Prediction of Mine Gas Emission Based on Time Series Analysis

2012 ◽  
Vol 616-618 ◽  
pp. 450-454 ◽  
Author(s):  
Hai Dong Meng ◽  
Dong Yuan Zang ◽  
Yu Chen Song
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Prediction Method ◽  
Ar Model ◽  
Prediction Methods ◽  
Gas Emission ◽  
Gas Concentration ◽  
Series Analysis ◽  
Mine Gas

Because the variation of mine gas concentration is influenced by various factors, so it’s impossible for traditional prediction methods of mine gas emission to include all the factors. To solve the problem, the paper proposed a prediction method of mine gas emission based on AR model of time series analysis. The experiment results indicated that the method can predict mine gas emission accurately.

scholarly journals Nonlinear time series analysis of the fluctuations of the geomagnetic horizontal field

2002 ◽  
Vol 20 (2) ◽  
pp. 175-183 ◽  
Author(s):  
B. George ◽  
G. Renuka ◽  
K. Satheesh Kumar ◽  
C. P. Anil Kumar ◽  
C. Venugopal
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Correlation Dimension ◽  
Prediction Method ◽  
Nonlinear Time Series ◽  
Nonlinear Time Series Analysis ◽  
Suitable Model ◽  
Nonlinear Prediction ◽  
Series Analysis ◽  
Hourly Data

Abstract. A detailed nonlinear time series analysis of the hourly data of the geomagnetic horizontal intensity H measured at Kodaikanal (10.2° N; 77.5° E; mag: dip 3.5° N) has been carried out to investigate the dynamical behaviour of the fluctuations of H. The recurrence plots, spatiotemporal entropy and the result of the surrogate data test show the deterministic nature of the fluctuations, rejecting the hypothesis that H belong to the family of linear stochastic signals. The low dimensional character of the dynamics is evident from the estimated value of the correlation dimension and the fraction of false neighbours calculated for various embedding dimensions. The exponential decay of the power spectrum and the positive Lyapunov exponent indicate chaotic behaviour of the underlying dynamics of H. This is also supported by the results of the comparison of the chaotic characteristics of the time series of H with the pseudo-chaotic characteristics of coloured noise time series. We have also shown that the error involved in the short-term prediction of successive values of H, using a simple but robust, zero-order nonlinear prediction method, increases exponentially. It has also been suggested that there exists the possibility of characterizing the geomagnetic fluctuations in terms of the invariants in chaos theory, such as Lyapunov exponents and correlation dimension. The results of the analysis could also have implications in the development of a suitable model for the daily fluctuations of geomagnetic horizontal intensity.Key words. Geomagnetism and paleomagnetism (time variations, diurnal to secular) – History of geophysics (solar-planetary relationships) Magnetospheric physics (storms and substorms)

The Research of Predicting the Carbonation Depth of Concrete with Time-Series Analysis

2013 ◽  
Vol 351-352 ◽  
pp. 1694-1699
Author(s):  
Gui Zhou Li ◽  
Xin Gang Zhou
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Influence Factors ◽  
Paper Analysis ◽  
Ar Model ◽  
Carbonation Depth ◽  
Predicting Model ◽  
Concrete Carbonation ◽  
Series Analysis ◽  
Changes Over Time

This paper analysis and reviews the calculation and the predicting model of concrete carbonation depth, also discusses the influence factors of concrete carbonization and the applicability of the predicting model. In order to reduce or avoid the effect of complex factors such as material composition, humidity and temperature on the calculation of the carbonation depth and the prediction results, the predicting model of concrete carbonation depth based on the time-series changes is investigated. In this model, Box-Jenkins time series analysis is utilized to establish the regression model-AR model, which reflect the concrete carbonation depth changes over time. The research and analysis shows that the model has characteristics of simple and high precision, and with the measured data increased and updated, the prediction result is getting better and better. Using this method to evaluate the life of concrete structures which under the affection of carbonation, only need to test the carbonation depth of concrete, and the other parameters is not need consider.

scholarly journals Examination and Forecasting of Drug Consumption Based on Recurrent Deep Learning

2019 ◽  
Vol 8 (2S10) ◽  
pp. 414-420
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Analysis ◽  
Evaluation Method ◽  
Short Term Memory ◽  
Prediction Method ◽  
Pharmaceutical Drugs ◽  
Data Set ◽  
Series Analysis ◽  
One Year

The provision of pharmaceutical drugs in quantities appropriate to consumption is an important point in the pharmaceutical industry and storage of medicines, as the production of large quantities of unnecessary drugs leads to a longer storage of drugs. Meanwhile most medicines have a short shelf life. When the amount of production is less than required, this affects the satisfaction of the customer and the marketing of the drug. Time series analysis is the appropriate solution to this problem. Deep learning has been adapted for the purpose of time series analysis and a prediction of the required quantities drugs. A recurrent neural network with Long-Short Term Memory LSTM has been used by deep learning. The proposed methodology is based on the seasonal number of prescription required quantities with the number of quarters as indicators. The aim of the research is to forecast the drugs amount needed for one year. The proposed method is assessed using two types of evaluation. The first one is based on MSE and the visualization of the actual data and forecasted data. The proposed method has reached a low value of MSE and the visualization graph is semi-identical, whereas the second evaluation method compares the result of the proposed method with traditional forecasting method. Multiple linear regression is a traditional prediction method used with the data set, whose results are relatively good and promising compared to the results of the traditional method.

Sign in / Sign up

Export Citation Format

Share Document