Research on prediction for coal and gas outburst based on Matlab neural network toolbox and its application

In order to predict the danger of coal and gas outburst in mine coal layer correctly, on the basis of the VLBP and LMBP algorithm in Matlab neural network toolbox, one kind of modified BP neural network was put forth to speed up the network convergence speed in this paper. Firstly, according to the characteristics of coal and gas outburst, five key influencing factors such as excavation depth, pressure of gas, and geologic destroy degree were selected as the judging indexes of coal and gas outburst. Secondly, the prediction model for coal and gas outburst was built. Finally, it was verified by practical examples. Practical application demonstrates that, on the one hand, the modified BP prediction model based on the Matlab neural network toolbox can overcome the disadvantages of constringency and, on the other hand, it has fast convergence speed and good prediction accuracy. The analysis and computing results show that the computing speed by LMBP algorithm is faster than by VLBP algorithm but needs more memory. And the resuits show that the prediction results are identical with actual results and this model is a very efficient prediction method for mine coal and gas outburst, and has an important practical meaning for the mine production safety. So we conclude that it can be used to predict coal and gas outburst precisely in actual engineering.

Prediction of oxygen concentration and temperature distribution in loose coal based on BP neural network

An effective method for preventing spontaneous combustion of coal stockpiles on the ground is to control the air-flow in loose coal. In order to determine and predict accurately oxygen concentrations and temperatures within coal stockpiles, it is vital to obtain information of self-heating conditions and tendencies of spontaneous coal combustion. For laboratory conditions, we designed our own experimental equipment composed of a control-heating system, a coal column and an oxygen concentration and temperature monitoring system, for simulation of spontaneous combustion of block coal （13-25 mm） covered with fine coal （0-3 mm）. A BP artificial neural network （ANN） with 150 training samples was gradually established over the course of our experiment. Heating time, relative position of measuring points, the ratio of fine coal thickness, artificial density, voidage and activation energy were selected as input variables and oxygen concentration and temperature of coal column as output variables. Then our trained network was applied to predict the trend on the untried experimental data. The results show that the oxygen concentration in the coal column could be reduced below the minimum still able to induce spontaneous combustion of coal - 6% by covering the coal pile with fine coal, which would meet the requirement to prevent spontaneous combustion of coal stockpiles. Based on the prediction of this ANN, the average errors of oxygen concentration and temperature were respectively 0.5% and 7 ℃, which meet actual tolerances. The implementation of the method would provide a practical guide in understanding the course of self-heating and spontaneous combustion of coal stockpiles.

Bayesian discriminant analysis for prediction of coal and gas outbursts and application

Based on the principle of Bayesian discriminant analysis, we established a model of Bayesian discriminant analysis for predicting coal and gas outbursts. We selected five major indices which affect outbursts, i.e., initial speed of methane diffusion, a consistent coal coefficient, gas pressure, destructive style of coal and mining depth, as discriminating factors of the model. In our model, we divided the type of coal and gas outbursts into four grades regarded as four normal populations. We then obtained the corresponding discriminant functions through training a set of data from engineering examples as learning samples and evaluated their criteria by a back substitution method to verify the optimal properties of the model. Finally, we applied the model to the prediction of coal and gas outbursts in the Yunnan Enhong Mine. Our results coincided completely with the actual situation. These results show that a model of Bayesian discriminant analysis has excellent recognition performance, high prediction accuracy and a low error rate and is an effective method to predict coal and gas outbursts.

Development of regional prediction information system of coal and gas outburst

Coal and gas outburst information system is based on-Geographic Information System(GIS), with which the relation among mine geological structure, coal features, stress field and coal and gas outburst were researched, and also the relation between gas distributed condition and dangerous degrees. Various prediction method, index and technique were applied to realize the data visualization; the accuracy of region prediction was increased. The system has successfully applied in Huainan minging area and Pingdingshan minging area.

