Gravure printing, which is a roll-to-roll printed electronics system suitable for high-speed patterning of functional layers have advantages of being applied to flexible webs in large areas. As each of the printing procedure from inking to doctoring followed by ink transferring and setting influences the quality of the pattern geometry, it is necessary to detect and diagnose factors causing the printing defects beforehand. Data acquisition with three triaxial acceleration sensors for fault diagnosis of four major defects such as doctor blade tilting fault was obtained. To improve the diagnosis performances, optimal sensor selection with Sensor Data Efficiency Evaluation, sensitivity evaluation for axis selection with Directional Nature of Fault and feature variable optimization with Feature Combination Matrix method was applied on the raw data to form a Smart Data. Each phase carried out on the raw data progressively enhanced the diagnosis results in contents of accuracy, positive predictive value, diagnosis processing time, and data capacity. In the case of doctor blade tilting fault, the diagnosis accuracy increased from 48% to 97% with decreasing processing time of 3640 s to 16 s and the data capacity of 100 Mb to 5 Mb depending on the input data between raw data and Smart Data.

A roll-to-roll manufacturing system performs printing and coating on webs to mass-produce large-area functional films. The functional film of a multilayered structure is composed of layers with different components for performance improvement. The roll-to-roll system is capable of controlling the geometries of the coating and printing layers using process variables. However, research on geometric control using process variables is limited to single-layer structures only. This study entails the development of a method to proactively control the geometry of the upper coated layer by using the lower-layer coating process variable in the manufacture of a double-coated layer. The correlation between the lower-layer coating process variable and upper coated layer geometry was examined by analyzing the lower-layer surface roughness and spreadability of the upper-layer coating ink. The correlation analysis results demonstrate that tension was the dominant variable in the upper coated layer surface roughness. Additionally, this study found that adjusting the process variable of the lower-layer coating in a double-layered coating process could improve the surface roughness of the upper coating layer by up to 14.9%.

Roll-to-roll systems that include rotary components such as driven rolls and idle rollers have significant potential for application in fabrication of flexible functional devices. They are inexpensive, mass producible, and environmentally friendly; however, even minor defects in their component bearings can render them susceptible to severe damage, which necessitates accurate diagnoses of bearing quality. The main steps in machine learning for fault diagnosis include feature extraction and selection. In the case of high-dimensional feature data, critical study is required to identify the best feature combination for proper diagnosis. Thus, this study aims to develop a method that extracts fault characteristics of a bearing from the measured signal and qualify the bearing according to the Mahalanobis distances and differences in density between normal and faulty data groups. Features extracted from vibration data collected from industry-scale roll-to-roll systems and CWRU data were trained with principal component analysis, other modern feature selection techniques, and the proposed algorithm-based eight classifiers. Compared with the existing algorithm, the accuracy increased by up to 9.24%, the training time decreased by up to 34.46%, and the number of features to obtain the maximum accuracy decreased by up to 59.92%. Thus, the proposed algorithm provides an effective and time-efficient approach to improve the accuracy of fault diagnosis of rotary components.

Fault diagnosis systems are used to improve the productivity and reduce the costs of the manufacturing process. However, the feature variables in existing systems are extracted based on the classification performance of the final model, thereby limiting their applications to models with different conditions. This paper proposes an algorithm to improve the characteristics of feature variables by considering the cutting conditions. Regardless of the frequency band, the noise of the measurement data was reduced through an oversampling method, setting a window length through a cutter sampling frequency, and improving its sensitivity to shock signal. An experiment was subsequently performed to confirm the performance of the model. Using normal and wear tools on AI7075 and SM45C, the diagnosis accuracies were 97.1% and 95.6%, respectively, with a reduction of 85% and 83%, respectively, in the time required to develop a diagnosis model. Therefore, the proposed algorithm reduced the model computation time and developed a model with high accuracy by enhancing the characteristics of the feature variable. The results of this study can contribute significantly to the establishment of a high-precision monitoring system for various processing processes.

No abstract