面向产品族的建模技术研究

文中针对大规模定制生产中的快速变型设计要求,研究了产品族模型的组成和表达方法,提出了产品族建模中的关键技术;建立了一个适合于产品族建模的信息环境。     

Structural Synthesis of Modular Weakly Connected Neural Networks. II. Nuclear Neural Networks

The simplest modular neural network is investigated, in which each module is a single-layer perceptron (a neural kernel). Numerical indices of quality by the criteria of operating speed and plasticity are proposed to characterize structural properties of nuclear neural networks. Based on the indices introduced, optimum procedures of structural synthesis are constructed.     

Structural Synthesis of Modular Weakly Connected Neural Networks. I. Methodology of Structural Synthesis of Modular Neural Networks

Structural models of modular neural networks without loops are considered. The notion of a weakly connected network is introduced. A genetic principle of generation of weakly connected neural networks is proposed, and its reproductive power is proved on the basis of the theory of categories. Algorithmic realizations of structural synthesis are considered. Some examples are given.     

A Case Study on Applying a Tool for Automated System Analysis Based on Modular Specifications Written in TRIO

An effective means for analyzing and reasoning on software systems is to use formal specifications to simulate their execution. The simulation traces can be used for specification testing and reused for functional testing of the system later in the development process. It is widely acknowledged that, to deal with the complexity of industrial-size systems, specifications must be structured into modules providing abstraction mechanisms and clear interfaces. In our past work, we defined and implemented a method for simulating specifications written in the TRIO temporal logic language, and applied it to functional testing of time-critical industrial systems. In the present paper, we report on a case study with a tool that analyzes TRIO specifications by taking advantage of their modular structure, so as to overcome the well-known state-explosion problem and make the proposed method really scalable. We discuss the fundamental operations and the algorithms on which the tool is based. Then, we illustrate its use in a realistic case study, inspired from an industrial application. Finally, we comment on the overall results in terms of usability of the tool and effectiveness of the approach, and we outline future improvements.     

Pipelined parallelisation of automatic face inspection

A parallel pipeline is shown to be a natural method of speeding up a typical computer vision application, face inspection using `eigenfaces'. Faces within a stream of video images are continuously surveyed in a manner akin to a `conveyor belt' inspection process. The parallelisation is a new exemplar of a scheme for the rapid prototyping of large-scale, multi-algorithm applications suitable for transfer to a message-passing multicomputer. A general solution, pipelined processor farms, is preferred to a customised solution. This paper gives details of the software tools and software engineering methods employed to tackle this class of problem.     

用演化算法求解抛物型方程扩散系数的识别问题

基于演化算法给出了一类求解参数识别反问题的一般方法,该方法表明只要找到好的、求解相应的正问题的数值方法,演化算法就可以用于求解此类反问题。设计有效的求解反问题的演化算法的关键是寻找一种适合反问题的解空间的编码表示形式、适当的适应值函数形式以及有效的计算正问题的数值方法。该文结合算法、传统的求解反问题的工方法和正则化技术,设计了一类求解参数识别反问题的方法。为验证此类方法,将其用于求解一维扩散方程的     

Prediction-based Iterative Learning Control (PILC) for Uncertain Dynamic Nonlinear Systems Using System Identification Technique

Prediction-based Iterative Learning Control (PILC) is proposed in this paper for a class of time varying nonlinear uncertain systems. Convergence of PILC is analyzed and the uniform boundedness of tracking error is obtained in the presence of uncertainty and disturbances. It is shown that the learning algorithm not only guarantees the robustness, but also improves the learning rate despite the presence of disturbances and slowly varying desired trajectories in succeeding iterations. The effectiveness of the proposed PILC is presented by simulations.     

一种改进的基于模板匹配的集装箱字符识别方法

字符识别是计算机模式识别中较为常见的问题,对于印刷体的字符来说,经常采用二值化和模板匹配方法进行识别。在实际应用中,为了提高识别率,减少计算量和运行时间,解决正确识别二值化后的正反不同图象的问题,提出一种改进的自适应的模板匹配方法,理论与实验结果表明具有较高的识别和坚韧性。     

基于Hopfield神经网络的线性系统参数辨识

基于Ｈｏｐｆｉｅｌｄ神经网络的优化计算原理,提出了一种新的线性系统参数辨识方法,利用连续型ＨＮＮ辨识线性系统Ｉ／Ｏ差分方程计算系统的传递函数矩阵,最终获得了可观标准型的状态空间表达式,仿真结果证明了这种只方法的有效性。