International Journal of Prognostics and Health Management最新文献_第10页

Development of An Integrated Framework for Cyber Physical System (CPS)-Enabled Rehabilitation System 网络物理系统(CPS)康复系统综合架构的发展

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2021-01-01 DOI: 10.36001/ijphm.2021.v12i4.2913

Jianshe Feng, Feng Zhu, Pin Li, Hossein Davari, Jay Lee

A Cyber-Physical System (CPS)-enabled rehabilitation system framework for enhanced recovery rate in gait training systems is presented in this paper. Recent advancements in sensing and data analytics have paved the way for the transformation of healthcare systems from experience-based to evidence-based. To this end, this paper introduces a CPS-enabled rehabilitation system that collects, processes, and models the data from patient and rehabilitative training machines. This proposed system consists of a set of sensors to collect various physiological data as well as machine parameters. The sensors and data acquisition systems are connected to an edge computing unit that handles the data preprocessing, analytics, and results visualization. Advanced machine learning algorithms are used to analyze data from physiological data, machine parameters, and patients’ metadata to quantify each patient’s recovery progress, devise personalized treatment strategies, adjust machine parameters for optimized performance, and provide feedback regarding patient’s adherence to instructions. Moreover, the accumulation of the knowledge gathered by patients with different conditions can provide a powerful tool for better understanding the human-machine interaction and its impact on patient recovery. Such system can eventually serve as a ‘Virtual Doctor’, providing accurate feedback and personalized treatment strategies for patients.

本文提出了一种基于信息物理系统(CPS)的康复系统框架，用于提高步态训练系统的恢复速度。传感和数据分析方面的最新进展为医疗保健系统从基于经验向基于证据的转变铺平了道路。为此，本文介绍了一个支持cps的康复系统，该系统收集、处理和建模来自患者和康复训练机器的数据。该系统由一组传感器组成，用于收集各种生理数据和机器参数。传感器和数据采集系统连接到处理数据预处理、分析和结果可视化的边缘计算单元。先进的机器学习算法用于分析来自生理数据、机器参数和患者元数据的数据，以量化每位患者的恢复进度，设计个性化治疗策略，调整机器参数以优化性能，并提供关于患者遵守指示的反馈。此外，不同病情患者收集的知识的积累可以为更好地理解人机交互及其对患者康复的影响提供强大的工具。该系统最终可以作为“虚拟医生”，为患者提供准确的反馈和个性化的治疗策略。

{"title":"Development of An Integrated Framework for Cyber Physical System (CPS)-Enabled Rehabilitation System","authors":"Jianshe Feng, Feng Zhu, Pin Li, Hossein Davari, Jay Lee","doi":"10.36001/ijphm.2021.v12i4.2913","DOIUrl":"https://doi.org/10.36001/ijphm.2021.v12i4.2913","url":null,"abstract":"A Cyber-Physical System (CPS)-enabled rehabilitation system framework for enhanced recovery rate in gait training systems is presented in this paper. Recent advancements in sensing and data analytics have paved the way for the transformation of healthcare systems from experience-based to evidence-based. To this end, this paper introduces a CPS-enabled rehabilitation system that collects, processes, and models the data from patient and rehabilitative training machines. This proposed system consists of a set of sensors to collect various physiological data as well as machine parameters. The sensors and data acquisition systems are connected to an edge computing unit that handles the data preprocessing, analytics, and results visualization. Advanced machine learning algorithms are used to analyze data from physiological data, machine parameters, and patients’ metadata to quantify each patient’s recovery progress, devise personalized treatment strategies, adjust machine parameters for optimized performance, and provide feedback regarding patient’s adherence to instructions. Moreover, the accumulation of the knowledge gathered by patients with different conditions can provide a powerful tool for better understanding the human-machine interaction and its impact on patient recovery. Such system can eventually serve as a ‘Virtual Doctor’, providing accurate feedback and personalized treatment strategies for patients.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"70086412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Length of Time-Series Gait Data on Lyapunov Exponent for Fall Risk Detection 基于Lyapunov指数的时间序列步态数据长度检测跌倒风险

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2021-01-01 DOI: 10.36001/ijphm.2021.v12i4.2917

