视觉校对约束下生产线搬运机械手抓取定位控制  

Grasping and Positioning Control of Production Line Handling Manipulator under Visual Proofreading Constraints

作　　者：孙文革[1] SUN Wenge(College of Mechanical and Electronic Engineering,Xinjiang Vocational University,Urumqi 830013,China)

机构地区：[1]新疆职业大学机械电子工程学院,新疆乌鲁木齐830013

出　　处：《机械制造与自动化》2024年第5期203-208,共6页Machine Building & Automation

摘　　要：针对智能生产线环境中存在的随机振动、噪声等干扰因素会对机械手的传感器精度产生影响,导致生产线搬运机械手抓取定位控制精度低的问题,提出智能视觉约束的生产线搬运机械手抓取定位控制方法。分析生产线搬运机械手的动作流程,了解机械手在进行抓取操作时需要确定目标物体位置存在的问题;通过改进的YOLOv2模型识别待搬运物体的位置,估计出待搬运物体的大小;使用改进K-means聚类算法通过聚类过程估计出待搬运物体与机械手之间的相对距离和大小,改进单纯依靠传感器的弊端。设计PLC控制器来实现对机械手的定位控制;同时引入小脑模型神经网络模拟人类小脑的运动控制能力,优化PID控制算法,使机械手在抓取和定位控制中更加稳定和精确。实验结果表明:所提方法使生产线搬运机械手抓取定位时抗干扰性较强,精度较高,抓取定位控制效率较好。In order to improve the low grasping and positioning control accuracy of production line handling manipulator caused by random vibration,noise and other confounding existing in intelligent production line environment,which affects the sensor accuracy of manipulator,a research on grasping and positioning control method of the production line handling manipulator with intelligent visual constraints is proposed.The movement process of the production line handling manipulator is analyzed and the problems that the manipulator needs to determine the position of the target object during grasping operations are comprehended.With the improved YOLOv2 model,the position of the object ready for transportation is identified and its size is estimated.The improved K-means clustering algorithm is applied to estimate the relative distance between the object to be moved and the robotic arm through the clustering process to remedy the drawbacks of sole reliance on sensors.A PLC controller is designed to achieve positioning control of the robotic arm,and with the introduction of cerebellar model neural network,the motion control ability of the human cerebellum is simulated and the PID control algorithm is optimized,which enable the robotic arm to be more stable and accurate in grasping and positioning control.The experimental results show that the proposed method has strong anti-interference ability,high accuracy and good grasping and positioning control efficiency for the production line handling robot arm.

关 键 词：生产线搬运机械手 PLC控制器 PID控制算法 小脑模型神经网络 抓取定位控制 

分 类 号：TP241[自动化与计算机技术—检测技术与自动化装置]