This paper presents a comparative study between two maximum power point tracking (MPPT) algorithms, the incremental conductance algorithm (InC) and the fuzzy logic controller (FLC). The two algorithms were applied to a low photovoltaic power conversion system, and they both use different PI controllers and grid synchronization techniques. Moreover, both InC and FLC methods have Clarke and Park Transformation. To some extent, the incremental conductance and fuzzy logic controller approaches are similar, but their control loops are different. Therefore, the InC has classic Proportional Integrative (PI) controllers with simple phase-locked loops (PLL). At the same time, the FLC works with fuzzy logic PI controllers linked with the Second Order Generalized Integrator (SOGI). The proposed techniques examine the solar energy conversion performance of the photovoltaic (PV) system under possible irradiance changes and constant temperature conditions. Finally, a performance comparison has been made between InC and FLC, which demonstrates the effectiveness of the fuzzy controller over the incremental conductance algorithm. FLC turns to convert photovoltaic power easily, decreasing fluctuations, and it offers a quick response to the variation of solar irradiance (shading effect). The simulation results show a superior performance of the controller with fuzzy logic, which helps the inverter convert over 99% of the power generated by the photovoltaic panels. In comparison, the incremental conductance algorithm converts around 80%.
This paper presents a real-time implementation workflow of neural networks for autonomous driving tasks. The UNet structure is chosen for a road segmentation task, providing good performance for low complexity. The model is trained and validated using two datasets, KITTI (validation of the model with respect to state of art) and a local highway dataset (UHA dataset), collected by the laboratory research team. The performance of the model for road detection is evaluated using the F1 score metric. After a simulation validation on both sets, the model is integrated into a real vehicle through the RTMaps platform. The application is tested in real-time conditions, around the city, under various weather and light. Finally, the proposed model proves low complexity and good performance for real-time road detection tasks.
Intelligent vehicles (IVs) are pursued in both research laboratories and industries to revolutionize transportation systems. Since the driving surroundings can be cluttered and the weather conditions may vary, environment perception in IVs represents a challenging task. Therefore, multi-modal sensors are engaged. In perception, outstanding performance is obtained by employing deep learning algorithms. However, deep learning often relies on probabilities while there is a better formalism to handle prediction uncertainty. To circumvent this, in this work, evidence theory is combined with a camera-lidar-based deep learning fusion architecture. The coupling is based on generating basic belief functions using distance to prototypes. It also uses a distance-based decision rule. Because IVs have constrained computational power, a reduced deep-learning architecture is leveraged in this formulation. In the task of road detection, the evidential approach outperforms the probabilistic one. Besides, ambiguous features can be prudently settled as ignorance rather than making a possibly wrong decision using probability. The coupling is also extended to the task of semantic segmentation. This shows how evidential formulation can be easily adapted to the multi-class case. Therefore, the evidential formulation is generic and produces a more accurate and versatile prediction while maintaining the trade-off between performances and computational costs in IVs. This work uses the KITTI dataset.
1 November 2021 in IOP Conference Series: Earth and Environmental Science
The paper presents a low-power conversion system focusing on implementing new solar inverter control techniques implemented with Fuzzy Logic. The power generated by a solar panel requires robust approaches and efficient methods to be used at its maximum. Therefore, a promising strategy is a Fuzzy Logic based on the Maximum Power Point Tracking (MPPT) algorithm. To gather efficient power conversion, our proposed model uses a control loop composed of Fuzzy Proportional Integrative (PI) regulators, Clarke and Park transform, followed by a synchronization grid mechanism Second-order generalized integrator (SOGI) based phase-locked loops (PLLs). The proposed technique examines photovoltaic system (PV) performance with respect to its non-linearities and eventual shaded conditions that can occur in the PV array. The shading effect is tested by varying the irradiance, which determines the variation of the output current and implicitly of the output power. The simulation results show that the inverter control system is very efficient, generating stable and nearly sinusoidal current and voltage characteristics. Thus, the inverter converts over 99 % of the power generated by PV arrays.
In self-navigation problems for autonomous vehicles, the variability of environmental conditions, complex scenes with vehicles and pedestrians, and the high-dimensional or real-time nature of tasks make segmentation challenging. Sensor fusion can representatively improve performances. Thus, this work highlights a late fusion concept used for semantic segmentation tasks in such perception systems. It is based on two approaches for merging information coming from two neural networks, one trained for camera data and one for LiDAR frames. The first approach involves fusing probabilities along with calculating partial conflicts and redistributing data. The second technique focuses on making individual decisions based on sources and fusing them later with weighted Shannon entropies. The two segmentation models are trained and evaluated on a particular KITTI semantic dataset. In the realm of multi-class segmentation tasks, the two fusion techniques are compared and evaluated with illustrative examples. Intersection over union metric and quality of decision are computed to assess the performance of each methodology.
13 June 2025 in International Journal of Approximate Reasoning