Stacked supervised Poisson autoencoders-based soft-sensor for defects prediction in steelmaking process

Zhang, Xinmin; Kano, Manabu; Tani, Masahiro

doi:10.1016/j.compchemeng.2023.108182

Cited by 8 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To compare with other soft sensors, this study carried out experiments comparing three perspectives: shallow learning, deep learning, and deep supervised learning soft sensor models. We compare the endpoint carbon content and temperature prediction performance of eleven soft sensor models, namely KN, SVM, multilayer perceptron (MLP), DNN, SAE, SSAE [39], SSPAE [26], SS-SAE [27], SDBN [34], Transfermor [38], and ST-LSTM [40]. It is apparent that the SD-DBN regression model outperforms both the single model and the other deep learning models among the twelve distinct models.The SD-DBN model's good performance on the BOF steelmaking dataset may be due to its better feature extraction structure, which effectively captures high-quality information necessary for regression prediction.…”

Section: Comparison Experimentsmentioning

confidence: 99%

“…Wang et al [25] introduced a stacked supervised autoencoder (SSAE) technique to pre-train the deep neural network (DNN) and extract deep fault-related characteristics from the initial input data, which enhances the classifier's classification accuracy. Zhang et al [26] integrated the Poisson regression network layer into the deep autoencoder framework. They proposed a new data-driven soft sensor named stacked supervised Poisson autoencoder (SSPAE) for predicting soft sensor during steelmaking.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

BOF steelmaking endpoint carbon content and temperature soft sensor based on supervised dual-branch DBN

Lu,

Liu,

Chen

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Accurate prediction of endpoint carbon content and temperature is critical in the basic oxygen furnace (BOF) steelmaking process. Although deep learning soft sensor approaches have the capacity to extract abstract features from high-dimensional nonlinear steelmaking data, they confront the challenge of a low correlation between acquired features and labels. This work presents a BOF steelmaking soft sensor model based on supervised dual-branch deep belief network (SD-DBN) to address this issue. The SD-DBN model incorporates label information into the feature extraction process and fuses crucial feature information to complete the feature extraction in order to extract features that are closely connected to the target variables. First, the supervised Restricted Boltzmann Machine (RBM) is improved by using a pruning strategy to extract features that are highly correlated with quality information, and then the autocorrelation key feature extraction module is spliced and fused to form a dual-branch feature extraction module to improve key information extraction. Second, stacking the supervised dual-branch RBM modules to build a deep feature extraction network enhances the deep extraction capabilities of data features. This deep network stacking not only increases the impact of essential target data in hierarchical training, but it also acquires characteristics associated with the target variables.

show abstract

Section: Comparison Experimentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

BOF steelmaking endpoint carbon content and temperature soft sensor based on supervised dual-branch DBN

Lu,

Liu,

Chen

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…[4][5][6] Data-driven soft sensor modelling methods have lower requirements for process mechanism knowledge, which to a certain extent frees the model from dependence on complete physical and chemical knowledge. [7] Moreover, datadriven soft sensors have the advantages of easy implementation and high effectiveness, so such methods have been widely used in quality prediction and quality monitoring tasks in the fields of chemicals, [4,8] textile, [9,10] ironmaking, [11][12][13] sintering, [14] steelmaking, [15] and so forth.…”

Section: Introductionmentioning

confidence: 99%

A review of just‐in‐time learning‐based soft sensor in industrial process

Sheng,

Qian,

Song

et al. 2024

Can J Chem Eng

Self Cite

View full text Add to dashboard Cite

Data‐driven soft sensing approaches have been a hot research field for decades and are increasingly used in industrial processes due to their advantages of easy implementation and high efficiency. However, nonlinear and time‐varying problems widely exist in practical industrial processes. Just‐in‐time learning (JITL) was proposed to solve these problems and has attracted great attention in practical applications. To present a comprehensive review of JITL‐based soft sensor studies and provide detailed technical guidance for new researchers, this paper introduces the recent research on JITL‐based soft sensor modelling methods in the industrial process from three aspects: similarity criterion, sample subset, and local model, which include the whole process of establishing a JITL‐based soft sensor. Moreover, the future research and innovation directions of JITL‐based soft sensors in industrial processes are also prospected.

show abstract

Stacked dynamic target regularization enhanced autoencoder for soft sensor in industrial processes

Guo,

Zhao,

2024

Can J Chem Eng

View full text Add to dashboard Cite

Stacked autoencoders (SAEs) have great potential in developing soft sensors due to their excellent feature extraction capabilities. However, the pre‐training stage of SAE is unsupervised and some important information related to target variables may be discarded. Meanwhile, as the depth of the network increases, reconstruction errors continue to accumulate, resulting in incomplete feature representations of the original input. In addition, the dynamic nature of the data affects the predictive results of the model. To address these issues, the stacked dynamic target regularization enhanced autoencoder (SDTR‐EAE) method is proposed, which adds the DTR and the original input information layer by layer to enhance the feature extraction. To adapt to the dynamic changes in data and extract target‐related features, entropy weight grey relational analysis (EW‐GRA) is used as the DTR term to constrain the weight matrix and suppress irrelevant features. To reduce the accumulation of information loss during the reconstruction, an information enhancement layer is introduced, where the original inputs and the information of the hidden layers of previous DTR‐EAE units are added to the follow‐up DTR‐EAE unit. Finally, in the regression process, the DTR term is used again to fully utilize depth features for quality prediction and prevent overfitting. Experimental verifications using the debutanizer column and thermal power plant are conducted to validate the effectiveness of the proposed modelling method.

show abstract

Stacked supervised Poisson autoencoders-based soft-sensor for defects prediction in steelmaking process

Cited by 8 publications

References 33 publications

BOF steelmaking endpoint carbon content and temperature soft sensor based on supervised dual-branch DBN

BOF steelmaking endpoint carbon content and temperature soft sensor based on supervised dual-branch DBN

A review of just‐in‐time learning‐based soft sensor in industrial process

Stacked dynamic target regularization enhanced autoencoder for soft sensor in industrial processes

Contact Info

Product

Resources

About