Machine Learning and Dynamic Optimization for Engineers
Main.ShortCourse History
Hide minor edits - Show changes to output
Added lines 46-49:
(:cellnr:)
Dec 13-16, 2021
(:cell:)
Seoul, South Korea (16 participants)
Dec 13-16, 2021
(:cell:)
Seoul, South Korea (16 participants)
Changed line 33 from:
to:
Salt Lake City, Utah, USA (5 day) with [[http://www.apco-inc.com/upcoming-events|APCO, Inc]]
Added lines 42-45:
(:cellnr:)
Jan 4-8, 2021
(:cell:)
Seoul, South Korea (73 participants)
Jan 4-8, 2021
(:cell:)
Seoul, South Korea (73 participants)
Changed line 29 from:
Manama, Bahrain
to:
Manama, Bahrain with University of Bahrain
Changed line 5 from:
to:
Machine Learning and Dynamic Optimization is a 3 day short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on machine learning and system optimization. It includes hands-on tutorials in data science, classification, regression, predictive control, and optimization.
Changed line 1 from:
(:title Cyber-Physical Optimization:)
to:
(:title Machine Learning and Dynamic Optimization for Engineers:)
Changed line 1 from:
(:title Machine Learning and Dynamic Optimization:)
to:
(:title Cyber-Physical Optimization:)
Changed line 5 from:
to:
Cyber-Physical Optimization is a Machine Learning and Dynamic Optimization 3 day short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on machine learning and system optimization. It includes hands-on tutorials in data science, classification, regression, predictive control, and optimization.
Changed line 1 from:
(:title Short Course (3 day):)
to:
(:title Machine Learning and Dynamic Optimization:)
Changed line 5 from:
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on machine learning and cyber-physical system optimization.
to:
Machine Learning and Dynamic Optimization is a 3 day short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on machine learning and cyber-physical system optimization.
Changed line 29 from:
[[https://www.eventbrite.com/e/machine-learning-and-dynamic-optimization-tickets-89374594819?ref=elink|Salt Lake City, Utah, USA (5 day)]]
to:
[[https://www.eventbrite.com/e/machine-learning-and-dynamic-optimization-tickets-89374594819?ref=elink|Salt Lake City, Utah, USA (5 day)]] with [[http://www.apco-inc.com/upcoming-events|APCO, Inc]]
Added lines 15-16:
%width=550px%Attach:mlcourse2020_south_korea.png
Changed line 25 from:
Seoul, South Korea
to:
Seoul, South Korea (47 participants)
Added lines 12-13:
%width=550px%Attach:machine_learning_dynopt_course.png
Changed line 52 from:
[[https://apmonitor.com/pdc/index.php/Main/LinearProgramming|Gekko Introduction]]
to:
[[https://apmonitor.com/pdc/index.php/Main/LinearProgramming|Gekko Introduction]] and [[https://playground.tensorflow.org|Machine Learning]]
Changed lines 105-106 from:
[[Main/TCLabD|Lab D - MHE]]
to:
[[Main/TCLabD|Lab D - MHE]] or [[Main/TCLabE|Lab E - Hybrid Model Estimation]]
Changed line 110 from:
to:
Changed lines 112-113 from:
[[Main/TCLabE|Lab E - Hybrid Model Estimation]]
to:
[[https://github.com/APMonitor/begin_python|TCLab Incubator Project]]
Changed line 150 from:
[[Main/ControlTypes|Crane Pendulum]] or [[Main/ModelSimulation|Flight Control]]
to:
[[Main/DynamicOptimizationBenchmarks|Dynamic Optimization Benchmarks]]
Changed lines 152-153 from:
[[Main/TCLabF|Lab F - Linear Model Predictive Control]]
to:
[[Main/IntegralObjective|Integral Objective]] and [[Main/EconomicDynamicOptimization|Economic Objective]]
Changed lines 163-164 from:
[[Main/NonlinearControl|Nonlinear MPC]], [[Main/ControllerObjective|Control Objectives]]/[[Main/ControllerObjective|Tuning]], and [[Main/OrthogonalCollocation|Orthogonal Collocation]]
to:
[[Main/ControlTypes|Crane Pendulum]] or [[Main/ModelSimulation|Flight Control]]
Changed lines 165-166 from:
[[Main/TCLabG|Lab G -Nonlinear Model Predictive Control]]
to:
[[Main/TCLabF|Lab F - Linear Model Predictive Control]]
Changed line 176 from:
[[Main/DiscreteVariables|Mixed Integer Optimization]]
to:
[[Main/NonlinearControl|Nonlinear MPC]], [[Main/ControllerObjective|Control Objectives]]/[[Main/ControllerObjective|Tuning]], and [[Main/OrthogonalCollocation|Orthogonal Collocation]]
Changed lines 178-179 from:
to:
[[Main/TCLabG|Lab G -Nonlinear Model Predictive Control]]
Changed line 183 from:
[[Main/MultiObjectiveOptimization|Multi-Objective Optimization]]
to:
[[Main/DiscreteVariables|Mixed Integer Optimization]]
