Transient stability (TS) and short-term voltage stability (STVS) assessment are of fundamental importance for the operation security of power systems. Both phenomena can be mutually influenced in weak power systems due to the proliferation of power electronic interface devices and the phase-out of conventional heavy machines (e.g., thermal power plants). There is little research on the assessment of both types of stability together, despite the fact that they develop over the same short-term period, and that they can have a major influence on the overall transient performance driven by large electrical disturbances (e.g., short circuits). This work addresses this open research challenge by proposing a methodology for the joint assessment of TS and STVS. The methodology aims at estimating the resulting short-term stability state (STSS) in stable, or unstable conditions, following critical events, such as the synchronism loss of synchronous generators (SG) or the stalling of induction motors (IM). The estimations capture the mechanisms responsible for the degradations of TS and STVS, respectively. The paper overviews the off-line design of the data-driven STSS classification methodology, which supports the design and training of a hybrid deep neural network RCNN (recurrent convolutional neural network). The RCNN can automatically capture spatial and temporal features from the power system through a time series of selected physical variables, which results in a high estimation degree for STSS in real-time applications. The methodology is tested on the New England 39-bus system, where the results demonstrate the superiority of the proposed methodology over other traditional and deep learning-based methodologies. For reference purposes, the numerical tests also illustrate the classification performance in special situations, when the training is performed by exclusively using measurements from generation and motor load buses, which constitute locations where the investigated stability can be observed.

Research on sustainable business models (BMs) rooted in the circular economy is expanding in industry and academia, encouraging companies to enhance their impact on profits, people, and the planet. However, developing sustainable BMs is complex due to the conflicting objectives of sustainability dimensions and competition with traditional models. This work addresses this challenge by proposing a Sustainable Business Guide (SBG) supported by artificial intelligence (AI) to assist in decision-making. The SBG supports the design and assessment of business models by integrating inspection; business opportunity exploration; technical, economic, and environmental analyses; an AI-based decision support system; and Porter’s Five Forces, focusing on the aeronautical and wind energy sectors.

Detecting defects predictively during the welding process, such as porosity, is of vital importance as it allows for the avoidance of degradation in the quality, durability, and productivity of the weld. Research into predictively identifying these types of defects in Submerged Arc Welding (SAW) is quite limited due to the difficulty of gathering data along the process. This remains a challenge to drive the optimization of the manufacturing of pieces that include such welds as the case of large components like pipes in the oil and gas industry. Therefore, this work addresses this challenge and proposes a methodology based on a deep hybrid neural network called recurrent convolutional neural network (RCNN). This deep learning model is capable of detecting and predicting surface porosity defects in real-time using the continuous voltage electrical signal from the SAW process. The training of the RCNN model involved using various weld beads, some with surface porosity and others without. On the one hand, defects were labeled based on the location of the pores along the weld, while on the other hand, the voltage electrical signals were processed and organized. The proposed framework based on RCNN was tested in other weld beads, where the results were satisfactory with the model achieving a high accuracy rate of around 80% in predictive pore detection. Moreover, the model’s processing time was <10 ms, meeting the requirements for real-time applications.

Although several data-driven approaches for short-term voltage stability (STVS) assessment have been proposed, most of them do not extend to corrective control actions nor consider the joint dynamics of generation and load. To address this gap, this work introduces a real-time adaptive load shedding scheme (ALSS) driven by an integrated assessment of the short-term stability state (STSS) and the identification of critical induction motors (CIM) as the mechanism driving STVS instability. The methodology employs two recurrent convolutional neural network (RCNN) models operating in parallel: i) the STSS-RCNN, which classifies the system state as stable, unstable by transient stability (TS), or unstable by STVS; and ii) the CIM-RCNN, which identifies the critical motors responsible for instability, thereby inherently recognizing STVS-related problems. The joint operation of these models ensures that the ALSS is activated only when both responses consistently recognize an STVS event. This enables not only the correct activation of the load shedding scheme but also its accuracy and adaptive parameterization based on the identified CIMs. Validation on the IEEE 39-bus test system demonstrates that the proposed approach achieves robust real-time performance, outperforms single deep learning baselines, and significantly overcomes traditional load shedding schemes in efficiency and reliability.

La carga dinámica, especialmente los motores de inducción (MI), representa la fuerza motriz responsable del fenómeno de recuperación retardada de tensión inducida por falla (FIDVR) [1]. En este trabajo se propone una metodología para identificar los motores de inducción causantes del fenómeno FIDVR que oriente en la parametrización de un esquema de desconexión de carga (ubicación de carga a desconectar) con el fin de mitigar de una forma más efectiva este fenómeno. La metodología utiliza los valores de magnitud de tensión obtenidos con dispositivos PMU para detectar al fenómeno y la velocidad de rotación de los MI para identificar los motores causantes del FIDVR. Se aplica la metodología propuesta en el sistema de prueba New England de 39 barras en donde se compara el esquema de desconexión de carga basado en el comportamiento de los MI con un esquema convencional UVLS. Los resultados muestran que el esquema de desconexión de carga propuesto es más efectivo ya que desconecta menor cantidad de carga y a la vez logra cumplir criterios de recuperación de tensión transitoria post falla.

El creciente uso de fuentes renovables para la generación de energía eléctrica plantea nuevos desafíos para la estabilidad de los sistemas eléctricos de potencia. Este trabajo estudia el impacto de la incorporación de generación renovable (fotovoltaica y eólica) sobre las estabilidades transitoria y de tensión de corto plazo. Para lograrlo, se evalúa la respuesta del sistema obtenida mediante simulación dinámica en una gran cantidad de escenarios operativos ante contingencias n-1 y bajo distintas condiciones de carga y despacho de generación renovable. Se clasifica cada escenario en estable o inestable empleando una metodología basada en el análisis de la evolución del ángulo de los generadores sincrónicos para detectar condición de pérdida de paso y se diferencia el tipo de inestabilidad a través de la acción de control que logra salvar al sistema de la inestabilidad. Este estudio se realiza sobre el sistema IEEE New England de 39 barras en 10.000 estados operativos ante contingencias severas. Los resultados obtenidos muestran que la incorporación de generación renovable aumenta la cantidad de escenarios inestables de corto plazo del sistema eléctrico tanto por tensión como por estabilidad transitoria.