School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China.
Energy Department, Politecnico di Milano, 20156 Milano, Italy.
Sensors (Basel). 2023 Jan 14;23(2):965. doi: 10.3390/s23020965.
Data redundancy and data loss are relevant issues in condition monitoring. Sampling strategies for segment intervals can address these at the source, but do not receive the attention they deserve. Currently, the sampling methods in relevant research lack sufficient adaptability to the condition. In this paper, an adaptive sampling framework of segment intervals is proposed, based on the summary and improvement of existing problems. The framework is implemented to monitor mechanical degradation, and experiments are implemented on simulation data and real datasets. Subsequently, the distributions of the samples collected by different sampling strategies are visually presented through a color map, and five metrics are designed to assess the sampling results. The intuitive and numerical results show the superiority of the proposed method in comparison to existing methods, and the results are closely related to data status and degradation indicators. The smaller the data fluctuation and the more stable the degradation trend, the better the result. Furthermore, the results of the objective physical indicators are obviously better than those of the feature indicators. By addressing existing problems, the proposed framework opens up a new idea of predictive sampling, which significantly improves the degradation monitoring.
数据冗余和数据丢失是状态监测中的相关问题。分段间隔的采样策略可以从源头上解决这些问题，但它们并没有得到应有的重视。目前，相关研究中的采样方法对状态的适应性不足。本文在总结和改进现有问题的基础上，提出了一种基于分段间隔的自适应采样框架。该框架用于监测机械退化，并在模拟数据和真实数据集上进行了实验。随后，通过颜色图直观地展示了不同采样策略采集样本的分布，并设计了五个指标来评估采样结果。直观和数值结果表明，与现有方法相比，所提出的方法具有优越性，结果与数据状态和退化指标密切相关。数据波动越小，退化趋势越稳定，结果越好。此外，客观物理指标的结果明显优于特征指标的结果。通过解决现有问题，所提出的框架为预测采样开辟了新思路，显著提高了退化监测的效果。
