Designing an Intelligent Control Philosophy in Reservoirs of Water Transfer Networks in Supervisory Control and Data Acquisition System Stations

In this paper, a hybrid neural-genetic fuzzy system is proposed to control the flow and height of water in the reservoirs of water transfer networks. These controls will avoid probable water wastes in the reservoirs and pressure drops in water distribution networks. The proposed approach combines the artificial neural network, genetic algorithm, and fuzzy inference system to improve the performance of the supervisory control and data acquisition stations through a new control philosophy for instruments and control valves in the reservoirs of the water transfer networks. First, a multi-core artificial neural network model, including a multi-layer perceptron and radial based function, is proposed to forecast the daily consumption of the water in a reservoir. A genetic algorithm is proposed to optimize the parameters of the artificial neural networks. Then, the online height of water in the reservoir and the output of artificial neural networks are used as inputs of a fuzzy inference system to estimate the flow rate of the reservoir inlet. Finally, the estimated inlet flow is translated into the input valve position using a transform control unit supported by a nonlinear autoregressive exogenous model. The proposed approach is applied in the Tehran water transfer network. The results of this study show that the usage of the proposed approach significantly reduces the deviation of the reservoir height from the desired levels.

Decision Model of Knowledge Transfer in Big Data Environment

A decision model of knowledge transfer is presented on the basis of the characteristics of knowledge transfer in a big data environment.This model can determine the weight of knowledge transferred from another enterprise or from a big data provider.Numerous simulation experiments are implemented to test the efficiency of the optimization model.Simulation experiment results show that when increasing the weight of knowledge from big data knowledge provider,the total discount expectation of profits will increase,and the transfer cost will be reduced.The calculated results are in accordance with the actual economic situation.The optimization model can provide useful decision support for enterprises in a big data environment.

Hardware-in-the-loop simulation of communication networks

To enhance the fidelity and accuracy of the simulation of communication networks,hardware-in-the-loop（HITL） simulation was employed.HITL simulation methods was classified into three categories,of which the merits and shortages were compared.Combing system-in-the-loop（SITL） simulation principle with high level architecture（HLA）,an HITL simulation model of asynchronous transfer mode（ATM） network was constructed.The throughput and end-to-end delay of all-digital simulation and HITL simulation was analyzed,which showed that HITL simulation was more reliable and effectively improved the simulation credibility of communication network.Meanwhile,HLA-SITL method was fast and easy to achieve and low-cost during design lifecycle.Thus,it was a feasible way to research and analyze the large-scale network.

Inventory Management and Demand Forecasting Improvement of a Forecasting Model Based on Artificial Neural Networks

Forecasting is predicting or estimating a future event or trend.Supply chains have been constantly growing in most countries ever since the industrial revolution of the 18th century.As the competitiveness between supply chains intensifies day by day,companies are shifting their focus to predictive analytics techniques to minimize costs and boost productivity and profits.Excessive inventory(overstock)and stock outs are very significant issues for suppliers.Excessive inventory levels can lead to loss of revenue because the company's capital is tied up in excess inventory.Excess inventory can also lead to increased storage,insurance costs and labor as well as lower and degraded quality based on the nature of the product.Shortages or out of stock can lead to lost sales and a decline in customer contentment and loyalty to the store.If clients are unable to find the right products on the shelves,they may switch to another vendor or purchase alternative items.Demand forecasting is valuable for planning,scheduling and improving the coordination of all supply chain activities.This paper discusses the use of neural networks for seasonal time series forecasting.Our objective is to evaluate the contribution of the correct choice of the transfer function by proposing a new form of the transfer function to improve the quality of the forecast.

