A Soft Sensor Model of Sintering Process Quality Index Based on Multi-Source Data Fusion

Abstract

In complex industrial processes such as sintering, key quality variables are difficult to measure online and it takes a long time to obtain quality variables through offline testing. Moreover, due to the limitations of testing frequency, quality variable data are too scarce. To solve this problem, this paper proposes a sintering quality prediction model based on multi-source data fusion and introduces video data collected by industrial cameras. Firstly, video information of the end of the sintering machine is obtained via the keyframe extraction method based on the feature height. Secondly, using the shallow layer feature construction method based on sinter stratification and the deep layer feature extraction method based on ResNet, the feature information of the image is extracted at multi-scale of the deep layer and the shallow layer. Then, combining industrial time series data, a sintering quality soft sensor model based on multi-source data fusion is proposed, which makes full use of multi-source data from various sources. The experimental results show that the method effectively improves the accuracy of the sinter quality prediction model.

Logistics Center Selection and Logistics Network Construction from the Perspective of Urban Geographic Information Fusion

“…In maritime activities, Ye et al [ 39 ] developed an Adaptive Data Fusion (ADF) model using multi-source AIS data to predict ship trajectories effectively. In complex industrial settings like sintering, Yuxuan et al [ 40 ] proposed a quality prediction model that merges industrial camera video data with process parameters. Moreover, Yiqi et al [ 41 ] established a deep learning approach based on multi-data fusion for water quality prediction in urban sewer networks, considering environmental, social, and water quantity indicators, along with monitorable water quality standards.…”

Intelligent Soft Sensors

“…The next paper [ 10 ] deals with the merging of data from different sources in sintering processes and highlights the growing importance of integrating different types of data for better predictions. By cleverly merging visual data with traditional time series process data, the method achieves significant improvements in predicting complicated quality variables such as FeO content.…”