锻压技术

压力机故障实时自诊断方法与系统

英文标题：Real-time self-diagnostic method and system for press fault

作者：张传锦高建波王岩袁全范宏伟

分类号：TH16；TP23

出版年,卷(期):页码：2020,45(6):136-140

摘要：

为了提高用于金属冲压成形领域的压力机故障的诊断效率，提出了一种压力机故障实时自诊断方法，该方法将压力机多种信息融合并判断压力机故障点。首先，诊断系统从控制系统中获取压力机当前的运行状态信息；然后，推理机结合各类信息阈值和状态进行数据分析，并根据数据分析结果和故障现象描述等信息进行故障推理匹配，找出可能故障点，同时，根据多维数据诊断压力机潜在故障；最后，根据诊断结果处理故障并反馈给诊断系统，系统根据反馈维护更新诊断系统数据库。通过在压力机上的实际应用，证明本文的故障实时自诊断方法可快速定位故障点、缩短故障处理时间、提高生产效率。

In order to improve the fault diagnosis efficiency of press in the field of metal stamping, a real-time self-diagnostic method of press fault was proposed to determine the fault points of press by combining various press information. Firstly, the diagnostic system obtained the information about the current operating state of press from the control system. Then, the reasoning machine combined the various types of information threshold and statuses for data analysis and performed fault reasoning matching based on the data analysis results and the fault phenomenon descriptions to find possible fault points. At the same time, the potential faults of press were diagnosed by multi-dimensional data. Finally, the faults were processed according to the diagnostic result and fed back to the diagnostic system, and the diagnostic system database was updated based on the feedback maintenance. Therefore, the practical application on press show that the above real-time self-diagnostion of fault can locate the fault points quickly, shorten the fault processing time and improve the production efficiency.

基金项目：

山东省重点研发计划（2017CXGC0807）

张传锦（1990-），男，硕士，工程师 E-mail：keli_tech20@126.com

参考文献：

［1］罗词文. WFL机床人机交互故障诊断系统研究
［D］. 南京: 东南大学，2017.

Luo C W. Fault Diagnostic System of Human-computer Interaction of WFL Mill-turn
［D］. Nanjing: Southeast University, 2017.

［2］吴冬敏，邵剑平，芮延年. 基于蚁群算法和神经网络的数控机床故障诊断技术研究
［J］. 机械设计与制造，2013， (1):165-167.

Wu D M, Shao J P, Rui Y N. Research on CNC machine fault diagnosis based on ant colony algorithm and neural network
［J］. Machinery Design & Manufacture, 2013， (1):165-167.

［3］Edrington B, Zhao B, Hansel A, et al. Machine monitoring system based on MTConnect technology
［J］. Procedia CIRP，2014，22(1): 92-97.

［4］付振华，丁杰雄，张信，等. 多传感器融合在数控机床故障诊断中的应用研究
［J］. 机械设计与制造，2014，(2):140-142.

Fu Z H, Ding J X, Zhang X, et al. Attempt on application of multi-sensor data fusion in fault diagnosis of CNC machine tools
［J］. Machinery Design & Manufacture, 2014, (2):140-142.

［5］朱奕玮，阎秋生，路家斌，等. 基于剪切力特征的圆盘剪分切机故障监测方法
［J］. 锻压技术，2019，44(12):131-138.

Zhu Y W, Yan Q S, Lu J B, et al. Condition monitoring method for disc slitting machine based on shearing force characteristics
［J］. Forging & Stamping Technology, 2019, 44(12): 131-138.

［6］曹莉，唐玲，吴浩，等. 基于免疫神经网络的数控机床故障诊断研究
［J］. 机床与液压，2016，44(13):184-190.

Cao L, Tang L, Wu H, et al. Research on CNC machine tool fault diagnosis based on immune neural network
［J］. Machine Tool & Hydraulics, 2016, 44(13):184-190.

［7］陈德道，安虎平. 基于模糊故障树的数控机床故障诊断方法
［J］. 机床与液压，2015，43 (5):177-180.

Chen D D, An H P. Fault diagnosis method of CNC machine tool based on fuzzy fault tree
［J］. Machine Tool & Hydraulics,2015，43 (5): 177-180.

［8］曹春平，倪俊，李猛，等. 基于专家系统的压力机故障诊断系统
［P］.中国,107272646，2017-10-20.

Chao C P, Ni J, Li M, et al. Press fault diagnosis system based on expert system
［P］. China, 107272646，2017-10-20.

［9］张邦成，伊晓静，王占礼，等. 利用置信规则库的数控机床伺服系统故障诊断
［J］. 振动、测试与诊断，2013，33(4): 694-700.

Zhang B C, Yi X J, Wang Z L, et al. Fault diagnosis of CNC machine servo system using confidence rule base
［J］. Journal of Vibration, Measurement & Diagnosis, 2013,33 (4): 694-700.

［10］赵炯，盛凡，周杰，等. 设备故障监测与诊断系统数据库设计
［J］. 机械设计与制造,2014，(5):155-158.

Zhao J, Sheng F, Zhou J, et al. Database design of equipment fault monitoring and diagnosis system
［J］, Machinery Design & Manufacture, 2014, (5):155-158

［11］张金萍，白广彬. 基于主元分析与KNN算法的旋转机械故障识别方法
［J］. 机械设计与制造，2017，(6):23-25.

Zhang J P, Bai G B. Method of rotating machinery fault pattern recognition based on PCA and KNN algorithm
［J］. Machinery Design & Manufacture, 2017，(6):23-25.

［12］林阳昊. 数控机床故障诊断专家系统设计
［D］.成都:西华大学，2017.

Lin Y H. Design of Fault Diagnosis Expert System for Numerical Control Machine
［D］.Chengdu: Xihua University, 2017.

服务与反馈：

【文章下载】【加入收藏】