Printing Apparatus Machine-Learned Transport Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing printing apparatuses face challenges in maintaining accurate print length control due to aging deterioration of rollers, medium characteristics, and environmental changes, leading to issues like discontinuous marks or overlapping prints.
Innovation Solution
A printing apparatus equipped with a machine-learned model that optimizes the transportation mechanism's setting values, such as pressure, tensile force, and attachment force, using reinforcement learning to maintain the print length close to a reference, even with changes in environment and medium type.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a tensile force applied to a printing medium is controlled as in JP-A-2009-256095, then print length control is improved, but precision deteriorates due to aging deterioration of rollers, characteristics of printing medium, and environment of usage
Solution Approach 1:
The patent implements a feedback mechanism where the actual print length is measured and compared with the target print length, and the setting value of the transportation mechanism is automatically adjusted based on the deviation. This closed-loop control system compensates for changes in roller characteristics, printing medium properties, and environmental conditions, maintaining reliable print length control over time without manual recalibration.
Solution Approach 2:
The printing apparatus performs self-adjustment by automatically modifying its own transportation mechanism settings based on measured print length deviations. The system uses its own operational data to learn and adapt optimal setting values, eliminating the need for external intervention or manual recalibration due to aging or environmental changes.
2Manufacturing precision
If fixed setting values are used for the transportation mechanism, then device complexity is reduced, but manufacturing precision deteriorates due to inability to adapt to environmental changes and medium characteristics
Solution Approach 1:
The patent dynamically changes the setting parameters of the transportation mechanism based on measured print length deviations. The system adjusts parameters such as transportation speed, acceleration, and tension forces in response to environmental conditions, printing medium characteristics, and roller aging, maintaining high print length accuracy without requiring complex mechanical structures.
3Adaptability or versatility
If manual adjustment of transportation mechanism settings is performed, then adaptability to different conditions is improved, but productivity decreases due to time-consuming calibration
Solution Approach 1:
The printing apparatus automatically performs the adaptation process by measuring print length deviations and adjusting its own transportation mechanism settings without human intervention. This self-learning capability eliminates time-consuming manual calibration while maintaining adaptability to changing conditions such as roller aging, environmental variations, and different printing medium characteristics.
Solution Approach 2:
The system continuously monitors print length and performs incremental adjustments to the transportation mechanism settings during normal operation. This continuous adaptation process ensures the system remains optimized without requiring periodic shutdowns for manual recalibration, maintaining both adaptability and productivity.
Data Source
AI summary
A printing apparatus provided with a transportation mechanism for a printing medium includes: a storage configured to store a machine-learned model that outputs a setting value of the transportation mechanism for causing, based on state variables including a print length as a length of a print product printed on the printing medium, the print length to be close to a reference; and a processor configured to perform printing by controlling the transportation mechanism in accordance with the setting value acquired based on the machine-learned model.