نوع مقاله : مقاله پژوهشی
نویسندگان
1 دانشکده مهندسی برق - دانشگاه یزد
2 گروه مخابرات- دانشکده مهندسی برق - دانشگاه یزد-یزد - ایران
چکیده
کلیدواژهها
موضوعات
عنوان مقاله [English]
نویسندگان [English]
Shovel is a type of mechanical excavator set that is used in open pit mines. the shovel bucket has a number of teeth, which increase the efficiency of the bucket. Prolonged direct impact of bucket teeth on ore during loading causes unexpected teeth breakage. One of the factors that stop the crusher is the separation of this tooth from the shovel bucket and loading and transfer to the crusher due to the lack of sufficient visibility of the operator on the teeth. The entry of this teeth into the crusher causes the crusher to jam and stop the production cycle. Therefore, it is necessary to propose a bucket shovel teeth detection algorithm with high accuracy and in real time. To solve this problem, we improved the accuracy of the model by making changes in the basic yolov5 model structure. The proposed method was evaluated on a new data set from shovel under real working conditions. The results obtained with an average accuracy of 93.5% and a complexity of 16.1 indicate the improvement of the detection accuracy and the reduction of the complexity in the detection process, which meets the requirements of accurate and real-time detection of bucket shovel teeth.
کلیدواژهها [English]
)