Advanced Process Control and Continuous Processing in ...
Advanced Process Control and Continuous Processing in Pharmaceutical Manufacturing: What Can We Learn from Other Industries Paul Brodbeck
What is Process Control? How? Why? Benefits? Why Advanced Process Control? Advanced Controls ◦ ◦ ◦ ◦
MPC Kalman Filter Neural Networks LP Optimization
Controlling process variable to a desired SP. ◦ ◦ ◦ ◦ ◦ ◦ ◦ ◦
Reactor Temperature Heat Exchanger Flow Rate Boiler Pressure OTC Tablet (API) Concentration. Dryer Moisture Content House Temperature Car Speed Distillation Column Production Rate
Feed Back Control – Modeled after Human Beings Closed Loop Control – Level, Press, Flow, API Concentration (%) Vary output – Valve, Pump, Agitator, Fan
WHY? Manual vs. Automatic Quality – Temperature Variability Temperature Cycling ◦ Poor Quality ◦ Inefficient ◦ Wear and Tear on Heater and Parts
Auto change SP at day/night Cost Savings Control Improves Quality & Reduces Costs
WHY? Manual vs. Automatic Quality – Constant Speed Speed Cycling
◦ Poor Quality ◦ Inefficient ◦ Wear and Tear on Car and Parts
Get there faster!
Control Improves Quality & Reduces Costs
◦ Set Speed closer to speed limit ◦ Less Risk/Less Speeding Tickets
WHY? Manual vs. Automatic Production Yields Profit
Improves Quality Reduces Costs Increases Production
Reduce Variability! Edward Deming – Quality Program Japan Post WWWII Better Quality ◦ Autos, Semi-Conductors, Steel…
1980’s American Manufacturing Poor Quality Statistical Process Control Control Process Reduce Variability Increase Quality
Variable Parameters
Variable Quality
Controlled Parameters
Fixed Quality
Improve Quality Increase Yields Increase Production Reduce off-spec Reduce Bad Batches Reduce Energy Costs Reduce Production Costs Improve Safety Reduce Risk Increase Profitability
Optimal Control Good Control Ok Control Good Enough Control Poor Control No Control
Basic Process Control GOOD?
Advanced Process Control BETTER?
Advanced Control
Basic PID No Control
Advanced PID
Control
Optimization
Optimal Control
Tuning Constants: 1. Proportional (P) 2. Integral (I) 3. Derivative (D)
Applications Car Cruise Control Home Heating/AC, Distillation Columns Chemical Reactors Bioreactors Crystallization Chromatography
Industries Chemical Pharmaceutical Petroleum Automotive Robots Aerospace Boilers Missile Guidance
Applications Distillation Columns Robotics Drones Aerospace Robots Missile Guidance Stock Market, Operations Research Economics Scheduling
Industries Chemical Pharmaceutical Petroleum Automotive Robots Aerospace Boilers Missile Guidance
1. Model Predictive Control (MPC) ◦ Distillation Columns, Robotics, Drones, Aerospace…
2. Kalman Filter ◦ Robots, Aerospace, Missile Guidance…
3. Neural Networks (NN) ◦ Pattern Recognition, Stock Market, Genetics…
4. Linear Programming (LP) Optimization ◦ Operations Research, Economics, Scheduling
Machine Learning ◦ Computer Science & Statistics ◦ Real World Problem Prediction/Optimization
Search Engines Stock Market Prediction Pattern Recognition (OCR) Robotics Recommender Systems DNA Sequencing Chemometrics
Numerical Methods Statistics Modeling Analytics Linear Programming Optimization
MPC Neural Networks MVA Tools MLR PCA PLS Kalman Filter Multivariate SPC
Optimal Control Slow Processes Large Dead Times Multiple Loops (50x25) Complex Dynamics Strongly Correlated Loops
Multi-Loop PID
Multi-Loop MPC
P
ny
J w y i 1 j 1
y j
set j
k i y j k i w
Controlled variable deviations y: Controlled variable u: Actuator △u: Predicted adjustment
2
M nu
i 1 j 1
u j
M nu
u j k i 1 w u j k i 1 u j i 1 j 1 2
controller adjustments
Tuning parameters 1. Output weights (wyj) 2. Rate weightsu ( ) wj 3.Input weight ( ) wuj 4. Prediction horizon 5. Control horizon Singh, R., Ierapetritou, M., Ramachandran, R. (2013). European Journal of Pharmaceutics and Biopharmaceutics, http://dx.doi.org/10.1016/j.ejpb.2013.02.019.
