Because most mechanical instruments have no special intelligent interface, it is difficult to achieve automatic data acquisition, at the same time the domestic meter specifications have not been completely unified, so...
详细信息
ISBN:
(纸本)9781450387811
Because most mechanical instruments have no special intelligent interface, it is difficult to achieve automatic data acquisition, at the same time the domestic meter specifications have not been completely unified, so it is difficult to achieve high accuracy and high efficiency by manual data collection. In recent years, with the continuous development of information technology and computer hardware, people's demand for intelligence is also increasing. In this paper, through the optimization of the meter image preprocessing a convolution neural network model based on improved LeNet-5 is proposed to identify the meter image. Using ReLU function instead of traditional sigmoid function to solve the problem of gradient dispersion, and using max pooling to improve the sampling richness. Adding the dropout function in the full connection layer to prevent the neural network from over fitting. The experimental results show that the prediction results can be improved by optimizing the image preprocessing and improving the network model of LeNet-5. The accuracy rate can reach 99.8%, and the recognition speed is fast.
Electric vehicles (EVs) are becoming more popular in modern society. These vehicles can be charged at home or in public areas with standard outlets. However, the extra power demand affects the distribution network (DN...
详细信息
ISBN:
(纸本)9781479924509
Electric vehicles (EVs) are becoming more popular in modern society. These vehicles can be charged at home or in public areas with standard outlets. However, the extra power demand affects the distribution network (DN) in terms of power losses. If these vehicles are connected into the DN during peak times, it increases the power losses. One effective methods to solve this issue would be the introduction of energy storage systems (ESSs). Therefore, both active and reactive power dispatch combined with different charging periods, off peak and peak, for the ESS is proposed in this paper. The research provides both uncoordinated optimal active-reactive power flow (UA-RPF) of the ESS and the coordinated optimal active-reactive power flow (CA-RPF) of the ESS, which improves the performance of the DN. Results for the IEEE-33 distribution system are presented. It is demonstrated that 1.43MW total power losses (TPL) and 1.64MW of imports from the transmission network (TN) can be reduced by using the proposed approach.
Distributed inductive power transfer (IPT) systems address the range restrictions of electric vehicles (EVs), charging the battery on-road through a loosely coupled transformer. Comparing different primary and seconda...
详细信息
ISBN:
(纸本)9781479922635
Distributed inductive power transfer (IPT) systems address the range restrictions of electric vehicles (EVs), charging the battery on-road through a loosely coupled transformer. Comparing different primary and secondary coil topologies is the main objective of this paper. Variations including single and multiphase layouts are analyzed by laboratory experimentation and finite element simulations. A system parameter optimization algorithm is introduced, utilizing sensitivity analysis techniques and equivalent circuit representation. Interphase power circulation in multiphase system primaries is addressed by a terminal correction setup, minimizing the interphase mutual inductance. The optimized designs are compared in terms of power and efficiency under alignment variations.
The increasing number of electric vehicles (EVs) in the near future will require control systems endowed with adequate algorithms able to manage their recharging process and avoiding massive investment in reinforcemen...
详细信息
ISBN:
(纸本)9781467380539
The increasing number of electric vehicles (EVs) in the near future will require control systems endowed with adequate algorithms able to manage their recharging process and avoiding massive investment in reinforcement of low voltage distribution network infrastructure. The deployment of EVs as an alternative to internal combustion engines will pose new challenges for electric power systems, grid operators, electricity suppliers and consumers. The impacts of the increasing penetration of EVs will be felt at the level of the distribution grid, as the lack of infrastructure capacity may hinder the increasing number of EVs from being simultaneously charged. Scenarios in which there is no local coordination between all the EVs to be charged through the same distribution power transformer may lead to new peak demands, possibly impeding the charging of all the vehicles. Therefore, the increasing number of EVs will require a control system to manage their recharging process. This study proposes the development of a decentralized charging control system, which is able to control and optimize the charging process of number of EVs in a coordinate way. Thus charging a greater number of EVs will be feasible without needing to invest in increasing the capacity of the grid infrastructure. To accomplish this, the algorithm considers the users' preferences, such as their next time of use and desired state of charge while taking every user's tariff scheme into consideration (i.e. different price structures/values and contracted power). The optimization objectives will be set for both the distribution grid operator, maximizing the number of EVs being charged simultaneously and for the consumers, minimizing the deviation from the minimum cost of the charge. Various entities are interested in such management. For instance, the distribution grid operator is interested in managing the charging to incorporate the maximum number of EVs without massively reinforcing the grid, whereas the co
Nurse rostering problem is to construct a nurse roster for a given period,which is *** this paper,we apply cuckoo search algorithm to the problem and adjust the parameters of the algorithm through *** show that the pr...
