Joshua Holstein

Background:

The landscape of modern manufacturing industries is witnessing an exponential increase in the volume of data generated by machinery. This data, albeit a rich resource, is underutilized when it comes to refining production processes. Traditional data analysis often zeroes in on singular features and, in the process, overlooks the complex relationships and correlations among these features. This oversight leads to missed opportunities for enhancing efficiency and more accurate defect detection. The introduction of sophisticated methodologies such as process mining and causal AI aims to decipher these hidden correlations and provide actionable insights.

Research Goal:

In association with Bayer AG, the objective of this thesis project is to utilize process mining techniques and causal AI for an in-depth analysis of machine-generated data in the manufacturing context. The aim is not merely to identify correlations between data features but to interpret and articulate these relationships in a way that is beneficial to domain experts. To achieve this, you will engage with industry professionals through interviews to understand their perspectives and needs concerning this kind of analysis. The insights gained will then be implemented in a Python environment for further evaluation and testing.

In the course of this thesis, you will:

- Apply your theoretical understanding to address real-world manufacturing problems

- Explore advanced techniques such as process mining and causal AI

- Collaborate closely with domain experts in the effort to enhance the efficiency and environmental sustainability of manufacturing processes

We invite applications from those who:

- Have a strong interest in machine learning and data analysis

- Are self-driven and goal-oriented, eager to address contemporary real-world problems, and motivated to contribute original ideas

- Are comfortable engaging with professionals, for instance, through interview studies

- Possess excellent English language skills, as the thesis will be written in English

Details:

Start: Immediately

Duration: 6 months

Location: Bayer AG, Remote or nearby Grenzach-Whylen

We promise a challenging research topic, attentive mentorship, and an environment that fosters both practical and theoretical skills. Interested candidates should send their CV, transcript of records, and a brief letter of motivation to Joshua.Holstein@kit.edu.