propagation neural network.
In order to achieve the purpose, the invention adopts the following technical scheme:
a coal mine working face mine pressure data prediction method based on a reverse propagation neural network is characterized in that historical roof mine pressure data and mining technical data of corresponding positions, which are collected by a coal mine working face and a working face under mining, are trained in the reverse propagation neural network, and the trained reverse propagation neural network predicts the roof mine pressure data of any position of any working face according to requirements.
The invention further improves the method that the roof mine pressure historical data of the mined working face and the mining working face of the mine are collected, and the roof mine pressure historical data comprises 2 parameters of the periodic step distance of the incoming pressure and the periodic intensity of the incoming pressure.
The invention has the further improvement that 11 mining technical parameters including the burial depth, the burial depth elevation change rate, the coal seam thickness change rate, the mining thickness, the coal seam inclination angle change rate, the direct roof thickness, the basic roof thickness, the inclination length and the propulsion speed of the corresponding position of the working face are recorded while the roof mine pressure historical data are collected.
The invention is further improved in that 11 parameters of the depth of burial, the change rate of the height of burial, the thickness of the coal bed, the change rate of the thickness of the coal bed, the mining thickness, the inclination angle of the coal bed, the change rate of the inclination angle of the coal bed, the thickness of a direct roof, the thickness of a basic roof, the inclination length and the propulsion speed are used as input parameters of the reverse propagation neural network, and 2 parameters of the period pressure step and the period pressure intensity are used as output parameters of the reverse propagation neural network.
The further improvement of the invention is that the number of nodes of an input layer of the reverse propagation neural network model is 11, the number of nodes of an output layer is 2, and the number of the hidden layers is 1 for simplifying the network.
The further improvement of the invention is that the weight and the bias of the reverse propagation neural network model are randomly endowed with an initial value, the initial value of the weight is ensured to be less than 1, and then the training is repeated.
The method is further improved in that the trained reverse propagation neural network model predicts the roof pressure data of any position of any working face according to requirements, namely, the burial depth, the change rate of burial depth elevation, the coal seam thickness, the change rate of coal seam thickness, the mining thickness, the coal seam inclination angle, the change rate of coal seam inclination angle, the direct roof thickness, the basic roof thickness, the inclination length and the propulsion speed at the predicted position are input into the reverse propagation neural network, and then predicted values of the coming pressure step distance and the coming pressure strength of the coming period at the position can be output.
Compared with the prior art, the invention has at least the following beneficial technical effects:
in order to solve the practical problem that the working face top plate pressure step distance and the pressure intensity calculation error are large, the mine pressure data of the working face is predicted by adopting a reverse propagation neural network in an artificial intelligence technology.
The main advantages of the back-propagation neural network include: the method has a self-learning function, and the self-learning function is particularly significant to prediction; the function of associative memory is provided; the method has the capability of searching the optimal solution at a high speed, the optimal solution of a complex problem is searched, a large amount of calculation is usually needed, and the high-speed calculation capability of a computer can be exerted by utilizing a reverse propagation neural network, so that the optimal solution can be quickly found; the method has strong nonlinear fitting capability, can map any complex nonlinear relation, has simple learning rule and is convenient for computer realization.
The mine pressure data prediction of the working face by utilizing the reverse propagation neural network has the advantages of high prediction accuracy, simplicity, high efficiency and the like.
The invention utilizes 11 mining technical parameters of burial depth, burial depth elevation change rate, coal seam thickness variation rate, mining thickness, coal seam inclination angle variation rate, direct top thickness, basic top thickness, tendency length and propulsion speed as input parameters of a reverse propagation neural network, 2 parameters of periodic pressure step and periodic pressure intensity as output parameters of the reverse propagation neural network, establishes a nonlinear incidence relation between the 11 input parameters and the 2 output parameters, and provides a new idea combined with an artificial intelligence technology for the prediction of the mine pressure data of a working face.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
Detailed Description
It should be noted that the following description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
Examples
The embodiment discloses a coal mine working face mine pressure data prediction method based on a reverse propagation neural network, which specifically comprises the following steps:
the method comprises the following steps: the method comprises the steps of collecting roof mine pressure historical data of a mined working face of a certain coal mine and the mining working face in the mining process since mining, wherein the roof mine pressure historical data comprises 2 parameters including periodic incoming pressure step distance and periodic incoming pressure intensity, and the parameters are used as output parameters of a reverse propagation neural network.
Step two: when the historical data of the roof mine pressure is collected, 11 parameters including the burial depth, the change rate of burial depth elevation, the thickness of the coal seam, the change rate of thickness of the coal seam, the mining thickness, the inclination angle of the coal seam, the change rate of the inclination angle of the coal seam, the thickness of a direct roof, the basic roof thickness, the inclination length and the propulsion speed of the corresponding position of a working face are recorded at the same time and used as input parameters of a reverse propagation neural network.