Changed lines 185-186 from:
to:
Mixed-Integer TCLab
Changed line 196 from:
to:
[[Main/MultiObjectiveOptimization|Multi-Objective Optimization]]
Changed lines 198-199 from:
[[Main/ProjectLab|Project Proposals]]
to:
[[Main/TCLabH|Lab H - Adaptive Model Predictive Control]]
Changed line 203 from:
to:
Group Projects
Changed lines 205-206 from:
[[Main/ProjectLab|Stage 1 - Develop Digital Twin Model]]
to:
[[Main/ProjectLab|Project Overview]]
Changed line 236 from:
to:
Group Project Proposals
Changed lines 238-239 from:
to:
[[Main/ProjectLab|Project Proposals]]
Changed line 241 from:
9:15 AM
to:
9:30 AM
Changed line 245 from:
[[Main/ProjectLab|Stage 1 - Develop Digital Twin Model (continued)]]
to:
[[Main/ProjectLab|Stage 1 - Develop Digital Twin Model]]
Changed line 25 from:
to:
[[https://www.eventbrite.com/e/machine-learning-and-dynamic-optimization-tickets-89374594819?ref=elink|Salt Lake City, Utah, USA (5 day)]]
Changed line 23 from:
May 12-14, 2020
to:
May 11-15, 2020
Changed line 25 from:
to:
<a href="https://www.eventbrite.com/e/machine-learning-and-dynamic-optimization-tickets-89374594819?ref=elink" target="_blank">Salt Lake City, Utah, USA (5 day)</a>
Changed line 103 from:
[[Main/EstimatorTypes|Moving Horizon Estimation]] with [[Main/EstimatorObjective|Objectives]] and [[Main/EstimatorTuning|Tuning]]
to:
[[Main/EstimatorTypes|Moving Horizon Estimation]] with [[Main/EstimatorObjective|Objectives]]/[[Main/EstimatorTuning|Tuning]]
Changed line 83 from:
Machine Learning [[Main/MachineLearningClassifier|Classification]], [[Main/DeepLearning|Regression]] and [[Main/LSTMNetwork|LSTM Networks]]
to:
Machine Learning [[Main/MachineLearningClassifier|Classification]], [[Main/DeepLearning|Deep Learning]], and [[Main/LSTMNetwork|LSTM Networks]]
Changed lines 72-73 from:
[[Main/TCLabA|Lab A - SISO Model]]
to:
[[Main/TCLabA|Lab A - SISO Model]] or [[Main/TCLabB|Lab B - MIMO Model]]
Changed line 83 from:
Machine Learning [[Main/MachineLearningClassifier|Classification]], [[Main/DeepLearning|Regression]], and [[Main/LSTMNetwork|LSTM Networks]]
to:
Machine Learning [[Main/MachineLearningClassifier|Classification]], [[Main/DeepLearning|Regression]] and [[Main/LSTMNetwork|LSTM Networks]]
Changed lines 85-86 from:
[[Main/TCLabB|Lab B - MIMO Model]]
to:
[[Main/MachineLearningClassifier|TCLab Classification]]
Changed line 90 from:
to:
[[Main/DynamicData|Data Regression]] for [[Main/DataSimulation|SISO]]/[[Main/ModelIdentification|MIMO]] Identification
Changed line 83 from:
to:
Machine Learning [[Main/MachineLearningClassifier|Classification]], [[Main/DeepLearning|Regression]], and [[Main/LSTMNetwork|LSTM Networks]]
Changed lines 163-164 from:
[[Main/NonlinearControl | Nonlinear MPC]] with [[Main/ControllerObjective|Control Objectives]]/[[Main/ControllerObjective|Tuning]]
to:
[[Main/NonlinearControl|Nonlinear MPC]], [[Main/ControllerObjective|Control Objectives]]/[[Main/ControllerObjective|Tuning]], and [[Main/OrthogonalCollocation|Orthogonal Collocation]]
Added lines 428-470:
}
</style>
(:htmlend:)
(:html:)
<style>
.button {
border-radius: 4px;
background-color: #1e90ff;
border: none;
color: #FFFFFF;
text-align: center;
font-size: 28px;
padding: 20px;
width: 250px;
transition: all 0.5s;
cursor: pointer;
margin: 5px;
}
.button span {
cursor: pointer;
display: inline-block;
position: relative;
transition: 0.5s;
}
.button span:after {
content: '\00bb';
position: absolute;
opacity: 0;
top: 0;
right: -20px;
transition: 0.5s;
}
.button:hover span {
padding-right: 25px;
}
.button:hover span:after {
opacity: 1;
right: 0;
</style>
(:htmlend:)
(:html:)
<style>
.button {
border-radius: 4px;
background-color: #1e90ff;
border: none;
color: #FFFFFF;
text-align: center;
font-size: 28px;
padding: 20px;
width: 250px;
transition: all 0.5s;
cursor: pointer;
margin: 5px;
}
.button span {
cursor: pointer;
display: inline-block;
position: relative;
transition: 0.5s;
}
.button span:after {
content: '\00bb';
position: absolute;
opacity: 0;
top: 0;
right: -20px;
transition: 0.5s;
}
.button:hover span {
padding-right: 25px;
}
.button:hover span:after {
opacity: 1;
right: 0;
Changed lines 5-11 from:
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on machine learning and cyber-physical system optimization. See the [[Main/HomePage|course syllabus]] for a registration link to indicate interest in one of the courses.
