Sökning: "Failure models"
Visar resultat 6 - 10 av 368 uppsatser innehållade orden Failure models.
6. Design of cooling-air permeable coil support
Master-uppsats, KTH/HållfasthetsläraSammanfattning : Coil supports are integral load-bearing components employed in generators andmotors. They serve the purpose of preventing excessive deformation and maintaininga stable position of the coils responsible for generating power and magnetic fieldswhen rotating. LÄS MER
7. Context-aware Swedish Lexical Simplification : Using pre-trained language models to propose contextually fitting synonyms
Kandidat-uppsats, Linköpings universitet/Institutionen för datavetenskapSammanfattning : This thesis presents the development and evaluation of context-aware Lexical Simplification (LS) systems for the Swedish language. In total three versions of LS models, LäsBERT, LäsBERT-baseline, and LäsGPT, were created and evaluated on a newly constructed Swedish LS evaluation dataset. LÄS MER
8. Condition Monitoring Of Machine Components From Drive Data Using Semi-Supervised Anomaly Detection Methods
Master-uppsats, Uppsala universitet/Institutionen för informationsteknologiSammanfattning : The mission of the machine manufacturer is to gain insights from machine data to increase their machines' efficiency and sustainability. Continuously monitoring the machine data with machine learning helps to detect emerging mechanical problems and prevents unexpected failures. LÄS MER
9. Development of a Compact Drive System for Total Artificial Heart
Master-uppsats, KTH/Medicinteknik och hälsosystemSammanfattning : Over eight decades of research into total artificial hearts (TAHs) has significantly contributed to saving end-stage heart failure patients. However, at the current stage of development TAHs have several limitations, one of them being their bulkiness. LÄS MER
10. Supervised Failure Diagnosis of Clustered Logs from Microservice Tests
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : Pinpointing the source of a software failure based on log files can be a time consuming process. Automated log analysis tools are meant to streamline such processes, and can be used for tasks like failure diagnosis. This thesis evaluates three supervised models for failure diagnosis of clustered log data. LÄS MER