Condition monitoring is increasingly used to anticipate and detect failures of industrial machines.Failures of machines can cause high maintenance or replacement costs.If neglected,it may result in catastrophic accide...Condition monitoring is increasingly used to anticipate and detect failures of industrial machines.Failures of machines can cause high maintenance or replacement costs.If neglected,it may result in catastrophic accidents leading to production shrinkage.The potential failure would negatively affect the profitability of the company,including production shut down,cost of spare parts,cost of labor,damage of reputation,risk of injury to people and the environment.In recent years,condition-based maintenance( CBM) and prognostic and health management( PHM) are developed and formed a strong connection among science,engineering,computer,reliability,communication,management,etc.Computerized maintenance management systems( CMMS) store a lot of data regarding the fault diagnosis and life prediction of the machinery equipment.It's too necessary to uncover useful knowledge from the huge amount of data.It's vital to find the ways to obtain useful and concise information from these data.This information can be of great influence in the decision making of managers.This article is a review of intelligent approaches in machinery faults diagnosis and prediction based on PHM and CBM.展开更多
Fault diagnosis plays a significant role in conducting condition-based maintenance and health management for gas turbines(GTs) to improve reliability and reduce costs. Various diagnosis methods developed by modeling e...Fault diagnosis plays a significant role in conducting condition-based maintenance and health management for gas turbines(GTs) to improve reliability and reduce costs. Various diagnosis methods developed by modeling engine systems or certain components implement faults detection and diagnosis based on the measurement of systemic parameters deviations. However, these conventional model-based methods are hindered by limitations of inability to handle the nonlinear nature, measurement uncertainty, fault coupling and other implementing problems. Recently, the development of artificial intelligence algorithms has provided an effective solution to the above problems, triggering broad researches for data-driven fault diagnosis methods with better accuracy,dynamic performance, and universality. This paper presents a systematic review of recently proposed intelligent fault diagnosis methods for GT engines, according to the classification of shallow learning methods, deep learning methods and hybrid intelligent methods. Moreover, the principle of typical algorithms, the evolution of enhanced methods, and the assessment of pros and cons are summarized to conclude the present status and look forward to the future in the field of GT fault diagnosis. Possible directions for development in method validation, information fusion, and interpretability of intelligent diagnosis methods are concluded in the end to provide insightful concepts for scholars in related fields.展开更多
Convolutional neural networks(CNNs)are well suited to bearing fault classification due to their ability to learn discriminative spectro-temporal patterns.However,gathering sufficient cases of faulty conditions in real...Convolutional neural networks(CNNs)are well suited to bearing fault classification due to their ability to learn discriminative spectro-temporal patterns.However,gathering sufficient cases of faulty conditions in real-world engineering scenarios to train an intelligent diagnosis system is challenging.This paper proposes a fault diagnosis method combining several augmentation schemes to alleviate the problem of limited fault data.We begin by identifying relevant parameters that influence the construction of a spectrogram.We leverage the uncertainty principle in processing time-frequency domain signals,making it impossible to simultaneously achieve good time and frequency resolutions.A key determinant of this phenomenon is the window function's choice and length used in implementing the shorttime Fourier transform.The Gaussian,Kaiser,and rectangular windows are selected in the experimentation due to their diverse characteristics.The overlap parameter's size also influences the outcome and resolution of the spectrogram.A 50%overlap is used in the original data transformation,and±25%is used in implementing an effective augmentation policy to which two-stage regular CNN can be applied to achieve improved performance.The best model reaches an accuracy of 99.98%and a cross-domain accuracy of 92.54%.When combined with data augmentation,the proposed model yields cutting-edge results.展开更多
Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of...Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of increasing under prolonged operation and varying working conditions.Hence, the accurate fault severity categorization of bearings is vital in diagnosing faults that arise in rotating machinery.The variability and complexity of the recorded vibration signals pose a great hurdle to distinguishing unique characteristic fault features.In this paper, the efficacy and the leverage of a pre-trained convolutional neural network(CNN) is harnessed in the implementation of a robust fault classification model.In the absence of sufficient data, this method has a high-performance rate.Initially, a modified VGG16 architecture is used to extract discriminating features from new samples and serves as input to a classifier.The raw vibration data are strategically segmented and transformed into two representations which are trained separately and jointly.The proposed approach is carried out on bearing vibration data and shows high-performance results.In addition to successfully implementing a robust fault classification model, a prognostic framework is developed by constructing a health indicator(HI) under varying operating conditions for a given fault condition.展开更多
煤矿坑道钻机自动化和智能化程度的提高、作业范围和应用场景的扩展,使其系统复杂性和工作环境恶劣程度随之增加,对煤矿坑道钻机可靠性提出新的挑战。为有效降低因钻机故障带来的安全风险,提升钻机全寿命周期的任务品质,煤矿坑道钻机状...煤矿坑道钻机自动化和智能化程度的提高、作业范围和应用场景的扩展,使其系统复杂性和工作环境恶劣程度随之增加,对煤矿坑道钻机可靠性提出新的挑战。为有效降低因钻机故障带来的安全风险,提升钻机全寿命周期的任务品质,煤矿坑道钻机状态监测与故障诊断技术应运而生。首先从钻机状态参数采集、数据处理、诊断方法、系统应用等四个方面对煤矿坑道钻机关键系统状态监测和故障诊断技术研究现状进行总结分析,然后在故障预测与健康管理(prognostics and health management, PHM)技术基本概念的基础上根据集中式与分布式结合的方式提出了坑道钻机PHM技术框架,最后对煤矿坑道钻机PHM技术发展趋势进行展望,旨在为新一代煤矿坑道钻机及相关煤矿机械装备PHM技术的研究开展提供参考和借鉴。展开更多
针对现有城市轨道交通(简称:城轨)设备状态信息采集不完整、设备运维管理缺少决策支持数据、各专业运维业务缺乏统筹协调、运维效率低等现实问题,着眼于城轨设备综合运维管理,基于故障预测与健康管理(PHM,Prognostics Health Management...针对现有城市轨道交通(简称:城轨)设备状态信息采集不完整、设备运维管理缺少决策支持数据、各专业运维业务缺乏统筹协调、运维效率低等现实问题,着眼于城轨设备综合运维管理,基于故障预测与健康管理(PHM,Prognostics Health Management)理念,提出城轨设备智能运维系统的总体架构和功能框架,探讨亟需深入研究的关键技术。该系统通过采集和利用大量设备监测数据,利用故障诊断模型、人工智能算法和工作流引擎,在实现关键设备健康管理的基础上,自动生成设备运维计划,辅助设备运维管理决策,支持多业务作业协同,有助于提高城轨设备整体运维效能,提高城轨设备健康水平和性能,最小化停运时间,降低维修保障费用,保障城轨安全、可靠、高效运营。展开更多
随着智能变电站系统自动化程度的快速发展以及新型传感器的广泛应用,智能变电站内电气设备数据挖掘直接关系着智能变电站的可靠性、稳定性和安全性。针对大数据背景下智能变电站的智能运维,着重介绍故障预测与健康管理(prognostics and ...随着智能变电站系统自动化程度的快速发展以及新型传感器的广泛应用,智能变电站内电气设备数据挖掘直接关系着智能变电站的可靠性、稳定性和安全性。针对大数据背景下智能变电站的智能运维,着重介绍故障预测与健康管理(prognostics and health management,PHM)技术在智能变电站的应用,并采用状态检修系统开放体系架构(open system architecture condition-based management,OSA-CBM)标准对PHM系统的层次结构进行了梳理。首先,在对智能变电站系统结构进行分析的基础上,重点总结了可用于智能变电站的基于数据驱动的各种故障诊断及寿命预测方法;然后,系统分析了智能变电站中的检修管理的研究成果;最后,基于OSA-CBM架构提出了一种可用于智能变电站的PHM架构。展开更多
基金Fundamental Research Funds for the Central Universities,China(No.DUT17GF214)
文摘Condition monitoring is increasingly used to anticipate and detect failures of industrial machines.Failures of machines can cause high maintenance or replacement costs.If neglected,it may result in catastrophic accidents leading to production shrinkage.The potential failure would negatively affect the profitability of the company,including production shut down,cost of spare parts,cost of labor,damage of reputation,risk of injury to people and the environment.In recent years,condition-based maintenance( CBM) and prognostic and health management( PHM) are developed and formed a strong connection among science,engineering,computer,reliability,communication,management,etc.Computerized maintenance management systems( CMMS) store a lot of data regarding the fault diagnosis and life prediction of the machinery equipment.It's too necessary to uncover useful knowledge from the huge amount of data.It's vital to find the ways to obtain useful and concise information from these data.This information can be of great influence in the decision making of managers.This article is a review of intelligent approaches in machinery faults diagnosis and prediction based on PHM and CBM.
基金financially supported by the National Natural Science Foundation of China (No. 61890921, 61890923, and 52372371)the key projects of Aero Engine and Gas Turbine Basic Science Center (No. P2022-B-V-001-001 and P2022B-V-002-001)。
文摘Fault diagnosis plays a significant role in conducting condition-based maintenance and health management for gas turbines(GTs) to improve reliability and reduce costs. Various diagnosis methods developed by modeling engine systems or certain components implement faults detection and diagnosis based on the measurement of systemic parameters deviations. However, these conventional model-based methods are hindered by limitations of inability to handle the nonlinear nature, measurement uncertainty, fault coupling and other implementing problems. Recently, the development of artificial intelligence algorithms has provided an effective solution to the above problems, triggering broad researches for data-driven fault diagnosis methods with better accuracy,dynamic performance, and universality. This paper presents a systematic review of recently proposed intelligent fault diagnosis methods for GT engines, according to the classification of shallow learning methods, deep learning methods and hybrid intelligent methods. Moreover, the principle of typical algorithms, the evolution of enhanced methods, and the assessment of pros and cons are summarized to conclude the present status and look forward to the future in the field of GT fault diagnosis. Possible directions for development in method validation, information fusion, and interpretability of intelligent diagnosis methods are concluded in the end to provide insightful concepts for scholars in related fields.
