期刊文献+
共找到1,832篇文章
< 1 2 92 >
每页显示 20 50 100
Application of extension method to fault diagnosis of transformer 被引量:4
1
作者 邓宏贵 曹建 +1 位作者 罗安 夏向阳 《Journal of Central South University of Technology》 EI 2007年第1期88-93,共6页
A novel extension diagnosis method was proposed for enhancing the diagnosis ability of the conventional dissolved gas analysis. Based on the extension theory a matter-element model was established for qualitatively an... A novel extension diagnosis method was proposed for enhancing the diagnosis ability of the conventional dissolved gas analysis. Based on the extension theory a matter-element model was established for qualitatively and quantitatively describing the fault diagnosis problem of power transformers. The degree of relation based on the dependent functions was employed to determine the nature and the grade of the faults in a transformer system. And the proposed method was verified with the experimental data. The results show that accuracy rate of the diagnosis method exceeds 90% and two kinds of faults can be detected at the same time. 展开更多
关键词 power transformer fault diagnosis extension theory matter-element model dependent function
在线阅读 下载PDF
Application of local wave ti me-frequency method in reciprocating mechanical fault diagnosis
2
作者 Wang Lei Wang Fengtao Ma Xiaojiang 《仪器仪表学报》 EI CAS CSCD 北大核心 2006年第z1期380-381,共2页
To diagnosethe reciprocating mechanical fault.We utilizedlocal waveti me-frequency approach.Firstly,we gave the principle.Secondly,the application of local wave ti me-frequency was given.Finally,we discusseditsvirtue ... To diagnosethe reciprocating mechanical fault.We utilizedlocal waveti me-frequency approach.Firstly,we gave the principle.Secondly,the application of local wave ti me-frequency was given.Finally,we discusseditsvirtue in reciprocating mechanical fault diagnosis. 展开更多
关键词 LOCAL WAVE method TIME-FREQUENCY analysis fault diagnosis
在线阅读 下载PDF
Novel robust fault diagnosis method for flight control systems 被引量:11
3
作者 Guo Yuying Jiang Bin +1 位作者 Zhang Youmin Wang dianfei 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2008年第5期1017-1023,共7页
A novel robust fault diagnosis scheme, which possesses fault estimate capability as well as fault diagnosis property, is proposed. The scheme is developed based on a suitable combination of the adaptive multiple model... A novel robust fault diagnosis scheme, which possesses fault estimate capability as well as fault diagnosis property, is proposed. The scheme is developed based on a suitable combination of the adaptive multiple model (AMM) and unknown input observer (UIO). The main idea of the proposed scheme stems from the fact that the actuator Lock-in-Place fault is unknown (when and where the actuator gets locked are unknown), and multiple models are used to describe different fault scenarios, then a bank of unknown input observers are designed to implement the disturbance de-coupling. According to Lyapunov theory, proof of the robustness of the newly developed scheme in the presence of faults and disturbances is derived. Numerical simulation results on an aircraft example show satisfactory performance of the proposed algorithm. 展开更多
关键词 fault diagnosis adaptive multiple model unknown input observer flight control.
