• Home
  • Search
  • Self-Supervised Learning and Multisource Heterogeneous Information Fusion Based Quality Anomaly Detection for Heavy-Plate Shape
  • Cite Icon21
  • https://doi.org/10.1109/tase.2023.3265649Copy DOI Icon

Self-Supervised Learning and Multisource Heterogeneous Information Fusion Based Quality Anomaly Detection for Heavy-Plate Shape

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Plate shape quality anomaly detection suffers from the problems of less labeled and multisource heterogeneous (MSH) data due to the complex production process with multi-process and multi-equipment. To address these problems, this paper proposes a self-supervised learning framework based on MSH contrastive learning (MSH-CL). In the proposed framework, an encoder is designed to extract the MSH information, which contains an MSH feature extract network (MSH-FEN) and an MSH feature fusion network (MSH-FFN). In MSH-FEN, a two-pathway CNN network is employed to extract the MSH feature. Then, a cross-MSH (CMSH) data fusion strategy based on the attention mechanism is designed to characterize the relationship between the MSH data in the MSH-FFN. The learning process consists of two phases, namely the self-supervised feature learning phase based on the contrastive learning (CL) and the supervised fine-tuning phase. The former phase is responsible for training the encoder with massive unlabeled data. Then, a classifier followed by the encoder is built with less labeled data in the supervised fine-tuning phase, which is applied to plate shape quality anomaly detection. Finally, the experiments are carried out on the real-world data set collected from a heavy-plate production process. The experimental results demonstrate the effectiveness and superiority of the proposed approach. Note to Practitioners—This paper focuses on the problem of shape quality anomaly detection for the heavy-plate production process, which is crucial to steel-making. However, the most quality-relevant data-driven modeling approaches suffer from the problem of requiring massive labeled data. In addition, the data generated in the practice heavy-plate production process have the characteristics of multisource heterogeneous (MSH). Motivated by the challenge of the less labeled and MSH data modeling, this paper proposed a self-supervised feature learning approach to learn a feature encoder to model the MSH data. Then, fine-tuning is used to obtain the model to detect the plate shape quality. In the feature encoder, a cross-MSH (CMSH) data fusion strategy is proposed. Finally, the effectiveness of the proposed approach is demonstrated by comparing it with other advanced algorithms. The proposed approach can be extended to other heavy-plate quality anomaly detection problems with less labeled and MSH data.

Similar Papers
  • Conference Article

Three-Dimensional Integrated System for Multi-Source Heterogeneous Data

  • Jul 01, 2019
  • Ling Ding +3
  • PDF
  • Research Article
  • Citations64

Big Data Health Care Platform With Multisource Heterogeneous Data Integration and Massive High-Dimensional Data Governance for Large Hospitals: Design, Development, and Application

  • Apr 13, 2022
  • JMIR Medical Informatics
  • Miye Wang +7
  • Book Chapter
  • Citations8

MHDML: Construction of a Medical Lakehouse for Multi-source Heterogeneous Data

  • Jan 01, 2022
  • Qi Xiao +8
  • Research Article
  • Citations52

Self-Supervised Feature Learning and Phenotyping for Assessing Age-Related Macular Degeneration Using Retinal Fundus Images

  • Jul 02, 2021
  • Ophthalmology Retina
  • Baladitya Yellapragada +4
  • Book Chapter
  • Citations12

Case Discrimination: Self-supervised Feature Learning for the Classification of Focal Liver Lesions

  • Jan 01, 2021
  • Haohua Dong +6
  • Research Article
  • Citations14

Multi-source heterogeneous data fusion technology for electric power based on big data mining

  • Nov 01, 2024
  • Journal of Computational Methods in Sciences and Engineering
  • Zhongjian Liu +6
  • Research Article
  • Citations5

A review of structural health monitoring for fixed offshore wind turbines driven by multisource heterogeneous data

  • Sep 14, 2025
  • Structural Health Monitoring
  • Xin Fang +3
  • PDF
  • Research Article
  • Citations51

Spatio-Temporal Knowledge Graph Based Forest Fire Prediction with Multi Source Heterogeneous Data

  • Jul 21, 2022
  • Remote Sensing
  • Xingtong Ge +6
  • Research Article
  • Citations45

A graph neural network-based stock forecasting methodutilizing multi-source heterogeneous data fusion.

  • May 27, 2022
  • Multimedia Tools and Applications
  • Xiaohan Li +4
  • Conference Article
  • Citations6

Exploiting Self-Supervised and Semi-Supervised Learning for Facial Landmark Tracking with Unlabeled Data

  • Oct 12, 2020
  • Shi Yin +3
  • Preprint Article

Rethinking Self-Supervised Learning in Computer Vision: Challenges, Tasks, and Methods

  • Feb 20, 2026
  • Zezhou Cheng
  • Research Article

A Review of Multi-source Heterogeneous Twin Data Processing Methods in Traffic Scenes

  • Jun 15, 2024
  • International Journal of Computer Science and Information Technology
  • Yu Yan
  • Research Article
  • Citations2

Research on privacy data protection of power wireless network based on heterogeneous data sequence

  • Apr 08, 2022
  • Energy Reports
  • Furong Li +1
  • Research Article
  • Citations1

Contrastive Masked Feature Modeling for Self-Supervised Representation Learning of High-Resolution Remote Sensing Images

  • Feb 17, 2026
  • Remote Sensing
  • Shiyan Pang +4
  • PDF
  • Research Article

Characteristic Analysis of Multisource Heterogeneous Data in Digital City Planning Based on Internet of Things

  • Nov 12, 2021
  • Mobile Information Systems
  • Xiao Xiao
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.