Robust Soft Sensor with Deep Kernel Learning for Quality Prediction in Rubber Mixing Processes

Zheng, Shi-Yi; Liu, Kaixin; Xu, Yili; Chen, Hao; Zhang, Xuelei; Liu, Yi

doi:10.3390/s20030695

Cited by 21 publications

(13 citation statements)

References 37 publications

(75 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future research, more efforts are encouraged to extend the library of heterogeneous similarity measures and improve the diversity generation mechanism for building high-performance JIT soft sensors. Moreover, although this paper mainly focuses on manipulating input variables for building diverse input spaces based on evolutional multiobjective optimization approach, exploiting feature extraction by deep learning and making use of unlabeled data by semisupervised learning for improving the prediction performance of soft sensors are also interesting [47]. ese will be investigated in the future.…”

Section: Discussionmentioning

confidence: 99%

Ensemble Just-In-Time Learning-Based Soft Sensor for Mooney Viscosity Prediction in an Industrial Rubber Mixing Process

Jin

Wang

et al. 2020

Advances in Polymer Technology

View full text Add to dashboard Cite

e lack of online sensors for Mooney viscosity measurement has posed significant challenges for enabling efficient monitoring, control, and optimization of industrial rubber mixing process. To obtain real-time and accurate estimations of Mooney viscosity, a novel soft sensor method, referred to as multimodal perturbation-(MP-) based ensemble just-in-time learning Gaussian process regression (MP-EJITGPR), is proposed by exploiting ensemble JIT learning. is method employs perturbations on similarity measure and input variables for generating the diversity of JIT learners. Furthermore, a set of accurate and diverse JIT learners are built through an evolutionary multiobjective optimization by balancing the accuracy and diversity objectives explicitly. Moreover, all base JIT learners are combined adaptively using a finite mixture mechanism. e proposed method is applied to an industrial rubber mixing process for Mooney viscosity prediction, and the experimental results demonstrate its effectiveness and superiority over traditional soft sensor methods.

show abstract

Section: Discussionmentioning

confidence: 99%

Ensemble Just-In-Time Learning-Based Soft Sensor for Mooney Viscosity Prediction in an Industrial Rubber Mixing Process

Jin

Wang

et al. 2020

Advances in Polymer Technology

View full text Add to dashboard Cite

show abstract

“…Therefore, the accurate and reliable online measurement of Mooney viscosity is essential for monitoring, controlling and optimizing rubber-mixing production process. To solve this problem, data-driven soft sensor technology has been widely used for online real-time estimation of Mooney viscosity in recent years [3][4][5][6][7]. Such inferential methods realize the real-time and accurate estimation of Mooney viscosity by establishing the mathematical model between the easily measured secondary variables such as the temperature in the mixer cavity, the pressure of the stamping part, the motor speed and the motor power and the primary variable Mooney viscosity.…”

Section: Introductionmentioning

confidence: 99%

“…Until now, data-driven soft sensor methods for industrial Mooney viscosity prediction mainly include partial least squares (PLS) [8], Gaussian process regression (GPR) [3], extreme learning machine (ELM) [4] and deep learning (DL) [7]. However, these methods are essentially global modeling techniques, which cannot effectively deal with strong nonlinearity and multi-mode characteristics.…”

Section: Introductionmentioning

confidence: 99%

Deep Semi-Supervised Just-in-Time Learning Based Soft Sensor for Mooney Viscosity Estimation in Industrial Rubber Mixing Process

et al. 2022

View full text Add to dashboard Cite

Soft sensor technology has become an effective tool to enable real-time estimations of key quality variables in industrial rubber-mixing processes, which facilitates efficient monitoring and a control of rubber manufacturing. However, it remains a challenging issue to develop high-performance soft sensors due to improper feature selection/extraction and insufficiency of labeled data. Thus, a deep semi-supervised just-in-time learning-based Gaussian process regression (DSSJITGPR) is developed for Mooney viscosity estimation. It integrates just-in-time learning, semi-supervised learning, and deep learning into a unified modeling framework. In the offline stage, the latent feature information behind the historical process data is extracted through a stacked autoencoder. Then, an evolutionary pseudo-labeling estimation approach is applied to extend the labeled modeling database, where high-confidence pseudo-labeled data are obtained by solving an explicit pseudo-labeling optimization problem. In the online stage, when the query sample arrives, a semi-supervised JITGPR model is built from the enlarged modeling database to achieve Mooney viscosity estimation. Compared with traditional Mooney-viscosity soft sensor methods, DSSJITGPR shows significant advantages in extracting latent features and handling label scarcity, thus delivering superior prediction performance. The effectiveness and superiority of DSSJITGPR has been verified through the Mooney viscosity prediction results from an industrial rubber-mixing process.

show abstract

“…[ 20 , 21 , 22 ]. Among the most extensively used deep networks architectures are stacked autoencoder (SAE) [ 23 , 24 ], deep belief network (DBN) [ 25 , 26 ], convolutional neural network (CNN) [ 26 , 27 ] and long short-term memory (LSTM) [ 28 , 29 ]. For deep learning structures such as SAE, the greedy layer-wise unsupervised pre-training and supervised fine-tuning are very significant.…”

Section: Introductionmentioning

confidence: 99%

Industrial Semi-Supervised Dynamic Soft-Sensor Modeling Approach Based on Deep Relevant Representation Learning

Lima

Araújo

2021

Sensors

View full text Add to dashboard Cite

Soft sensors based on deep learning have been growing in industrial process applications, inferring hard-to-measure but crucial quality-related variables. However, applications may present strong non-linearity, dynamicity, and a lack of labeled data. To deal with the above-cited problems, the extraction of relevant features is becoming a field of interest in soft-sensing. A novel deep representative learning soft-sensor modeling approach is proposed based on stacked autoencoder (SAE), mutual information (MI), and long-short term memory (LSTM). SAE is trained layer by layer with MI evaluation performed between extracted features and targeted output to evaluate the relevance of learned representation in each layer. This approach highlights relevant information and eliminates irrelevant information from the current layer. Thus, deep output-related representative features are retrieved. In the supervised fine-tuning stage, an LSTM is coupled to the tail of the SAE to address system inherent dynamic behavior. Also, a k-fold cross-validation ensemble strategy is applied to enhance the soft-sensor reliability. Two real-world industrial non-linear processes are employed to evaluate the proposed method performance. The obtained results show improved prediction performance in comparison to other traditional and state-of-art methods. Compared to the other methods, the proposed model can generate more than 38.6% and 39.4% improvement of RMSE for the two analyzed industrial cases.

show abstract

Robust Soft Sensor with Deep Kernel Learning for Quality Prediction in Rubber Mixing Processes

Cited by 21 publications

References 37 publications

Ensemble Just-In-Time Learning-Based Soft Sensor for Mooney Viscosity Prediction in an Industrial Rubber Mixing Process

Ensemble Just-In-Time Learning-Based Soft Sensor for Mooney Viscosity Prediction in an Industrial Rubber Mixing Process

Deep Semi-Supervised Just-in-Time Learning Based Soft Sensor for Mooney Viscosity Estimation in Industrial Rubber Mixing Process

Industrial Semi-Supervised Dynamic Soft-Sensor Modeling Approach Based on Deep Relevant Representation Learning

Contact Info

Product

Resources

About