在线阅读 下载PDF
The Research of the Equation Model on the System-level Fault Diagnosis 被引量:5
4
作者 Hengnong Xuan1, Dafang Zhang2, Yue Wu3, Minwei He4 (1,4: Dept. of Computer, Wuyi University, Jiangmen, Guangdong, 529020, China (2: Dept. of Computer, Hunan University, Changsha, 410082, China ) (3: Institute of Computer Science and Engineering, Univers 《湖南大学学报(自然科学版)》 EI CAS CSCD 2000年第S2期148-157,共10页
In this paper we propose an equation model of system-level fault diagnoses, and construct corresponding theory and algorithms. People can turn any PMC model on ex-test into an equivalent equation (or a system of equat... In this paper we propose an equation model of system-level fault diagnoses, and construct corresponding theory and algorithms. People can turn any PMC model on ex-test into an equivalent equation (or a system of equations), and find all consistent fault patterns based on the equation model. We can also find all fault patterns, in which the fault node numbers are less than or equal to t without supposing t-diagnosable. It is not impossible for all graphic models. 展开更多
关键词 PMC MODEL EQUATION MODEL ex-test system-level fault diagnosis DIAGNOSTIC algorithm
在线阅读 下载PDF
A Neural-based L1-Norm Optimization Approach for Fault Diagnosis of Nonlinear Resistive Circuits 被引量:2
5
作者 Yigang He School of Electrical & Information Engineering, Hunan Univ,Changsha 410082,P.R.China Yichuang Sun Department of Electronic,Communication & electrical Engineering,Faculty of Engineering and Information Sciences,University of Hertfordshire,Hatfie 《湖南大学学报(自然科学版)》 EI CAS CSCD 2000年第S2期143-147,共5页
This paper deals with fault isolation in nonlinear analog circuits with tolerance under an insufficient number of independent voltage measurements.A neural network-based L1-norm optimization approach is proposed and u... This paper deals with fault isolation in nonlinear analog circuits with tolerance under an insufficient number of independent voltage measurements.A neural network-based L1-norm optimization approach is proposed and utilized in locating the most likely faulty elements in nonlinear circuits.The validity of the proposed method is verified by both extensive computer simulations and practical examples.One simulation example is presented in the paper. 展开更多
关键词 fault diagnosis NEURAL networks Optimization methods NONLINEAR CIRCUITS Anlog CIRCUITS
在线阅读 下载PDF
A Complete Analytic Model for Fault Diagnosis of Power Systems 被引量:33
6
作者 LIU Daobing GU Xueping LI Haipeng 《中国电机工程学报》 EI CSCD 北大核心 2011年第34期I0008-I0008,10,共1页
现代大规模互联电网提高了电力系统运行的稳定性和经济性,同时也给电网的故障诊断增加了难度。对电网保护配置和断路器动作规则进行深入分析,提出一种新的电网故障诊断模型——完全解析模型,并为基于此模型的故障诊断提出一种实用有效... 现代大规模互联电网提高了电力系统运行的稳定性和经济性,同时也给电网的故障诊断增加了难度。对电网保护配置和断路器动作规则进行深入分析,提出一种新的电网故障诊断模型——完全解析模型,并为基于此模型的故障诊断提出一种实用有效的求解方法。在完全解析模型中,故障假说(即可疑故障设备的故障情况)与保护、断路器的动作情况及拒动和误动情况一同表示成逻辑变量,而保护配置和断路器动作规则以逻辑方程组形式进行充分表达,逻辑方程组的每个解析解对应一个故障模式(设备故障状态和保护动作、断路器跳闸状态及拒动/误动情况),是对故障情形的完整解释。本模型对故障诊断规则和保护、断路器的动作逻辑进行完全解析,并完整保留了故障设备、保护动作和断路器跳闸之间的耦合关系,克服了已有解析模型的缺陷。算例表明,保留完整耦合关系的完全解析模型可有效提高故障诊断的准确性和容错能力。 展开更多
关键词 英文摘要 内容介绍 编辑工作 期刊
在线阅读 下载PDF
Static-deformation based fault diagnosis for damping spring of large vibrating screen 被引量:7
7
作者 彭利平 刘初升 +1 位作者 李珺 王宏 《Journal of Central South University》 SCIE EI CAS 2014年第4期1313-1321,共9页
Based on the statics theory, a novel and feasible twice-suspended-mass method(TSMM) was proposed to deal with the seldom-studied issue of fault diagnosis for damping springs of large vibrating screen(LVS). With the st... Based on the statics theory, a novel and feasible twice-suspended-mass method(TSMM) was proposed to deal with the seldom-studied issue of fault diagnosis for damping springs of large vibrating screen(LVS). With the static balance characteristic of the screen body/surface as well as the deformation compatibility relation of springs considered, static model of the screen surface under a certain load was established to calculate compression deformation of each spring. Accuracy of the model was validated by