Journal Article10.1109/TII.2020.3021047
Cooperative Deep Dynamic Feature Extraction and Variable Time-Delay Estimation for Industrial Quality Prediction
Le Yao,Zhiqiang Ge +1 more
62
TL;DR: A novel data-driven industrial quality predictor is proposed based on the cooperative deep dynamic feature extraction and variable time-delay (VTD) estimation, which helps improve the prediction performance of the proposed SSDFE network.
read more
Abstract: In this article, a novel data-driven industrial quality predictor is proposed based on the cooperative deep dynamic feature extraction and variable time-delay (VTD) estimation. A semisupervised dynamic feature extracting (SSDFE) network is first proposed to extract nonlinear dynamic features to build a regression model for output quality prediction. Due to the inherent process structure and different positions of sampling instruments, time-delays commonly exist between process variables and quality variables, which may distort the original distribution and relationship in collected data. To recover the original process data pattern, the VTDs are regarded as model parameters and cooperatively obtained in the training process of the SSDFE network through an integer differential evolution algorithm. With the estimated VTD values, the reconstructed dataset further helps improve the prediction performance of the proposed SSDFE network. Two case studies are presented to demonstrate the superiority of the proposed method with VTD estimation.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A review on autoencoder based representation learning for fault detection and diagnosis in industrial processes
TL;DR: In this paper , a comprehensive review of autoencoder-based industrial applications is presented, which mainly includes two parts: AE-based representation learning and monitoring strategies, which illustrate the entire design process of auto-encoderbased monitoring methods.
123
Path Enhanced Bidirectional Graph Attention Network for Quality Prediction in Multistage Manufacturing Process
TL;DR: A novel path enhanced bidirectional graph attention network (PGAT) is proposed in this article and achieves the state-of-the-art results on this dataset, which confirms the effectiveness of PGAT.
43
Dynamic Time Features Expanding and Extracting Method for Prediction Model of Sintering Process Quality Index
TL;DR: Wang et al. as discussed by the authors proposed a dynamic time feature expanding and extracting framework for the sinter quality prediction, where the original data are differentiated, compensated for time delay, expanded, and serialized by using time characteristics, and the input time series is reconstructed.
32
Semi-Supervised Deep Dynamic Probabilistic Latent Variable Model for Multimode Process Soft Sensor Application
TL;DR: Wang et al. as mentioned in this paper proposed a dynamic mixture variational autoencoder regression model to handle the multimode industrial process modeling with dynamic features, where a corresponding semi-supervised data sequence division scheme is introduced to make full use of the information in both labeled and unlabeled data.
32
A soft sensor modeling method with dynamic time-delay estimation and its application in wastewater treatment plant
TL;DR: A weighted relevance vector machine model based on dynamic time-delay estimation (DTDE-WRVM) is proposed to realize the dynamic characteristic extraction and quality variable prediction in soft sensor modeling.
25
References
Data-driven soft sensor development based on deep learning technique
TL;DR: The comparison of modeling results demonstrates that the deep learning technique is especially suitable for soft sensor modeling because of the following advantages over traditional methods.
529
Nonlinear Dynamic Soft Sensor Modeling With Supervised Long Short-Term Memory Network
Xiaofeng Yuan,Lin Li,Yalin Wang +2 more
TL;DR: A supervised LSTM (SLSTM) network is proposed to learn quality-relevant hidden dynamics for soft sensor application, which is composed of basic SLSTM unit at each sampling instant.
493
Review of soft sensor methods for regression applications
TL;DR: A literature review on each of the main issues of SSR development, including the treatment of missing data, outlier detection, selection of input variables, model training, validation, and SSR maintenance will be performed.
295
DSTP-RNN: A dual-stage two-phase attention-based recurrent neural network for long-term and multivariate time series prediction
TL;DR: Zhang et al. as discussed by the authors proposed a dual-stage two-phase recurrent neural network (DSTP-based RNN) for long-term time series prediction, where the first phase produces violent but decentralized response weight, while the second phase leads to stationary and concentrated response weight.
290
Deep Learning of Semisupervised Process Data With Hierarchical Extreme Learning Machine and Soft Sensor Application
Le Yao,Zhiqiang Ge +1 more
TL;DR: The proposed semisupervised HELM method is applied in a high–low transformer to estimate the carbon monoxide content, which shows a significant improvement of the prediction accuracy, compared to traditional methods.
290