A Detail-Preserving Multi-Scale Cascaded Network for Infrared Rotary Kiln Shell Temperature Recognition and Refractory Lining Assessment

Li, Jie; He, Jianxin; Liu, Hao; Hou, Yunhan; Dong, Zhiming; Zhang, Qian

doi:10.3390/met16060597

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

A Detail-Preserving Multi-Scale Cascaded Network for Infrared Rotary Kiln Shell Temperature Recognition and Refractory Lining Assessment

by

Jie Li

¹

,

Jianxin He

²,

Hao Liu

²

,

Yunhan Hou

²,

Zhiming Dong

^2,*

and

Qian Zhang

³

¹

School of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai 200240, China

²

School of Computer Science and Engineering, Chongqing University of Science and Technology, Chongqing 401331, China

³

Mingyue Lake Laboratory, Chongqing 401331, China

^*

Author to whom correspondence should be addressed.

Metals 2026, 16(6), 597; https://doi.org/10.3390/met16060597 (registering DOI)

Submission received: 30 April 2026 / Revised: 27 May 2026 / Accepted: 28 May 2026 / Published: 29 May 2026

(This article belongs to the Section Computation and Simulation on Metals)

Download Versions Notes

Abstract

Rotary kiln shell temperature monitoring is essential for metallic shell protection and refractory lining maintenance in high-temperature industrial processes, while smoke, dust, thermal diffusion and non-kiln heat sources make valid shell temperature extraction difficult. This study develops a multi-scale cascaded network with low-resolution space-to-depth downsampling (MSC-LSTD) for infrared kiln shell segmentation and temperature recognition. Global infrared thermal images and local laser temperature measurements are used to construct a calibrated rotary kiln infrared dataset, and predicted kiln shell masks are mapped to temperature matrices for valid shell temperature analysis. MSC-LSTD achieves 99.82% aAcc, 99.14% mAcc and 97.03% mIoU on the rotary kiln infrared dataset, showing robust segmentation performance under complex thermal interference. The proposed framework provides a practical image-based solution for kiln shell overheating warning and refractory lining degradation assessment.

Keywords: rotary kiln; infrared thermography; kiln shell temperature recognition; multi-scale cascaded network; thermal image segmentation

Share and Cite

MDPI and ACS Style

Li, J.; He, J.; Liu, H.; Hou, Y.; Dong, Z.; Zhang, Q. A Detail-Preserving Multi-Scale Cascaded Network for Infrared Rotary Kiln Shell Temperature Recognition and Refractory Lining Assessment. Metals 2026, 16, 597. https://doi.org/10.3390/met16060597

AMA Style

Li J, He J, Liu H, Hou Y, Dong Z, Zhang Q. A Detail-Preserving Multi-Scale Cascaded Network for Infrared Rotary Kiln Shell Temperature Recognition and Refractory Lining Assessment. Metals. 2026; 16(6):597. https://doi.org/10.3390/met16060597

Chicago/Turabian Style

Li, Jie, Jianxin He, Hao Liu, Yunhan Hou, Zhiming Dong, and Qian Zhang. 2026. "A Detail-Preserving Multi-Scale Cascaded Network for Infrared Rotary Kiln Shell Temperature Recognition and Refractory Lining Assessment" Metals 16, no. 6: 597. https://doi.org/10.3390/met16060597

APA Style

Li, J., He, J., Liu, H., Hou, Y., Dong, Z., & Zhang, Q. (2026). A Detail-Preserving Multi-Scale Cascaded Network for Infrared Rotary Kiln Shell Temperature Recognition and Refractory Lining Assessment. Metals, 16(6), 597. https://doi.org/10.3390/met16060597

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

A Detail-Preserving Multi-Scale Cascaded Network for Infrared Rotary Kiln Shell Temperature Recognition and Refractory Lining Assessment

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI