Abstract
Deep learning has shown the great power in the field of fault detection. However, for incipient faults with tiny amplitude, the detection performance of the current deep learning networks (DLNs) is not satisfactory. Even if prior information about the faults is utilized, DLNs can't successfully detect faults 3, 9 and 15 in Tennessee Eastman process (TEP). These faults are notoriously difficult to detect, lacking effective detection technologies in the field of fault detection. In this work, we propose Autoencoder-assisted Feature Ensemble Net (AE-FENet): a deep feature ensemble framework that uses the unsupervised autoencoder to conduct the feature transformation. Compared with the principle component analysis (PCA) technique adopted in the original Feature Ensemble Net (FENet), autoencoder can mine more exact features on incipient faults, which results in the better detection performance of AE-FENet. With same kinds of basic detectors, AE-FENet achieves a state-of-the-art average accuracy over 96% on faults 3, 9 and 15 in TEP, which represents a significant enhancement in performance compared to other methods. Plenty of experiments have been done to extend our framework, proving that DLNs can be utilized efficiently within this architecture.
Abstract (translated)
深度学习在故障检测领域表现出了巨大的威力。然而,对于初始故障(幅值较小)的检测,当前的深度学习网络(DLNs)的检测性能并不令人满意。即使利用先前的故障信息,DLNs也无法成功检测田纳西东部过程(TEP)中的第3、9和15个故障。这些故障尤其难以检测,在故障检测领域缺乏有效的检测技术。在这项工作中,我们提出了自编码器辅助特征集成网络(AE-FENet): 一个深度特征集成框架,利用无监督的自动编码器进行特征转换。与原始特征集成网络(FENet)中采用的原则成分分析(PCA)技术相比,自动编码器可以挖掘更多的精确特征,从而使AE-FENet在初始故障检测方面的性能更佳。与相同类型的基本检测器相比,AE-FENet在TEP中的第3、9和15个故障上实现了超过96%的顶级平均准确率,这表明与其他方法相比,性能有了显著的提高。已经进行了很多实验来扩展我们的框架,证明DLNs可以有效地利用这种架构。
URL
https://arxiv.org/abs/2404.13941