Abstract

Hydraulic support plays a key role in ground control of longwall mining. The smart prediction methods of support load are important for achieving intelligent mining. In this paper, the hydraulic support load data is decomposed into trend term, cycle term, and residual term, and it is found that the data has clear trend and period features, which can be called time series data. Based on the autoregression theory and weighted moving average method, the time series model is built to analyze the load data and predict its evolution trend, and the prediction accuracy of the sliding window model, ARIMA (Autoregressive Integrated Moving Average) model, and SARIMA (Seasonal Autoregressive Integrated Moving Average) model to the hydraulic support load under different parameters are evaluated, respectively. The results of single-point and multipoint prediction test with various sliding window values indicate that the sliding window method has no advantage in predicting the trend of the support load. The ARIMA model shows a better short-term trend prediction than the sliding window model. To some extent, increasing the length of the autoregressive term can improve the long-term prediction accuracy of the model, but it also increases the sensitivity of the model to support load fluctuation, and it is still difficult to predict the load trend in one support cycle. The SARIMA model has better prediction results than the sliding window model and the ARIMA model, which reveals the load evolution trend accurately during the whole support cycle. However, there are many external factors affecting the support load, such as overburden properties, hydraulic support moving speed, and worker’s operation. The smarter model of SARIMA considering these factors should be developed to be more suitable in predicting the hydraulic support load.

Highlights

  • With the rapid development of the Internet of Things, Cloud Computing, Big Data, Artificial Intelligence, and coal mine, integrating these emerging technologies will greatly change the traditional way of coal extraction [1,2,3]

  • The hydraulic support is the main equipment of longwall mining face, and it plays an important role to ensure the safety of the working space

  • The hydraulic support load has strong time series characteristics, and the time series model can be used for prediction and analysis

Read more

Summary

Introduction

With the rapid development of the Internet of Things, Cloud Computing, Big Data, Artificial Intelligence, and coal mine, integrating these emerging technologies will greatly change the traditional way of coal extraction [1,2,3]. Many other scholars [10,11,12,13,14,15,16,17,18,19] analyzes the fracture instability process of the overburden on working face in various mining conditions, proposes a method for calculating the suitable working resistance of the hydraulic support, and reveals the relationship between surrounding rock fracture instability and hydraulic support load. The existing hydraulic support load analysis methods just count the interval pressure and capture the initiation and peak support load, sometimes the resistance forces at the end of the support cycle are monitored Based on these data, the roof fracture step and the pressure in surrounding rock can be estimated roughly. This paper uses a time series model based on statistics to analyze and predict the load data of hydraulic support under the condition of small samples. By comparing the prediction results of varies models with responding parameters, and the adaptability of different models to the prediction of hydraulic support load, it obtains a more reasonable analysis and prediction method for hydraulic support load

General Methodology
Analysis and Prediction of Support Load Based on Sliding Window
Analysis and Prediction of Support Load Based on Autoregressive Model
Discussion
Conclusions

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 call

Disclaimer: 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.