Machine Learning Model for Liquid Discharge Head Image Quality Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing liquid discharge systems, such as ink jet printers, face challenges in determining the impact of discharge abnormalities on image quality, as current methods struggle to accurately assess how abnormalities like ink thickening or bubble mixing affect printed images.
Innovation Solution
A machine learning method is employed to obtain discharge parameters and image quality determination results, learning a relationship between these factors to generate a model that estimates the quality of printed images, thereby improving the detection of discharge abnormalities and image quality assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If machine learning is used to learn the relationship between discharge parameters and image quality, then image quality assessment accuracy is improved, but system complexity increases
Solution Approach 1:
The patent introduces a machine learning model as an intermediary component that processes discharge parameters and predicts image quality. This mediator learns the complex relationship between discharge conditions and image quality outcomes, enabling accurate assessment without directly implementing complex measurement systems. The model acts as a bridge between simple parameter measurement and complex quality evaluation.
2Measurement precision
If discharge abnormality detection is enhanced through machine learning, then detection accuracy is improved, but processing time increases
Solution Approach 1:
The machine learning model is trained in advance on a large dataset of discharge parameters and corresponding image quality outcomes. This preliminary training phase allows the model to learn complex patterns and relationships beforehand. During actual operation, the pre-trained model can quickly predict image quality and detect abnormalities without performing complex real-time analysis, thus reducing processing time while maintaining high detection accuracy.
3Manufacturing precision
If the relationship between discharge parameters and image quality is learned using machine learning, then discharge condition optimization is improved, but computational resources increase
Solution Approach 1:
The patent replaces complex computational optimization methods with a machine learning model that has been trained to directly predict image quality outcomes. Instead of performing intensive real-time computational optimization to determine optimal discharge conditions, the pre-trained model provides rapid predictions that guide discharge parameter adjustment. This substitution reduces the computational burden during operation while maintaining optimization effectiveness.
Data Source
AI summary
A machine learning method includes: obtaining a discharge parameter on discharging performed by a liquid discharge head discharging liquid; obtaining an image quality determination result produced by determining a printed image quality; and learning the relationship between the discharge parameter and the image quality determination result. Also, the discharge parameter desirably includes a discharge state value indicating a discharge state of the liquid discharge head and a discharge result value indicating a discharge result of the liquid discharged on a print medium from the liquid discharge head. The machine learning method includes learning the relationship between the discharge state value and the discharge result value, and the image quality determination result.