CN111967745B - Fully-mechanized coal mining and caving time intelligent determination method based on BP neural network and probability statistics - Google Patents
Fully-mechanized coal mining and caving time intelligent determination method based on BP neural network and probability statistics Download PDFInfo
- Publication number
- CN111967745B CN111967745B CN202010780427.3A CN202010780427A CN111967745B CN 111967745 B CN111967745 B CN 111967745B CN 202010780427 A CN202010780427 A CN 202010780427A CN 111967745 B CN111967745 B CN 111967745B
- Authority
- CN
- China
- Prior art keywords
- neural network
- value
- coal
- caving
- fully
- 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
- 239000003245 coal Substances 0.000 title claims abstract description 92
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 68
- 238000005065 mining Methods 0.000 title claims abstract description 36
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012549 training Methods 0.000 claims abstract description 19
- 239000010410 layer Substances 0.000 claims description 10
- 210000002569 neuron Anatomy 0.000 claims description 9
- 239000002356 single layer Substances 0.000 claims description 8
- 238000007599 discharging Methods 0.000 abstract description 5
- 238000007619 statistical method Methods 0.000 abstract description 5
- 238000011156 evaluation Methods 0.000 description 5
- 238000007418 data mining Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000005312 nonlinear dynamic Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- 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
- 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
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an intelligent fully-mechanized coal mining and caving time determining method based on BP neural network and probability statistics, relates to the technical field of mining engineering, and solves the technical problem of low accuracy of manual coal caving. The method comprises the following steps: extracting the bearing pressure and position characteristic index parameters of the hydraulic support before top coal is discharged; and taking the obtained index parameters as BP neural network input indexes, taking the corresponding fully mechanized coal caving time as an output value, training data by adopting BP neural network algorithm, establishing a mathematical relation model of each index-coal caving time, and predicting the coal caving time according to the model. Randomly giving initial parameters of the BP neural network, and repeating training to obtain a large number of predicted values with the same input; a large number of predicted values obtained by statistical analysis by adopting a probability statistical method are used for determining the interval where the maximum probability is; giving a final predicted value based on the interval where the median, average and maximum probability of a large number of predicted values are located; the method realizes the intelligent decision of the coal discharging time.
Description
Technical Field
The invention relates to the technical field of mining engineering, in particular to an intelligent fully-mechanized coal mining and caving time determining method based on BP neural network and probability statistics.
Background
The intelligent decision is a key development direction of intelligent mining, decision problems of coal mining have high nonlinearity, complexity and ambiguity, a common algorithm is often difficult to compete, a BP neural network algorithm (Back Propagation Neural Network) has strong nonlinear dynamic processing capacity, characteristics can be extracted from sample data through mapping of the high nonlinearity without knowing the relation between input and output, and an implicit nonlinear corresponding relation between the input and the output is established so as to predict unknown parameters through known samples, so that intelligent decision of the parameters is realized.
At present, the top coal caving working face mainly takes manual operation, including the top coal caving time is controlled by workers through experience, the efficiency is low, the danger is high, but due to the particularity of coal mining and the complexity of underground geological environment, the number of samples used for training in BP neural network decision-making is often smaller, the commonality difference is larger, the ideal effect can be achieved only by manually selecting proper neural network layers and neuron numbers, the degree of manual intervention is higher, the effective autonomy is lacking, and the realization of the intelligent prediction of fewer people and no people is a great difficulty, so that the existing comprehensive coal caving time determining method needs to be further improved.
Disclosure of Invention
The invention provides an intelligent fully-mechanized coal mining and caving time determining method based on BP neural network and probability statistics, which aims to solve the technical problems of low accuracy of manual coal caving, small number of training samples of the neural network and large variability.
