Graduation/Internship: Transforming Data Into Asset Health Insights

Assignment

We are looking for an ambitious student to take on a challenging graduation assignment focused on enhancing our predictive maintenance services. The core objective of this assignment is to evaluate our predictive maintenance services automatically. This involves analyzing field and ticket data, which are crucial for accurate evaluation of our models.

However, one of the main challenges is that ticket data is often spread across various platforms and formats, making it unstructured and difficult to analyze. Your task will be to develop a method or tool to consolidate and structure this data, enabling more effective and automated evaluations of our predictive maintenance services.

Given the complexity of handling unstructured ticket data, Large Language Models (LLMs) offer a promising solution to streamline this process. By efficiently parsing and interpreting unstructured data, LLMs can significantly enhance our predictive maintenance services. Their advanced capabilities allow for the extraction of meaningful patterns and insights from disparate data sources, which in turn improves predictive accuracy and operational efficiency.

Department

The intern will work in the Digital Service Platform department, responsible for driving Vanderlande digital transformation through the creation of Digital Services. He or she will be working in the Predictive Maintenance team, a multidisciplinary, multicultural and distributed team focused on converting data into insights to drive and optimize Maintenance. The team has data science, data engineer, software development and frontend development capabilities.

The student will have ample support and access to the existing knowledge within the team. If the internship is successful, their work will be used by the team to improve and enlarge the existing product.

Your responsibilities

• The student will be trained on the loopsorter functioning, and will be provided a few data sets to choose from. The student is expected to:
• Interact with SMEs to fine-tune their loopsorter understanding and define potential of the chosen data set(s)
• Develop a model that based on the acquired data can provide insights on the loopsorter health
• Validate the model outcome (and possibly improve the model) with SMEs and end-users
• A successful internship will deliver a model that can be productized and integrated with the existing Predictive Maintenance solution

Your profile

• Data science and ML knowledge
• Python knowledge
• (Preferred) Familiarity with Azure and Databricks
• Mandatory enrolment in a Dutch Education System and resident of The Netherlands*

Contact

Do you recognize yourself in this challenging profile? And are you looking for an internship/graduation assignment in our organization? For more information, contact us by e-mail: internship@vanderlande.com