基于神经网络的泵机组运行效率研究

Study of Operation Efficiency for Pump Unit Based on Neural Network

现代长距离输油管道大多采用密闭输送的方式,目前输油系统普遍使用离心泵机组作为提供能量的动力装置。机组效率是评价泵机组运行节能与否的重要因素。通过分析影响机组效率的主要因素,根据机组效率与各因素之间的关系,利用人工神经网络构建泵性能的预测模型,并使用实际测量的参数来训练网络。预测结果表明,神经网络可以实现对离心泵机组效率的精确预测并可用于实际应用。

The tight-pipeline was used for the long-distance pipelines, and the centrifugal pump units were used as power plants in oil transport system. The efficiency of pump units is a very important factor for evaluating. By analyzing the main factors affecting the unit efficiency and according to the relationships between the unit efficiency and various factors, artificial neural network prediction models were used to construct the prediction model of pump performance and the actual measured parameters were used to train network. The results show that the neural network can realize the accurate prediction to the efficiency of centrifugal pump units and can apply to practical applications