基于行人流线网络的上海轨道交通长江南路站行人设施布置方案优化

针对既有行人流线网络法中实结点模型存在的不足,提出了改进模型,并将改进方法应用于上海轨道交通18号线长江南路站行人设施布置优化方案。利用流线饱和度、设施最大拥堵面积等指标分析了原方案及3个优化方案在多种客流工况下的客流适应性,并给出了推荐方案。对推荐方案的客流进行了测试,结果表明,改进的行人流线网络法能够有效评价行人设施布置方案,且在车站行人设施布置方案的局部及整体调整时,行人流线网络法较行人流微观仿真法简便。

城轨站行人流线网络客流分配算法与软件实现

为实现符合城市轨道交通车站行人流线网络特点的行人设施客流分配,首先将分方向实结点时间阻抗与结点客流方向引入最短路径识别,将其嵌入连续平均法,建立了适用于城市轨道交通车站行人流线网络的客流分配算法.然后,利用C#和Matlab语言在AutoCAD环境下开发了相应的客流分配软件,并在此过程中提出了结点客流方向获取方法.算例表明,该算法能够实现考虑分方向实结点时间阻抗的城轨站行人设施客流分配;与TransCAD、VISUM相比,软件符合行人流线网络特点,操作简便.

企业人员流动探析

企业在人力资源管理中始终存在着人员流动问题,人员的流动包括由社会向企业流动、企业内部不同岗位之间流动、因工作中办理业务在各部门间的流动和从企业向社会流动几个进程。本文就企业中存在的人员流动现象进行简单概括分析,并最终归纳出企业人员流动在企业中形成的网络结构,使企业从另一个高度层面透视企业中的人员流动问题。

Optimum design of flow distribution in quenching tank for heat treatment of A357 aluminum alloy large complicated thin-wall workpieces by CFD simulation and ANN approach

Based on the computational fluid dynamics （CFD） method, a quenching tank with two agitator systems and two flow-equilibrating devices was selected to simulate flow distribution using Fluent software. A numerical example was used to testify the validity of the quenching tank model. In order to take tank parameters （agitation speed, position of directional flow baffle and coordinate position in quench zone） into account, an approach that combines the artificial neural network （ANN） with CFD method was developed to study the flow distribution in the quenching tank. The flow rate of the quenching medium shows a very good agreement between the ANN predicted results and the Fluent simulated data. Methods for the optimal design of the quenching tank can be used as technical support for industrial production.

DEPTH PREDICTION OF RAIN WATER ON ROAD SURFACE BASED ON ARTIFICIAL NEURAL NETWORK

A model based on the non-linear artificial neural network （ANN） is established to predict the thickness of the water film on road surfaces. The weight and the threshold can be determined by training test data, and the water film thickness on the road surface can be accurately predicted by the empirical verification based on sample data. Results show that the proposed ANN model is feasible to predict the water film thickness of the road surface.

Prediction of 2A70 aluminum alloy flow stress based on BP artificial neural network

The hot deformation behavior of 2A70 aluminum alloy was investigated by means of isothermal compression tests performed on a Gleeble-1500 thermal simulator over 360～480 ℃ with strain rates in the range of 0.01～1 s-1 and the largest deformation up to 60%. On the basis of experiments, a BP artificial neural network （ANN） model was constructed to predict 2A70 aluminum alloy flow stress. True strain, strain rates and temperatures were input to the network, and flow stress was the only output. The comparison between predicted values and experimental data showed that the relative error for the trained model was less than ±3% for the sampled data while it was less than ±6% for the non-sampled data. Furthermore, the neural network model gives better results than nonlinear regression method. It is evident that the model constructed by BP ANN can be used to accurately predict the 2A70 alloy flow stress.

SIMULATION AND PREDICTION OF DEBRIS FLOW USING ARTIFICIAL NEURAL NETWORK

Debris flow is one of the most destructive phenomena of natural hazards. Recently, major natural hazard, claiming human lives and assets, is due to debris flow in the world. Several practical methods for forecasting debris flow have been proposed, however, the accuracy of these methods is not high enough for practical use because of the stochastic and non-linear characteristics of debris flow. Artificial neural network has proven to be feasible and useful in developing models for nonlinear systems. On the other hand, predicting the future behavior based on a time series of collected historical data is also an important tool in many scientific applications. In this study we present a three-layer feed-forward neural network model to forecast surge of debris flow according to the time series data collected in the Jiangjia Ravine, situated in north part of Yunnan Province of China. The simulation and prediction of debris flow using the proposed approach shows this model is feasible, however, further studies are needed.

