机器人故障检测的统计特征工程:机器学习和深度学习分类器的比较研究
1Department of Mechatronics Engineering, Erciyes University, 38039 Kayseri, Türkiye.
Sensors (Basel, Switzerland)
|March 14, 2026
概括
这项研究比较了机器学习和深度学习的机器人故障检测使用力-扭矩传感器数据. 使用原始时间序列特征的naive Bayes实现了最高的准确性,证明了机器人故障分类统计特征的有效性.
科学领域:
- 机器人技术 机器人技术 机器人技术
- 机器学习 机器学习
- 传感器数据分析数据分析
背景情况:
- 工业机器人在制造业中至关重要,需要可靠的故障检测以确保运营连续性.
- 及早准确地识别机器人执行失败对于系统可靠性至关重要.
研究的目的:
- 为了全面比较机器学习和深度学习方法来分类机器人执行失败.
- 评估不同特征工程方法对分类性能的影响.
- 确定机器人故障检测中最有效的算法和功能.
主要方法:
- 利用来自工业机器人的力-扭矩传感器数据.
- 提出了三个特征工程方法:基线 (原始时间序列),域6 (基本统计) 和域12 (综合统计).
- 在30次运行中使用嵌套和k-fold交叉验证评估了10个分类算法 (8ML,2DL).
主要成果:
- 特性工程显著影响了分类性能.
- 使用基线特征的天真贝叶斯分类器实现了最高的准确性 (93.85% ± 0.90).
- 域12功能集在多个算法中持续提高了性能.
结论:
- 时间域统计特征对于机器人故障分类是有效的.
- 来自Fx和Fy传感器的斜度特征被确定为故障检测的关键.
- 该研究强调了功能工程在优化机器人故障检测系统方面的重要性.
相关概念视频
02:16Stereotype Content Model
15.6K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.6K
01:19Survival Tree
462
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
462