国外文献 > 3.企业技术文献 > TIMKEN铁姆肯 >
关键词搜索：
| 标 题： |
An Industrial IoT Approach to Enable Remote Asset Health Monitoring for Short Line Railroad Operators
工业物联网方法用于实现短线路铁路运营商的远程资产健康监测 |
| 作 者： |
Wyatt Pena
Arsh Nadkarni
Jonathan Barket
Christopher Curti
Charles Miner
Gabriela Galvan |
| 关键词： |
Railroad [铁路]
Rolling stock [车辆]
Sensors [传感器]
Internet-of-Things (IoT) [物联网（IoT）]
Condition-based maintenance (CBM) [基于状态的维护（CBM）]
Prognostic health management (PHM) [预测性健康管理（PHM）]
Near real-time monitoring [近乎实时监控]
Vibration analysis [振动分析]
Remote asset/Fleet health management [远程资产/车队健康管理] |
| 出版年： |
2024 |
| 文集名： |
2024 IEEE International Conference on Prognostics and Health Management (ICPHM 2024)
2024年IEEE国际预测与健康管理会议（ICPHM 2024） |
| 会议名： |
2024 IEEE International Conference on Prognostics and Health Management (ICPHM 2024)
2024年IEEE国际预测与健康管理会议（ICPHM 2024） |
| 届 次： |
|
| 摘 要： |
This paper presents findings from a comprehensive two-part industrial case study focused on remote asset health monitoring and diagnostics in the railroad industry. The case study was carried out through a multiparty collaboration project between Ridgetop Group Inc. (Ridgetop), Reading and Blue Mountain Northern (RBMN) Railroad, and Innovative Operations Technology LLC in Port Clinton, PA. The first phase of the study, spanning March 2023 to August 2023, involved field testing Ridgetop's original Sentinel Motion Development Kit (SMDK). This kit comprises a wireless network of customized smart sensors that are mounted on Timken bearing end caps and transmit critical vibration and temperature data to a cellular-connected gateway system. The Linux-based gateway hosts Ridgetop's Sentinel MotionView software package for data acquisition, analysis, and sensor-gateway management. Results from this initial phase guided the research team in optimizing the custom sensor hardware design and it led to the development of new software analytics for near real-time monitoring and diagnosis of critical faults and anomalies associated with bearings, wheels, and track conditions. Encouraged by these results, Ridgetop undertook a redesign of the modular SMDK technology elements to align more closely with the IEEE 1856-2017 PHM Standard Framework for Prognostics and Health Management of Electronic Systems. The results from the second phase, spanning September 2023 to April 2024, details Ridgetop's completion of the hardware, firmware, and software redesign process as a means to realize the following eight functional blocks outlined in the IEEE 1856-2017 standard; 1) Sensors (S), 2) Data Acquisition (DA), 3) Data Manipulation (DM), 4) State Detection (SD), 5) Health Assessment (HA), 6) Prognostic Assessment (PA), 7) Advisory Generation (AG), and 8) Health Management (HM).
本文介绍了一项针对铁路行业远程资产健康监测与诊断的综合性两阶段工业案例研究结果。该案例研究由Ridgetop Group Inc.（Ridgetop）、Reading和Blue Mountain Northern（RBMN）铁路公司，以及位于宾夕法尼亚州克林顿港的Innovative Operations Technology LLC共同合作开展。研究的第一阶段于2023年3月至8月进行，期间对Ridgetop自主研发的Sentinel Motion Development Kit（SMDK）进行了现场测试。该套件包含一组定制化的智能传感器，安装在Timken轴承端盖上，并将关键的振动和温度数据传输至一个连接蜂窝网络的网关系统。基于Linux的网关系统运行着Ridgetop的Sentinel MotionView软件包，用于数据采集、分析以及传感器与网关的管理。第一阶段的研究成果指导了研究团队优化定制化传感器硬件设计，并推动开发出新的软件分析工具，实现对轴承、车轮及轨道状态相关关键故障和异常的近实时监测与诊断。受这些成果的鼓舞，Ridgetop对模块化SMDK技术组件进行了重新设计，使其更紧密地符合IEEE 1856-2017标准中关于电子系统预测性维护与健康管理的标准框架。第二阶段工作时间为2023年9月至2024年4月，详细记录了Ridgetop完成硬件、固件和软件重设计的过程，旨在实现IEEE 1856-2017标准中所列出的以下八个功能模块：1) 传感器（S），2) 数据采集（DA），3) 数据处理（DM），4) 状态检测（SD），5) 健康评估（HA），6) 预测评估（PA），7) 咨询生成（AG），8) 健康管理（HM）。 |
| 中文内容为网络AI翻译，专业术语未必准确，仅供参考。 |
京公网安备 11010202009788