- 标题
- 摘要
- 关键词
- 实验方案
- 产品
过滤筛选
- 2018
- Conditional Random Fields (CRF)
- Convolutional Neural Network (CNN)
- Fine Classification
- Airborne hyperspectral
- Optoelectronic Information Science and Engineering
- Wuhan University
- Central South University
- Hubei University
-
A convolutional neural network for prediction of laser power using melt-pool images in laser powder bed fusion
摘要： In laser powder bed fusion, a convolutional neural network could build a good regression model to predict a laser power value from a melt-pool image. To empirically validate it, we used the acquired image data from a monitoring system inside metal additive manufacturing equipment and optimally configured a convolutional network by the grid search of hyper-parameters. The proposed network showed only 0.12 % of test images were out of the criterion for judging the predicted laser power value to be reliable and showed more accurate results than deep feed-forward neural network in the prediction of laser power states unseen in training steps. We expect that the proposed model could be utilized to discover the problematic position in additive-manufactured layers causing defects during a process.
关键词： convolutional neural network,melt-pool image,process monitoring,metal additive manufacturing,laser powder bed fusion
更新于2025-09-19 17:13:59
-
[IEEE 2018 11th UK-Europe-China Workshop on Millimeter Waves and Terahertz Technologies (UCMMT) - HangZhou, China (2018.9.5-2018.9.7)] 2018 11th UK-Europe-China Workshop on Millimeter Waves and Terahertz Technologies (UCMMT) - Graphene-based THz Antenna with A Graphene-metal CPW Feeding Structure
摘要： This paper proposes an adaptive radial basis function (RBF) neural network (NN) fuzzy control scheme to enhance the performance of shunt active power ?lter (APF).The RBF NN is utilized on the approximation of nonlinear function in the APF dynamic model and the weights of the RBF NN are adjusted online according to adaptive law from the Lyapunov stability analysis to ensure the state hitting the sliding surface and sliding along it. In order to compensate the network approximation error and eliminate the existing chattering, the sliding mode control term is adjusted by adaptive fuzzy systems, which can enhance the robust performance of the system. The simulation results of APF using the proposed method con?rm the effectiveness of the proposed controller, demonstrating the outstanding compensation performance and strong robustness.
关键词： adaptive fuzzy control,Sliding mode control,radial basis function neural network (RBF NN)
更新于2025-09-19 17:13:59
-
CNN based automatic detection of photovoltaic cell defects in electroluminescence images
摘要： Automatic defect detection is gaining huge importance in photovoltaic (PV) field due to limited application of manual/visual inspection and rising production quantities of PV modules. This study is conducted for automatic detection of PV module defects in electroluminescence (EL) images. We presented a novel approach using light convolutional neural network architecture for recognizing defects in EL images which achieves state of the art results of 93.02 % on solar cell dataset of EL images. It requires less computational power and time. It can work on an ordinary CPU computer while maintaining real time speed. It takes only 8.07 milliseconds for predicting one image. For proposing light architecture, we perform extensive experimentation on series of architectures. Moreover, we evaluate data augmentation operations to deal with data scarcity. Overfitting appears a significant problem; thus, we adopt appropriate strategies to generalize model. The impact of each strategy is presented. In addition, cracking patterns and defects that can appear in EL images are reviewed; which will help to label new images appropriately for predicting specific defect types upon availability of large data. The proposed framework is experimentally applied in lab and can help for automatic defect detection in field and industry.
关键词： PV cell cracking,Automatic defect detection,Convolutional neural network (CNN),Electroluminescence,Deep learning,Photovoltaic (PV) modules
更新于2025-09-19 17:13:59
-
Forecasting the Performance of a Photovoltaic Solar System Installed in other Locations using Artificial Neural Networks
摘要： Photovoltaic solar energy has been spread all over the world, and in Brazil this energy source has been getting considerable space in the last years, being driven mainly by the energy crises. However, when installed in regions with low incidence of solar irradiation, this technology presents a loss of efficiency in the generation of energy. As an alternative to this consideration, a power prediction study could be conducted prior to its installation, based on local climate information that directly influences power generation, verifying the feasibility of system implementation and avoiding unrewarded investment. Therefore, the objective of this work is to predict the viability of the installation of a photovoltaic system of 3kWp in different places, with the assist of an Artificial Neural Network. Thus, the feedforward network was used for the training, being trained and validated with the support of MatlabVR , and inserting samples of temperature and solar irradiation as input variables. Through the performance methods, the results are favorable for this application, presenting validations with RMSE% in the range of 13-20% and R of not less than 0.93. The predictions presented RMSE% around 19-25% and average powers close to the real values generated by the PV system.
