Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

PMI-DT: Leveraging Digital Twins and Machine Learning for Predictive Modeling and Inspection in Manufacturing

Chas Hamel, Md Manjurul Ahsan, Shivakumar Raman

TL;DR

A Predictive Maintenance and Inspection Digital Twin (PMI-DT) framework with a focus on precision measurement and predictive quality assurance using 3D-printed 1''-4 ACME bolt, CyberGage 360 vision inspection system, SolidWorks, and Microsoft Azure is introduced.

Abstract

Over the years, Digital Twin (DT) has become popular in Advanced Manufacturing (AM) due to its ability to improve production efficiency and quality. By creating virtual replicas of physical assets, DTs help in real-time monitoring, develop predictive models, and improve operational performance. However, integrating data from physical systems into reliable predictive models, particularly in precision measurement and failure prevention, is often challenging and less explored. This study introduces a Predictive Maintenance and Inspection Digital Twin (PMI-DT) framework with a focus on precision measurement and predictive quality assurance using 3D-printed 1''-4 ACME bolt, CyberGage 360 vision inspection system, SolidWorks, and Microsoft Azure. During this approach, dimensional inspection data is combined with fatigue test results to create a model for detecting failures. Using Machine Learning (ML) -- Random Forest and Decision Tree models -- the proposed approaches were able to predict bolt failure with real-time data 100% accurately. Our preliminary result shows Max Position (30%) and Max Load (24%) are the main factors that contribute to that failure. We expect the PMI-DT framework will reduce inspection time and improve predictive maintenance, ultimately giving manufacturers a practical way to boost product quality and reliability using DT in AM.

PMI-DT: Leveraging Digital Twins and Machine Learning for Predictive Modeling and Inspection in Manufacturing

TL;DR

A Predictive Maintenance and Inspection Digital Twin (PMI-DT) framework with a focus on precision measurement and predictive quality assurance using 3D-printed 1''-4 ACME bolt, CyberGage 360 vision inspection system, SolidWorks, and Microsoft Azure is introduced.

Abstract

Over the years, Digital Twin (DT) has become popular in Advanced Manufacturing (AM) due to its ability to improve production efficiency and quality. By creating virtual replicas of physical assets, DTs help in real-time monitoring, develop predictive models, and improve operational performance. However, integrating data from physical systems into reliable predictive models, particularly in precision measurement and failure prevention, is often challenging and less explored. This study introduces a Predictive Maintenance and Inspection Digital Twin (PMI-DT) framework with a focus on precision measurement and predictive quality assurance using 3D-printed 1''-4 ACME bolt, CyberGage 360 vision inspection system, SolidWorks, and Microsoft Azure. During this approach, dimensional inspection data is combined with fatigue test results to create a model for detecting failures. Using Machine Learning (ML) -- Random Forest and Decision Tree models -- the proposed approaches were able to predict bolt failure with real-time data 100% accurately. Our preliminary result shows Max Position (30%) and Max Load (24%) are the main factors that contribute to that failure. We expect the PMI-DT framework will reduce inspection time and improve predictive maintenance, ultimately giving manufacturers a practical way to boost product quality and reliability using DT in AM.

Paper Structure

This paper contains 22 sections, 10 equations, 17 figures, 7 tables.

Table of Contents

  1. Introduction
  2. Motivation of the Study
  3. Literature Review
  4. Methodology
  5. Physical Twin Creation
  6. CyberGage 360 DT Validation
  7. DT Development in the Azure Environment
  8. Data Collection and Processing
  9. Data Preparation and Feature Engineering
  10. Handling Missing Values
  11. Feature Engineering
  12. Outlier Detection and Handling
  13. Data Exploration
  14. Model Selection and Training
  15. Machine Learning Models
  16. ...and 7 more sections

Figures (17)

  • Figure 1: Conical hole plug assembly. (a) An external view of the process flow in the conical hole plug assembly. (b) A detailed view of the plug mechanism. Item 1 represents the conical plug, Item 2 is the conical hole, and Item 3 is the 1-1/2”–6 Grade 8 bolt. The red arrows depict internal pressure at 1400 bar (22,000 psi).
  • Figure 2: Deformed vs acceptable threads of the Bolt.
  • Figure 3: Proposed framework of Predictive Maintenance and Inspection DT (PMI-DT) for ACME bolts, including seven stages: (1) Physical Twin Creation, (2) CyberGage 360 DT Validation, (3) DT Development in the Azure Environment, (4) Data Collection and Processing, (5) Data Preparation and Feature Engineering, (6) Machine Learning Model Development, and (7) Model Evaluation.
  • Figure 4: Illustration of (a) the fully defined 3D CAD model of the 1”-4 ACME Bolt and (b) the 3D-printed physical twin of the 1”-4 ACME Bolt using Nylon-12.
  • Figure 5: Nominal critical features identified in Geomagic Control X for the ACME Bolt.
  • ...and 12 more figures