Chalmers Open Digital Repository

Välkommen till Chalmers öppna digitala arkiv!

Här hittar du:

  • Studentarbeten utgivna på lärosätet, såväl kandidatarbeten som examensarbeten på grund- och masternivå
  • Digitala specialsamlingar, som t ex Chalmers modellkammare
  • Utvalda projektrapporter

Forskningspublikationer, rapporter och avhandlingar hittar du i research.chalmers.se

 

Enheter i Chalmers ODR

Välj en enhet för att se alla samlingar.

Senast inlagda

Bild saknas
Post
Evaluating the Strategic Value of Maintenance in Swedish Manufacturing – A Survey Study
(2024) Khatri, Sagar; Chalmers tekniska högskola / Institutionen för industri- och materialvetenskap; Chalmers University of Technology / Department of Industrial and Materials Science; Ylipää, Torbjörn; Ylipää, Torbjörn
This Master's thesis examines the strategic importance of maintenance in the manufacturing industry, focusing on how annual investments in maintenance influence operational efficiency and financial performance. The research utilizes a mixed-methods approach, combining literature review and surveys conducted across various Swedish manufacturing firms. It assesses the impact of maintenance strategies on annual investments and the required skills for workers, emphasizing the increasing need for continuous training due to rising labor costs associated with skilled personnel. Key findings indicate that firms adopting advanced maintenance strategies, which integrate predictive and proactive techniques supported by modern technologies, significantly reduce operational costs and minimize downtime. These strategies not only enhance the sustainability of manufacturing processes but also address environmental challenges, making a strong case for their broader adoption. However, the study identifies challenges such as the high initial costs of technology and the continuous need for upskilling workers to keep pace with technological advancements. The thesis supports viewing maintenance as a strategic investment within the manufacturing sector, crucial for improving productivity and achieving a competitive advantage while promoting sustainable practices.
Bild saknas
Post
A Study on Commuting Therapy, Designing a Human-Vehicle Interaction System to Enhance the Commuting Experience with Emotion-Based Multisensory Strategies
(2024) Lu, Xiaonan; Chalmers tekniska högskola / Institutionen för industri- och materialvetenskap; Chalmers University of Technology / Department of Industrial and Materials Science; Aryana, Bijan; Aryana, Bijan
Commuting is often perceived as mundane and time-consuming. However, commute also offers an opportune space and time for design interventions that can enhance well-being during the daily commute. This thesis project explores the design opportunities to enhance the leisure experience during commuting, with a focus on Jordan’s Four Product Pleasures. This project reimagines commute as a transition period aimed at improving human well-being, transforming it into a more pleasurable experience. As a result, this project introduces an affective human-vehicle interaction system within the smart cabin, employing multisensory emotion regulation strategies, including vision, aroma, music, and haptics. Specifically, this project details the design of a multisensory experience tailored to driver emotional states during commutes. The proposed design was evaluated through a VR car simulator in a qualitative user study, which revealed user preferences for multisensory experiences.
Bild saknas
Post
Deployment of an Unsupervised Anomaly Detection Model Using Anomalib and PyTorch, Is it feasible on a low-powered edge-device?
(2025) Kunnathupurakkal Subramanian, Sooraj; Hedin, Ludvig; Chalmers tekniska högskola / Institutionen för industri- och materialvetenskap; Chalmers University of Technology / Department of Industrial and Materials Science; Skoogh, Anders; Chen, Siyuan; Marti, Silvan
The deployment of pre-trained unsupervised anomaly detection models on low-cost and low-powered edge devices, specifically the Raspberry Pi 5, is a promising approach for cost effective and scalable solution for real-time monitoring in production environments. This thesis investigates the plausibility and performance of running such models on the RP5, focusing on their ability to accurately detect anomalies in real-time. This thesis addresses the challenges with hard hardware limitations, software configuration, dataset creation and model performance in an edge environment. To enable the training and validation of the model a custom dataset consisting of mugs stained with food coloring to act as anomalies. While the model successfully ran on the RP5 the inference results demonstrated a lack in accuracy with false positives and negatives as-well as a cycle time of 2000-3000 ms per image, was deemed to slow for real-time applications. Although the findings suggest that with further optimizations, such reducing the resolution of input data and further developing the inference script, the cycle time could be significantly reduced. As well as improving the accuracy by reducing the prevalence of false positives and negatives. Thus the model could be an effective solution for real-time anomaly detection.