Victoria Smith Hussain, Christopher W. Frames, T. Lockhart

Falls are the leading cause of disability in older adults with a third of adults over the age of 65 falling every year. Quantitative fall risk assessments using inertial measurement units and local dynamics stability (LDS) have shown that it is possible to identify at-risk persons. However, there are inconsistencies in the literature on how to calculate LDS and how much data is required for a reliable result. This study investigates the reliability and minimum required strides for 6 algorithm-normalization method combinations when computing LDS using young healthy and community dwelling elderly individuals. Participants wore an accelerometer at the lower lumbar while they walked for three minutes up and down a long hallway. This study concluded that the Rosenstein et al. algorithm was successfully and reliably able to differentiate between both populations using only 50 strides. It was also found normalizing the gait time series data by either truncating the data using a fixed number of strides or using a fixed number of strides and normalizing the entire time series to a fixed number of data points performed better when using the Rosenstein et al. algorithm.

跌倒是老年人致残的主要原因，每年有三分之一的65岁以上的成年人摔倒。使用惯性测量单元和局部动力学稳定性(LDS)的定量跌倒风险评估表明，有可能识别有风险的人。然而，关于如何计算LDS以及需要多少数据才能得到可靠的结果，文献中存在不一致的地方。本研究探讨了6种算法-归一化方法组合在计算年轻健康和社区居住老年人LDS时的可靠性和最小所需步幅。参与者在一条长长的走廊上下行走三分钟时，腰下部佩戴了一个加速度计。本研究得出结论，Rosenstein等人的算法仅使用50步就能成功可靠地区分两个种群。还发现，在使用Rosenstein等人的算法时，通过使用固定步幅截断数据或使用固定步幅并将整个时间序列归一化为固定数量的数据点来规范化步态时间序列数据的效果更好。

{"title":"Length of Time-Series Gait Data on Lyapunov Exponent for Fall Risk Detection","authors":"Victoria Smith Hussain, Christopher W. Frames, T. Lockhart","doi":"10.36001/ijphm.2021.v12i4.2917","DOIUrl":"https://doi.org/10.36001/ijphm.2021.v12i4.2917","url":null,"abstract":"Falls are the leading cause of disability in older adults with a third of adults over the age of 65 falling every year. Quantitative fall risk assessments using inertial measurement units and local dynamics stability (LDS) have shown that it is possible to identify at-risk persons. However, there are inconsistencies in the literature on how to calculate LDS and how much data is required for a reliable result. This study investigates the reliability and minimum required strides for 6 algorithm-normalization method combinations when computing LDS using young healthy and community dwelling elderly individuals. Participants wore an accelerometer at the lower lumbar while they walked for three minutes up and down a long hallway. This study concluded that the Rosenstein et al. algorithm was successfully and reliably able to differentiate between both populations using only 50 strides. It was also found normalizing the gait time series data by either truncating the data using a fixed number of strides or using a fixed number of strides and normalizing the entire time series to a fixed number of data points performed better when using the Rosenstein et al. algorithm.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"70086102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Integration of future maintenance actions in the prediction parameters of the ATLAS COPCO ZR 200 compressor 在阿特拉斯·科普柯ZR 200压缩机的预测参数中集成了未来的维护行动

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2021-01-01 DOI: 10.36001/ijphm.2021.v12i2.2916

Agnes Virginie Tjahe, B. M. Mtopi Fotso, M. Fogué, N. Zerhouni

The prediction of several failure modes of an industrial equipment requires the development of prediction systems with several interdependent parameters. The integration of future maintenance actions with this type of prediction system is a major asset for maintenance decision making. This is even more relevant in the event that after having predicted the future occurrence of several failure modes, the maintenance department does not have the necessary resources to correct all the predicted failure modes at once. In this case it becomes necessary to know how much longer the equipment will work if future partial maintenance actions that do not correct all failure modes are implemented. It is to contribute to the resolution of this problem that we propose an architecture integrating the future maintenance actions to the prediction of several interdependent parameters. This architecture is based on the association of Proportional Integral Derivative regulators to Neuro-Fuzzy systems taking into account the four previous instants to predict the next instant. An application is made with accuracies of the order of 70% for the prediction of the phenomena of fouling of the coolers and of the order of 90% for the prediction of the phenomena of clogging of the filters of the ATLAS COPCO compressor, this with Central Processing Unit values not exceeding one minute.

