scholarly journals A Fault Warning Method for Electric Vehicle Charging Process Based on Adaptive Deep Belief Network

2021 ◽  
Vol 12 (4) ◽  
pp. 265
Author(s):  
Dexin Gao ◽  
Yi Wang ◽  
Xiaoyu Zheng ◽  
Qing Yang
Keyword(s):  
Electric Vehicle ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Deep Belief Network ◽  
Time Data ◽  
Belief Network ◽  
Electric Vehicle Charging ◽  
Pearson Coefficient ◽  
Ev Model ◽  
Ev Charging

If an accident occurs during charging of an electric vehicle (EV), it will cause serious damage to the car, the person and the charging facility. Therefore, this paper proposes a fault warning method for an EV charging process based on an adaptive deep belief network (ADBN). The method uses Nesterov-accelerated adaptive moment estimation (NAdam) to optimize the training process of a deep belief network (DBN), and uses the historical data of EV charging to construct the ADBN of the normal charging process of an EV model. The real-time data of EV charging is obtained and input into the constructed ADBN model to predict the output, calculate the Pearson coefficient between the predicted output and the actual measured value, and judge whether there is a fault according to the size of the Pearson coefficient to realize the fault warning of the EV charging process. The experimental results show that the method is not only able to accurately warn of a fault in the EV charging process, but also has higher warning accuracy compared with the back propagation neural network (BPNN) and conventional DBN methods.

scholarly journals Deep Belief Network for Predicting the Predisposition to Lung Cancer in TP53 Gene

2020 ◽  
pp. 171-177 ◽  
Author(s):  
Zahraa Naser Shahweli
Keyword(s):  
Neural Network ◽  
Lung Cancer ◽  
Smoking Habit ◽  
Back Propagation ◽  
Tp53 Gene ◽  
Back Propagation Neural Network ◽  
Biological Data ◽  
Deep Belief Network ◽  
Restricted Boltzmann Machines ◽  
Belief Network

Lung cancer, similar to other cancer types, results from genetic changes. However, it is considered as more threatening due to the spread of the smoking habit, a major risk factor of the disease. Scientists have been collecting and analyzing the biological data for a long time, in attempts to find methods to predict cancer before it occurs. Analysis of these data requires the use of artificial intelligence algorithms and neural network approaches. In this paper, one of the deep neural networks was used, that is the enhancer Deep Belief Network (DBN), which is constructed from two Restricted Boltzmann Machines (RBM). The visible nodes for the first RBM are 13 nodes and 8 nodes in each hidden layer for the two RBMs. The enhancer DBN was trained by Back Propagation Neural Network (BPNN), where the data sets were divided into 6 folds, each is split into three partitions representing the training, validation, and testing. It is worthy to note that the proposed enhancer DBN predicted lung cancer in an acceptable manner, with an average F-measure value of  0. 96 and an average Matthews Correlation Coefficient (MCC) value of 0. 47 for 6 folds.

Research and Implementation of Temperature-Rise Test System for Electric Vehicle Charging Coupler

2013 ◽  
Vol 333-335 ◽  
pp. 2327-2332
Author(s):  
Xuan Zhang ◽  
Zhi Ming Li ◽  
Xu Ling Li
Keyword(s):  
Electric Vehicle ◽  
Temperature Rise ◽  
Virtual Instrument ◽  
Critical Factor ◽  
Test System ◽  
Current Data ◽  
Time Data ◽  
Data Preservation ◽  
Electric Vehicle Charging ◽  
Ev Charging

The safety performance of Electric Vehicle (EV) charging equipments during the charging process will be the critical factor to the development of EVs Industry. Because of the high investment costs and the low accuracy of temperature-rise test system for EV charging coupler, a new remote test system including virtual instrument LabVIEW technology and communication transformation technology is applied to practical work. One temperature-rise test system designed for EV charging coupler is shown in this paper. With the advantages of LabVIEW as graphic programming and multithreading, real-time data acquisition, on-line monitoring and dynamic data preservation can be achieved by this temperature-rise test system. This test system simulates the change status of current data and makes a comprehensive research and evaluation temperature-rise characteristics of the charging coupler by analyzing the collected parameters and historical data when charging for EV.

