Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jan 12, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Automated inspection of P&ID object recognition using deep learning.

Ji-Beob Kim1, Yoochan Moon1, Seung-Tae Han1

  • 1School of Mechanical Engineering, Korea University, 145 Anam-ro, Seongbuk-gu, Seoul, 02841, Republic of Korea.

Scientific Reports
|November 7, 2025
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Enhancing chromium coating thickness estimation with multi-head attention LSTM and data augmentation.

Scientific reports·2026
Same author

Rule-based design verification for mechanical parts with dynamic rule subset selection.

Scientific reports·2025
Same author

Machine-learning-based ground sink susceptibility evaluation using underground pipeline data in Korean urban area.

Scientific reports·2022
Same author

3D convolutional neural network for machining feature recognition with gradient-based visual explanations from 3D CAD models.

Scientific reports·2022
Same author

Machining feature recognition based on deep neural networks to support tight integration with 3D CAD systems.

Scientific reports·2021

This study introduces an automated method to improve object recognition in digitized piping and instrumentation diagrams (P&IDs). The new approach significantly reduces errors and speeds up the correction process for P&ID data.

Area of Science:

  • Engineering
  • Computer Science
  • Artificial Intelligence

Background:

  • Digitizing Piping and Instrumentation Diagrams (P&IDs) is crucial for industrial applications.
  • Manual error correction in P&ID object recognition is time-consuming and prone to persistent errors.

Purpose of the Study:

  • To propose a novel, automated method for inspecting and correcting object recognition errors in digitized P&IDs.
  • To enhance the accuracy and efficiency of P&ID data processing.

Main Methods:

  • Utilizing deep learning for unrecognized object inspection by generating patches and classifying missing elements.
  • Implementing optimal inspection methods for misrecognized objects, including deep learning-based feature vector similarity, text error detection, and line error detection.
Keywords:
Deep learningError detectionFeature representationObject inspectionPiping and instrumentation diagram

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Related Experiment Videos

Last Updated: Jan 12, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

1.0K

Main Results:

  • Unrecognized object inspection achieved 100% recall.
  • Misrecognized object inspection demonstrated high accuracy and F1 scores for symbols (99.2%, 96.7%), text (95.8%, 97.3%), and lines (100%).
  • Overall error correction time was reduced by approximately 40%.

Conclusions:

  • The proposed method effectively automates the inspection of object recognition results in P&IDs.
  • This approach significantly improves accuracy and reduces the time required for P&ID data correction.
  • The validated results confirm the method's efficacy on real-world industrial P&IDs.