to:
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on machine learning and cyber-physical system optimization.
(:html:)
<a href='https://apmonitor.com/do/index.php/Main/InfoSheet'>
<button class="button"><span>Registration</span></button>
</a>
(:htmlend:)
(:html:)
<a href='https://apmonitor.com/do/index.php/Main/InfoSheet'>
<button class="button"><span>Registration</span></button>
</a>
(:htmlend:)
Changed line 77 from:
[[Main/OrthogonalCollocation|Collocation Methods]]
to:
[[Main/MachineLearningClassifier|Classification]] and [[Main/OrthogonalCollocation|Collocation]] Methods
Changed line 46 from:
[[https://apmonitor.com/pdc/index.php/Main/LinearProgramming|Linear Programming]]
to:
[[https://apmonitor.com/pdc/index.php/Main/LinearProgramming|Gekko Introduction]]
Changed line 170 from:
[[Main/DiscreteVariables|Mixed Integer]] and [[Main/MultiObjectiveOptimization|Multi-Objective Optimization]]
to:
[[Main/DiscreteVariables|Mixed Integer Optimization]]
Changed line 177 from:
[[Main/DeepLearning|Machine Learning]] and [[Main/DynamicData|Data Regression]] for [[Main/DataSimulation|SISO]]/[[Main/ModelIdentification|MIMO]] Identification
to:
[[Main/MultiObjectiveOptimization|Multi-Objective Optimization]]
Changed line 5 from:
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on machine learning and cyber-physical system optimization.
to:
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on machine learning and cyber-physical system optimization. See the [[Main/HomePage|course syllabus]] for a registration link to indicate interest in one of the courses.
Changed line 5 from:
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on engineering design and real-time control applications.
to:
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on machine learning and cyber-physical system optimization.
Changed line 8 from:
(:cell width=30%:)
to:
(:cell width=25%:)
Changed line 10 from:
(:cell width=70%:)
to:
(:cell width=40%:)
Changed line 1 from:
(:title Course on Cyber-Physical Optimization:)
to:
(:title Short Course (3 day):)
Changed lines 5-6 from:
to:
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on engineering design and real-time control applications.
(:table border=0 frame=hsides width=95%:)
(:cell width=30%:)
'''Date'''
(:cell width=70%:)
'''Location'''
(:cellnr:)
Jan 13-15, 2020
(:cell:)
Seoul, South Korea
(:cellnr:)
May 12-14, 2020
(:cell:)
Salt Lake City, Utah, USA
(:cellnr:)
June 16-18, 2020
(:cell:)
Idaho Falls, Idaho, USA
(:cellnr:)
July 14-16, 2020
(:cell:)
Houston, Texas, USA
(:tableend:)
Concepts taught in this course include machine learning, regression, classification, mathematical modeling, nonlinear programming, and advanced control methods such as model predictive control.
(:table border=0 frame=hsides width=95%:)
(:cell width=30%:)
'''Date'''
(:cell width=70%:)
'''Location'''
(:cellnr:)
Jan 13-15, 2020
(:cell:)
Seoul, South Korea
(:cellnr:)
May 12-14, 2020
(:cell:)
Salt Lake City, Utah, USA
(:cellnr:)
June 16-18, 2020
(:cell:)
Idaho Falls, Idaho, USA
(:cellnr:)
July 14-16, 2020
(:cell:)
Houston, Texas, USA
(:tableend:)
Concepts taught in this course include machine learning, regression, classification, mathematical modeling, nonlinear programming, and advanced control methods such as model predictive control.
