- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
A Novel Charging and Discharging Algorithm of Plug-in Hybrid Electric Vehicles Considering Vehicle-to-Grid and Photovoltaic Generation
摘要： Considering, the high penetration of plug-in electric vehicles (PHEVs), the charging and discharging of PHEVs may lead to technical problems on electricity distribution networks. Therefore, the management of PHEV charging and discharging needs to be addressed to coordinate the time of PHEVs so as to be charged or discharged. This paper presents a management control method called the charging and discharging control algorithm (CDCA) to determine when and which of the PHEVs can be activated to consume power from the grid or supply power back to grid through the vehicle-to-grid technology. The proposed control algorithm considers fast charging scenario and photovoltaic generation during peak load to mitigate the impact of the vehicles. One of the important parameters considered in the CDCA is the PHEV battery state of charge (SOC). To predict the PHEV battery SOC, a particle swarm optimization-based artificial neural network is developed. Results show that the proposed CDCA gives better performance as compared to the uncoordinated charging method of vehicles in terms of maintaining the bus voltage profile during fast charging.
关键词： state of charge,artificial neural network,particle swarm optimization,plug-in hybrid electric vehicle,charging and discharging control algorithm
更新于2025-09-16 10:30:52
-
[IEEE 2019 18th International Conference on Optical Communications and Networks (ICOCN) - Huangshan, China (2019.8.5-2019.8.8)] 2019 18th International Conference on Optical Communications and Networks (ICOCN) - Calibration of a 2×2 Optical Switch Based on the Back-Propagation Artificial Neural Network
摘要： We propose a method to calibrate 2×2 dual-ring assisted Mach-Zehnder interferometer switches based on a back-propagation artificial neural network (BP-ANN). The DR-MZI switch can be set to the cross or bar state at any operating wavelength in a free spectral range with the BP-ANN based algorithm. It is an effective method that can be adopted for calibration of DR-MZI switch elements in a large-scale switch fabric.
关键词： artificial neural network,device calibration,optical switch
更新于2025-09-16 10:30:52
-
Reinforcement Learning-Based Energy Management of Smart Home with Rooftop Solar Photovoltaic System, Energy Storage System, and Home Appliances
摘要： This paper presents a data-driven approach that leverages reinforcement learning to manage the optimal energy consumption of a smart home with a rooftop solar photovoltaic system, energy storage system, and smart home appliances. Compared to existing model-based optimization methods for home energy management systems, the novelty of the proposed approach is as follows: (1) a model-free Q-learning method is applied to energy consumption scheduling for an individual controllable home appliance (air conditioner or washing machine), as well as the energy storage system charging and discharging, and (2) the prediction of the indoor temperature using an artificial neural network assists the proposed Q-learning algorithm in learning the relationship between the indoor temperature and energy consumption of the air conditioner accurately. The proposed Q-learning home energy management algorithm, integrated with the artificial neural network model, reduces the consumer electricity bill within the preferred comfort level (such as the indoor temperature) and the appliance operation characteristics. The simulations illustrate a single home with a solar photovoltaic system, an air conditioner, a washing machine, and an energy storage system with the time-of-use pricing. The results show that the relative electricity bill reduction of the proposed algorithm over the existing optimization approach is 14%.
关键词： reinforcement learning,smart grid,artificial neural network,smart home,consumer comfort,home energy management system
更新于2025-09-16 10:30:52
-
A Hybrid Intelligent Approach for Solar Photovoltaic Power Forecasting: Impact of Aerosol Data
摘要： The penetration of solar photovoltaic (PV) power in distributed generating system is increasing rapidly. The increased level of PV penetration causes various issues like grid stability, reliable power generation and power quality; therefore, it becomes utmost important to forecast the PV power using the meteorological parameters. The proposed model is developed on the basis of meteorological data as input parameters, and the impacts of these parameters have been analyzed with respect to forecasted PV power. The main focus of this research is to explore the performance of optimization-based PV power forecasting models with varying aerosol particles and other meteorological parameters. A newly developed intelligent approach based on grey wolf optimization (GWO) using multilayer perceptron (MLP) has been used to forecast the PV power. The performance of the GWO-based MLP model is evaluated on the basis of statistical indicators such as normalized mean bias error (NMBE), normalized mean absolute error (NMAE), normalized root-mean-square error (NRMSE) and training error. The results of the developed model show the values of NMBE, NMAE and NRMSE as 2.267%, 4.681% and 6.67% respectively. To validate the results, a comparison has been made with particle swarm optimization, Levenberg–Marquardt algorithm and adaptive neuro-fuzzy approach. The performance of the model is found better as compared to other intelligent techniques. The obtained results may be used for demand response applications in smart grid environment.