Application of dynamic set-pair analysis in coal and gas outburst prediction

Analyzed the factors which affected the coal and gas outburst,then established the corresponding indicator system.Built a dynamic set-pair analysis prediction model which combined of Markov model and set-pair analysis model,and then it applied to coal and gas outburst prediction.Finally,compared the prediction results with the actual results As provided a reference to the coalmine in safety decision-making.The research results indicate that there are four districts in high dangerous level,two districts in middle level and one district in low level,which consistent with the actual situation;the dynamic set-pair analysis model has a good effect in predicting coal and gas outburst.Especially in the continuous time intervals,according to the data of mined exploration and the connec- tion degree analysis,we can deduce the dangerous levels of unexplored districts from the historical data.In different districts,the relevant indicators can be adjusted accordingly,so as to enhance the accuracy of the prediction.

Prediction method for risks of coal and gas outbursts based on spatial chaos theory using gas desorption index of drill cuttings

Based on the evolution of geological dynamics and spatial chaos theory, we proposed the advanced prediction an advanced prediction method of a gas desorption index of drill cuttings to predict coal and gas outbursts. We investigated and verified the prediction method by a spatial series data of a gas desorption index of drill cuttings obtained from the 113112 coal roadway at the Shitai Mine. Our experimental results show that the spatial distribution of the gas desorption index of drill cuttings has some chaotic charac- teristics, which implies that the risk of coal and gas outbursts can be predicted by spatial chaos theory. We also found that a proper amount of sample data needs to be chosen in order to ensure the accuracy and practical maneuverability of prediction. The relative prediction error is small when the prediction pace is chosen carefully. In our experiments, it turned out that the optimum number of sample points is 80 and the optimum prediction pace 30. The corresponding advanced prediction pace basically meets the requirements of engineering applications.

Pattern recognition prediction of coal and gas outburst hazard in the sixth mine of Hebi

Based on the systematical analysis influence factors of coal and gas outburst, the main factors and their magnitude was determined by the corresponding methods.With the research region divided into finite predicting units,the internal relation between the factors and the hazard of coal and gas outburst,that was combination model of influence factors,was ascertained through multi-factor pattern recognition method.On the basis of contrastive analysis the pattern of coal and gas outburst between prediction region and mined region,the hazard of every predication unit was determined.The mining area was then divided into coal and gas outburst dangerous area,threaten area and safe area re- spectively according to the hazard of every predication unit.Accordingly the hazard of mining area is assessed.

Matter-elements model and application for prediction of ccoal and gas outburst

The theory and method of extenics were applied to establish classical field matterelements and segment field matter elements for coal and gas outburst.A matter-element model for prediction was established based on five matter-elements,which includedgas pressure,types of coal damage,coal rigidity,initial speed of methane diffusionand in-situ stress.Each index weight was given fairly and quickly through the improvedanalytic hierarchy process,which need not carry on consistency checks,so accuracy ofassessment can be improved.

Application of computational intelligence platform in coal and gas outburst prediction

The present situation of lacking fast and effective coal and gas outburst prediction techniques will lead to long out- burst prevention cycles and poor accurate prediction effects and slows down coal roadway drive speed seriously. Also, due to historical and economic reasons, some coal mines in China are equipped with poor safety equipment, and the staff professional capability is low. What＇s worse, artificial and mine geological conditions have great influences on the traditional technologies of coal and gas outburst prediction. Therefore, seeking a new fast and efficient coal and gas outburst prediction method is nec- essary. By using system engineering theory, combined with the current mine production conditions and based on the coal and gas outburst composite hypothesis, a coal and gas outburst spatiotemporal forecasting system was established. This system can guide forecasting work schedule, optimize prediction technologies, carry out step-by-step prediction and eliminate hazard hier- archically. From the point of view of application, the proposed system improves the prediction efficiency and accuracy. On this basis, computational intelligence methods to construct disaster information analysis platform were used. Feed-back results pro- vide decision support to mine safety supervisors.

