Quantitative composition–property modelling of rubber mixtures by utilising artificial neural networks

✍ Scribed by András P Borosy

• Book ID: 104309734
• Publisher: Elsevier Science
• Year: 1999
• Tongue: English
• Weight: 84 KB
• Volume: 47
• Category: Article
• ISSN: 0169-7439
• DOI: 10.1016/s0169-7439(98)00212-3

✦ Synopsis

A significant opportunity exists to improve operations and resulting profitability by streamlining the formulation design Ž . task. Artificial Neural Network ANN approximation addresses this opportunity that is most useful in an environment where theoretical descriptions are difficult to obtain, but partial knowledge about the process is known and input-output data are Ž . available. Quantitative relationships between the composition and process variables of formulation and the physico-chem-Ž . ical properties of the product are modelled by an Adaptively Learning Artificial Neural Network ALANN . The trained ALANN is then used as an interpolating function to estimate product performance when given specific formulations and Ž . processing requirements direct modelling . The trained ALANN is also used as the object function of a Nelder-Mead sim-Ž . plex to optimise formulation and processing to accomplish desired product characteristics inverse modelling . ALANN was compared to another application by using data from rubber industry.