Using Predictive Modeling to Increase Efficiency and Effectiveness

2 Automation for Process Industries

3 PlantPAx Advanced Process Control Portfolio Real-time Optimization Increasing Effort & Increasing Value Model Predictive Control Nonlinear Multivariable Control Linear Multivariable Control Inferential Sensors Advanced Regulatory Control Regulatory Control Pavilion8 Dynamic MPC PlantPAx Model Builder PlantPAx Fuzzy Designer Logix IMC, CC, MMC Logix PID, PIDE, AOI

4 Why Advanced Process Control? Advanced Regulatory Control Focus is on PROCESS variables levels, flows, temperatures, pressures, etc. Improve poorly performing loops and/or automate manual loops Compensate for dead-time and simple process interactions Improve process stability, consistency, reliability Advanced Supervisory Control Focus is on PRODUCT variables production rate, product quality, product specifications (e.g. moisture, color, density, purity, etc.) Sends setpoints to process control loops good regulatory control is prerequisite to achieve full MPC benefits Improve product quality Increase throughput and/or yield Reduce energy usage

5 Scalable Portfolio of Advanced Controls Value-Add Optimize Control Predict Regulate Span of Control Single Loop Multiple Loops Process Unit Multiple Units Area Plant-wide

6 Starch Dryer Example PID Temperature Control Neither moisture laboratory samples nor moisture soft sensor are available Disturbances are not corrected or slowly corrected Ambient humidity Starch consistency Inlet air flow temperature Output limit PID T out Ctrl SP T out Dried starch out T in Setpoint SP PID Inlet Temp Ctrl Valve Position Feeder Speed VFD Motor Starch feeder Time Delay Hot air & starch mixture Inlet temp Hot Steam Hot Water 12 bar 2 bar Heat recovery CTRL-valve(s) heat flow Heat exchangers Inlet air flow T_Z1 T_Z2 T in

7 PID Control Performance Moisture SP Moisture PV Feed Rate Exhaust Temperature PV Exhaust Temperature SP

8 What is a Model? Models Represent Knowledge A model explains or emulates the behavior of a process... monomer modifier catalyst y = a 3 u 3 + a 2 u 2 + a 1 u + a 0 melt index density using a computational/mathematical representation

9 Uses of Models Analysis Analyze vast amounts of historical data to discover unknown correlations and relationships to gain better insight into the process Prediction Build models that can accurately predict process changes based on changing process inputs and disturbances Combine prediction models with real-time data to build Soft Sensors to identify product changes before they occur, allowing pro-active operator actions Control Closed-loop multivariable model predictive control (MPC) provides faster responses to changing operating conditions and constraints to minimize product variability and improve yields Optimization Steady-state models can identify the optimum operating parameters based on current conditions and constraints to meet desired economic objectives (maximize rate, minimize energy, )

10 You Can t Control What You Can t Measure Process Samples What if in-line sensors are unavailable, unreliable, too expensive Process Adjustments One hour to one day delay! Analysis Lab Results 143.0

11 Solution: Soft Sensor Software model that predicts process values based on real-time process data Process Samples Analysis Process Adjustments Real-time measurement! 143.0 Soft Sensor Prediction Real-time Process Data % Lab Results 0.34 0.45 0.12 U 0.14 o 2c π t 0.46 0.67 u 2 u = c t 2 t 2 +1 rate temp thick 0.34 12.01 5.10 0.45 12.34 5.34 0.12 12.67 5.23-1 exp ( x - υ ) 2 4c 2 t 0.14 13.03 6.02 0.46 13.67 6.70 0.67 13.69 4.98 dυ

12 PlantPAx ModelBuilder PlantPAx ModelBuilder for off-line data analysis and modeling SoftSensor Designer converts models to AOI s Process Samples Analysis Process Adjustments 143.0

Model Based APC Function Blocks Regulatory control functions based on Internal Model Control (IMC) algorithm Handles first order plus dead-time (FOPDT) models Gain, time constant, and delay parameters Good for processes with dead-time or processes with simple coupling Different Function Blocks for Specific Problems IMC (Internal Model Control) Replace single PID loop to address dead-time CC (Coordinated Control) Additional control outputs (2 or 3) for coordinating multiple actuators for a single process variable MMC (Modular Multivariable Control) Coordinates 2 loops that interact with each other 0 0 0 0 PV PV SPProg IMC_01 IMC... Internal Model Control SPCascade SPProg CV1Prog CV2Prog CV3Prog PV1 PV2 SP1Prog SP2Prog CV1Prog CV2Prog CC_01 CVEU SP ProgOper CC... Coordinated Control MMC_01 CV1EU CV2EU CV3EU Copyright 2012 Rockwell Automation, Inc. All rights reserved. SP ProgOper MMC... Modular Multivariable Control CV1EU CV2EU CV3EU SP1 SP2 ProgOper 0 0 0 0 0 13