u j
manipulated variable deviations
2
Actuator
Control variable
Control variable
Actuat or
NIR signal Filtered NIR signal CV (API composition)
Actuato r Ratio SP
1
2
3
Statistically Optimal Estimator Numerous Applications ◦ ◦ ◦ ◦ ◦
De facto Standard Robotics Aerospace Missile Guidance Economics Signal Processing
State Prediction based on: ◦ Noisy Data ◦ Physical Model (Error increases w/ Time)
Takes a statistical average of: ◦ Measured Variable ◦ Model
Acts Recursively to continuously predict most probable state. First used by NASA to predict location of rockets ◦ Uncertain GPS Signal ◦ Physical Model error increases with time
Use measurement signal to correct errors with model. Use model to validate measured values.
dF(x)/dx = f(x)*(1-f(x))
E-mail Spam Internet Browser recommender systems Pattern Recognition ◦ Bar coders ◦ Facial identification ◦ Robotics
Pharma ◦ Soft Sensors ◦ Non-Linear Control
Combination of Linear Regressions Model Non-Linear Data
14
12
10
8 Fit Raw Data
6
4
2
0 1
2
3
4
5
6
7
8
9
10
11
Linear Programming A mathematical/computer optimization technique Solve a system of linear equations Can be used to find the minimum and maximum states of process control Can be made subject to multiple constraints
Pusher Function Maximize Flow subject to constraints
Introduce new/advanced technology With: ◦ PAT ◦ Continuous Manufacturing
What is Process Control? How? Why? Benefits? Why Advanced Process Control? Advanced Controls ◦ ◦ ◦ ◦
MPC Kalman Filter Neural Networks LP Optimization
Controlling process variable to a desired SP. ◦ ◦ ◦ ◦ ◦ ◦ ◦ ◦
Reactor Temperature Heat Exchanger Flow Rate Boiler Pressure OTC Tablet (API) Concentration. Dryer Moisture Content House Temperature Car Speed Distillation Column Production Rate
Feed Back Control – Modeled after Human Beings Closed Loop Control – Level, Press, Flow, API Concentration (%) Vary output – Valve, Pump, Agitator, Fan
WHY? Manual vs. Automatic Quality – Temperature Variability Temperature Cycling ◦ Poor Quality ◦ Inefficient ◦ Wear and Tear on Heater and Parts
Auto change SP at day/night Cost Savings Control Improves Quality & Reduces Costs
WHY? Manual vs. Automatic Quality – Constant Speed Speed Cycling
◦ Poor Quality ◦ Inefficient ◦ Wear and Tear on Car and Parts
Get there faster!
Control Improves Quality & Reduces Costs
◦ Set Speed closer to speed limit ◦ Less Risk/Less Speeding Tickets
WHY? Manual vs. Automatic Production Yields Profit
Improves Quality Reduces Costs Increases Production
Reduce Variability! Edward Deming – Quality Program Japan Post WWWII Better Quality ◦ Autos, Semi-Conductors, Steel…
1980’s American Manufacturing Poor Quality Statistical Process Control Control Process Reduce Variability Increase Quality
Variable Parameters
Variable Quality
Controlled Parameters
Fixed Quality
Improve Quality Increase Yields Increase Production Reduce off-spec Reduce Bad Batches Reduce Energy Costs Reduce Production Costs Improve Safety Reduce Risk Increase Profitability
Optimal Control Good Control Ok Control Good Enough Control Poor Control No Control
Basic Process Control GOOD?