Changed line 1 from:
(:title Short Course on Cyber-Physical Optimization:)
to:
(:title Course on Cyber-Physical Optimization:)
Changed line 1 from:
(:title Cyber-Physical Optimization:)
to:
(:title Short Course on Cyber-Physical Optimization:)
Changed lines 114-115 from:
[[https://apmonitor.com/pdc/index.php/Main/LinearProgramming|Linear Programming]]
to:
[[Main/DynamicControl|Velocity Control]]
Changed line 119 from:
[[Main/ControlTypes|Crane Pendulum]], [[Main/DynamicControl|Cruise Control]], or [[Main/ModelSimulation|Flight Control]]
to:
[[Main/ControlTypes|Crane Pendulum]] or [[Main/ModelSimulation|Flight Control]]
Changed line 282 from:
%width=550px%Attach:tclab_front.jpg
to:
%width=350px%Attach:tclab_front.jpg
Changed lines 282-284 from:
Each participant is provided with a [[https://apmonitor.com/do/index.php/Main/AdvancedTemperatureControl|Temperature Control Lab]] for hands-on exercises. Exercises are conducted in-class with additional supplementary material that can be completed after the class concludes. The objective of the 3 day short-course is to give enough background information so that researchers and practitioners can extend the methods to applications related to their field of study or industrial process.
to:
%width=550px%Attach:tclab_front.jpg
Each participant has a [[https://apmonitor.com/do/index.php/Main/AdvancedTemperatureControl|Temperature Control Lab]] for hands-on exercises. Exercises are conducted in-class with additional supplementary material that can be completed after the class concludes. The objective of the 3 day short-course is to give enough background information so that researchers and practitioners can extend the methods to applications related to their field of study or industrial process.
Each participant has a [[https://apmonitor.com/do/index.php/Main/AdvancedTemperatureControl|Temperature Control Lab]] for hands-on exercises. Exercises are conducted in-class with additional supplementary material that can be completed after the class concludes. The objective of the 3 day short-course is to give enough background information so that researchers and practitioners can extend the methods to applications related to their field of study or industrial process.
Deleted lines 6-7:
Deleted line 247:
Added lines 281-282:
Each participant is provided with a [[https://apmonitor.com/do/index.php/Main/AdvancedTemperatureControl|Temperature Control Lab]] for hands-on exercises. Exercises are conducted in-class with additional supplementary material that can be completed after the class concludes. The objective of the 3 day short-course is to give enough background information so that researchers and practitioners can extend the methods to applications related to their field of study or industrial process.
Changed line 105 from:
'''Day 1'''
to:
'''Day 2'''
Changed line 198 from:
'''Day 1'''
to:
'''Day 3'''
Changed line 11 from:
(:cell width=10%:)
to:
(:cell width=15%:)
Changed line 13 from:
(:cell width=50%:)
to:
(:cell width=45%:)
Changed lines 104-106 from:
(:cell width=10%:)
'''Day2'''
(:cell width=50%:)
'''Day
(:cell width=
to:
(:cell width=15%:)
'''Day 1'''
(:cell width=45%:)
'''Day 1'''
(:cell width=45%:)
Changed lines 197-199 from:
(:cell width=10%:)
'''Day3'''
(:cell width=50%:)
'''Day
(:cell width=
to:
(:cell width=15%:)
'''Day 1'''
(:cell width=45%:)
'''Day 1'''
(:cell width=45%:)
Added lines 1-398:
(:title Cyber-Physical Optimization:)
(:keywords schedule, course, cyber-physical, machine learning, short course, dynamic optimization, engineering:)
(:description Short course on machine learning and dynamic optimization for scientists and engineers.:)
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on engineering design and real-time control applications. Concepts taught in this course include machine learning, regression, classification, mathematical modeling, nonlinear programming, and advanced control methods such as model predictive control.
Each participant is provided with a [[https://apmonitor.com/do/index.php/Main/AdvancedTemperatureControl|Temperature Control Lab]] for hands-on exercises. Exercises are conducted in-class with additional supplementary material that can be completed after the class concludes. The objective of the 3 day short-course is to give enough background information so that researchers and practitioners can extend the methods to applications related to their field of study or industrial process.
