Design and Implementation of a TinyML-Based Power Quality Disturbance Classification System on the STM32H743VIT6

dc.contributor.authorHamri, Amina
dc.contributor.authorDirecteur: Ghouti, Abdellaoui; Co-Directeur: Mimouni, Faiza
dc.date.accessioned2026-11-18T08:52:32Z
dc.date.issued2026-10-06
dc.description.abstractThis work presents the development of an intelligent embedded system for power quality disturbance monitoring and classification using artificial intelligence. A synthetic dataset containing 17,000 signals across 17 classes was used to train and compare two deep learning models: CNN-1D and BiLSTM. The models achieved test accuracies of 95.5% and 93%, respectively. The CNN-1D model was successfully deployed and validated on the STM32H743 microcontroller using TinyML, achieving an inference time of 24.873 ms. Noise robustness experiments revealed a significant performance degradation, highlighting the need for further improvements and additional validation using real electrical signals before practical deployment.
dc.identifier.urihttps://thesis.essa-tlemcen.dz/handle/123456789/840
dc.language.isoen
dc.publisherHigher School In Applied Sciences -Tlemcen-
dc.subjectPower Quality
dc.subjectArtificial Intelligence
dc.subjectDeep Learning
dc.subjectCNN-1D
dc.subjectBiLSTM
dc.subjectTinyML
dc.subjectSTM32.
dc.titleDesign and Implementation of a TinyML-Based Power Quality Disturbance Classification System on the STM32H743VIT6
dc.typeThesis

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Master thesis.pdf
Size:
2.3 MB
Format:
Adobe Portable Document Format