关键词： Solar power forecasting,Artificial neural network,Distributed power generation,Grey wolf optimization,Solar PV
更新于2025-09-16 10:30:52
-
Feasibility of gem identification using reflectance spectra coupled with artificial intelligence
摘要： Standard traditional gem identification requires expert supervision, while sophisticated modern methods are time-consuming and expensive. In contrast, reflectance spectroscopy coupled with artificial intelligence is economical and convenient and does not require specialist supervision. This study established an artificial neural network model that consists of standard multilayered, feed-forward, and back-propagation neural networks, and obtained reflectance spectra of a transparent gem (almandine), an opaque gem (turquoise), several almandine imitations (agate, plastic, and glass), and several treated turquoise samples (dyed, impregnated, and Zachery treated) using an Analytical Spectral Devices spectrometer. The acquired spectra were used to train and test the artificial neural network model. The results show that the model can effectively discriminate between genuine and imitation gems of different classes. However, discrimination between natural and treated gems of same class is not as effective as discrimination of gems of different classes. The results suggest that an artificial neural network based on reflectance spectroscopy could serve as a useful tool for preliminary gem identification, and the advanced identification needs further training and investigation.
关键词： reflectance spectrum,artificial neural network,Artificial intelligence,gem identification
更新于2025-09-12 10:27:22
-
Systematic approach for determining optimal processing parameters to produce parts with high density in selective laser melting process
摘要： Relying on trial-and-error methods to determine the optimal processing parameters which maximize the density of parts produced using selective laser melting (SLM) technique is costly and time consuming. With a given SLM machine characteristics (e.g., laser power, scanning speed, laser spot size, and laser type), powder material, and powder size distribution, the present study proposes a more systematic strategy to reduce the time and cost in finding optimal parameters for producing high-density components. In the proposed approach, a circle packing design algorithm is employed to identify 48 representative combinations of the laser scanning speed and laser power for a commercial Nd:YAG SLM system. For each parameter combination, finite element heat transfer simulations are performed to calculate the melt pool dimensions and peak temperature for 316L stainless steel powder deposited on a 316L substrate. The simulated results are then used to train the artificial neural networks (ANNs). The trained ANNs are used to predict the melt pool dimensions and peak temperature for 3600 combinations of the laser power and laser speed in the design space. The resulting processing maps are then inspected to determine the particular parameter combinations which produce stable single scan tracks with good adhesion to the substrate and a peak temperature lower than the evaporation point of the SS 316L powder bed. Finally, the surface roughness measurements are employed to confirm the parameter settings which maximize the SLM component density. The experimental results show that the proposed approach results in a maximum component density of 99.97 %, an average component density of 99.89%, and a maximum standard deviation of 0.03%.
关键词： Additive manufacturing,Selective laser melting,Surface roughness,Artificial neural network,Surrogate model
更新于2025-09-12 10:27:22
-
Free Space Optical Communication (System Design, Modeling, Characterization and Dealing with Turbulence) || 4. Mitigation of beam wandering due to atmospheric turbulence and prediction of control quality using intelligent decision making tools
摘要： In a Free Space Optical Link (FSOL), atmospheric turbulence causes fluctuations in both intensity and phase of the received beam and impairs link performance. Beam motion is one of the main causes for major power loss. This chapter presents an investigation of the performance of two types of controller designed for aiming a laser beam at a particular spot under dynamic disturbances. Multiple experiment observability nonlinear input-output data mapping is used as the principal component for the controllers’ design. The first design is based on the Taguchi method while the second is the Artificial Neural Network (ANN) method. These controllers process the beam location information from a static linear map of a 2D plane: Optoelectronic Position Detector (OPD) as observer, and then generate the necessary outputs to steer the beam with a micro-electromechanical mirror: Fast Steering Mirror (FSM). The beam centroid is computed using a Mono-Pulse Algorithm (MPA). Evidence of suitability and effectiveness of the proposed controllers are comprehensively assessed and quantitatively measured in terms of coefficients of correlation, correction speed, control exactness, centroid displacement and stability of the receiver signal through the experimental results from the FSO link setup established for the horizontal range of 0.5 km at an altitude of 15.25 m. The test field type is open flat terrain, grass and a few isolated obstacles.
