Neodymium (NdFeB) rare earth Permanent Magnets (PMs) are widely used in the manufacturing of Line-Start Permanent Magnet Synchronous Motors (LSPMSMs). During the initial startup of LSPMSMs, irreversible PM demagnetization often occurs. This research provides a thorough examination of the PM demagnetization process during the initiation of a 15-kW, 3000-rpm LSPMSM, which was converted from a squirrel-cage Induction Motor (IM) featuring a 3-bar PM. Utilizing Ansys/Maxwell2D software for simulations and conducting experiments, this study reveals that upon starting the LSPMSM, demagnetization occurs at the two outermost PM pairs. This leads to unstable motor operation at synchronous speed, significant current fluctuations, and a substantial decrease in performance. The findings suggest that to ensure effective LSPMSM operation, it is crucial to either restrict frequent restarts or select an appropriate PM type to prevent partially irreversible demagnetization, thereby enhancing power efficiency.

Accurate forecasting of solar power is essential for enhancing the stability and efficiency of power systems with high Photovoltaic (PV) penetration. This paper proposes a novel hybrid model based on a Stacking Ensemble (SE) of XGBoost, LightGBM, and Random Forest (RF), with optimal weights determined using the Limited Memory Broyden–Fletcher Goldfarb Shanno with Box constraints (L-BFGS-B) algorithm. The model is trained and tested on real-world data from a 49.5 MW solar power plant in Vietnam. The experimental results show that the proposed SE-XGB-LGBM-RF-OW model outperforms individual learners and deep learning baselines in both accuracy and training time. It consistently achieves a Normalized Mean Absolute Percentage Error (NMAPE) below 1.2% across all seasons. Compared to LSTM and GRU models, SE reduces Root Mean Square Error (RMSE) by more than 90% and shortens training time by over 20 times. Additionally, it significantly lowers the MAPE and NMAPE values, with improvements exceeding 90% in most seasonal test cases, highlighting the model’s superior accuracy and generalization capability.

Global energy crises have been leading to serious consequences for world economic growth and competitiveness among countries. The economical and efficient use of energy has become an irreversible trend in the world and Vietnam in particular. Energy saving not only helps reduce production costs improve profits and competitiveness of businesses, but also contributes to reducing pressure on the national energy system. This study synthesizes the results of 686 responses on energy saving behavior from 49 enterprises in various industries in Vietnam; 49 were answered by company leaders, middle managers answered 146, and 491 were answered by employees conducting the survey. The study uses the exploratory factor analysis method and SEM linear regression equation analysis. Smart-PLS and SPSS software are used to perform the analysis. To determine the factors influencing energy usage behavior in industrial enterprises, the author proposed the research model based on the Theory of Planned Behavior (TPB) combined with Institutional Theory. 13 influencing factors have been considered in the following direction: 1) a group of factors related to promoting the construction of an energy-saving culture in enterprises; 2) a group of factors related to institutions and regulations to promote energy saving in enterprises; 3) a group of influencing factors coming from outside the business. The analysis results show that subjective benchmark factors, behavioral control and energy-saving attitude are significant positive predictive factors for energy-saving intention). Organizational interventions positively impact subjective standards, behavior control, and attitudes. In particular, the financial factor plays an important role, not only directly affecting energy-saving behavior but also significantly affecting the management factor (TMP). However, cultural factors, TMP, and cooperation did not show a significant influence on energy-saving behavior. We propose energy saving measures at different levels to promote energy-saving implementation in Vietnamese industrial enterprises based on the research results.