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

A significant opportunity exists to improve operations and resulting profitability by streamlining the formulation design 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 available. Quantitative relationships between the composition (and process variables) of formulation and the physico-chemical 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 processing requirements (direct modelling). The trained ALANN is also used as the object function of a Nelder–Mead simplex to optimise formulation and processing to accomplish desired product characteristics (inverse modelling). ALANN was compared to another application by using data from rubber industry.