Congratulations Alexander Barlo, PhD in Mechanical Engineering!

• Post by: Tobias Larsson
• 16th December 2025
• No Comment

Alexander Barlo successfully defended his PhD thesis “Towards Sustainable and Intelligent Manufacturing Processes: Data-Driven Insights from Automotive Manufacturing” in front of a full house at BTH, and also some 45 people online. The Dane made a popular presentation of his research and took the audience through his findings and application cases within mechanical engineering and automotive industry, with emphasis on modelling and simulation and adding smartness to the process, and then landed in a summary of his findings.

Barlo has focused on data-driven decision support and monitoring for automotive sheet-metal forming, motivated by the increasing variability in incoming materials (e.g., recycled steels) and process conditions that threaten quality and robustness in production. The thesis systematically explores how machine-learning methods, combined with finite-element (FE) simulation and existing press-shop data, can be used to (1) detect anomalous incoming material coils before they reach the press (unsupervised PCA + Local Outlier Factor, validated via FE simulations showing tolerance risks), (2) train “intelligent quality controllers” using synthetically generated data from stochastic/high-fidelity FE models to reduce dependence on scarce labelled production data, and (3) extract actionable process health indicators from existing signals, e.g., computing process work by integrating punch force over crank angle for practical in-line monitoring. Ultimately, the thesis contributes a pragmatic path for industry to move toward more sustainable and intelligent manufacturing by coupling simulation-driven data generation with ML and low-friction integration into real stamping workflows.

Alexander has been in highly collaborative applied research environment taking part in several research projects throughout the course of the PhD;
ADSUP – Advanced Contact Pattern Digitalization Set-Up for Stamping and High Pressure Die Casting Applications | 2024-2026, CiSMA – Circular Steel for Mass Market Applications, PREDICT, I-Stamp – Intelligent and sustainable stamping processes using hybrid control strategies together with process monitoring, Next Generation Production Process, with funding from EU, KKS, VINNOVA, and Swedish Energy Agency.

Faculty opponent was Assistant Professor Jos Havinga (University of Twente, Netherlands) and the grading committee consisted of Associate Professor Kristina Wärmefjord (Chalmers University of Technology, Sweden), Dr. Nagore Otegi Martinez (Mondragon Unibertsitatea, Spain), and Associate Professor Andreas Linderholt (Linnaeus University, Sweden).

Professor Havinga invited Alexander into a conversation around the work he had performed and by this creating an interesting dialogue that took the audience through both the motivation of the work, the scientific approach and results, together with the industrial aspects of applied work done by Alexander via industrial cases. A fair amount of focus was spent on data points.

After the opponent, grading committee, and audience have had the chance to bring up their questions, the grading committee left the room for their discussion and eventually returned with the verdict; a pass!

We gratulate our newest PhD on an important milestone in his career, and future success in the upcoming career with DTU Construct.

Abstract

Global manufacturing is entering an era of unprecedented variability in material properties, driven by sustainability goals and market volatility. The adoption of recycled steels introduces supplier-specific differences, while cost-reduction strategies and geopolitical disruptions (tariffs, trade barriers, and resource shortages) further amplify process scatter. These dynamics challenge conventional quality control in automotive sheet metal forming and demand intelligent, adaptable production systems.

This dissertation addresses how data-driven methods can strengthen process robustness without major infrastructure changes. Three guiding hypotheses are explored: (H1) machine learning can provide insights into the impact of input variations; (H2) synthetic data can supplement or replace operational data for model development; and (H3) existing sensor signals can be reinterpreted to reduce reliance on additional instrumentation.

A hybrid methodology combining finite element simulations, stochastic modeling, and industrial press shop data was developed. Key contributions include: (1) generation of synthetic datasets for predictive modeling of draw-in and cushion force; (2) application of unsupervised learning for early detection of anomalous material batches; and (3) a novel process monitoring metric, process work, derived from existing sensors to monitor process health.

The findings provide a framework for integrating intelligent data-driven tools into legacy systems, supporting the transition toward resilient and sustainable manufacturing practices.

Keywords: Data-Driven Manufacturing, Machine Learning in Manufacturing, Process Monitoring and Control, Sheet Metal Forming

Download full thesis here: https://urn.kb.se/resolve?urn=urn:nbn:se:bth-28765

The presentation part of the PhD defense session

Spotify Podcast episode on the PhD thesis

• https://open.spotify.com/episode/5jTM1T0zsEy9CLgjlKON05?si=w0orgULaR_O7LGMf_lkBWA

More information

• BTH press: “AI gör bilproduktionen smartare och mer hållbar“
• Congratulations Alexander Barlo, Licentiate in Mechanical Engineering!
• Research Spotlight; Alexander Barlo
• AI gör bilproduktionen smartare och mer hållbar (Bilsport 20260102)
• AI ska göra bilproduktionen smartare och mer hållbar (Svensk Verkstad 20251212)
• AI gör bilproduktionen smartare och mer hållbar (Dagens Infrastruktur 20251212)