A Machine-Learning-Based and IoT-Enabled Robot Swarm System for Pipeline Crack Detection

In today’s expanding cities, pipeline networks are becoming an essential part of the industrial infrastructure. Monitoring these pipelines autonomously is becoming increasingly important. Inspecting pipelines for cracks is one specific task that poses a huge burden on humans. Undetected cracks may p...

Full description

Saved in:
Bibliographic Details
Main Authors: Ayman Kandil, Mounib Khanafer, Ali Darwiche, Reem Kassem, Fatima Matook, Ahmad Younis, Habib Badran, Maryam Bin-Jassem, Ossama Ahmed, Ali Behiry, Mohammed El-Abd
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:IoT
Subjects:
Online Access:https://www.mdpi.com/2624-831X/5/4/43
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850049801039642624
author Ayman Kandil
Mounib Khanafer
Ali Darwiche
Reem Kassem
Fatima Matook
Ahmad Younis
Habib Badran
Maryam Bin-Jassem
Ossama Ahmed
Ali Behiry
Mohammed El-Abd
author_facet Ayman Kandil
Mounib Khanafer
Ali Darwiche
Reem Kassem
Fatima Matook
Ahmad Younis
Habib Badran
Maryam Bin-Jassem
Ossama Ahmed
Ali Behiry
Mohammed El-Abd
author_sort Ayman Kandil
collection DOAJ
description In today’s expanding cities, pipeline networks are becoming an essential part of the industrial infrastructure. Monitoring these pipelines autonomously is becoming increasingly important. Inspecting pipelines for cracks is one specific task that poses a huge burden on humans. Undetected cracks may pose multi-dimensional risks. In this paper, we introduce the Pipeline Leak Identification Emergency Robot Swarm (PLIERS) system, an industrial system that deploys Internet-of-Things (IoT), robotics, and neural network technologies to detect cracks in emptied water and sewage pipelines. In PLIERS, a swarm of robots inspect emptied pipelines from the inside to detect cracks, collect images of them, and register their locations. When the images are taken, they are fed into a cloud-based module for analysis by a convolutional neural network (CNN). The CNN is used to detect cracks and identify their severity. Through extensive training and testing, the CNN model performance showed promising scores for accuracy (between 80% and 90%), recall (at least 95%), precision (at least 95%), and F1 (at least 96%). Additionally, through the careful design of a prototype for a water/sewage pipeline structure with several types of cracks, the robots used managed to exchange information among themselves and convey crack images to the cloud-based server for further analysis. PLIERS is a system that deploys modern technologies to detect and recognize cracks in pipeline grids. It adds to the efforts of improving instrumentation and measurement approaches by using robots, sensory, IoT principles, and the efficient analysis of CNNs.
format Article
id doaj-art-fd7ede5d2f86489ca2ce85248812c203
institution DOAJ
issn 2624-831X
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series IoT
spelling doaj-art-fd7ede5d2f86489ca2ce85248812c2032025-08-20T02:53:38ZengMDPI AGIoT2624-831X2024-12-015495196910.3390/iot5040043A Machine-Learning-Based and IoT-Enabled Robot Swarm System for Pipeline Crack DetectionAyman Kandil0Mounib Khanafer1Ali Darwiche2Reem Kassem3Fatima Matook4Ahmad Younis5Habib Badran6Maryam Bin-Jassem7Ossama Ahmed8Ali Behiry9Mohammed El-Abd10Department of Computer Science and Engineering, American University of Sharjah, University City, Sharjah P.O. Box 26666, United Arab EmiratesCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitCollege of Engineering and Applied Sciences, American University of Kuwait, P.O. Box 3323, Safat 13034, KuwaitIn today’s expanding cities, pipeline networks are becoming an essential part of the industrial infrastructure. Monitoring these pipelines autonomously is becoming increasingly important. Inspecting pipelines for cracks is one specific task that poses a huge burden on humans. Undetected cracks may pose multi-dimensional risks. In this paper, we introduce the Pipeline Leak Identification Emergency Robot Swarm (PLIERS) system, an industrial system that deploys Internet-of-Things (IoT), robotics, and neural network technologies to detect cracks in emptied water and sewage pipelines. In PLIERS, a swarm of robots inspect emptied pipelines from the inside to detect cracks, collect images of them, and register their locations. When the images are taken, they are fed into a cloud-based module for analysis by a convolutional neural network (CNN). The CNN is used to detect cracks and identify their severity. Through extensive training and testing, the CNN model performance showed promising scores for accuracy (between 80% and 90%), recall (at least 95%), precision (at least 95%), and F1 (at least 96%). Additionally, through the careful design of a prototype for a water/sewage pipeline structure with several types of cracks, the robots used managed to exchange information among themselves and convey crack images to the cloud-based server for further analysis. PLIERS is a system that deploys modern technologies to detect and recognize cracks in pipeline grids. It adds to the efforts of improving instrumentation and measurement approaches by using robots, sensory, IoT principles, and the efficient analysis of CNNs.https://www.mdpi.com/2624-831X/5/4/43automationconvolutional neural networkindustrial applicationinstrumentation and measurementInternet of Thingspipeline crack detection
spellingShingle Ayman Kandil
Mounib Khanafer
Ali Darwiche
Reem Kassem
Fatima Matook
Ahmad Younis
Habib Badran
Maryam Bin-Jassem
Ossama Ahmed
Ali Behiry
Mohammed El-Abd
A Machine-Learning-Based and IoT-Enabled Robot Swarm System for Pipeline Crack Detection
IoT
automation
convolutional neural network
industrial application
instrumentation and measurement
Internet of Things
pipeline crack detection
title A Machine-Learning-Based and IoT-Enabled Robot Swarm System for Pipeline Crack Detection
title_full A Machine-Learning-Based and IoT-Enabled Robot Swarm System for Pipeline Crack Detection
title_fullStr A Machine-Learning-Based and IoT-Enabled Robot Swarm System for Pipeline Crack Detection
title_full_unstemmed A Machine-Learning-Based and IoT-Enabled Robot Swarm System for Pipeline Crack Detection
title_short A Machine-Learning-Based and IoT-Enabled Robot Swarm System for Pipeline Crack Detection
title_sort machine learning based and iot enabled robot swarm system for pipeline crack detection
topic automation
convolutional neural network
industrial application
instrumentation and measurement
Internet of Things
pipeline crack detection
url https://www.mdpi.com/2624-831X/5/4/43
work_keys_str_mv AT aymankandil amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT mounibkhanafer amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT alidarwiche amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT reemkassem amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT fatimamatook amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT ahmadyounis amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT habibbadran amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT maryambinjassem amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT ossamaahmed amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT alibehiry amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT mohammedelabd amachinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT aymankandil machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT mounibkhanafer machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT alidarwiche machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT reemkassem machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT fatimamatook machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT ahmadyounis machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT habibbadran machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT maryambinjassem machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT ossamaahmed machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT alibehiry machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection
AT mohammedelabd machinelearningbasedandiotenabledrobotswarmsystemforpipelinecrackdetection