Many studies applying Brain-Computer Interfaces (BCIs) based on Motor Imagery (MI) tasks for rehabilitation have demonstrated the important role of detecting the Event-Related Desynchronization (ERD) to recognize the user's motor intention. Nowadays, the development of MI-based BCI approaches without or with very few calibration stages session-by-session for different days or weeks is still an open and emergent scope. In this work, a new scheme is proposed by applying Convolutional Neural Networks (CNN) for MI classification, using an end-to-end Shallow architecture that contains two convolutional layers for temporal and spatial feature extraction. We hypothesize that a BCI designed for capturing event-related desynchronization/synchronization (ERD/ERS) at the CNN input, with an adequate network design, may enhance the MI classification with fewer calibration stages. The proposed system using the same architecture was tested on three public datasets through multiple experiments, including both subject-specific and non-subject-specific training. Comparable and also superior results with respect to the state-of-the-art were obtained. On subjects whose EEG data were never used in the training process, our scheme also achieved promising results with respect to existing non-subject-specific BCIs, which shows greater progress in facilitating clinical applications.

Currently, the modeling of complex chemical-physical processes is drastically influencing industrial development. Therefore, the analysis and study of the combustion process of the boilers using machine learning (ML) techniques are vital to increase the efficiency with which this equipment operates and reduce the pollution load they contribute to the environment. This work aims to predict the emissions of CO, CO₂, NOx, and the temperature of the exhaust gases of industrial boilers from real data. Different ML algorithms for regression analysis are discussed. The following are input variables: ambient temperature, working pressure, steam production, and the type of fuel used in around 20 industrial boilers. Each boiler's emission data was collected using a TESTO 350 Combustion Gas Analyzer. The modeling, with a machine learning approach using the Gradient Boosting Regression algorithm, showed better performance in the predictions made on the test data, outperforming all other models studied. It was achieved with predicted values showing a mean absolute error of 0.51 and a coefficient of determination of 99.80%. Different regression models (DNN, MLR, RFR, GBR) were compared to select the most optimal. Compared to models based on Linear Regression, the DNN model has better prediction performance. The proposed model provides a new method to predict CO₂, CO, NOx emissions, and exhaust gas outlet temperature.

This work focuses on the modeling and simulation of constant pressure systems based on variable speed pumps, with the aim of studying and evaluating their performance from a multidisciplinary approach. Using the physical models of the Simscape library, from MATLAB/Simulink R2019b, two study cases are assembled consisting of: piping system, a hydropneumatic tank, centrifugal pumps with an induction motor, variable speed drives, and a control system. Case one is comprised of one pump at a fixed speed and another at variable speed, and case two with both pumps at variable speed. For the parameterization of the models, data from manufacturers and process requirements are used. The different stages of the control system are integrated and configured; these are constant V/f control, slip compensation, space vector modulation (SVM,) and pressure controller. The dynamic response of the system, power saving, transient current at startup, and harmonic distortion are evaluated. The results showed that both cases kept the pressure constant in the face of variable flow demand and smoothed out the current during startup. Case two saved more energy (between 28 and 49%) but generated more harmonic distortion. In addition, both cases have better performance compared with traditional fixed-speed technologies.

Active Disturbance Rejection Control (ADRC) is a control methodology used in chemical processes, aircraft, motors, and other systems. This paper compares the results of an ADRC controller to a Proportional Integral Derivative controller (PID), applied to two degrees of freedom robots. A Linear Extended State Observer (LESO) is used to reconstruct the state variables and unknown parameters needed to control the position of each link. The ADRC can achieve the tracking position and estimate the velocity of each link. The results of the simulation program are shown.

The number of injector holes and the fuel-injection pressure in an internal combustion engine can affect engine performance and exhaust emissions. Conversion of a port-injection gasoline engine to an HCNG direct-injection engine improves engine performance and exhaust emissions. In addition, increasing the injection pressure helps to increase engine performance. In this study, AVL Fire software was used to perform simulation by certain adjustments. The injection pressure was applied in mods of 15, 20, and 25 bars, the injector holes numbers were 3 and 6, the compression ratio changed from 10:1 to 14:1, and the amount of hydrogen enrichment to natural gas was in mods of 10%, 20%, 30%, and 40%. This paper discusses the items above with regard to power, torque, combustion chamber pressure, fuel conversion efficiency, and exhaust emissions. The result determined that increasing the number of injector holes improves the performance engine and reduces CO emission so that the contour plots confirmed the balanced distribution of temperature and pressure. According to obtained results, maximum engine performance improved from 2.5% to 5% at different speeds and 30% added hydrogen, 25 bar injection pressure, and 6-hole injectors. The amount of CO decreased by approximately 30%, and NOx increased by about 10%.