对工业设备的多种失效模式进行预测，需要开发具有多个相互依赖参数的预测系统。未来维修行动与这种类型的预测系统的集成是维修决策的主要资产。在预测了未来出现的几种故障模式之后，维护部门没有必要的资源来立即纠正所有预测的故障模式，这一点就更加重要了。在这种情况下，就有必要知道，如果未来的部分维护措施不能纠正所有的故障模式，设备还能工作多久。为了解决这个问题，我们提出了一个架构，将未来的维护行动集成到几个相互依赖的参数的预测中。该结构基于比例积分导数调节器与神经模糊系统的关联，并考虑到前四个瞬间来预测下一个瞬间。在阿特拉斯·科普柯压缩机过滤器堵塞现象的预测中，准确度为70%左右，而在中央处理单元值不超过一分钟的情况下，准确度为90%左右。

{"title":"Integration of future maintenance actions in the prediction parameters of the ATLAS COPCO ZR 200 compressor","authors":"Agnes Virginie Tjahe, B. M. Mtopi Fotso, M. Fogué, N. Zerhouni","doi":"10.36001/ijphm.2021.v12i2.2916","DOIUrl":"https://doi.org/10.36001/ijphm.2021.v12i2.2916","url":null,"abstract":"The prediction of several failure modes of an industrial equipment requires the development of prediction systems with several interdependent parameters. The integration of future maintenance actions with this type of prediction system is a major asset for maintenance decision making. This is even more relevant in the event that after having predicted the future occurrence of several failure modes, the maintenance department does not have the necessary resources to correct all the predicted failure modes at once. In this case it becomes necessary to know how much longer the equipment will work if future partial maintenance actions that do not correct all failure modes are implemented. It is to contribute to the resolution of this problem that we propose an architecture integrating the future maintenance actions to the prediction of several interdependent parameters. This architecture is based on the association of Proportional Integral Derivative regulators to Neuro-Fuzzy systems taking into account the four previous instants to predict the next instant. An application is made with accuracies of the order of 70% for the prediction of the phenomena of fouling of the coolers and of the order of 90% for the prediction of the phenomena of clogging of the filters of the ATLAS COPCO compressor, this with Central Processing Unit values not exceeding one minute.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"70085943","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reaction Wheels Fault Isolation Onboard 3-Axis Controlled Satel-lite using Enhanced Random Forest with Multidomain Features 基于多域特征增强随机森林的三轴控制卫星反作用轮故障隔离

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2021-01-01 DOI: 10.36001/ijphm.2021.v12i2.3078

Afshin Rahimi, Mofiyinoluwa O. Folami

As the number of satellite launches increases each year, it is only natural that an interest in the safety and monitoring of these systems would increase as well. However, as a system becomes more complex, generating a high-fidelity model that accurately describes the system becomes complicated. Therefore, imploring a data-driven method can provide to be more beneficial for such applications. This research proposes a novel approach for data-driven machine learning techniques on the detection and isolation of nonlinear systems, with a case-study for an in-orbit closed loop-controlled satellite with reaction wheels as actuators. High-fidelity models of the 3-axis controlled satellite are employed to generate data for both nominal and faulty conditions of the reaction wheels. The generated simulation data is used as input for the isolation method, after which the data is pre-processed through feature extraction from a temporal, statistical, and spectral domain. The pre-processed features are then fed into various machine learning classifiers. Isolation results are validated with cross-validation, and model parameters are tuned using hyperparameter optimization. To validate the robustness of the proposed method, it is tested on three characterized datasets and three reaction wheel configurations, including standard four-wheel, three-orthogonal, and pyramid. The results prove superior performance isolation accuracy for the system under study compared to previous studies using alternative methods (Rahimi & Saadat, 2019, 2020).

随着每年卫星发射数量的增加，对这些系统的安全和监测的兴趣自然也会增加。然而，随着系统变得越来越复杂，生成一个准确描述系统的高保真模型也变得越来越复杂。因此，采用数据驱动的方法可以为这样的应用程序提供更多的好处。本研究提出了一种用于非线性系统检测和隔离的数据驱动机器学习技术的新方法，并以反作用轮作为执行器的在轨闭环控制卫星为例进行了研究。利用三轴控制卫星的高保真模型生成反作用轮正常状态和故障状态的数据。生成的仿真数据用作隔离方法的输入，然后通过从时间域、统计域和谱域提取特征对数据进行预处理。然后将预处理的特征输入到各种机器学习分类器中。通过交叉验证验证隔离结果，并使用超参数优化调整模型参数。为了验证该方法的鲁棒性，在三个特征数据集和三种反应轮构型(包括标准四轮、三正交和金字塔)上进行了测试。结果证明，与之前使用替代方法的研究相比，所研究系统的性能隔离精度更高(Rahimi & Saadat, 2019, 2020)。

