Combine AI and First Principles to Improve Model Performance

Accelerate your digitalization journey and improve your model predictions by utilizing industrial data to build comprehensive, accurate hybrid models. Benefit from seamless integration with existing process simulators such as Aspen HYSYS® and Aspen Plus®. This training class will focus on building, validating and deploying Aspen Hybrid Models to leverage the power of AI without engineers requiring data science or machine learning expertise.
 

Audience:

  • Process Engineers who would like to learn how to apply AI and machine learning to improve their modeling activities.

Training Details

  • Course Id:

    EHM020

  • Duration:

    0.5 day(s)

  • CEUs Awarded:

    0.4

  • Level:

    Intermediate

Benefits

  • Address problems that cannot be solved with first principles models alone
  • Build better models faster and sustain accurate models longer
  • Improve predictive insights using AI and Machine learning

Approach

  • Instruction on basic topics
  • An experienced instructor will select an appropriate order in which to present the modules
  • Discussion about the general approach and the key elements for successful simulations
  • Instructor-guided demonstrations of features
  • Hands-on workshops using examples from the petroleum processing industry
  • Detailed course notes

Tasks

Creating Aspen Hybrid Models
  • Review overall approach to building Aspen Hybrid Models
  • Identify tools needed to create Aspen Hybrid Models
  • Discuss how to login to Aspen AI Model Builder
  • Understand how to deploy Aspen Hybrid Models in Aspen Plus/Aspen HYSYS
  • Demonstration: Create a simple column model using the Reduced Order Sensor Workflow to illustrate the overall approach in building and deploying Aspen Hybrid Models
Workflow for AI Driven Hybrid Models for Engineering
  • Review data format required for using the AI Driven workflow
  • Discuss different options available for data cleaning
  • Analyze results for the model built using parity and coefficient plots as well as accuracy and predictability values
  • Workshop: Create an AI Driven Hybrid model for a membrane using plant data for deployment in Aspen Plus or Aspen HYSYS

Pre-requisites

A background in chemical/process engineering and data analysts
 

Subsequent Courses

  • EHM101 Introduction to Aspen Hybrid ModelsTM for Engineering
  • RPA105 Introduction to Hybrid Modeling for Planning

Agenda

Creating Aspen Hybrid Models
  • Review overall approach to building Aspen Hybrid Models
  • Identify tools needed to create Aspen Hybrid Models
  • Discuss how to login to Aspen AI Model Builder
  • Understand how to deploy Aspen Hybrid Models in Aspen Plus/Aspen HYSYS
  • Demonstration: Create a simple column model using the Reduced Order Sensor Workflow to illustrate the overall approach in building and deploying Aspen Hybrid Models
Workflow for AI Driven Hybrid Models for Engineering
  • Review data format required for using the AI Driven workflow
  • Discuss different options available for data cleaning
  • Analyze results for the model built using parity and coefficient plots as well as accuracy and predictability values
  • Workshop: Create an AI Driven Hybrid model for a membrane using plant data for deployment in Aspen Plus or Aspen HYSYS

Register for a Class

Date Class Type Location Price Language

Aspen Technology, Inc. awards Continuing Education Units (CEUs) for training classes conducted by our organization. One CEU is granted for every 10 hours of class participation.