Abstract
Condition monitoring of industrial equipment, combined with machine learning algorithms, may significantly improve maintenance activities on modern cyber-physical production systems. However, data of proper quality and of adequate quantity, modeling both good operational conditions as well as abnormal situations throughout the operational lifecycle, are required. Nevertheless, this is difficult to acquire in a non-destructive approach. In this context, this study investigates an approach to enable a transition from preventive maintenance activities, that are scheduled at predetermined time intervals, into predictive ones. In order to enable such approaches in a cyber-physical production system, a deep learning algorithm is used, allowing for maintenance activities to be planned according to the actual operational status of the machine and not in advance. An autoencoder-based methodology is employed for classifying real-world machine and sensor data, into a set of condition-related labels. Real-world data collected from manufacturing operations are used for training and testing a prototype implementation of Long Short-Term Memory autoencoders for estimating the remaining useful life of the monitored equipment. Finally, the proposed approach is evaluated in a use case related to a steel industry production process.
Highlights
Digitization in production systems mandates the use of new Information and Communication Technology (ICT) systems in order to improve performance in manufacturing.the enormous amount of information generated and gathered by manufacturingICT systems as well as Internet of Things (IoT) devices installed on the factory floor usually remains underutilized
This study discussed a deep learning approach based on Long Short-Term Memory (LSTM)-autoencoders for assessing the condition of a hot rolling milling machine and estimating its remaining useful life (RUL) value
Real-world data were used for training and testing a prototype implemented in Python
Summary
Digitization in production systems mandates the use of new Information and Communication Technology (ICT) systems in order to improve performance in manufacturing. The evolution of embedded systems and sensors in conjunction with the ever-increasing digitization of modern shop-floors has enabled the generation of an enormous volume of digital information The analysis of those data may reveal underlying patterns not visible to the human operator and may support proactive decision making [8]. Insight can be created on the actual condition of production equipment, through the adoption of data-driven techniques for condition monitoring and assessment of its operational condition, as discussed in Entezami et al [9] and Chuang et al [10] This can enable a transition from time-based preventive maintenance to predictive maintenance (PdM) or a combination of them. The development of a prototype method and the implementation of a software prototype have shown that the proposed method can provide information regarding the machine’s health without requiring any specialization and additional skills from the industry operators
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
