- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Optimal Pulse-Shaping in Actively Q-Switched Ytterbium-Doped Fiber Lasers
摘要： In an actively Q-switched ?ber laser (AQS-FL) a type of acousto-optic modulator (AOM) or (potentially) electro-optic modulator (EOM) controls the generation of output nanosecond wide pulses. An integrated Gaussian pulse shape is desirable in many applications such as material processing, microfab- rication, ultrasound generation, gold photothermal therapy, etc. However, because of the system dynamics, generation of perfect Gaussian pulse shapes is not guaranteed in an AQS-FL, additionally designing the AQS-FL for a desired pulse peak and duration is an inverse problem which needs cumbersome trial- error efforts. We have developed a framework consisting of a rigorous FDM method plus a dedicated and innovative multi-objective genetic algorithm (GA) which assists the designer in achieving the desired Gaussian pulses within a reasonable time frame. The developed GA evolves the timing parameters of modulator plus the pump power and ?ber length until the suitable goal is reached. To demonstrate the ?exibility and design feasibility of our GA, three different single pulse and pulse train generation scenarios on a 7.5 m long Ytterbium-doped double clad ?ber (YD-DCF) are examined to achieve the Gaussian,150 Wand 200 W peak power, 250 ns and 300 ns width pulses. To the best of our knowledge, it is the ?rst implementation of an intelligent algorithm for optimizing the output pulse of an AQS-FL. It is worth noting that depending on the ?ber host material and modulator speci?cations, much higher peak powers and different pulse durations are feasible, furthermore in case of utilizing the AOM, the pertaining limitations and feasibility are considered.
关键词： Fiber laser,genetic algorithm (GA),optimization,Q-switching
更新于2025-09-23 15:21:01
-
[IEEE 2019 IEEE 13th International Conference on Compatibility, Power Electronics and Power Engineering (CPE-POWERENG) - Sonderborg, Denmark (2019.4.23-2019.4.25)] 2019 IEEE 13th International Conference on Compatibility, Power Electronics and Power Engineering (CPE-POWERENG) - An AN-GA Controlled SEPIC Converter for Photovoltaic Grid Integration
摘要： In this paper, Artificial Neural Network (ANN) optimization with Genetic Algorithm (GA) is implemented. The optimized training to ANN is provide using Bayesian regulation. For this study, a Photovoltaic (PV) system has considered and optimal power tracking been interpreted with proper adjustment of ANN weights using GA approach, which reduces the Root Mean Square Error (RMSE). In this work, the single-ended primary – inductor converter (SEPIC) has been utilized for better power tracking from PV modules. SEPIC Converter accomplish with impedance matching power device and provides utmost PV power tracking. Space vector pulse width modulation-dSPACE interface been utilized as an inverter control. Simulated responses show the potency of the proposed system under sag, swell and varying loading conditions.
关键词： Root Mean Square Error (RMSE),SEPIC.,Grid,Photovoltaic,Artificial neural network (ANN),Genetic Algorithm (GA)
更新于2025-09-19 17:13:59
-
Visual Docking Against Bubble Noise With 3-D Perception Using Dual-Eye Cameras
摘要： Recently, many studies have been performed worldwide to extend the persistence of underwater operations by autonomous underwater vehicles. Underwater battery recharging technology is one of the solutions even though challenges still remain. The docking function plays an important role not only in battery recharging but also in other advanced applications, such as intervention. Visual servoing in undersea environments inevitably encounters difficulties in recognizing the environment when captured images are disturbed by noise. This study describes the effective recognition performance and robustness against air bubble disturbances in images captured by a real-time position and orientation (pose) tracking and servoing system using stereo vision for a visual-servoing-type underwater vehicle. The recognition of the vehicle pose based on dynamic images captured by dual video cameras was performed by a real-time multistep genetic algorithm (RM-GA). In previous studies, the docking performance was investigated under the condition that there were no disturbances in the captured images that address image degradation. In this paper, the robustness of the RM-GA against air bubble disturbances was verified through visual servoing and docking experiments in a pool test to confirm that the system can continue to recognize the pose of the 3-D marker and can maintain the desired pose by visual servoing. Then, the effectiveness of the proposed system against real disturbances such as turbidity that may degrade the visibility of the system in the sea was confirmed by conducting the docking experiment in a real sea, having verified the practicality of the proposed method.
关键词： genetic algorithm (GA),Air bubble noises,visual servoing,dual-eye cameras,underwater vehicle
更新于2025-09-11 14:15:04
-
[IEEE IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Valencia, Spain (2018.7.22-2018.7.27)] IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium - Innovative Multi Pcnn Based Network for Green Area Monitoring - Identification and Description of Nearly Indistinguishable Areas - In Hyperspectral Satellite Images
摘要： The paper presents an original neural network approach for region of interest detection and classification in multi-spectral satellite images. The proposed method uses a sequence of Pulse Coupled Neural Networks that identifies plausible regions of interest. These regions are passed to a dimension reduction algorithm, Principle Component Analysis, in order to generate the input data for a Support Vector Machine classifier, that validates the data. The algorithm's parameters are optimized using a Genetic Algorithm. The algorithm is designed to distinguish regions that are extremely similar, such as parks in a city that has entire districts made up of houses with yards. The algorithm has been tested on images provided by the Sentinel-2 satellite, and it proved that it can recall 76.85% of the pixels marked as park in the ground truth data, which was obtained from OpenStreetMap.
关键词： Genetic Algorithm (GA),Pulse Coupled Neural Network (PCNN),Principle Component Analysis (PCA),Support Vector Machine (SVM)
更新于2025-09-10 09:29:36
-
An enhanced Dynamic Modeling of PV Module Using Levenberg- Marquardt Algorithm
摘要： An improved dynamic modeling of PV cell/modules based on automatic parameters extraction is proposed in this paper. For the sake of clarity, three models are compared in this study including, Single Diode (SDM), Double Diode (DDM) and the empirical model developed by Sandia National Laboratory (SANDIA). The use of nominal parameters or the values given by manufacturer in both SDM and DDM diode saturation current I0 and photo-generation current Iph equations can engender a significant error depending on the operating conditions and the consumed lifetime. Hence, these values can be handled as model parameters, and can be adjusted using automatic parameters extraction algorithms. Moreover, parameters based on static extraction methods (with fixed irradiation and temperature) namely, Rs, Rsh and n do not give satisfactory results under variable irradiation and temperature, which involve the use of a dynamic adjustment method to improve these parameters. In this way, static parameters extraction using genetic algorithm (GA) is proposed as a first stage for both SDM and DDM. After that, a dynamic parameters extraction based on the Levenberg-Marquardt algorithm (LMA) has been employed in the purpose to adjust some nominal parameters provided by the literature and the manufacturer, and those given by the static method. The idea consists of considering the PV module and the MPPT as a single system with dynamic inputs (irradiation and temperature) and output (Impp, Vmpp and Pmpp) to minimize the error between the measured and the simulated outputs. The validity of the proposed approach is compared with dynamic LMA models, nominal parameters based models, and the models based on static GA extracted parameters under of different weather conditions and out-door measurements. The improved models show promising results in terms of agreement with real data.
关键词： Photovoltaic module,Genetic Algorithm (GA),Dynamic Parameters Extraction,Static Parameters Extraction,Levenberg- Marquardt (LM)
更新于2025-09-04 15:30:14