Skip to main content
. 2017 Nov 22;34(12):2596–2613. doi: 10.1007/s11095-017-2308-y

Fig. 5.

Fig. 5

Workflow showing the data-driven knowledge discovery approach for the detection and minimization of disturbance variables. After selection of the targeted disturbance class via risk assessment tools, data has to be generated and/or accumulated. Indications about disturbing variables/ descriptors can be generated by correlation analysis or – if possible – via mechanistic modelling. Obtained knowledge/ information has to be implemented in the design space to allow minimization of the identified disturbances.