Seung-Jun Shin

As the demand for precision in the manufacturing industry grows, Digital Twin (DT) technology is gaining attention for its potential to enhance equipment performance and process reliability. However, existing research has primarily focused on specific stages of design or operation, leaving a gap in the literature concerning DT models that can be utilized throughout the entire equipment lifecycle. To address this gap, this study proposes a method for developing a DT that employs a consistent Finite Element (FE) model across all phases of the equipment lifecycle. We utilized actual measurement data to ensure high fidelity in the FE model of previous-generation equipment, which we refer to as the Pre-DT. This Pre-DT was instrumental in improving design during the new equipment development phase. Additionally, the DT model was implemented to predict equipment status in real time using the Reduced-Order Model (ROM) method, functioning as a virtual sensor during operation. This approach was applied to the equipment development process, aligned with the asset lifecycle concept of RAMI 4.0, and was tested on an MLCC cutting equipment to validate its effectiveness.

The rapid expansion of electric vehicles and energy storage systems requires lithium-ion batteries with simultaneously high energy density and reliability. In this regard, the joint between the copper (Cu) current collector and the Cu tab becomes a critical determinant to represent cell performance and safety. However, Cu exhibits low absorptivity under infrared ray lasers and high thermal conductivity. These material characteristics disturb stable keyhole formation and molten pool flow, which result in weld defects. Relevant studies proposed high-power green and blue lasers, beam shaping, and spatial beam oscillation; however, they remain limited to provide the fundamental process knowledge enabling stable and persistent use of infrared ray lasers, which have been widely installed in production lines. This study presents the empirical analysis to characterize laser welded joints between Cu tabs and multi-layered foils in the infrared ray laser. In this study, welding tests are conducted on a joint of a Cu tab and multi-layered foil using a TruDisk 8000 infrared disk laser. Design factors are tab thickness (0.4, 0.5, 0.6 mm), foil thickness (5, 6, 8 ㎛), and the number of foil layers (5, 10, 20). Weld performance is evaluated through bead appearance inspections and tensile shear strength (TSS) tests. The maximum TSS for 5 layer stacks is measured, wherein a peak strength of 10.79 kgf is achieved with a combination of a 0.5 mm tab and 6 ㎛ foil on a 20-layer stack. The experimental results provide fundamental knowledge to correlate design factors with the joint strength in Cu foil-tab welding assembly.

This study presents a preventive maintenance methodology to predict the remaining useful life (RUL) of mechanical systems and determine cost-effective replacement schedules. The approach integrates machine learning for RUL prediction, Weibull distribution for reliability analysis, and a block replacement model with minimal repair to optimize preventive maintenance. Many existing studies rarely incorporate RUL prediction results into determining optimal maintenance actions due to the high uncertainty in RUL prediction. To address this, the proposed methodology emphasizes not stopping at the prediction stage but integrating RUL predictions into actionable maintenance strategies to reduce uncertainty and improve applicability in industrial contexts. A case study using the open CMAPSS dataset demonstrates the feasibility of the approach. The value of this study lies in proposing a methodology that not only utilizes prediction-based proactive outcomes instead of predefined replacement intervals but also integrates them with subsequent maintenance strategies, providing practical and cost-effective solutions for industrial applications.

Wire arc additive manufacturing (WAAM) has gained attention as a feasible process in large-scale metal additive manufacturing due to its high deposition rate, cost efficiency, and material diversity. However, WAAM induces a degree of uncertainty in the process stability and the part quality owing to its non-equilibrium thermal cycles and layer-by-layer stacking mechanism. Anomaly detection is therefore necessary for the quality monitoring of the parts. Most relevant studies have applied machine learning to derive data-driven models that detect defects through feature and pattern learning. However, acquiring sufficient data is time- and/or resource-intensive, which introduces a challenge to applying machine learning-based anomaly detection. This study proposes a multisource transfer learning method that generates anomaly detection models for balling defect detection, thus ensuring quality monitoring in WAAM. The proposed method uses convolutional neural network models to extract sufficient image features from multisource materials, then transfers and fine-tunes the models for anomaly detection in the target material. Stepwise learning is applied to extract image features sequentially from individual source materials, and composite learning is employed to assign the optimal frozen ratio for converging transferred and present features. Experiments were performed using a gas tungsten arc welding-based WAAM process to validate the classification accuracy of the models using low-carbon steel, stainless steel, and Inconel.

As the legislative pressure to reduce energy consumption is increasing, data analysis of power consumption is critical in the production planning of manufacturing facilities. In previous studies, a machine, conducting a single continuous operation, has been mainly observed for power estimation. However, a modularized production line, which conducts complex discrete operations, is more like the actual factory system than an identical simple machine. During the information collection of such production lines, it is important to interpret and distinguish mixed signals from multiple machines to ensure that there is no reduction in the information quality due to noise and signal fusion and discrete events. A data pipeline from data collection from different sources to pre-processing, data conversion, synchronization, and deep learning classification to estimate the total power use of the future process plan is proposed herein. The pipeline also establishes an auto-labeled data set of individual operations that contributes to building power estimation models without manual data pre-processing. The proposed system is applied to a modular factory connected with machine controllers using standardized protocols individually and linked to a centralized power monitoring system. Specifically, a robot arm cell was investigated to evaluate the pipeline with the result of the power profile synchronized with the robot program.

This article reviews the state of the art of prediction and optimization for sequence-driven scheduling in job shop flexible manufacturing systems (JS-FMSs). The objectives of the article are to (1) analyze the literature related to algorithms for sequencing and scheduling, considering domain, method, objective, sequence type, and uncertainty; and to (2) examine current challenges and future directions to promote the feasibility and usability of the relevant research. Current challenges are summarized as follows: less consideration of uncertainty factors causes a gap between the reality and the derived schedules; the use of stationary dispatching rules is limited to reflect the dynamics and flexibility; production-level scheduling is restricted to increase responsiveness owing to product-level uncertainty; and optimization is more focused, while prediction is used mostly for verification and validation, although prediction-then-optimization is the standard stream in data analytics. In future research, the degree of uncertainty should be quantified and modeled explicitly; both holistic and granular algorithms should be considered; product sequences should be incorporated; and sequence learning should be applied to implement the prediction-then-optimization stream. This would enable us to derive data-learned prediction and optimization models that output accurate and precise schedules; foresee individual product locations; and respond rapidly to dynamic and frequent changes in JS-FMSs.