Abstract
Accurate quantitative analysis and prediction of dust concentration in mines play a vital role in avoiding pneumoconiosis to a certain extent, improving industrial production efficiency, and protecting the ecological environment. The research has far‐reaching significance for the prediction of dust concentration in mines in the future. Aiming at the shortcomings of the grey GM (1, 1) model in forecasting the data sequence with large random fluctuation, a grey Markov chain forecasting model is established. Firstly, considering the timeliness of monitoring data, the new dust concentration data is supplemented by using the method of cubic spline interpolation in the original data sequence. Therefore, the GM (1, 1) model is established by the method of metabolism. Then, the GM (1, 1) model is optimized by the theory of the Markov chain model. According to the relative error range generated during the prediction, the state interval is divided. Subsequently, the corresponding state probability transition matrix is constructed to obtain the grey Markov prediction model. The model was applied to the prediction of mine dust concentration and compared with the prediction results of the BP neural network model, grey prediction model, and ARIMA (1, 2, 1) model. The results showed that the prediction accuracy of the grey Markov model was significantly improved compared with other traditional prediction models. Therefore, the rationality and accuracy of this model in the prediction of mine dust concentration were verified.
Highlights
Accurate quantitative analysis and prediction of dust concentration in mines play a vital role in avoiding pneumoconiosis to a certain extent, improving industrial production efficiency, and protecting the ecological environment. e research has farreaching significance for the prediction of dust concentration in mines in the future
Considering the timeliness of monitoring data, the new dust concentration data is supplemented by using the method of cubic spline interpolation in the original data sequence. erefore, the GM (1, 1) model is established by the method of metabolism. en, the GM (1, 1) model is optimized by the theory of the Markov chain model
The corresponding state probability transition matrix is constructed to obtain the grey Markov prediction model. e model was applied to the prediction of mine dust concentration and compared with the prediction results of the BP neural network model, grey prediction model, and ARIMA (1, 2, 1) model. e results showed that the prediction accuracy of the grey Markov model was significantly improved compared with other traditional prediction models. erefore, the rationality and accuracy of this model in the prediction of mine dust concentration were verified
Summary
2.1. eoretical Basis of the Neural Network. e learning and training process of the neural network method includes two stages: forward propagation and backward propagation. For a given raw data sequence, the GM(1, 1) model of a first-order differential equation is generated by one accumulation, and the original sequence is processed as follows: X(1) x(1)(1), x(1)(2), . Accumulate the time series of samples and construct the grey differential equation as follows: dx(1) + ax(1) b, dt (2). E details of the Grey Markov model are introduced briefly as follows: Step: the result state division of GM (1, 1) model prediction e fitting data obtained by the model are compared with the actual sample data, and their relative values are used as the correction value λ (k) for interval division. According to the interval state of the prediction results, the one-step transition probability is determined, and the state matrix of the research system is constructed [27,28,29,30]. Step : model correction e residuals between the measured value and the simulation value are calculated, and the average residuals of all states in each state interval are taken to correct the predicted value of the grey Markov model
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
