摘要
为提高断路器寿命预测效率并制定合理的维修方案,基于断路器非周期振动信号可以充分表征剩余寿命的特性,提出一种基于冠豪猪优化算法(CPO)的改进特征模态分解-双向时间卷积网络-双向门控循环单元-注意力机制(IFMD-BiTCN-BiGRU-AT)预测模型。首先通过融合适应度函数和新周期估计方法改进特征模态分解法,弥补其处理非周期信号能力差的缺陷,并利用CPO实现IFMD自适应分解。其次,引入双向并行结构及注意力机制,构建BiTCN-BiGRU-AT预测模型来充分提取时间-空间重要特征,同时利用CPO搜索最优超参组合。最后,搭建断路器信号采集处理实验平台进行实验验证,用该方法进行预测并设计消融实验及多模型对比实验。最终,该方法得到的拟合度、平均绝对误差(MAE)、均方根误差(RMSE)指标分别为99.28%、80.33、98.17。相较于其他3种信号处理方法,经IFMD处理后,预测拟合度平均提高19.7%,且有最高的预测效率;相较于其他模型,该模型的预测拟合度平均提高18.3%,MAE、RMSE平均降低60.9%、61.6%。实验结果表明了该方法的有效性与性能优势。
In order to improve the efficiency of circuit breaker life prediction and formulate a reasonable maintenance plan,an IFMDBiTCN-BiGRU-AT prediction model based on crown porcupine optimization algorithm(CPO)is proposed based on the characteristics that the non-periodic vibration signal of the circuit breaker can fully characterize the residual life.Firstly,the feature mode decomposition method is improved by integrating the fitness function and the new period estimation method to make up for its poor ability to deal with non-periodic signals,and the IFMD adaptive decomposition is realized by using CPO.Secondly,a two-way parallel structure and attention mechanism are introduced.The BiTCN-BiGRU-AT prediction model is constructed to fully extract the important features of time-space,and the CPO is used to search the optimal hyperparameter combination.Finally,the experimental platform of circuit breaker signal acquisition and processing is built for experimental verification.The method is used to predict and design ablation experiments and multi-model comparison experiments.Finally,the fitting degree,MAE and RMSE indexes obtained by this method are 99.28%,80.33 and 98.17 respectively.Compared with the other three signal processing methods,the prediction fitting degree is increased by 19.7%on average after IFMD processing,and the prediction efficiency is the highest.Compared with other models,the prediction fitting degree of the model is increased by 18.3%on average,and the MAE and RMSE are reduced by 60.9%and 61.6%on average.Experimental results show the effectiveness and performance advantages of the proposed method.
作者
李斌
王幸之
王志鹏
Li Bin;Wang Xingzhi;Wang Zhipeng(Faculty of Electrical and Control Engineering,Liaoning Technical University,Huludao 125105,China)
出处
《电子测量与仪器学报》
北大核心
2025年第10期255-268,共14页
Journal of Electronic Measurement and Instrumentation
基金
国家自然科学基金(5167158)
2024年辽宁省教育厅基本科研项目(LJ232410147055)资助。
关键词
改进特征模态分解
冠豪猪优化算法
双向时间卷积网络
双向门控循环单元
剩余寿命预测
improve feature mode decomposition
crested porcupine optimizer algorithm
bidirectional time convolutional network
bidirectional gate controlled loop unit
residual life
