AI for Engineering

Partial discharge (PD) testing based on IEC 60270 is widely employed for assessing the insulation integrity of power transformers. Although numerous statistical descriptors can be extracted from PD measurements, redundant and irrelevant features can degrade classification performance, particularly in small datasets. This study proposes a binary hybrid particle whale optimization algorithm (BHPWOA) for multi-objective wrapper-based feature selection in transformer insulation severity classification. The analysis comprises 64 IEC 60270 partial-discharge test sessions collected from 30 power transformers. Seventeen candidate statistical, temporal, spectral, derived, and test-configuration features were evaluated; the transformer identifier (TransClass) was excluded before wrapper optimization because it would not be available for an unseen transformer. Candidate subsets were assessed with a k-nearest neighbors (KNN) classifier using five-fold StratifiedGroupKFold cross-validation grouped by TransformerID, with min–max scaling fitted exclusively within each training fold. BWOA and BSFSA achieved the best multi-objective fitness (−0.9227) with the two-feature subset {CV_PD, Exc100}, corresponding to an 88.2% reduction, 93.75% accuracy, and macro-F1 of 0.9313. BHPWOA selected five features {MeanPD, CV_PD, Exc100, Q95_PD, MeanPD_Early}, corresponding to a 70.6% reduction, 92.19% accuracy, and macro-F1 of 0.9163. Across five BHPWOA stability runs, the mean feature count was 4.6 +/− 1.02, mean accuracy was 0.909 +/− 0.021, and mean macro-F1 was 0.903 +/− 0.022; CV_PD and Exc100 were selected in all five runs. Because the same grouped partition is used for wrapper selection and reported out-of-fold performance, these values are internal, non-nested grouped-CV estimates rather than independent outer-CV estimates.

Ultra-low-resolution (ULR) thermal array sensors (e.g., $8\times 8$) offer a privacy-preserving and cost-effective paradigm for intelligent edge perception. However, extracting robust spatial features is severely hindered by extreme spatial aliasing, background thermal interference, and environmental temperature drift. In this paper, we propose VMEMSTNet, an ultra-lightweight framework that tackles the ULR perception bottleneck through a thermodynamics-inspired cross-modal learning strategy. Rather than treating ULR recognition purely as a computer vision task, our approach integrates the underlying sensing physics. To bridge the resolution gap, we leverage a high-resolution visual modality strictly as offline cross-modal guidance. Specifically, a YOLOv8n-seg teacher provides spatial shape priors via Gaussian thermal diffusion—explicitly mimicking physical heat dissipation for spatial knowledge translation—while a MobileNetV2 teacher guides semantic probability distillation. Furthermore, a thermodynamics-inspired preprocessing pipeline fuses dynamic quantile-based normalization with absolute temperature difference ($\Delta T$) to maintain contrast consistency across environmental drifts. Using hand gesture recognition as a representative spatial classification task, experimental results demonstrate that VMEMSTNet achieves 95.7% accuracy. Remarkably, it outperforms heavier generic edge models while utilizing only 20.0 k parameters and 0.135 MFLOPs. By effectively decoupling spatial semantics from thermodynamic noise, this work establishes a robust, hardware-aware deployment pathway for ULR thermal perception on resource-constrained microcontrollers.

Recent advances in Generative AI are creating new opportunities for engineering and geosciences activities. This study examined whether the initial production of Territorial and Environmental Diagnosis (TED) reports could be co-piloted by multi-agent systems. The study proposed a challenge between a classical engineering workflow and a multi-agent framework (MAF) combining specialized agents boosted by LLMs for data retrieval, Data Visualization, writing, statistical description, and publishing within a unified deterministic workflow. To evaluate the effectiveness of the MAF, a blind comparative assessment was conducted using sections of TED reports produced by internal experts for three French municipalities as reference case studies. The framework was tested across several key thematic sections, and MAF outputs were compared with the outputs generated by territorial experts. The evaluation focused on Data Relevance, Writing Quality, Data Visualization, Contextual Relevance, and Overall Rating. The results of our experiments indicate that MAF reduced, within tested conditions, the time required for reporting while maintaining a level of quality comparable to conventional reports. Evaluations confirmed that MAF performed well in themes relying on processing data, while human-produced reports retained an advantage in topics requiring deeper contextual interpretation. These findings support the potential of MAF as co-pilots for TED production in engineering workflows.