Abstract
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.
Highlights
Roll-to-roll processing is highly advantageous because it results in multiple functional layers of electronic circuitry printed on large flexible materials [1,2,3]
We find that the misalignment of the doctor blade, eccentricity of the nip and printing rolls, and non-uniform nip pressure can be indirectly measured via the vibration of the doctor blade, the nip roll, and the frames supporting the printing module
Doctor Blade Tilting Fault Diagnosis Based on Raw Data
Summary
Roll-to-roll processing is highly advantageous because it results in multiple functional layers of electronic circuitry printed on large flexible materials (i.e., web) [1,2,3]. To derive high-quality patterns with uniform thickness using the roll-to-roll gravure printing process, it is necessary to recognize and diagnose these. The aim is to recognize defects in advance and improve the diagnosis results by optimizing the training (input) data acquired from multiple sensors for the machine-learning fault diagnosis model. The smart data clearly show the characteristics of the vibration caused by the factors mentioned above, and they are selected from the raw dataset using the proposed methods in three phases to maximize performance efficiency. Most studies regarding fault diagnosis have shown methods of feature extraction to improve the results of machine learning from the data acquisition of sensors. Diagnosing the abnormal conditions with multiple sensors show promising results of fault diagnosis; the efficiency of diagnosis performance is without consideration. Related to Lee et al, this paper proposes strategies based on quantification methods to evaluate the efficiency of each phase [19]
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