Prediction of roadheaders' performance using artificial neural network approaches (MLP and KOSFM)

A pplication o f m echanical excavators is one o f th e m o st com m only used excavation m eth o d s because itcan bring th e p ro ject m ore productivity, accuracy and safety. A m ong th e m echanical excavators, roadhead ers are m echanical m iners w h ich have b een extensively u se d in tu n n elin g , m ining an d civil indu stries. Perform ance pred ictio n is an im p o rta n t issue for successful ro a d h e a d e r application andgenerally deals w ith m achine selection, p ro d u ctio n rate an d b it consu m p tio n . The m ain aim o f thisresearch is to investigate th e c u ttin g p erfo rm an ce （in stan tan eo u s c u ttin g rates （ICRs）） o f m ed iu m -d u tyro ad h ead ers by using artificial neural n etw o rk （ANN） approach. T here are d ifferent categories forANNs, b u t based o n train in g alg o rith m th e re are tw o m ain k in d s： supervised and u n su p erv ised . Them u lti-lay er p ercep tro n （MLP） an d K ohonen self-organizing feature m ap （KSOFM） are th e m o st w idelyused neu ral netw o rk s for supervised an d u n su p erv ised ones, respectively. For gaining this goal, ad atab ase w as prim arily provided from ro ad h e a d e rs＇ p erfo rm an ce an d geom echanical characteristics o frock form ations in tu n n els and d rift galleries in Tabas coal m ine, th e larg est an d th e only fullymech an ized coal m ine in Iran. T hen th e datab ase w as analyzed in o rd e r to yield th e m ost im p o rtan tfactor for ICR by using relatively im p o rta n t factor in w hich G arson eq u atio n w as utilized. The MLPn etw o rk w as train ed by 3 in p u t p ara m e te rs including rock m ass pro p erties, rock quality d esignation（RQD）, in tact rock p ro p erties such as uniaxial com pressive stre n g th （UCS） an d Brazilian ten sile stren g th（BTS）, and o n e o u tp u t p a ra m e te r （ICR）. In o rd e r to have m ore v alidation o n MLP o u tp u ts, KSOFM visualizationw as applied. The m ean square e rro r （MSE） an d regression coefficient （R ） o f MLP w e re found tobe 5.49 an d 0.97, respectively. M oreover, KSOFM n etw o rk has a m ap size o f 8 x 5 and final qu an tizatio nan d topographic erro rs w e re 0.383 an d 0.032, respectively. The results show th a t MLP neural n etw orkshave a strong capability to p red ict an d ev alu ate th e perfo rm an ce o f m ed iu m -d u ty ro ad h ead ers in coalm easu re rocks. Furtherm ore, it is concluded th a t KSOFM neural n etw o rk is an efficient w ay for u n d e rstand in g system beh av io r an d know ledge extraction. Finally, it is indicated th a t UCS has m ore influenceo n ICR b y applying th e b e st train ed MLP n etw o rk w eig h ts in G arson eq u atio n w h ich is also confirm ed byKSOFM.

△P index with different gas compositions for instantaneous outburst prediction in coal mines

In this study we measured the △P(initial speed of gas emission) index with different gas concentrations of carbon dioxide(pure CO2,90% CO2+10% CH4,67% CO2+33% CH4,50% CO2+50% CH4,30% CO2+10% CH4 and pure CH4) of coal samples from the No.2 coal seam in the Yaojie Coal Mine,Gansu province,China.The effect of carbon dioxide concentration,gas composition,coal strength and particle size of coal samples on the △P index was investigated.The experimental results show that with gas of various compositions,the △P value of three samples were clearly different.The △P index of coal samples A,B and C(0.2～0.25 mm) were 4,6 and 7 with pure CH4 and 22,30 and 21 when pure CH4 was used.Carbon dioxide concentration affects the △P index markedly.The △P index increases with an increase in carbon dioxide concentration,especially for coal B.Hence,the △P index and K(another outburst index) values tested only with pure CH4 for prediction of the danger of outburst is not accurate.It is important to determine the initial speed of gas emission given the gas composition of the coal seam to be tested for exact outburst prediction.