{"title":"Reaction Wheels Fault Isolation Onboard 3-Axis Controlled Satel-lite using Enhanced Random Forest with Multidomain Features","authors":"Afshin Rahimi, Mofiyinoluwa O. Folami","doi":"10.36001/ijphm.2021.v12i2.3078","DOIUrl":"https://doi.org/10.36001/ijphm.2021.v12i2.3078","url":null,"abstract":"As the number of satellite launches increases each year, it is only natural that an interest in the safety and monitoring of these systems would increase as well. However, as a system becomes more complex, generating a high-fidelity model that accurately describes the system becomes complicated. Therefore, imploring a data-driven method can provide to be more beneficial for such applications. This research proposes a novel approach for data-driven machine learning techniques on the detection and isolation of nonlinear systems, with a case-study for an in-orbit closed loop-controlled satellite with reaction wheels as actuators. High-fidelity models of the 3-axis controlled satellite are employed to generate data for both nominal and faulty conditions of the reaction wheels. The generated simulation data is used as input for the isolation method, after which the data is pre-processed through feature extraction from a temporal, statistical, and spectral domain. The pre-processed features are then fed into various machine learning classifiers. Isolation results are validated with cross-validation, and model parameters are tuned using hyperparameter optimization. To validate the robustness of the proposed method, it is tested on three characterized datasets and three reaction wheel configurations, including standard four-wheel, three-orthogonal, and pyramid. The results prove superior performance isolation accuracy for the system under study compared to previous studies using alternative methods (Rahimi & Saadat, 2019, 2020).","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"70086218","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Maintenance Costs and Advanced Maintenance Techniques in Manufacturing Machinery: Survey and Analysis. 制造机械维修成本与先进维修技术:调查与分析。

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2021-01-01 DOI: 10.36001/ijphm.2021.v12i1.2883

Douglas Thomas, Brian Weiss

The costs/benefits associated with investing in advanced maintenance techniques is not well understood. Using data collected from manufacturers, we estimate the national losses due to inadequate maintenance and make comparisons between those that rely on reactive maintenance, preventive maintenance, and predictive maintenance. The total annual costs/losses associated with maintenance is estimated to be on average $222.0 billion, as estimated using Monte Carlo analysis. Respondents were categorized into three groups and compared. The first group is the top 50 % of respondents that rely on reactive maintenance, measured in expenditures. The remaining respondents were split in half based on their reliance on predictive maintenance. The top 50 % of respondents in using reactive maintenance, measured in expenditures, compared to the other respondents suggests that there are substantial benefits of moving away from reactive maintenance toward preventive and/or predictive maintenance. The bottom 50 %, which relies more heavily on predictive and preventive maintenance, had 52.7 % less unplanned downtime and 78.5 % less defects. The comparison between the smaller two groups, which rely more heavily on preventive and predictive maintenance, shows that there is 18.5 % less unplanned downtime and 87.3 % less defects for those that rely more on predictive than preventive.

投资于高级维护技术的成本/收益还没有得到很好的理解。利用从制造商那里收集的数据，我们估计了由于维护不足造成的全国损失，并比较了依赖于被动维护、预防性维护和预测性维护的损失。根据蒙特卡罗分析，与维护相关的年度总成本/损失估计平均为2220亿美元。受访者被分为三组并进行比较。第一组是依靠被动维护(以支出衡量)的前50%的受访者。其余的受访者根据对预测性维护的依赖程度分成了两派。与其他受访者相比，使用被动维护的前50%的受访者(以支出衡量)表明，从被动维护转向预防性和/或预测性维护有实质性的好处。最低的50%更依赖于预测性和预防性维护，其计划外停机时间减少了52.7%，缺陷减少了78.5%。较小的两组之间的比较，更依赖于预防性和预见性维护，显示有18.5%的计划外停机时间减少，而那些更依赖于预测性而不是预防性的缺陷减少了87.3%。