Step three: and establishing a reverse propagation neural network model, wherein the number of nodes of an input layer is 11, the number of nodes of an output layer is 2, the number of nodes of a hidden layer is 1, and the number of nodes of the hidden layer is 15-22.
Step four: randomly selecting the number of hidden layer nodes of the neural network within the limited range of the step four; and randomly endowing weights and bias initial values among layers of the reverse propagation neural network model, but ensuring that the weight initial values are less than 1.
Step five: and (3) training and learning, namely establishing a back propagation neural network model between input parameters (burial depth, burial depth elevation change rate, coal seam thickness change rate, mining thickness, coal seam inclination angle change rate, direct top thickness, basic top thickness, inclination length and propulsion speed) and output parameters (periodic pressure step and periodic pressure intensity), reading in recorded input parameter samples, predicting output parameter values and storing.
Step six: and repeating the step six until the whole part of sample data is trained.
Step seven: and after the training is finished, the error precision of the reverse propagation neural network and the weight and the offset value between layers of the reverse propagation neural network are saved.
Step eight: inputting the burial depth, the change rate of the burial depth elevation, the thickness of the coal bed, the change rate of the thickness of the coal bed, the mining thickness, the inclination angle of the coal bed, the change rate of the inclination angle of the coal bed, the thickness of the direct roof, the basic roof thickness, the inclination length and the propulsion speed parameter values at the predicted position of the working face, and automatically predicting the periodic incoming pressure step distance and the periodic incoming pressure value of the position by the inverse propagation neural network according to the stored weight and offset value among the layers.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (7)
1. The method is characterized in that historical data of the mine pressure of the working face of the coal mine and mining technical data of corresponding positions collected by the working face of the coal mine and the working face under mining are used for training in the reverse propagation neural network, and the trained reverse propagation neural network predicts the mine pressure data of the roof at any position of any working face according to requirements.
2. The method for predicting the mine pressure data of the coal mine working face based on the inverse propagation neural network is characterized in that the mine pressure historical data of the top plate of the mined working face and the mining working face of the mine are collected, wherein the mine pressure historical data comprise 2 parameters of the periodic pressure step and the periodic pressure intensity.
3. The method for predicting the mine pressure data of the coal mine working face based on the back propagation neural network as claimed in claim 2, wherein 11 mining technical parameters including the burial depth, the change rate of the burial depth elevation, the coal seam thickness change rate, the mining thickness, the coal seam inclination angle change rate, the direct roof thickness, the basic roof thickness, the dip length and the propulsion speed of the corresponding position of the working face are recorded while the historical data of the mine pressure of the top plate is collected.
4. The method for predicting the mine pressure data of the coal mine working face based on the inverse propagation neural network as claimed in claim 3, wherein 11 parameters of the total of the burial depth, the burial depth elevation change rate, the coal seam thickness change rate, the mining thickness, the coal seam inclination angle change rate, the immediate roof thickness, the basic roof thickness, the dip length and the propulsion speed are used as input parameters of the inverse propagation neural network, and 2 parameters of the total of the period pressure step and the period pressure intensity are used as output parameters of the inverse propagation neural network.
5. The method for predicting the mine pressure data of the coal mine working face based on the reverse propagation neural network as claimed in claim 4, wherein the number of nodes of an input layer of the reverse propagation neural network model is 11, the number of nodes of an output layer is 2, and the number of hidden layers is 1 for simplifying the network.
6. The method for predicting the mine pressure data of the coal mine working face based on the inverse propagation neural network is characterized in that the weight and the bias of the inverse propagation neural network model are randomly endowed with initial values, the initial values of the weight are ensured to be less than 1, and then the training is repeated.