基金supported by the National Natural Science Foundation of China(42027805)the National Aeronautical Fund(ASFC-20172080005)。
文摘Convolutional neural networks(CNNs)are well suited to bearing fault classification due to their ability to learn discriminative spectro-temporal patterns.However,gathering sufficient cases of faulty conditions in real-world engineering scenarios to train an intelligent diagnosis system is challenging.This paper proposes a fault diagnosis method combining several augmentation schemes to alleviate the problem of limited fault data.We begin by identifying relevant parameters that influence the construction of a spectrogram.We leverage the uncertainty principle in processing time-frequency domain signals,making it impossible to simultaneously achieve good time and frequency resolutions.A key determinant of this phenomenon is the window function's choice and length used in implementing the shorttime Fourier transform.The Gaussian,Kaiser,and rectangular windows are selected in the experimentation due to their diverse characteristics.The overlap parameter's size also influences the outcome and resolution of the spectrogram.A 50%overlap is used in the original data transformation,and±25%is used in implementing an effective augmentation policy to which two-stage regular CNN can be applied to achieve improved performance.The best model reaches an accuracy of 99.98%and a cross-domain accuracy of 92.54%.When combined with data augmentation,the proposed model yields cutting-edge results.
基金supported by the National Natural Science Foundation of China (42027805)National Aeronautical Fund (ASFC-2017 2080005)National Key R&D Program of China (2017YFC03 07100)。
文摘Rolling element bearings are machine components used to allow circular movement and hence deliver forces between components of machines used in diverse areas of industry.The likelihood of failure has the propensity of increasing under prolonged operation and varying working conditions.Hence, the accurate fault severity categorization of bearings is vital in diagnosing faults that arise in rotating machinery.The variability and complexity of the recorded vibration signals pose a great hurdle to distinguishing unique characteristic fault features.In this paper, the efficacy and the leverage of a pre-trained convolutional neural network(CNN) is harnessed in the implementation of a robust fault classification model.In the absence of sufficient data, this method has a high-performance rate.Initially, a modified VGG16 architecture is used to extract discriminating features from new samples and serves as input to a classifier.The raw vibration data are strategically segmented and transformed into two representations which are trained separately and jointly.The proposed approach is carried out on bearing vibration data and shows high-performance results.In addition to successfully implementing a robust fault classification model, a prognostic framework is developed by constructing a health indicator(HI) under varying operating conditions for a given fault condition.
文摘煤矿坑道钻机自动化和智能化程度的提高、作业范围和应用场景的扩展,使其系统复杂性和工作环境恶劣程度随之增加,对煤矿坑道钻机可靠性提出新的挑战。为有效降低因钻机故障带来的安全风险,提升钻机全寿命周期的任务品质,煤矿坑道钻机状态监测与故障诊断技术应运而生。首先从钻机状态参数采集、数据处理、诊断方法、系统应用等四个方面对煤矿坑道钻机关键系统状态监测和故障诊断技术研究现状进行总结分析,然后在故障预测与健康管理(prognostics and health management, PHM)技术基本概念的基础上根据集中式与分布式结合的方式提出了坑道钻机PHM技术框架,最后对煤矿坑道钻机PHM技术发展趋势进行展望,旨在为新一代煤矿坑道钻机及相关煤矿机械装备PHM技术的研究开展提供参考和借鉴。
文摘针对现有城市轨道交通(简称:城轨)设备状态信息采集不完整、设备运维管理缺少决策支持数据、各专业运维业务缺乏统筹协调、运维效率低等现实问题,着眼于城轨设备综合运维管理,基于故障预测与健康管理(PHM,Prognostics Health Management)理念,提出城轨设备智能运维系统的总体架构和功能框架,探讨亟需深入研究的关键技术。该系统通过采集和利用大量设备监测数据,利用故障诊断模型、人工智能算法和工作流引擎,在实现关键设备健康管理的基础上,自动生成设备运维计划,辅助设备运维管理决策,支持多业务作业协同,有助于提高城轨设备整体运维效能,提高城轨设备健康水平和性能,最小化停运时间,降低维修保障费用,保障城轨安全、可靠、高效运营。
文摘随着智能变电站系统自动化程度的快速发展以及新型传感器的广泛应用,智能变电站内电气设备数据挖掘直接关系着智能变电站的可靠性、稳定性和安全性。针对大数据背景下智能变电站的智能运维,着重介绍故障预测与健康管理(prognostics and health management,PHM)技术在智能变电站的应用,并采用状态检修系统开放体系架构(open system architecture condition-based management,OSA-CBM)标准对PHM系统的层次结构进行了梳理。首先,在对智能变电站系统结构进行分析的基础上,重点总结了可用于智能变电站的基于数据驱动的各种故障诊断及寿命预测方法;然后,系统分析了智能变电站中的检修管理的研究成果;最后,基于OSA-CBM架构提出了一种可用于智能变电站的PHM架构。
