上海交通大学学报(自然版) ›› 2011, Vol. 45 ›› Issue (07): 1000-1005.

• 自动化技术、计算机技术 • 上一篇    下一篇

统计模式识别和自回归滑动平均模型在
设备剩余寿命预测中的应用

廖雯竹1,潘尔顺2,王莹2,奚立峰2   

  1. (1.重庆大学 机械工程学院, 重庆 400030; 2.上海交通大学 机械与动力工程学院, 上海 200240)
  • 收稿日期:2010-07-28 出版日期:2011-07-29 发布日期:2011-07-29
  • 基金资助:

    国家自然科学基金资助项目(50875168, 50905115);国家高技术研究发展计划(863)项目(2008042801)

Research of Predicting Machine’s Remaining Useful Life Based on Statistical Pattern Recognition and Auto-regressive and Moving Average Model

 LIAO  Wen-Zhu-1, PAN  尔Shun-2, WANG  Ying-2, XI  Li-Feng-2   

  • Received:2010-07-28 Online:2011-07-29 Published:2011-07-29

摘要: 为了对设备预知性维护研究提供支持,采用统计模式识别(SPR)方法对设备进行性能评估,获取设备健康指标;再运用自回归滑动平均模型(ARMA)对设备剩余寿命进行预测,建立了基于设备健康状况的设备剩余寿命预测模型.对生产过程中刀具加工设备寿命预测进行分析和验证结果表明,该设备评估和预测方法是有效且实用的.

关键词: 健康指标, 统计模式识别, 自回归滑动平均模型, 剩余寿命, 预测

Abstract: Considering the important applications of predictive maintenance (PdM) today, it becomes essential to acquire machine’s condition and its deterioration process. A machine’s remaining useful life (RUL) model was proposed in which a statistical pattern recognition (SPR) method is developed to estimate machine’s health index (HI) and an autoregressive and moving average (ARMA) model is used to predict machine’s RUL based on HI information, which greatly supports PdM planning. Through a case study, the computational results show that the proposed model is efficient and practical.

Key words:  health index (HI), statistical pattern recognition (SPR), autoregressive and moving average (ARMA) model, remaining useful life (RUL), prediction

中图分类号: