Prediction of Failures in the Air Pressure System of Scania Trucks Using a Random Forest and Feature Engineering
Prediction of Failures in the Air Pressure System of Scania Trucks Using a Random Forest and Feature Engineering
复制标题
使用随机森林和特征工程预测斯堪尼亚卡车气压系统的故障
DOI：
10.1007/978-3-319-46349-0_36
复制
发表时间：
2016
期刊：
影响因子：
3.9
通讯作者：
Oliver R. Sampson
中科院分区：
文献类型：
--
作者：
Christopher Gondek;D. Hafner;Oliver R. Sampson
本文展示了一种数据分析方法，以最大限度地减少斯堪尼亚卡车气压系统的总体维护成本。使用直方图上的特征创建。然后对随机选择的属性子集进行评估，以生成特征的顺序和最终子集。最后，应用随机森林并进行微调。结果清楚地表明，在现场进行数据分析是有益的，并改进了检查每辆卡车或没有卡车直到故障的天真方法。
This paper demonstrates an approach in data analysis to minimize overall maintenance costs for the air pressure system of Scania trucks. Feature creation on histograms was used. Randomly chosen subsets of attributes were then evaluated to generate an order and a final subset of features. Finally, a Random Forest was applied and fine-tuned. The results clearly show that data analysis in the field is beneficial and improves upon the naive approaches of checking every truck or no truck until failure.