A Conceptual Framework for the Design and Development of Automated Online Condition Monitoring System for Elevators (AOCMSE) Using IoT

2019 ◽  
pp. 189-207
Author(s):  
M. S. Starvin ◽  
A. Sherly Alphonse
Keyword(s):  
Conceptual Framework ◽  
Monitoring System ◽  
Condition Monitoring ◽  
Principal Component ◽  
Design And Development ◽  
Vibration Data ◽  
Vibration Sensors ◽  
Traction Motors ◽  
Condition Monitoring System ◽  
Learning Machine

The reliability of an elevator system in a smart city is of great importance. This chapter develops a conceptual framework for the design and development of an automated online condition monitoring system for elevators (AOCMSE) using IoT techniques to avoid failures. The elevators are powered by the traction motors. Therefore, by placing vibration sensors at various locations within the traction motor, the vibration data can be acquired and converted to 2D grayscale images. Then, maximum response-based directional texture pattern (MRDTP) can be applied to those images which are an advanced method of feature extraction. The feature vectors can also be reduced in dimension using principal component analysis (PCA) and then given to extreme learning machine (ELM) for the classification of the faults to five categories. Thus, the failure of elevators and the consequences can be prevented by sending this detected fault information to the maintenance team.

scholarly journals Train Type Identification at S&C

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Martina Kratochvílová ◽  
Jan Podroužek ◽  
Jiří Apeltauer ◽  
Ivan Vukušič ◽  
Otto Plášek
Keyword(s):  
Machine Learning ◽  
Monitoring System ◽  
Condition Monitoring ◽  
Dynamical Response ◽  
Vibration Data ◽  
Suitable Tool ◽  
Acceleration Data ◽  
Condition Monitoring System

The presented paper concerns the development of condition monitoring system for railroad switches and crossings that utilizes vibration data. Successful utilization of such system requires a robust and efficient train type identification. Given the complex and unique dynamical response of any vehicle track interaction, the machine learning was chosen as a suitable tool. For design and validation of the system, real on-site acceleration data were used. The resulting theoretical and practical challenges are discussed.

scholarly journals Design and Development of Condition Monitoring System for Wind Turbines Based on Generator Output Voltages

2020 ◽  
Vol 32 (3) ◽  
pp. 895
Author(s):  
Rong-Mao Lee ◽  
Shih-Hsuan Hu ◽  
Cheng-Chi Wang ◽  
Tsung-Chia Chen ◽  
Jui-Hung Liu
Keyword(s):  
Monitoring System ◽  
Condition Monitoring ◽  
Wind Turbines ◽  
Design And Development ◽  
Condition Monitoring System ◽  
Generator Output

scholarly journals Automatic Threshold Setting and Its Uncertainty Quantification in Wind Turbine Condition Monitoring System

2020 ◽  
Vol 6 (4) ◽  
Author(s):  
Kun S. Marhadi ◽  
Georgios Alexandros Skrimpas
Keyword(s):  
Probability Distribution ◽  
Wind Turbine ◽  
Monitoring System ◽  
Condition Monitoring ◽  
Bootstrap Method ◽  
Operating Conditions ◽  
Vibration Data ◽  
Optimal Thresholds ◽  
Johnson Distribution ◽  
Condition Monitoring System

Setting optimal alarm thresholds in vibration based condition monitoring system is inherently difficult. There are no established thresholds for many vibration based measurements. Most of the time, the thresholds are set based on statistics of the collected data available. Often times the underlying probability distribution that describes the data is not known. Choosing an incorrect distribution to describe the data and then setting up thresholds based on the chosen distribution could result in sub-optimal thresholds. Moreover, in wind turbine applications the collected data available may not represent the whole operating conditions of a turbine, which results in uncertainty in the parameters of the fitted probability distribution and the thresholds calculated. In this study, Johnson, Normal, and Weibull distributions are investigated; which distribution can best fit vibration data collected from a period of time. False alarm rate resulted from using threshold determined from each distribution is used as a measure to determine which distribution is the most appropriate. This study shows that using Johnson distribution can eliminate testing or fitting various distributions to the data, and have more direct approach to obtain optimal thresholds. To quantify uncertainty in the thresholds due to limited data, implementations with bootstrap method and Bayesian inference are investigated.

Revenue Service Demonstration of On-Board Condition Monitoring System

2003 ◽  
Author(s):  
John Donelson ◽  
Wayne M. Zavis ◽  
David G. Toth ◽  
S. K. Punwani ◽  
Monique Ferguson Stewart ◽  
...  
Keyword(s):  
Monitoring System ◽  
Condition Monitoring ◽  
Rolling Stock ◽  
Prototype System ◽  
Vibration Sensors ◽  
Board Monitoring ◽  
Condition Monitoring System ◽  
Railroad Bearings ◽  
Railroad Bearing ◽  
Class F

The Office of Research and Development of the Federal Railroad Administration (FRA) is sponsoring a project to develop and demonstrate an on-board condition monitoring system for freight trains. The objective of the system is to improve railroad safety and efficiency through continuous monitoring of mechanical components in order to detect defects before they cause breakdowns and accidents. The project, which commenced in June 1999, is part of the Rolling Stock Program Element in FRA’s Five-Year Strategic Plan for Railroad Research, Development and Demonstrations [1]. Science Applications International Corporation (SAIC) and Wilcoxon Research (WR) designed and developed a prototype system in 2000. The prototype system was tested during the period Nov. 2000–Nov. 2001 on a vehicle provided by the Research and Tests Department at Norfolk Southern Corporation. A Revenue Service Demonstration is scheduled to commence in October 2003. The monitoring system will be installed on five coal hopper cars and tested in revenue service. Southern Company Service is providing the test cars. The train will operate on a Norfolk Southern line between a coalmine near Berry, AL and an electric power plant, located 35 miles southeast of Birmingham. The demonstration is scheduled to run for six months. The demonstration will showcase some of the latest technologies in wireless communications and railroad bearings. A tri-mode cell telephone will be used for data telemetry between the on-board monitoring system and a web-accessible database. The Timken Company has developed two innovative systems that will be deployed in the demonstration — a permanent magnet generator mounted inside a Class F railroad bearing and bearing health monitoring system featuring temperature and vibration sensors, a tachometer, a micro-controller and an RF transmitter mounted inside a Class F bearing.

Description of a Vibration Diagnostic Trending Approach for a Condition Monitoring System for the LM2500 Gas Turbine

1995 ◽  
Author(s):  
John J. Hartranft
Keyword(s):  
Gas Turbine ◽  
Monitoring System ◽  
Condition Monitoring ◽  
Technical Information ◽  
Diagnostic System ◽  
Vibration Monitoring ◽  
Engine Operation ◽  
Vibration Data ◽  
Marine Propulsion ◽  
Condition Monitoring System

In a gas turbine marine propulsion installation, especially a military type role, the design of an effective gas turbine vibration diagnostic system must provide both technical information for maintenance and operational risk assessment for continued engine operation. In order to fulfill these criteria, a vibration monitoring system must provide not only a feedback of measured vibration levels, it must also provide an interpretation of those levels. This paper describes a potential approach to trending LM2500 gas turbine generated vibration data for use in a condition monitoring system.

Sign in / Sign up

Export Citation Format

Share Document