A Dynamic Weighing Method for Portal Crane in Bulk Port: Based on Clustering and BP Neural Network

In the process of cargo handling in bulk port, dynamic weighing of cargo is the basis of the information management system for bulk cargo handling. Due to many interference factors, it is difficult to obtain the actual lifting weight of portal crane by using mechanical way. To address this issue, a new method of using motor power is proposed in this paper. In this method, the real-time motor voltage, current and power factor during hoisting operations are collected and input into a pre-trained BP neural network to calculate the lifting weight of portal crane. K-means clustering algorithm is used to analyze and filter the measured data for finding the required power value. The BP neural network model can well reflect the relationship between lifting weight and the instantaneous output power of the portal crane hoisting mechanism motor (lifting motor and open-closed motor). Finally, the experimental results demonstrate the effectiveness of the proposed method.