No abstract

Abstract:In modern manufacturing systems and industries, more and more research efforts have been made in developing effective machine health monitoring systems. Among various machine health monitoring approaches, data-driven methods are gaining in popularity due to the development of advanced sensing and data analytic techniques. However, considering the noise, varying length and irregular sampling behind sensory data, this kind of sequential data cannot be fed into classification and regression models directly. Therefore, previous work focuses on feature extraction/fusion methods requiring expensive human labor and high quality expert knowledge. With the development of deep learning methods in the last few years, which redefine representation learning from raw data, a deep neural network structure named Convolutional Bi-directional Long Short-Term Memory networks (CBLSTM) has been designed here to address raw sensory data. CBLSTM firstly uses CNN to extract local features that are robust and informative from the sequential input. Then, bi-directional LSTM is introduced to encode temporal information. Long Short-Term Memory networks (LSTMs) are able to capture long-term dependencies and model sequential data, and the bi-directional structure enables the capture of past and future contexts. Stacked, fully-connected layers and the linear regression layer are built on top of bi-directional LSTMs to predict the target value. Here, a real-life tool wear test is introduced, and our proposed CBLSTM is able to predict the actual tool wear based on raw sensory data. The experimental results have shown that our model is able to outperform several state-of-the-art baseline methods.

No abstract

No abstract

Advances in cloud computing reshape the manufacturing industry into dynamically scalable, on-demand service oriented, and highly distributed cost-efficient business model. However it also poses challenges such as reliability, availability, adaptability, and safety on machines and processes across spatial boundaries. To address these challenges, this paper investigates a cloud-based paradigm of predictive maintenance based on mobile agent to enable timely information acquisition, sharing and utilization for improved accuracy and reliability in fault diagnosis, remaining service life prediction, and maintenance scheduling. In the new paradigm, a low-cost cloud sensing and computing node is firstly developed with embedded Linux operating system, mobile agent middleware, and open source numerical libraries. Information sharing and interaction is achieved by mobile agent to distribute the analysis algorithms to cloud sensing and computing node to locally process data and share analysis results. Comparing to the commonly used clientserver paradigm, the mobile agent approach enhances the system flexibility and adaptability, reduces raw data transmission, and instantaneously responds to dynamic changes of operations and tasks. Finally, the presented cloud-based paradigm of predictive maintenance is validated on a motor tested system.