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

Shuihua Zheng,Xuelei Zhang,Hao Chen,Yili Xu,Kaixin Liu,Yi Liu

doi:10.3390/s20030695

Abstract

Although several data-driven soft sensors are available, online reliable prediction of the Mooney viscosity in industrial rubber mixing processes is still a challenging task. A robust semi-supervised soft sensor, called ensemble deep correntropy kernel regression (EDCKR), is proposed. It integrates the ensemble strategy, deep brief network (DBN), and correntropy kernel regression (CKR) into a unified soft sensing framework. The multilevel DBN-based unsupervised learning stage extracts useful information from all secondary variables. Sequentially, a supervised CKR model is built to explore the relationship between the extracted features and the Mooney viscosity values. Without cumbersome preprocessing steps, the negative effects of outliers are reduced using the CKR-based robust nonlinear estimator. With the help of ensemble strategy, more reliable prediction results are further obtained. An industrial case validates the practicality and reliability of EDCKR.

Highlights

The rubber mixing process is the first and important phase in tire and rubber manufacturing.During the process, natural rubber, synthetic raw materials, and additives are put into the internal mixer
Most of the existing Mooney viscosity soft sensors belong to the first category, such as shallow neural networks (NNs) [10,11], partial least squares (PLS) [12,13], Gaussian process regression (GPR) [12,13,14,15], and extreme learning machine (ELM) [16]
When deep brief network (DBN) is applied to regression problems, higher-level features are learnt in the unsupervised learning stage to absorb

Summary

Introduction

The rubber mixing process is the first and important phase in tire and rubber manufacturing. Most of the existing Mooney viscosity soft sensors belong to the first category, such as shallow neural networks (NNs) [10,11], partial least squares (PLS) [12,13], Gaussian process regression (GPR) [12,13,14,15], and extreme learning machine (ELM) [16] They learn a labeled dataset n o n oN. To the best of our knowledge, DNNs have never been applied to rubber mixing processes, especially for the Mooney viscosity modeling and prediction. Another common challenge for a practice soft sensor development is its reliability.

Restricted Boltzmann Machine Construction n o

Restricted Boltzmann Machine Construction l l

Deep Correntropy Kernel Regression Model

Reliability Enhancement Using Bagging-Based Ensemble Strategy

Industrial Mooney Viscosity Prediction

Conclusions