Using Ensemble Model to Reduce Downtime in Manufacturing Industry: An Advanced Diagnostic Framework for Early Failure Detection
- Title
- Using Ensemble Model to Reduce Downtime in Manufacturing Industry: An Advanced Diagnostic Framework for Early Failure Detection
- Creator
- Thenmozhi S.; Kumudavalli M.V.; Karthikeyan P.; Kumar C.S.; Sharmila S.
- Description
- The fourth industrial resolution marks a significant shift that uses emerging technologies such as intelligent automation, extensive machine-to-machine communication, and the internet of things (IoT) to modernize conventional manufacturing and industrial methods. The examination of vast data gathered in modern industrial facilities has not only greatly leveraged artificial intelligence (AI) tools but has also driven the development of innovative technologies. In this context, a novel framework for predictive maintenance in the production sector is introduced in this research, which depends on an ensemble model. First, a set of input features are collected from sensors. Then, data normalization technique is applied to standardize and prepare data for further analysis. These normalized input features are then used to train an ensemble classifier. In the ensemble model, multilayer perceptron (MLP), K-nearest neighbors (KNN), and support vector machine (SVM) are serve as base classifiers. Efficacy of the designed framework is validated using predictive maintenance dataset. Results demonstrated that the proposed ensemble model exhibited improved accuracy compared to individual base classifiers. The results further demonstrated that the implemented model had superior efficiency compared to the other benchmark models. 2025 selection and editorial matter, Amit Kumar Tyagi, Shrikant Tiwari, and Gulshan Soni; individual chapters, the contributors.
- Source
- Data Analytics and Artificial Intelligence for Predictive Maintenance in Smart Manufacturing, pp. 184-196.
- Date
- 2024-01-01
- Publisher
- CRC Press
- Coverage
- Thenmozhi S., Dayanandasagar College of Engineering, Karnataka, Bengaluru, India; Kumudavalli M.V., Dayanandasagar College of Engineering, Karnataka, Bengaluru, India; Karthikeyan P., Department of Computer Science and Information Engineering, National Chung Cheng University, Chiayi, Taiwan; Kumar C.S., School of Business and Management, CHRIST (Deemed to be University), Karnataka, Bangalore, India; Sharmila S., Dayanandasagar College of Engineering, Karnataka, Bengaluru, India
- Rights
- Restricted Access
- Relation
- ISBN: 978-104015139-6; 978-103276952-3
- Format
- Online
- Language
- English
- Type
- Book chapter
Collection
Citation
Thenmozhi S.; Kumudavalli M.V.; Karthikeyan P.; Kumar C.S.; Sharmila S., “Using Ensemble Model to Reduce Downtime in Manufacturing Industry: An Advanced Diagnostic Framework for Early Failure Detection,” CHRIST (Deemed To Be University) Institutional Repository, accessed February 23, 2025, https://archives.christuniversity.in/items/show/17956.