当前位置: X-MOL 学术Qual. Reliab. Eng. Int. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A deep learning approach for predicting critical events using event logs
Quality and Reliability Engineering International ( IF 2.3 ) Pub Date : 2021-02-22 , DOI: 10.1002/qre.2853
Congfang Huang 1 , Akash Deep 1 , Shiyu Zhou 1 , Dharmaraj Veeramani 1
Affiliation  

Event logs, comprising data on the occurrence of different types of events and associated times, are commonly collected during the operation of modern industrial machines and systems. It is widely believed that the rich information embedded in event logs can be used to predict the occurrence of critical events. In this paper, we propose a recurrent neural network model using time-to-event data from event logs not only to predict the time of the occurrence of a target event of interest, but also to interpret, from the trained model, significant events leading to the target event. To improve the performance of our model, sampling techniques and methods dealing with the censored data are utilized. The proposed model is tested on both simulated data and real-world datasets. Through these comparison studies, we show that the deep learning approach can often achieve better prediction performance than the traditional statistical model, such as, the Cox proportional hazard model. The real-world case study also shows that the model interpretation algorithm proposed in this work can reveal the underlying physical relationship among events.

中文翻译:

一种使用事件日志预测关键事件的深度学习方法

事件日志包括有关不同类型事件发生和相关时间的数据,通常在现代工业机器和系统的运行期间收集。人们普遍认为,事件日志中嵌入的丰富信息可用于预测关键事件的发生。在本文中,我们提出了一种循环神经网络模型,该模型使用来自事件日志的时间到事件数据,不仅可以预测感兴趣的目标事件发生的时间,还可以从训练模型中解释导致到目标事件。为了提高我们模型的性能,使用了处理删失数据的采样技术和方法。所提出的模型在模拟数据和真实数据集上进行了测试。通过这些对比研究,我们表明,与传统的统计模型(例如 Cox 比例风险模型)相比,深度学习方法通​​常可以实现更好的预测性能。实际案例研究还表明,这项工作中提出的模型解释算法可以揭示事件之间的潜在物理关系。
更新日期:2021-02-22
down
wechat
bug