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

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

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.

Considering the important applications of predictive maintenance （PdM） today, it becomes es sential 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 esti mate 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.