关键词： solar irradiation,renewable energy,electrical systems,energy efficiency,power forecasting,feedforward,artificial neural network,root mean square error,solar photovoltaic system,distributed generation
更新于2025-09-19 17:13:59
-
[IEEE 2019 15th International Conference on Emerging Technologies (ICET) - Peshawar, Pakistan (2019.12.2-2019.12.3)] 2019 15th International Conference on Emerging Technologies (ICET) - Performance Evaluation of an Evacuated Flat Plate Photovoltaic-Thermal (PVT) Collector for Heat and Electricity
摘要： To avoid resources on green earth being exhausted much earlier by human beings, energy saving has been one of the key issues in our everyday lives. In fact, energy control for some appliances is an effective method to save energy at home, since it prevents users from consuming too much energy. Even though there are numerous commercial energy-effective products that are helpful in energy saving for particular appliances, it is still hard to find a comprehensive solution to effectively reduce appliances’ energy consumption in a house. Therefore, in this paper, an intelligent energy control scheme, named the residence energy control system (RECoS) is proposed, which is developed based on wireless smart socket and Internet of Things technology to minimize energy consumption of home appliances without deploying sensors. The RECoS provides four control modes, including peak-time control, energy-limit control, automatic control, and user control. The former two are operated for all smart sockets in a house, while the latter two are used by individual smart sockets, aiming to enhance the functionality of energy control. The experimental results show that the proposed scheme can save up to 43.4% of energy for some appliances in one weekday.
关键词： smart living,neural network,Energy control system,smart socket,Internet of Things (IoT)
更新于2025-09-19 17:13:59
-
High coupling efficiency 2D metasurface integrated with strip waveguide in SOI for mid-IR wavelengths
摘要： To avoid resources on green earth being exhausted much earlier by human beings, energy saving has been one of the key issues in our everyday lives. In fact, energy control for some appliances is an effective method to save energy at home, since it prevents users from consuming too much energy. Even though there are numerous commercial energy-effective products that are helpful in energy saving for particular appliances, it is still hard to find a comprehensive solution to effectively reduce appliances’ energy consumption in a house. Therefore, in this paper, an intelligent energy control scheme, named the residence energy control system (RECoS) is proposed, which is developed based on wireless smart socket and Internet of Things technology to minimize energy consumption of home appliances without deploying sensors. The RECoS provides four control modes, including peak-time control, energy-limit control, automatic control, and user control. The former two are operated for all smart sockets in a house, while the latter two are used by individual smart sockets, aiming to enhance the functionality of energy control. The experimental results show that the proposed scheme can save up to 43.4% of energy for some appliances in one weekday.
关键词： smart living,smart socket,neural network,Internet of Things (IoT),Energy control system
更新于2025-09-19 17:13:59
-
Improving precision in the prediction of laser texturing and surface interference of 316L assessed by neural network and adaptive neuro-fuzzy inference models
摘要： Laser-based surface texturing provides highly controlled interference fit between two parts. In this work, artificial intelligence-based models were used to predict the surface properties of laser processed stainless steel 316 samples. Artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) were used to predict the characteristics of laser surface texturing. The models based on feedforward neural network (FFNN) were developed to examine the effect of the laser process parameters for surface texturing on 316L cylindrical pins. The accuracy of the models was measured by calculating the root mean square error and mean absolute error. The reliability of the ANFIS and FFNN models for the output prediction of the laser surface texturing (LST) system were investigated by using the data measured from experiments based on a 3^3 factorial design, with main processing parameters set as laser power, pulse repetition frequency, and percentage of laser spot overlap. The relative assessment of the models was performed by comparing percentage error prediction. Finally, the impact of input data was examined using predicted response surface plots. Results showed that ANFIS prediction was 48% more accurate compared with that provided by the FFNN model.
