AI System Improves Induction Motor Fault Detection
A new machine learning framework combining multimodal sensor fusion and contrastive learning improves induction motor fault classification accuracy to 84.31%.
A new machine learning framework combining multimodal sensor fusion and contrastive learning improves induction motor fault classification accuracy to 84.31%.
Comparative laboratory testing reveals that mechanical vibration signals combined with wrapper-based machine learning provide superior diagnostic robustness over electrical current ...
A study in Machine Learning with Applications shows that retrieval-augmented generation significantly improves the diagnostic performance of compact large language ...
An extended AR-AI disassembly station now integrates PCB burn screening and washing-unit sensor tests with human confirmation for component reuse.
A new review links vibration sources, structural fatigue and emerging digital monitoring technologies in the design of electric vehicle battery ...
Researchers have developed an attention-enhanced residual network that converts structural vibration data into Markov transition field images and detects local ...
Brazilian researchers have combined vibration analysis with explainable artificial intelligence to diagnose unbalance, misalignment, and cracks in rotors supported by ...
Researchers have developed a time-frequency gated transformer that reconstructs the full dynamic response of structures from sparse vibration sensor data, ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine