检索结果-内蒙古大学图书馆

Research on Intelligent Diagnosis of Wear Faults of Centrifugal Pumps Based on Stacked Autoencoder 3

Research on Intelligent Diagnosis of Wear Faults of Centrifu...

3rd International Conference on Sensing, Measurement and Data Analytics in the Era of Artificial Intelligence, ICSMD 2022

作者： Xiang, Mingsheng Li, Yingli Feng, Kun Beijing University of Chemical Technology Key Laboratory of Engine Health Monitoring-Control and Networking Ministry of Education Beijing China China Petroleum Safety and Environmental Protection Technology Research Institute Beijing China Beijing University of Chemical Technology Beijing Key Laboratory of High-End Mechanical Equipment Health Monitoring and Self-Recovery Beijing China

ISBN: (纸本)9781665492812

Mechanical fault diagnosis is very important in industry because early detection can avoid some dangerous situations, and not much research has been done on the diagnosis of wear faults in centrifugal pumps. With the rapid development of data analysis techniques, data-driven diagnosis methods are becoming increasingly popular. In this study, stacked autoencoder based method is proposed to solve the centrifugal pump seal wear fault diagnosis problem. The method extracts power spectral density features directly from the vibration signal and chunks the features, greatly reducing the training difficulty and improving the accuracy of the model. The effectiveness of the method is verified using a centrifugal pump dataset, and the results show that the method can diagnose not only the fault site but also the degree of wear. © 2022 IEEE.

关键词： power spectral density stacked autoencoder wear failure

来源：评论

学校读者我要写书评

暂无评论

Active Suppression of Multi-frequency Vibration of Rotor Based on Adaptive Immersion & Invariant Theory 11th

Active Suppression of Multi-frequency Vibration of Rotor Bas...

引用

11th IFToMM International Conference on Rotordynamics, IFToMM 2023

作者： Gao, Xinyu Bao, Yifan Zhang, Zeliang Yao, Jianfei School of Mechanical and Electrical Engineering Beijing University of Chemical Technology Beijing100029 China Beijing Key Laboratory of Health Monitoring and Self-Recovering for High-End Mechanical Equipment Beijing University of Chemical Technology Beijing100029 China Key Lab of Engine Health Monitoring-Control and Networking of Ministry of Education Beijing University of Chemical Technology Beijing100029 China

ISBN: (纸本)9783031404542

This paper describes an active suppression method based on Immersion and Invariance Theory (I&I) for the multi-frequency vibration of rotor in rotating machinery. The approach decomposes the multi-frequency excitation vectorially in Cartesian coordinate system. And the high-order non-linear system is immersed into the low-order system. AMA is used as the actuator in control system. The model of rotor-bearing-AMA system is established, integrating the model of unbalance and misalignment. A zero bias current strategy combined PD-I&I control algorithm is proposed by analyzing the influence of electromagnetic force nonlinearity. An adaptive notch filter is designed to meet the need of multi-speed control and cope with the influence of speed fluctuation. Finally, simulation and experimental research are carried out to verify and analyze the effectiveness of the proposed method to suppress multi-frequency vibration. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Real-Time Intelligent Diagnosis of Co-frequency Vibration Faults in Rotating Machinery Based on Lightweight-Convolutional Neural Networks

引用

Chinese Journal of Mechanical engineering 2024年第2期37卷 264-282页

作者： Xin Pan Xiancheng Zhang Zhinong Jiang Guangfu Bin Beijing Key Laboratory of Health Monitoring and Self-recovery for High-End Mechanical Equipment College of Mechanical and Electrical EngineeringBeijing University of Chemical TechnologyBeijing 100029China Key Laboratory of Engine Health Monitoring-Control and Networking(Ministry of Education) College of Mechanical and Electrical EngineeringBeijing University of Chemical TechnologyBeijing 100029China College of Mechanical Engineering Hunan University of Science and TechnologyXiangtan 411201China

The co-frequency vibration fault is one of the common faults in the operation of rotating equipment,and realizing the real-time diagnosis of the co-frequency vibration fault is of great significance for monitoring the health state and carrying out vibration suppression of the *** engineering scenarios,co-frequency vibration faults are highlighted by rotational frequency and are difficult to identify,and existing intelligent methods require more hardware conditions and are exclusively ***,Lightweight-convolutional neural networks(LW-CNN)algorithm is proposed in this paper to achieve real-time fault *** critical parameters are discussed and verified by simulated and experimental signals for the sliding window data augmentation *** on LW-CNN and data augmentation,the real-time intelligent diagnosis of co-frequency is ***,a real-time detection method of fault diagnosis algorithm is proposed for data acquisition to fault *** is verified by experiments that the LW-CNN and sliding window methods are used with high accuracy and real-time performance.

