Litcius/Paper detail

Quality-Driven Regularization for Deep Learning Networks and Its Application to Industrial Soft Sensors

Chen Ou, Hongqiu Zhu, Yuri A. W. Shardt, Lingjian Ye, Xiaofeng Yuan, Yalin Wang, Chunhua Yang

2022IEEE Transactions on Neural Networks and Learning Systems103 citationsDOI

Abstract

The growth of data collection in industrial processes has led to a renewed emphasis on the development of data-driven soft sensors. A key step in building an accurate, reliable soft sensor is feature representation. Deep networks have shown great ability to learn hierarchical data features using unsupervised pretraining and supervised fine-tuning. For typical deep networks like stacked auto-encoder (SAE), the pretraining stage is unsupervised, in which some important information related to quality variables may be discarded. In this article, a new quality-driven regularization (QR) is proposed for deep networks to learn quality-related features from industrial process data. Specifically, a QR-based SAE (QR-SAE) is developed, which changes the loss function to control the weights of the different input variables. By choosing an appropriate inductive bias for the weight matrix, the model provides quality-relevant information for predictive modeling. Finally, the proposed QR-SAE is used to predict the quality of a real industrial hydrocracking process. Comparative experiments show that QR-SAE can extract quality-related features and achieve accurate prediction performance.

Topics & Concepts

Artificial intelligenceDeep learningRegularization (linguistics)Computer scienceSoft sensorMachine learningProcess (computing)Key (lock)Artificial neural networkFeature (linguistics)Deep belief networkPattern recognition (psychology)Process controlData miningSupervised learningEngineeringQuality (philosophy)AutoencoderData qualityData modelingFunction (biology)Feature extractionFault Detection and Control SystemsAdvanced Control Systems OptimizationMachine Fault Diagnosis Techniques