14 Improved Starch Dryer Control with APC IMC Moisture Control Moisture Soft Sensor is used for outlet moisture control Exhaust T Ctrl Moisture Ctrl IMC PV SP Moisture SoftSens Amb Air Humidity Moisture Lab Sensor Sample Dried starch out PID SP PV Tout Tin Setpoint SP PID Inlet Temp Ctrl Valve Position CV Feeder Speed VFD Motor Starch density Starch feeder Time Delay Hot air & starch mixture Inlet temp Hot Steam Hot Water 12 bar 2 bar Heat recovery CTRL-valve(s) heat flow Heat exchangers Inlet air flow T_Z1 T_Z2 Tin

15 IMC Control with Soft Sensor SP Change

16 IMC Control with Soft Sensor

17 Model Predictive Control A Systematic Approach for Control of Processes with Constrained Nonlinear Dynamics Model Predictive Controller Targets, Constraints Optimizer Trial actions Control actions Trial outcomes Process Model Process Measurements Disturbances The key to effective control is good modeling

18 Spray Dryer Challenges From Mixers Hold Tank Deaerator Slurry Flow Slurry Temperature Slurry Density To Cyclones Tower Pressure Tower Top Controller OP Temperature PIC 319 TT 301-304 Avg Control powder moisture to target Maintain tower temperature and tower under-pressure below limits Minimize tower temperature when possible to reduce energy usage Drop Tank FIC 305 TT 310 DT 304 Dual valve slurry flow control FIC 314 Inlet Air Flow VSD Natural Gas Flow FT 804 CV 347 Slurry Recirculation Valve TIC 315 Inlet Air Temperature Multiple interacting control loops Powder Moisture No inline moisture sensor

19 Spray Dryer Solution from Rockwell Automation From Mixers To Cyclones Manipulate air flow, slurry flow, and air temperature setpoints to control powder moisture to target and Pavilion8 maintain tower temperature Model Predictive & pressure Control within constraints while compensating for slurry temperature and density variations Drop Tank Hold Tank Deaerator Slurry Flow FIC 305 Slurry Temperature TT 310 Slurry Density DT 304 Tower Pressure Tower Top Controller OP Temperature PIC 319 TT 301-304 Avg Powder PlantPAx Moisture Model Prediction Builder PlantPAx Startup Fuzzy Setpoints Designer FIC 314 Inlet Air Flow VSD Natural Gas Flow FT 804 CV 347 Slurry Recirculation Valve TIC 315 Inlet Air Temperature Logix Slurry IMC, Flow CC, MMC Inlet Logix air flow PID, and PIDE, temperature AOI Powder Moisture

20 Spray Dryer Model Predictive Control

21 Spray Dryer MPC Performance Metrics

22 Benefits of Model Predictive Control SPECIFICATION OR LIMIT KEY TARGET BEFORE MPC TIME WITH MPC WITH OPTIMIZATION Faster moisture measurement and tighter control allows average moisture target to be increased Sell more water/less expensive ingredients Reduce energy used for drying Increase throughput through dryer

23 Pavilion MPC Applications CPG Typical Spray Benefits Dryers Evaporators increase Energy Centers Process Types variability reduction Milk Powder product Coffee reduction 5 to Laundry 10% energy Detergent Conc. juice 5 to 8% production 30 to 60 % moisture 20 to 50% off-spec consumption reduction CMM Typical Crushing/Grinding Benefits Kilns 2 to 5% & Drying production increase Stockpile Blending Process 2 to 5% Types energy consumption reduction 20 Cement to 40% product variability Minerals reduction 10 Fertilizer to 30% off-spec Ammonia product reduction Polymer/Chemical Typical Reactors/Extruders Benefits Distillation Towers 4 to 8% prime product Furnaces yield increase Process 35 to 75% Types product variability PE, PP, reduction PS, PC 20-40% Ethylene transition Plants time reduction 3 to Styrene 7% feed Plants stock wastage Crude reduction Refining Gas Plants Bio-fuels Typical Project Payback: 3 to 9 months! Typical DDGS Benefits Evap/Dryer Water 4 to12% Balance ethanol production Fermentation capacity increase Distillation Process 2 to 5% Types ethanol yield increase 3 to Corn 6% energy Ethanol use/gallon Cane reduction Ethanol Bio-diesel 1 to 2% DDGS yield increase

24 Benefits of PlantPAx Advanced Controls Smart, Safe & Sustainable Production

25 PlantPAx Advanced Controls & Optimization Scalable, integrated controls & optimization Value assessments and engagement methodology Industry expertise and best practices Sustained Value Services & Support Faster time to Value / Lower TCO