Advanced process control in the cloud

Engineering and IT Insight: When considering which applications to move to the cloud to reduce costs, consider moving advanced process control (APC) model building and APC model validation tools—usually lightly used and usually not mission critical. Learn three types of cloud-based services.

02/22/2013


Controls and IT Integration, Control EngineeringUsing the “cloud” is not something that is normally considered for process control, but the situation is slightly different when using advanced process control (APC). APC uses predictive models of a process to generate setpoints and control moves that are better than those generated by typical PID algorithms. APC is usually used where responses are nonlinear or even discontinuous and where multiple process values can be required to generate the correct control move. Implementing APC usually involves three steps: building the APC model, validating the APC model using data from a running system, and executing the model to generate setpoints and control moves.

Model execution is implemented in real-time control systems and is not suitable for moving to the cloud. Cloud response times are variable and accessibility is problematic, so this is not an environment for any real-time control. Model execution is often performed within a distributed control system (DCS), programmable logic controller (PLC), or an attached PC. Most DCS vendors provide APC elements in their control systems, but these are usually just model execution blocks that assume you have already created and validated the APC model.

APC model building, however, is different. If you are lucky to have very smart engineers, you may be able to build an APC model from first principles. First principles allow you to use knowledge of your processes to construct mathematical models, accounting for all required product quality attributes and all possible process parameters needed to achieve the attribute targets. Most people are not lucky enough to have the knowledge or resources to build first principle models. Even something as simple as a blending operation may require so much physical modeling as to make it impractical for general use. In these cases, you can use pattern analysis tools to discover the mathematical relationships between the process parameters and the quality attributes to develop an empirical model.

Pattern analysis tools take a lot of data and use a lot of computing time, but they are only occasionally needed, usually when the process changes or equipment is changed. Lots of data, lots of computing power, and only occasional needs are the sweet spot for a cloud-based solution. A purchased pattern analysis system would require servers and databases that would normally sit unused, tying up capital and consuming IT support resources.

Three types of cloud-based services

A cloud-based solution may be a system as a service (SAAS), in which the cloud service vendor provides an operating system environment, such as a Microsoft Windows Server, that runs your application. Another option is a platform as a service (PAAS), in which the cloud service vendor provides a bare-bones machine that you load with your operating system and application. A third option is an application as a service (AAAS), in which the cloud service vendor provides a full application and the environment. Any one of these options should provide a lower cost solution than locally hosting and maintaining an application that you will use only rarely. Model building for advanced process control that produces an empirically derived model is a good candidate for a cloud-based solution.

Many APC projects fail because the models are not maintained, and over time they fail to accurately reflect the real behavior of the system. There should be, but often is not, a schedule for regular validation of the model. Model validation compares the expected results from the model with the actual results from the system. When validation is not performed, small changes in material properties, or equipment changes due to aging or replacement of equipment, will eventually result in an invalid model. Invalid models will generate suboptimal or even wrong control moves for the process. Validation can be performed on every production run, but if the model was built from statistical data, then validation should be performed when only enough data is available to smooth out random variations.

Model validation is also a process that requires a lot of data and computing power, yet may be only occasionally run. APC model validation is also a good candidate for a cloud-based solution. One of the advantages of a cloud solution is the general ability to scale up the database space available and computing power available for short periods of time. Online retailers take advantage of this by scaling up during the main shopping seasons, then downsizing and saving money during off-seasons. You can use these same scale-up features to validate your APC models when the cloud vendor’s systems are being least used and are available at reduced rates.

When considering which applications you can move to the cloud to reduce your capital and support costs, consider moving your APC model building and APC model validation tools. These tools are usually lightly used and are usually not mission critical applications. So when your CIO says, “Everything to the cloud,” your manufacturing IT team will have a plan in place.

 

- Dennis Brandl is president of BR&L Consulting in Cary, N.C., www.brlconsulting.com. His firm focuses on manufacturing IT. Contact him at dbrandl(at)brlconsulting.com. Edited by Mark T. Hoske, content manager, CFE Media, Control Engineering and Plant Engineering, mhoske(at)cfemedia.com.

ONLINE extra - This posted version contains more information than the print / digital edition from March 2013 Control Engineering, including explanation of three types of cloud-based services



No comments
Consulting-Specifying Engineer's Product of the Year (POY) contest is the premier award for new products in the HVAC, fire, electrical, and...
Consulting-Specifying Engineer magazine is dedicated to encouraging and recognizing the most talented young individuals...
The MEP Giants program lists the top mechanical, electrical, plumbing, and fire protection engineering firms in the United States.
Water use efficiency: Diminishing water quality, escalating costs; Lowering building energy use; Power for fire pumps
Building envelope and integration; Manufacturing industrial Q&A; NFPA 99; Testing fire systems
Labs and research facilities: Q&A with the experts; Water heating systems; Smart building integration; 40 Under 40 winners
Maintaining low data center PUE; Using eco mode in UPS systems; Commissioning electrical and power systems; Exploring dc power distribution alternatives
Protecting standby generators for mission critical facilities; Selecting energy-efficient transformers; Integrating power monitoring systems; Mitigating harmonics in electrical systems
Commissioning electrical systems in mission critical facilities; Anticipating the Smart Grid; Mitigating arc flash hazards in medium-voltage switchgear; Comparing generator sizing software
As brand protection manager for Eaton’s Electrical Sector, Tom Grace oversees counterfeit awareness...
Amara Rozgus is chief editor and content manager of Consulting-Specifier Engineer magazine.
IEEE power industry experts bring their combined experience in the electrical power industry...
Michael Heinsdorf, P.E., LEED AP, CDT is an Engineering Specification Writer at ARCOM MasterSpec.