煤矸分拣机器人的煤矸动态称重方法

打开文本图片集

中图分类号：TD67 文献标志码：A Dynamic weighing method for coal and gangue in coal-gangue sorting robots CAO Xiangang1，2，LIUYizhel2，WUXudong1.2，WANG Peng12，ZHANG Ye1.2

（1.SchoolofMechanicalEngineering，Xi'an UniversityofScienceandTechnology，Xi'an71oo54，China; 2.ShaanxiKeyLaboratoryofMine Electromechanical Equipment IntelligentDetectionand Control，

Xi'an 710054，China）

Abstract： Image recognition-based coal-gangue sorting robots have become aresearch hotspot in the field of coal-gangue separation.To addressthe issue of lowrecognition accuracycaused by complex real-world conditions—such as dust adhesion，lighting variation，water stains，and coal slury coverage—a dynamic weighing method for coal and ganguewas proposed，integratinga tension sensorand anacceleration sensor toenable secondary recognition.By analyzing the influence mechanismof triaxial acceleration on the tension sensor during the high-speed motion of the robotic arm ina coal-gangue sorting robot，a dynamic weighing model for coal and gangue based on triaxial acceleration compensation was established.Furthermore，an outlierelimination mechanism based on the interquartile range （IQR） algorithm was introduced to suppressrandom noise in the dynamic weighing model.An experimental platform for dynamic weighing ofcoal and gangue inacoal-gangue sorting robot was constructed to conduct experiments.Experimental results showed that the weighing error reached 66.43% without triaxial acceleration compensation. After introducing z -axis，and x -and y. -axis acceleration compensation， the errors were reduced to 12.97% and 8.69% ，respectively.With the addition of the IQR algorithm， the weighing error of the dynamic weighing model was further reduced to 4.69% ，representing a 61.74% reduction compared to the case without triaxial acceleration compensation and the IQR algorithm. The model was able to achieve secondary recognition between coal and gangue when their density diference exceeded 0.35g/cm3 ， effectively solving the problem of low recognition accuracy under complex real-world conditions.

Key words： coal-gangue sorting robot; dynamic weighing of coal and gangue; secondary recognition for coal and gangue; acceleration compensation; interquartile range algorithm

0 引言

煤矸分选是原煤生产过程中的关键环节之二[1-2]，目前常用基于图像识别[3]、X射线探测[4]、热红外响应分析[5]、高光谱成像[6]、激光反射率检测[7]等方法实现煤与矸石的有效识别。（剩余12302字）