Upload
others
View
0
Download
0
Embed Size (px)
Citation preview
This report was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor any agency thereof, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.
Learning process models from simula2ons
This report was prepared as an account of work sponsored by an agency of the United States Government. Neither the United States Government nor any agency thereof, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.
Alison Cozad1, Nick Sahinidis12, and David Miller2
1 Department of Chemical Engineering, Carnegie Mellon University 2 Na2onal Energy and Technology Laboratory
Carnegie Mellon University
PROBLEM STATEMENT
2
! Challenges: ‒ Lack of an algebraic model ‒ Computa2onally costly simula2ons ‒ OKen noisy func2on evalua2ons ‒ Scarcity of fully robust simula2ons
Process simulation
Carnegie Mellon University
SIMULATION-‐BASED METHODS
3
! Es2mated gradient based ‒ Finite element, perturba2on analysis,
etc. ! Deriva2ve-‐free op2miza2on (DFO)
‒ Local/global ‒ Stochas2c/determinis2c
! What is modeled? ‒ Objec2ve, objec2ve + constraints,
disaggregated system ! Type of model
‒ Linear/nonlinear ‒ Simple/Complex ‒ Algebraic/black-‐box
! Op2mizer ‒ Deriva2ve/deriva2ve-‐free
Simulator Optimizer Simulator Modeler Optimizer
Indirect methods
Direct methods
Carnegie Mellon University
RECENT WORK IN CHEMICAL ENG
4
Simulator Modeler Optimizer
Indirect methods
Full process
Disaggregated
Kriging Neural nets Other
§ Michalopoulos, et. Al., 2001
§ Palmer and Realff, 2002
§ Huang, et. al., 2006 § Davis and
Ierapetriton, 2012
§ Caballero and Grossmann, 2008
§ Palmer and Realff, 2002
§ Henao and Maravelias, 2011
Carnegie Mellon University
PROCESS DISAGGREGATION
Surrogate models of blocks
Disaggregated blocks of process unit(s)
Simula2on
f1(x) f3(x) f2(x)
Algebraic constraints Mass balances Design specs
Nonlinear program Algebraic model for optimization
Carnegie Mellon University
! Build a model of output variables z as a func2on of input variables x over a specified interval
MODELING PROBLEM STATEMENT
Independent variables: Operating conditions, inlet flow
properties, unit geometry
Dependent variables: Efficiency, outlet flow conditions,
conversions, heat flow, etc.
6
Process simulation
Carnegie Mellon University
! Model ques2ons: ‒ What is the func2onal form of the model? ‒ How complex of a model is needed? ‒ Will this be tractable in an algebraic op2miza2on framework?
! Sampling ques2ons: ‒ How many sample points are needed to define an accurate model? ‒ Where should these points be sampled?
! Desired model traits: ü Accurate ü Tractable in algebraic op2miza2on: Simple func2onal forms ü Generated from a minimal data set
MODELING PROBLEM STATEMENT
7
Carnegie Mellon University
ALGORITHMIC FLOWSHEET
true
Stop
Update training data set
Start
false
Initial sampling
Build surrogate model
Adaptive sampling
Model converged?
8
Carnegie Mellon University
ALGORITHMIC FLOWSHEET
true
Stop
Update training data set
Start
false
Initial sampling
Build surrogate model
Adaptive sampling
Model converged?
9
Carnegie Mellon University
! Goal: To generate an ini2al set of input variables to evenly sample the problem space
! La2n hypercube design of experiments -‐ Space-‐filling design
DESIGN OF EXPERIMENTS
10
Carnegie Mellon University
! AKer running the design of experiments, we will evaluate the black-‐box func2on to determine each zi
INITIAL SAMPLING
Ini2al training set
11
Process simulation
Carnegie Mellon University
ALGORITHMIC FLOWSHEET
true
Stop
Update training data set
Start
false
Initial sampling
Build surrogate model
Adaptive sampling
Model converged?
12
Carnegie Mellon University
! Goal: Iden2fy the func2onal form and complexity of the surrogate models
! Func2onal form: ‒ General func2onal form is unknown: Our method will iden2fy
models with combina2ons of simple basis func2ons
MODEL IDENTIFICATION
13
Carnegie Mellon University
OVERFITTING AND TRUE ERROR
14
! Empirical error: ‒ Error between the model and the sampled data points
! True error: ‒ Error between the model and the true func2on
Complexity
Erro
r
Ideal Model
Overfitting Underfitting
Carnegie Mellon University
SURROGATE MODEL
15
! Surrogate model can have the form
! Low-‐complexity desired surrogate form
! is chosen to ‒ Reduce overfidng ‒ Achieve surrogate simplicity for a tractable final op2miza2on model
Carnegie Mellon University
BEST SUBSET METHOD
16
! Generalized best subset problem:
! Goodness of fit: ‒ Corrected Akaike Informa2on Criterion (AICc)
• Gives an es2mate of the difference between a model and the true func2on
Accuracy + Complexity
Carnegie Mellon University
FINAL BEST SUBSET MODEL
17
! This model is solved for increasing values of T un2l the AICc worsens
Carnegie Mellon University
ALGORITHMIC FLOWSHEET
true
Stop
Update training data set
Start
false
Initial sampling
Build surrogate model
Adaptive sampling
Model converged?
