Dry Electrode Mixing Conditions from Dispersion Image Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The dry electrode manufacturing process faces challenges in controlling process conditions due to the difficulty in optimizing mixing conditions, which can vary with equipment size and material amounts.
Innovation Solution
A system is developed that includes a microscope for measuring dispersion images of dry electrode mixtures and a computing apparatus for machine-learning these images. This system calculates a target mixing condition for a second dry electrode mixture based on learned data, optimizing the mixing process regardless of equipment size or material amounts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a dry process is used to manufacture electrodes without solvent, then energy density is increased and manufacturing time is reduced, but mixing condition control becomes very difficult
Solution Approach 1:
The patent applies parameter changes by using machine learning to determine optimal mixing parameters (mixing time, mixing speed, temperature, humidity) based on desired electrode properties. The system calculates specific mixing conditions that achieve target dispersion states, enabling precise control of mixing parameters in the dry process while maintaining high productivity.
Solution Approach 2:
The patent replaces traditional mechanical trial-and-error mixing optimization with an information-processing system. A computing apparatus uses machine learning models to calculate optimal mixing conditions, substituting empirical mechanical adjustment with computational determination of mixing parameters.
2Manufacturing precision
If mixing conditions are optimized for one equipment size and material amount, then mixing precision is improved, but adaptability to different equipment sizes and material amounts deteriorates
Solution Approach 1:
The patent implements universality through a machine learning system that can determine optimal mixing conditions for various equipment sizes and material amounts using a unified approach. The computing apparatus calculates mixing parameters applicable across different scales by considering the desired dispersion state as the common target, making the system universally applicable to different production scenarios.
Solution Approach 2:
The patent applies dynamics by making mixing parameters adjustable and adaptable based on specific process conditions. The machine learning model dynamically calculates optimal mixing time, speed, temperature, and humidity according to the particular equipment configuration and material quantity, allowing the system to adapt to changing conditions while maintaining mixing precision.
Data Source
AI summary
Disclosed is a dry electrode for secondary batteries. A system for calculating a mixing condition for a dry electrode includes a microscope configured to measure dispersion images of a first dry electrode mixture for each mixing condition, wherein an electrode active material, a conductive material, and a binder in the first dry electrode mixture are mixed by a mixer. A computing apparatus is configured to machine-learn the dispersion images of the first dry electrode mixture, to receive comparative dispersion images of a second dry electrode mixture, and to calculate a target mixing condition for the second dry electrode mixture based on machine-learned data of the dispersion images.