研究基于多传感器信息融合的船舶机械设备状态智能检测方法，智能化诊断船舶机械设备异常状态。采用改进小波阈值去除多振动传感器采集的机械设备振动信号噪声成分后，经基于多传感器信息融合的信号特征提取方法，提取去噪后振动信号幅值的均方根、方差、峰值、脉冲、峭度、均值、最大值、最小值、峰峰值、方根幅值特征，并使用特征级与数据级融合方式，将多信号特征信息融合；通过基于极限学习机优化的设备状态智能检测方法，以特征信息分类的方式，将融合后的设备振动信号特征作为分类目标，根据特征值的上下限，判断设备运行状态。实验验证表明，此方法应用下，多传感器对船舶机械设备振动信号的感知时间差极短，可缩短设备状态检测延迟，并准确检测设备异常状态。
This paper studies the intelligent detection method of ship mechanical equipment state based on multi-sensor information fusion, and intelligently diagnoses the abnormal state of ship mechanical equipment. After removing the noise components of mechanical equipment vibration signals collected by multiple vibration sensors by using improved wavelet threshold, the root mean square, variance, peak value, pulse, kurtosis, mean value, maximum value, minimum value, peak to peak value and root square amplitude characteristics of vibration signal amplitude after noise removal are extracted by using the signal feature extraction method based on multi-sensor information fusion, and the feature level and data level fusion method is used to fuse the multi signal feature information. Through the intelligent detection method of equipment state based on the optimization of limit learning machine, the fused equipment vibration signal features are used as the classification target in the way of feature information classification, and the equipment operation state is judged according to the upper and lower limits of the eigenvalue. Experimental verification: under the application of this method, the perception time difference of multi-sensor to the vibration signal of ship mechanical equipment is extremely short, which can shorten the delay of equipment status detection and accurately detect the abnormal status of equipment.
2022,44(23): 173-176 收稿日期：2022-09-04
DOI：10.3404/j.issn.1672-7649.2022.23.036
分类号：TH165
基金项目：河南省教育厅科技项目（21B460022）；2022年度河南省高等学校重点科研项目（22A880027）
作者简介：刘艳宾(1983-)，男，实验师，研究方向为智能制造及机械工程
参考文献：
[1] 田慧, 林叶锦, 张均东. 基于单分类算法OSVM船用燃气轮机状态评估[J]. 船舶工程, 2020, 42(7):152-156
[2] 郑露. 海上平台起重机状态监测系统设计[J]. 船海工程, 2019, 48(1):130-133
[3] 王瑞涵, 陈辉, 管聪. 基于机器学习的船舶机舱设备状态监测方法[J]. 中国舰船研究, 2021, 16(1):158-167
WANG Runhan, CHEN Hui, GUAN Cong. Condition monitoring method for marine engine room equipment based on machine learning[J]. Chinese Journal of Ship Research, 2021, 16(1):158-167
[4] 叶永伟, 程毅飞, 赖剑人, 等. 基于改进关联规则的卸船机故障预测模型[J]. 中国机械工程, 2019, 30(20):2463-2472
[5] 张春林, 程文. 船舶行业设备维修智能管理平台应用实践[J]. 船海工程, 2020, 49(4):42-45+49
[6] 骆撷冬, 马栋梁, 张松林, 等. 基于门控循环单元神经网络的箱型梁结构裂纹损伤检测方法[J]. 中国舰船研究, 2022, 17(4):194-203
LUO Xiedong, MA Dongliang, ZHANG Songlin, et al. GRU neural network-based method for box girder crack damage detection[J]. Chinese Journal of Ship Research, 2022, 17(4):194-203