A fully-mechanized coal mining and caving time intelligent determination method based on BP neural network and probability statistics comprises the following steps:
step A, extracting the pressure born by a hydraulic support and the characteristic index parameters of the position state before the top coal of the working face is discharged;
step B, taking the obtained parameters as BP neural network input indexes and corresponding fully-mechanized coal mining and caving time as output values, training data by adopting BP neural network algorithm, establishing mathematical relation models of indexes and caving time, and predicting the fully-mechanized coal mining and caving time;
step C, randomly giving initial parameters of the BP neural network, and repeatedly training the BP neural network to obtain a large number of predicted values with the same input;
step D, adopting a probability statistics method to statistically analyze the plurality of predicted values, and determining the interval where the maximum probability is located;
and E, giving a final predicted value according to the median value, the average value and the interval of the maximum probability of the plurality of predicted values.
Preferably, the BP neural network is an improved BP neural network based on a probability statistical method, and after training data by adopting a BP neural network algorithm, the accuracy of an output value is verified by using measured data.
Preferably, the bit characteristic index parameters comprise front post pressure before coal discharge, front post pressure after coal discharge, inclination angle of top beam before coal discharge and shield Liang Qingjiao before coal discharge.
Preferably, the measured data comprises measured top coal pre-discharge hydraulic support bearing pressure, measured pre-discharge front column pressure, measured pre-discharge back column pressure, measured pre-discharge top beam inclination angle, measured pre-discharge shield Liang Qingjiao and measured fully-mechanized coal mining and discharge time.
It is also preferable that the BP neural network initial parameters include a value range of the number of layers of the neural network and the number of single-layer neurons, and the number of layers of the neural network and the number of single-layer neurons are randomly selected in the value range; the threshold value and the initial error value of the BP neural network are set to be random values; and repeatedly training the BP neural network M times, wherein M is an integer greater than 10000, so as to obtain a large number of predicted values.
Further preferably, in step D, N is equally divided into intervals where the plurality of predicted values are located, where N is a natural number greater than 3, and the proportion of each intra-interval predicted value to the total amount is counted.
It is further preferred that in step E, when only the median value is within the maximum probability interval, the median value is taken as the final predicted value; when only the average value is in the maximum probability interval, taking the average value as the final predicted value; when the median and the average are both in the maximum probability interval, taking the mean of the median and the average as the final predicted value; and when the middle value and the average value are both outside the maximum probability interval, taking the middle value of the maximum probability interval as the final predicted value.
The fully-mechanized coal mining and caving time intelligent determination method based on BP neural network and probability statistics has the beneficial effects that: the method has the advantages that the data predicted by the BP neural network are deeply mined based on a statistical method, the manual intervention degree is low, the evaluation information is rich, the result accuracy is high, and the method is simple, efficient, convenient and quick; in addition, by extracting the pressure and position characteristic evaluation indexes of the hydraulic support before coal discharge, the state before coal discharge of the hydraulic support and the fully-mechanized coal mining and discharging time are established in a corresponding relation, and the coal discharging time is intelligently decided before coal discharge, so that convenience is provided for intelligent mining and automatic coal discharge; when the neural network is used for training, the initial parameters are randomly selected, so that the influence of manual selection of the initial parameters on a prediction result is reduced, and the automation level of decision making is effectively improved; by adopting a probability statistics method, data mining is carried out in a large number of predicted values, and the accuracy of prediction is effectively improved.
Drawings
FIG. 1 is a flow chart of an intelligent fully-mechanized coal mining and caving time determining method based on BP neural network and probability statistics;
fig. 2 is a histogram of probability distribution of a number of predictors.
Detailed Description
Detailed description is given to a specific embodiment of the fully-mechanized coal mining and caving time intelligent determination method based on BP neural network and probability statistics, which is provided by the invention, by referring to figures 1 and 2.
