Model-Based Vibration Condition Monitoring for Fault Detection and Diagnostics in Large Hydrogenerators

2018 ◽  
pp. 105-119
Author(s):  
Geraldo Carvalho Brito ◽  
Roberto Dalledone Machado ◽  
Anselmo Chaves Neto
Keyword(s):  
Fault Detection ◽  
Condition Monitoring ◽  
Vibration Condition ◽  
Model Based

scholarly journals On Digital Twin Condition Monitoring Approach for Drivetrains in Marine Applications

2019 ◽  
Author(s):  
Sigrid S. Johansen ◽  
Amir R. Nejad
Keyword(s):  
Fault Detection ◽  
Condition Monitoring ◽  
Offshore Wind ◽  
Test Rig ◽  
Digital Twin ◽  
Model Based ◽  
Twin Model ◽  
Digital Twins ◽  
Fidelity Model

Abstract A digital twin is a virtual representation of a system containing all information available on site. This paper presents condition monitoring of drivetrains in marine power transmission systems through digital twin approach. A literature review regarding current operations concerning maintenance approaches in todays practices are covered. State-of-the-art fault detection in drivetrains is discussed, founded in condition monitoring, data-based schemes and model-based approaches, and the digital twin approach is introduced. It is debated that a model-based approach utilizing a digital twin could be recommended for fault detection of drivetrains. By employing a digital twin, fault detection would be extended to relatively highly diagnostic and predictive maintenance programme, and operation and maintenance costs could be reduced. A holistic model system approach is considered, and methodologies of digital twin design are covered. A physical-based model rather than a data based model is considered, however there are no clear answer whereas which type is beneficial. That case is mostly answered by the amount of data available. Designing the model introduces several pitfalls depending on the relevant system, and the advantages, disadvantages and appropriate applications are discussed. For a drivetrain it is found that multi-body simulation is advised for the creation of a digital twin model. A digital twin of a simple drivetrain test rig is made, and different modelling approaches were implemented to investigate levels of accuracy. Reference values were derived empirically by attaching sensors to the drivetrain during operation in the test rig. Modelling with a low fidelity model showed high accuracy, however it would lack several modules required for it to be called a digital twin. The higher fidelity model showed that finding the stiffness parameter proves challenging, due to high stiffness sensitivity as the experimental modelling demonstrates. Two industries that could have significant benefits from implementing digital twins are discussed; the offshore wind industry and shipping. Both have valuable assets, with reliability sensitive systems and high costs of downtime and maintenance. Regarding the shipping industry an industrial case study is done. Area of extra focus is operations of Ro-Ro (roll on-roll off) vessels. The vessels in the case study are managed by Wilhelmsen Ship Management and a discussion of the implementation of digital twins in this sector is comprised in this article.

scholarly journals Gaussian Mixture Model Based Classification Revisited: Application to the Bearing Fault Classification

2020 ◽  
Vol 66 (4) ◽  
pp. 215-226 ◽  
Author(s):  
Branislav Panić ◽  
Jernej Klemenc ◽  
Marko Nagode
Keyword(s):  
Fault Detection ◽  
Gaussian Mixture Model ◽  
Mixture Model ◽  
Condition Monitoring ◽  
Gaussian Mixture ◽  
Classification Method ◽  
Fault Classification ◽  
Classification Methods ◽  
Bearing Fault ◽  
Model Based

Condition monitoring and fault detection are nowadays popular topic. Different loads, enviroments etc. affect the components and systems differently and can induce the fault and faulty behaviour. Most of the approaches for the fault detection rely on the use of the good classification method. Gaussian mixture model based classification are stable and versatile methods which can be applied to a wide range of classification tasks. The main task is the estimation of the parameters in the Gaussian mixture model. Those can be estimated with various techniques. Therefore, the Gaussian mixture model based classification have different variants which can vary in performance. To test the performance of the Gaussian mixture model based classification variants and general usefulness of the Gaussian mixture model based classification for the fault detection, we have opted to use the bearing fault classification problem. Additionally, comparisons with other widely used non-parametric classification methods are made, such as support vector machines and neural networks. The performance of each classification method is evaluated by multiple repeated k-fold cross validation. From the results obtained, Gaussian mixture model based classification methods are shown to be competitive and efficient methods and usable in the field of fault detection and condition monitoring.

scholarly journals A new model-based approach for power plant Tube-ball mill condition monitoring and fault detection

2014 ◽  
Vol 80 ◽  
pp. 10-19 ◽  
Author(s):  
Shen Guo ◽  
Jihong Wang ◽  
Jianlin Wei ◽  
Paschalis Zachariades
Keyword(s):  
Power Plant ◽  
Fault Detection ◽  
Condition Monitoring ◽  
Ball Mill ◽  
New Model ◽  
Model Based

Signal-based and Model-based Wheel Fault Detection of Omni-directional Vehicle with Mecanum Wheel

2020 ◽  
Author(s):  
Peter I-Tsyuen Chang ◽  
Chih-Cheng Liu ◽  
Shih-Chia Fan Chiang ◽  
Chen-Yang Lan
Keyword(s):  
Fault Detection ◽  
Model Based ◽  
Mecanum Wheel

Model-based fault detection filter for Markovian jump linear systems applied to a control moment gyroscope

2021 ◽  
Vol 59 ◽  
pp. 99-108
Author(s):  
Leonardo de Paula Carvalho ◽  
Fabio Yukio Toriumi ◽  
Bruno Augusto Angélico ◽  
Oswaldo Luiz do Valle Costa
Keyword(s):  
Fault Detection ◽  
Linear Systems ◽  
Markovian Jump ◽  
Jump Linear Systems ◽  
Control Moment Gyroscope ◽  
Fault Detection Filter ◽  
Model Based ◽  
Control Moment ◽  
Markovian Jump Linear Systems ◽  
Detection Filter
Sign in / Sign up

Export Citation Format

Share Document