摘要
为降低机械自动化制造过程中的废品率,提出模式识别在机械自动化制造过程中的质量监控方法,监控自动化制造过程中的产品质量,提高对产品质量的识别精准度。基于机械自动化制造过程中的质量检测环节,创建机械自动化制造过程中的产品质量监控流程。采用数字化测量仪采集机械自动化制造生产线质量数据,创建SPC控制图。基于SPC控制图模式识别的质量监控方法,将k-means算法与粒子群算法相结合,利用改进k-means算法获取控制图模式产品质量数据集聚类中心,结合欧氏距离,提取SPC控制图距离特征。将其输入多分类的支持向量机中,识别机械自动化制造过程中的产品质量控制图模式类型,诊断异常因素,并采取相应调控措施,实现机械自动化制造过程中的质量监控。实验表明:该方法可有效提高控制图的识别精准度,缩短训练与测试时间;并有效监控机械自动化制造过程中的产品质量。
In order to reduce the scrap rate in the mechanical automatic manufacturing process,the quality monitoring method of pattern recognition in the mechanical automatic manufacturing process is proposed to monitor the product quality in the automatic manufacturing process and improve the identification accuracy of product quality.Based on the quality detection link in the mechanical automatic manufacturing process,the product quality monitoring process in the mechanical automatic manufacturing process is created.The digital measuring instrument is used to collect the quality data of the mechanical automatic manufacturing production line,and the SPC control chart is created.Based on the quality monitoring method of SPC control chart pattern recognition,the k-means algorithm is combined with particle swarm optimization algorithm,The improved k-means algorithm is used to obtain the cluster center of the product quality data set of the control chart pattern.Combined with the Euclidean distance,the distance feature of the SPC control chart is extracted and input into the multi classification support vector machine to identify the pattern type of the product quality control chart in the mechanical automatic manufacturing process,diagnose the abnormal factors,and take corresponding control measures,realize quality monitoring in mechanical automatic manufacturing process.Experiments show that this method can effectively improve the recognition accuracy of control chart and shorten the training and testing time and effectively monitor the product quality in the process of mechanical automatic manufacturing.
作者
黄亮
HUANG Liang(Zhejiang Linix Motor Co.,Ltd.,Dongyang 322100,China)
出处
《机械与电子》
2022年第11期9-14,共6页
Machinery & Electronics