基于FPGA的输送带跑偏检测系统设计

Design of Conveyor Belt Deviation Detecting System Based on FPGA

针对带式输送机运行过程中的跑偏问题,在分析了目前输送带跑偏检测方法的基础上,提出了基于机器视觉的跑偏检测方法,并在FPGA平台上采用VerilogHDL语言实现。通过CMOS图像传感器采集输送带运行视频数据,经格式转换和图像滤波后进行边缘提取和跑偏检测。在跑偏检测部分,采用坐标统计法与分组近似法相结合的方式来识别输送带的横向跑偏和扭转跑偏特征。仿真和实验结果表明,系统能够实现30帧/s的实时处理,并准确检测出输送带的故障特征。

For the conveyor belt deviation during operation,a deviation detecting method based on machine vision was proposed on the basis of the current detection methods,and realized on FPGA through the Verilog HDL language.The CMOS image sensor was used to collect the conveyor belt running video data.Then edge extraction and off-tracking detection were performed after format conversion and image filtering.The lateral and torsional deviated characteristics of the conveyor belt were identified through the combination of coordinate statistics and grouping approximation.Simulation and experimental results show that the system can process 30 frames per second in real time and accurately detect the fault features of the conveyor belt.