Self- Fault Recovery by Robots

Saumya Shukla

doi:10.36948/ijfmr.2025.v07i03.46852

Self- Fault Recovery by Robots

Author(s)	Ms. Saumya Shukla
Country	India
Abstract	This work presents an integrated remote-controlled robotics framework with computer-aided fault detection using deep learning. Robotic execution in real time is coupled with intelligent fault analysis in the presented framework to reduce human intervention and make the system more robust. A Raspberry Pi-equipped mobile robot with a high-resolution webcam is controlled remotely using a Python-based platform developed with Pygame and socket programming. The robot captures video information from its environment and uploads it to a cloud platform (Google Colab) for processing and defect classification. Leveraging a transfer learning approach, the system employs the MobileNet architecture, pre-trained on labeled images of mechanical faults, including misalignment, blockage, and surface wear. The images captured are analyzed with TensorFlow in the cloud to ascertain defect occurrence and type. When a fault is detected, the system is able to automatically initiate recovery actions based on pre-configured rules, significantly boosting operational autonomy. Experimental evaluation was conducted within a simulated fault condition indoor laboratory environment. The model achieved a high classification accuracy of 91%, precision and recall up to 0.90 and 0.93, respectively. These readings affirm the model's superiority in detecting and responding to mechanical faults across various environments. System architecture centers around modularity, allowing future upgradeability by reinforcement learning algorithms or more detailed sensory inputs. While encouraging, there are still problems of light sensitivity as well as generalization to new fault types. Nevertheless, the work illustrates the integrability of robotic control, machine vision, and cloud AI toward achieving intelligent autonomous robotic systems for manufacturing.
Keywords	Remote-Controlled Robotics Deep Learning Fault Detection MobileNet Transfer Learning Cloud-Based Image Processing
Field	Engineering
Published In	Volume 7, Issue 3, May-June 2025
Published On	2025-06-01
DOI	https://doi.org/10.36948/ijfmr.2025.v07i03.46852
Short DOI	https://doi.org/g9m2ct

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 3 Cover Page Vol 7 Isu 2 Cover Page Vol 7 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Self- Fault Recovery by Robots

Share this