Optimization and forecasting of reinforced wire ropes for tower crane by using hybrid HHO-PSO and ANN-HHO algorithms

Abstract

Wire rope is a vital component of every crane. Wire rope faults are related to the operation, fabrication environment, etc., and the prevalent mode of failure is fatigue. The aim of this study is to develop an advanced tower crane applicable to wire rope with integrated reinforcement. Steel wire ropes are superiorly used in several tower crane applications, but they may create certain failures such as less fatigue and wear-resistant. In this study, steel wires are strengthened by granite and Zinc oxide (ZnO) reinforcement. Two sets of wire ropes are prepared as complete and partial reinforcement of steel wire with seven strands and 15 wires. The failure tests such as hardness, wear analysis, tensile strength, and fatigue life are optimized using hybrid Harris Hawk optimization-based Particle swarm Optimization (Hybrid HHO-PSO). Besides, the experimented wire rope performances are predicted using hybrid Artificial Neural Network based HHO (Hybrid ANN-HHO). Fully reinforced wire ropes provide better performances for both experimented and optimization behaviors. This provides 1818 MPa of maximum tensile strength, 0.23 mm of minimal wear depth, and 3.38x104 times better fatigue life. In the HHO-PSO optimization method, the obtained better tensile strength is 1822 MPa, wear depth is 0.66 mm, and Fatigue life is 3.57 x104 times. Besides, from the predicted outcomes, ANN-HHO provides a minimal error value than the ANN approach. The result of this study will open up different ways for the advancement of wire rope in tower crane application by improving its load bearing capacity. The outcomes from this research can be practically applicable for increasing the load bearing capacity of the tower crane without increasing the number of wires and strands in the wire rope.