Samara National Research University Named after S.P. Korolev, Moskovskoye Shosse 34, 443086 Samara, Russia.
Image Processing Systems Institute of the RAS-Branch of the Federal Scientific Research Centre "Crystallography and Photonics" of the Russian Academy of Sciences, Molodogvardeyskaya 151, 443001 Samara, Russia.
Sensors (Basel). 2021 Jun 27;21(13):4410. doi: 10.3390/s21134410.
This paper examines the effectiveness of neural network algorithms for hydraulic system fault detection and a novel neural network architecture is suggested. The proposed gated convolutional autoencoder was trained on a simulated training set augmented with just 0.2% data from the real test bench, dramatically reducing the time needed to spend with the actual hardware to build a high-quality fault detection model. Our fault detection model was validated on a test bench and showed accuracy of more than 99% of correctly recognized hydraulic system states with a 10-s sampling window. This model can be also leveraged to examine the decision boundaries of the classifier in the two-dimensional embedding space.
本文研究了神经网络算法在液压系统故障检测中的有效性，并提出了一种新的神经网络架构。所提出的门控卷积自动编码器在模拟训练集上进行训练，仅使用实际测试台的 0.2%数据进行扩充，大大减少了在实际硬件上花费的时间，从而构建了高质量的故障检测模型。我们的故障检测模型在测试台上进行了验证，在 10 秒的采样窗口下，液压系统状态的正确识别准确率超过 99%。该模型还可用于检查分类器在二维嵌入空间中的决策边界。
