Pruning Redundant Alarm Correlation Patterns

1　ＩｎｔｒｏｄｕｃｔｉｏｎＴｈｅｓｔｉｃｋｉｎｇｐｏｉｎｔｏｆａｓｓｏｃｉａｔｉｏｎｒｕｌｅａｌｇｏｒｉｔｈｍｓｄｅｐｅｎｄｓｏｎｅｆｆｅｃｔｉｖｅｌｙｆｉｎｄｉｎｇａｌｌｃｏｒｒｅｌａｔｉｏｎｐａｔｔｅｒｎｓｔｈａｔｓａｔｉｓｆｙｖａｌｕｅｒｅｑｕｉｒｅｍｅｎｔｉｎｔｈｅｍａｇｎａｎｉｍｉｔｙｏｆｄａｔａ.Ｂｕｔｔｈｅａｌｇｏｒｉｔｈｍｓａｌｓｏｂｒｉｎｇａｎｅｇａｔｉｖｅｅｆ ｆｅｃｔ:ｔｈｅｎｕｍｂｅｒｏｆａｓｓｏｃｉａｔｉｏｎｒｕｌｅｓｉｓｖｅｒｙｌａｒｇｅ.Ａｌｓｏｉｎｆｏｒｍａｔｉｏｎ…     

广义杠杆规则及其在配方计算中的应用

作者将相图中的一维杠杆规则推广至多元配料系统而成为广义杠杆规则，并利用这一规则对配方计算中解的可行域问题进行了深入的讨论，给出了几何解释及工艺诠释，对配方设计有一定的指导作用。     

模糊Petri网及知识表示

在建造专家系统中虽然有很多种知识表示方法，但都有不尽人意的地方，本文试图用一种新的方法－Ｐｅｔｒｉ网模型来表示知识。本文给出了Ｆｕｚｚｚｙ Ｐｅｔｒｉ网和广义Ｆｕｚｚｙ Ｐｅｔｒｉ网两种模型，并给出了相应的推理算法，一旦专家知识用Ｐｅｔｒｉ网表示后，根据Ｐｅｔｒｉ网固有的特性，我们就能处理专家系统中并行推理、无回溯推理，反向推理等问题。     

基于Patel-Teja状态方程的统一粘度模型(Ⅱ)应用于油气藏流体粘度的预测

基于(I)报根据pVT和Tμp图形的相似性和Patel-Teja状态方程建立的预测纯流体气、液相粘度的统一模型,通过引入常规的状态方程参数的混合规则,将其应用于二元轻烃混合物共计1894个数据点及模拟天然气高压粘度的预测,平均相对误差分别为13.78%和16.75%;应用于油藏原油和天然气高压粘度的预测,结果优于现有的有关油气藏流体粘度模型.     

基于约束优化的联想记忆模型学习算法

本文提出了一种对称互连神经元网络的学习策略,利用全局约束优化方法确定连接权。优化过程采用了梯度下降技术。这种学习算法可以保证训练样本成为系统的稳定吸引子,并且具有优化意义上的最大吸引域。本文讨论了网络的存储容量,训练样本的渐近稳定性和吸引域大小。计算机实验结果说明了学习算法的优越性。     

全局最小均方算法

本文提出了一种基于全局均方误差最小准则的全局最小均方（ＴＬＭＳ）算法，在理论上分析了它的统计特性和收敛性，用数字仿真技术优良地它的性能。     

单元系T—p相图的数学结构

作者以化学元素的稳定单质为基准,推演出了任意物质M_i(相态Ω)的热力学生成活度{相态Ω)的函数形式:?D_Ω数值的大小体现着相态Ω的热力学相对稳定性.根据集合论原理沿D(稳定性)座标取极大值的方法把物理性质互不连续的各个异相态连结在一起,建立了单元系在T-p面上的优势分布方程(PSDE):■作者以H_2O为实例,计算了T-p相图,与实验相图基本一致.     

An application of expert systems techniques to the on-line control and fault diagnosis of a mixing process

An application of expert hierarchical control is described in this paper. The control is implemented in a two-level configuration, where the lower layer performs direct regulation control and the upper layer performs supervisory functions. In the regulation layer, a rule-based controller performs the regulation task, where the controller is constructed upon causal relations between subsystems. The control action is inferred from the measurement of both controlled and noncontrolled variables. In the supervisory layer, the main function is a fault diagnosis system which diagnoses faults on-line. The diagnosis is based upon reasoning from the structure of the system and the functions of its components, and efficient diagnosis is achieved by dividing the system into several subsystems. The overall technique has been successfully implemented on a pilot scale mixing process under on-line computer control.     

The impact of the Hebbian learning rule on research in behavioural neuroscience.

Hebb's principal theoretical propositions, the cell assembly and the nature of synaptic change, were generated at a time when the focus of work in behavioural neuroscience was directed at understanding issues such as the principles governing the behaviour of animals in neuropsychological studies of learning and memory and the role of drives in the control of behaviours like sex and feeding and drinking. It was not until attention shifted to understanding the neural underpinnings of learning and memory that Hebb's propositions had an impact on behavioural neuroscience as they provided a simple, and testable, mechanism for synaptic plasticity observed both in learning and in other forms of experience-dependent neural change. But much of the field remains interested in other issues such as sensation and perception, motivation, attention, and so on, and to date, Hebb's propositions have had little impact. (PsycINFO Database Record (c) 2010 APA, all rights reserved)