Master Thesis - Intelligent Sound Diagnostics
Göteborg, SE, 417 15
MSc Thesis proposal at Volvo Group
(60 ECTS credits/student, 40 weeks/student, two students)
Intelligent Sound Diagnostics
Background:
The heavy-duty vehicle industry is a vital component of global logistics, responsible for transporting goods across vast distances. However, the reliability of trucks is often compromised by the occurrence of unusual noises emanating from various components when they malfunction. These noises not only degrade the customer experience but also pose a significant risk of downtime, which can lead to substantial financial losses. To increase efficiency and reduce time for root cause analysis we would like to leverage the potential of AI technologies to expedite the diagnosis process and enhance the accuracy of service recommendations.
Objectives:
By automating the diagnosis of noise-related issues, we can increase efficiency and improve customer satisfaction.
For the master’s thesis, we would like to focus on the following specific objectives:
- Data Collection and Organization: The first objective is to gather and organize a comprehensive dataset of noise recordings associated with various vehicle components. This dataset will serve as the foundation for developing AI models capable of diagnosing component health based on noise characteristics.
- Noise Characteristic Analysis: The project will focus on analyzing and summarizing the noise characteristics associated with vehicle health. Understanding these characteristics is crucial for developing models that can accurately identify the source and type vehicle health issues.
- Development of ML/AI Models: We aim to establish multiple reliable machine learning (ML) and AI models to assess noise patterns from various angles. The ultimate goal is to pinpoint the root causes of vehicle health issues, thereby providing precise service recommendations.
Scope:
The scope of this project encompasses heavy duty vehicles produced by Volvo. If resources permit, the scope may be extended to other products within Volvo AB. The project will initially concentrate on specific components. However, the long-term goal is to expand the focus to include more components.
Technical Details:
The project will employ a range of signal processing techniques, machine learning strategies, and neural network models to achieve its objectives. Key technical aspects include:
- Signal Processing: Multiple advanced signal processing methods will be employed to extract meaningful features from noise recordings. These features are not only crucial knowledge in their own right but will also be utilized across various scenarios. If necessary, they will serve as inputs for the ML/AI models to achieve more accurate diagnostic results.
- Machine Learning Techniques: Various machine learning techniques will be applied to develop models that can classify noise patterns and predict associated root causes. Techniques such as supervised learning, unsupervised learning, and reinforcement learning may be utilized depending on the nature of the data and the specific requirements of the models.
- Neural Network Models: Neural networks, particularly deep learning models, will be employed to capture complex patterns in the noise data. These models are well-suited for handling large datasets and can provide high accuracy in fault diagnosis.
- Model Integration: The project will also focus on integrating the results from different models to arrive at the most suitable conclusions. This involves developing a framework for model fusion, where outputs from multiple models are combined to enhance the reliability and accuracy of the diagnosis.
Conclusion: By harnessing the power of AI and machine learning, this project aims to revolutionize the way truck health is diagnosed. The implementation of automated, intelligent diagnostic systems will not only reduce downtime but also improve the overall efficiency of service provision. As the project evolves, it will pave the way for more comprehensive and accurate diagnosis, ultimately enhancing the reliability and performance of trucks in the industry.
The Master of Science Thesis work will be performed at Volvo Group Trucks Technology, (Gothenburg, Sweden) and starts 15 September 2025 or after agreement.
Industry supervisors: Jin Zhou and Patrik Johansson at Volvo GTT
University supervisors: TBD
If you have any questions, please contact Janos Turcsany, Group Manager NVH & Climate, janos.turcsany@volvo.com
We value your data privacy and therefore do not accept applications via mail.
Who we are and what we believe in
We are committed to shaping the future landscape of efficient, safe, and sustainable transport solutions. Fulfilling our mission creates countless career opportunities for talents across the group’s leading brands and entities.
Applying to this job offers you the opportunity to join Volvo Group. Every day, you will be working with some of the sharpest and most creative brains in our field to be able to leave our society in better shape for the next generation. We are passionate about what we do, and we thrive on teamwork. We are almost 100,000 people united around the world by a culture of care, inclusiveness, and empowerment.
Group Trucks Technology are seeking talents to help design sustainable transportation solutions for the future. As part of our team, you’ll help us by engineering exciting next-gen technologies and contribute to projects that determine new, sustainable solutions. Bring your love of developing systems, working collaboratively, and your advanced skills to a place where you can make an impact. Join our design shift that leaves society in good shape for the next generation.