Premium
Assessing Earth‐Moving Operation Capacity by Neural Network‐Based Simulation with Physical Factors
Author(s) -
Chao LiChung
Publication year - 2001
Publication title -
computer‐aided civil and infrastructure engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.773
H-Index - 82
eISSN - 1467-8667
pISSN - 1093-9687
DOI - 10.1111/0885-9507.00233
Subject(s) - excavator , computer science , task (project management) , process (computing) , production (economics) , simulation , object (grammar) , artificial neural network , work (physics) , constant (computer programming) , industrial engineering , engineering , artificial intelligence , mechanical engineering , systems engineering , economics , macroeconomics , programming language , operating system
The traditional deterministic method for estimating the production capacity of an earth‐moving operation assumes constant midpoint physical job conditions. In contrast generic simulation models use input of task times without linking production directly to physical factors. This paper presents a microlevel simulation approach, based on thorough evaluation of the effects of changing physical conditions on task times and production, and uses a typical excavation and hauling operation for illustration. Trained neural networks are employed as the computing mechanism for determining equipment cycle times and optimizing the work zone of the excavator. The obtained times are fed directly into a simulation process to establish the cumulative production rate as the achievable operation capacity. Object‐oriented programming is suggested for implementing the solution procedures. The results for two models of excavators in various job conditions are compared with the deterministic estimates.