Example 1
The intelligent fully-mechanized coal mining and caving time determining method based on BP neural network and probability statistics is characterized in that the method is based on statistics method to deeply mine the data predicted by BP neural network, the manual intervention degree of the method is low, the evaluation information is rich, the result accuracy is high, the method is simple and efficient, and the method is convenient and quick, and comprises the following specific steps:
and A, extracting the pressure born by the hydraulic support and the characteristic index parameters of the position state before the top coal of the working face is discharged. The bit characteristic index parameters comprise front column pressure before coal discharge, front column pressure after coal discharge, front top beam inclination angle before coal discharge and shield Liang Qingjiao before coal discharge, and all the parameters can be extracted through on-site actual measurement records. By extracting the pressure and position characteristic evaluation indexes of the hydraulic support before coal discharge, the corresponding relation between the state before coal discharge and the fully-mechanized coal discharge time of the hydraulic support is established, and the coal discharge time is intelligently decided before coal discharge, so that convenience is provided for intelligent mining and automatic coal discharge.
And B, taking the obtained parameters as BP neural network input indexes and the corresponding fully mechanized coal mining and caving time as output values, training the data by adopting BP neural network algorithm, establishing mathematical relation models of indexes and caving time, and predicting the fully mechanized coal mining and caving time. The BP neural network is an improved BP neural network based on a probability statistical method, and after training data by adopting a BP neural network algorithm, the accuracy of an output value can be verified by using measured data.
And C, randomly giving initial parameters of the BP neural network, and repeatedly training the BP neural network to obtain a large number of predicted values with the same input.
The BP neural network initial parameters comprise a value range of the number of layers of the neural network and the number of single-layer neurons, and the number of the layers of the neural network and the number of the single-layer neurons are randomly selected in the value range; setting a threshold value and an error initial value of the BP neural network as random values; and repeating training the BP neural network M times, wherein M is an integer greater than 10000, so as to obtain a large number of predicted values. When the neural network is trained, the initial parameters are randomly selected, so that the influence of manual selection of the initial parameters on a prediction result is reduced, and the automation level of decision making is effectively improved
And D, adopting a probability statistics method to statistically analyze the plurality of predicted values, and determining the interval where the maximum probability is located.
N equally dividing the interval where a large number of predicted values are located to obtain a probability distribution histogram, wherein N is a natural number greater than 3, and counting the proportion of the predicted values in each interval to the total amount.
And E, giving a final predicted value according to the median value, the average value and the interval of the maximum probability of the plurality of predicted values. And the probability statistics method is adopted to conduct data mining in a large number of predicted values, so that the accuracy of prediction is effectively improved.
Specifically, when only the median value is within the maximum probability interval, the median value is taken as the final predicted value; when only the average value is in the maximum probability interval, taking the average value as the final predicted value; when the median and the average are both in the maximum probability interval, taking the mean of the median and the average as the final predicted value; and when the middle value and the average value are both outside the maximum probability interval, taking the middle value of the maximum probability interval as the final predicted value.
The steps of the method can be realized through computer programming, the pressure and position characteristic evaluation indexes of the hydraulic support before coal discharge are extracted, the state before coal discharge of the hydraulic support and the fully-mechanized coal mining and discharging time are established in a corresponding relation, the coal discharging time is intelligently decided before coal discharge, a new idea is provided for intelligent mining and automatic coal discharge, and the intelligent coal mining is facilitated.
Example 2
Based on the embodiment 1, the intelligent fully-mechanized coal mining and caving time determining method based on the BP neural network and probability statistics is described through specific application.
And step one, collecting the front coal caving pressure and position characteristic parameters of 14 hydraulic supports of the fully mechanized mining face, wherein the parameters comprise front coal caving column pressure, rear coal caving column pressure, front coal caving top beam inclination angle, front coal caving shield Liang Qingjiao and corresponding coal caving time.
And step two, taking the front column pressure (MPa) before coal discharge, the front and rear column pressure (MPa) before coal discharge, the inclination angle (degree) of the front top beam before coal discharge and the shield Liang Qingjiao (degree) before coal discharge as input parameters, and taking the corresponding coal discharge time as output parameters to serve as input and output vectors of the BP neural network.
