Digital‐twin assisted: Fault diagnosis using deep transfer learning for machining tool condition

Abstract

The rapid development forms a new transition of information technologies to offer an intelligent manufacturing. The manufacturer has revolutionized the stages of product lifecycle including process planning and maintenance for the early detection of potential system failures and proactive management. Technological advancements including big data, the cloud, and the Internet of Things have applied digital‐twin for industrial practice. It has low‐power wireless‐enabled devices to play a vital role in various industrial automation systems such as industry logistics, portable equipment, and intelligent wireless monitoring. It is evident that industrial manufacturers are nowadays aiming to transform the machine into fully automated systems that not only control the operation of the equipment but also try to meet the demand of future markets effectively. One of the challenging issues in the automation of the machinery process is the deployment of reliable systems to analyze the machinery condition such as fault diagnosis. Thus, this article proposes a digital‐twin‐assisted fault diagnosis using deep transfer learning to analyze the operational conditions of machining tools. Moreover, this proposed system has developed an intelligent tool‐holder that integrates a k‐type thermocouple and cloud data acquisition system over the WiFi module. The analytical study proves that this intelligent tool‐holder provides better accuracy to demonstrate the optimization of milling and drilling operations of cutting tools.

Digital Twin for Integration of Design-Manufacturing-Maintenance: An Overview

“…Luo et al [100,172,173] established a multi-domain unified modeling approach for digital twins, explored the mapping strategy between physical and digital spaces, and proposed a self-prediction and self-maintenance method for digital twins. If machine tools can be built with a digital twin in virtual space that can monitor the health status and operating history of machine tools at any time, unnecessary losses caused by unexpected events can be greatly avoided [101,[174][175][176][177]. Scaglioni et al [98] developed a dynamic model of the Mandelli M5 machine tool.…”

Usage of GAMS-based Digital Twins and Clustering to Improve Energetic Systems Control

“…Accurate models aren't always available for the system of which we want to build a DT for its operating conditions. The problem of the availability of data could possibly be solved using Generative Adversarial Networks (GANs) [18][19][20] and/or transfer learning [21][22][23][24][25], but the technology is still maturing. For this study, General Additive Models (GAMs) are used as they are a category of ML that requires few to none hyperparameters tuning to approximates nonlinear relationships with a combination of linear formulation of a series of smoothening functions [26].…”

CNC Machine Tool Fault Diagnosis Integrated Rescheduling Approach Supported by Digital Twin-Driven Interaction and Cooperation Framework

“…At the service stage, DT can diagnosis and predict equipment faults based on real-time status data. Based on deep transfer learning algorithm to realize digital twin-assist fault diagnosis for analyzing the operating status of machine tools [20]. Xiong et al [21] proposed a digital twin-driven predictive maintenance framework that combined a datadriven with LSTM model to perform predictive maintenance on aero-engine, and the experimental results showed that the method had high predictive accuracy.…”