{"title":"Maintenance Costs and Advanced Maintenance Techniques in Manufacturing Machinery: Survey and Analysis.","authors":"Douglas Thomas, Brian Weiss","doi":"10.36001/ijphm.2021.v12i1.2883","DOIUrl":"https://doi.org/10.36001/ijphm.2021.v12i1.2883","url":null,"abstract":"The costs/benefits associated with investing in advanced maintenance techniques is not well understood. Using data collected from manufacturers, we estimate the national losses due to inadequate maintenance and make comparisons between those that rely on reactive maintenance, preventive maintenance, and predictive maintenance. The total annual costs/losses associated with maintenance is estimated to be on average $222.0 billion, as estimated using Monte Carlo analysis. Respondents were categorized into three groups and compared. The first group is the top 50 % of respondents that rely on reactive maintenance, measured in expenditures. The remaining respondents were split in half based on their reliance on predictive maintenance. The top 50 % of respondents in using reactive maintenance, measured in expenditures, compared to the other respondents suggests that there are substantial benefits of moving away from reactive maintenance toward preventive and/or predictive maintenance. The bottom 50 %, which relies more heavily on predictive and preventive maintenance, had 52.7 % less unplanned downtime and 78.5 % less defects. The comparison between the smaller two groups, which rely more heavily on preventive and predictive maintenance, shows that there is 18.5 % less unplanned downtime and 87.3 % less defects for those that rely more on predictive than preventive.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9890517/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10715531","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Measurement and Evaluation for Prognostics and Health Management (PHM) for Manufacturing Operations - Summary of an Interactive Workshop Highlighting PHM Trends. 生产运营诊断和健康管理（PHM）的测量与评估 - 突出 PHM 趋势的互动研讨会摘要。

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2021-01-01 DOI: 10.36001/ijphm.2021.v12i1.2653

Brian A Weiss, Michael P Brundage

Personnel from the National Institute of Standards and Technology (NIST) organized and led a Measurement and Evaluation for Prognostics and Health Management for Manufacturing Operations (ME4PHM) workshop at the 2019 Annual Conference of the Prognostics and Health Management Society held on September 23^rd, 2019 in Scottsdale, Arizona. This event featured panel presentations and discussions from industry, government, and academic participants who are focused in advancing monitoring, diagnostic, and prognostic (collectively known as prognostic and health management (PHM)) capabilities within manufacturing operations. The participants represented a diverse cross-section of technology developers, integrators, end-users/manufacturers (from small to large), and researchers. These contributors discussed 1) what works well, 2) common challenges that need to be addressed, 3) where the community's priorities should be focused, and 4) how PHM technological adoption can be sped in a cost-effective manner. This report summarizes the workshop and offers lessons learned regarding the current state of PHM. Based upon the discussions, recommended next steps to advance this technological domain are also presented.

2019年9月23日，在亚利桑那州斯科茨代尔举行的2019年预报与健康管理学会年会上，美国国家标准与技术研究院（NIST）的人员组织并主持了制造运营预报与健康管理测量与评估（ME4PHM）研讨会。本次活动的特色是由专注于推进制造运营中的监测、诊断和预后（统称为预后和健康管理 (PHM)）能力的行业、政府和学术界人士进行小组发言和讨论。与会者代表了技术开发人员、集成商、最终用户/制造商（从小型到大型）以及研究人员等不同的跨部门人员。这些参与者讨论了 1) 哪些技术行之有效，2) 需要应对的共同挑战，3) 社区的优先重点，以及 4) 如何以具有成本效益的方式加快 PHM 技术的采用。本报告对研讨会进行了总结，并提供了有关 PHM 现状的经验教训。在讨论的基础上，还提出了推进该技术领域的下一步建议。

{"title":"Measurement and Evaluation for Prognostics and Health Management (PHM) for Manufacturing Operations - Summary of an Interactive Workshop Highlighting PHM Trends.","authors":"Brian A Weiss, Michael P Brundage","doi":"10.36001/ijphm.2021.v12i1.2653","DOIUrl":"10.36001/ijphm.2021.v12i1.2653","url":null,"abstract":"Personnel from the National Institute of Standards and Technology (NIST) organized and led a Measurement and Evaluation for Prognostics and Health Management for Manufacturing Operations (ME4PHM) workshop at the 2019 Annual Conference of the Prognostics and Health Management Society held on September 23rd, 2019 in Scottsdale, Arizona. This event featured panel presentations and discussions from industry, government, and academic participants who are focused in advancing monitoring, diagnostic, and prognostic (collectively known as prognostic and health management (PHM)) capabilities within manufacturing operations. The participants represented a diverse cross-section of technology developers, integrators, end-users/manufacturers (from small to large), and researchers. These contributors discussed 1) what works well, 2) common challenges that need to be addressed, 3) where the community's priorities should be focused, and 4) how PHM technological adoption can be sped in a cost-effective manner. This report summarizes the workshop and offers lessons learned regarding the current state of PHM. Based upon the discussions, recommended next steps to advance this technological domain are also presented.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ftp.ncbi.nlm.nih.gov/pub/pmc/oa_pdf/ed/a6/nihms-1729079.PMC8381745.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39355074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Review of Techniques to Mitigate Jamming in Electromechanical Actuators for Safety Critical Applications 缓解安全关键应用机电执行器干扰的技术综述

