Coal-Gangue Recognition Method for Top-Coal Caving Based on Improved ACGAN and PCSA-MobileNetV3

被引：0

作者：

Dai, Jialiang ^{[1
]}

Si, Lei ^{[1
]}

Li, Jiahao ^{[1
]}

Wang, Zhongbin ^{[1
]}

Wei, Dong ^{[1
]}

Gu, Jinheng ^{[1
]}

Li, Xin ^{[1
]}

Liu, Yang ^{[1
]}

机构：

[1] China Univ Min & Technol, Sch Mech & Elect Engn, Xuzhou 221116, Jiangsu, Peoples R China

来源：

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT | 2025年 / 74卷

基金：

中国国家自然科学基金;

关键词：

Vibrations; Generators; Coal; Generative adversarial networks; Training; Image recognition; Data models; Face recognition; Data augmentation; Accuracy; Auxiliary classifier generative adversarial network (ACGAN); coal-gangue recognition; data augmentation; MobileNetV3; vibration signal; IMPACT-SLIP EXPERIMENTS; IDENTIFICATION; TECHNOLOGY;

D O I：

10.1109/TIM.2025.3547522

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

At the top-coal caving face, accurately and quickly identifying the content of coal and gangue is an important prerequisite for intelligent and efficient mining. Data scarcity has been caused by the limited conditions in the mine, restricting the recognition of the coal-gangue mix ratio at the top-coal caving face. Therefore, this article proposes a method for identifying the coal-gangue mix ratio under insufficient sample conditions, based on improved auxiliary classifier generative adversarial network (IACGAN) and parallel coordinate and squeeze-and-excite attention (PCSA)-MobileNetV3. First, the coal-gangue vibration data are mapped into 2-D vibration spectral images. Then, the IACGAN is enhanced with a self-attention (SA) mechanism and residual structure to generate diverse, high-quality training samples despite sample deficiency. These generated images are then added to the dataset to expand the dataset size. Finally, the PCSA mechanism is integrated into the MobileNetV3 model to classify coal-gangue vibration spectral images based on the learned spatial and spectral features. The experimental results indicate that the proposed method outperforms superior recognition performance and effectively assists in the mix ratio recognition of coal and gangue under a small sample.

引用

页数：11

共 43 条

[1]

Arjovsky M, 2017, Arxiv, DOI [arXiv:1701.07875, DOI 10.48550/ARXIV.1701.07875]

[2] An integrated framework of optimized learning networks for classifying oil-mixed microplastics [J].

Chen, Yifu ;

Zhang, Baiyu ;

Yang, Min ;

Xin, Xiaying ;

Kang, Qiao ;

Ye, Xudong ;

Chen, Bing .

JOURNAL OF CLEANER PRODUCTION, 2022, 379

[3]

Daquan Z, 2020, Arxiv, DOI [arXiv:2007.02269, 10.48550/arXiv.2007.02269]

[4]

[窦希杰 Dou Xijie], 2020, [振动与冲击, Journal of Vibration and Shock], V39, P39

[5]

Goodfellow IJ, 2014, arXiv, DOI [DOI 10.48550/ARXIV.1406.2661, 10.48550/arXiv.1406.2661]

[6] Transfer learning empowers accurate pharmacokinetics prediction of small samples [J].

Guo, Wenbo ;

Dong, Yawen ;

Hao, Ge-Fei .

DRUG DISCOVERY TODAY, 2024, 29 (04)

[7]

Hou Q., 2021, arXiv, DOI [arXiv:2103.02907, 10.48550/arXiv.2103.02907]

[8]

Howard A, 2019, Arxiv, DOI [arXiv:1905.02244, 10.48550/arXiv.1905.02244]

[9] Dual-energy X-ray transmission identification method for coal and gangue with different thicknesses and densities [J].

Li, Deyong ;

He, Lei ;

Guo, Yongcun ;

Wang, Shang ;

Cheng, Gang .

MEASUREMENT, 2024, 225

[10] Time-frequency ridge estimation: An effective tool for gear and bearing fault diagnosis at time-varying speeds [J].

Li, Yifan ;

Zhang, Xin ;

Chen, Zaigang ;

Yang, Yaocheng ;

Geng, Changqing ;

Zuo, Ming J. .

MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2023, 189

← 1 2 3 4 5 →