Thesis worker - Human Senses Mimicking: Audio Anomaly Detection i Göteborg

The best place to work in the Global Automotive Industry. Join us on this exciting journey into the future, we want to hear from you!

Om tjänsten

Thesis Worker at Volvo Cars

Welcome to explore the world of Volvo Cars by writing your thesis with us! As a thesis worker in our organization you are supported by a supervisor who follows you during your project. All thesis projects are arranged in business critical areas and therefore you will be able to contribute to our company purpose – providing freedom to move in a safe, sustainable and personal way – from day one! 

 

 

Background
Comfort is an increasingly important aspect of a car and modern vehicles are designed to be noiseless and give high quality audio experiences. Factors such as road types and tires can affect interior noise levels. There can also be specific things such as loose panels or mechanical faults that can induce unwanted noises. For humans, these unwanted noises are generally easy to distinguish from normal noise and trained mechanic might even determine the source of the fault from sound alone. As cars become more intelligent and are equipped with more advanced active noise cancellation, they will also need to be better able to detect these noises themselves. This thesis will investigate methods for audio analysis and detection of anomalous sounds, to replicate this human capability in software.


Available Project – Human Senses Mimicking: Audio Anomaly Detection
This thesis will take part at the Vehicle Data & Diagnostics department at Volvo Cars, and look into methodologies for profiling and analysing in-cabin sound with the purpose of better detecting unwanted noise that needs to be corrected, but also for improved noise cancellation. There are multiple types of sounds and in order to be able to distinguish or classify these sounds, the sound needs to be described by the correct features and characteristics. Therefore, this thesis will look into state of the art methodologies for profiling and processing sound, with a specific focus on what the discriminant feature space should look like for optimal performance. For the right profile it could also include a review of suitable modelling and anomaly detection algorithms.

 

Main research question: What are suitable methods for profiling of audio-image of a car for anomaly detection?

•    Literature Review: Review of methods for characterising and describing sound of relevant qualia. 
•    Analysis: Evaluate descriptive power of said methods and suggest collection of features to use when profiling a sound-image.
•    Practical: Data collection to evaluate algorithms / sensors / features on, set up design of experiments to test hypotheses.
•    Practical: Evaluate methods on collection of car data, both for building understanding of normal case car in different scenarios as well as on fault-injected car.

 

Your contribution is our future
1-2 Master student(s) with a background in Applied Mathematics, Computer Science, Mechanical Design, Mechatronics, or similar education. Courses in Digital Signal Processing and Fourier Transform & Statistical Machine Learning will be useful. Should you have a co-worker in mind to work along with, don’t forget to include their name in the cover letter.

 

Duration
•    The duration of the Thesis is 20 weeks
•    The Thesis starts in January 2023 or earlier if possible.
•    30 ECTS (academic credits) if in agreement with your Thesis Advisor in University
•    This thesis is suitable for 1- 2 students
 
Be part of the change – apply today!
Selection will be ongoing during the application period, so do not hesitate to send in your application. Attach your CV and personal letter stating your interests within the given area and your thoughts and credentials.
Apply as soon as possible but no later than 2022-11-30!

 

Please note that due to GDPR, applications via email will not be accepted.

 

For questions about the thesis work, please contact Michael Wallgren Fjellander at michael.wallgren.fjellander@volvocars.com.
 

The thesis will be part of a portfolio of advanced engineering and research projects at Volvo Cars. For details and further questions, please feel free to reach out to us and we’ll take it over a cup of (virtual?) coffee!

 

We are Volvo Cars 
Volvo Cars is a company on a mission to bring traditional car manufacturing into a connected, sustainable and smart future. Since 1927, we've been known for our commitment to safety and for creating innovative cars that make life less complicated. In 2010, we decided to radically redefine our business, resulting in a totally new generation of cars and technology, as well as steady growth and record sales - and we're only getting started. By 2025, we aim to have yearly sales of 1.2 million cars, 50% of which will be electric vehicles and sold directly to customers through digital channels. We also intend to strengthen our position as a modern, progressive employer committed to diversity and gender and racial equality. We believe in the power of people. Join us and be part of Volvo Cars' transformation.

Publicerad den

29-11-2022

Extra information

Status
Öppen
Ort
Göteborg
Typ av kontrakt
Heltidsjobb (erfaren)
Typ av jobb
IT
Körkort önskas
Nej
Tillgång till bil önskas
Nej
Personligt brev krävs
Nej

Göteborg | IT | Heltidsjobb (erfaren)

Ansök nu

Dela jobbannonsen