摘要
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑-机器学习的最新研究结果已经发表。根据NewsRx记者来自法国贝桑松的新闻报道，研究表明，“系统膨胀传感器测量的数据驱动预测，以预测退化演变和预测故障，对应于剩余使用寿命(RUL)的估计。该任务使用特征工程建立预测指标(HI)，机器L收益(ML)来估计RUL。”我们的新闻记者从F ranche-comte大学的研究中获得了一句话：“然而，来自类似系统在不同条件下的OPE评级的高可变性对RUL的性能产生了负面影响。因此，”本文提出了一种结合特征和ML工程方法来提供可解释的RUL预测的新方法，其关键贡献在于构造有效的预测指标，隔离不同的轮廓参数，实现对每个系统的自适应RUL提取，并利用这些指标和RUL轨迹训练一组异质ML预测器，有效地解决变异性问题，提高RUL性能。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Machine Learn ing have been published. According to news originating from Besancon, France, by NewsRx correspondents, research stated, “Data -driven prognostics of systems ex ploit sensor measurements to predict the degradation evolution and anticipate fa ilures, corresponding to the estimation of the remaining useful life (RUL). This task uses feature engineering to build prognostic indicators (HI) and machine l earning (ML) to estimate the RUL.” Our news journalists obtained a quote from the research from the University of F ranche-Comte, “However, high variability in data coming from similar systems ope rating under different conditions negatively affects the RUL performance. Hence, this paper presents a new methodology that combines feature and ML engineering methods to provide an explainable RUL prediction. The key contributions lie in c onstructing efficient prognostic indicators that isolate distinct profile trajec tories, enabling adaptive RUL extraction for each system. An ensemble of heterog eneous ML predictors is also trained using these indicators and RUL trajectories , effectively addressing variability issues and enhancing RUL performance.”
NETL
NSTL