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2020-12-20 DOI: 10.36001/IJPHM.2018.V9I3.2749

Yameen M. Hussain, S. Burrow, Leigh Henson, P. Keogh

This paper presents a review of techniques to mitigate jamming in Electromechanical Actuators (EMA) for safety critical applications in aerospace. Published progress to date is evaluated, with the remaining challenges highlighted. Through the use of Hierarchical Process Modelling (HPM), two key approaches to mitigate jamming were identified: (1) Fault Diagnostics (FD) and (2) Fault tolerant design. The development of a fault tolerant EMA system is currently at an early stage for implementation within safety critical systems due to the increased complexity of such systems (for example the anti-jamming system may require FD functionality itself). Challenges also exist for FD approaches particularly in achieving a robust means of fault detection. It is proposed that a hybrid FD approach, using a combination of model based and data-driven techniques to predict the onset of jamming, would be beneficial in capturing the discrepancies between the predicted and observed behaviour used to isolate and identify faults. Furthermore, several aspects of modelling and of data-driven methodologies for FD in the literature omit potentially important behaviours, and recommendations are made to improve upon this. For example, the simulation of faults in test stand analysis and the fidelity modelling of the motor and mechanical components are key areas to develop.

本文综述了在航空航天安全关键应用中减轻机电执行器（EMA）干扰的技术。对迄今为止公布的进展情况进行了评估，并强调了剩余的挑战。通过使用分层过程建模（HPM），确定了两种减轻干扰的关键方法：（1）故障诊断（FD）和（2）容错设计。由于这种系统的复杂性增加，容错EMA系统的开发目前处于在安全关键系统中实施的早期阶段（例如，抗干扰系统本身可能需要FD功能）。FD方法也存在挑战，特别是在实现稳健的故障检测手段方面。提出了一种混合FD方法，将基于模型的技术和数据驱动的技术相结合来预测干扰的发生，这将有助于捕捉用于隔离和识别故障的预测和观察行为之间的差异。此外，文献中FD建模和数据驱动方法的几个方面省略了潜在的重要行为，并提出了改进建议。例如，试验台分析中的故障模拟以及电机和机械部件的保真度建模是需要开发的关键领域。

{"title":"A Review of Techniques to Mitigate Jamming in Electromechanical Actuators for Safety Critical Applications","authors":"Yameen M. Hussain, S. Burrow, Leigh Henson, P. Keogh","doi":"10.36001/IJPHM.2018.V9I3.2749","DOIUrl":"https://doi.org/10.36001/IJPHM.2018.V9I3.2749","url":null,"abstract":"This paper presents a review of techniques to mitigate jamming in Electromechanical Actuators (EMA) for safety critical applications in aerospace. Published progress to date is evaluated, with the remaining challenges highlighted. Through the use of Hierarchical Process Modelling (HPM), two key approaches to mitigate jamming were identified: (1) Fault Diagnostics (FD) and (2) Fault tolerant design. The development of a fault tolerant EMA system is currently at an early stage for implementation within safety critical systems due to the increased complexity of such systems (for example the anti-jamming system may require FD functionality itself). Challenges also exist for FD approaches particularly in achieving a robust means of fault detection. It is proposed that a hybrid FD approach, using a combination of model based and data-driven techniques to predict the onset of jamming, would be beneficial in capturing the discrepancies between the predicted and observed behaviour used to isolate and identify faults. Furthermore, several aspects of modelling and of data-driven methodologies for FD in the literature omit potentially important behaviours, and recommendations are made to improve upon this. For example, the simulation of faults in test stand analysis and the fidelity modelling of the motor and mechanical components are key areas to develop.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2020-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48587264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 16

Non-Contact Quantification of Longitudinal and Circumferential Defects in Pipes using the Surface Response to Excitation (SuRE) Method 用表面激励响应（SuRE）方法对管道中纵向和周向缺陷进行非接触定量

