Back to Search
Start Over
Identification of Abnormal Conditions for Fused Magnesium Melting Process Based on Deep Learning and Multisource Information Fusion
- Source :
- IEEE Transactions on Industrial Electronics. 69:3017-3026
- Publication Year :
- 2022
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2022.
-
Abstract
- Fused magnesium furnace (FMF) is the vital equipment for Magnesia refractory production. The melting process of FMF is subject to melting temperature, magnesite quality and composition, and much more dynamic factors, which are prone to abnormal conditions such as overheating, abnormal exhausting, semi-molten and affect the stability and safety of the production seriously. Due to the difficulties of effectively monitoring and accurately identifying the abnormal conditions with the existing methods, this paper proposes a novel method for identifying the abnormal conditions of FMF based on deep learning and multi-information fusion. First, the Wasserstein distance based Generative Adversarial Networks (GAN) with Gradient Penalty (WGAN-GP) is developed to solve the problem of obtaining overheating condition image samples with obvious visual characteristics. Then, the image-based Deep Convolutional Neural Network (DCNN) model is established to recognize the abnormal condition images and extract image features whose training set is the combination of the generated images and the original images. Finally, based on multi-source information fusion, the traditional process current data are fused with the extracted image features, and a support vector machine model is established to complete the classification and identification of the FMF working-conditions. Various experiments on actual industrial data show that the proposed method is effective and advanced.
- Subjects :
- business.industry
Computer science
Deep learning
Process (computing)
Stability (learning theory)
Pattern recognition
Convolutional neural network
Image (mathematics)
Support vector machine
Identification (information)
Control and Systems Engineering
Artificial intelligence
Electrical and Electronic Engineering
business
Multi-source
Subjects
Details
- ISSN :
- 15579948 and 02780046
- Volume :
- 69
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Industrial Electronics
- Accession number :
- edsair.doi...........c6e838adb08e336461c7f6d456fe9fd1