摘要
针对现有船舶柴油机进排气系统监测技术存在的测点布置受限、模型精度不高等问题,提出一种基于多维参数感知矩阵和知识融合的健康监测工艺。该工艺通过构建多源异构数据采集网络采集多源异构数据,并利用卡尔曼滤波算法实现数据融合与噪声抑制;采用小波分解和奇异值分解方法解耦异常信号特征谱;引入状态检修模型和预测性维护策略优化全生命周期维护方案。实验结果表明,该工艺在故障诊断准确率、特征提取精度等方面均优于传统方法,为船舶柴油机进排气系统健康管理提供了技术支持。
Aiming at the problems such as limited measurement point layout and low model accuracy existing in the current monitoring technology of the intake and exhaust system of marine diesel engines,a health monitoring process based on multidimensional parameter perception matrix and knowledge fusion is proposed.This process collects multi-source heterogeneous data by constructing a multi-source heterogeneous data acquisition network and uses the Kalman filtering algorithm to achieve data fusion and noise suppression.The characteristic spectra of abnormal signals are decoupled by using wavelet decomposition and singular value decomposition methods.The condition-based maintenance model and predictive maintenance strategy are introduced to optimize the whole life cycle maintenance scheme.The experimental results show that this process is superior to the traditional methods in terms of the accuracy of fault diagnosis and the precision of feature extraction,providing technical support for the health management of the intake and exhaust systems of marine diesel engines.
作者
赵永超
曲志林
杨军
ZHAO Yongchao;QU Zhilin;YANG Jun(Weichai Heavy Machinery Co.,Ltd.,Weifang 261108;Weichai Power Co.,Ltd.,Weifang 261001)
出处
《现代制造技术与装备》
2025年第8期111-114,共4页
Modern Manufacturing Technology and Equipment
关键词
船舶柴油机
进排气系统
健康监测
marine diesel engine
intake and exhaust system
health monitoring