both an experiment based on the suspended mass method and the properties of the 3D deformation space in a numerical simulation. Furthermore, by adopting the Taylor formula and the control variate method, quantitative relationship between the change of damping spring deformation and the change of spring stiffness, defined as the deformation sensitive coefficient(DSC), was derived mathematically, from which principle of the TSMM for spring fault diagnosis is clarified. In the end, an experiment was carried out and results show that the TSMM is applicable for diagnosing the fault of single spring in a LVS. 展开更多
关键词 static deformation suspended mass method large vibrating screen damping spring fault diagnosis
在线阅读 下载PDF
Broken Rotor Bar Fault Diagnosis of Induction Motors Using a Hybrid Bare-bones Particle Swarm Optimization Algorithm 被引量:10
8
作者 WANG Panpan SHI Liping ZHANG Yong HAN Li 《中国电机工程学报》 EI CSCD 北大核心 2012年第30期I0011-I0011,13,共1页
在传统定子电流频谱分析中,感应电机转子断条故障特征经常被基波分量淹没而无法准确检测。针对该问题,提出一种基于混合骨干微粒群优化算法的转子断条故障诊断新方法。该方法首先根据电流信号与单位余弦基函数的内积最大准则,利用混合... 在传统定子电流频谱分析中,感应电机转子断条故障特征经常被基波分量淹没而无法准确检测。针对该问题,提出一种基于混合骨干微粒群优化算法的转子断条故障诊断新方法。该方法首先根据电流信号与单位余弦基函数的内积最大准则,利用混合骨干微粒群算法强大的全局搜索能力,准确估计出基波波形参数;然后利用波形参数构造出基波表达式,并将其从原电流信号中剔除,达到突出故障特征的目的。针对微粒群算法在进化后期收敛缓慢的缺点,通过K–均值聚类方式,引入单纯形法对其进行改进,使整个算法的广度探索与深度开发能力得到了有效均衡。最后,对模拟数据和实测信号进行实验,结果验证了所提方法的有效性和优越性。 展开更多
关键词 转子断条故障 混合粒子群优化算法 故障诊断 异步电动机 感应电机 故障发生
在线阅读 下载PDF
Research and application of hierarchical model for multiple fault diagnosis
9
作者 An Ruoming Jiang Xingwei Song Zhengji 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2005年第4期957-961,共5页
Computational complexity of complex system multiple fault diagnosis is a puzzle at all times. Based on the well known Mozetic's approach, a novel hierarchical model-based diagnosis methodology is put forward for impr... Computational complexity of complex system multiple fault diagnosis is a puzzle at all times. Based on the well known Mozetic's approach, a novel hierarchical model-based diagnosis methodology is put forward for improving efficency of multi-fault recognition and localization. Structural abstraction and weighted fault propagation graphs are combined to build diagnosis model. The graphs have weighted arcs with fault propagation probabilities and propagation strength. For solving the problem of coupled faults, two diagnosis strategies are used: one is the Lagrangian relaxation and the primal heuristic algorithms; another is the method of propagation strength. Finally, an applied example shows the applicability of the approach and experimental results are given to show the superiority of the presented technique. 展开更多
关键词 hierarchical model fault propagation graphs multiple fault diagnosis propagation strength.
在线阅读 下载PDF
Establishment and Optimization of State Feature System of Diesel Engine Fault Diagnosis
10
作者 Liu Min-lin Liu Bo-yun College of Power Engineering,Naval University of Engineering,Wuhan 430033, China 《中国舰船研究》 2010年第3期47-51,共5页
For too many state features are used in the diesel engine state evaluation and fault diagnosis, it is not easy to obtain the rational eigenvalues. In the paper, the cylinder subassembly of diesel engine is used to sea... For too many state features are used in the diesel engine state evaluation and fault diagnosis, it is not easy to obtain the rational eigenvalues. In the paper, the cylinder subassembly of diesel engine is used to search for the method of establishing state feature system and optimal approach. The signal of diesel engine has been collected when the piston ring and airtight ring are working at different states, then with the Bootstrap method and Genetic Algorithm (GA), an optimum parameter combination is received. Example shows this method is simple and efficient for establishing diesel engine state feature system, Thus, this method is valuable for the virtual state evaluation of similar complex system. 展开更多
关键词 diesel engine fault diagnosis bootstrap method genetic algorithm.