关键词： atmospheric turbulence,Artificial Neural Network (ANN),Mono-Pulse Algorithm (MPA),Fast Steering Mirror (FSM),beam wandering,Taguchi method,Free Space Optical Link (FSOL),Optoelectronic Position Detector (OPD)
更新于2025-09-12 10:27:22
-
Free Space Optical Communication (System Design, Modeling, Characterization and Dealing with Turbulence) || 5. Low power and compact RSM and neural-controller design for beam wandering mitigation with a horizontal-path propagating Gaussian-beam wave: focused beam case
摘要： Beam wander on the detector plane is one of the main causes of major power loss which severely degrades the performance of Free Space Optical (FSO) links. Confronted with this big problem, designing a suitable controller to compensate beam wandering at a fast rate so as to increase beam stability becomes significant. This chapter presents an investigation of the performance of two types of controller designed for increasing the stability of the beam on the detector plane under dynamic disturbances. The first design is based on Taguchi’s method: Response Surface Model (RSM) controller while the second is the Artificial Neural Network (ANN) method (neural-controller). These controllers process the beam spot information and generate the necessary outputs to mitigate beam wandering, so as to perfectly couple the Power In the Bucket (PIB): receiver aperture, into the detector. Pipelined-parallel architecture for both controllers are proposed and developed in a Field Programmable Gate Array (FPGA). The implementation of these two candidate controllers is described in detail as installed at the receiver station. Evidence of the suitability and the effectiveness of the proposed controllers in terms of prediction exactness, prediction error, reduction of beam wander, response to impulse and effective scintillation index are provided through experimental results from the FSO link established for the horizontal range of 0.5 km at an altitude of 15.25 m.
关键词： Artificial Neural Network (ANN),Field Programmable Gate Array (FPGA),beam wander,Free Space Optical (FSO) links,Response Surface Model (RSM)
更新于2025-09-12 10:27:22
-
Optimized hatch space selection in double-scanning track selective laser melting process
摘要： Additive manufacturing (AM) techniques such as selective laser melting (SLM) have many advantages over traditional manufacturing methods. However, the quality of SLM products is critically dependent on the process parameters, e.g., the laser power, scanning speed, powder layer thickness, hatch space, and scan length. Determining the parameter settings which optimize the product quality is a challenging, but extremely important problem for manufacturers. In a previous study, the present group determined the optimal values of the laser power and scanning speed for 316L stainless steel powder beds. The present study extends this work to investigate the effects of the hatch space and scan length on the melting pool characteristics in a double-scanning track SLM process. A three-dimensional finite element model is constructed to predict the features of the scan track melt pool for various values of the hatch space and scan length. A circle packing design method is then used to select a representative set of hatch space and scan length parameters to train artificial neural networks (ANNs) to predict the melt pool temperature, melt pool depth, and overlap rate between adjacent the trained ANNs are used to create process maps relating the scan track features to the hatch space and scan length. The optimal hatch space and scan length region of the temperature process map is then determined based on a joint consideration of the peak temperature (less than 3300 K), the difference in depth of adjacent melt pools (less than 10 μm), and the overlap rate of adjacent scan tracks (25~35%). The results indicate that the optimal hatch space is equal to 61% of the laser spot size given an SLM system with a laser power of 180 W, a scanning speed of 680 mm/s, a laser spot size of 120 μm, and a 316L SS powder layer thickness of 50 μm.
关键词： Artificial neural network,Parameter optimization,Selective laser melting,Hatch space,Surrogate modeling
更新于2025-09-12 10:27:22
-
A prediction model for finding the optimal laser parameters in additive manufacturing of NiTi shape memory alloy
摘要： Shape memory alloys (SMAs) have been applied for various applications in the fields of aerospace, automotive, and medical. Nickel-titanium (NiTi) is the most well-known alloy among the others due to its outstanding functional characteristics including superelasticity (SE) and shape memory effect (SME). These particular properties are the result of the reversible martensite-to-austenite and austenite-to-martensite transformations. In recent years, additive manufacturing (AM) has provided a great opportunity for fabricating NiTi products with complex shapes. Many researchers have been investigating the AM process to set the optimal operational parameters, which can significantly affect the properties of the end-products. Indeed, the functional and mechanical behavior of printed NiTi parts can be tailored by controlling laser power, laser scan speed, and hatch spacing having them a crucial role in properties of 3D-printed parts. In particular, the effect of the input parameters can significantly alter the mechanical properties such as strain recovery rates and the transformation temperatures; therefore, using suitable parameter combination is of paramount importance. In this framework, the present study develops a prediction model based on artificial neural network (ANN) to generate a nonlinear map between inputs and outputs of the AM process. Accordingly, a prototyping tool for the AM process, also useful for dealing with the settings of the optimal operational parameters, will be built, tested, and validated.
关键词： Shape memory alloys,Modeling,NiTi,Artificial neural network,Additive manufacturing
更新于2025-09-12 10:27:22