基于机器视觉的压力表智能读数系统

打开文本图片集

中图法分类号：TP391.4 文献标识码：A 文章编号：1000-2324（2025）04-0681-09

IntelligentReadingSystemforPressureGaugesBased on Machine Vision

WANG Bi-jun³，HOU Jia-bin²， ZHANG Kai-xing²， ZHENGLai-chen²， ZHOU Chang-an²，LIU Xin'

1.CollegeofAgriculture/ShandongAgriculturalUniversity，Tai'an271ol8，China

2.CollegeofMechanicalandElectronicEngineering/ShandongAgricultural UniversityTai'an2718，China

3.TaianPanranPressureInstrumentCo.Tai'an271018，China

Abstract：Pressure gaugesare essential measurement tools inindustrial production，capableofefective measurementof mechanical working pressure.Their calibration process often requires separate equipment，such as presure sources and controlers，whichrelieson wired connections.This setupis prone toconnector wearandcable cluttr.Thus，we developan al-in-one intelligentreadingcalibrationsystemofpressregauges toachievetheorganicfusionofequipmentandcables.It includesafullyautomaticair pressuregenerator，avisual inspection device，aquick-change lifting device，andapressure gaugereading method basedon the improved Mask R-CNN dep learming model.The test results ofthe pneumatic pressure generatorshow thattheabsolute errr is withinO.O02，thecontrol stabilityand cycle stabilityare inaccordance with the standards of the calibration regulations，and the pressure generation reaches 600kPa ，meeting performance design requirements. For pressure gauge reading test， the relative error is within 1.05% for small-range gauges and 4.57% for largerrange gauges， with a higher identification accuracy.

Keywords：Pressure calibration; visual detection; fully automatic air pressure generator; Mask R-CNN

引言

且相当部分的压力计量器具属于法定强制检定范围[2]。（剩余10304字）