在线阅读 下载PDF
Simulation Research of Fault Model of Detecting Rotor Dynamic Eccentricity in Brushless DC Motor Based on Motor Current Signature Analysis 被引量:12
11
作者 赵向阳 葛文韬 《中国电机工程学报》 EI CSCD 北大核心 2011年第36期I0011-I0011,共1页
基于Ansoft/Maxwell设置动态偏心故障,建立求解电机电感和磁链的有限元模型,通过仿真,证明了将感应电机动态偏心故障的特征频率经过简化后,同样适用于无刷直流电动机。基于Ansoft/Simplorer建立无刷直流电动机系统的仿真模型。在... 基于Ansoft/Maxwell设置动态偏心故障,建立求解电机电感和磁链的有限元模型,通过仿真,证明了将感应电机动态偏心故障的特征频率经过简化后,同样适用于无刷直流电动机。基于Ansoft/Simplorer建立无刷直流电动机系统的仿真模型。在电机稳态运行下,对定子电流进行傅里叶分析,研究并建立基于定子电流监测动态偏心故障的仿真模型:动态偏心故障与特征频率的关系、动态偏心故障程度与特征频率幅值的关系。进而研究了无刷直流电动机稳态运行时转速波动对偏心故障监测的影响。仿真结果表明,转子偏心程度加大,特征频率的幅值增加。 展开更多
关键词 电机转子 故障检测 电流特征 偏心 直流 仿真 模型 机械故障
在线阅读 下载PDF
Fault detection and diagnosis for data incomplete industrial systems with new Bayesian network approach 被引量:15
12
作者 Zhengdao Zhang Jinlin Zhu Feng Pan 《Journal of Systems Engineering and Electronics》 SCIE EI CSCD 2013年第3期500-511,共12页
For the fault detection and diagnosis problem in largescale industrial systems, there are two important issues: the missing data samples and the non-Gaussian property of the data. However, most of the existing data-d... For the fault detection and diagnosis problem in largescale industrial systems, there are two important issues: the missing data samples and the non-Gaussian property of the data. However, most of the existing data-driven methods cannot be able to handle both of them. Thus, a new Bayesian network classifier based fault detection and diagnosis method is proposed. At first, a non-imputation method is presented to handle the data incomplete samples, with the property of the proposed Bayesian network classifier, and the missing values can be marginalized in an elegant manner. Furthermore, the Gaussian mixture model is used to approximate the non-Gaussian data with a linear combination of finite Gaussian mixtures, so that the Bayesian network can process the non-Gaussian data in an effective way. Therefore, the entire fault detection and diagnosis method can deal with the high-dimensional incomplete process samples in an efficient and robust way. The diagnosis results are expressed in the manner of probability with the reliability scores. The proposed approach is evaluated with a benchmark problem called the Tennessee Eastman process. The simulation results show the effectiveness and robustness of the proposed method in fault detection and diagnosis for large-scale systems with missing measurements. 展开更多
关键词 fault detection and diagnosis Bayesian network Gaussian mixture model data incomplete non-imputation.
