z-logo
open-access-imgOpen Access
Investigating the Working Efficiency of Typical Work in High-Altitude Alpine Metal Mining Areas Based on a SeqGAN-GABP Mixed Algorithm
Author(s) -
Hua Ning,
He Huang,
Xinhong Zhang
Publication year - 2021
Publication title -
advances in civil engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.379
H-Index - 25
eISSN - 1687-8094
pISSN - 1687-8086
DOI - 10.1155/2021/9941415
Subject(s) - backpropagation , computer science , artificial neural network , data mining , altitude (triangle) , effects of high altitude on humans , algorithm , artificial intelligence , machine learning , mathematics , meteorology , physics , geometry
Man-machine efficacy evaluations of typical work in the safe mining of high-altitude alpine metal mines are associated with fuzziness, multiple indexes, and large subjective components. This results in difficulties in the prediction of the typical work efficiency in high-altitude alpine metal mining areas. In this study, ergonomic theory was applied to establish the evaluation index system of typical work efficiency in high-altitude alpine metal mining areas by studying the cooperative relationship between operators, working machines, working environment, and design variables. First, we investigated the collaborative relationship between workers, operating machinery, operating environment, and design variables in order to establish the evaluation index system of typical work efficiency in high-altitude alpine metal mining areas. Second, principal component analysis (PCA) was integrated with the fusion entropy weight method to (i) analyze the coupling correlation and overlapping effects between the factors influencing efficiency at different altitudes and (ii) to determine the key influencing factors. Third, a model based on the sequence generative adversarial network genetic algorithm backpropagation (SeqGAN-GABP) hybrid algorithm was established to predict the trends in the operating efficiency of typical work types in high-altitude alpine metal mining areas. Finally, three high-altitude alpine metal mines in Xinjiang were selected as representative examples to verify the proposed framework by comparing it with other state-of the art models (multiple linear regression prediction model, backpropagation (BP) neural network model, and genetic algorithm back propagation (GA-BP) neural network model). Results determine the average relative error of each model as 2.74%, 1.97%, 1.29%, and 1.02%, respectively, indicating the greater accuracy of our proposed method in predicting the efficiency of typical work types in high-altitude alpine mining areas. This study can provide a scientific basis for the establishment of mining safety judgment standards in high-altitude alpine areas.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here
Accelerating Research

Address

John Eccles House
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom