Regression Modeling for Climate-Adaptive Polyurethane Foam Formulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for producing polyurethane foams struggle to accurately account for the effects of changing climate factors on product properties, leading to variations in raw density and compression deflection, and often result in the disposal of off-specification material due to the lack of effective data cleansing, preprocessing, and automated correction mechanisms.
Innovation Solution
A method involving a combined transformed regression model that uses climate parameters to adjust the composition of the reaction mixture, incorporating data cleansing and preprocessing techniques, and enabling automated formulation corrections through a user interface or FPGA implementation to ensure consistent product quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If heuristic rules based on shop personnel experience are used to adjust formulation, then ease of operation is improved, but manufacturing precision deteriorates due to inability to account for multiple simultaneous climate factors
Solution Approach 1:
The patent replaces manual heuristic adjustment by shop personnel with an automated computer-based regression model system. The system automatically processes climate data and calculates formulation adjustments, eliminating the need for manual experience-based decision-making while improving precision through mathematical modeling of multiple climate factors simultaneously.
Solution Approach 2:
The regression model acts as an intermediary between climate measurements and formulation adjustments. It processes raw climate data (temperature, humidity, pressure) and translates it into precise formulation corrections, serving as a mathematical mediator that connects environmental conditions to optimal production parameters.
2Manufacturing precision
If regression models are used to account for climate factors, then manufacturing precision is improved, but device complexity increases due to data cleansing and preprocessing requirements
Solution Approach 1:
The system performs preliminary data cleansing and preprocessing automatically before applying the regression model. By pre-processing the climate data (handling missing values, outliers, and formatting) in advance, the system simplifies the main regression analysis step and reduces the complexity burden during critical production decision-making.
Solution Approach 2:
The regression model system is self-sufficient in handling its own data requirements. It automatically detects and corrects data quality issues, performs necessary transformations, and generates formulation adjustments without requiring external manual intervention, thereby managing its own complexity internally.
3Productivity
If automated formulation corrections are implemented, then productivity is improved through reduced waste, but device complexity increases due to FPGA or user interface integration
Solution Approach 1:
The patent extracts the complex regression analysis and formulation calculation functions into a separate computing platform that can be implemented via FPGA or user interface. This modular extraction allows the core productivity-enhancing logic to be isolated from the production process control, enabling flexible implementation while maintaining system integrity.
Solution Approach 2:
The system changes the state of formulation parameters automatically based on real-time climate data. By continuously adjusting formulation parameters (component ratios, mixing conditions) in response to measured climate conditions, the system maintains optimal product quality across varying environmental conditions, thereby improving productivity through waste reduction.
Data Source
Figure 1
Figure 2
AI summary
A method of producing a chemical product from a reaction mixture containing at least two components includes the steps of: I) providing a data set comprising a plurality of production instances, each production instance comprising data on (a) the composition of the reaction mixture and/or process conditions, (b) at least one climate parameter at the production site of the product, and (c) at least one target physical property of the product; II) generating a regression model for each target physical property of the product using the data set, wherein in the regression model a respective target physical property is the dependent variable and at least part of the other data in the data set, excluding any remaining target physical properties, are independent variables; III) transforming each regression model to obtain a transformed regression model where a) the composition of the reaction mixture and/or b) the process conditions of a reaction depends on at least one climate parameter at the production site of the product and each target physical property is assigned a desired value; IV) combining the transformed regression models to obtain a combined regression model.