针对目前电力工程费用计算复杂、时间成本较高且准确性低的问题,文中开展了基于改进BiLSTM的电力工程数据智能分析算法设计研究.从技术、工程量和费用三个维度构建了电力工程数据智能分析指标体系,进而提出了一种基于BiLSTM与Attention联合模型的电力工程费用预测算法.该算法将电力工程数据作为BiLSTM的模型输入,并采用Attention机制提高了对重要数据的关注程度.通过引入数据指标与电力工程费用的自动关联分析技术,实现了对电力工程费用的精准预测.仿真算例分析结果表明,与LSTM及BiLSTM算法相比,所提算法具有更高的预测准确性,平均预测误差小于5%.
Aiming at the problems of complex calculation of power engineering cost,high time cost and low accuracy,this paper carries out the design and research of intelligent analysis algorithm of power engineering data based on improved BiLSTM.The intelligent analysis index system of power engineering data is constructed from three dimensions of technology,engineering quantity and cost,and then a power engineering cost prediction algorithm based on the joint model of BiLSTM and Attention is proposed.The algorithm takes the power engineering data as the model input of BiLSTM,and uses the Attention mechanism to improve the attention to important data.By introducing the automatic correlation analysis technology between data indicators and power engineering costs,the accurate prediction of power engineering costs is realized.The simulation results show that compared with LSTM and BiLSTM algorithm,the proposed algorithm has higher prediction accuracy,and the average prediction error is less than 5%.