And thirdly, considering that four input parameters and one output parameter are adopted, limiting the layer number range of the BP neural network to be between 2 and 10 layers, and limiting the neuron number of the single-layer neural network to be between 2 and 20.
Step four, randomly selecting the number of layers of the neural network and the number of single-layer neurons within the limited range; the threshold value and the error value are randomly initialized; the model training target error is set to be 10 < -5 >.
And fifthly, training and learning, establishing a neural network model of the corresponding relation between the hydraulic support pressure before coal discharge and the bit characteristic index and the coal discharge time, inputting the hydraulic support pressure before coal discharge and the bit characteristic index to be predicted, predicting the coal discharge time and storing.
Step six, repeatedly executing the step four and the step five 10000 times to obtain 10000 times of random initial prediction results, and counting probability distribution of the random initial prediction results, as shown in figure 2.
And seventhly, calculating a median value of 10000 times of prediction results as 8.6184s, an average value as 8.6702s, and if the median value and the average value are both in a range of 8.25-8.75s with highest probability, finally predicting the coal release time as the average value of the median value and the average value as 8.64s.
It should be understood that the above description is not intended to limit the invention to the particular embodiments disclosed, but to limit the invention to the particular embodiments disclosed, and that the invention is not limited to the particular embodiments disclosed, but is intended to cover modifications, adaptations, additions and alternatives falling within the spirit and scope of the invention.
Claims (5)
1. The intelligent fully-mechanized coal mining and caving time determining method based on BP neural network and probability statistics is characterized by comprising the following steps:
step A, extracting bearing pressure and position characteristic index parameters of a hydraulic support before top coal discharge of a working face, wherein the position characteristic index parameters comprise front column pressure before coal discharge, front column pressure after coal discharge, top beam inclination angle before coal discharge and shield Liang Qingjiao before coal discharge;
step B, taking the obtained parameters as BP neural network input indexes and corresponding fully-mechanized coal mining and caving time as output values, training data by adopting BP neural network algorithm, establishing mathematical relation models of indexes and caving time, and predicting the fully-mechanized coal mining and caving time;
step C, randomly giving initial parameters of the BP neural network, and repeatedly training the BP neural network to obtain a large number of predicted values with the same input;
step D, adopting a probability statistics method to statistically analyze the plurality of predicted values, and determining the interval where the maximum probability is located;
step E, giving a final predicted value according to the median value, the average value and the interval of the maximum probability of the plurality of predicted values, and taking the median value as the final predicted value when only the median value is in the interval of the maximum probability; when only the average value is in the maximum probability interval, taking the average value as the final predicted value; when the median and the average are both in the maximum probability interval, taking the mean of the median and the average as the final predicted value; and when the middle value and the average value are both outside the maximum probability interval, taking the middle value of the maximum probability interval as the final predicted value.
2. The fully-mechanized coal mining and caving time intelligent determination method based on the BP neural network and probability statistics according to claim 1, wherein the BP neural network is an improved BP neural network based on a probability statistics method, and after training data by adopting a BP neural network algorithm, the accuracy of an output value is verified by using measured data.
3. The intelligent fully-mechanized coal mining and caving time determination method based on the BP neural network and probability statistics according to claim 2, wherein the measured data comprises measured hydraulic support bearing pressure before top coal caving, measured front column pressure before coal caving, measured front and rear column pressure before coal caving, measured top beam dip angle before coal caving, measured pre-coal caving shield Liang Qingjiao and measured fully-mechanized coal mining and caving time.
4. The intelligent fully-mechanized coal mining and caving time determining method based on BP neural network and probability statistics according to claim 1, wherein the BP neural network initial parameters comprise a value range of the number of layers of the neural network and the number of single-layer neurons, and the number of layers of the neural network and the number of single-layer neurons are randomly selected in the value range; the threshold value and the initial error value of the BP neural network are set to be random values; and repeatedly training the BP neural network M times, wherein M is an integer greater than 10000, so as to obtain a large number of predicted values.