ANN Based Performance Analysis of UPFC in Power Flow Control

The Unified Power Flow Controller （UPFC） is one of the most versatile Flexible AC Transmission Systems （FACTS） devices that has unique capability of independently controlling the real and reactive power flows, in addition to regulate the system bus voltage. This paper presents performance analysis of Unified Power Flow Controller based on two axis theory. Based on this analysis, a new Artificial Neural Network （ANN） based controller has been proposed to improve the system performance. The controller rules are structured depending upon the relationship between series inserted voltage and the desired changes in real/reactive power flow in the power system. The effects of different controllers along with parameters of series transformer and transmission line have been investigated through developed control block model in SIMULINK tool box of MATLAB. The effectiveness of the proposed scheme is demonstrated by case studies.

Bit-stream linear artificial neural networks based on Sigma-delta modulation

To solve the excessive huge scale problem of the traditional multi-bit digital artificial neural networks （ANN） hardware implementation methods, a bit-stream ANN construction method based on direct sigma-delta （Z-A） signal processing is presented. The bit-stream adder, multiplier and fully digital X-A modulator used in the bit-stream linear ANN are implemented in a field programmable gate array （FPGA）. A bit-stream linear ANN based on these bit-stream modules is presented and implemented. To verify the function and performance of the bit-stream linear ANN, the bit-stream adaptive predictor and the bit-stream adaptive noise cancellation system are presented. The predicted result of the bit-stream adaptive predictor is very close to the desired signal. Also, the bit-stream adaptive noise cancellation system removes the electric power noise effectively.

Artificial neural network approach for rheological characteristics of coal-water slurry using microwave pre-treatment

Detailed experimental investigations were carried out for microwave pre-treatment of high ash Indian coal at high power level(900 W) in microwave oven. The microwave exposure times were fixed at60 s and 120 s. A rheology characteristic for microwave pre-treatment of coal-water slurry(CWS) was performed in an online Bohlin viscometer. The non-Newtonian character of the slurry follows the rheological model of Ostwald de Waele. The values of n and k vary from 0.31 to 0.64 and 0.19 to 0.81 Pa·sn,respectively. This paper presents an artificial neural network(ANN) model to predict the effects of operational parameters on apparent viscosity of CWS. A 4-2-1 topology with Levenberg-Marquardt training algorithm(trainlm) was selected as the controlled ANN. Mean squared error(MSE) of 0.002 and coefficient of multiple determinations(R^2) of 0.99 were obtained for the outperforming model. The promising values of correlation coefficient further confirm the robustness and satisfactory performance of the proposed ANN model.

Optimization of GERD Therapeutic Regimen Based on ANN and Realization of MATLAB

Objective To optimize therapeutic regimens for gastro-esophageal reflux disease(GERD),artificial neural networks(ANNs)are used to simulate and set up an intelligent traditional Chinese medicine(TCM)treatment system.Methods ANNs were employed for machine learning;the clinical syndrome differentiation and treatment determination were simulated through systematic learning of therapeutic regimens for GERD symptoms in the ancient literature;and case simulation was conducted to achieve objective verification.Results The conformity of machinery prescription with the ancient literature exceeded95%.Conclusion The application of machine learning to TCM intelligent prescription is feasible and worthy of further study.

Application of ANNs Model with the SDSM for the Hydrological Trend Prediction in the Sub-catchment of Kurau River, Malaysia

The paper describes the application of SDSM （statistical downscaling model） and ANNs （artificial neural networks） models for prediction of the hydrological trend due to the climate-change. The SDSM has been calibrated and generated for the possible future scenarios of meteorological variables, which are temperature and rainfall by using GCMs （global climate models）. The GCM used is SRES A2. The downscaled meteorological variables corresponding to SDSM were then used as input to the ANNs model calibrated with observed station data to simulate the corresponding future streamflow changes in the sub-catchment of Kurau River. This study has discovered the hydrological trend over the catchment. The projected monthly streamflow has shown a decreasing trend due to the increase in the, mean of temperature for overall months, except the month of August and November.

