[关键词]
[摘要]
针对地铁车轮磨耗数据时间跨度较长引起的长期依赖问题,为了进一步提升预测精度,本文提出了一种将麻雀搜索算法(SSA)优化双向长短期记忆网络(Bi-LSTM)的改进BiLSTM网络模型,用于地铁车轮磨耗预测。首先利用麻雀搜索算法对双向长短期记忆网络算法的神经元个数、迭代次数、输入批量和学习率等超参数在给定范围内进行寻优,得到参数最优值,接着以参数最优值来构建改进BiLSTM网络模型,对车轮磨耗进行预测分析。以车轮踏面磨耗和轮缘磨耗作为研究对象,将某地铁1车厢1号车轮的现场实测历史磨耗数据作为输入,对该模型进行训练及验证分析,并与MLP、LSTM、BiLSTM以及SSA-LSTM模型的预测结果进行对比。研究表明:改进BiLSTM网络模型的磨耗预测精度更高,与LSTM、BiLSTM以及SSA-LSTM网络模型相比,踏面磨耗的平均绝对百分误差(MAPE)分别降低了13.28%、10.32%、1.47%,轮缘磨耗分别降低了9.5%、0.46%、0.02%,并与同一地铁2号、4号车的1号轮磨耗数据进行对比,结果验证了该模型有较好的泛化性。本文提出的基于改进BiLSTM网络的车轮磨耗预测模型可以有效提高预测精度,为地铁轮对智能化管理提供理论支持,延长车轮使用寿命。
[Key word]
[Abstract]
In order to address the issue of long-term dependence caused by the extended time span of wheel wear data and improve the prediction accuracy, this paper an improved BiLSTM metro wheel wear prediction model is proposed by optimizing Bidirectional Long short-term memory network (Bi-LSTM) with Sparrow search algorithm (SSA). Firstly, the hyperparameters of the Bi-LSTM algorithm, such as the number of neurons, iteration count, input batch size, and learning rate, are optimized using the SSA. This optimization process is conducted within a specified range to obtain the optimal values of these hyperparameters. This optimization process aims to obtain the optimal parameter values. Subsequently, the SSA-BiLSTM network model is constructed using these optimal parameter values to predict and analyze wheel wear. Tread wear and flange wear are taken as the research objects, and the measured historical wear data of wheel No.1 of the metro’s carriage # 1 are used as inputs to metro and validate the model, and compare the prediction results with those of MLP, LSTM, BiLSTM and SSA-LSTM models. The results show that the improved bidirectional long short-term memory network model has higher wear prediction accuracy, and the mean absolute percentage error (MAPE) of tread wear is reduced by 13.28%, 10.32%, and 1.47%, and flange wear by 9.5%, 0.46%, and 0.02%, respectively, and the model"s excellent generalization ability was verified by comparing it with the wear data of the first wheel of the same metro trains 2 and 4. The results confirmed that the model exhibits strong generalization capabilities. The wheel wear prediction model with improved BiLSTM network proposed in this paper can effectively improve the prediction accuracy, providing theoretical support for intelligent management of metro wheelsets and extending the wheel"s lifespan.
[中图分类号]
[基金项目]
基于热振融合的轮对轴箱并发故障自适应诊断方法研究