Dynamic prediction of gas emission based on wavelet neural network toolbox

This paper presents a method for dynamically predicting gas emission quantity based on the wavelet neural network （WNN） toolbox. Such a method is able to predict the gas emission quantity in adjacent subsequent time intervals through training the WNN with even time-interval samples. The method builds successive new model with the width of sliding window remaining invariable so as to obtain a dynamic prediction method for gas emission quantity. Furthermore, the method performs prediction by a self-developed WNN toolbox. Experiments indicate that such a model can overcome the deficiencies of the traditional static prediction model and can fully make use of the feature extraction capability of wavelet base function to reflect the geological feature of gas emission quantity dynamically. The method is characterized by simplicity, flexibility, small data scale, fast convergence rate and high prediction precision. In addition, the method is also characterized by certainty and repeatability of the predicted results. The effectiveness of this method is confirmed by simulation results. Therefore, this method will exert practical significance on promoting the application of WNN.

Pattern Recognition and Forecast of Coal and Gas Outburst

Coal and gas outburst is a complicated dynamic phenomenon in coal mines, Multi-factor Pattern Recognition is based on the relevant data obtained from research achievements of Geo-dynamic Division, With the help of spatial data management, the Neuron Network and Cluster algorithm are applied to predict the danger probability of coal and gas outburst in each cell of coal mining district. So a coal-mining district can be divided into three areas： dangerous area, minatory area, and safe area. This achievement has been successfully applied for regional prediction of coal and gas outburst in Hualnan mining area in China.

Design of artificial neural networks using a genetic algorithm to predict saturates of vacuum gas oil

Accurate prediction of chemical composition of vacuum gas oil （VGO） is essential for the routine operation of refineries. In this work, a new approach for auto-design of artificial neural networks （ANN） based on a genetic algorithm （GA） is developed for predicting VGO saturates. The number of neurons in the hidden layer, the momentum and the learning rates are determined by using the genetic algorithm. The inputs for the artificial neural networks model are five physical properties, namely, average boiling point, density, molecular weight, viscosity and refractive index. It is verified that the genetic algorithm could find the optimal structural parameters and training parameters of ANN. In addition, an artificial neural networks model based on a genetic algorithm was tested and the results indicated that the VGO saturates can be efficiently predicted. Compared with conventional artificial neural networks models, this approach can improve the prediction accuracy.

Distribution of Heavy Hydrocarbon in Coal Seams and Its Use in Predicting Outburst of Coal

In order to verify whether any special gas component exists in outburst samples or not, coal samples from both outburst coal seams and non-outburst coal seams were collected. Some gases were extracted from the samples and analyzed qualitatively and quantitatively on chromatogram-mass spectrograph. The qualitative analysis show that there is no special gases in coal seams. And the quantitative analysis indicates that the heavy hydrocarbon content in coal samples from outburst coal seams is apparently higher than that from non-outburst district ones, which reflects the damage of geological tectonic movement to coal body in history. Therefore, the heavy hydrocarbon content of coal sample can be used as an index to predict coal outburst.

Advances in gas content based on outburst control technology in Huainan, China

The sudden and violent nature of coal and gas outbursts continues to pose a serious threat to coal mine safety in China. One of the key issues is to predict the occurrence of outbursts. Current methods that are used for predicting the outbursts in China are considered to be inadequate, inappropriate or impractical in some seam conditions. In recent years, Huainan Mining Industry Group(Huainan) in China and the Commonwealth Scientific and Industrial Research Organisation(CSIRO) in Australia have been jointly developing technology based on gas content in coal seams to predict the occurrence of outbursts in Huainan. Significant progresses in the technology development have been made, including the development of a more rapid and accurate system in determining gas content in coal seams, the invention of a sampling-while-drilling unit for fast and pointed coal sampling, and the coupling of DEM and LBM codes for advanced numerical simulation of outburst initiation and propagation. These advances are described in this paper.