在线阅读 下载PDF
Open-circuit fault diagnosis and fault tolerance for shunt active power filter 被引量:2
13
作者 PENG Tao ZHAO Shuai +1 位作者 DAN Han-bing YU Hua-xiong 《Journal of Central South University》 SCIE EI CAS CSCD 2017年第11期2582-2595,共14页
The open-circuit fault of the power switches in shunt active power filter(SAPF) would exacerbate the harmonic pollution of power grid, and degrade the reliability of the devices and system. A fault diagnosis method is... The open-circuit fault of the power switches in shunt active power filter(SAPF) would exacerbate the harmonic pollution of power grid, and degrade the reliability of the devices and system. A fault diagnosis method is proposed based on reference model and an over-modulation strategy under hardware fault tolerance for SAPF. First, a mathematic model is established for SAPF. Second, the residuals are generated by comparing the outputs of reference model and those of actual model, and open-switch fault is detected and diagnosed by residual evaluation. After that, hardware fault tolerance is performed with the three-phase four-switch(TPFS) topology to isolate the faulty phase. Finally, the over-modulation strategy is proposed to increase the voltage transfer ratio of the TPFS topology. Simulation and experimental results verified the feasibility and effectiveness of the proposed method. 展开更多
关键词 fault diagnosis fault TOLERANT reference model over-modulation THREE-PHASE four-switch TOPOLOGY SHUNT active power filter
在线阅读 下载PDF
基于改进去噪扩散概率模型的风电机组故障样本生成方法 被引量:1
14
作者 孟昱煜 张沣琦 +2 位作者 火久元 常琛 陈峰 《振动与冲击》 北大核心 2025年第4期286-297,共12页
为解决风电机组故障诊断中故障样本不足而导致模型准确率不高的问题,将当下备受关注的数据增强方法-去噪扩散概率模型(denoising diffusion probability model,DDPM)引入到故障诊断领域以生成大量高质量的故障样本数据集。因此,结合Tran... 为解决风电机组故障诊断中故障样本不足而导致模型准确率不高的问题,将当下备受关注的数据增强方法-去噪扩散概率模型(denoising diffusion probability model,DDPM)引入到故障诊断领域以生成大量高质量的故障样本数据集。因此,结合Transformer网络,提出了一种DDPM-Transformer风电机组故障样本生成方法。