Towards scalable and reusable predictive models for cyber twins in manufacturing systems

Abstract

Smart factories are intelligent, fully-connected and flexible systems that can continuously monitor and analyse data streams from interconnected systems to make decisions and dynamically adapt to new circumstances. The implementation of smart factories represents a leap forward compared to traditional automation. It is underpinned by the deployment of cyberphysical systems that, through the application of Artificial Intelligence, integrate predictive capabilities and foster rapid decision-making. Deep Learning (DL) is a key enabler for the development of smart factories. However, the implementation of DL in smart factories is hindered by its reliance on large amounts of data and extreme computational demand. To address this challenge, Transfer Learning (TL) has been proposed to promote the efficient training of models by enabling the reuse of previously trained models. In this paper, by means of a specific example in aluminium can manufacturing, an empirical study is presented, which demonstrates the potential of TL to achieve fast deployment of scalable and reusable predictive models for Cyber Manufacturing Systems. Through extensive experiments, the value of TL is demonstrated to achieve better generalisation and model performance, especially with limited datasets. This research provides a pragmatic approach towards predictive model building for cyber twins, paving the way towards the realisation of smart factories.

Twin tools for intelligent manufacturing: a case study

“…While the simulator represents the plant that works in ideal reference conditions, the digital twin follows the real trend of production and any misalignment of the two requires reflections on the causes and the definition of corrective actions to improve the plant and schedule proactive maintenance or even resource replacement. In this context, Giannetti and Essien (2021) and Wang et al (2021) propose predictive models for digital twins in order to address the dynamic and often stochastic nature of time series signals. The information on the misalignment can be evaluated on different levels and, in our case, we preferred to refer to key performance indicators that the industry has considered strategic for production.…”

Prediction Model of Grain Mold Probability Based on Naive Bayes Algorithm

“…The working principle of the electronic nose is similar to that of the human nose. The volatile substances in the gas enter the sensor array that simulates the olfactory cells in the nose, which will interact with the sensor array and generate electrical signals; the electrical signals are converted into numerical values through an electronic interface into signal processing; and then the recorded data are analyzed for recognition according to a data statistical system that simulates brain functions [13].…”