FactoryTalk Analytics Pavilion’
Complex industrial processes make it challenging to be both market driven and sustain profitable operations. Manufacturers must adjust their production methodology to introduce a greater variety of higher value products and shorter production runs. They need to produce more, run efficiently and improve product quality to the limits of available equipment. For this, they must ensure maximum uptime and more efficient transitions with less waste. In addition, manufacturers are facing stronger public demand to reduce their environmental impact and operate within regulated emissions limits.
Rockwell Automation FactoryTalk® Analytics™ Pavilion8® Model Predictive Control (MPC) is an intelligence layer on top of automation systems that continuously drives the plant to achieve multiple business objectives—cost reductions, decreased emissions, consistent quality and production increases—in real time. FactoryTalk Analytics Pavilion8 software’s flexible hybrid modeling capabilities incorporates all available process knowledge to deliver the most accurate, highest fidelity models possible. It uniquely provides a single solution that can handle both nonlinear and linear processes simultaneously, driving improved results across a wide range of process technologies. Our MPC technology continuously assesses current and predicted operational data, compares them to desired results, and drives new control targets to reduce process variability, operate within equipment constraints and improve performance.
Greater Model Accuracy
FactoryTalk Analytics Pavilion8 software offers hybrid modeling based on empirical data, first principles equations, operator knowledge or using any combination thereof. Soft Sensor® applications can integrate with other FactoryTalk Analytics Pavilion8 software providing timely in-process measurements to increase accuracy of control actions. In addition, our patented Extrapolated Gain Constrained Neural Networks deliver model accuracy beyond the historic operating ranges. All this expedites deployment, minimizes need to adjust models as process range is extended, and maximizes the value delivered.
Tighter Operational Control
The solution incorporates changing process dynamics over wide process operating ranges. Its parametric model representation provides a compact, computationally efficient controller model without sacrificing accuracy. This improves plant performance across wider operating regions, provides tighter operating range control and significantly increases flexibility across changing grades including more rapid new product introduction.
Higher Controller Performance
You can maintain a contextual history of control actions and improve troubleshooting via controller replay capability. The embedded controller performance metrics track and present performance enabling accelerated, effective sustainability. This allows quick identification and resolution of model mismatch or tuning parameter errors for improved controller performance. It also helps achieve predictable, sustainable performance through continuous controller monitoring.
Industry Use Cases
Leveraging Data to Solve Unique Challenges
Food and Beverage
An international dairy producer was challenged with controlling the drying process to consistently meet government regulations. Rockwell Automation recommended a closed-loop, moisture-control application to better manage product moisture. They designed, developed, and deployed a predictive model-based control solution based on its FactoryTalk Analytics Pavilion8 modular software platform. By feeding sensor data throughout the line, model-based controls could use the data to allow the line to respond in a predictive fashion, significantly reducing moisture variability, raising dryer throughput, and reducing the energy needed to dry the caseinate. As a result, the dairy producer achieved up to a 42% reduction in quality variability, up to 0.38% increase in average moisture content, and a 6–15.8% increase in production throughput.
Cement
A North America based cement company was challenged with decreasing energy usage, increasing production and improving product quality by decreasing deviation in cement finish mill. Leveraging the process expertise of Rockwell Automation engineering resources and steady-state optimization with model predictive control to deliver an advanced process control solution capable of managing process setpoints and transitions. The solution’s predictive capabilities enabled plant personnel to anticipate performance and proactively manage equipment limits. As a result, the solution increased throughput of 4.8% and 5.7% on two mills, increased finish mill production by 5% and reduced power consumption by 3.5 KWh/s ton of cement produced.
Chemical
An international petrochemical provider needed a way to meet specific production targets, including increasing production of a complex chemical, reducing off-spec material, and reducing transition times between grades. With the FactoryTalk Analytics Pavilion8 MPC solution, the company created online predictive models that augmented hardware instruments and laboratory analyses to provide real-time estimates of process and product conditions. As a result, the petrochemical provider reduced the variability of product properties by 50%, decreased transition times by up to 50%, increased production by 7% and increased efficiencies in monomer and catalyst use.