Addressing issues in bioprocess monitoring and control

In order to improve the monitoring and control of an industrial fermentation process plant a fault detection and advisory system was developed. The need to utilise both algorithmic and rule based fault detection methods is discussed. Following this, the implementation strategy based on the use of G2 from Gensym is outlined. The KAT knowledge elicitation method was used to capture efficiently the fault detection rule set at the seed stage of the process. Examples of the method of elicitation and details of process performance estimation using algorithmic methods are given. Finally, the integration with multivariate data-based methods for fault detection and process application of the combined system is described.