首先,将用于计算机视觉图像生成领域的DDPM模型应用于风电机组故障诊断领域中,通过前向加噪过程将数据逐渐转化为噪声,再通过逆向去噪过程将噪声逐步恢复为原始数据,实现从噪声中生成故障数据,解决数据不平衡问题;其次,通过对原始DDPM中使用的U-net模块进行改进,使用Transformer模型替换U-net网络,利用扩散后的数据和添加的噪声训练Transformer模型,实现噪声预测,以提高故障数据的生成质量;最后,使用多种生成模型评价指标对生成的故障数据进行评价,在监督控制和数据采集系统(supervisory control and data acquisition,SCADA)故障数据生成中论证改进DDPM-Transformer模型的性能。通过试验证明,所提DDPM-Transformer模型与现有的生成模型相比,最大均值异(maximum mean discrepancy,MMD)最大提升0.13,峰值信噪比(peak signal to noise ratio,PSNR)最大提升7.8。所提模型可以有效地生成质量更高的风电机组故障样本,从而基于该样本集辅助训练基于深度学习的故障诊断模型,可以使诊断模型具有更高精度和良好的稳定性。 展开更多
关键词 DDPM TRANSFORMER 风电机组 故障诊断 样本生成
在线阅读 下载PDF
基于随机森林算法的智能转向系统故障诊断
15
作者 马世典 戴永根 +2 位作者 江浩斌 唐斌 李傲雪 《江苏大学学报(自然科学版)》 北大核心 2025年第5期514-522,共9页
针对现有汽车转向系统故障诊断研究方法泛化性差和故障数据集存在缺陷的问题,提出一种基于随机森林(random forest,RF)算法的智能转向系统故障诊断方法.首先基于Simscape进行智能转向系统物理模型的搭建,与CarSim进行联合仿真,设置多种... 针对现有汽车转向系统故障诊断研究方法泛化性差和故障数据集存在缺陷的问题,提出一种基于随机森林(random forest,RF)算法的智能转向系统故障诊断方法.首先基于Simscape进行智能转向系统物理模型的搭建,与CarSim进行联合仿真,设置多种转向系统关键故障,并采集多种行驶工况下的故障样本来建立数据集.然后建立基于RF的故障诊断模型,对输入数据进行分类,实现智能转向系统的故障诊断,并与典型算法进行对比研究.最后搭建转向系统台架,采集不平衡样本来建立数据集,研究该方法的诊断效果.结果表明:使用RF算法对仿真故障数据集进行故障诊断,故障诊断准确率约为87.43%;试验验证中该方法故障诊断准确率高达99.93%,且具有较快的诊断速度和较好的泛化性能. 展开更多
关键词 智能转向系统 故障诊断 随机森林算法 Simscape物理模型 CarSim联合仿真
在线阅读 下载PDF
考虑保护逻辑约束的电网故障诊断解析模型
16
作者 刘道兵 翁文波 +2 位作者 李世春 张业丽 洪亚伦 《电力系统及其自动化学报》 北大核心 2025年第5期13-20,共8页
为解决故障假说内部变量取值无约束导致模型求解时可能出现多解和误解的问题,提出了考虑保护逻辑约束的电网故障诊断解析模型。首先,通过主保护与后备保护动作逻辑上的配合关系,建立约束条件对故障假说内部变量进行限制,筛选出符合实际... 为解决故障假说内部变量取值无约束导致模型求解时可能出现多解和误解的问题,提出了考虑保护逻辑约束的电网故障诊断解析模型。首先,通过主保护与后备保护动作逻辑上的配合关系,建立约束条件对故障假说内部变量进行限制,筛选出符合实际故障情形的故障假说;其次,引入装置通道异常告警信息,构建故障假说评价函数,对满足约束条件的故障假说进行评价;然后,采用模糊集理论和二进制粒子群优化算法求解,得到满意度最大的故障假说,结合告警信息推算整个故障过程;最后,通过故障算例验证了所提模型的有效性和通用性。 展开更多
关键词 故障诊断 解析模型 约束条件 通道异常告警 粒子群优化算法
在线阅读 下载PDF
气隙偏心对永磁发电机绕组绝缘温度特性影响
17
作者 何玉灵 白怡凡 +4 位作者 张文 李勇 徐明星 王晓龙 唐贵基 《哈尔滨工程大学学报》 北大核心 2025年第5期944-954,共11页
绕组绝缘温度是影响永磁发电机发电效率和运行安全的重要因素,现有研究主要关注正常工况下的损耗-温升特性,对于非正常工况下铁芯-绕组的损耗-热载特性和绝缘温升规律研究亟待深入。本文以一台5kVA永磁发电机为例,对气隙偏心前后的发电... 绕组绝缘温度是影响永磁发电机发电效率和运行安全的重要因素,现有研究主要关注正常工况下的损耗-温升特性,对于非正常工况下铁芯-绕组的损耗-热载特性和绝缘温升规律研究亟待深入。本文以一台5kVA永磁发电机为例,对气隙偏心前后的发电机定子绕组绝缘温度场进行了分析。对发电机气隙偏心前后的气隙磁通密度、定子电流和损耗表达式进行了理论推导;根据传热基本原理,建立了发电机磁-热耦合三维模型,应用有限元仿真得到绕组绝缘温度场结果;通过实验对理论和仿真结果进行验证。结果表明,随着气隙偏心程度的增大,发电机各部分损耗增加,定子铁心及绕组绝缘的温度随之升高。同时基于偏心故障下的定子铁心和绕组绝缘温升特性,提出了一种新型的定子铁心通风结构改善发电机的通风散热,通过对比2种不同结构下的定子温度场,表明该结构明显降低了发电机定子铁心和绕组绝缘温度,为通风结构的设计提供了一定的参考。 展开更多
