Curable Composition Recipe System for Sidestream Materials
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial sidestream raw materials pose challenges in determining optimal end-products due to varying amounts, compositions, and availability, making it difficult to produce curable compositions like geopolymer-based building materials effectively.
Innovation Solution
A system that receives information on available sidestream and virgin raw materials, determines recipes for curable products based on target feature information, and improves usability of sidestream materials through machine learning models, user interfaces, and communication interfaces, optimizing the production process by sending order requests and feedback for raw material suppliers and manufacturers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If sidestream based raw materials are used for production of curable compositions, then environmental impact is reduced and economic value is created, but the varying amounts, compositions and availability make it difficult to determine optimal end-products and produce curable compositions effectively
Solution Approach 1:
The system changes parameters by receiving target feature information (compressive strength, flexural tensile strength, splitting tensile strength, density, structural weight, CO2 emissions, natural resources consumption) and adjusting the recipe accordingly. The machine learning model modifies material compositions and proportions based on these parameter changes to optimize both environmental impact and manufacturing feasibility.
Solution Approach 2:
The system implements feedback loops by receiving determined feature information of the produced product and using this feedback to teach and improve the machine learning model. This continuous feedback mechanism enables the system to learn from actual production results and refine its recipe recommendations, resolving the difficulty in producing effective curable compositions from variable sidestream materials.
2Productivity
If a system is implemented to determine recipes based on target feature information, then production efficiency is improved, but system complexity increases
Solution Approach 1:
The machine learning model performs self-service by automatically determining optimal recipes based on received target feature information and available raw material data. The system self-adjusts and self-improves through feedback mechanisms, reducing the need for complex manual intervention while maintaining high production efficiency.
Solution Approach 2:
The system achieves multi-functionality by handling multiple tasks through a single integrated platform: receiving raw material information, determining recipes, optimizing for target features, and learning from feedback. This universal approach improves productivity without proportionally increasing complexity, as one system performs multiple functions that would otherwise require separate processes.
3Manufacturing precision
If machine learning models are used to determine recipes, then optimization of curable composition production is achieved, but the need for teaching and feedback mechanisms increases operational complexity
Solution Approach 1:
The feedback mechanism receives determined feature information of the produced product and uses this to teach the machine learning model. This feedback loop enables continuous improvement of manufacturing precision without requiring complex operational procedures, as the system automatically learns from production results and refines its recipe determination algorithms.
Data Source
AI summary
The embodiments relate to a system, devices, methods, and computer programs for determining a recipe for curable compositions. The system may receive information related to available sidestream based and/or virgin raw materials suitable for production of curable products. In addition, the system may receive a request to deliver a recipe for a curable end-product. The request may include target feature information of an end-product. The system may further determine the recipe for the requested end-product on basis of the received target information and the information related to the available raw materials. In addition, the system may provide separate user interface and/or communication interfaces for raw material producers and end-product manufacturers.