融合工艺信息的复杂零件加工状态识别方法

中国机械工程

融合工艺信息的复杂零件加工状态识别方法

朱绍维1,2;牟文平1;汤立民1;杜丽2

1.中航工业成都飞机工业(集团)有限责任公司，成都，610092
2.电子科技大学，成都，611731

出版日期:2016-06-10 发布日期:2016-06-08
基金资助:
国家科技重大专项(2012ZX04001012)

Cutting Status Identification Method for Complex Parts Integrating with Process Informations

Zhu Shaowei1,2;Mou Wenping1;Tang Limin1;Du Li2

1.AVIC Chengdu Aircraft Industrial (Group) Co.,Ltd.,Chengdu,610092
2.University of Electronic Science and Technology,Chengdu,611731

Online:2016-06-10 Published:2016-06-08

摘要/Abstract

摘要： 为解决基于物理信号的加工监控系统在复杂零件数控加工过程中易受工艺波动影响而导致误报警的问题，提出两种融入零件工艺信息的方法来提高加工状态识别的准确率。为验证其可行性，基于数控系统OPC接口开发了一套远程监控系统原型，结合工艺信息和主轴实时切削功率对加工状态进行识别，一旦发现异常，立即控制机床停止加工。在典型飞机结构件上开展了应用验证，结果表明：融入工艺信息后，加工状态识别准确率明显提升。

关键词: 加工监控, 复杂零件, 工艺信息, OPC

Abstract: In CNC machining of complex parts, the physical signal-based machining monitoring system was easily affected by the process fluctuations, which led to false alarms. In order to figure out this problem,two methods integrated process informations were proposed to improve the accuracy of cutting status identification. To test and verify their feasibility, a remote monitoring prototype system was developed based on the OPC interface of numerical control system, which identified the cutting status integrating with the process informations and real-time cutting power of spindle, and stoped the cutting once abnormal cutting was detected. Application tests were conducted on several typical aircraft structure parts, the results show that the accuracy of process identification is promoted after integrating with the process informations.

Key words: machining monitoring, complex parts, process information, OPC

中图分类号:

TH166
TH165

朱绍维, 牟文平, 汤立民, 杜丽. 融合工艺信息的复杂零件加工状态识别方法[J]. 中国机械工程.

Zhu Shaowei, Mou Wenping, Tang Limin, Du Li. Cutting Status Identification Method for Complex Parts Integrating with Process Informations[J]. China Mechanical Engineering.

参考文献

[1]Bhattacharyya P, Sengupta D, Mukhopadhyay S, et al. On-line Tool Condition Monitoring in Face Milling Using Current and Power Signals[J]. International Journal of Production Research, 2008, 46(4): 1187-1201.

[2]Ghosh N, Ravi Y B, Patra A, et al. Estimation of Tool Wear during CNC Milling Using Neural Network-based Sensor Fusion[J]. Mechanical Systems and Signal Processing, 2007, 21(1): 466-479.

[3]王海丽, 翁德玮, 胡兆燕, 等. 基于模糊神经网络的刀具磨损识别[J]. 上海交通大学学报, 2002, 36(8): 1086-1090.

Wang Haili, Weng Dewei, Hu Zhaoyan, et al. Tool Wear Monitoring Using Fuzzy Neural Network[J]. Journal of Shanghai Jiaotong University, 2002, 36(8): 1086-1090.

[4]王海丽, 马春翔, 邵华,等. 车削过程中刀具破损和磨损状态的自动识别[J]. 上海交通大学学报, 2006, 40(12): 2057-2062.

Wang Haili, Ma Chunxiang, Shao Hua, et al. The Tool Wear and Breakage Monitoring in Turning Using Neural Network[J]. Journal of Shanghai Jiaotong University, 2006, 40(12): 2057-2062.

[5]Dey S, Stori J A. A Bayesian Network Approach to Root Cause Diagnosis of Process Variations[J]. International Journal of Machine Tools and Manufacture, 2005, 45(1): 75-91.

[6]Geramifard O, Xu J X, Zhou J H, et al. Multimodal Hidden Markov Model-based Approach for Tool Wear Monitoring[J]. IEEE Transactions on Industrial Electronics,2014, 61(6): 2900-2911.

[7]Xie N, Chen L, Zheng B, et al.A Rough Set-based Effective State Identification Method of Multisensor Tool Condition Monitoring System[J]. Advances in Mechanical Engineering, 2014, 6(8): 947-962.

[8]Li X, Djordjevich A,Venuvinod P K. Current-sensor-based Feed Cutting Force Intelligent Estimation and Tool Wear Condition Monitoring[J]. IEEE Transactions on industrial electronics, 2000,47(3): 697-702.

[9]Abellan-Nebot J V, Subiron F R. A Review of Machining Monitoring Systems Based on Artificial Intelligence Process Models[J]. International Journal of Advanced Manufacturing Technology, 2010, 47(1): 237-257.

[10]Siemens.通过ETHERNET建立OPC服务器与S7 PLC的S7连接.(2014-03-07)[2015-07-28].https://support.industry.siemens.com/cs/document/83102835/ethernetsimatic-net-opc-plc-s7?dti=0&pnid=13613&lc=zh-CN.