A method of optimizing parameter values in a process for producinga product, which process is essentially controlled by a set of parametersaffecting aset of properties characterizing the product. The method uses an analytichierarchyprocess (AHP) to associate a weight with each property according to itsrelativeimportance to obtain desired product characteristics. The method also usesparameterdata and measured property data from a required number of experimental runs ofthe process, from which data property behavior relations between each propertyandthe parameters are statistically established, which relations give estimatedpropertyvalues. Using the property weights, a process goal function is established,which isexpressed in terms of weighted deviations between the estimated propertyvalues andthe corresponding goal values for the properties. Finally, the process goalfunctionis minimized in order to generate a set of optimal parameter values for theprocess.The AHP process may be further used to evaluate the optimal solution comparedtoa set of other alternative solutions. The method allows the use of input dataobtainedfrom a minimum number of experimental runs, to generate a reliable set ofparameter values. An example illustrating an application of the method for thedesign ofa pharmaceutical formulation is described.
展开▼
