CHE 55400

Smart Manufacturing In Process Industries
Smart Manufacturing in the Process Industries

About Course Insights
Course Insights is a platform for faculty to share detailed information about the courses they teach. This page is not to be interpreted as being the official course syllabus for this course.
About the Course
This course surveys the tools and techniques, which are relevant to support the multiple levels of technical decisions that arise in modern integrated operation of manufacturing resources with examples drawn from the chemical, petrochemical, pharmaceutical industries – examples of the process industries. The real time generation and sharing of associated data and knowledge via relevant IT methodology and the effective use of this information in the various levels of the process operations management hierarchy are currently termed Industry 4.0 (Europe) and Smart Manufacturing (US). The topics covered in the course span all of the technical components and decision levels in the operations decision hierarchy. Topics include the role of on-line and at-line process measurements, elements of sensor network design, information systems to support process operations, plant data reconciliation, detection and diagnosis of process faults, condition-based monitoring of plant assets, plant wide control, real time process optimization, production planning and scheduling, and supply chain management. Each topic will be addressed by first summarizing the basic role and scope of that component, then discussing the elements of the decision problem, and outlining some representative tools available to address that decision problem. Each major topic will include a lecture given by an industrial practitioner who will offer a perspective on the state of industrial practice.
 
Prerequisites: A basic understanding of Python Programming
Course Goals/Learning Objectives
  1. Explain the key decisions that are made at each level of the operational hierarchy of an integrated process system
  2. Define what the various types of manufacturing and enterprise data are, how they are generated and managed and what their functions are in supporting these decisions
  3. Explain the role of models in supporting the decisions made at each level of the operational hierarchy
  4. Evaluate and improve a plant wide control system for a given manufacturing system
  5. Identify condition-based monitoring of a manufacturing system, how it is performed and what its outcomes should be
  6. Explain the nature and role of planning and scheduling models and tools as applied at the plant and supply chain levels
Learning Resources, Technology and Texts
  • There is NO required textbook for this course
    • There will be readings available within Brightspace
  • Software
    • MatLab (which can be accessed via ECN). For more information about accessing Matlab, click here.
    • We will also be analyzing data using “Anaconda,” (a popular Python distribution), click here to learn more about how to download it and get started.
  • Hardware requirements
    • A laptop that can connect to the internet and run the Microsoft Office Suite (which is available free to all Purdue Students)
  • Brightspace learning management system
    • Access the course via Purdue’s Brightspace learning management system. Begin with the Start Here tab, which describes how the course Brightspace is organized. It is strongly suggested that you explore and become familiar not only with the site navigation but with content and resources available for this course. See the Student Services widget on the campus homepage for resources such as Technology Help, Academic Help, Campus Resources, and Protect Purdue.
Course Schedule
Week
Topics
Assignments
Week 1
Introduction to Smart Manufacturing
 
Week 2
Sensors and Plant Data Reconciliation
HW/Lab 1 - Data Reconciliation
Week 3
Error Detection and Information Systems
 
Week 4
Statistical Methods and Monitoring/Diagnosis Applications
HW/Lab 1 Due
Week 5
PLS Models and Applications and Review of Diagnostic Methods
HW/Lab 2 - Process Analytics using Multivariate Methods
Week 6
Condition Based Monitoring
 
Week 7
ML and AI Models
 
Week 8
Data Analytics
 
Week 9
Optimization
 
Week 10
State Estimation
HW/Lab 3 - Optimization
Week 11
Plant Wide Control
 
Week 12
Scheduling and Planning Introduction
HW/Lab 4 – Machine Learning
Week 13
Scheduling and Planning Methods
 
Week 14
Industrial Application
HW/Lab 5 - Scheduling and Planning
Week 15
Supply Chain Management
 
Week 16
Final Group Projects
Final Presentation & Project Due
Course Registration
This course is available to the public outside of formal degree programs.  If you are interested in taking the course as a non-degree seeking student, please visit: 
 
Course credit is applicable for the Online Interdisciplinary Master of Science in Engineering from Purdue University's College of Engineering.  For more information please visit: 

CHE 55400

Course Catalog
CHE 55400 Smart Manufacturing In Process Industries

Description
Credit Hours: 3.00. This course surveys the tools and techniques, which are relevant to support the multiple levels of technical decisions that arise in modern integrated operation of manufacturing facilities in the chemical related process industries. The linkage of these decisions levels and sharing of associated data and knowledge via effective IT methodology is currently termed Smart Manufacturing in the US and Industry 4.0 in Europe. The topics covered in the course include the structure of the operations decision hierarchy, role of online process measurements, elements of sensor network design, information systems to support process operations, plant data reconciliation, detection and diagnosis of process faults, plant wide control, real time process optimization, production planning and scheduling, and supply chain management. Each topic will be addressed by first summarizing the basic role and scope of that component, then discussing the structure of the decision problem, and then will outline some representative tools available to address that decision problem. Each major topic will include a lecture given by an industrial practitioner who will offer a perspective on the state of industrial practice. Permission of instructor required.
3.000 Credit hours
Levels:  Undergraduate, Graduate, Professional
Schedule Types:  Distance Learning, Lecture
Offered By:  School of Chemical Engineering
Department:  Chemical Engineering
Course Attributes
Upper Division
May be offered at any of the following campuses:  West Lafayette Continuing Ed West Lafayette
Learning Objectives
1. Explain the function, information requirements and main decisions made at each level of the operational hierarchy of an integrated processing system. 2. Understand the design requirements of a sensor network, that insures that all variables which must be managed are observable. 3. Explain that process data storage requirements are and how these requirements are met in integrated process systems. 4. Know how to use data reconciliation methods to obtain the maximum likelihood estimate of the state of process. 5. Explain why exceptional events are important to process operations. 6. Use multivariate statistic methods to determine whether and when an exceptional event has occurred. 7. Explain what fault diagnosis is, why it is needed and what general types of methods are available for effective diagnosis. 8. Understand the role of plant-wide control and how it relates to individual unit operations control. 9. Test, evaluate and improve a specific plant wide control systems design using a process simulation model. 10. Explain the role of real time process operations and the differences between steady state and dynamic RTO. 11. Implement and solve a steady state RTO problem based on material balances. 12. Explain the differences and relationship between process planning and scheduling. 13. Represent a process planning problem by formulating a linear programming model and solving it using standard LP tools. 14. Explain the main decision variables of a process scheduling application and understand the underlying computational complexity of scheduling problems. 15. Represent a scheduling problem using a state task network and solve it using a commercial solver. 16. Explain how supply chain management relates to the operational planning of individual processes. 17. Understand the main components and operational decision variables of a supply chain optimization problem. 18. Explain the information requirements for effective supply chain management. 19. Understand where the sources of uncertainty arise in supply chain planning and what strategies can be used to accommodate to these uncertainties.
Other Information
Restrictions:  May not be enrolled as the following Classifications: Freshman: 15 - 29 hours Junior: 75 - 89 hours Sophomore: 45 - 59 hours Junior: 60 - 74 hours Freshman: 0 - 14 hours Sophomore: 30 - 44 hours