Vibration and acoustic analysis actively support the nondestructive and noninvasive fault diagnostics of rotating machines at early stages. Nonetheless, the acoustic signal is less used because of its vulnerability to external interferences, hindering an efficient and robust analysis for condition monitoring (CM). This paper presents a novel methodology to characterize different failure signatures from rotating machines using either acoustic or vibration signals. Firstly, the signal is decomposed into several narrow-band spectral components applying different filter bank methods such as empirical mode decomposition, wavelet packet transform, and Fourier-based filtering. Secondly, a feature set is built using a proposed similarity measure termed cumulative spectral density index and used to estimate the mutual statistical dependence between each bandwidth-limited component and the raw signal. Finally, a classification scheme is carried out to distinguish the different types of faults. The methodology is tested in two laboratory experiments, including turbine blade degradation and rolling element bearing faults. The robustness of our approach is validated contaminating the signal with several levels of additive white Gaussian noise, obtaining high-performance outcomes that make the usage of vibration, acoustic, and vibroacoustic measurements in different applications comparable. As a result, the proposed fault detection based on filter bank similarity features is a promising methodology to implement in CM of rotating machinery, even using measurements with low signal-to-noise ratio.

Nowadays, bearings installed in industrial electric motors are constituted as the primary mode of a failure affecting the global energy consumption. Since industries’ energy demand has a growing tendency, interest for efficient maintenance in electric motors is decisive. Vibration signals from bearings are employed commonly as a non-invasive approach to support fault diagnosis and severity evaluation of rotating machinery. However, vibration-based diagnosis poses a challenge concerning the signal properties, e.g., highly dynamic and non-stationary. Here, we introduce a knowledge-based tool to analyze multiple health conditions in bearings. Our approach includes a stochastic feature selection method, termed Stochastic Feature Selection (SFS), highlighting and interpreting relevant multi-domain attributes (time, frequency, and time–frequency) related to the bearing faults discriminability. In particular, a relief-F-based ranking and a Hidden Markov Model are trained under a windowing scheme to achieve our SFS. Obtained results in a public database demonstrate that our proposal is competitive compared to state-of-the-art algorithms concerning both the number of features selected and the classification accuracy.

The Modular Multilevel Converter (MMC) topology has become one of the most promising solution in HVDC applications when compared with similar approaches. The evaluation of the power losses in an MMC terminal is fundamental to estimate the overall converter efficiency and size the required thermal management system. In this paper, a complete comparison of two methods to calculate conduction and switching losses in an MMC terminal is presented. The first method considers the average model of the MMC to calculate the overall losses. In addition to the average model, the second method considers the effect of the capacitor on the average current flowing through each semiconductor device. In order to compare and evaluate the two approaches, extensive time-domain simulations are carried out in an MMC terminal under different operating conditions. Analytical results show that there is a slightly difference in the overall efficiency using both methods (≈2.9%). As initial statement, the second method is more convenient to implement, since all the parameters from the manufacturer's data sheet are considered.

Objetivo: Presentar una metodología para la planificación de movimientos de sistemas autónomos con múltiples agentes. Metodología: Se define y parametriza el comportamiento físico de un equipo de sistemas de navegación autónoma, luego se describe e implementa un algoritmo de síntesis de políticas de control que interpreta estas descripciones convertidas a fórmulas LTL y se genera un modelo que permite hacer abstracciones automáticas. A partir de configuraciones genéricas de solución, se deriva en el caso de múltiples robots con una única tarea en un entorno con obstáculos fijos. La metodología se valida en diferentes escenarios y se analizan los resultados. Resultados: La metodología propuesta para planificación de movimientos en sistemas con múltiples agentes, combina dos técnicas del estado del arte, permitiendo mitigar la explosión combinacional de estados presente en los enfoques tradicionales. Conclusiones: La metodología que se presenta resuelve el problema de síntesis de autómatas para el control de alto nivel, con cambio de tareas durante la ejecución. Bajo ciertos criterios, se mitiga el problema de explosión combinacional de estados asociado a estos sistemas. La solución es óptima respecto al número de transiciones seguidas por los miembros del equipo. Financiamiento: Universidad Tecnológica de Pereira

Ensuring safe coexistence between human operators and industrial robot manipulators is a critical challenge in collaborative manufacturing environments. Existing approaches rely either on dedicated safety-rated hardware, which is expensive and difficult to retrofit, or on purely vision-based classifiers that discard the precise kinematic state available from the robot controller, leading to unresolved visual ambiguities when different joint configurations produce similar appearances from fixed camera viewpoints. Kinematics-only approaches, while precise, lack the spatial context needed to disambiguate configurations near workspace boundaries. We propose RGBJointsNet, a late-fusion multimodal deep learning classifier that combines RGB visual features extracted by a frozen EfficientNet-B2 convolutional backbone with a compact kinematic stream processing the 12-dimensional joint angle vector of a dual-UR5 robotic cell. The model maps each observation to one of five mutually exclusive workspace zones: rest ($C_0$), nominal ($C_1$), extended ($C_2$), shared/collision-risk ($C_3$), and joint-limit/singularity ($C_4$). A dedicated simulation environment built on ROS 2 Humble Hawksbill and Gazebo Classic 11 was used to generate a labelled dataset of 54,309 frames and 162,927 RGB images from three calibrated overhead cameras, with analytic ground-truth labels derived from closed-form forward kinematics. Training on a CPU with a feature-caching strategy brings the per-epoch wall-clock time to seconds, making the approach tractable without GPU hardware. On the held-out test set, the model achieves 87.1% overall accuracy and a macro-averaged F1 score of 90.0%, with near-perfect recall of 99.3% for the safety-critical shared zone $C_3$. The trained classifier is integrated as an ROS 2 inference node capable of running at 10 $\mathrm{Hz}$ on a standard workstation. Our results demonstrate that joint angle information is a decisive complement to RGB imagery for fine-grained, safety-oriented workspace classification in simulation-derived settings.

En este trabajo se plantea una metodología para la síntesis de autómatas en aplicaciones de navegación autónoma terrestre con una tarea global. La metodología propuesta se basa en el diseño de autómatas por gramáticas regulares y permite generar una política de control para la conducción autónoma de un vehículo en un ambiente parcialmente controlado mientras se extrae información del entorno a través de sensores. Además, se plantean los inconvenientes que se presentan al tratar de abordar esta aplicación con enfoques tradicionales que implican la síntesis de autómatas finitos no deterministas. Por último, se presentan losautómatas obtenidos al validar la metodología propuesta a través de simulaciones utilizando el software MATLAB con el Toolbox integrado de realidad virtual (V-Realm Builder).