Research on the Prediction of Gas Emission Quantity in Coal Mine Based on Grey System and Linear Regression for One Element

Guo-xun, Jing; Xu, Sen; Heng, Xianwei; Chuang-qi, Li

doi:10.1016/j.proeng.2011.11.2342

Cited by 14 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Having data {(1, ε 1 ), ..., (n, ε n )} and the linear model representing those data with the form : ε * k = α.k + β. Using the Least Mean Square method [8], we find the coefficients α and β minimizing the quantity :…”

Section: Resultsmentioning

confidence: 99%

“…Cheng and al, in [4], uses Markov chains to predict customer lifetime, however M. Cavers and al used in [5] a Markovian transition matrix to represent recurrent states of an Earthquake sequences grouped in zones. In an other side, linear regression is used also for forecasting next value and the trend extraction according to works of D. Ying Ying Sim and al in [7] (2014) and J. Guo-xun and al in [8] (2011). In this work we propose a finite state prediction algorithm.…”

Section: Related Workmentioning

confidence: 99%

“…For this, the use of Markov chains ( [3], [4] and [5]) seems to be the best way to predict environment discrete states. In an other side, the auto-rectification mechanism relies on linear regression ( [7] and [8]) to extract the residues trend and predict eventual next residue.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Low Complexity Auto-Adaptive Algorithm for Finite State Prediction Given Historical Observations

Tigani¹,

Ouzzif²,

Saadane³

2015

CAE

View full text Add to dashboard Cite

This work presents an auto-configurable algorithm for finite state prediction. The specificity of this algorithm is the capacity of self-rectification of the prediction strategy before final decision. The auto-rectification mechanism is based on two parallel mathematical models : a Markov chain model for next state prediction rectified with a linear regression model for residues forecasting. For a normal distribution, the interactivity between the two models allows the algorithm to self-optimize its performance and then make better prediction. This work proposes also some statistical key performance indicators in order to prove the efficiency of the approach. Simulation results shows the advantages of the proposed algorithm compared with the traditional one.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Low Complexity Auto-Adaptive Algorithm for Finite State Prediction Given Historical Observations

Tigani¹,

Ouzzif²,

Saadane³

2015

CAE

View full text Add to dashboard Cite

show abstract

“…In emission prediction methods, the commonly used prediction methods mainly include the neural network analysis method [17][18][19][20], data fusion theory [21][22][23], and multiple regression method [24,25]. Dong et al [24] thought that the application of Gaussian process regression to gas emission time series analysis is a feasible and effective gas emission prediction method, which has high practical application value.…”

Section: Introductionmentioning

confidence: 99%

“…Yuan et al [42] proposed the grey GM (1,1) gas emission prediction model, which realized the real-time, dynamic and nonlinear prediction of gas emission. Jing et al [25] used the grey GM (1,1) and linear regression to predict methane emissions, and showed that the former has higher accuracy. Xu et al [43] proposed using an adaptive GM (1,1) to study traffic pollution emissions in China.…”

Section: Introductionmentioning

confidence: 99%

Research on Prediction Accuracy of Coal Mine Gas Emission Based on Grey Prediction Model

Zeng¹,

2021

Processes

View full text Add to dashboard Cite

In order to achieve the accuracy of gas emission prediction for different workplaces in coal mines, three coal mining workings and four intake and return air roadway of working face in Nantun coal mine were selected for the study. A prediction model of gas emission volume based on the grey prediction model GM (1,1) was established. By comparing the predicted and actual values of gas emission rate at different working face locations, the prediction error of the gray prediction model was calculated, and the applicability and accuracy of the gray prediction method in the prediction of gas gushing out from working faces in coal mines were determined. The results show that the maximum error between the predicted and actual measured values of the gray model is 2.41%, and the minimum value is only 0.07%. There is no significant prediction error over a larger time scale; the overall prediction accuracy is high. It achieves the purpose of accurately predicting the amount of gas gushing from the working face within a short period of time. Consequently, the grey prediction model is of great significance in ensuring the safety production of coal mine working face and promote the safety management of coal mine.

show abstract

Top corner gas concentration prediction using t‐distributed Stochastic Neighbor Embedding and Support Vector Regression algorithms

Shi

Lü

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

SummaryThe excess of gas concentration in the top corner of coal working face has always been the main factor restricting the safe productivity of coal mines. Therefore, the rapid and accurate prediction of top corner gas concentration is an effective method to prevent gas disasters. At the same time, the development of the Internet of things has made the gas monitoring data collected by the coal mine safety monitoring system exhibit nonlinear big data characteristics. In order to mine the characteristic data related to the gas concentration of the top corner from a high‐dimensional and nonlinear monitoring datasets, a model that integrates the t‐distributed Stochastic Neighbor Embedding algorithm (t‐SNE) and the Support Vector Regression (SVR) algorithm to predict the gas concentration of the top corner on the coal working face is proposed. First, the multidimensional monitoring data are nonlinearly dimension‐reduced by t‐SNE algorithm, which enabled the spatial feature data of the monitoring data to be extracted. After that, the SVR algorithm was used to construct the nonlinear regression model between the spatial feature data and the actual gas concentration of the top corner to predict the gas concentration of the top corner. The experimental results show that the predictive model based on t‐SNE and SVR was better than the multiple linear regression, SVR, Principal Components Analysis (PCA) + SVR. The results show the model based on t‐SNE and SVR was more stable and could provide more accurate predictions, anomaly sensitivity, and the fitness is 0.55628405, which can better fit the actual gas concentration of the top corner.

show abstract

Research on the Prediction of Gas Emission Quantity in Coal Mine Based on Grey System and Linear Regression for One Element

Cited by 14 publications

References 0 publications

Low Complexity Auto-Adaptive Algorithm for Finite State Prediction Given Historical Observations

Low Complexity Auto-Adaptive Algorithm for Finite State Prediction Given Historical Observations

Research on Prediction Accuracy of Coal Mine Gas Emission Based on Grey Prediction Model

Top corner gas concentration prediction using t‐distributed Stochastic Neighbor Embedding and Support Vector Regression algorithms

Contact Info

Product

Resources

About