Research on the membrane fouling diagnosis of MBR membrane module based on ECA-CNN. Issue 3 (June 2022)

• Record Type: Journal Article
• Authors: Shi, Yaoke; Wang, Zhiwen; Du, Xianjun; Ling, Guobi; Jia, Wenchao; Lu, Yanrong
• Is Part Of: Journal of environmental chemical engineering. Volume 10:Issue 3(2022)
• Publication Date: 2022-06
• Subjects: Membrane fouling -- Convolutional neural network -- Attention mechanism -- Feature extraction -- Fault diagnosis; Chemical engineering -- Environmental aspects -- Periodicals; Environmental engineering -- Periodicals; Chemical engineering -- Environmental aspects; Environmental engineering; Periodicals; 660.0286
• DOI: 10.1016/j.jece.2022.107649
• Languages: English
• ISSNs: 2213-2929

Abstract

Abstract: In order to make it easier to extract fault features, reduce model complexity and improve the accuracy of membrane fouling diagnosis on membrane modules, a membrane module fault diagnosis method based on attention mechanism and convolutional neural network (ECA-CNN) is proposed in this study. First, the convolution kernel is used to extract the image features of the input layer. At the same time, a rectified linear unit (ReLU) is connected after each convolution layer, and a batch normalization layer (BN) is added to solve the problem of internal co variate shift, so as improving the expression ability of nonlinear models. Secondly, in batches after the first layer, add the attention mechanism module (ECA), extract the important features and connect to the pooling layer, reduce the network calculation complexity, and improve the accuracy and efficiency of the network. Finally, the membrane module operating data is used as the research object to conduct fault diagnosis experiments as verification. This method can improve the diagnosis accuracy to a large extent, in which the highly difficult fault classification and localization can be accomplished. Besides, the effluent quality from the membrane water treatment system may be improved with this method with less energy consumption, paving the theoretical foundation for actual production. Graphical Abstract: ga1 Highlights: ECA-CNN model improves the diagnostic accuracy and reduces the risk of over fitting. Reduce the complexity of the model and improve the noise resistance of the network. ECA-CNN model can diagnose membrane module fouling more accurately and faster.