Temperature Prediction of Heating Furnace Based on Deep Transfer Learning.

Xiaofeng Zhou,Naiju Zhai

doi:10.3390/s20174676

Abstract

Heating temperature is very important in the process of billet production, and it directly affects the quality of billet. However, there is no direct method to measure billet temperature, so we need to accurately predict the temperature of each heating zone in the furnace in order to approximate the billet temperature. Due to the complexity of the heating process, it is difficult to accurately predict the temperature of each heating zone and each heating zone sensor datum to establish a model, which will increase the cost of calculation. To solve these two problems, a two-layer transfer learning framework based on a temporal convolution network (TL-TCN) is proposed for the first time, which transfers the knowledge learned from the source heating zone to the target heating zone. In the first layer, the TCN model is built for the source domain data, and the self-transfer learning method is used to optimize the TCN model to obtain the basic model, which improves the prediction accuracy of the source domain. In the second layer, we propose two frameworks: one is to generate the target model directly by using fine-tuning, and the other is to generate the target model by using generative adversarial networks (GAN) for domain adaption. Case studies demonstrated that the proposed TL-TCN framework achieves state-of-the-art prediction results on each dataset, and the prediction errors are significantly reduced. Consistent results applied to each dataset indicate that this framework is the most advanced method to solve the above problem under the condition of limited samples.

Highlights

As one of the most important pieces of combustion equipment in the metallurgical production process, the heating furnace is the most important piece of energy consumption equipment in the steel rolling production line
Published research shows that temporal convolutional network (TCN) models perform significantly better than recurrent network structures in sequence modeling problems, including speech analysis and synthesis tasks [19]
In view of the above two difficulties, and combined with the characteristics of the similarity of each heating zone, we propose a multi heating zone temperature prediction framework based on transfer learning (TL) [22]

Summary

Introduction

As one of the most important pieces of combustion equipment in the metallurgical production process, the heating furnace is the most important piece of energy consumption equipment in the steel rolling production line. The optimization of the heating furnace is of great significance to iron and steel metallurgical enterprises. The main function of the heating furnace is to heat the billet, make it reach the predetermined temperature, and roll it [1]. The billet temperature cannot be directly measured. We take the temperature of the heating furnace collected by the thermocouple sensor as the billet heating temperature. It is difficult to predict the furnace temperature accurately. It is mainly manifested in the following aspects:

Objectives

Methods

Findings

Discussion

Conclusion