Deep Learning and Time Series Analysis for Internet of Things Device Predictive Maintenance

Clicks: 4
ID: 313095
2024
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #272 of 705 articles by views in Journal of Computing & Biomedical Informatics

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 705 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
The expansion of the Internet of Things (IoT) devices in many industries has ushered the era of using data to optimize the organization. Nonetheless, the innovation of maintenance methods for the networked devices that are reliable and operate continuously is a necessity. This study focuses on building and using a predictive maintenance framework for IoT devices integrating the benefits of the TSA and the DL methods. The general aim of this project is to enhance the accuracy and quality of predictive maintenance operations, which will reduce the downtime of the equipment and increase the efficiency of resources use. The investigation methodology includes collecting a variety of data types from the Internet of Things devices such as sensor readings, error logs, and maintenance records. The next step is a comprehensive data pre-processing that entails cleaning, normalization, and feature extraction of the dataset before analysis. The fundamental analytical components of the proposed framework comprise of the Time Series Analysis that is used to detect the time series patterns in the IoT data. Through the use of statistical methods and the process of splitting up the time series data, we can better understand the device's performance as well as recurring patterns, which provide valuable information to us. Simultaneously, Deep Learning models, especially RNNs and LSTMs, employing previous patterns is used for forecasting maintenance requirements. The findings from applying the preventive maintenance model to real IoT data proved to be highly accurate and efficient in predicting maintenance requirements. The article highlights the current challenges of IoT devices maintenance prediction and suggests directions for further studies. It involves studying edge computing, federated learning, and incorporating XAI in models to boost their interpretability. In the last, the research represents the importance of preventive maintenance for the reliability of IoT devices. It offers a roadmap for businesses that wish to benefit from the full potential of data analytics and artificial intelligence for operational optimization.
Reference Key
imported_1777058995_69ebc4b312169 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Javaid Ahmad Malik
Journal Journal of Computing & Biomedical Informatics
Year 2024
DOI
DOI not found
URL
https://jcbi.org/index.php/Main/article/view/492
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.