A dynamic prediction method for coal and gas outburst based on hybrid intelligence

Abstract

The present invention proposes a dynamic prediction method for coal and gas outburst based on hybrid intelligence. The process includes: data detection; data processing using the mean value batch estimation fusion method; forming new problems to be predicted; using case clustering-based case retrieval and Matching method, case retrieval and matching for new problems, if the case retrieval and matching are valid, use the weighted average method to reuse the cases, and get the prediction results of coal and gas outburst, if the case retrieval and matching are invalid, run OBPNN The outburst prediction model is used to obtain the prediction results of coal and gas outburst. The proposed method is verified by the measured data, and the example verification results show that the proposed method gives high-precision prediction results, and has good robustness, and the modeling algorithm is more efficient and the prediction time is shorter.

Description

technical field [0001] The invention belongs to the field of coal and gas outburst disaster prediction, and in particular relates to a dynamic prediction method for coal and gas outburst based on hybrid intelligence. Background technique [0002] Coal and gas outburst is one of the most dangerous disasters in the mining process, with high occurrence frequency and great social impact. Rapid, accurate and dynamic prediction of coal and gas outburst is particularly important for effective prevention and control of coal and gas outburst disasters in mines. Up to now, scholars at home and abroad have done a lot of research on coal and gas outburst prediction, and put forward a variety of prediction methods, such as electromagnetic radiation monitoring method, RES theory method, SVM method, ANN method, case reasoning method, etc. The case-based reasoning (CBR) prediction method of coal and gas outburst is a new method proposed in recent years. It uses historical experience cases ...

AI Technical Summary

Problems solved by technology

The reasoning and prediction methods of coal and gas outburst cases in the above literature are all based on effective case retrieval and matching, that is, under the condition that cases larger than the threshold can be obtained from the case database, the coal and gas outburst risk prediction research is carried out, and the risk prediction of coal and gas outburst is not carried out in invalid cases. In the case of retrieval and matching, that is, when cases larger than the threshold cannot be obtained, in-depth research on coal and gas outburst risk prediction is carried out

Due to the comprehensive complexity of coal and gas outbursts such as suddenness, nonlinearity, diversity and uncertainty of influencing factors, it is very difficult to obtain cases that traverse all situations of coal and gas outbursts, and invalid case retrieval and matching will inevitably occur Case

Images