Lithium-ion battery degradation trajectory early prediction with synthetic dataset and deep learning

Knowing the long-term degradation trajectory of Lithium-ion(Li-ion) battery in its early usage stage is critical for the maintenance of the battery energy storage system(BESS) in reality. Previous battery health diagnosis methods focus on capacity and state of health(SOH) estimation which can receive only the short-term health status of the cell. This paper proposes a novel degradation trajectory prediction method with synthetic dataset and deep learning, which enables to grasp the characterization of the cell's health at a very early stage of Li-ion battery usage. A transferred convolutional neural network(CNN) is chosen to finalize the early prediction target, and the polynomial function based synthetic dataset generation strategy is designed to reduce the costly data collection procedure in real application. In this thread, the proposed method needs one full lifespan data to predict the overall degradation trajectories of other cells. With only the full lifespan cycling data from 4 cells and 100 cycling data from each cell in experimental validation, the proposed method shows a good prediction accuracy on a dataset with more than 100 commercial Li-ion batteries.

MODELING OF THE PRIORITY SCHEDULING INPUT-LINE GROUP OUTPUT WITH MULTI-CHANNEL IN ATM EXCHANGE SYSTEM

In this paper, an extended Kendall model for the priority scheduling input-line group output with multi-channel in Asynchronous Transfer Mode （ATM） exchange system is proposed and then the mean method is used to model mathematically the non-typical non-anticipative PRiority service （PR） model. Compared with the typical and non-anticipative PR model, it expresses the characteristics of the priority scheduling input-line group output with multi-channel in ATM exchange system. The simulation experiment shows that this model can improve the HOL block and the performance of input-queued ATM switch network dramatically. This model has a better developing prospect in ATM exchange system.

The Application of NPs in WCDMA Systems

Recent efforts to add new services to the wide-band code division multiple accesses （WCDMA） system have increased interest in network processor （NP）-based routers that are easy to extend and evolve. In this paper, an application of NPs in routing engine module （REM） of radio network controller （RNC） in WCDMA system is proposed. The measuring results show that NPs have good performance and efficiency in routing traffic of the communication network and the simulation verifies the fast forwarding function of NPs.

Transnational technology transfer network in China:Spatial dynamics and its determinants

Patent transfer has been regarded as an important channel for the nations and regions to acquire external technology,and also a direct research object to depict the relationship between supply and demand of technology flow.Therefore,based on traceable patent transfer data,this article has established a dual-pipeline theoretical framework of transnational-domestic technology transfer from the interaction of the global and local(glocal)perspective,and combines social networks,GIS spatial analysis as well as spatial econometric model to discover the spatial evolution of China’s transnational technology channels and its determinant factors.It is found that:(1)The spatial heterogeneity of the overall network is significant while gradually weakened over time.(2)The eastward shift of the core cities involved in transnational technology channels is accelerating,from the hubs in North America(New York Bay Area,Silicon Valley,Caribbean offshore financial center,etc.)and West Europe(London offshore financial center etc.)to East Asia(Tokyo and Seoul)and Southeast Asia(Singapore),which illustrates China has decreased reliance on the technology from the USA and West Europe.(3)The four major innovation clusters:Beijing-Tianjin-Hebei region(Beijing as the hub),Yangtze River Delta(Shanghai as the hub),The Greater Bay Area(Shenzhen and Hong Kong as the hubs)and north Taiwan(Taipei and Hsinchu as the hubs),are regarded as global technology innovation hubs and China’s distribution centers in transnational technology flow.Among those,Chinese Hong Kong’s betweenness role of technology is strengthened due to linkage of transnational corporations and their branches,and low tax coverage of offshore finance,thus becoming the top city for technology transfer.Meanwhile,Chinese Taiwan’s core position is diminishing.(4)The breadth,intensity,and closeness of domestic technology transfer are conducive to the expansion of transnational technology import channels.Additionally,local economic level has positive effect on transnational technology transfer channels while technology strength and external economic linkage have multifaceted influences.

Deep transfer network of heterogeneous domain feature in machine translation

In order to address the shortcoming of feature representation limitation in machine translation(MT)system,this paper presents a feature transfer method in MT.Meta feature transfer of the decoding process considered not only their own translation system,but also transferred knowledge of another translation system.The domain meta feature and the objective function of domain adaptation are used to better model the domain transfer task.In this paper,extensive experiments and comparisons are made.The experiment results show that the proposed model has a significant improvement in domain transfer task.The first model has better performance than baseline system,which improves 3.06 BLEU score on the news test set,improves 3.27 BLEU score on the education test set,and improves 3.93 BLEU score on the law test set;The second model improves 3.16 BLEU score on the news test set,improves 3.54 BLEU score on the education test set,and improves 4.2 BLEU score on the law test set.