Predicting formation lithology from log data by using a neural network

In order to increase drilling speed in deep complicated formations in Kela-2 gas field, Tarim Basin, Xinjiang, west China, it is important to predict the formation lithology for drilling bit optimization. Based on the conventional back propagation （BP） model, an improved BP model was proposed, with main modifications of back propagation of error, self-adapting algorithm, and activation function, also a prediction program was developed. The improved BP model was successfully applied to predicting the lithology of formations to be drilled in the Kela-2 gas field.

Predicting gas-bearing distribution using DNN based on multi-component seismic data: Quality evaluation using structural and fracture factors

The tight-fractured gas reservoir of the Upper Triassic Xujiahe Formation in the Western Sichuan Depression has low porosity and permeability. This study presents a DNN-based method for identifying gas-bearing strata in tight sandstone. First, multi-component composite seismic attributes are obtained.The strong nonlinear relationships between multi-component composite attributes and gas-bearing reservoirs can be constrained through a DNN. Therefore, we identify and predict the gas-bearing strata using a DNN. Then, sample data are fed into the DNN for training and testing. After optimized network parameters are determined by the performance curves and empirical formulas, the best deep learning gas-bearing prediction model is determined. The composite seismic attributes can then be fed into the model to extrapolate the hydrocarbon-bearing characteristics from known drilling areas to the entire region for predicting the gas reservoir distribution. Finally, we assess the proposed method in terms of the structure and fracture characteristics and predict favorable exploration areas for identifying gas reservoirs.

Forecasting and optimal probabilistic scheduling of surplus gas systems in iron and steel industry

To make full use of the gas resource, stabilize the pipe network pressure, and obtain higher economic benefits in the iron and steel industry, the surplus gas prediction and scheduling models were proposed. Before applying the forecasting techniques, a support vector classifier was first used to classify the data, and then the filtering was used to create separate trend and volatility sequences. After forecasting, the Markov chain transition probability matrix was introduced to adjust the residual. Simulation results using surplus gas data from an iron and steel enterprise demonstrate that the constructed SVC-HP-ENN-LSSVM-MC prediction model prediction is accurate, and that the classification accuracy is high under different conditions. Based on this, the scheduling model was constructed for surplus gas operating, and it has been used to investigate the comprehensive measures for managing the operational probabilistic risk and optimize the economic benefit at various working conditions and implementations. It has extended the concepts of traditional surplus gas dispatching systems, and provides a method for enterprises to determine optimal schedules.

Method and practice of deep favorable shale reservoirs prediction based on machine learning

A set of methods for predicting the favorable reservoir of deep shale gas based on machine learning is proposed through research of parameter correlation feature analysis principle, intelligent prediction method based on convolution neural network(CNN), and integrated fusion characterization method based on kernel principal component analysis(KPCA) nonlinear dimension reduction principle.(1) High-dimensional correlation characteristics of core and logging data are analyzed based on the Pearson correlation coefficient.(2) The nonlinear dimension reduction method of KPCA is used to characterize complex high-dimensional data to efficiently and accurately understand the core and logging response laws to favorable reservoirs.(3) CNN and logging data are used to train and verify the model similar to the underground reservoir.(4) CNN and seismic data are used to intelligently predict favorable reservoir parameters such as organic carbon content, gas content, brittleness and in-situ stress to effectively solve the problem of nonlinear and complex feature extraction in reservoir prediction.(5) KPCA is used to eliminate complex redundant information, mine big data characteristics of favorable reservoirs, and integrate and characterize various parameters to comprehensively evaluate reservoirs. This method has been used to predict the spatial distribution of favorable shale reservoirs in the Ordovician Wufeng Formation to the Silurian Longmaxi Formation of the Weirong shale gas field in the Sichuan Basin, SW China. The predicted results are highly consistent with the actual core, logging and productivity data, proving that this method can provide effective support for the exploration and development of deep shale gas.