人工智能方法用于熔喷过程在线检测的研究

熔喷生产最终产品质量的控制，对于过程优化具有重要的意义。产品质量的在线检测是过程监测与质量控制必不可少的。本文首次在熔喷系统中引入人工智能的研究方法，对熔喷非织造布的厚度与纤维直径进行在线预测。实测数据与人工神经网络的预测结果吻合较好，从而证实了人工神经网络用于模拟熔喷过程的可行性。网络的输入包括：挤出机温度、喷头温度、熔融体挤出速率、空气流率及接收距离。神经元计算的输出是纤维直径与熔喷非织布的厚度。文中进一步提出了将神经网络与专家系统相结合的研究路线，以实现熔喷过程的优化控制。     

A combined queueing network and stochastic Petri-net approach for evaluating the performability of fault-tolerant computer systems

In this paper the performability analysis of fault-tolerant computer systems using a hierarchical decomposition technique is presented. A special class of queueing network (QN) models, the so-called BCMP [4], and generalized stochastic Petri nets (GSPN) [1] which are often used to separately model performance and reliability respectively, have been combined in order to preserve the best modelling features of both.

A conceptual model is decomposed into GSPN and BCMP submodels, which are solved in isolation. Then, the remaining GSPN portion of the model is aggregated with flow-equivalents of BCMP models, in order to compute performability measures. The substitutes of BCMP models are presented by means of simple GSPN constructs, thereby preserving the 1st and 2nd moments of the throughput. A simple example of a data communication system where failed transmissions are corrected, is presented.     

Fast and Compact 16 by 16 Cellular Neural Network Implementation

The paper presents a Cellular Neural Network implementation based on a high gain sigmoid operation. The required simplifications to the original theory are described that allow the use of high gain. With this design black and white images can be processed. The basic building blocks in a cell are described. A 16×16 cells network has been designed and processed with 1.2 micron CMOS technology. Measurement results which show the operation of the network are presented.     

Forecasting of Turkey's net electricity energy consumption on sectoral bases

In this study forecast of Turkey's net electricity energy consumption on sectoral basis until 2020 is explored. Artificial neural networks (ANN) is preferred as forecasting tool. The reasons behind choosing ANN are the ability of ANN to forecast future values of more than one variable at the same time and to model the nonlinear relation in the data structure. Founded forecast results by ANN are compared with official forecasts.     

Predictive modeling of mercury speciation in combustion flue gases using GMDH-based abductive networks

Modeling mercury speciation is an important requirement for estimating harmful emissions from coal-fired power plants and developing strategies to reduce them. First-principle models based on chemical, kinetic, and thermodynamic aspects exist, but these are complex and difficult to develop. The use of modern data-based machine learning techniques has been recently introduced, including neural networks. Here we propose an alternative approach using abductive networks based on the group method of data handling (GMDH) algorithm, with the advantages of simplified and more automated model synthesis, automatic selection of significant inputs, and more transparent input–output model relationships. Models were developed for predicting three types of mercury speciation (elemental, oxidized, and particulate) using a small dataset containing six inputs parameters on the composition of the coal used and boiler operating conditions. Prediction performance compares favourably with neural network models developed using the same dataset, with correlation coefficients as high as 0.97 for training data. Network committees (ensembles) are proposed as a means of improving prediction accuracy, and suggestions are made for future work to further improve performance.     

Tree-shaped flow structures designed by minimizing path lengths

This paper outlines a direct route to the construction of effective tree-shaped flow structures. Dendritic flow structures dominate the design of natural and engineered flow systems, especially in thermal and fluid systems. The starting point is the optimization of the shape of each elemental area or volume, such that the length of the flow path housed by the element is minimized. Proceeding toward larger and more complex structures - from elements, to first constructs, second constructs, etc. - the paper develops tree-shaped flow structures between one point and a straight line, one point and a plane, a circle and its center, and a point and many points distributed uniformly over an area. In the latter, the construction method is applied to a fluid flow configuration with laminar fully developed flow. The constructions reveal several features that are supported by empirical observations of natural tree-shaped flows: asymmetry, flow rate imbalance, pairing or bifurcation, angles between branches, and Y-shaped constructs that lie in a plane. It is shown that these basic features are necessary because of “packing”, i.e., assembling optimized elements into a fixed space, and filling the space completely. For the flow between an area and one point, the best elemental shape is the regular hexagon. It is shown that the emergence of string-shaped links that connect two or more elements are necessary features, which are also required by packing. Strings cover some of the inner zones of the tree network, particularly the inner zones of large and complex trees. Dichotomous Y-shaped constructs dominate the tree structure, especially the peripheral zones of the tree canopy. The practical importance of the simplified design method is discussed.     

全双极WTA模型的改进及其实现

提出了一种相似度的新定义，使双极ＷＡＴ模型的实现更加简洁明了。增加一个阈值使系统能判别非存储模式或因其信息量过低而无法鉴定的输入模式，阈值的大小与要求的容错能力有关。双极相似度及阈值通过光学方法实现。阈值的光学实现使系统仍具有照明不变性。通过电路实现取及ＷＴＡ网络的迭代运算。     

GENERALIZED INVERSE GROUP OF SIGNAL AND ITS IMPLEMENTATION WITH NEURAL NETWORKS

A new concept, the generalized inverse group (GIG) of signal, is firstly proposed and its properties, leaking coefficients and implementation with neural networks are presented. Theoretical analysis and computational simulation have shown that (1) there is a group of finite length of generalized inverse signals for any given finite signal, which forms the GIG; (2) each inverse group has different leaking coefficients, thus different abnormal states; (3) each GIG can be implemented by a grouped and improved single-layer perceptron which appears with fast convergence. When used in deconvolution, the proposed GIG can form a new parallel finite length of filtering deconvolution method. On off-line processing, the computational time is reduced to O(N) from O(N2). And the less the leaking coefficient is, the more reliable the deconvolution will be.