(268f) Intelligent Alarm Management Framework to Detect, Diagnose and Mitigate Faults in a Continuous Pharmaceutical Manufacturing Process | AIChE

(268f) Intelligent Alarm Management Framework to Detect, Diagnose and Mitigate Faults in a Continuous Pharmaceutical Manufacturing Process


Gupta, A. - Presenter, Purdue University
Reklaitis, G. V., Purdue University
Nagy, Z. K., Purdue University
Giridhar, A., Purdue University

One of the important challenges in real time process management is the implementation of intelligent systems that can assist human operators in making control decisions. Modern technological advances have resulted in increasingly complicated processes that present considerable challenges in their design, analysis and management for successful operation. Given the size, scope, and complexity of these modern engineered systems and their interactions, it is becoming increasingly difficult for people to anticipate, diagnose and control serious abnormal events in a timely manner. Failure of the operator to exercise the appropriate mitigation actions often has an adverse effect on the product quality, process safety, occupational health and environment. Hence, there exist considerable incentives to develop intelligent systems for automating fault diagnosis and mitigation. The difficulties associated with implementing intelligent control and the opportunities for improvements are even greater in the pharmaceutical manufacturing domain due to processing challenges. Most pharmaceutical manufacturing involves particulate matter and the behaviors of particles are not well defined. Also, there are very few sensing methods that are well developed to monitor the process online.

In this work, a complete plant-wide control framework has been developed for the integrated continuous pharmaceutical tablet manufacturing process. The designed control system consists of three layers and includes: i) low-level or regulatory control, ii) MPC or supervisory control and iii) EEM module. The regulatory control tries to keep the controlled process variable at a specified value. Limitations to regulatory control were found in dealing with certain exceptional events where it exacerbates the situation instead of controlling it. The supervisory controller supersedes the regulatory controller and oversees the whole plant. The EEM module forms the top layer and helps to mitigate exceptional events which are missed by the other layers. The three layers of control along with the ontological data management system TOPS forms the complete package of Intelligent Alarm System (IAS). The number of process variable that are measured determines the strength of the framework. Hence, various sensing scheme has been developed to monitor the process online.  NIR spectroscopy along with Microwave sensing is used to monitor content uniformity of the blend and ribbon density and moisture content of the ribbons. A partial least square model is developed for the measurement of these properties through NIR and a resonance model is developed for microwave sensor. Online measurement of particle size distribution is done through the use of Eyecon imaging technique.

The IAS framework is applied on pilot scale continuous pharmaceutical tablet manufacturing plant consisting of feeders, blenders, roller compacter, granulator and tablet-press. Numerous abnormal events were studied by simulating the situation in the lab and faults signatures and trends were stored in the ontological database along with the corresponding mitigation strategy. The framework developed was able to detect and diagnose various common abnormal events, including those involving a single process unit, multiple units as well as controller faults.   


A. Gupta, A. Giridhar, G.V. Reklaitis and V. Venkatasubramanian, Intelligent Alarm Systems applied to Continuous Pharmaceutical Manufacturing, ESCAPE 23 proceedings, Lappeenranta, Finland, June 2013

A. Gupta, A. Giridhar, V. Venkatasubramanian and G.V. Reklaitis, Intelligent Alarm Systems applied to Continuous Pharmaceutical Manufacturing – an integrated approach, Industrial and Engineering Chemistry Research, DOI: 10.1021/ie3035042, March 2013

J. Austin, A. Gupta, R. McDonnell, G. V. Reklaitis, M. T. Harris, The Use of Near Infrared and Microwave Resonance Sensing to Monitor a Continuous Roller Compaction Process, Journal of Pharmaceutical Sciences, DOI: 10.1002/jps.23536, March 2013