Online Analytics Improves Batch Operations

Field trial shows value for fault detection and quality prediction.

By Robert Wojewodka, Lubrizol, and Dawn Marruchella, Emerson Process Management

Share Print Related RSS
Page 3 of 3 1 | 2 | 3 Next » View on one page

IMPORTANT IMPROVEMENTS
The Rouen facility has realized numerous and ongoing benefits that started immediately. Some include:
• During a "train the trainer" class, the online analytics uncovered a fault in the actual process -- a previously undetected problem with the mass flow meter for a key component charged into the batch. This fault was going unnoticed with "traditional" monitoring systems. This revelation helped highlight the benefits of the technology and certainly got the attention of operations management!
• Once up and running, the field trial showed an increasing deviation on the key-component density measurement through several batches. This phenomenon was linked to the start of plugging. It was quickly solved by applying steam without time cycle impact.
• The online tool indicated a problem with the cooling system of the reactor. It detected that a key component was being introduced too slowly and the reactor temperature was running a little bit higher. The problem was solved on the cooler.

Using a univariate approach would not have shown this.
• A process fault detection led to identification of a regular issue on the unit's reactor-heating control loop. This prompted actions to revisit the loop tuning on key process control parameters.
• Another problem was detected on the hot-oil heating system -- an upstream boiler was negatively impacting operations. Discovering the problem in the traditional manner would have taken a number of days. The plant avoided losing five hours for the batch in process and following batches.

Actual Versus Predicted Results 
 Figure 5. Graph compares process variable trend
to modeled value and limits.

NEXT STEPS
The Rouen field trial was successfully completed in mid-2010. The teams are in the process of updating and redeploying the batch analysis models following several significant process redesign changes. This is necessary because these changes modified the batch operations and phases.

An additional and successful field trial was completed in a bioscience application area. This further cemented the benefits of these approaches to batch process modeling.

If the results of these field trials hold true for others, online analytics will provide manufacturers with additional insight and benefits through greater understanding of batch processes. This should lead to an increase in the consistency of quality products as well as greater throughput through better yields and decreased cycle time and outages -- in short, more good batches at a lower cost to manufacturers.


ROBERT WOJEWODKA is technology manager, process improvement team leader, for The Lubrizol Corp., Wickliffe, Ohio. DAWN MARRUCHELLA is a marketing manager for Emerson Process Management, Austin, Texas. E-mail them at Robert.Wojewodka@Lubrizol.com and Dawn.Marruchella@Emerson.com.

Further Reading
Wojewodka, R., and Marruchella, D., "Benefits Achieved Using Online Analytics in a Batch Manufacturing Facility," WBF Make2Profit Conference, Austin, Texas (May 2010).

Wojewodka, R., and Blevins, T., "Data Analytics in Batch Operations," Control, p. 53, May 2008, www.controlglobal.com/articles/2008/164.html.
Wojewodka, R., Moro, P., and Blevins, T., "Lubrizol, Emerson Redefining Collaboration," online video, www.controlglobal.com/articles/2007/321.html.

Page 3 of 3 1 | 2 | 3 Next » View on one page
Share Print Reprints Permissions

What are your comments?

Join the discussion today. Login Here.

Comments

No one has commented on this page yet.

RSS feed for comments on this page | RSS feed for all comments