详细信息
Nurse rostering problem is to construct a nurse roster for a given period,which is *** this paper,we apply cuckoo search algorithm to the problem and adjust the parameters of the algorithm through *** show that the proposed algorithm performed well under many circumstances by comparison between our algorithm and other approximation algorithms.
This paper proposed an improved Stud Genetic algorithm using the Opposition-based strategy(SGAO) to improve the performance of the traditional SGA and accelerate its convergence *** SGAO,we use opposition-based approa...
详细信息
ISBN:
(纸本)9781510823808
This paper proposed an improved Stud Genetic algorithm using the Opposition-based strategy(SGAO) to improve the performance of the traditional SGA and accelerate its convergence *** SGAO,we use opposition-based approach to initialize the population and to perform mutation with the aim to improve the quality of *** experiments,we use some benchmark functions to the show the performance of the proposed approach and compare it with other algorithms such as genetic algorithm,different evolutionary,particle swarm optimization and stud genetic *** show that SGAO has faster convergence speed and higher solution precision.
Ecology evolutionary algorithm of food chain(EEAFC) as a new power transmission network planning approach is applied to power transmission network expansion planning,the objective function is selected as achieving min...
详细信息
Ecology evolutionary algorithm of food chain(EEAFC) as a new power transmission network planning approach is applied to power transmission network expansion planning,the objective function is selected as achieving minimal investment sum of transmission *** at the different characteristics of the scale and the quality of various populations in ecology evolutionary algorithm of food chain,selection methods such as proportional model and deterministic sampling are used in low population and intermediate population separately,senior population uses optimal reserved strategy but dose not use reproduction operator,which gives further consideration to both the overall search and the local search *** expansion transmission corridor as decision variable,a real number encoding method is proposed for reducing the dimension numbers of *** test was performed on the 18-bus system,the calculation results verify the feasibility and superiority of the proposed algorithm.
In this paper, a physical model device of twelve-accelerometer’ inertial measurement unit is designed and manufactured to solve the High-speed projectile attitude angular estimation’s low precision’s problem. And p...
详细信息
In this paper, a physical model device of twelve-accelerometer’ inertial measurement unit is designed and manufactured to solve the High-speed projectile attitude angular estimation’s low precision’s problem. And proposing methods to calibrate misalignment angle and position installation error. According to the mathematical model of angular speed solving with the installation errors, nonlinear least squares is used to compensate accelerometers’ installation errors. Simulation result shows that this method can suppress installation errors effectively and acquire attitude of high efficiency. This method has some actual application value.
This paper mainly focuses on the problem of optimal lane change between vehicle platoonings. In order to evaluate the influence of the speed fluctuation of the vehicle platooning system in different scenarios, a fluct...
详细信息
This paper mainly focuses on the problem of optimal lane change between vehicle platoonings. In order to evaluate the influence of the speed fluctuation of the vehicle platooning system in different scenarios, a fluctuation evaluation index is designed with consideration of merging comfort. Further, a corresponding optimization algorithm is proposed to search the optimal lane change speed and distance when vehicles request to merging into platoon. Above analysis is important because changing lane at the optimal speed can suppress the disturbance caused by merging into platoon and improve the stability of the vehicle platooning system, which has potential benefits for improving the merging comfort, and reducing the fuel consumption of the entire platoon system. Simulation results show that the proposed optimization algorithm is effective to find the value of lane change factors corresponding to the minimum system speed fluctuation.
In order to optimize the knapsack problem further, this paper proposes an innovative model based on dynamic expectation efficiency, and establishes a new optimization algorithm of 0-1 knapsack problem after analysis a...
详细信息
In order to optimize the knapsack problem further, this paper proposes an innovative model based on dynamic expectation efficiency, and establishes a new optimization algorithm of 0-1 knapsack problem after analysis and research. Through analyzing the study of 30 groups of 0-1 knapsack problem from discrete coefficient of the data, we can find that dynamic expectation model can solve the following two types of knapsack problem. Compared to artificial glowworm swam algorithm, the convergence speed of this algorithm is ten times as fast as that of artificial glowworm swam algorithm, and the storage space of this algorithm is one quarter that of artificial glowworm swam algorithm. To sum up, it can be widely used in practical problems.
暂无评论