论文标题
基于人工神经网络的系统，用于使用微小的声音数据检测机器故障：案例研究
An artificial neural network-based system for detecting machine failures using tiny sound data: A case study
论文作者
论文摘要
为了提倡研究基于深度学习的机器故障检测系统的研究，我们基于微小的声音数据集提供了对拟议系统的案例研究。我们的案例研究调查了一个变量自动编码器（VAE），用于增强Valmet AB的小型钻头数据集。一个气门数据集包含134种声音，分为两类：从瓦尔梅特AB的钻机中记录的“异常”和“正常”，这是瑞典Sundsvall的一家公司，该公司为生物燃料的生产提供了设备和流程。使用深度学习模型检测到如此小的声音数据集上的故障训练通常不会成功。我们采用了VAE来通过合成原始声音的新声音来增加微小数据集中的声音数量。增强数据集是通过将这些综合声音与原始声音相结合来创建的。我们使用了一个高通滤波器，其通带频率为1000 Hz和一个具有22 \ kern的低通滤波器0.16667EM000 Hz，以在增强数据集中的预处理声音中，然后将其转换为MEL频谱图。然后使用这些MEL频谱图对预训练的2D-CNN ALEXNET进行训练。与使用原始的微型声音数据集进行训练预先训练的Alexnet时，使用增强声音数据集将CNN模型的分类结果提高了6.62 \％（94.12 \％（在增强数据集对87.5 \％培训时，在原始数据集中训练时接受培训时）。
In an effort to advocate the research for a deep learning-based machine failure detection system, we present a case study of our proposed system based on a tiny sound dataset. Our case study investigates a variational autoencoder (VAE) for augmenting a small drill sound dataset from Valmet AB. A Valmet dataset contains 134 sounds that have been divided into two categories: "Anomaly" and "Normal" recorded from a drilling machine in Valmet AB, a company in Sundsvall, Sweden that supplies equipment and processes for the production of biofuels. Using deep learning models to detect failure drills on such a small sound dataset is typically unsuccessful. We employed a VAE to increase the number of sounds in the tiny dataset by synthesizing new sounds from original sounds. The augmented dataset was created by combining these synthesized sounds with the original sounds. We used a high-pass filter with a passband frequency of 1000 Hz and a low-pass filter with a passband frequency of 22\kern 0.16667em000 Hz to pre-process sounds in the augmented dataset before transforming them to Mel spectrograms. The pre-trained 2D-CNN Alexnet was then trained using these Mel spectrograms. When compared to using the original tiny sound dataset to train pre-trained Alexnet, using the augmented sound dataset enhanced the CNN model's classification results by 6.62\%(94.12\% when trained on the augmented dataset versus 87.5\% when trained on the original dataset).