Study of damage identification for bridges based on deep belief network

2020 ◽  
Vol 23 (8) ◽  
pp. 1562-1572
Author(s):  
Qi Guo ◽  
Lei Feng ◽  
Ruyi Zhang ◽  
Haijun Yin
Keyword(s):  
Neural Network ◽  
Damage Identification ◽  
Damage Index ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Deep Belief Network ◽  
Belief Network ◽  
Modal Data ◽  
Damage Location ◽  
Incomplete Measurement

To solve the problem of poor anti-noise ability faced by traditional pattern recognition methods in damage identification field, a bridge damage identification method based on deep belief network was proposed. Taken the modal curvature difference as the damage index, three restricted Boltzmann machines were constructed for pre-training. Then, the Softmax classifier and neural network were used to identify the damage location and degree under the environmental cases of no noise, weak noise, and strong noise, respectively. Subsequently, the influence of incomplete measurement modal data on the method was studied. Finally, damage identification based on deep belief network was implemented to a continuous beam bridge and compared with that of the back propagation neural network. The results showed that the proposed method could be highly effective not only on damage location but also on degree identification. Compared with back propagation neural network, deep belief network method may possess better identification ability and stronger anti-noise ability. It also demonstrates good identification effect under the condition of incomplete measurement modal data.

scholarly journals Leveraging User Preferences to Develop Profitable Business Models for Electric Vehicle Charging

2021 ◽  
Vol 12 (2) ◽  
pp. 60
Author(s):  
Felix Röckle ◽  
Thimo Schulz
Keyword(s):  
Case Studies ◽  
Electric Vehicle ◽  
Business Models ◽  
Brand Image ◽  
User Preferences ◽  
Value Network ◽  
Electric Vehicle Charging ◽  
Utility Companies ◽  
Physical Assets ◽  
Ev Charging

To design profitable business models for electric vehicle (EV) charging it is necessary to understand user preferences. For this purpose, prior literature is analyzed to develop a conceptual framework linking a company’s assets, the surrounding value network, and user preferences. Then, survey insights from two EV charging projects (ultra-E, SLAM) are summarized to illustrate user preferences in this area. Based on this data, the framework is eventually visualized by applying it to four case studies from the EV charging market. Based on the case studies, the following six key findings are derived: 1. Companies that have a very strong position in one of the three resource classes that define the quality-of-service provision (physical assets, digital assets, brand image) demand a higher price for fast charging. 2. Utility companies leverage their existing customer base. 3. New to the industry firms leverage their brand image to enter the market. 4. Selling below cost is not sustainable. 5. Sharp price distinctions reflect the power balance within the value network. 6. Power plays may result in a fragmented market.

scholarly journals Selecting Locations of Electric Vehicle Charging Stations Based on the Traffic Load Eliminating Method

Energies ◽  
2020 ◽  
Vol 13 (7) ◽  
pp. 1650 ◽  
Author(s):  
Bong-Gi Choi ◽  
Byeong-Chan Oh ◽  
Sungyun Choi ◽  
Sung-Yul Kim
Keyword(s):  
Electric Vehicle ◽  
Electric Vehicles ◽  
Traffic Load ◽  
Queueing Model ◽  
Traffic Data ◽  
Electric Vehicle Charging ◽  
Supply Equipment ◽  
Charging Stations ◽  
Ev Charging ◽  
Charging Demand

Establishing electric vehicle supply equipment (EVSE) to keep up with the increasing number of electric vehicles (EVs) is the most realistic and direct means of promoting their spread. Using traffic data collected in one area; we estimated the EV charging demand and selected priority fast chargers; ranging from high to low charging demand. A queueing model was used to calculate the number of fast chargers required in the study area. Comparison of the existing distribution of fast chargers with that suggested by the traffic load eliminating method demonstrated the validity of our traffic-based location approach.

scholarly journals Lateral and Longitudinal Driving Behavior Prediction Based on Improved Deep Belief Network

