Earticle

This essay proposes a method of BP neural network constrained optimization based on previous studies. The optimization method based on the BP neural network, takes the minimum output of a neural network as an example, gives the general mathematical models, derives and gives the partial derivatives of BP network's output to input, and uses the Sigmoid Function as the transmission function in the article. On the previous studies basis, the basic ideas, algorithms and related models are given, based on the constrained optimization issues of BP neural network. We can adjust the input values of BP neural network to obtain the minimum or maximum output value by using this method. This optimization method links the optimization and fitting of BP networks together and expands the application of the BP neural network. At last, in this essay, the optimization method is applied in an example.

Accurate forecast of logistics demand can provide scientific guidance for logistics planning and decision making. With the complexity and uncertainty characteristics in logistics demand, the forecasting of logistics demand shows comprehensive and complex. The forecasting precision of the traditional forecasting methods often are not satisfying. It is necessary to look for novel forecasting methods to enhance the forecasting precision of logistics demand. Integrating the unbiased GM (1,1) model (UGM (1,1)) into the adaptive inertia weight particle swarm optimization (AIWPSO) algorithm, this paper developed a novel model for forecasting logistics demand, called AIWPSO-UGM (1,1) model, in which the UGM (1,1) model was used to forecast logistics demand and the AIWPSO algorithm was adopted to optimize the grey parameters needed in UGM (1,1) model. Two examples were selected to prove the out-of-sample performance of the AIWPSO-UGM (1,1) model in forecasting logistics demand. The results imply that the proposed AIWPSO-UGM (1,1) model performs better in logistics demand forecasting compared to the GM (1,1) model optimized by AIWPSO algorithm (AIWPSO-GM (1,1)), UGM (1,1), and GM (1,1) models.

Renewable sources integration is gaining importance in electrical utilities all over the world. The liberization of power sector in competitive regime, the share of renewable energy sources is increasing and it is essential to carry out the impact of clean energy on the system performance In this paper, analysis has been carried out with the PV-based distribution generation in the power system network. A Mixed Integer Nonlinear Programming (MINLP) approach has been utilized for determining optimal location and number of distributed generators considering minimization of fuel cost of conventional and solar PV power. The pattern of nodal real and reactive power prices have been obtained with and without PV integration. The results are also obtained for, loss reduction, fuel cost saving and voltage profile. The impact of different load models as PQ load and Zip load model has been studied. The proposed MINLP based optimization approach has been applied for IEEE24 bus reliability test system.

A comprehensive compensation device with paralleled decoupling for suppressing harmonics current, reactive power, and DC Bias of power transformer is proposed. Harmonics current and reactive current are detected by instantaneous reactive power theory. In this way, the fundamental active power is converted to be compensated reactive power and harmonics by controlling the converter. Compared to the ASVG with IGBT, the capacity and withstanding voltage level of ASVG with GTO are improved. The voltage across the devices of APF with multi-level inverter is reduced because of the paralleled decoupling connection. The harmonics compensation with multi-stage inverter can also reduce the voltage across the devices effectively. The reactive power compensator can work as a controllable rectifier and output controllable current by changing control algorithm. This current injects neutral point of transformer and suppresses its DC Bias, which has obvious effect on a power transformer. As a part of intelligent power grid, this compensator plays an important role for the development of smart grid automation.

Starting from the phenomenon that a large number of trains’ actual arrival & departure time deviate from specified time in train working diagram in the database of high speed railway dispatching system, the paper analyzes the defects of current train running time calculation method. Based on data mining theory, a section running time deviation calculation model for high speed railway train is proposed. Then the properties of train section running time deviation are studied in three different cases (non-stop both at the start and the end of section, stop at the end of section, and departure at the start of section) with the data from a Chinese railway bureau dispatching system, and its further influence on carrying capacity is analyzed. The results show that three deviation cases all fit Gauss distribution and the accumulative deviation time can increase the transport capacity for more than 1 million passengers per year.

With the global increase in energy prices and the urgent need to reduce CO2 emissions to the atmosphere, high energy usage is the main problem the greenhouse industry facing. Optimized control of supplemental lighting intensity and quality help to improve productivity and energy efficiency of greenhouse. In this paper,LED light source module is developed according to the design of light distribution of RRGB chip based on plants need for uniform lighting. Adaptive LED supplementary lighting system realize collection, storage and call of environmental data, and adaptive regulation of red, green, and blue light output based on combination of upper computer LabVIEW and controller STM32.PC based on LabVIEW monitor environmental parameters,and call or choose PPFD setting value of red, green, blue three bands of light based on expert database. The controller communicating with LabVIEW wirelessly through WiFi module, conducts real-time detection and adaptive regulation on photosynthetic photon flux density (PPFD) of red, green and blue bands according to PPFD setting value. This intelligent supplemental lighting system meets the requirement of plants for lighting environment and greatly saving energies through adaptive adjustment of PPFD of red, green and blue bands in environment according to the setting based on different supplemental lighting demands of different plants or the same plant in different growth stages for PPFD and light quality ratio.

Korean society is rapidly entering an aging society owing to the decline in fertility rates. As the elderly who are vulnerable to disasters increase, the probability that disaster damage has lead to casualities is growing. Especially, in case of water disaster, while people need to evacuate from low areas to high areas due to nature of diaster, there is resitrction in moving depending on the slope and travel didstance for the elderly. Therefore, this study aims to analyze the evaculation time of the elderly considering the slope in order to respond to storm and flood related disasters which occupy the most part in Korea.

The transfer of human resources refers to the transfer of human resources across different regions, industries and organizations depending on the development trends in the respective areas, economic environment and personal development needs. It is a process where the revenue of human resources improves continuously, and regional economy, industries and organizations are growing. Reasonable transfers across regions, industries and organizations can further realize the potential of individuals and enhance their advantageous position in the job market. Moreover, the transfers can optimize human resource allocation and the overall regional industrial development, improving the utilization of human resources. According to the law of diminishing returns, when there is perfect competition across regions, industries and organizations, the marginal utility of the side that has human resources shortage is higher than the side that has surplus. The human resources will flow to the side with shortage till the marginal revenue of the two sides reaches equilibrium. This is the ideal condition for human resources transfer. This paper is aimed to build models for individual human resource decision-making, organizational decision-making and dynamic balance respectively, in order to facilitate the equilibrium transfer of human resources across different regions, industries and organizations, and finally to achieve the optimal allocation of human resources.

Many CEOs have often introduced various types of management innovation for the firm’s profitability improvement. If the firm is, however, in a situation in which the firm is not ready to adopt those management innovations, it is not possible to achieve the goal of profit enhancement. In this study, we analyze the relationship between the preliminary elements of management innovation and profitability, and want to introduce the key success factors of management innovation. After investigating preliminary elements of the management innovation adoption through existing literature review, we conducted a questionnaire survey to Korean K-company. Then, by utilizing the structural equation modeling with AMOS, we analyzed the impact of preliminary elements of the management innovation adoption on the profitability. We found out that there are main preliminary elements of the management innovation adoption directed to profitability enhancement. From this finding, it would be possible to assist promoting successful management innovation of the company. By searching and enhancing the preliminary elements of management innovation affecting the profitability, it would be possible to reduce the innovation failure in the future business.