(:table border=0 frame=hsides width=95%:)
(:cell width=10%:)
'''Day 1'''
(:cell width=50%:)
'''Topic'''
(:cell width=40%:)
'''Activity'''
(:cellnr:)
9:00 AM
(:cell:)
Overview of [[https://youtu.be/WCTTY4baYLk|Course]], [[https://apmonitor.com/pdc/index.php/Main/OptimizationIntroduction|Optimization]], and [[https://gekko.readthedocs.io/en/latest/|GEKKO]]
(:cell:)
[[https://apmonitor.com/pdc/index.php/Main/LinearProgramming|Linear Programming]]
(:cellnr:)
9:30 AM
(:cell:)
[[https://apmonitor.com/pdc/index.php/Main/ArduinoTemperatureControl|TCLab Overview]]
(:cell:)
[[https://github.com/APMonitor/begin_python|Begin Python with TCLab]]
(:cellnr:)
10:30 AM
(:cell:)
Break
(:cell:)
(:cellnr:)
10:45 AM
(:cell:)
[[Main/DynamicModeling|Digital Twin]] with [[Main/ModelFormulation|Physics-based Simulation]]
(:cell:)
[[Main/TCLabA|Lab A - SISO Model]]
(:cellnr:)
12:00 PM
(:cell:)
Lunch Break
(:cell:)
(:cellnr:)
1:00 PM
(:cell:)
[[Main/OrthogonalCollocation|Collocation Methods]]
(:cell:)
[[Main/TCLabB|Lab B - MIMO Model]]
(:cellnr:)
2:00 PM
(:cell:)
[[Main/DeepLearning|Machine Learning]] and [[Main/DynamicData|Data Regression]] for [[Main/DataSimulation|SISO]]/[[Main/ModelIdentification|MIMO]] Identification
(:cell:)
[[Main/TCLabC|Lab C - Parameter Estimation]]
(:cellnr:)
3:00 PM
(:cell:)
Break
(:cell:)
(:cellnr:)
3:30 PM
(:cell:)
[[Main/EstimatorTypes|Moving Horizon Estimation]] with [[Main/EstimatorObjective|Objectives]] and [[Main/EstimatorTuning|Tuning]]
(:cell:)
[[Main/TCLabD|Lab D - MHE]]
(:cellnr:)
4:30 PM
(:cell:)
[[Main/DynamicOptimizationBenchmarks|Dynamic Optimization Benchmarks]]
(:cell:)
[[Main/TCLabE|Lab E - Hybrid Model Estimation]]
(:cellnr:)
5:30 PM
(:cell:)
Day 1 Review
(:cell:)
Day 1 Assessment Activity
(:cellnr:)
6:00 PM
(:cell:)
Conclude Day 1
(:cell:)
(:tableend:)
----
(:table border=0 frame=hsides width=95%:)
(:cell width=10%:)
'''Day 2'''
(:cell width=50%:)
'''Topic'''
(:cell width=40%:)
'''Activity'''
(:cellnr:)
9:00 AM
(:cell:)
[[Main/DynamicControl|Dynamic Control Introduction]]
(:cell:)
[[https://apmonitor.com/pdc/index.php/Main/LinearProgramming|Linear Programming]]
(:cellnr:)
9:30 AM
(:cell:)
[[Main/ControlTypes|Crane Pendulum]], [[Main/DynamicControl|Cruise Control]], or [[Main/ModelSimulation|Flight Control]]
(:cell:)
[[Main/TCLabF|Lab F - Linear Model Predictive Control]]
(:cellnr:)
10:30 AM
(:cell:)
Break
(:cell:)
(:cellnr:)
10:45 AM
(:cell:)
[[Main/NonlinearControl | Nonlinear MPC]] with [[Main/ControllerObjective|Control Objectives]]/[[Main/ControllerObjective|Tuning]]
(:cell:)
[[Main/TCLabG|Lab G -Nonlinear Model Predictive Control]]
(:cellnr:)
12:00 PM
(:cell:)
Lunch Break
(:cell:)
(:cellnr:)
1:00 PM
(:cell:)
[[Main/DiscreteVariables|Mixed Integer]] and [[Main/MultiObjectiveOptimization|Multi-Objective Optimization]]
(:cell:)
Mixed-Integer TCLab
(:cellnr:)
2:00 PM
(:cell:)
[[Main/DeepLearning|Machine Learning]] and [[Main/DynamicData|Data Regression]] for [[Main/DataSimulation|SISO]]/[[Main/ModelIdentification|MIMO]] Identification
(:cell:)
[[Main/TCLabH|Lab H - Adaptive Model Predictive Control]]
(:cellnr:)
3:00 PM
(:cell:)
Break
(:cell:)
(:cellnr:)
3:30 PM
(:cell:)
Create Project Proposals and Evaluate Resources
(:cell:)
[[Main/ProjectLab|Project Proposals]]
(:cellnr:)
4:30 PM
(:cell:)
Determine Application Scope
(:cell:)
[[Main/ProjectLab|Stage 1 - Develop Digital Twin Model]]
(:cellnr:)
5:30 PM
(:cell:)
Day 2 Review
(:cell:)
Day 2 Assessment Activity