关键词： Artificial neural network,Adaptive neuro-fuzzy inference system,Laser texturing
更新于2025-09-19 17:13:59
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - An Economic and Environmental Assessment of Residential Rooftop Photovoltaics with Second Life Batteries in the US
摘要： Extreme learning machine (ELM) is emerged as an effective, fast, and simple solution for real-valued classification problems. Various variants of ELM were recently proposed to enhance the performance of ELM. Circular complex-valued extreme learning machine (CC-ELM), a variant of ELM, exploits the capabilities of complex-valued neuron to achieve better performance. Another variant of ELM, weighted ELM (WELM) handles the class imbalance problem by minimizing a weighted least squares error along with regularization. In this paper, a regularized weighted CC-ELM (RWCC-ELM) is proposed, which incorporates the strength of both CC-ELM and WELM. Proposed RWCC-ELM is evaluated using imbalanced data sets taken from Keel repository. RWCC-ELM outperforms CC-ELM and WELM for most of the evaluated data sets.
关键词： extreme learning machine,Real valued classification,complex valued neural network,class imbalance problem,regularization,weighted least squares error
更新于2025-09-19 17:13:59
-
[IEEE 2019 Research, Invention, and Innovation Congress (RI2C) - Bangkok, Thailand (2019.12.11-2019.12.13)] 2019 Research, Invention, and Innovation Congress (RI2C) - A Single-Stage High-Power-Factor LED Driver based on Interleaved ZCDS Class-E Rectifier
摘要： This paper presents a voice conversion (VC) method that utilizes the recently proposed probabilistic models called recurrent temporal restricted Boltzmann machines (RTRBMs). One RTRBM is used for each speaker, with the goal of capturing high-order temporal dependencies in an acoustic sequence. Our algorithm starts from the separate training of one RTRBM for a source speaker and another for a target speaker using speaker-dependent training data. Because each RTRBM attempts to discover abstractions to maximally express the training data at each time step, as well as the temporal dependencies in the training data, we expect that the models represent the linguistic-related latent features in high-order spaces. In our approach, we convert (match) features of emphasis for the source speaker to those of the target speaker using a neural network (NN), so that the entire network (consisting of the two RTRBMs and the NN) acts as a deep recurrent NN and can be fine-tuned. Using VC experiments, we confirm the high performance of our method, especially in terms of objective criteria, relative to conventional VC methods such as approaches based on Gaussian mixture models and on NNs.
关键词： recurrent temporal restricted Boltzmann machine (RTRBM),speaker specific features,voice conversion,Deep Learning,recurrent neural network
更新于2025-09-19 17:13:59
-
[IEEE 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - Chicago, IL, USA (2019.6.16-2019.6.21)] 2019 IEEE 46th Photovoltaic Specialists Conference (PVSC) - High Efficiency Semi-Transparent Organic Photovoltaics
摘要： A novel adaptive radial basis function neural network H-in?nity control strategy with robust feedback compensator using linear matrix inequality (LMI) approach is proposed for micro electro mechanical systems vibratory gyroscopes involving parametric uncertainties and external disturbances. The proposed system is comprised of a neural network controller, which is designed to mimic an equivalent control law aimed at relaxing the requirement of exact mathematical model and a robust feedback controller, which is derived to eliminate the effect of modeling error and external disturbances. Based on the Lyapunov stability theorem, it is shown that H-in?nity tracking performance of the gyroscope system can be achieved, all variables of the closed-loop system are bounded, and the effect due to external disturbances on the tracking error can be attenuated effectively. Numerical simulations are investigated to demonstrate that the satisfactory tracking performance and strong robustness against external disturbances can be obtained using the proposed adaptive neural H-in?nity control strategy with robust feedback compensator by LMI technique.
关键词： H-In?nity Control,Adaptive control,neural network control
更新于2025-09-19 17:13:59