210 likes | 261 Views
Hybrid Modeling & Model Predictive Control . The Potential to Leverage Success in Other Industries. Discussion Overview. Model Predictive Control – 15 years of Reducing Variability & Improving Quality Process Understanding – Leveraging Fundamental AND Empirical Knowledge
E N D
Hybrid Modeling & Model Predictive Control The Potential to Leverage Success in Other Industries
Discussion Overview • Model Predictive Control – 15 years of Reducing Variability & Improving Quality • Process Understanding – Leveraging Fundamental AND Empirical Knowledge • Design Space – ensuring model accuracy with multi-dimensional boundaries • Lesson’s Learned and Success Achieved in other Industries • A Practical Risk Based Approach to Implementation
Pavilion Technologies • Our Mission • Deliver the world’s leading model-based software to improve our customers’ profitability • Founded in 1991 • Combined intellectual property of DuPont and Eastman Chemical Company • Global Presence • Offices in North America, Europe, China, and Pacific Rim • Financials • Acquired on November 1, 2007 by Commitment to Innovation • Team of researchers, computer scientists and industry experts leveraging more than 155 patents in the field of modeling, control and optimization 3
monomer • melt index • modifier • y = a3 u3 + a2 u2 • + a1 u + a0 • density • catalyst What is a Model? A model explains or emulates the behavior of a process ... … using a set of computations A model provides predictive capability through “computational experimentation” • Manufacturing assets can be understood • Manufacturing assets can be managed • Note that the "process" need not be physical 4
Model Develop Statistical Models Characterize Process Trace of Outputs vs. Inputs Trace of Output Sensitivities Interactive Set-Point Analysis Multivariate Data Analysis Model Development 6
What is a Good Model? Desired Model Features • Offer prediction accuracy and maintain computational efficiency • Provide global validity over the entire operation region • Enable optimal combination of empirical data, first-principles models, and process knowledge • Remain physically meaningful • Offer robustness to modeling inaccuracies and disturbances by enabling optimization-based modification of the models • Enable solution standardization by simplifying template building 7
Established Modeling Paradigms aren't Enough First Principles Modeling • Leverage explicit knowledge based on scientific principles • Strengths • Global validity • Parameters have physical meaning • Not data dependant • Weaknesses • Typically incomplete • Slow evaluation (solver) • Could contain implicit outputs Empirical Modeling • Leverage implicit knowledge based on historical/test data • Strengths • Typically explicit • Fast evaluation (no solver) • Wide applicability and quick to develop • Weaknesses • Valid for observed data • Often lacks physical meaning • Requires rich data 8
Building Parametric Hybrid Models Specify Hybrid Model Structure • Often a composite model that includes both empirical and FP components EmpiricalModel First-PrinciplesModel Train the Model using Constrained Optimization • Often constraints are imposed to ensure model parameters reflect first-principles knowledge EmpiricalModel First-PrinciplesModel ConstrainedTrainer decreasingconstrainteffects increasingconstrainteffects 9
Flexible Composite Modeling Example Fundamental Models
Plant “Obedience” is an advanced form of “steady State” APC manages the dynamics & rapid disturbances that occur Consistency of operation Enables optimal targets to be achieved with “confidence” Preserves safety - plant, people & product • Capacity Target uplift = Plant • Obedience and improved • steady state will increase • capacity within dryer limits • Yield Target uplift = Plant • Obedience and VOA control • will allow moisture to increase. Pavilion8 in Drying Processes – The Primary Objectives • Plant Obedience = APC on when the model is in the valid zone approx @ 30% solids 11
Fermentation Control Application Capabilities • 50% reduction in batch EtOH and Dextrose/residual sugars variability • Continuously manage enzymes to maximize throughput and ethanol yields • Optimal target on temperature and pH for fermentation • Manage fermentations to match production targets Benefits • Increase in batch drop ethanol yield (MMGPY) by 0.5-1.0% • Increase in fermentation capacity by 5-12% (MMGPY) • Increase in batch yields (gal/bu) by 2-5% • Reduce enzymes/gal ($$ enzymes/gal) by 5-10% 12
Bio-Fermentation Batch A-1022 Predicted vs Actual
Bio-Fermentation Batch A-1145 Predicted vs Actual
Reactor Control Application Capabilities • Adjust reactor conditions to maintain at-grade quality control of the resin properties • Control concentrations within the reactor for improved reactor stability • Control and/or maximizes production rates within the reactor • Optimize transitions • Standardize reactor best practices for complex procedures Benefits • Faster transition times • Reduce off-spec • Increase production • Reduce variability • Improve catalyst and monomer efficiency 15
Discover Analyze Existing Processes Develop Develop Statistical Models Characterize Process Demonstrate Substantiate Statistical Correlations Deploy Perform Continuous Monitoring & Analysis Better Process Knowledge Through Analytics 4 Steps of PAT Implementation by John R. Davis, PE and John Wasynczuk, PhD 16
Discover Analyze existing processes Data Consolidation & Visualization DCS/SCADA Historical Data PAT Sensor Array Data Quality LIMS MES/ERP Data Preprocessing Remove Outliers Signal Conditioning Begin analysis in hours not days & weeks • 4 Steps of PAT Implementation by John R. Davis, PE and John Wasynczuk, PhD 17
Develop Develop Statistical Models Characterize Process Trace of Outputs vs. Inputs Trace of Output Sensitivities Interactive Set-Point Analysis Multivariate Data Analysis Pavilion’s modeling technology can incorporate fundamental models into empirical models, leveraging the benefits both provide for Linear, Non-Linear, Monotonic and Non-monotonic processes • 4 Steps of PAT Implementation by John R. Davis, PE and John Wasynczuk, PhD 18
Demonstrate Substantiate Statistical Correlations Predicted vs. Actual Scatter-Plots Interactive What-Ifs Tools Provide different input values to tool predicts output values (Prediction) Provide desired output values to tool determines best input values (Optimization) • 4 Steps of PAT Implementation by John R. Davis, PE and John Wasynczuk, PhD 19
22/4/03 • 5pm • 22/4/03 • 11pm • 23/4/03 • 5am • 23/4/03 • 11am • 23/4/03 • 5pm Moisture Inferential Accuracy Powder Moisture Inferential Accuracy 20
Deploy Perform continuous monitoring & analysis • 4 Steps of PAT Implementation by John R. Davis, PE and John Wasynczuk, PhD • 104 • 102 • SPECIFICATION OR LIMIT • 100 • 98 • 96 • 94 • 92 • 90 • WITH ADVANCED PROCESS CONTROL & OPTIMIZATION • BEFORE ADVANCED • PROCESS CONTROL • Optimization • BENEFIT Advanced Control • Standard • Control 21
Lessons Learned • A systematic modeling approach enables cross-divisional collaboration (research, operations, quality, engineering) • There are a number of unit processes (fermentation, drying, mixing, etc.) that have proven results improvements leveraging this approach and technology in other industries