(:cellnr:)
6:00 PM
(:cell:)
Conclude Day 2
(:cell:)
(:tableend:)
----
(:table border=0 frame=hsides width=95%:)
(:cell width=10%:)
'''Day 3'''
(:cell width=50%:)
'''Topic'''
(:cell width=40%:)
'''Activity'''
(:cellnr:)
9:00 AM
(:cell:)
Overview of Group Project
(:cell:)
(:cellnr:)
9:15 AM
(:cell:)
Physics-based Modeling Review
(:cell:)
[[Main/ProjectLab|Stage 1 - Develop Digital Twin Model (continued)]]
(:cellnr:)
10:30 AM
(:cell:)
Break
(:cell:)
(:cellnr:)
10:45 AM
(:cell:)
Machine Learning and Time-Series Regression Review
(:cell:)
[[Main/ProjectLab|Stage 2 - Machine learning or time-series models]]
(:cellnr:)
12:00 PM
(:cell:)
Lunch Break
(:cell:)
(:cellnr:)
1:00 PM
(:cell:)
Parameter Regression Review
(:cell:)
[[Main/ProjectLab|Stage 3 - Parameter Regression]]
(:cellnr:)
2:00 PM
(:cell:)
Moving Horizon Estimation Review
(:cell:)
[[Main/ProjectLab|Stage 4 - Adaptive Model Update (MHE)]]
(:cellnr:)
3:00 PM
(:cell:)
Break
(:cell:)
(:cellnr:)
3:30 PM
(:cell:)
Model Predictive Control Review
(:cell:)
[[Main/ProjectLab|Stage 5 - Model Predictive Control]]
(:cellnr:)
4:30 PM
(:cell:)
(:cell:)
Group Project Presentation Preparation
(:cellnr:)
5:30 PM
(:cell:)
(:cell:)
Group Project Presentations (3 min each)
(:cellnr:)
6:00 PM
(:cell:)
Conclude Day 3 and Course
(:cell:)
Certificates of Completion
(:tableend:)
(:html:)
<style type="text/css">
div.table-title {
display: block;
margin: auto;
max-width: 600px;
padding:5px;
width: 100%;
}
.table-title h3 {
color: #fafafa;
}
.table-fill {
background: white;
border-radius:3px;
border-collapse: collapse;
height: 320px;
margin: auto;
max-width: 600px;
padding:5px;
width: 100%;
box-shadow: 0 5px 10px rgba(0, 0, 0, 0.1);
animation: float 5s infinite;
}
th {
color:#D5DDE5;;
background:#1b1e24;
border-bottom:4px solid #9ea7af;
border-right: 1px solid #343a45;
text-align:left;
vertical-align:middle;
}
th:first-child {
border-top-left-radius:3px;
}
th:last-child {
border-top-right-radius:3px;
border-right:none;
}
tr {
border-top: 1px solid #C1C3D1;
border-bottom-: 1px solid #C1C3D1;
color:#666B85;
font-weight:normal;
}
tr:hover td {
border-top: 1px solid #22262e;
border-bottom: 1px solid #22262e;
}
tr:first-child {
border-top:none;
}
tr:last-child {
border-bottom:none;
}
tr:nth-child(odd) td {
background:#EEEEEE;
}
tr:last-child td:first-child {
border-bottom-left-radius:3px;
}
tr:last-child td:last-child {
border-bottom-right-radius:3px;
}
td {
background:#FFFFFF;
padding:5px;
text-align:left;
vertical-align:middle;
border-right: 1px solid #C1C3D1;
}
td:last-child {
border-right: 0px;
}
th.text-left {
text-align: left;
}
th.text-center {
text-align: center;
}
th.text-right {
text-align: right;
}
td.text-left {
text-align: left;
}
td.text-center {
text-align: center;
}
td.text-right {
text-align: right;
}
</style>
(:htmlend:)
(:keywords schedule, course, cyber-physical, machine learning, short course, dynamic optimization, engineering:)
(:description Short course on machine learning and dynamic optimization for scientists and engineers.:)
Machine Learning and Dynamic Optimization is a short course on the theory and applications of numerical methods for solution of time-varying systems with a focus on engineering design and real-time control applications. Concepts taught in this course include machine learning, regression, classification, mathematical modeling, nonlinear programming, and advanced control methods such as model predictive control.
