Natural Rubber Blend Optimization via Data-Driven Modeling: The Implementation for Reverse Engineering
Natural rubber formulation methodologies implemented within industry primarily implicate a high dependence on the formulator’s experience as it involves an educated guess-and-check process. The formulator must leverage their experience to ensure that the number of iterations to the final blend compo...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-05-01
|
| Series: | Polymers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-4360/14/11/2262 |
| _version_ | 1797491957472165888 |
|---|---|
| author | Allen Jonathan Román Shiyi Qin Julio C. Rodríguez Leonardo D. González Victor M. Zavala Tim A. Osswald |
| author_facet | Allen Jonathan Román Shiyi Qin Julio C. Rodríguez Leonardo D. González Victor M. Zavala Tim A. Osswald |
| author_sort | Allen Jonathan Román |
| collection | DOAJ |
| description | Natural rubber formulation methodologies implemented within industry primarily implicate a high dependence on the formulator’s experience as it involves an educated guess-and-check process. The formulator must leverage their experience to ensure that the number of iterations to the final blend composition is minimized. The study presented in this paper includes the implementation of blend formulation methodology that targets material properties relevant to the application in which the product will be used by incorporating predictive models, including linear regression, response surface method (RSM), artificial neural networks (ANNs), and Gaussian process regression (GPR). Training of such models requires data, which is equal to financial resources in industry. To ensure minimum experimental effort, the dataset is kept small, and the model complexity is kept simple, and as a proof of concept, the predictive models are used to reverse engineer a current material used in the footwear industry based on target viscoelastic properties (relaxation behavior, tan<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi mathvariant="sans-serif">δ</mi></mrow></semantics></math></inline-formula>, and hardness), which all depend on the amount of crosslinker, plasticizer, and the quantity of voids used to create the lightweight high-performance material. RSM, ANN, and GPR result in prediction accuracy of 90%, 97%, and 100%, respectively. It is evident that the testing accuracy increases with algorithm complexity; therefore, these methodologies provide a wide range of tools capable of predicting compound formulation based on specified target properties, and with a wide range of complexity. |
| first_indexed | 2024-03-10T00:56:41Z |
| format | Article |
| id | doaj.art-62f25beff0c8442382edd792dfba0ff9 |
| institution | Directory Open Access Journal |
| issn | 2073-4360 |
| language | English |
| last_indexed | 2024-03-10T00:56:41Z |
| publishDate | 2022-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Polymers |
| spelling | doaj.art-62f25beff0c8442382edd792dfba0ff92023-11-23T14:42:11ZengMDPI AGPolymers2073-43602022-05-011411226210.3390/polym14112262Natural Rubber Blend Optimization via Data-Driven Modeling: The Implementation for Reverse EngineeringAllen Jonathan Román0Shiyi Qin1Julio C. Rodríguez2Leonardo D. González3Victor M. Zavala4Tim A. Osswald5Polymer Engineering Center, Department of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI 53706, USAScalable Systems Laboratory, Department of Chemical and Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USASOAN Laboratories, Bogotá, ColombiaScalable Systems Laboratory, Department of Chemical and Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USAScalable Systems Laboratory, Department of Chemical and Biological Engineering, University of Wisconsin-Madison, Madison, WI 53706, USAPolymer Engineering Center, Department of Mechanical Engineering, University of Wisconsin-Madison, Madison, WI 53706, USANatural rubber formulation methodologies implemented within industry primarily implicate a high dependence on the formulator’s experience as it involves an educated guess-and-check process. The formulator must leverage their experience to ensure that the number of iterations to the final blend composition is minimized. The study presented in this paper includes the implementation of blend formulation methodology that targets material properties relevant to the application in which the product will be used by incorporating predictive models, including linear regression, response surface method (RSM), artificial neural networks (ANNs), and Gaussian process regression (GPR). Training of such models requires data, which is equal to financial resources in industry. To ensure minimum experimental effort, the dataset is kept small, and the model complexity is kept simple, and as a proof of concept, the predictive models are used to reverse engineer a current material used in the footwear industry based on target viscoelastic properties (relaxation behavior, tan<inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi mathvariant="sans-serif">δ</mi></mrow></semantics></math></inline-formula>, and hardness), which all depend on the amount of crosslinker, plasticizer, and the quantity of voids used to create the lightweight high-performance material. RSM, ANN, and GPR result in prediction accuracy of 90%, 97%, and 100%, respectively. It is evident that the testing accuracy increases with algorithm complexity; therefore, these methodologies provide a wide range of tools capable of predicting compound formulation based on specified target properties, and with a wide range of complexity.https://www.mdpi.com/2073-4360/14/11/2262viscoelasticitymachine learningresponse surface methodologynatural rubberreverse engineeringformulation |
| spellingShingle | Allen Jonathan Román Shiyi Qin Julio C. Rodríguez Leonardo D. González Victor M. Zavala Tim A. Osswald Natural Rubber Blend Optimization via Data-Driven Modeling: The Implementation for Reverse Engineering Polymers viscoelasticity machine learning response surface methodology natural rubber reverse engineering formulation |
| title | Natural Rubber Blend Optimization via Data-Driven Modeling: The Implementation for Reverse Engineering |
| title_full | Natural Rubber Blend Optimization via Data-Driven Modeling: The Implementation for Reverse Engineering |
| title_fullStr | Natural Rubber Blend Optimization via Data-Driven Modeling: The Implementation for Reverse Engineering |
| title_full_unstemmed | Natural Rubber Blend Optimization via Data-Driven Modeling: The Implementation for Reverse Engineering |
| title_short | Natural Rubber Blend Optimization via Data-Driven Modeling: The Implementation for Reverse Engineering |
| title_sort | natural rubber blend optimization via data driven modeling the implementation for reverse engineering |
| topic | viscoelasticity machine learning response surface methodology natural rubber reverse engineering formulation |
| url | https://www.mdpi.com/2073-4360/14/11/2262 |
| work_keys_str_mv | AT allenjonathanroman naturalrubberblendoptimizationviadatadrivenmodelingtheimplementationforreverseengineering AT shiyiqin naturalrubberblendoptimizationviadatadrivenmodelingtheimplementationforreverseengineering AT juliocrodriguez naturalrubberblendoptimizationviadatadrivenmodelingtheimplementationforreverseengineering AT leonardodgonzalez naturalrubberblendoptimizationviadatadrivenmodelingtheimplementationforreverseengineering AT victormzavala naturalrubberblendoptimizationviadatadrivenmodelingtheimplementationforreverseengineering AT timaosswald naturalrubberblendoptimizationviadatadrivenmodelingtheimplementationforreverseengineering |