As coal ore and other resources are continuously mined, a three-zone structure is formed underground consisting of a sagging zone, fault zone, and caving zone. The use of well-logging data to identify the three zones is important for production safety and environmental management. Owing to the scarcity of data that can reflect three zones in normal coal mining, conventional identification and prediction methods face challenges when extracting data features, incurring a degree of uncertainty within prediction results. Accordingly, the accurate identification of the three zones has become a critical objective in daily production. To address this issue, we developed a method called a method called backpropagation neural networks with Dempster–Shafer (DS) evidence theory. Initially, we preprocessed the training data and deployed two backpropagation neural networks (BPNNs) to predict the three zones according to two parameters. According to these prediction results, the local and global credibility of each prediction is calculated and used to obtain the basic probability assignment function required for the DS evidence theory. Finally, the DS evidence theory is used to fuse the two BPNNs prediction results, thereby producing the final prediction results. The proposed method was demonstrated to improve prediction accuracy by 6.4% compared to a conventional neural network.

1. [1] X. Zhang et al., “Study on the Law and Risk of Spontaneous Combustion of Residual Coal During Water Drainage in Goaf,” Energies, Vol.15, No.23, Article No.8896, 2022. https://doi.org/10.3390/en15238896
2. [2] Y. Zheng et al., “Study on multi-field evolution and influencing factors of coal spontaneous combustion in goaf,” Combustion Science and Technology, Vol.195, pp. 247-264, 2023. https://doi.org/10.1080/00102202.2021.1947262
3. [3] J. Li et al., “The application of ultrasonic imaging technology in the detection of water filled goaf area: A case study,” 51st US Rock Mechanics/Geomechanics Symp., pp. 1915-1920, 2017.
4. [4] R. Ding et al., “GIS-based subsidence prediction of Yuzhou goaf area at the middle route of the south-to-north water diversion project,” Geotechnical and Geological Engineering, Vol.37, pp. 1411-1420, 2019. https://doi.org/10.1007/s10706-018-0695-4
5. [5] K. Zhang et al., “Classification strategies of electrical characterization based on k-means clustering: Applying controlled-source audio-frequency magnetotellurics for goaf detection,” SEG Technical Program Expanded Abstracts, pp. 631-635, 2020. https://doi.org/10.1190/segam2020-3407930.1
6. [6] J. Zhou et al., “Identification of large-scale goaf instability in underground mine using particle swarm optimization and support vector machine,” Int. J. of Mining Science and Technology, Vol.23, No.5, pp. 701-707, 2013. https://doi.org/10.1016/j.ijmst.2013.08.014
7. [7] Y. Yao et al., “Accurate Measurement Method of Drilling Depth Based on Multi-Sensor Data Fusion,” J. Adv. Comput. Intell. Intell. Inform., Vol.26, No.3, pp. 367-374, 2022. https://doi.org/10.20965/jaciii.2022.p0367
8. [8] Y. Jiang et al., “Health diagnosis of marine engine room equipment based on BP and DS evidence theory,” Vibroengineering Procedia, Vol.45, pp. 15-21, 2022. https://doi.org/10.21595/vp.2022.22896
9. [9] K. Zhao et al., “A New Multi-classifier Ensemble Algorithm Based on D-S Evidence Theory,” Neural Processing Letters, Vol.54, pp. 5005-5021, 2022. https://doi.org/10.1007/s11063-022-10845-2
10. [10] S. Wu et al., “A model for evaluation of surrounding rock stability based on D-S evidence theory and error-eliminating theory,” Bulletin of Engineering Geology and the Environment, Vol.80, pp. 2237-2248, 2021. https://doi.org/10.1007/s10064-020-02060-x
11. [11] J. Geng and Z. Wei, “A new method for constructing the basic probability assignment function in D-S evidence theory,” J. of Physics: Conf. Series, Vol.1746, Article No.012038, 2021. https://doi.org/10.1088/1742-6596/1746/1/012038
12. [12] Q. Cui et al., “Comprehensive evaluation of electric power prediction models based on DS evidence theory combined with multiple accuracy indicators,” J. of Modern Power Systems and Clean Energy, Vol.10, No.3, pp. 597-605, 2021. https://doi.org/10.35833/MPCE.2020.000470
13. [13] J. Cai et al., “Face Fatigue Feature Detection Based on Improved D-S Model in Complex Scenes,” IEEE Access, Vol.11, pp. 101790-101798, 2023. https://doi.org/10.1109/ACCESS.2023.3314665
14. [14] Z.-M. Teng et al., “GPS Map Matching Algorithm Based on Improved D-S Evidence Theory in Complex Road Sections,” J. of Network Intelligence, Vol.8, No.1, pp. 89-99, 2023.
15. [15] Y. Wang and S. Wang, “Feature selection for set-valued data based on D-S evidence theory,” Artificial Intelligence Review, Vol.56, pp. 2667-2679, 2023. https://doi.org/10.1007/s10462-022-10241-1