5. The intelligent fully-mechanized coal mining and caving time determining method based on BP neural network and probability statistics according to claim 1, wherein in the step D, N equally dividing the interval where the plurality of predicted values are located, wherein N is a natural number greater than 3, and the proportion of the predicted values in each interval to the total amount is counted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010780427.3A CN111967745B (en) | 2020-08-06 | 2020-08-06 | Fully-mechanized coal mining and caving time intelligent determination method based on BP neural network and probability statistics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010780427.3A CN111967745B (en) | 2020-08-06 | 2020-08-06 | Fully-mechanized coal mining and caving time intelligent determination method based on BP neural network and probability statistics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111967745A CN111967745A (en) | 2020-11-20 |
| CN111967745B true CN111967745B (en) | 2023-10-24 |
Family
ID=73364661
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010780427.3A Active CN111967745B (en) | 2020-08-06 | 2020-08-06 | Fully-mechanized coal mining and caving time intelligent determination method based on BP neural network and probability statistics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111967745B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112465063B (en) * | 2020-12-11 | 2023-05-23 | 中国矿业大学 | Coal gangue identification method in top coal caving process based on multi-sensing information fusion |
| CN116202574B (en) * | 2023-04-28 | 2023-07-18 | 太原理工大学 | Evaluation method for working state of hydraulic support |
| CN117743988B (en) * | 2024-02-20 | 2024-04-19 | 太原理工大学 | Instant prediction method for pressure-bearing state of hydraulic support after initial support |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544273A (en) * | 2013-10-21 | 2014-01-29 | 武汉钢铁(集团)公司 | Method for assessing integral states of furnace conditions by aid of pattern recognition technology |
| CN104700153A (en) * | 2014-12-05 | 2015-06-10 | 江南大学 | PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization |
| CN104732300A (en) * | 2015-04-07 | 2015-06-24 | 北京国能日新***控制技术有限公司 | Neural network wind power short-term forecasting method based on fuzzy partition theory |
| CN106443619A (en) * | 2016-09-09 | 2017-02-22 | 北京航空航天大学 | Background extraction method based on combined processing of maximum probability threshold and model prediction for target RCS measurement |
| CN108229721A (en) * | 2017-12-04 | 2018-06-29 | 西北大学 | The Forecasting Methodology of pyrolysis of coal product based on Speed Controlling Based on Improving BP Neural Network |
| CN108846527A (en) * | 2018-08-27 | 2018-11-20 | 云南电网有限责任公司电力科学研究院 | A kind of photovoltaic power generation power prediction method |
| EP3474189A1 (en) * | 2017-10-18 | 2019-04-24 | Aptiv Technologies Limited | A device and a method for assigning labels of a plurality of predetermined classes to pixels of an image |
| CN109856631A (en) * | 2019-02-27 | 2019-06-07 | 中国矿业大学 | Coal method is put in a kind of intelligence based on top coal amounts of thickness variation real-time monitoring |
| CN110363344A (en) * | 2019-07-11 | 2019-10-22 | 安徽理工大学 | Probability integral parameter prediction method based on MIV-GP algorithm optimization BP neural network |
-
2020
- 2020-08-06 CN CN202010780427.3A patent/CN111967745B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103544273A (en) * | 2013-10-21 | 2014-01-29 | 武汉钢铁(集团)公司 | Method for assessing integral states of furnace conditions by aid of pattern recognition technology |
| CN104700153A (en) * | 2014-12-05 | 2015-06-10 | 江南大学 | PH (potential of hydrogen) value predicting method of BP (back propagation) neutral network based on simulated annealing optimization |
| CN104732300A (en) * | 2015-04-07 | 2015-06-24 | 北京国能日新***控制技术有限公司 | Neural network wind power short-term forecasting method based on fuzzy partition theory |
| CN106443619A (en) * | 2016-09-09 | 2017-02-22 | 北京航空航天大学 | Background extraction method based on combined processing of maximum probability threshold and model prediction for target RCS measurement |
