Study On The Key Technologies Of Personnel Detection And Pre-warning In Shearer Operating Space

With the development of intelligent technology,how to promote the transformation of fully mechanized mining automation to intelligent fully mechanized mining is one of the core problems to be solved in the current coal industry.Fully mechanized mining face has the characteristics of low illumination and poor working environment.In intelligent fully mechanized mining face,shearer operation mode is changed from local control to remote control.In local mode,other personnel can be reminded to avoid straying into the operating space by observation and warning of the personnel who following the shearer.With the operation mode change for mechanically electromechanical equipment,it has become a key problem to be solved urgently to ensure the workers’ safety in the electromechanical equipment operating space.Unfortunately,although shearer has functions including three-dimensional positioning,memory cutting,remote monitoring and etc.,the detection and pre-warning function for errant personnel who straying into the shearer operating space has not yet been realized.The lack of this function may lead to serious safety accidents once underground personnel straying into the shearer operating space.Hence,it is necessary to research the key technologies of personnel detection and pre-warning in shearer operating space to realize the safety production when shearer operating and achieve safe and efficient production of coal mine.In this paper,the key technologies of personnel detection and pre-warning in shearer operating space are researched.The infrared thermal imager is utilized to collect the infrared images for the shearer operating space,and it is studied that the infrared image denoising method for the infrared images with complex mixed noise.Then,the motion features and position extraction model of personnel target in shearer operation space is established.Finally,the target position prediction and estimation algorithm based on the Strong Tracking Filter is designed to realize personnel position prediction and pre-warning in shearer operation space.The main work in this paper can be summarized as follow:(1)On the basis of the cooperative-work model among the shearer,hydraulic support and scraper conveyor,the overall framework of the personnel detection and pre-warning system in shearer operating space is constructed by combining the functional requirements of the personnel detection and pre-warning system;the main components and implementation procedure are analyzed.(2)The noise composition and characteristics of the infrared images collected from the shearer operating space are analyzed,and anti-allergy filtering models for infrared images are established against the non-uniform noise.The spatiotemporal variant of the anti-allergy filtering model is constructed by combining the time domain characteristics of infrared image sequences collected from the shearer operating space,and the quality of the infrared image collected from the shearer operating space is improved by the spatiotemporal variant.(3)The function requirements of the personnel detection system in shearer operating space were analyzed;An extraction model for motion features of the moving personnel in the infrared image domain of the shearer operating space is established;A extraction method for the motion features of infrared moving foreground target under dynamic background is studied by combining the infrared image sequence characteristics,to extract the motion features of moving foreground target in shearer operating space.(4)An image segmentation method is proposed to realize the segmentation of complex infrared images collected from shearer operating space by combining the infrared scene characteristics in shearer operating space.By using the improved infrared image segmentation method based on the local information weight and the Gold-panning Algorithm,the infrared images collected from shearer operating space are segmented effectively.A personnel location detection algorithm based on morphological weight is designed,which effectively integrates the motion features and location information of personnel in the shearer operating space,and the location information of the moving personnel is extracted completely.(5)A pre-warning and protection method for personnel in shearer operating space is established;Based on the motion features and location information of personnel in shearer operating space,the location prediction and tracking model of moving personnel is established.Then,the personnel hazard pre-warning function in shearer operating space is implemented.The key technologies of personnel detection and pre-warning in shearer operating space are researched in this paper,and a personnel detection and pre-warning system in shearer operating space is designed.Finally,underground industrial experiments are carried out to verify enhance the proposed methods including the denoising algorithm for infrared images collected from the fully mechanized working face,motion feature extraction algorithm,location information detection algorithm,and personnel location prediction and danger states pre-warning method.The result indicates that: the system can effectively extract the motion features and position information of moving personnel in the shearer operating space,realize the pre-warning for the dangers of personnel,and provide technical support for the safety production of intelligent fully mechanized mining face.In this dissertation,there are 60 figures,21 tables and 218 references.