基于改进粒子群算法的土石方调配优化研究

粒子群优化算法是一类随机全局优化技术,具有收敛速度快、规则简单、易于实现的优点.针对标准粒子群算法搜索精度不高,易陷入局部最优的缺点,本文对标准粒子群算法进行了改进,改进的算法在粒子飞行中动态地调整粒子飞行的惯性权重,提高了标准粒子群算法收敛速度与收敛精度,降低了早熟收敛的比率.本文分析了用线性规划方法进行土石方调配的优缺点,并把本文提出的改进粒子群算法用于面板堆石坝的土石方调配优化中.与线性规划方法相比,该方法对土石方调配问题的约束和目标函数没有线性要求,具有可以考虑实际工程中非线性约束的优点,因此比常用的线性规划方法更接近工程实际.通过对某大型面板堆石坝的土石方调运分析以及与线性规划调运结果比较,表明本文提出的算法是正确可行的.     

Earthwork digital twin for teleoperation of an automated bulldozer in edge dumping

The unstructured construction site with a complex and changeable environment brings challenges to human–machine interaction. In this study, the earthwork digital twin (DT) is proposed to realize accurate and real-time perception, which can support the teleoperation of an automated bulldozer. The overall framework includes anterior-time DT, real-time DT, and posterior-time DT, which integrates three-dimensional modeling, edge detection, and blade trajectory algorithms. Multidimensional heterogeneous data in bulldozer teleoperation can be displayed in real-time to ensure construction safety. Big data during teleoperation of the construction process can be collected, stored, and analyzed. The DT proposed in this study was successfully applied in a major construction project in China, and testing results show its universality, robustness, and advanced performance. The key technologies proposed in this study can be applied to solve the common problems in the construction industry, which is promising for future intelligent construction.