Prediction of Boiler Drum Pressure and Steam Flow Rate Using Artificial Neural Network

Numerical simulation of complex systems and components by computers is a fundamental phase of any modern engineering activity. The traditional methods of simulation typically entail long, iterative processes which lead to large simulation times, often exceeding transient real time. Artificial neural networks （ANNs） may be advantageous in this context, the main advantage being the speed of computation, the capability of generalizing from the few examples, robustness to noisy and partially incomplete data and the capability of performing empirical input-output mapping without complete knowledge of underlying physics. In this paper, the simulation of steam generator is considered as an example to show the potentialities of this tool. The data required for training and testing the ANN is taken from the steam generator at Abott Power Plant, Champaign （USA）. The total number of samples is 9600 which are taken at a sampling time of three seconds. The performance of boiler （drum pressure, steam flow rate） has been verified and tested using ANN, under the changes in fuel flow rate, air flow rate and load disturbance. Using ANN, input-output mapping is done and it is observed that ANN allows a good reproduction of non-linear behaviors of inputs and outputs.

Compressor Map Prediction by Neural Networks

This paper presents a study where artificial neural networks are used as a curve fitting method applying measured data from an axial compressor test rig to predict the compressor map. Emphasis is on models for prediction of pressure ratio, compressor mass flow and mechanical efficiency. Except for evaluation of interpolation and extrapolation capabilities, this study also investigates the effect of the design parameters such as number of neurons and size of training data. To reduce the effect of noise, the auto associative neural network has been applied for noise filtering of the data from the parameters used to calculate the efficiency. In summary, the results show that artificial neural network can be used for compressor map prediction, but it should be emphasized that the selection of data normalisation scale is crucial for the model where compressor mass flow is predicted. Furthermore, it is shown that the AANN （auto associative neural network） can be used to the reduce noise in measured data and thereby enhance the quality of the data.

Application ofArtificial Neural Networks in Instantaneous Peak Flow Estimation for Kharestan Watershed, Iran

Understanding the amount of instantaneous peak flow in watersheds is one of the most important factors that plays important role in planning and designing of projects related to water and river engineering. The purpose of this study is to compare the efficiency of artificial neural network and empirical methods for estimating instantaneous peak flow in Kharestan Watershed located northwest of Fars Province, Iran. For this purpose, 25 years of daily peak and instantaneous peak flow of Jamal Beig Hydrometric Station was considered. Then the estimation was done based on empirical methods including Fuller, Sangal and Fill-Steiner and artificial neural network and were compared based on RMSE and R2 . Results showed that estimation of artificial neural network is more accurate than empirical methods with RMSE = 13.710 and R2=0.942 which indicated the lower errors of artificial neural network method compared with empirical methods.

Low-Dimensional SIR Epidemic Models with Demographics on Heterogeneous Networks

To investigate the impacts of demographics on the spread of infectious diseases, a susceptib- le-infectious-recovered （SIR） pairwise model on heterogeneous networks is established. This model is reduced by using the probability generating function and moment closure approximations. The basic reproduction number of the low-dimensional model is derived to rely on the recruitment and death rate, the first and second moments of newcomers＇ degree distribution. Sensitivity analysis for the basic reproduction number is performed, which indicates that a larger variance of newcomers＇ degrees can lead to an epidemic outbreak with a smaller transmission rate, and contribute to a slight decrease of the final density of infectious nodes with a larger transmission rate. Besides, stochastic simulations indicate that the low-dimensional model based on the log-normal moment closure assumption can well capture important properties of an epidemic. And the authors discover that a larger recruitment rate can inhibit the spread of disease.

Parameters optimization and nonlinearity analysis of grating eddy current displacement sensor using neural network and genetic algorithm

A grating eddy current displacement sensor(GECDS) can be used in a watertight electronic transducer to realize long range displacement or position measurement with high accuracy in difficult industry conditions.The parameters optimization of the sensor is essential for economic and efficient production.This paper proposes a method to combine an artificial neural network(ANN) and a genetic algorithm(GA) for the sensor parameters optimization.A neural network model is developed to map the complex relationship between design parameters and the nonlinearity error of the GECDS,and then a GA is used in the optimization process to determine the design parameter values,resulting in a desired minimal nonlinearity error of about 0.11%.The calculated nonlinearity error is 0.25%.These results show that the proposed method performs well for the parameters optimization of the GECDS.