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2020-12-16 DOI: 10.36001/IJPHM.2017.V8I2.2600

Amin Baghalian, Shervin Tashakori, V. Senyurek, D. McDaniel, H. Fekrmandi, I. Tansel

Rapid screening and monitoring of hollow cylindrical structures using active guided-waves based structural health monitoring (SHM) techniques are important in chemical, petro-chemical, oil and gas industries. Successful implementation of the majority of these techniques in the SHM of pipes depends on the identification of the appropriate guided-waves modes and their frequencies for each application. The highly dispersive nature of the guided-waves and presence of multi modes at each frequency makes the mode selection and the interpretation of signals a challenging task. The surface response to excitation (SuRE) method was developed to detect the defects and loading condition changes on plates with minimum dependence on the excitation of particular modes at certain frequencies. In the present study, the SuRE method is proposed for quantification of longitudinal and circumferential defects, with varying severities, as common examples of axisymmetric and nonaxisymmetric defects in pipes. The results indicate that the SuRE method can be used effectively for damage quantification in hollow cylinders.

使用基于主动导波的结构健康监测（SHM）技术对空心圆柱结构进行快速筛选和监测在化学、石油化工、石油和天然气行业具有重要意义。这些技术中的大多数在管道SHM中的成功实施取决于每种应用的适当导波模式及其频率的识别。导波的高度色散特性和每个频率下多模式的存在使得模式选择和信号解释成为一项具有挑战性的任务。开发了表面激振响应（SuRE）方法，以检测板上的缺陷和载荷条件变化，并使其在特定频率下对特定模式的激振具有最小的依赖性。在本研究中，提出了SuRE方法来量化不同严重程度的纵向和周向缺陷，作为管道中轴对称和非轴对称缺陷的常见例子。结果表明，SuRE方法可以有效地用于空心圆柱体的损伤定量。

{"title":"Non-Contact Quantification of Longitudinal and Circumferential Defects in Pipes using the Surface Response to Excitation (SuRE) Method","authors":"Amin Baghalian, Shervin Tashakori, V. Senyurek, D. McDaniel, H. Fekrmandi, I. Tansel","doi":"10.36001/IJPHM.2017.V8I2.2600","DOIUrl":"https://doi.org/10.36001/IJPHM.2017.V8I2.2600","url":null,"abstract":"Rapid screening and monitoring of hollow cylindrical structures using active guided-waves based structural health monitoring (SHM) techniques are important in chemical, petro-chemical, oil and gas industries. Successful implementation of the majority of these techniques in the SHM of pipes depends on the identification of the appropriate guided-waves modes and their frequencies for each application. The highly dispersive nature of the guided-waves and presence of multi modes at each frequency makes the mode selection and the interpretation of signals a challenging task. The surface response to excitation (SuRE) method was developed to detect the defects and loading condition changes on plates with minimum dependence on the excitation of particular modes at certain frequencies. In the present study, the SuRE method is proposed for quantification of longitudinal and circumferential defects, with varying severities, as common examples of axisymmetric and nonaxisymmetric defects in pipes. The results indicate that the SuRE method can be used effectively for damage quantification in hollow cylinders.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49508487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 16

Gas Turbine Engine Condition Monitoring Using Gaussian Mixture and Hidden Markov Models 基于高斯混合和隐马尔可夫模型的燃气轮机状态监测

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2020-11-20 DOI: 10.36001/IJPHM.2018.V9I2.2734

William R. Jacobs, H. Edwards, Ping Li, V. Kadirkamanathan, A. Mills

This paper investigates the problem of condition monitoring of complex dynamic systems, specifically the detection, localisation and quantification of transient faults. A data driven approach is developed for fault detection where the multidimensional data sequence is viewed as a stochastic process whose behaviour can be described by a hidden Markov model with two hidden states — i.e. ‘healthy / nominal’ and ‘unhealthy / faulty’. The fault detection is performed by first clustering in a multidimensional data space to define normal operating behaviour using a Gaussian-Uniform mixture model. The health status of the system at each data point is then determined by evaluating the posterior probabilities of the hidden states of a hidden Markov model. This allows the temporal relationship between sequential data points to be incorporated into the fault detection scheme. The proposed scheme is robust to noise and requires minimal tuning. A real-world case study is performed based on the detection of transient faults in the variable stator vane actuator of a gas turbine engine to demonstrate the successful application of the scheme. The results are used to demonstrate the generation of simple and easily interpretable analytics that can be used to monitor the evolution of the fault across time.