关键词 永磁发电机 气隙偏心 定子铁心 绕组绝缘 温度场 有限元法 故障诊断 结构优化
在线阅读 下载PDF
谐波微弱信号特征的方差曲线周期识别法
18
作者 薛强 田瑞兰 +1 位作者 李海萍 关淮桐 《振动.测试与诊断》 北大核心 2025年第1期51-56,199,共7页
针对随机因素和微弱信号初相位影响的问题,构造了强噪声背景下检测谐波微弱信号频率、相位的方差曲线周期识别法。首先,基于随机Melnikov函数和系统关于相位分岔图的周期特性,初步提出周期识别法;其次,论证分岔图和方差曲线具有一致性,... 针对随机因素和微弱信号初相位影响的问题,构造了强噪声背景下检测谐波微弱信号频率、相位的方差曲线周期识别法。首先,基于随机Melnikov函数和系统关于相位分岔图的周期特性,初步提出周期识别法;其次,论证分岔图和方差曲线具有一致性,进一步将周期识别法优化为方差曲线周期识别法;然后,基于频谱泄露最小原则,设计自适应离散傅里叶变换数据处理方法来解决由方差曲线不光滑而引起的结果不准确问题;最后,采用二次检测来解决检测系统中策动力信号与被测信号存在频差而导致动力学转迁的不明显问题。仿真结果表明,该方法不受被测信号初相位影响,可识别淹没在强噪声中的微弱信号,被识别信号的信噪比可低达-74.96 dB。列车轴箱轴承故障实验中获得的方差曲线周期现象清晰,也表明了该方法的工程实用性。 展开更多
关键词 轴承 故障诊断 信号处理 DUFFING系统 方差曲线周期法 自适应离散傅里叶变换
在线阅读 下载PDF
基于概率模型与信息熵的局部线性嵌入算法
19
作者 刘远红 毋毓斌 《计算机科学》 北大核心 2025年第S1期643-650,共8页
局部线性嵌入算法采用欧氏距离选择邻域点,这通常会损失数据集本身的非线性特征,造成邻域点选取错误,且仅使用欧氏距离构造权重会导致信息挖掘不充分。针对以上问题,提出基于概率模型与信息熵的局部线性嵌入算法(Probability informatio... 局部线性嵌入算法采用欧氏距离选择邻域点,这通常会损失数据集本身的非线性特征,造成邻域点选取错误,且仅使用欧氏距离构造权重会导致信息挖掘不充分。针对以上问题,提出基于概率模型与信息熵的局部线性嵌入算法(Probability information entropy-LLE,PIE-LLE)。首先,为了使邻域点选择更加合理,从数据集的概率分布角度出发,考虑样本点及其邻域的概率分布,为样本点构造符合局部分布的邻域集合。其次,为了充分提取样本的局部结构信息,在权重构造阶段,分别计算样本所属邻域概率以及每个样本的信息熵,融合二者信息重构低维样本。最后,在两个轴承故障数据集上的实验表明,所提方法故障识别准确度最高达到了100%,高于其他对比算法;在邻域点个数5~15范围内,PIE-LLE算法展现出良好的低维可视化效果;在参数敏感性实验中,该算法可以保持Fisher指标较大,有效提高了算法的分类准确度和稳定性。 展开更多
关键词 局部线性嵌入算法 概率模型 信息熵 特征提取 故障诊断
在线阅读 下载PDF
基于电流变化率增量的悬浮电磁铁故障诊断
20
作者 蒋启龙 姚卫丰 张晔 《西南交通大学学报》 北大核心 2025年第4期1042-1049,共8页
为提高复杂工况下悬浮电磁铁线圈故障诊断的准确性,基于故障前、后电流特性变化,考虑温度、加减载、气隙扰动等因素的影响,提出一种基于周期内电流变化率增量的电磁铁线圈故障诊断方法.通过建立两电平控制下电磁铁线圈输出电流变化率增... 为提高复杂工况下悬浮电磁铁线圈故障诊断的准确性,基于故障前、后电流特性变化,考虑温度、加减载、气隙扰动等因素的影响,提出一种基于周期内电流变化率增量的电磁铁线圈故障诊断方法.通过建立两电平控制下电磁铁线圈输出电流变化率增量的数学模型,分析得到电流变化特性,明确电磁铁线圈匝间短路是电流变化率增量异常的本质因素,即可通过检测电流变化率增量变化来作为故障判断条件;针对间隙变化导致电流变化率增量改变触发误诊断的问题,采用最小二乘法求解实际间隙与正常状态下电量变化率增量的关系式,建立查找表,从而根据间隙变化来实时调整电流变化率增量阈值.经过仿真和实验验证:该算法适用于磁浮列车的各种工况,鲁棒性强;在线圈短路比5%时,故障诊断准确率高达97%,灵敏度高;能够在一个基波周期内完成故障诊断,诊断速度快. 展开更多
关键词 磁浮列车 悬浮电磁铁 电流变化率增量 故障诊断 最小二乘法
在线阅读 下载PDF
上一页 1 2 92 下一页 到第
使用帮助 返回顶部