Research On Collaborative Planning Technology Of Three Fully Mechanized Miningmachines Based On Deep Learning

The intelligent technology of fully mechanized mining face is continuously advancing and its ultimate goal is to realize unmanned fully mechanized mining face.At present,in the harsh conditions of coal mines,although some of the domestic mines can achieve a certain degree of automation,the overall comprehensive mining equipment is still dominated by the on-site operation of underground workers,the popularity of automation technology is not high,the manual operation of comprehensive mining equipment is time-consuming and laborious,and the work efficiency is low,once a safety accident occurs,it is very easy to cause casualties.Therefore,the study of cooperative control of fully mechanized mining equipment is one of the key technologies to realize intelligent and unmanned fully mechanized mining face,and is the premise and foundation to realize safe and efficient production of fully mechanized mining face.Aiming at the problems existing in the intelligent development of fully mechanized coal mining faces,this thesis takes the core equipment of fully mechanized coal mining faces,such as shearers,scraper conveyors,and hydraulic supports,as the research object.Through combining the working mechanism of the three machines,theoretical models,and experiments,it proposes a deep learning based collaborative planning method for fully mechanized coal mining based on the fusion of multiple features such as dynamic distribution,shared collaboration,and so on,It plays a positive role in the intelligent development of collaborative control technology in fully mechanized mining faces.The main research content and results of this article are as follows:(1)The structure and function of the core equipment of the fully mechanized mining face,such as the shearer,scraper conveyor,and hydraulic support,are analyzed in depth.A three-machine physical sensing system is constructed.Based on the working mechanism of the fully mechanized mining equipment,a technical scheme for the comprehensive mining three-machine collaborative planning based on deep learning is proposed,a comprehensive mining three-machine collaborative planning model based on deep learning is established,and the overall architecture design of the comprehensive mining three-machine collaborative planning system based on deep learning is completed.(2)Aiming at the poor efficiency of collaborative operation between shearers and scraper conveyors,the requirements for collaborative planning of mining and transportation equipment were analyzed,and a collaborative speed planning model for mining and transportation equipment based on the judgment of the load current of the scraper conveyor was designed.Select CNN-LSTM combined neural network to establish a collaborative speed prediction model for mining and transportation equipment.On the basis of studying the variation model of airborne coal quantity in scraper conveyor and analyzing the relationship between transportation load and motor current of scraper conveyor,establish a current judgment model for scraper conveyor based on GRU,which provides a basis for speed planning of mining and transportation equipment.(3)Analyzed the principle of hydraulic support collaborative following action,designed a hydraulic support collaborative following control scheme based on the traction speed of the coal mining machine,planned the hydraulic support collaborative following action under the collaborative planning speed of mining and transportation equipment,and established a hydraulic support moving distance prediction model using PSO-BP combined neural network,Based on the preset displacement distance output,the support control system is used to plan and control the hydraulic support movement at the current moment by setting the displacement sensor on the support.(4)Experiments were conducted on the collaborative planning technology of the three machines in the underground fully mechanized mining face,and experimental analysis was conducted to verify that the method proposed in this thesis can effectively predict and plan the operating status of the fully mechanized mining equipment.Compared with manual operation,the deep learning based collaborative planning production method of the three machines in fully mechanized mining improves the reliability and productivity of the fully mechanized mining face.