本文研究了复杂动态系统的状态监测问题，特别是瞬态故障的检测、定位和量化。开发了一种用于故障检测的数据驱动方法，其中多维数据序列被视为一个随机过程，其行为可以通过具有两个隐藏状态的隐马尔可夫模型来描述，即“健康/标称”和“不健康/故障”。故障检测是通过首先在多维数据空间中聚类来执行的，以使用高斯均匀混合模型来定义正常操作行为。然后通过评估隐马尔可夫模型的隐藏状态的后验概率来确定系统在每个数据点的健康状态。这允许将顺序数据点之间的时间关系结合到故障检测方案中。所提出的方案对噪声是鲁棒的，并且需要最小的调谐。基于燃气轮机发动机可变定子叶片执行器瞬态故障的检测，进行了真实世界的案例研究，以证明该方案的成功应用。结果用于演示生成简单且易于解释的分析，可用于监测故障随时间的演变。

{"title":"Gas Turbine Engine Condition Monitoring Using Gaussian Mixture and Hidden Markov Models","authors":"William R. Jacobs, H. Edwards, Ping Li, V. Kadirkamanathan, A. Mills","doi":"10.36001/IJPHM.2018.V9I2.2734","DOIUrl":"https://doi.org/10.36001/IJPHM.2018.V9I2.2734","url":null,"abstract":"This paper investigates the problem of condition monitoring of complex dynamic systems, specifically the detection, localisation and quantification of transient faults. A data driven approach is developed for fault detection where the multidimensional data sequence is viewed as a stochastic process whose behaviour can be described by a hidden Markov model with two hidden states — i.e. ‘healthy / nominal’ and ‘unhealthy / faulty’. The fault detection is performed by first clustering in a multidimensional data space to define normal operating behaviour using a Gaussian-Uniform mixture model. The health status of the system at each data point is then determined by evaluating the posterior probabilities of the hidden states of a hidden Markov model. This allows the temporal relationship between sequential data points to be incorporated into the fault detection scheme. The proposed scheme is robust to noise and requires minimal tuning. A real-world case study is performed based on the detection of transient faults in the variable stator vane actuator of a gas turbine engine to demonstrate the successful application of the scheme. The results are used to demonstrate the generation of simple and easily interpretable analytics that can be used to monitor the evolution of the fault across time.","PeriodicalId":42100,"journal":{"name":"International Journal of Prognostics and Health Management","volume":null,"pages":null},"PeriodicalIF":2.1,"publicationDate":"2020-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42451927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

PHM Survey : Implementation of Signal Processing Methods for Monitoring Bearings and Gearboxes PHM综述：轴承和齿轮箱监测信号处理方法的实现

IF 2.1 Q2 Engineering

International Journal of Prognostics and Health Management

Pub Date : 2020-11-20 DOI: 10.36001/IJPHM.2018.V9I2.2736

A. Soualhi, Y. Hawwari, K. Medjaher, G. Clerc, Razik Hubert, F. Guillet

The reliability and safety of industrial equipments are one of the main objectives of companies to remain competitive in sectors that are more and more exigent in terms of cost and security. Thus, an unexpected shutdown can lead to physical injury as well as economic consequences. This paper aims to show the emergence of the Prognostics and Health Management (PHM) concept in the industry and to describe how it comes to complement the different maintenance strategies. It describes the benefits to be expected by the implementation of signal processing, diagnostic and prognostic methods in health-monitoring. More specifically, this paper provides a state of the art of existing signal processing techniques that can be used in the PHM strategy. This paper allows showing the diversity of possible techniques and choosing among them the one that will define a framework for industrials to monitor sensitive components like bearings and gearboxes.

工业设备的可靠性和安全性是公司在成本和安全性方面越来越紧迫的行业中保持竞争力的主要目标之一。因此，意外关闭可能会导致人身伤害和经济后果。本文旨在展示行业中出现的预测和健康管理(PHM)概念，并描述它如何补充不同的维护策略。它描述了在健康监测中实施信号处理、诊断和预后方法所预期的好处。更具体地说，本文提供了可用于PHM策略的现有信号处理技术的最新状态。本文允许展示各种可能的技术，并从中选择一种技术，为工业监控轴承和齿轮箱等敏感部件定义一个框架。

引用次数: 11