Image Forming System Control Parameter Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The existing image forming systems face challenges in accurately setting control parameters for unregistered sheet types and struggle to optimize numerous control parameters in real-time during high-speed operations, leading to decreased productivity and potential image quality issues.

Innovation Solution

The system employs two distinct methods for determining control parameters: one based on real-time physical property measurements using a machine learning model and another based on pre-defined sheet types, allowing for dynamic selection between these methods to optimize control parameter settings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If control parameters are uniformly optimized based on data of a large number of sheet physical properties, then manufacturing precision is improved, but productivity deteriorates due to large amount of calculation required

Engineering Contradiction:

Improvecontrol parameter optimization accuracyVSAvoidimage forming speed

Core Design Contradiction:

Manufacturing precisionVSProductivity

Solution Approach 1:

The patent segments the control parameter optimization process into two distinct approaches: a machine learning-based method for rapid parameter determination and a statistical method for comprehensive optimization. This segmentation allows the system to handle different aspects of parameter optimization separately, maintaining both speed and accuracy without requiring uniform optimization of all parameters simultaneously.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent replaces traditional mechanical calculation methods with machine learning models to determine control parameters. The machine learning model processes sheet physical property data and outputs optimized control parameters much faster than conventional statistical methods, enabling real-time parameter adjustment during high-speed image forming operations while maintaining optimization accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If control parameters are set based on pre-registered sheet types, then ease of operation is improved, but adaptability deteriorates for unregistered sheet types

Engineering Contradiction:

Improvecontrol parameter setting simplicityVSAvoidsupport for unregistered sheet types

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

The patent implements a self-service mechanism where the machine learning model automatically determines control parameters based on measured sheet physical properties, eliminating the need for manual registration of sheet types. The system serves itself by autonomously adapting to new sheet types through machine learning inference, maintaining ease of operation while significantly improving adaptability to unregistered materials.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent changes the approach from fixed, pre-registered sheet type parameters to dynamic parameters derived from actual measured physical properties. By using machine learning to map measured properties to control parameters, the system can adapt to any sheet type regardless of whether it is pre-registered, while maintaining simple operation through automated parameter determination.

Inventive Principle:

Principle #35Parameter changes

3Device complexity

If multiple control parameters are determined using the same method, then device complexity is reduced, but manufacturing precision deteriorates due to inability to optimize each parameter individually

Engineering Contradiction:

Improvecontrol parameter determination structureVSAvoidcontrol parameter optimization accuracy

Core Design Contradiction:

Device complexityVSManufacturing precision

Solution Approach 1:

The patent segments the control parameter determination into two functional components: a machine learning-based determination method for rapid parameter extraction and a statistical-based optimization method for comprehensive parameter tuning. This segmentation allows each parameter to be optimized individually through the statistical method while maintaining overall system simplicity through the automated machine learning framework.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces dynamic flexibility in the control parameter determination process by allowing selection between different determination methods based on specific requirements. The system can dynamically switch between machine learning-based rapid determination and statistical-based comprehensive optimization, enabling individual parameter optimization without increasing overall device complexity.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentEP4528384A1Image forming system, control parameter setting method, and program

Publication Date: 2025.03.26 KONICA MINOLTA INC

Figure 1
Figure 2A~2B
Figure 3~4

AI summary

An image forming system (U) includes, a first control parameter determination means (301) that determines a value of a control parameter for sheet processing; a second control parameter determination means (301) that determines the value of the control parameter for the sheet processing by a method different from the first control parameter determination means; and a selection means configured to be capable of setting which of the first control parameter determination means and the second control parameter determination means is used to determine the value of at least one of a plurality of control parameters.