关键词： Co-frequency vibration Real-time diagnosis LW-CNN Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Coupled Effects of Misalignment and Viscoelastic Deformation on Dynamically Loaded Journal Bearings

SSRN

引用

SSRN 2023年

作者： Xiong, Guoqing Mao, Zhiwei Zhang, Jinjie Wang, Zijia Jiang, Zhinong Key Laboratory of Engine Health Monitoring-Control and Networking Ministry of Education Beijing University of Chemical Technology Beijing100029 China State Key Laboratory of Tribology Tsinghua University Beijing China

Numerous studies on the lubrication characteristics of journal bearings with existing journal misalignment and bearing elastic deformation have demonstrated that both significantly affect the lubrication performance. Recent studies have also indicated that viscoelastic deformation is more useful than elastic deformation for determining the effects of strong impact loads caused by internal combustion engine detonation. However, studies involving the coupled effects of misalignment and viscoelastic deformation have not been reported yet. Therefore, this study proposes a transient lubrication model that couples the influences of journal misalignment and bearing viscoelastic deformation, considering the contact surface morphology and oil film cavitation effects. A numerical model was used to determine the evolution of lubrication performance under a transient time-varying dynamic load, and the coupled influences of misalignment and viscoelastic deformation on the lubrication performance of dynamically loaded journal bearings were systematically explored. The results show that the coupling of journal misalignment and viscoelastic deformation increases the probability of metal-to-metal contact. The difference in the coupling of misalignment and elastic deformation is exhibited in the distribution, amplitude, and occurrence phases of the performance parameters. Increasing the journal speed and applied load significantly enhances the coupled effects of journal misalignment and viscoelastic deformation on the lubrication performance. Under high speeds, heavy loads, and large and rapidly changing impact loads, the coupled effects of misalignment and viscoelastic deformation should be considered. © 2023, The Authors. All rights reserved.

关键词： Dynamic loads

来源：评论

学校读者我要写书评

暂无评论

A Fault Diagnosis Method for Valve Train of Diesel engine Considering Incomplete Feature Set

A Fault Diagnosis Method for Valve Train of Diesel Engine Co...

引用

International Conference on Sensing, Diagnostics, Prognostics, and control (SDPC)

作者： Zhinong Jiang Yuehua Lai Zijia Wang Jinjie Zhang Key Laboratory of Engine Health Monitoring Control and Networking Ministry of Education Beijing University of Chemical Technology Beijing China Beijing Key Laboratory of Health Monitoring Control and Fault Self-recovery for High-end Machinery Beijing University of Chemical Technology Beijing China

ISBN: (数字)9781728101996

ISBN: (纸本)9781728102009

Abnormal valve clearance is a common fault of diesel engine, and early warning of abnormal valve clearance plays an important role in the condition based maintenance of diesel engine. Although information fusion technology can improve the accuracy of fault diagnosis, it cannot guarantee that the fused features can perfectly represent the required key information. For the incomplete feature set, a method combining multi-domain feature and improved support vector machine is proposed. Firstly, the extraction of multi-domain feature is carried out to deeply explore the state information of valve train contained in the original vibration signal. The statistical characteristics and waveform characteristics are extracted from time domain vibration signals, and the frequency domain feature similar to time-domain feature is extracted after the Fourier transform of the vibration signal. What's more, according to the working principle of diesel engine, the energy characteristics in angular frequency domain are extracted. Then, an improved support vector machine method based on multi-domain feature is proposed to further reduce the diagnostic errors caused by incomplete feature set. Finally, the proposed method is compared with other traditional methods about the fault diagnosis of valve train of diesel engine. The results show that the proposed method is applicable to the fault diagnosis of valve train of diesel engine with good accuracy, and the generalization ability of diagnostic model is greatly improved.