18
Carnegie Mellon University
! Goal: Search the problem space for areas of model inconsistency or model mismatch
! More succinctly, we are trying to find points that maximizes the model error with respect to the independent variables
‒ Op2mized using a black-‐box or deriva2ve-‐free solver (SNOBFIT) [Huyer and Neumaier, 08]
ADAPTIVE SAMPLING
Surrogate model
19
Carnegie Mellon University
ADAPTIVE SAMPLING ! Goal: Search the problem space for areas of model
inconsistency or model mismatch
! More succinctly, we are trying to find points that maximizes the model error with respect to the independent variables
Black-box function Data points Surrogate model
Carnegie Mellon University
ADAPTIVE SAMPLING ! Goal: Search the problem space for areas of model
inconsistency or model mismatch
! More succinctly, we are trying to find points that maximizes the model error with respect to the independent variables
Surrogate model
Black-box function Data points True
minimum
Current surrogate optimum
Carnegie Mellon University
ADAPTIVE SAMPLING ! Goal: Search the problem space for areas of model
inconsistency or model mismatch
! More succinctly, we are trying to find points that maximizes the model error with respect to the independent variables
Black-box function Data points Surrogate model
New sample point after interrogating
the surrogate
Model error
Carnegie Mellon University
ADAPTIVE SAMPLING ! Goal: Search the problem space for areas of model
inconsistency or model mismatch
! More succinctly, we are trying to find points that maximizes the model error with respect to the independent variables
Black-box function Data points New surrogate model
Carnegie Mellon University
ERROR MAXIMIZATION SAMPLING
24
! Informa2on gained using error maximiza2on sampling: 1. New data point loca2ons that will be used to befer train the next
itera2on’s surrogate model
2. Conserva2ve es2mate of the true model error • Defines a stopping criterion • Es2mates the final model error
Carnegie Mellon University
COMPUTATIONAL TESTING
25
! Surrogate genera2on methods have been implemented into a package:
ALAMO (Automated Learning of Algebraic Models for Op2miza2on)
! Modeling methods compared ‒ MIP – Proposed methodology ‒ EBS – Exhaus2ve best subset method
• Note: due to high CPU 2mes this was only tested on smaller problems ‒ LASSO – The lasso regulariza2on ‒ OLR – Ordinary least-‐squares regression
! Sampling methods compared ‒ DFO – Proposed error maximiza2on technique ‒ SLH – Single la2n hypercube (no feedback)
Carnegie Mellon University
DESCRIPTION – TEST SET A
26
! Two and three input black-‐box func2ons randomly chosen basis func2ons available to the algorithms with varying complexity from 2 to 10 terms
! Basis func2ons allowed:
Carnegie Mellon University
RESULTS – TEST SET A
27
Model accuracy Function evaluations
45 test problems, repeated 5 2mes, tested against 1000 independent data points
Carnegie Mellon University
MODEL COMPLEXITY – TEST SET A
28
Carnegie Mellon University
DESCRIPTION – TEST SET B
29
! Two input black-‐box func2ons with basis func2ons unavailable to the algorithms with
Carnegie Mellon University
RESULTS – TEST SET B
30
Model accuracy Function evaluations
12 test problems, repeated 5 2mes, tested against 1000 independent data points
Carnegie Mellon University
TEST CASE: CUMENE PRODUCTION
Generate Models:
Over the Range:
Benzene Propylene
Cumene
31
Cumene producFon simulaFon is form the Aspen Plus® Library
Carnegie Mellon University
! Maximum error found at each itera2on may increase ‒ Due to the deriva2ve-‐free solver is given more informa2on at each itera2on
GENERATING THE SURROGATES
0%
2%
4%
6%
8%
10%
12%
14%
1 2 3 4 5
Max
imum
real
tive e
rror
Iterations
xCTreactFrec
yes
true false
Initial data set: 3 points Final data set: 23 points
Carnegie Mellon University
PROCESS OPTIMIZATION
Benzene Propylene
Cumene
33
Carnegie Mellon University
CARBON CAPTURE OPTIMIZATION
34
! Problem statement: Capture 90% of CO2 from a 350MW power plant’s post combus2on flue gas with minimal increase in the cost of electricity
! Design considera2ons: ‒ Capture technology
• Bubbling fluidized bed, moving bed, fast fluidized bed, transport bed, etc.
