About the Role:

Background and Scientific Context

Modern production sites feature extensive building management systems and historian systems, which continuously record operational, status, and measurement data from technical equipment. Particularly in regulated production environments, the early detection of persistent deviations, inefficient operating modes, and critical conditions is of high relevance, as these can impact technical availability, energy efficiency, operational stability, and quality-relevant environmental conditions.

The focus of this master's thesis is therefore the development and evaluation of an AI-based method for identifying chronically critical operating conditions using building management system time series data, with the aim of subsequently deriving optimization approaches to improve ecological and economic parameters.

What You Will Achieve:

Objective of the Master's Thesis

The goal of this thesis is the development, prototypical implementation, and systematic evaluation of an AI-based method for detecting chronically critical operating conditions in multi-year building management system time series data. The central question is how persistent or recurring deviations from expected equipment behavior can be identified, characterized, and translated into technically interpretable findings using data-driven methods.

Research Questions

• What features of chronically critical operating conditions can be identified in multi-year building management system time series data, and how can these be distinguished from short-term outliers or operationally expected fluctuations?
• Which data-driven anomaly detection methods are suitable for analyzing historical building management system data in terms of detection performance, robustness, and interpretability?
• How can identified anomalies be structured, evaluated, and presented in relation to affected equipment, control loops, room conditions, or external influencing factors?
• What prerequisites and limitations arise for the practical implementation of the developed approach in an operational monitoring or decision support system?

Methodological Framework

The thesis includes the structured preparation and exploratory analysis of multi-year time series data from building management systems, the selection and implementation of suitable anomaly detection methods, and the systematic evaluation of results based on technically defined criteria. A comprehensible methodological derivation of the chosen approaches is expected, for example, based on statistical methods, rule-based baselines, or machine learning techniques for modeling normal operation and detecting persistent deviations.

A particular focus lies on evaluating the developed method in terms of detection quality, robustness against seasonal and operational fluctuations, traceability of findings, and practical applicability in an industrial environment. The thesis should demonstrate to what extent chronically critical conditions can be automatically identified and which form of result preparation is useful for subsequent operational use.

Expected Outcomes

• Scientifically grounded problem definition and delineation of the anomaly detection use case in building management system data
• Preparation and analysis of a multi-year dataset from equipment operation
• Development and prototypical implementation of a method for identifying chronically critical operating conditions
• Systematic assessment of the method in terms of detection performance, robustness, interpretability, and practical feasibility
• Derivation of technically justified recommendations for the future use of the approach in technical monitoring and operational optimization

Scientific Added Value

The master's thesis contributes to the question of how data-based anomaly detection can be applied in complex technical building systems under real industrial boundary conditions. The focus is not only on the development of a prototypical method but also on its scientifically grounded evaluation, reflection on methodological limitations, and the transferability of results to comparable equipment contexts.

Your Qualifications:

• Ongoing master's studies in automation engineering, computer science, data science, technical mathematics, process engineering, or a comparable field
• Interest in time series analysis, machine learning, and big data analysis in technical systems
• Experience in processing and evaluating larger databases as well as in using programming languages or analysis tools for data processing
• Structured and scientific working methods as well as the ability to document methods and results in a comprehensible manner
• Interest in combining scientific methodology with practical application in an industrial environment
• Good German and English skills, both written and spoken

Advantageous

• Basic knowledge of building management systems, HVAC systems, industrial automation, or process data analysis
• Understanding of sensor technology, measurement data quality, control loops, and operational boundary conditions of technical equipment

What We Offer You:

For this important and responsible position, the salary is €2,010.75 gross/month (full-time, collective agreement for the chemical industry).

• Awards as a top employer and certified family-friendly company
• Comprehensive further education and training opportunities as well as personal development and mentoring programs
• Diverse career development programs (talent, trainee, apprenticeship programs)
• Employee recommendation and recognition programs, employee stock purchase plan
• Active participation in various network groups (e.g., Diversity, Equity & Inclusion; Sustainability)
• Diverse health offerings (e.g., free vaccinations, psychological counseling, massages)
• Fitness offerings
• Company events & celebrations
• Company restaurant with subsidized prices
• Company childcare / bilingual company kindergarten
• Good public transportation access