共查询到19条相似文献,搜索用时 573 毫秒
1.
针对传统的神经网络在机械故障诊断方面的不足,利用偏差神经元改进了基于BP神经网络算法的内回归神经网络(IRN)算法,加快收敛速度,提高运算质量,并将其应用于旋转机械的振动故障诊断与识别。实例结果表明:该算法学习收敛较快,误差曲线平稳,对复合故障的识别性能好。图6表3参4 相似文献
2.
3.
4.
遗传神经网络在凝汽器系统故障诊断中的应用 总被引:4,自引:0,他引:4
针对BP神经网络学习收敛速度慢和易陷入局部极小值的不足,将遗传算法与神经网络相结合,提出了一种故障诊断的新方法——遗传神经网络优化故障诊断算法,并将其应用于凝汽器系统故障诊断中。经实例验证,该方法有效地提高了故障诊断的精度和速度。 相似文献
5.
提出了一种以振动信号小波包特征熵为特征向量的高压断路器机械故障诊断的智能算法,该算法利用小波包分解原理将高压断路器振动信号分解到不同的频段中,计算各频段的能量熵值,并将其作为神经网络的输入向量,同时利用粒子群算法对神经网络进行优化,以提高故障诊断的精度。试验结果表明:该方法不仅能够取得良好的分类效果,而且诊断速度与精度均高于传统神经网络算法,适用于高压断路器机械故障诊断 相似文献
6.
基于蚁群算法的神经网络在发动机故障诊断中的应用研究 总被引:2,自引:0,他引:2
BP算法在神经网络中应用较为广泛,但有收敛速度慢、易于陷入局部极小点的缺点。而蚁群算法是一种新型的模拟进化算法,有正反馈、分布式计算、全局收敛、启发式学习等特点。将蚁群算法和神经网络结合起来,应用于发动机故障诊断中,可以提高运算效率,具有广阔的应用前景。 相似文献
7.
针对变压器故障诊断中传统BP神经网络算法准确率低、收敛速度慢、易陷入局部极小值及对初始参数较为敏感等的不足,提出一种基于蝗虫优化(GOA)算法的BP神经网络故障诊断方法。建立以变压器故障特征气体为输入、故障类别为输出的故障诊断模型,利用GOA高效的计算性能和优良的全局搜索能力对BP神经网络的权值和阈值进行参数优化。仿真结果表明,GOA优化后的BP神经网络模型相比于传统BP神经网络和基于遗传算法优化的BP神经网络,能够在保留广泛映射能力的前提下,提升网络的学习速度和全局搜索能力,进而缩短训练所需时间,提高故障诊断精度。 相似文献
8.
9.
为了提高旋转机械滚动轴承故障诊断的准确率,提出一种基于变分模态分解(VMD)和缩放变异粒子群算法(SVPSO)优化BP神经网络的旋转机械滚动轴承故障诊断方法。通过在标准粒子群算法中加入缩放因子以及粒子变异操作提升其局部与全局寻优性能,得到一个改进的粒子群算法——缩放变异粒子群算法(SVPSO),再利用该算法优化BP网络的权值与阈值,提高BP神经网络的故障诊断精度;进一步,为了减少输入特征向量对BP神经网络分类性能的影响,采用VMD分解轴承振动信号,并计算其IMF分量时频熵的方法构建信号特征向量。通过与其他采用相同基准轴承数据集的诊断方法作对比,所提方法的故障诊断精度和算法稳定性均得到有效提升。 相似文献
10.
根据旋转机械复杂的故障特点,提出了结合谐小波分析、模糊理论和神经网络形成的谐小波模糊神经网络方法,并将其应用于旋转机械的故障诊断,实现了模糊故障诊断。通过计算机实现了全部算法。仿真和试验的结果表明:谐小波模糊神经网络在处理多故障耦合的情况时优势明显,故障诊断正确率高,证明该方法行之有效,为旋转机械的故障诊断提供了理论支持和新方法。图2表3参7 相似文献
11.
总结了数据挖掘技术在燃煤锅炉故障诊断、燃烧优化、污染物减排及机组优化运行等方面的应用现状,分析了关联规则、聚类分析、神经网络和支持向量机等数据挖掘算法在锅炉优化运行和污染物排放控制中的优缺点。分析表明:人工神经网络鲁棒性强、可自学习且适用面广,未来可基于焚烧机理并耦合其他算法进行工程应用;对于在高控制要求下智能化工况优化空间大的垃圾焚烧锅炉中的发展及应用,建议将数据挖掘技术与云计算平台结合,并考虑垃圾焚烧过程的实际工况和特性进一步开发数据预处理方法,扩大动态数据采集范围,提高模型的实际运行效率和泛化能力。 相似文献
12.
13.
柴油机排气氧化催化转化器故障诊断方案道路工况仿真分析 总被引:1,自引:0,他引:1
柴油机排气氧化催化转化器(DOC)的在线故障诊断是柴油车OBD系统的重要内容之一.本文根据DOC在线故障诊断技术研究的需要,对以DOC前后的排气温度和排气背压作为DOC催化剂老化、载体堵塞以及破损等失效故障诊断参数的在线故障诊断方案进行了道路工况下的仿真分析.研究结果表明,在一定的柴油车运行道路工况下,以DOC前后的排... 相似文献
14.
