Seminar Predictive Maintenance
Seminar machine learning: Predictive Maintenance
The Seminar is available in Tucan right here.
You can download the Slide From the KickOff-Meeting here: kick-off.pdf
When and where?
The Meetings will take place on Wednesdays at 17.10h in Room E202.
13.05.2015
- Current status of machine prognostics in condition-based maintenance: a review - Joachim Brehmer
- Prognostics and Health Management of Electronics - Nicolina Wenzler
20.05.2015
27.05.2015
03.06.2015
17.06.2015
- Developing Data Mining Based Prognostic Models for CF-18 Aircraft - Maria Pelevina
- A Data-Driven Approach for Monitoring Blade Pitch Faults in Wind Turbines - Olexandr Savchuk
24.06.2015
- Machine Learning for Predictive Maintenance a Multiple Classifiers Approach - Elias Heftrig
- Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network - Jens Sperling
01.07.2015
08.07.2015
- Learning to predict train wheel failures - Markus Heinrich
- Optimal replacement under partial observations - Sarah Holschneider
Organisation
The topics for the talks will be assigned in the Kickoff-Meeting on April 22nd. For further questions feel free to send an email to ml-sem@ke.tu-darmstadt.de.
Content
In the course of this seminar we will try to get an overview on the current state of research in this domain. We will concentrate on recent papers published in workshops, journals, and conferences regarding predictive maintenance. The topics will be announced as soon as possible.
The students are expected to give a 30 minute talk on the material they are assigned, followed by 15 minutes of questions. The content of the talk should exceed the scope of the paper, and demonstrate that a thorough understanding of the material was achieved.
Topics
- Current status of machine prognostics in condition-based maintenance: a review
- Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network
- Improving Rail network velocity: A machine learning approach to predictive maintenance
- Application of support vector machine for equipment reliability forecasting
- Multi-sensor data fusion using support vector machines for motor fault detection
- Towards a Machine Learning Algorithm for Predicting Truck Compressor Failures Using logged vehicle data
- Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis
- Developing Data Mining Based Prognostic Models for CF-18 Aircraft
- Online monitoring and fault identification of mean shifts in bivariate processes using decision tree learning techniques
- Remaining Useful Life Estimation of Critical Components With Application to Bearings
- A Data-Driven Approach for Monitoring Blade Pitch Faults in Wind Turbines
- Learning to predict train wheel failures
- Comparison of prognostic algorithms for estimating remaining useful life of batteries
- Prognostics and Health Management of Electronics
- Continuous-Time Predictive-Maintenance Scheduling for a Deteriorating System
- Optimal replacement under partial observations
- Diagnostics and Prognostics Method for Analog Electronic Circuits
- An adaptive machine learning decision system for flexible predictive maintenance
- Data fusion data mining-based architecture for condition-based maintenance
- Development of smart sensors system for machine fault diagnosis
- Machine Learning for Predictive Maintenance a Multiple Classifiers Approach
- Bearing fault prognosis based on health state probability estimation
- Multi component fault diagnosis of rotational mechanical system based on decision tree and support vector machine
- Fault detection and diagnosis in process data using one-class support
- One-class support vector machines—an application in machine fault detection and classification
- Power wind mill fault detection via one-class v-SVM vibration signal analysis
Talks
The talks are expected to be accompanied by slides. In case you do not own a laptop, please send us the slides in advance, so that we can prepare and test the slides. The talk and the slides are allowed to be both english or german, but we strongly encourage the students to give the talk in english.
Grading
The slides, the presentation and the Q'n'A section of the talk will influence the overall grade. Furthermore, it is expected of the students to participate in the discussions. There is no need for a written verdict of the material.
Most importantly, the autonomous elaboration on the material will influence the grade. To achieve a grade in the 1.x range, the talk needs to exceed the contentual recitation of the given material and include own ideas, own experience or even demos. An exact recitation of the papers will lead to a grade in the 2.x range. A weak presentation and lack of engagement in the discussions may lead to a grade in the 3.x range, or worse.