Each participant is provided with a [[https://apmonitor.com/do/index.php/Main/AdvancedTemperatureControl|Temperature Control Lab]] for hands-on exercises. Exercises are conducted in-class with additional supplementary material that can be completed after the class concludes. The objective of the 3 day short-course is to give enough background information so that researchers and practitioners can extend the methods to applications related to their field of study or industrial process.
(:table border=0 frame=hsides width=95%:)
(:cell width=10%:)
'''Day 1'''
(:cell width=50%:)
'''Topic'''
(:cell width=40%:)
'''Activity'''
(:cellnr:)
9:00 AM
(:cell:)
Overview of [[https://youtu.be/WCTTY4baYLk|Course]], [[https://apmonitor.com/pdc/index.php/Main/OptimizationIntroduction|Optimization]], and [[https://gekko.readthedocs.io/en/latest/|GEKKO]]
(:cell:)
[[https://apmonitor.com/pdc/index.php/Main/LinearProgramming|Linear Programming]]
(:cellnr:)
9:30 AM
(:cell:)
[[https://apmonitor.com/pdc/index.php/Main/ArduinoTemperatureControl|TCLab Overview]]
(:cell:)
[[https://github.com/APMonitor/begin_python|Begin Python with TCLab]]
(:cellnr:)
10:30 AM
(:cell:)
Break
(:cell:)
(:cellnr:)
10:45 AM
(:cell:)
[[Main/DynamicModeling|Digital Twin]] with [[Main/ModelFormulation|Physics-based Simulation]]
(:cell:)
[[Main/TCLabA|Lab A - SISO Model]]
(:cellnr:)
12:00 PM
(:cell:)
Lunch Break
(:cell:)
(:cellnr:)
1:00 PM
(:cell:)
[[Main/OrthogonalCollocation|Collocation Methods]]
(:cell:)
[[Main/TCLabB|Lab B - MIMO Model]]
(:cellnr:)
2:00 PM
(:cell:)
[[Main/DeepLearning|Machine Learning]] and [[Main/DynamicData|Data Regression]] for [[Main/DataSimulation|SISO]]/[[Main/ModelIdentification|MIMO]] Identification
(:cell:)
[[Main/TCLabC|Lab C - Parameter Estimation]]
(:cellnr:)
3:00 PM
(:cell:)
Break
(:cell:)
(:cellnr:)
3:30 PM
(:cell:)
[[Main/EstimatorTypes|Moving Horizon Estimation]] with [[Main/EstimatorObjective|Objectives]] and [[Main/EstimatorTuning|Tuning]]
(:cell:)
[[Main/TCLabD|Lab D - MHE]]
(:cellnr:)
4:30 PM
(:cell:)
[[Main/DynamicOptimizationBenchmarks|Dynamic Optimization Benchmarks]]
(:cell:)
[[Main/TCLabE|Lab E - Hybrid Model Estimation]]
(:cellnr:)
5:30 PM
(:cell:)
Day 1 Review
(:cell:)
Day 1 Assessment Activity
(:cellnr:)
6:00 PM
(:cell:)
Conclude Day 1
(:cell:)
(:tableend:)
----
(:table border=0 frame=hsides width=95%:)
(:cell width=10%:)
'''Day 2'''
(:cell width=50%:)
'''Topic'''
(:cell width=40%:)
'''Activity'''
(:cellnr:)
9:00 AM
(:cell:)
[[Main/DynamicControl|Dynamic Control Introduction]]
(:cell:)
[[https://apmonitor.com/pdc/index.php/Main/LinearProgramming|Linear Programming]]
(:cellnr:)
9:30 AM
(:cell:)
[[Main/ControlTypes|Crane Pendulum]], [[Main/DynamicControl|Cruise Control]], or [[Main/ModelSimulation|Flight Control]]
(:cell:)
[[Main/TCLabF|Lab F - Linear Model Predictive Control]]
(:cellnr:)
10:30 AM
(:cell:)
Break
(:cell:)
(:cellnr:)
10:45 AM
(:cell:)
[[Main/NonlinearControl | Nonlinear MPC]] with [[Main/ControllerObjective|Control Objectives]]/[[Main/ControllerObjective|Tuning]]
(:cell:)
[[Main/TCLabG|Lab G -Nonlinear Model Predictive Control]]
(:cellnr:)
12:00 PM
(:cell:)
Lunch Break
(:cell:)
(:cellnr:)
1:00 PM
(:cell:)
[[Main/DiscreteVariables|Mixed Integer]] and [[Main/MultiObjectiveOptimization|Multi-Objective Optimization]]
(:cell:)
Mixed-Integer TCLab
(:cellnr:)
2:00 PM
(:cell:)