关键词： Feature extraction Diesel engines Vibrations Valves Frequency-domain analysis Support vector machines Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Research on Motor Fault Identification Method Based on Vibration Current Multisource Data Fusion and Deep Learning 14

Research on Motor Fault Identification Method Based on Vibra...

引用

14th IEEE Global Reliability and Prognostics and health Management Conference, PHM-Hangzhou 2023

作者： He, Yiyi Feng, Kun Liu, Baoxia Key Lab of Engine Health Monitoring-Control and Networking of Ministry of Education Beijing University of Chemical Technology Beijing100029 China State Key Laboratory of High-end Compressor and System Technology Beijing University of Chemical Technology Beijing100029 China National Pipe Networknorth Company Pipeline Compressor Unit Maintenance Center Beijing University of Chemical Technology Beijing100029 China

ISBN: (纸本)9798350301359

Traditional motor fault diagnosis techniques are usually based on a single type of state parameter. However, the monitoring range of a single type of motor state parameters is very limited, and it is difficult to meet the needs of comprehensive fault diagnosis. The purpose of this paper is to propose a fault diagnosis method for typical AC induction motors by fusing two types of parameters, i. e. vibration data and current data, in order to improve the accuracy of diagnosis. Based on the analysis of the basic faults of typical AC asynchronous motors, this paper studies the methods of motor fault feature extraction, including Fast Fourier Transform (FFT) and Hilbert-Huang Transform (HHT). Then, the method of motor multi-sensor parameter fusion is studied, and the realization scheme of data fusion is designed. Convolutional neural network is constructed as a feature fusion tool. The results of fast Fourier transform (FFT) of current data and Hilbert-Huang transform (HHT) of voltage data of different fault types are input into CNN as fault features, and the deep-seated features are extracted by using CNN's feature extraction ability. Finally, the CNN network series Multilayer perceptron (MLP) was constructed to realize fault classification, and the motor fault identification and fault diagnosis were realized based on the motor vibration and current parameters. The results show that the motor fault diagnosis technology based on data fusion can improve the accuracy of diagnosis results, reduce the uncertainty caused by single parameter, and improve the accuracy of motor fault diagnosis. © 2023 IEEE.

关键词： data fusion deep learning fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Fault diagnosis for reciprocating compressor based on GLCM and HOG features fusion of time-frequency image

Fault diagnosis for reciprocating compressor based on GLCM a...

引用

International Conference on Sensing, Diagnostics, Prognostics, and control (SDPC)

作者： Hui Li Haipeng Zhao Zijia Wang Zhiwei Mao Key Lab of Engine Health Monitoring-Control and Networking Ministry of Education Beijing University of Chemical Technology Beijing China Beijing Key Laboratory of Health Monitoring Control and Fault Self-recovery for High-end Machinery Beijing University of Chemical Technology Beijing China

ISBN: (数字)9781728101996

ISBN: (纸本)9781728102009

In this paper, the gray level co-occurrence matrix (GLCM) and histogram of oriented gradient (HOG) features fusion of time-frequency image are introduced into the reciprocating compressor fault diagnosis. Firstly, vibration signals are acquired from the reciprocating compressor in different states of head tile and the wavelet transform distributions of vibration signals were displayed in time-frequency images. Secondly, GLCM and HOG methods are used to extract features from time-frequency images, then GLCM feature and HOG feature are fused and input into support vector machine for recognition and classification. By this way, the fault diagnosis of time series signals of reciprocating compressor is transferred to the classification of time-frequency images. The results show that can accurately realize diagnosis of small-head wear fault of reciprocating compressor.

关键词： Feature extraction Time-frequency analysis Image coding Vibrations Support vector machines Fault diagnosis Training

来源：评论

学校读者我要写书评

暂无评论

FINITE ELEMENT-BASED COMPRESSION SIMULATION AND PERMEATION PERFORMANCE MEASUREMENT AND control OF HIGH TEMPERATURE SEALING MATERIALS

引用

UPB Scientific Bulletin, Series D: Mechanical engineering 2023年第2期85卷 103-118页

作者： Chen, Lifang Guo, Yixiang Key Lab of Engine Health Monitoring Control and Networking of Ministry of Education Beijing University of Chemical Technology Beijing100029 China State Key Laboratory of High-end Compressor and System Technology Beijing University of Chemical Technology Beijing100029 China