Bild (thumbnail)
Post
Large-Scale Transformer-Based Multi-Target Tracking
(2024) Spjuth, Oliver; Chalmers tekniska högskola / Institutionen för matematiska vetenskaper; Andersson, Adam; Andersson, Adam; Svedung Wettervik, Benjamin
In military surveillance, radar-based tracking of objects is essential. The growing use of small-scale drones, as seen in the Russia-Ukraine war, necessitates tracking at low speeds. At these speeds, birds are also detected and the number of false detections increases, making the already complex Multi-Target Tracking (MTT) problem more challenging. Recent advances in machine learning, particularly the transformer ar- chitecture, present new opportunities to address these challenges, making it valuable to explore their application in air surveillance contexts. Although transformers have shown promise in related fields such as automotive radar, adapting them to air surveillance presents specific hurdles. These include managing the quadratic scaling of attention as the number of detections increases, ensuring accurate state estimation across large continuous areas, and simultaneously estimating a large number of targets. To address these challenges, a four-module pipeline was developed. The first module reduced attention complexity by generating local contexts of detections for paral- lel processing. This was followed by a transformer-encoder-based filter designed to eliminate false detections (FDF). Next, the original problem was partitioned into independent subproblems using a graph-based clustering approach. One suggested implementation utilized the attention scores from the FDF to construct edges be- tween detections (nodes). The Leiden algorithm, a community detection algorithm, was then applied to identify clusters of related detections. These clusters were sub- sequently processed in parallel by the final transformer-based MTT module. This approach significantly reduced the initial memory demands of attention from approximately 320 GB to 1.6 GB while maintaining performance across the pipeline. The false detection filter achieved a balanced accuracy and F1 score of 99%, ef- fectively reducing the problem complexity. The attention-score-based partitioning method accurately identified subproblems that were predominantly optimal (single- target) or near-optimal. When evaluated using MTT metrics, the pipeline employing the attention-score- based partitioning method demonstrated promising results, with few missed or false detections and a total inference time of approximately 0.5 seconds for over 100,000 detections. The system scaled effectively with increased complexity and adapted well to varying conditions.
Bild (thumbnail)
Post
Metal Additive Manufacturing for early concept Validation
(2024) Nordström, Nils Emil Fredrik; Chalmers tekniska högskola / Institutionen för industri- och materialvetenskap; Chalmers University of Technology / Department of Industrial and Materials Science; Hryha , Eduard; Hryha, Eduard
The manufacture of prototypes using metal additive manufacturing (AM) has been used for many years, however, there has been little research on how to heat treat AM aluminum parts to match the properties of parts manufactured using high pressure die casting (HPDC). Prototypes made using sand casting can only reach 70% of the strength of production HPDC parts, which is not ideal for early testing. As printed, the strength of AM aluminum alloys manufactured with Powder Bed Fusion – Laser Beam (PBF-LB) is much higher than HPDC aluminum alloy. Hence, AM parts can be heat treated to reduce their strength until it matches that of HPDC parts. This research investigated how the heat treatment of AM aluminum alloy AlSi10Mg affects its hardness, yield strength, ductility, and microstructure, as well as the mechanisms that cause the changes in properties. In addition, a replica of a production HPDC part was manufactured using AM to develop a prototype manufacturing process and to compare the results between them. The results showed that heat treating AM parts at 325ºC for 4 hours produced the closest yield strength to that of HPDC parts. However, the ductility was much greater for the AM parts due to differences in alloying elements and microstructure. For making an AM demonstrator, the process developed was to manufacture the part with PBF-LB along with some tensile bars, heat treat the part on the build plate, machine any critical surfaces, remove the support material, and treat the surface with glass blasting to remove any remaining particles/powder on the surface.