Prediction of Electric Load for Users Based on BP Neural Network
Journal of Computer Science and Artificial Intelligence · 29.03.2026 · 6 (3) · 6-8
DOI: 10.54097/zvz5ws33 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computer Science and Artificial Intelligence, online erschienen am 29.03.2026. Verfasst von Siyi Liu und 2 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Rock masses in underground engineering are generally subjected to complex three-dimensional stress conditions rather than uniaxial loading. Therefore, triaxial compression testing has become a fundamental approach for investigating the strength, deformation, and failure behavior of rocks. In recent decades, extensive studies have been conducted on rock failure laws under triaxial compression, with particular attention to the effects of confining pressure, crack initiation and propagation, damage evolution, and macroscopic failure modes. Existing studies indicate that confining pressure not only increases the peak strength and residual bearing capacity of rocks, but also suppresses tensile crack growth, promotes shear localization, and drives the transition from brittle failure to ductile failure. In addition, the full failure process of rocks under triaxial compression is characterized by distinct stages, including crack closure, elastic deformation, stable crack propagation, unstable crack propagation, and post-peak failure. Acoustic emission monitoring, ultrasonic wave velocity analysis, and energy-based methods have further improved the understanding of progressive rock damage and failure mechanisms. This paper systematically reviews the current research on the strength evolution, deformation characteristics, failure modes, and major controlling factors of rocks under triaxial compression. On this basis, the limitations of existing studies are discussed, especially with respect to fractured rock masses, layered composite rocks, and complex stress paths. Future research directions are also proposed, including multi-method characterization, multi-field coupling analysis, and the integration of laboratory results with engineering-scale applications. This review may provide a useful reference for the study of rock mechanics and the stability evaluation of deep underground engineering.
Zitieren
APA
Liu, S., Wang, R., & Fang, Y. (2026). Prediction of Electric Load for Users Based on BP Neural Network. Journal of Computer Science and Artificial Intelligence, 6(3), 6-8. https://doi.org/10.54097/zvz5ws33
Vancouver
Liu S, Wang R, Fang Y. Prediction of Electric Load for Users Based on BP Neural Network. Journal of Computer Science and Artificial Intelligence. 2026;6(3):6-8. doi:10.54097/zvz5ws33
BibTeX
@article{Liu2026,
author = {Liu, Siyi and Wang, Runmin and Fang, Yudong},
title = {Prediction of Electric Load for Users Based on BP Neural Network},
journal = {Journal of Computer Science and Artificial Intelligence},
year = {2026},
volume = {6},
number = {3},
pages = {6--8},
doi = {10.54097/zvz5ws33}
}
EUVIMED