‒ Number of reactors ‒ Reactor configura2on and geometry ‒ Opera2ng condi2ons
350 MW Coal fired power
plant
CO2 rich flue gas
CO2 poor flue gas
Ads
orbe
r
Reg
ener
ator
Carnegie Mellon University
SUPERSTRUCTURE OPTIMIZATION
35
Flue gas from power plant
a1
a2
a3
a4
d1
d2
d3
d4
Solid sorbent stream
Cleaned gas
Other capture trains
Cooling water Steam Work
Solid sorbent CO2 Capture
Carnegie Mellon University 36
! Model outputs (13 total) ! Geometry required (2) ! Opera2ng condi2on required (1) ! Gas mole frac2ons (2) ! Solid composi2ons (2) ! Flow rates (2) ! Outlet temperatures (3) ! Design constraint (1)
BUBBLING FLUIDIZED BED
! Model inputs (14 total) ‒ Geometry (3) ‒ Opera2ng condi2ons (4) ‒ Gas mole frac2ons (2) ‒ Solid composi2ons (2) ‒ Flow rates (4)
Bubbling fluidized bed adsorber diagram Outlet gas Solid feed
CO2 rich gas CO2 rich solid outlet
Cooling water
Carnegie Mellon University
ADAPTIVE SAMPLING
yes
true false
0%
4%
8%
12%
16%
1 3 5 7 9
Est
imat
ed re
lativ
e err
or
IterationsFGas_out Gas_In_P THX_out Tgas_out Tsorb_outdt gamma_out lp vtr xH2O_ads_outxHCO3_ads_out zCO2_gas_out zH2O_gas_out
Progression of mean error through the algorithm
Initial data set: 137 pts
Final data set: 261
Carnegie Mellon University
EXAMPLE MODELS Solid feed
CO2 rich gas
Cooling water
38
Carnegie Mellon University
SUPERSTRUCTURE OPTIMIZATION
39
Flue gas from power plant
a1
a2
a3
a4
d1
d2
d3
d4
Solid sorbent stream
Cleaned gas
Other capture trains
Cooling water Steam Work
Solid sorbent CO2 Capture
Carnegie Mellon University
SUPERSTRUCTURE OPTIMIZATION
40
Flue gas from power plant
a1
a2
a3
a4
d1
d2
d3
d4
Solid sorbent stream
Cleaned gas
Other capture trains
Cooling water Steam Work
Solid sorbent CO2 Capture
a1
a2
a3
a4
Add the set of surrogate models
generated for each adsorber
Solid sorbent CO2 Capture
Carnegie Mellon University
a1
Flue gas from power plant
PRELIMINARY RESULTS
41
a2
d1
Solid sorbent stream
Cleaned gas
Other capture trains
Regen. gas
Cooling water Steam Work
Carnegie Mellon University
! The algorithm we developed is able to model black-‐box func2ons for use in op2miza2on such that the models are ü Accurate ü Tractable in an op2miza2on framework (low-‐complexity models) ü Generated from a minimal number of func2on evalua2ons
! Surrogate models can then be incorporated within a op2miza2on framework flexible objec2ve func2ons and addi2onal constraints
CONCLUSIONS
Automated Learning of Algebraic Models for Optimization ALAMO
42
Carnegie Mellon University
MODEL REDUCTION TECHNIQUES
43
! Qualita2ve tradeoffs of model reduc2on methods
Backward elimina2on [Oosterhof, 63] Forward selec2on [Hamaker, 62]
Stepwise regression [Efroymson, 60]
Regularized regression techniques • Penalize the least squares objec3ve using the magnitude of the regressors
Best subset methods • Enumerate all possible subsets
Carnegie Mellon University
BEST SUBSET METHOD
44
! Surrogate subset model:
! Mixed-‐integer surrogate subset model:
! Generalized best subset problem mixed-‐integer formula2on:
Carnegie Mellon University
! Further reformula2on ‒ Replace bilinear terms with big-‐M constraints
‒ Decouple objec2ve into two problems
‒ Inner minimiza2on objec2ve reformula2on
MIXED-‐INTEGER PROBLEM
45
b) basis and coefficient selection
a) model sizing
Carnegie Mellon University
PROBLEM SIMPLIFICATIONS
46
‒ Inner problem • Sta2onarity condi2on used to solve for con2nuous variables
• Linear objec2ve used to solved for integer variables
-‐5
-‐4
-‐3
-‐2
-‐1
00 2 4 6
AICc
Number of basis functions in modelT
Solution
! Simplifica2ons: ‒ Outer problem
• The outer problem is parameterized by T and a local minima is found