Swarm Intelligent Shearer Cutting Pattern Recognition System Based on Integrated Learning

Abstract

The invention discloses a group intelligent shearer cutting pattern recognition system based on integrated learning, which is used to identify the cutting model of the coal shearer, including a data preprocessing module, and a shearer cutting pattern recognition limit gradient boosting (eXtreme Gradient Boosting, XGBoost) model modeling module, swarm intelligence optimization module, and unknown signal recognition module for shearer cutting. The present invention can accurately identify the cutting mode of the shearer, adopts the integrated learning algorithm to establish the recognition model of the cutting mode of the coal shearer, and avoids the model accuracy and loss caused by the randomness of the artificial selection of parameters by adding a group intelligent optimization process to the modeling process. Confidence drop problem.

Description

technical field [0001] The invention relates to the fields of signal processing, swarm intelligence optimization and integrated learning, in particular to a shearer cutting pattern recognition system combining integrated learning and swarm intelligence optimization algorithms. Background technique [0002] my country is making every effort to develop its economy, and its demand for energy is increasing day by day. Coal accounts for about 70% of the primary energy consumption and is one of the important pillars of the national economy. It is the development direction and trend of the coal mining industry to vigorously improve the automation, mechanization and informationization level of the coal mining process and reduce the number of underground workers. As the key equipment of the coal mining face, the shearer is of great significance in the process of coal production. Solving the problem of cutting pattern recognition of coal shearer is the premise of improving the degre...

AI Technical Summary

Problems solved by technology

On the one hand, the recognition rate is affected by geological conditions, which greatly increases the cost of detection equipment

On the other hand, the installation of the above-mentioned method equipment is too complicated and requires specific geological conditions, making the system difficult to maintain

The above problems lead to low recognition accuracy and poor robustness of traditional methods, which cannot be put into actual production use

Images