Image Formation Apparatus for Fast Multi-Color Misregistration Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional printing apparatuses face challenges in accurately predicting and correcting misregistration between single-color images due to factors like roller rotation errors and material expansion/contraction, which often results in reduced print quality, as the computation required for precise prediction takes too long.
Innovation Solution
An image formation apparatus that uses a first reasoner to infer misregistration based on all measurement data, followed by a second reasoner selecting key measurement items based on contribution to reduce the number of items used, thereby inferring misregistration quickly and accurately, and an ejection controller to correct ink ejection timing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of measurement items is increased to improve prediction accuracy, then the accuracy of misregistration prediction is improved, but the computation time increases making it difficult to correct ejection timing in time
Solution Approach 1:
The patent extracts and selects only the most important measurement items that contribute significantly to misregistration prediction. The selection unit identifies key measurement items from among multiple measurement items based on their contribution to prediction accuracy, thereby reducing the number of items used in computation while maintaining prediction accuracy within a predetermined threshold.
Solution Approach 2:
The patent changes the parameter of measurement item quantity by dynamically selecting a subset of measurement items. The selection unit adjusts which measurement items are used based on their contribution to prediction accuracy, transforming the approach from using all measurement items to using only the necessary subset, thus reducing computation time while preserving accuracy.
2Measurement precision
If all measurement items are used to infer misregistration, then the prediction accuracy is improved, but the device complexity and computation load increase
Solution Approach 1:
The patent extracts only the essential measurement items needed for accurate misregistration prediction. The selection unit identifies and extracts key measurement items from the full set of measurement items, reducing the complexity of the inference process while maintaining prediction accuracy within acceptable thresholds.
Solution Approach 2:
The patent applies partial action by using only a subset of measurement items rather than all available items. The selection unit determines the minimum necessary set of measurement items that provide sufficient prediction accuracy, avoiding the excessive computation that would result from processing all measurement items.
Data Source
AI summary
A technique for predicting the amount of misregistration accurately in a short time is provided. A measurement part acquires measurement data for each of a plurality of measurement items about a state of printing paper. A first reasoner infers the amount of misregistration between a first image formed by an ejection head and a second image formed by an ejection head, based on the measurement data on the plurality of measurement items. A second reasoner selects some measurement items from the plurality of measurement items, based on a contribution of each measurement item to the amount of misregistration inferred by the first reasoner. The second reasoner infers the amount of misregistration using the measurement data on the selected measurement items.