Advanced Process Control BETTER?
Advanced Control
Basic PID No Control
Advanced PID
Control
Optimization
Optimal Control
Tuning Constants: 1. Proportional (P) 2. Integral (I) 3. Derivative (D)
Applications Car Cruise Control Home Heating/AC, Distillation Columns Chemical Reactors Bioreactors Crystallization Chromatography
Industries Chemical Pharmaceutical Petroleum Automotive Robots Aerospace Boilers Missile Guidance
Applications Distillation Columns Robotics Drones Aerospace Robots Missile Guidance Stock Market, Operations Research Economics Scheduling
Industries Chemical Pharmaceutical Petroleum Automotive Robots Aerospace Boilers Missile Guidance
1. Model Predictive Control (MPC) ◦ Distillation Columns, Robotics, Drones, Aerospace…
2. Kalman Filter ◦ Robots, Aerospace, Missile Guidance…
3. Neural Networks (NN) ◦ Pattern Recognition, Stock Market, Genetics…
4. Linear Programming (LP) Optimization ◦ Operations Research, Economics, Scheduling
Machine Learning ◦ Computer Science & Statistics ◦ Real World Problem Prediction/Optimization
Search Engines Stock Market Prediction Pattern Recognition (OCR) Robotics Recommender Systems DNA Sequencing Chemometrics
Numerical Methods Statistics Modeling Analytics Linear Programming Optimization
MPC Neural Networks MVA Tools MLR PCA PLS Kalman Filter Multivariate SPC
Optimal Control Slow Processes Large Dead Times Multiple Loops (50x25) Complex Dynamics Strongly Correlated Loops
Multi-Loop PID
Multi-Loop MPC
P
ny
J w y i 1 j 1
y j
set j
k i y j k i w
Controlled variable deviations y: Controlled variable u: Actuator △u: Predicted adjustment
2
M nu
i 1 j 1
u j
M nu
u j k i 1 w u j k i 1 u j i 1 j 1 2
controller adjustments
Tuning parameters 1. Output weights (wyj) 2. Rate weightsu ( ) wj 3.Input weight ( ) wuj 4. Prediction horizon 5. Control horizon Singh, R., Ierapetritou, M., Ramachandran, R. (2013). European Journal of Pharmaceutics and Biopharmaceutics, http://dx.doi.org/10.1016/j.ejpb.2013.02.019.
u j
manipulated variable deviations
2
Actuator
Control variable
Control variable
Actuat or
NIR signal Filtered NIR signal CV (API composition)
Actuato r Ratio SP
1
2
3
Statistically Optimal Estimator Numerous Applications ◦ ◦ ◦ ◦ ◦
De facto Standard Robotics Aerospace Missile Guidance Economics Signal Processing
State Prediction based on: ◦ Noisy Data ◦ Physical Model (Error increases w/ Time)
Takes a statistical average of: ◦ Measured Variable ◦ Model
Acts Recursively to continuously predict most probable state. First used by NASA to predict location of rockets ◦ Uncertain GPS Signal ◦ Physical Model error increases with time
Use measurement signal to correct errors with model. Use model to validate measured values.
dF(x)/dx = f(x)*(1-f(x))
E-mail Spam Internet Browser recommender systems Pattern Recognition ◦ Bar coders ◦ Facial identification ◦ Robotics
Pharma ◦ Soft Sensors ◦ Non-Linear Control
Combination of Linear Regressions Model Non-Linear Data
14
12
10
8 Fit Raw Data
6
4
2
0 1
2
3
4
5
6
7
8
9
10
11
Linear Programming A mathematical/computer optimization technique Solve a system of linear equations Can be used to find the minimum and maximum states of process control Can be made subject to multiple constraints
Pusher Function Maximize Flow subject to constraints
Introduce new/advanced technology With: ◦ PAT ◦ Continuous Manufacturing
