设计舰船机械状态监测特征参数选取系统，提升舰船机械状态监测结果。系统通过数据采集终端内的传感器采集舰船电机的振动信号，经模数转换芯片转换该模拟信号为数字信号后输入数据采集卡，利用信号调理箱过滤数据采集卡传输数据过程中的电路谐波并转换电平，光纤通信模块通过CAD总线接收来自数据采集终端的舰船机械状态监测信息并将其输送至协议解析层，在该层解析、封装信息后输送至业务逻辑层，特征参数选取模块通过结合时序分析与主成分分析法的动态主成分分析法，提取数据处理后舰船机械状态监测信息的主成分，获取其特征参数，数据管理模块与数据库负责对舰船机械状态监测特征参数进行管理和存储，通过上位机实现与用户的交互。实验结果表明：该系统可精准采集舰船机械状态监测信息，具有较为优异的谐波过滤效果；可精准选取舰船电机中断、超速2种运行状态下的振动信号，可通过差异图形较好呈现舰船机械设备的电路电平变化情况。
The characteristic parameter selection system of ship mechanical condition monitoring is designed to improve the results of ship mechanical condition monitoring. The system collects the vibration signal of the ship motor through the sensor in the data acquisition terminal, converts the analog signal into digital signal through the analog-to-digital conversion chip, and then inputs it into the data acquisition card. The signal conditioning box is used to filter the circuit harmonics in the data transmission process of the data acquisition card and convert the level. The optical fiber communication module receives the ship mechanical condition monitoring information from the data acquisition terminal through the CAD bus and transmits it to the protocol analysis layer. After analyzing and encapsulating the information in this layer, it is transmitted to the business logic layer. The characteristic parameter selection module extracts the principal components of the ship mechanical condition monitoring information after data processing by combining the dynamic principal component analysis method of time series analysis and principal component analysis, and obtains its characteristic parameters. The data management module and database are responsible for managing and storing the characteristic parameters of ship mechanical condition monitoring, and realizes the interaction with users through the upper computer. The experimental results show that the system can accurately collect the monitoring information of ship mechanical condition, and has excellent harmonic filtering effect. It can accurately select the vibration signals under the two operating states of Ship Motor interruption and overspeed, and better present the circuit level change of ship mechanical equipment through difference graphics.
2022,44(12): 104-107 收稿日期：2022-01-17
DOI：10.3404/j.issn.1672-7649.2022.12.020
分类号：TH165.3
基金项目：浙江大学访问学者项目 (FX2018140)
作者简介：庄敏(1972-)，男，副教授，主要从事智能装备技术及算法等研究
参考文献：
[1] 李楠, 杨阳. 未知参数的舰船辐射噪声线谱Duffing振子检测方法[J]. 船舶力学, 2020, 24(2): 261–270
[2] 谭佳明, 陈玲玲, 蒋佳成, 等. 交流中压真空断路器机械特性在线监测装置的研制[J]. 高压电器, 2020, 56(7): 69–76
[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
[4] 吴金利, 马宏忠, 吴书煜, 等. 基于振动信号的高压并联电抗器故障诊断方法与监测系统研制[J]. 电测与仪表, 2020, 57(1): 113–120
[5] 刘军, 杨治田, 李旭, 等. 基于稳态特征的输电设备全维度状态监测系统[J]. 电网与清洁能源, 2020, 36(7): 24–29
[6] 程俭达, 刘炎, 李天匀, 等. 强化学习模式下舰船多状态退化系统的维修策略[J]. 中国舰船研究, 2021, 16(6): 45–51
[7] 穆锦标, 穆继亮, 邹杰, 等. 低功耗自供电机械设备状态监测系统设计[J]. 中北大学学报(自然科学版), 2021, 42(4): 355–360
[8] 潘志城, 张晋寅, 周海滨, 等. 基于振动信号时频域特征的换流变真空有载分接开关机械状态检测[J]. 高压电器, 2020, 56(6): 232–237
[9] 程林, 徐惠, 刘宇飞, 等. 基于电机输出功率的水平伸缩式隔离开关机械状态检测[J]. 电测与仪表, 2020, 57(11): 9–15
