Pattern Discovery in White Etching Crack Experimental Data Using Machine Learning Techniques
Pattern Discovery in White Etching Crack Experimental Data Using Machine Learning Techniques
复制标题
DOI：
10.3390/app9245502
复制
发表时间：
2019-12-01
影响因子：
2.7
通讯作者：
Jacobs, Georg
中科院分区：
文献类型：
--
作者：
Azzam, Baher;Harzendorf, Freia;Jacobs, Georg
白色蚀刻裂纹（WEC）失效是一种影响许多应用中轴承的失效模式，包括风力涡轮机齿轮箱，它会导致高昂的计划外维护成本。到目前为止，WEC故障是不可预测的，其根本原因尚未完全了解。虽然过去的几项研究都是在受控条件下产生白蚀斑的，但将不同实验中导致白蚀斑的不同因素组合的结果融合起来仍然是一个挑战。本文使用机器学习（ML）模型解决了这一挑战，该模型能够捕获属于几个实验的高维数据中的模式，以便识别对WECs风险有影响的变量。设计了三种不同的ML模型，并将其应用于包含大约700种高风险和低风险石油成分的数据集，以识别使给定石油成分对WECs具有高风险的构成化合物。这包括首次应用专门构建的基于神经网络的特征选择方法。在21种化合物中，有8种化合物通过基于随机森林和人工神经网络的模型被确定为具有影响力。关联规则也从数据中挖掘，以调查化合物组合和WEC风险之间的关系，导致结果支持之前的分析。此外，在一项涉及物理测试的单独调查中，已确定的影响最大的化合物被证明具有高WEC风险。所提出的方法可应用于其他实验数据，其中大量测量变量可能影响某一结果，并且需要确定影响最大的变量。
White etching crack (WEC) failure is a failure mode that affects bearings in many applications, including wind turbine gearboxes, where it results in high, unplanned maintenance costs. WEC failure is unpredictable as of now, and its root causes are not yet fully understood. While WECs were produced under controlled conditions in several investigations in the past, converging the findings from the different combinations of factors that led to WECs in different experiments remains a challenge. This challenge is tackled in this paper using machine learning (ML) models that are capable of capturing patterns in high-dimensional data belonging to several experiments in order to identify influential variables to the risk of WECs. Three different ML models were designed and applied to a dataset containing roughly 700 high- and low-risk oil compositions to identify the constituting chemical compounds that make a given oil composition high-risk with respect to WECs. This includes the first application of a purpose-built neural network-based feature selection method. Out of 21 compounds, eight were identified as influential by models based on random forest and artificial neural networks. Association rules were also mined from the data to investigate the relationship between compound combinations and WEC risk, leading to results supporting those of previous analyses. In addition, the identified compound with the highest influence was proved in a separate investigation involving physical tests to be of high WEC risk. The presented methods can be applied to other experimental data where a high number of measured variables potentially influence a certain outcome and where there is a need to identify variables with the highest influence.