Hot Deformation Behavior of Near-Β Titanium Alloy Ti-3mo-6cr-3al-3sn Based on Phenomenological Constitutive Model and a Machine Learning Algorithm

Xue-jia, Liu; Zhang, Haoyu; Zhang, Shuai; Wen, Peng; Zhou, Ge; Wang, Chuan; Chen, Lijia

doi:10.2139/ssrn.4487579

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The WOA can be divided into phases of exploration and development by imitating random food searching, encircling predation, and bubble predation during whale predation. Random food searching belongs to the exploration phase, and encircling predation and bubble predation belong to the development phase 25,26,27 . In the algorithm, the whale represents a point in the spatial problem, and the optimal position to hunt prey represents the optimal solution of the optimization problem, which, according to the algorithm principle, can be specified as Eq.…”

Section: Woa-bp Neural Network Modelingmentioning

confidence: 99%

Displacement prediction of fine-grained tailings ponds based on WOA-BP neural network

Liu,

Wang,

Liu

et al. 2024

Preprint

View full text Add to dashboard Cite

Tailing reservoir is an important auxiliary facility of mine and a dangerous source of man-made debris flow with high potential energy. China’s tailings ponds are shifting toward fine-grained high dams. Accordingly, displacement is one of the key factors affecting pond stability, and it is important to understand the displacement trend of the tailings pond to ensure its safe operation. Accordingly, this paper adopts the whale algorithm to optimize the back propagation(BP) neural network and establishes the WOA-BP neural network nonlinear prediction model to avoid the error generated by the model experiment due to the scaling effect. The infiltration line and displacement data of a tailings pond in Sichuan Province in the past two years are collected consecutively to form a learning sample, which is then used for training to predict the displacement of the tailings pond through the WOA-BP neural network model. Thereafter, these prediction results are compared with the actual monitoring values as well as the BP neural network model prediction values. The results revealed that the relative error of the WOA-BP neural network model prediction results was approximately 4.5%, and the Pearson correlation coefficients were all above 0.998. Compared with the traditional BP neural network model, the optimization model has a stronger search capability, wider application range, higher prediction accuracy, a more global optimal solution, and better response. The nonlinear fuzzy mapping provides new insights into tailings pond displacement and safety prediction.

show abstract

Section: Woa-bp Neural Network Modelingmentioning

confidence: 99%