[[Main/DeepLearning|Machine Learning]] and [[Main/DynamicData|Data Regression]] for [[Main/DataSimulation|SISO]]/[[Main/ModelIdentification|MIMO]] Identification
(:cell:)
[[Main/TCLabH|Lab H - Adaptive Model Predictive Control]]
(:cellnr:)
3:00 PM
(:cell:)
Break
(:cell:)
(:cellnr:)
3:30 PM
(:cell:)
Create Project Proposals and Evaluate Resources
(:cell:)
[[Main/ProjectLab|Project Proposals]]
(:cellnr:)
4:30 PM
(:cell:)
Determine Application Scope
(:cell:)
[[Main/ProjectLab|Stage 1 - Develop Digital Twin Model]]
(:cellnr:)
5:30 PM
(:cell:)
Day 2 Review
(:cell:)
Day 2 Assessment Activity
(:cellnr:)
6:00 PM
(:cell:)
Conclude Day 2
(:cell:)
(:tableend:)
----
(:table border=0 frame=hsides width=95%:)
(:cell width=10%:)
'''Day 3'''
(:cell width=50%:)
'''Topic'''
(:cell width=40%:)
'''Activity'''
(:cellnr:)
9:00 AM
(:cell:)
Overview of Group Project
(:cell:)
(:cellnr:)
9:15 AM
(:cell:)
Physics-based Modeling Review
(:cell:)
[[Main/ProjectLab|Stage 1 - Develop Digital Twin Model (continued)]]
(:cellnr:)
10:30 AM
(:cell:)
Break
(:cell:)
(:cellnr:)
10:45 AM
(:cell:)
Machine Learning and Time-Series Regression Review
(:cell:)
[[Main/ProjectLab|Stage 2 - Machine learning or time-series models]]
(:cellnr:)
12:00 PM
(:cell:)
Lunch Break
(:cell:)
(:cellnr:)
1:00 PM
(:cell:)
Parameter Regression Review
(:cell:)
[[Main/ProjectLab|Stage 3 - Parameter Regression]]
(:cellnr:)
2:00 PM
(:cell:)
Moving Horizon Estimation Review
(:cell:)
[[Main/ProjectLab|Stage 4 - Adaptive Model Update (MHE)]]
(:cellnr:)
3:00 PM
(:cell:)
Break
(:cell:)
(:cellnr:)
3:30 PM
(:cell:)
Model Predictive Control Review
(:cell:)
[[Main/ProjectLab|Stage 5 - Model Predictive Control]]
(:cellnr:)
4:30 PM
(:cell:)
(:cell:)
Group Project Presentation Preparation
(:cellnr:)
5:30 PM
(:cell:)
(:cell:)
Group Project Presentations (3 min each)
(:cellnr:)
6:00 PM
(:cell:)
Conclude Day 3 and Course
(:cell:)
Certificates of Completion
(:tableend:)
(:html:)
<style type="text/css">
div.table-title {
display: block;
margin: auto;
max-width: 600px;
padding:5px;
width: 100%;
}
.table-title h3 {
color: #fafafa;
}
.table-fill {
background: white;
border-radius:3px;
border-collapse: collapse;
height: 320px;
margin: auto;
max-width: 600px;
padding:5px;
width: 100%;
box-shadow: 0 5px 10px rgba(0, 0, 0, 0.1);
animation: float 5s infinite;
}
th {
color:#D5DDE5;;
background:#1b1e24;
border-bottom:4px solid #9ea7af;
border-right: 1px solid #343a45;
text-align:left;
vertical-align:middle;
}
th:first-child {
border-top-left-radius:3px;
}
th:last-child {
border-top-right-radius:3px;
border-right:none;
}
tr {
border-top: 1px solid #C1C3D1;
border-bottom-: 1px solid #C1C3D1;
color:#666B85;
font-weight:normal;
}
tr:hover td {
border-top: 1px solid #22262e;
border-bottom: 1px solid #22262e;
}
tr:first-child {
border-top:none;
}
tr:last-child {
border-bottom:none;
}
tr:nth-child(odd) td {
background:#EEEEEE;
}
tr:last-child td:first-child {
border-bottom-left-radius:3px;
}
tr:last-child td:last-child {
border-bottom-right-radius:3px;
}
td {
background:#FFFFFF;
padding:5px;
text-align:left;
vertical-align:middle;
border-right: 1px solid #C1C3D1;
}
td:last-child {
border-right: 0px;
}
th.text-left {
text-align: left;
}
th.text-center {
text-align: center;
}
th.text-right {
text-align: right;
}
td.text-left {
text-align: left;
}
td.text-center {
text-align: center;
}
td.text-right {
text-align: right;
}
</style>
(:htmlend:)