UROP Project

Acoustic Emission (AE) Signal Onset Detection for Enhancement of Machine Learning Algorithms



Jan Müller

Program Director UROP


+49 241 80-90299


Key Info

Basic Information

Project Offer-Number:
UROP International, RWTH UROP
Mineral Resources Engineering
Organisation unit:
RWTH Aachen University - Advanced Mining Technologies (AMT)
Language Skills:
English or German
Computer Skills:
Programming skills in Matlab or , Python or RStudio. Optional: experience with LabVIEW.
Prof. Dr.-Ing. K. Nienhaus


The Acoustic Emission Technology was investigated for condition monitoring, material flow characterization and fatigue testing at the institute for Advanced Mining Technologies. Pre-tests have already shown the potential of the application of this technology to the mining sector. With the help of advanced signal processing and/or machine learning algorithms, the aim is to provide even better test results. In order to achieve this, precise information of location and AE parameters are necessary. Within this UROP project, new methods for onset detection should be implemented and tested regarding the output of machine learning algorithms. We at AMT (Advanced Mining Technology) are committed to providing technologies and system solutions for harsh environments like in mining and heavy machinery construction. Resource efficiency, safety and social responsibility are our vision and mission. Our diverse team strives to always provide excellent and at the same time viable solutions.


- Develop scenarios for experiments - Implentation of onset detection methods for AE signals - Evaluate data recorded from different sensors - Adapt experiments and sensor settings - Optimize and analyze functionality of algorithms - Describe best practices - Implement and test your results together with team members on a test project


- Research oriented mindset - Strong problem solving skills - Experience in developing software in a team - Outstanding interpersonal skills - Basic knowledge of machine learning