Abstract
By monitoring a hydraulic system using artificial intelligence, we can detect anomalous data in a manufacturing workshop. In addition, by analyzing the anomalous data, we can diagnose faults and prevent failures. However, artificial intelligence, especially deep learning, needs to learn much data, and it is often difficult to get enough data at the real manufacturing site. In this paper, we apply augmentation to increase the amount of data. In addition, we propose real-time monitoring based on a deep-learning model that uses convergence of a convolutional neural network (CNN), a bidirectional long short-term memory network (BiLSTM), and an attention mechanism. CNN extracts features from input data, and BiLSTM learns feature information. The learned information is then fed to the sigmoid classifier to find out if it is normal or abnormal. Experimental results show that the proposed model works better than other deep-learning models, such as CNN or long short-term memory (LSTM).
Highlights
Mechanical fault diagnosis and condition monitoring using artificial intelligence technology are an significant part of the smart factory and fourth industrial revolution [1]
The proposed model used in the experiment is a model that combines convolutional neural network (CNN) and long short-term memory (LSTM), with the attention mechanism added
The model consisted of two one-dimensional convolutional layers, one maxpooling layer, one bidirectional long short-term memory network (BiLSTM) layer, the attention mechanism, and one fully connected layer of 200 units
Summary
Mechanical fault diagnosis and condition monitoring using artificial intelligence technology are an significant part of the smart factory and fourth industrial revolution [1]. We increased data by applying jittering and scaling techniques to existing data [4]. Among deep-learning algorithms, convolutional neural networks (CNNs) have been used for many classification problems and have worked well [5,6]. Sensors 2020, 20, 7099 method having an algorithm that combines CNN and bidirectional long short-term memory networks (BiLSTMs) [9] to monitor the condition of hydraulic systems. This research proposes a method of effectively inflating data by reinterpreting Jittering and Scaling, which are augmentation techniques commonly used in the vision domain, and applying them to 1D time series data. This research contributes to solving the data shortage problem by making the small-scale dataset including hydraulic system data useful for real time monitoring in industrial or manufacturing sites.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