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8498
Author(s):  
Lei Yang ◽  
Chunqing Zhao ◽  
Chao Lu ◽  
Lianzhen Wei ◽  
Jianwei Gong
Keyword(s):  
Neural Network ◽  
Rbf Neural Network ◽  
Back Propagation ◽  
Front Wheel ◽  
Driving Behavior ◽  
Deep Belief Network ◽  
Intelligent Vehicles ◽  
Support Vector ◽  
Safe Driving ◽  
Belief Network

Accurately predicting driving behavior can help to avoid potential improper maneuvers of human drivers, thus guaranteeing safe driving for intelligent vehicles. In this paper, we propose a novel deep belief network (DBN), called MSR-DBN, by integrating a multi-target sigmoid regression (MSR) layer with DBN to predict the front wheel angle and speed of the ego vehicle. Precisely, the MSR-DBN consists of two sub-networks: one is for the front wheel angle, and the other one is for speed. This MSR-DBN model allows ones to optimize lateral and longitudinal behavior predictions through a systematic testing method. In addition, we consider the historical states of the ego vehicle and surrounding vehicles and the driver’s operations as inputs to predict driving behaviors in a real-world environment. Comparison of the prediction results of MSR-DBN with a general DBN model, back propagation (BP) neural network, support vector regression (SVR), and radical basis function (RBF) neural network, demonstrates that the proposed MSR-DBN outperforms the others in terms of accuracy and robustness.

scholarly journals Performance Estimation of Wireless Electric Vehicle Charging System Based On Magnetic Coupling

2019 ◽  
Vol 8 (6) ◽  
pp. 4389-4394
Keyword(s):  
Electric Vehicle ◽  
Magnetic Coupling ◽  
Operating Regime ◽  
Performance Estimation ◽  
Ohmic Loss ◽  
Design Guideline ◽  
Charging System ◽  
Electric Vehicle Charging ◽  
Power Transfer Efficiency ◽  
Ev Charging

In order to achieve an efficient wireless Electric Vehicle (EV) charging system in non-ideal practical scenarios, a proper design guideline has been delineated through the simulation, theoretical calculation as well as experimental investigation. It is examined that the wireless power transfer efficiency (WPTE) is invariably affected by the configuration of the charging coils (coil radius & number of turns), coupling to loss ratio, ohmic loss, radiation resistance, operating frequency, magnetic coupling as well as physical air gap between the coils. It is found that there is a certain operating regime at which maximum WPTE can be uphold. The acquired results provide a comprehensive strategic plan that can be used in EV charging system

scholarly journals A Review of High Efficiency Non-Isolated DC-DC Power Converters for Electric Vehicle Charging Application

2020 ◽  
Vol 6 (1) ◽  
pp. 60-74
Author(s):  
Ratil H Ashique
Keyword(s):  
Electric Vehicle ◽  
High Efficiency ◽  
Power Converters ◽  
Renewable Energy Sources ◽  
Pulse Frequency ◽  
Soft Switching ◽  
Electric Vehicle Charging ◽  
Dc Power ◽  
Vehicle Charging ◽  
Ev Charging

The electric vehicle (EV) charging systems employ dc-dc power converters as EV chargers. Currently, the expected high penetration of electric vehicle (EV) demands for the integration of the renewable energy sources (RES) into the electric vehicle charging system as a promising solution to cut down the load on the electrical grid. These systems interface with RES by implementing dc-dc power converters. Moreover, with the advent of high-power dc charging, the charging efficiency is largely dependent on the performance of the power converters. Hence, to improve the charging, the soft switching dc-dc converters are implemented to maintain low switching losses and to achieve high-efficiency operation. This paper reviews the non-isolated, soft switching dc-dc power converters for EV charging application. For this purpose, different types of soft switching topologies, namely the snubber, the series resonant, the shunt resonant and the pulse frequency modulated converters are investigated. The advantages and the disadvantages associated with these converters are highlighted. Furthermore, to perform a comparative evaluation, the topologies are simulated in a standard simulation platform. Consequently, the relative standing of the converters depending on several parameters, i.e. the component count, the output voltage and current ripple, the soft switching range, and the power losses are established. Finally, based on these results, the optimum applicability of the converters in the EV charging application is determined. GUB JOURNAL OF SCIENCE AND ENGINEERING, Vol 6(1), Dec 2019 P 60-74

Sign in / Sign up

Export Citation Format

Share Document