| EP3474189A1 (en) * | 2017-10-18 | 2019-04-24 | Aptiv Technologies Limited | A device and a method for assigning labels of a plurality of predetermined classes to pixels of an image |
| CN108229721A (en) * | 2017-12-04 | 2018-06-29 | 西北大学 | The Forecasting Methodology of pyrolysis of coal product based on Speed Controlling Based on Improving BP Neural Network |
| CN108846527A (en) * | 2018-08-27 | 2018-11-20 | 云南电网有限责任公司电力科学研究院 | A kind of photovoltaic power generation power prediction method |
| CN109856631A (en) * | 2019-02-27 | 2019-06-07 | 中国矿业大学 | Coal method is put in a kind of intelligence based on top coal amounts of thickness variation real-time monitoring |
| CN110363344A (en) * | 2019-07-11 | 2019-10-22 | 安徽理工大学 | Probability integral parameter prediction method based on MIV-GP algorithm optimization BP neural network |
Non-Patent Citations (2)
| Title |
|---|
| Adaptive Statistic Tracking Control Based on Two-Step Neural Networks With Time Delays;Yang Yi 等;《IEEE TRANSACTIONS ON NEURAL NETWORKS》;第20卷(第3期);420-429 * |
| 基于概率统计与神经网络相结合的绝缘子盐密预测;周龙武 等;《水电能源科学》;第33卷(第12期);172-175 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111967745A (en) | 2020-11-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111967745B (en) | Fully-mechanized coal mining and caving time intelligent determination method based on BP neural network and probability statistics | |
| CN111860952B (en) | Method for rapidly optimizing key mining parameters of outburst coal seam | |
| US11989655B2 (en) | Prediction method, device and system for rock mass instability stages | |
| CN104850901B (en) | A kind of flexible measurement method and system based on multi-model prediction gas density | |
| US7292960B1 (en) | Method for characterization, detection and prediction for target events | |
| CN103617147A (en) | Method for identifying mine water-inrush source | |
| CN106503792B (en) | A kind of gas density prediction technique based on adaptation module neural network | |
| CN103984788B (en) | A kind of coal entry anchor rod support automated intelligent design and optimization system | |
| CN112761628B (en) | Shale gas yield determination method and device based on long-term and short-term memory neural network | |
| CN112862069B (en) | Landslide Displacement Prediction Method Based on SVR-LSTM Hybrid Deep Learning | |
| CN109934398A (en) | A kind of drill bursting construction tunnel gas danger classes prediction technique and device | |
| CN103473786A (en) | Gray level image segmentation method based on multi-objective fuzzy clustering | |
| CN107122860A (en) | Bump danger classes Forecasting Methodology based on grid search and extreme learning machine | |
| CN112100927A (en) | Prediction method for slope deformation and soft soil foundation settlement based on GA-BP neural network | |
| Schirmer et al. | Statistical forecasting of regional avalanche danger using simulated snow-cover data | |
| CN114036841A (en) | Landslide incidence prediction method and system based on semi-supervised support vector machine model | |
| CN106650446A (en) | Identification method and system of malicious program behavior, based on system call | |
| CN108280289A (en) | Bump danger classes prediction technique based on local weighted C4.5 algorithms | |
| CN114548482A (en) | Creep type landslide kinetic energy change rate face-slip early warning method | |
| CN115438823A (en) | Borehole wall instability mechanism analysis and prediction method and system | |
| Xue et al. | PREDICTION OF SLOPE STABILITY BASED ON GA-BP HYBRID ALGORITHM. | |
| CN114676550A (en) | Slope stability evaluation method | |
| CN117786794A (en) | Shield tunneling existing tunnel deformation optimization control method and system | |
| CN117540303A (en) | Landslide susceptibility assessment method and system based on cross semi-supervised machine learning algorithm | |
| KR20190114450A (en) | Method for optimization of multi-well placement of oil or gas reservoirs using artificial neural networks |
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 |