基于AI的刀具磨损对刨花质量和刨花板性能影响的评估  

The Assessment of The Impact of Tool Wear on Particles Quality and Particleboard Performance Based on AI

作　　者：何雨晨 李园 郑圣龙 杨兆金 黄鹤鸣 罗邦瑞 解林坤[1] 杜官本[1] 周华 万辉 HE Yu-chen;LI Yuan;ZHENG Sheng-long;YANG Zhao-jin;HUANG He-ming;LUO Bang-rui;XIE Lin-kun;DU Guan-ben;ZHOU Hua;WAN Hui(College of Materials Science and Engineering,Southwest Forestry University,Kunming 650223,Yunnan,P.R.China;Kunming Panel Artificial Board Co.,Ltd.,Kunming 650223,Yunnan,P.R.China;College of Big Data and Intelligent Engineering,Southwest Forestry University,Kunming 650223,Yunnan,P.R.China)

机构地区：[1]西南林业大学材料与化学工程学院,云南昆明650223 [2]昆明飞林人造板集团有限公司,云南昆明650403 [3]西南林业大学大数据与智能工程学院,云南昆明650224

出　　处：《林产工业》2024年第3期30-37,共8页China Forest Products Industry

基　　金：云南省人才培养专项(80201402);西南林业大学校级科研专项(111927)。

摘　　要：为推动人造板智能制造的发展,本文建立了一种基于AI计算机视觉技术的刨花尺寸与形状的检测方法,能自动识别刨花尺寸大小并区分出杆状、类矩形、类三角形和其他型4种刨花形状。在此基础上,对在不同切削时间的刨花形态变化、刨片机刀具磨损程度和工作电流进行了监测和诊断。同时,用这些刨花分组制备了相应的刨花板,并对其物理力学性能进行测试,建立了刨片机刀具磨损程度、电流消耗量、刨花形态与刨花板性能的数学关系模型,并找到刨片机优化换刀时间。结果表明:基于AI的刨花形态检测不但能够监测刀具磨损过程中刨花形态的变化,还可以有效预测刨花板的产品性能。在给定的生产条件下,刨片机开机运行2~4 h内切削出的刨花所制造的刨花板综合性能最好。In order to promote the development of intelligent manufacturing of wood-based panel manufacture,in this study,a particle size and geometric shape detection method based on AI computer vision technology was established,which can identify the particle size and distinguish four kinds of particle shapes,including rod,class rectangle,class triangle,and other types.Based on this,the particle shape change,the degree of tool wear,and the working current of the flaker at different cutting times were monitored.Meanwhile,particle boards were manufactured with the factory particles which were classified and the physical and mechanical properties of different particleboards were tested.Based on test results,mathematical models were built to find the correlation between the degree of tool wear,current consumption of flaker,particle shape,and particleboard performance.Then,the best tool change time of the flaker was determined.The results showed that AI defined detection index not only effectively reflected the change of particle shape in the process of continuous tool wear,but also effectively predicted the quality of particleboards.Under the given production conditions,the comprehensive performance of particleboard made at 2~4 h flaking time was the best.

关 键 词：计算机视觉技术 过程控制 刀具磨损 刨花质量 刨花板性能 

分 类 号：TS653.3[轻工技术与工程] TS396