To obtain the characteristic operational parameters of spacecraft heat seals, a customized tester is used to carry out the structure and performance research of the P-shaped heat seals. A heat-sealing test system is built to simulate real working conditions. The structure and the plan of the tester are optimized based on the finite element thermal analysis method. For different compression rates and pore-opening structures, the leakage rates of the P-shaped seal are tested at room temperature, high temperature, and different air pressures. The test results show that the leakage of the P-shaped sealing ring decreases with the increase of compression rate and the number of openings on the outer high-pressure side. These results are following those of the finite element theoretical analysis. The main control factors that affect the size of seal leakage have been preliminarily determined, and the data obtained from the test has laid the foundation for future research on sealing theory. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Seals

来源：评论

学校读者我要写书评

暂无评论

An intelligent fault diagnosis method for a diesel engine valve based on improved wavelet packet-Mel frequency and convolutional neural network

An intelligent fault diagnosis method for a diesel engine va...

引用

International Conference on Sensing, Diagnostics, Prognostics, and control (SDPC)

作者： Haipeng Zhao Zhiwei Mao Kun Chen Zhinong Jiang Key Lab of Engine Health Monitoring-Control and Networking of Ministry of Education Beijing University of Chemical Technology Beijing China Beijing Key Laboratory of High-End Mechanical Equipment Health Monitoring and Self-Recovery Beijing University of Chemical Technology Beijing China

ISBN: (数字)9781728101996

ISBN: (纸本)9781728102009

Considering the diesel engine vibration signals have the characteristics of the non-stability and non-linearity due to its compact-complex structure, strong noise and especially unstable operating conditions, we proposes an novel method based on improved wavelet packet-Mel frequency and convolutional neural network (CNN) to extract features and diagnose faults of diesel engine valve. Firstly, the wavelet packet transform is applied with the purpose of decomposing vibration signal and reconstructing each wavelet packet coefficient. Secondly, an improved Mel frequency cepstrum method is used to extract features from the reconstructed vibration signals. MFC algorithm is a well-known feature extraction technique widely used for speech recognition. Then, feature matrixes are constituted to obtain more definite and comprehensive time-frequency distributed representation, of which the row represents the average Mel frequency cepstrum coefficients and the column represents the frequency bands of wavelet packet decomposition in ascending order. Finally, a deep hierarchical CNN structure constructed by convolution layers, max-pooling layers and fully-connected layers is trained using a standard backpropagation, of which the input of first layer with 256 neurons is the above 2D feature matrixes and the output of final layer with 3 neurons is the number of vibration signal states. The experimental results of the fault diagnosis for the diesel engine valves show that the proposed method has the good diagnosis performance for diesel engine valve clearance faults.

关键词： Vibrations Diesel engines Valves Feature extraction Wavelet packets Fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

An Improved Initial Parameter Setting Method for Variational Time-Domain Decomposition

An Improved Initial Parameter Setting Method for Variational...

引用

Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD), International Conference on

作者： He Li Jiniie Zhang Zhinong Jiang Zhiwei Mao Key Laboratory of Engine Health Monitoring Control and Networking Ministry of Education Beijing University of Chemical Technology Beijing China State Key Laboratory of High-end Compressor and System Technology Beijing University of Chemical Technology Beijing China

Effectively decomposing vibration signals is crucial for identifying fault features and evaluating the performance of mechanical systems. Reciprocating mechanical vibration signals typically exhibit complex non-stationary and multi-impact characteristics, posing challenges in signal decomposition. Currently, in response to this issue, the Variational Time-Domain Decomposition (VTDD) method has been proposed to achieve outstanding adaptive impact separation in reciprocating mechanical vibration signals. However, VTDD has limitations in the initial parameter value settings, particularly when dealing with reciprocating mechanical signals under strong noise conditions, which result in slow convergence and less accurate decomposition. To address these limitations, this paper proposes an improved initial parameter value setting method based on a noise threshold-driven impact center estimation algorithm. This method preserves the impacts from vibration signals by estimating the noise threshold, then accurately estimates the number and positions of impacts, which is applied to replace the original VTDD parameter setting approach. Experimental results demonstrate that this improved method delivers excellent decomposition outcomes and applicability for both simulated and real mechanical vibration signals. In summary, by enhancing the initial parameter value setting, the VTDD method performance provides a more reliable tool for vibration signal analysis, especially in the challenging task of recognizing complex impact signals.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：