我国新疆、甘肃、宁夏、内蒙、浙江、黑龙江、江苏、广东等都在大规模建设风电场,这些风电场建成后,其故障维护就有了很大市场.以新疆风电场为基础,尝试开发用于风力机故障智能诊断的系统.首先介绍了风力机及其变频器系统的结构,分析了变频器的故障机理.使用SOM神经网络对风机变流器进行了诊断,用数据验证了诊断结果.把传统的电力电子设备故障诊断技术与新疆风力机变频器的故障诊断相结合,为风电大面积推广应用产生了积极作用. 相似文献
15.
机组的振动水平是表征电厂稳定安全最重要的标志之一.本文利用支持向量机的智能方法对机组的轴系故障进行诊断,在小样本集上取得了100%的分类精度.在此基础上,还引入部分噪声数据,统计其分类性能,展示了支持向量机的容错能力.最后分析了支持向量机方法在轴系振动故障振动的优势和缺陷,引入模糊输出支持向量机进行了改进,给设备维修提供了更多的参考信息. 相似文献
16.
In Seop Lim Jin Young Park Eun Jung Choi Min Soo Kim 《International Journal of Hydrogen Energy》2021,46(2):2543-2554
The temperature of a fuel cell has a considerable impact on the saturation of a membrane, electrochemical reaction speed, and durability. So thermal management is considered one of the critical issues in polymer electrolyte membrane fuel cells. Therefore, the reliability of the thermal management system is also crucial for the performance and durability of a fuel cell system. In this work, a methodology for component-level fault diagnosis of polymer electrolyte membrane fuel cell thermal management system for various current densities is proposed. Specifically, this study suggests fault diagnosis using limited data, based on an experimental approach. Normal and five component-level fault states are diagnosed with a support vector machine model using temperature, pressure, and fan control signal data. The effects of training data at different operating current densities on fault diagnosis are analyzed. The effects of data preprocessing method are investigated, and the cause of misdiagnosis is analyzed. On this basis, diagnosis results show that the proposed methodology can realize efficient component-level fault diagnosis using limited data. The diagnosis accuracy is over 92% when the residual basis scaling method is used, and data at the highest operating current density is used to train the support vector machine. 相似文献
17.
在线实时故障诊断具有直接实时准确等优点但电控柴油机的特点使得传统故障诊断方法已不能满足在线实时故障诊断的要求本文在分析各种故障诊断方法的基础上得出神经网络是电控柴油机在线实时故障诊断的一条新的途径并阐述了神经网络进行故障诊断的机会 相似文献
18.
《International Journal of Hydrogen Energy》2022,47(20):10976-10989
The performance of proton exchange Membrane fuel cell (PEMFC) fault diagnosis system plays an important role in normal operation of PEMFC. Therefore, a new fault diagnosis algorithm based on binary matrix encoding neural network called BinE-CNN is proposed. In BinE-CNN, high-dimensional features are extracted through binary encoding, and the feature maps are transferred to a convolutional neural network (CNN) to realize seven-category fault classification. For development of BinE-CNN, a PEMFC model is modeled to generate simulative datasets. Simulative test precision and Frames per second (FPS) of BinE-CNN have reached respectively 0.973 and 999.8 (better than support vector machines (SVM), long short-term memory neural network (LSTM), etc.). In experimental verification section, fault datasets are collected during bench test. After that, BinE-CNN is deployed on vehicle control unit (VCU) to verify its engineering value (real-time and precision). The result meet both requirements, with time cost of 96.15 ms and precision of 0.931. 相似文献
19.
Fault diagnosis of low-speed rolling bearing based on weighted reconstruction of vibration envelopes
The main bearing supports the rotation of the main shaft of a wind turbine. It bears heavy dead weights as well as variable speed dynamic loading during operations; thus, it is a vulnerable part in a wind turbine drive train. Because of the low speed and time-varying operations of the main bearing, vibrations generated by bearing faults are often weak in response amplitudes, low in frequency range, and smeared in damage feature energy. As a result, the applicability of the conventional acceleration envelope analysis (AEA) technique, a traditionally effective technology for bearing fault diagnosis, is limited in such cases. In order to resolve this, a modified AEA method specially designed for bearings with low and variable speed operation is proposed in this paper. First, the structural response is decomposed by means of variational mode decomposition (VMD) for the low frequency components to form a series of band-limited intrinsic mode functions (BLIMFs). Next, weighting factors are determined for the BLIMFs by defined energy ratios. Finally, a new envelope is reconstructed by weighting the envelopes of each BLIMF for bearing fault diagnosis. The effectiveness and practicality of the proposed method for the diagnosis of main bearing faults in wind turbines is verified through the analysis of measured data from a wind turbine in the field. The proposed method provides an effective way for bearing fault diagnosis at low and variable rotational speeds. 相似文献