An entransy dissipation-based optimization principle for solar power tower plants

The entransy theory, which can be used to optimize the heat transfer network of a solar power tower system （SPTS） and im- prove its energy efficiency, was introduced in this paper. Firstly, the irreversibility of the heat transfer processes in a SPTS was analyzed and the total entransy dissipation equation of a SPTS was derived. Then, two types of optimization problems （reduc- ing the total circulating flow rate or the total heat-exchanging area） of a SPTS were solved with conditional extremum model based on the formulas of total entransy dissipation. Finally, the entransy dissipation-based optimization principle was applied to a simple SPTS without re-heater and a complex SPTS with a re-heater. The results showed that under the chosen calculation conditions the minimum total thermal conductance was 19306.03 W K-~ for a SPTS without re-heater when the total heat ca- pacity rate of heat transfer fluid （HTF） was 3200 W K-1. The minimum total thermal conductance was about 7.9% lower than the value predicted based on the typical outlet temperature of a receiver. This meant that the total heat exchange area or initial investment could be effectively reduced under the prescribed total HTF circulating flow rate. We also studied the variation trends of the two optimized results including minimum total HTF heat capacity rate and minimum total thermal conductance. The minimum total HTF heat capacity rate decreased with the given total thermal conductance, the minimum total thermal conductance decreased first and then increased with the given total HTF heat capacity rate. We also found that for a SPTS with a re-heater, the mixing temperature and the mixing position of HTF had significant effects on the two types of optimization problems.

ANN modeling for diffusivity of mushroom and vegetables using a fluidized bed dryer

Drying characteristics in terms of diffusivity were studied for mushrooms and different vegetables in a fluidized bed dryer. Drying characteristics with falling rate regime were computed for all the sampi^z. Effective diffusivity of each sample was calculated. Mass transfer coefficients were determined. Mass transfer kinetics for drying of different samples was also found out. Correlations for the diffusivity of samples were developed by relating the experimentally observed data with the different system parame- ters on the basis of regression analysis. The developed correlations for effective moisture diffusivity of the samples are validated by artificial neural network （ANN） modeling. Finally calculated values of diffusivity obtained through both the methods are compared with the experimentally measured values which show a very good approximation thereby indicating the wide applicability of the developed correlations for industrial uses.

Two-level hierarchical feature learning for image classification

In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network(CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count(CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.

Rapid proton diffusion in hydroxyl functionalized imidazolium ionic liquids

There is considerable interest in using ionic liquids(ILs) as protic electrolytes. However, the reported proton transfer rate in ILs is quite slow. In this study, we report functionalizing imidazolium ILs with alcohol hydroxyls, aiming at constructing hydrogen bonding networks in the electrolyte, can stimulate fast proton hopping transfer. For demonstration, the diffusion of proton and Cl. in 1-(3-hydroxypropyl)-3-methylimidazolium tetrafluoroboride(C_3OHmimBF_4) were studied using cyclic voltammetry and potentiostatic method at 30 °C. The diffusion coefficient of proton is about one order of magnitude higher than that of Cl. in the same electrolyte, and about 5 times that of proton in the non-hydydroxyl 1-(butyl)-3-methylimidazolium tetrafluoroboride(BmimBF_4) when normalized to the diffusion coefficients of Cl. in respective ILs. In the meantime, 1H NMR spectra revealed a strong hydrogen bonding interaction between proton and C_3OHmimBF_4 which is absent between proton and BmimBF_4, thus the significantly higher diffusion coefficient of proton in C_3OHmimBF_4 may suggest the formation of effective hydrogen bonding networks, enabling rapid proton hopping via the Grotthuss mechanism.