7. The method for predicting the mine pressure data of the coal mine working face based on the inverse propagation neural network as claimed in claim 6, wherein the trained inverse propagation neural network model predicts the mine pressure data of the roof at any position of any working face according to requirements, namely, the burial depth elevation change rate, the coal seam thickness change rate, the mining thickness, the coal seam inclination angle change rate, the direct roof thickness, the basic roof thickness, the trend length and the propulsion speed at the predicted position are input into the inverse propagation neural network, and then the predicted values of the period coming pressure step distance and the period coming pressure intensity at the position can be output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011062494.8A CN112149912A (en) | 2020-09-30 | 2020-09-30 | Coal mine working face mine pressure data prediction method based on reverse propagation neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011062494.8A CN112149912A (en) | 2020-09-30 | 2020-09-30 | Coal mine working face mine pressure data prediction method based on reverse propagation neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112149912A true CN112149912A (en) | 2020-12-29 |
Family
ID=73951651
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011062494.8A Pending CN112149912A (en) | 2020-09-30 | 2020-09-30 | Coal mine working face mine pressure data prediction method based on reverse propagation neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112149912A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113700475A (en) * | 2021-07-28 | 2021-11-26 | 中石化石油工程技术服务有限公司 | Micro-amplitude structure logging while-drilling identification method and device, storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102592171A (en) * | 2011-12-30 | 2012-07-18 | 南京邮电大学 | Method and device for predicting cognitive network performance based on BP (Back Propagation) neural network |
| CN105260575A (en) * | 2015-11-17 | 2016-01-20 | 中国矿业大学 | Roadway surrounding rock deformation predicting method based on neural network |
| EP3620983A1 (en) * | 2018-09-05 | 2020-03-11 | Sartorius Stedim Data Analytics AB | Computer-implemented method, computer program product and system for data analysis |
-
2020
- 2020-09-30 CN CN202011062494.8A patent/CN112149912A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102592171A (en) * | 2011-12-30 | 2012-07-18 | 南京邮电大学 | Method and device for predicting cognitive network performance based on BP (Back Propagation) neural network |
| CN105260575A (en) * | 2015-11-17 | 2016-01-20 | 中国矿业大学 | Roadway surrounding rock deformation predicting method based on neural network |
| EP3620983A1 (en) * | 2018-09-05 | 2020-03-11 | Sartorius Stedim Data Analytics AB | Computer-implemented method, computer program product and system for data analysis |
Non-Patent Citations (5)
| Title |
|---|
| YAQIN WU .ETAL: "Prediction of coal and gas outburst: A method based on the BP neural network optimized by GASA", PROCESS SAFETY AND ENVIRONMENTAL PROTECTION, vol. 133, pages 64 - 72, XP085975831, DOI: 10.1016/j.psep.2019.10.002 * |
| 周廷扬;赵晓东;: "汝箕沟煤矿山地浅埋煤层矿压特征及上覆岩层运动规律研究", 西北煤炭, vol. 6, no. 3, pages 7 - 9 * |
| 姚建国,杜忠孝,郭藩强: "顶板来压预测预报的智能化方法(二)", 煤, vol. 6, no. 4, pages 14 - 16 * |
| 常峰: "基于GA-BP神经网络的工作面顶板矿压预测模型应用研究", 中国优秀硕士学位论文全文数据库 (工程科技Ⅰ辑), no. 9, pages 33 - 38 * |
| 郭文兵 等: "条带开采的非线性理论研究及应用", 中国矿业大学出版社, pages: 198 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113700475A (en) * | 2021-07-28 | 2021-11-26 | 中石化石油工程技术服务有限公司 | Micro-amplitude structure logging while-drilling identification method and device, storage medium and electronic equipment |
| CN113700475B (en) * | 2021-07-28 | 2024-06-07 | 中石化石油工程技术服务有限公司 | Method and device for identifying logging while drilling of micro-structure well, storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103984788B (en) | A kind of coal entry anchor rod support automated intelligent design and optimization system | |
| CN106096729A (en) | A kind of towards the depth-size strategy learning method of complex task in extensive environment | |
| CN109933577A (en) | Prediction technique and system can be tunneled based on TBM rock-machine dynamic state of parameters interaction mechanism tunnel | |
| CN114329810B (en) | Real-time prediction method for working posture of shield tunneling machine based on big data | |
| CN106952193A (en) | A kind of criminal case aid decision-making method based on fuzzy depth belief network | |
| CN103617147A (en) | Method for identifying mine water-inrush source | |
| CN111144281B (en) | Urban rail transit OD passenger flow estimation method based on machine learning | |
| CN108595803A (en) | Shale gas well liquid loading pressure prediction method based on recurrent neural network | |
| CN112879024A (en) | Dynamic prediction method, system and equipment for shield attitude | |
| CN112149912A (en) | Coal mine working face mine pressure data prediction method based on reverse propagation neural network | |
| CN112149255A (en) | Coal face hydraulic support working resistance prediction method based on LSTM neural network | |
| CN116384554A (en) | Method and device for predicting mechanical drilling speed, electronic equipment and computer storage medium | |
| CN112270123A (en) | Basin reservoir group runoff random generation method based on convolution generation countermeasure network | |
| CN111160490A (en) | Deep learning dangerous rock deformation prediction method and device based on multiple time sequences | |
| CN111946258B (en) | GRU-based sliding orientation intelligent control method | |
| CN113887049A (en) | Drilling speed prediction method and system for petroleum drilling based on machine learning | |
| CN109085751B (en) | Hexapod robot navigation method based on multi-granularity reinforcement learning | |
| CN105260556A (en) | Bridge crane modeling method adopting hairpin mutation operation RNA genetic algorithm | |
| CN117404099B (en) | TBM tunneling speed intelligent control method based on XGBoost algorithm | |
| CN117348500B (en) | Automatic control method and system for fully-mechanized coal mining face | |
| CN116089818B (en) | Workpiece surface roughness prediction method, system and product in machining process | |
| Wang et al. | A novel drilling rate of penetration (ROP) prediction method using data pre-processing techniques and TS fuzzy inference | |
| CN117932407A (en) | Lithology recognition prediction method based on Stacking algorithm | |
| Yu et al. | Application of artificial intelligence in coal mine ultra-deep roadway engineering—a review | |
| Zhang et al. | Real-time Rate of Penetration Prediction within Drill Work |
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 |