共查询到20条相似文献,搜索用时 718 毫秒
1.
针对舰船轮机设备故障信号监测中存在的运算量大、缺少故障数据、模型训练复杂、检测效率低、准确度不高等问题,设计了基于机器学习的舰船轮机设备多发故障信号监测方法。通过多种传感器采集舰船轮机设备振动信号,经小波变换降噪后,通过EMD经验模态分解提取舰船轮机设备振动信号特征,将其作为孤立森林算法输入进行异常信号检测,以异常信号检测结果为依据,构建决策二叉树支持向量机故障信号分类模型识别故障信号,实现舰船轮机设备多发故障信号监测,实验表明,该方法可以高效、准确地检测并识别舰船轮机设备的故障信号,而且适应性广泛,在舰船轮机设备的各种工况下,监测性能都十分良好。 相似文献
2.
3.
4.
传统舰船发动机故障诊断方法诊断时,需要对舰船发动机进行一定程度上的拆卸,无法完成零拆卸的故障检测,为此提出基于振动信号的舰船发动机故障诊断方法。使用不同波段振动信号作为检测探伤手段,采集多频段的振动信号,分析信号携带的诊断信息,完成舰船发动机故障诊断模型构建;计算振动信号非线性鲁棒值,锁定故障位置,通过编程分析,实现舰船发动机故障诊断。试验结果表明,设计的故障诊断方法比传统方法诊断定位准确率高2%,说明设计的诊断方法具备极高的有效性。 相似文献
5.
发动机振动信号分析是判断发动机状态的重要因素,传统方法忽略对发动机振动信号的处理,导致舰船发动机状态分析时间较长,为此设计一种基于人工智能技术的舰船发动机状态分析方法。采集舰船发动机的振动信号,采用时域分析法对振动信号处理,获得发动机振动信号特征中不同信号和不同时刻的相互依赖关系,依据人工智能技术确定振动信号的鲁棒值,从而确认舰船发动机异常情况,以此完成舰船发动机状态分析。在舰船发动机无故障情况下和有故障情况下进行了发动机状态分析的实验。结果证明,在无故障情况下和有故障情况下,本文设计方法对发动机状态的分析时间均比传统2种分析方法的分析时间短,证明此次设计的基于人工智能技术的舰船发动机状态分析方法分析效果好。 相似文献
6.
7.
8.
9.
中压发电机组是舰船的动力核心,中压发电机组在使用较长时间之后可能会出现振动异常的问题,通过对其进行振动检测,能够确定振动异常的位置和原因,并通过针对性的措施来解决问题,维护中压发电机的正常运行。本文以某舰船的中压发电机组故障问题为例,对中压发电机组振动监测与故障诊断进行了详细的分析。 相似文献
10.
舰船机械部件是一个非线性系统,舰船机械部件出现故障概率相当高,当前故障预测方法无法描述舰船机械部件故障的不确性,因此舰船机械部件故障预测精度低,为了提高舰船机械部件故障预测精度,克服当前舰船机械部件故障预测方法的缺陷,设计了一种舰船维护中机械潜在故障智能预测方法。首先提取描述舰船机械部件故障类别的特征信息,然后采用BP神经网络对舰船机械部件故障特征信息进行学习,确定相对应的舰船机械部件故障类别,并解决BP神经网络参数确定问题,最后与其他方法进行了对比实验。结果表明,本文方法的舰船机械部件故障预测精度超过95%,远远高于对比方法的舰船机械部件故障预测精度,改善了舰船机械部件故障诊断速度,具有十分广泛的应用前景。 相似文献
11.
12.
13.
14.
Adaptive neuro-fuzzy inference system (ANFIS) was applied to predict the risk of near-miss incidents during tanker shipping voyages. Firstly, near-miss incidents recorded by a global tanker shipping management company were analysed. Four variables—type of operation, vessel’s location, on-board position, and harm potential were selected to train and predict the risk levels of near-miss incidents. The selected variables were found to be correlated with the observed frequency at three risk levels, namely low, medium and high. Gravity factor (GF) was calculated using the frequency of the categories in each variable and their associated risk levels. The calculated GF values and the risk levels of near-miss incidents were used as input values in the ANFIS model. Triangular, Trapezoidal and Gaussian membership functions were used. Subsequently, fuzzy logical theory and artificial neural networks were applied to train the data. Causal factors in terms of direct contributory factors, indirect contributory factors and root contributory factors to the near-miss incidents were analysed. Risk control measures were also proposed to improve safety during tanker shipping. 相似文献
15.
W. Jacobs C. Reynaerts S. Andries S. van den Akker N. Moonen D. Lamoen 《Journal of Marine Science and Technology》2016,21(4):758-766
In a previous study, it was found that cargo tank operations like cleaning and venting, lead to higher cargo vapor concentrations around the ship’s superstructure. Can wind tunnel experiments confirm these findings? Is there an improvement when using higher outlets at high velocities compared to lower outlets with a low outlet velocity? Is there a relation between relative wind speed and measured concentration? These questions were investigated in the Peutz wind tunnel. By using a tracer gas for the wind tunnel experiments, concentration coefficients have been calculated for various settings. The study shows that using high-velocity outlets is an efficient way to keep concentrations as low as possible. The only exception is for relative wind directions from the bow. In this last case using a manhole as ventilation outlet leads to lower concentrations. With increasing wind speeds the building downwash effect resulted in higher concentration coefficients near the main deck. This study confirms our on-board measurements and suggests the lowering of the ventilation inlet of the accommodation, so that the high-velocity outlet can be used safely at all times. 相似文献
16.
机械噪声信号和振动信号一样,蕴含了机械设备运行状态的重要信息,当设备状态发生改变时,其声学特性同样会发生改变。但是,待识别的目标信号和其它设备的信号以及噪声信号混杂在一起,一般很难直接从测量的声信号中获得有用的信息。因此,排除或抑制干扰信号或背景噪声,准确地从低信噪比的混合信号中提取出待识别的目标信号,对声学监测与诊断方法十分关键,而盲信号处理技术为机械声学信号的分离提供了一个有力的解决手段。该文对盲信号技术在机械装置声学监测与诊断中的研究现状进行了概述,为盲信号进一步应用于机械中的声学分析打下基础。 相似文献
17.
Human error is the most important factor causing many ship accidents in maritime industry despite advanced technology and international regulations. Fatigue in seafarers is a well-known problem and a serious cause of ship accidents. There are many factors unique to the marine environment raising the potential for fatigue at sea. Due to the difficulties in measuring human fatigue and also in suggesting fatigue to be a root cause of accident, it is important to devise methods to detect and quantify the fatigue and mental symptoms. In this study, ‘Piper Fatigue Scale’ (PFS) has been used for measuring fatigue level and ‘Symptom Checklist 90- Revised’ (SCL-90-R) for detecting the severity of mental symptoms. Data analyses were performed using the SPSS (Statistical Package for the Social Sciences) software. According to the results of PFS analysis, a slight degree of fatigue is detected in all sub-dimensions of the scale. According to the results of SCL-90-R analysis, the distress of mental symptoms perceived by seafarers is not generally highly detected. In conclusion, the purpose of this study is to determine, by using subjective measurements, the fatigue level and mental symptoms among seafarers caused by working conditions on-board. 相似文献
18.
19.