ML Control Factor Prediction for Real-Time Manufacturing Adjustment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The secondary battery manufacturing process is prone to inconsistencies and errors due to worker input, leading to quality issues and production interruptions, as process conditions are difficult to adjust accurately and in real-time.

Innovation Solution

A system and method using machine learning to predict control factors for manufacturing facilities, incorporating a model execution management unit, storage unit, and communication unit to manage and execute facility control factor prediction models, ensuring accurate and real-time process adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If workers directly enter process conditions into manufacturing facilities, then the system is simple to operate, but the manufacturing precision and quality consistency deteriorate due to human error and fatigue

Engineering Contradiction:
Improveease of operationVSAvoidmanufacturing precision
Core Design Contradiction:
Ease of operationVSManufacturing precision

Solution Approach 1:

The system enables self-service by automatically determining optimal process conditions through the determination unit, which uses machine learning models to generate control factor recommendations without requiring worker intervention. The system serves itself by autonomously optimizing manufacturing parameters based on real-time data, eliminating human error while maintaining operational simplicity

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical system of manual worker input with an automated information processing system. The determination unit substitutes human decision-making with machine learning algorithms that process data and generate control recommendations, thereby eliminating human fatigue and error while improving manufacturing precision

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If workers directly adjust process conditions in real-time, then the system maintains simplicity, but the reliability deteriorates because workers cannot respond immediately to changes

Engineering Contradiction:
Improveease of operationVSAvoidreliability
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The system performs self-service by automatically monitoring process conditions and generating real-time control recommendations through the determination unit. The machine learning models continuously process incoming data and adjust control factors without human intervention, ensuring immediate response to process changes and maintaining high reliability

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system implements continuous feedback loops where the determination unit receives real-time process data, analyzes it through machine learning models, and generates control recommendations that are fed back to the manufacturing facility. This closed-loop feedback mechanism enables immediate response to process changes, improving reliability while maintaining operational simplicity

Inventive Principle:
Principle #23Feedback

3Manufacturing precision

If multiple prediction models are used for different manufacturing facilities, then the manufacturing precision improves, but the device complexity increases

Engineering Contradiction:
Improvemanufacturing precisionVSAvoiddevice complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The determination unit serves as a universal platform that can execute multiple different prediction models for various manufacturing facilities. Rather than requiring separate systems for each facility, the single determination unit is designed to handle diverse machine learning models, making the system multi-functional and reducing overall complexity while maintaining high precision across different facilities

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system segments the prediction functionality into separate machine learning models that can be independently developed and maintained, while the determination unit provides a unified interface. This segmentation allows each model to be optimized for specific facilities without increasing overall system complexity, as the determination unit manages and coordinates multiple specialized models

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP4686986A1Method and system for predicting control factors for manufacturing facilities based on machine learning
Publication Date: 2026.02.04 SAMSUNG SDI CO LTD
  • EP4686986A1 patent drawingFigure 1
  • EP4686986A1 patent drawingFigure 2
  • EP4686986A1 patent drawingFigure 3

AI summary

A system for predicting control factors for a manufacturing facility, performed by at least one processor, includes: a model execution management unit configured to execute or manage one or more facility control factor prediction models trained to predict control factors for a manufacturing facility received from a prediction model providing system, a storage unit configured to store data associated with the facility control factor prediction models, and a communication unit configured to receive an independent factor of one of a plurality of manufacturing facilities from a facility control system, and configured to transmit a control factor predicted value calculated by one of the one or more facility control factor prediction models based on the independent factor to the facility control system.