基于生存分析的设备剩余寿命预测技术研究

Research on Equipment Residual Life Prediction Based on Survival Analysis

剩余使用寿命(RUL)是指在某一规定操作时间内设备的有效使用寿命,但是由于RUL通常是随机和未知的,所以对RUL的预测必须依据有效的信息来源(如在设备健康监测环境中获得的信息)来进行。近年来,由于设备健康状态监测技术的迅速发展,使得如何快速有效地预测RUL也已越来越受到人们的关注,然而,由于RUL与可观测的设备健康信息之间具有复杂的关联性,所以目前并没有最佳的方法来使得预测达到期望中的有效准确。在此基础上,回顾了近年来RUL的建模发展,并在基于条件维护和状态预测的生存分析下审查集中统计数据驱动的方法,且对设备剩余寿命预测技术的合理性作出介绍。在此项工作中,也以退化信号为预测手段,通过建立分析退化模型来对设备剩余寿命预测技术进行性能评估,从而验证此项技术对于设备剩余使用寿命的合理预测是可行且有效的。

Remaining useful life(RUL)is the useful life left on an asset at a particular time of operation.RUL is typically random and unknown,and as such it must be estimated from available sources of information such as the information obtained in condition and health monitoring.The research on how to best estimate the RUL has gained popularity recently due to the rapid advances in condition and health monitoring techniques.However,due to its complicated relationship with observable health information,there is no such best approach which can be used universally to achieve the best estimate.As such this paper reviews the recent modeling developments for estimating the RUL.And review the centralized statistical data-driven method under the survival analysis based on conditional maintenance and state prediction,and put forward a reasonable technology of equipment residual life prediction.In this work,we also use the degradation signal as a prediction method to evaluate the performance of the equipment residual life prediction technology through the establishment of an analytical degradation model,so as to verify that this technology can effectively predict the remaining service life of the equipment and is feasible And effective.