Real-Time Prediction Model of Coal and Gas Outburst
Модель прогнозирования внезапных выбросов угля и газа в реальном времени
2020-10-29
SCID: 54.1/ne3vpdhy
Discuss with AI
Pauta criterionabnormal data identificationaccuracy 97.5%coal and gas outburst predictioncorrelation coefficient imputationmissing data imputationrandom forestreal-time predictionsensitivity 100%specificity 84.6%
Figures from the paper
Abstract (AI)
Coal and gas outburst has been one of the main threats to coal mine safety. Accurate coal and gas outburst prediction is the key to avoid accidents. The data is actual and complete by default in the existing prediction model. However, in fact, data missing and abnormal data value often occur, which results in poor prediction performance. Therefore, this paper proposes to use the correlation coefficient to complete the missing data filling in real time for the first time. The abnormal data identification is completed based on the Pauta criterion. Random forest model is used to realize the prediction model. The prediction performance of sensitivity 100%, accuracy 97.5%, and specificity 84.6% were obtained. Experiments show that the model can complete the prediction of coal and gas outburst in real time under the condition of missing data and abnormal data value, which can be used as a new prediction model of coal and gas outburst.
Key Findings
1
A real-time prediction model for coal and gas outburst was developed using a Random Forest classifier.
2
Abnormal data values are identified using the Pauta criterion before prediction.
3
Missing data are filled in real time using correlation coefficient–based imputation introduced for the first time in this context.
4
The model achieved sensitivity 100%, accuracy 97.5%, and specificity 84.6% on the evaluated data.
5
The proposed system can perform real-time outburst prediction despite missing and abnormal data, offering a practical new prediction approach.
Research Object
Coal and gas outburst prediction system for coal mines (real-time prediction model using random forest with real-time data completion and abnormality detection)
Research Subject
Real-time prediction performance and robustness of the model under missing and abnormal data, including data completion via correlation coefficient, abnormal-data identification via the Pauta criterion, and prediction metrics (sensitivity, accuracy, specificity)
Publication Details
Publication Date
2020-10-29
Journal
Publisher
ISSN
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest