实时专家智能控制系统REICS设计与应用

本文研究并设计了一种新型的用于工业控制过程的实时专家智能控制系统（ＲＥＩＣＳ），提出了一种表达控制领域知识的广义产生式规则，解决了多级知识表示和多级推理控制策略的问题。本文还介绍了ＲＥＩＣＳ设计过程、实现的方法和技术。通过温度控制以及在直流电机调速控制方面的应用研究表明，ＲＥＩＣＳ较常规ＰＩＤ和Ｆｕｚｚｙ控制有明显优越性，可适用于大型、复杂和不确定性系统的智能控制。     

面向对象数据模型到ERwin中ER图模型的转换

本文介绍一种面向对象的数据模型，这个模型ＣＯＲＥ模型为基础，给出ＬＯＧＩＣＷＯＲＫＳ公司的ＥＲｗｉｎ采用的ＥＲ图模型，接着着重讨论一种面向对象数据模型到ＥＲ图模型的转换算法。     

知识获取系统NDKAS的研究与应用

知识获取系统ＮＤＫＡＳ的研究与应用潘金贵，陈彬，陈晶，陈世福（南京大学计算机科学系南京２１０００８）ＴＨＥＲＥＳＥＡＲＣＨＡＮＤＡＰＰＬＩＣＡＴＩＯＮＯＮＴＨＥＫＮＯＷＬＥＤＧＥＡＣＱＵＩＳＩＴＩＯＮＳＹＳＴＥＭ－ＮＤＫＡＳ￥ＰａｎＪｉｎｇｕｉ；Ｃｈ...     

反求糙率的一种数值方法

反求糙率的一种数值方法杨世孝，肖子良（中山大学计算机科学系）ＡＮＵＭＥＲＩＣＡＬＭＥＴＨＯＤＦＯＲＦＩＮＤＩＮＧＲＯＵＧＨＮＥＳＳＲＡＴＥ￥ＹａｎｇＳｈｉ－ｘｉａｏ；ＸｉａｏＺｉ－ｌｉａｎｇ（ＤｅｐａｒｔｍｅｎｔｏｆＣｏｍｐｕｔｅｒＳｃｉｅｎｃｅ，Ｚ...     

一种新的求解线性时变系统的数值解法

一种新的求解线性时变系统的数值解法贾磊，孙优贤（山东轻工业学院机电系）（浙江大学工业控制研究所）ＡＮＥＷＮＵＭＥＲＩＣＡＬＭＥＴＨＯＤＯＦＴＨＥＬＩＮＥＡＲＴＩＭＥ－ＶＡＲＩＮＧＳＹＳＴＥＭＳＶＩＡＳＨＩＦＴＥＤＪＡＣＯＢＩＳＥＲＩＥＳ￥ＪｉａＬｅｉ...     

WEB应用服务器体系结构研究及其应用

本文对ＷＥＢ应用服务器的功能和体系结构进行了比较深入的探讨和研究,并对具有代表意义的ＯＲＡＣＬＥＷＥＢ ＡＰＰＬＩＣＡＴＩＯＮ ＳＥＲＶＥＲ（ＯＷＡＳ）进行分析、探讨。     

转炉吹炼实时控制专家系统RESC的设计与实现

本文分析了一个转炉吹炼实时控制专家系统ＲＥＳＣ的设计与实现，在开发中系统采用了专家系统技术，实时控制技术和吹炼控制模型相结合的方法，这里着重讨论了ＲＥＳＣ的系统结构，知识表示与推理机制，吹炼控制机制，网络通信以及主析实现技术。     

一种快速的贴体网格生成技术及其应用

一种快速的贴体网格生成技术及其应用刘仪，曹春丽，刘斌，向一敏（西安交通大学热动力工程系叶轮机械研究所）ＡＦＡＳＴＡＬＧＯＲＩＴＨＭＦＯＲＢＯＵＮＤＡＲＹ－ＦＩＴＴＥＤＧＲＩＤＧＥＮＥＲＡＴＩＯＮＡＮＤＮＵＭＥＲＩＣＡＬＡＮＡＬＹＳＩＳ￥ＬｉｕＹｉ；Ｃ...     

如何修改Protel 99SE仿真库及仿真模型

计算机模拟电路分析是建立在正确的器件模型的基础上的，而每一种器件都可以等效成由不同的Ｒ、Ｃ、Ｌ等单元组成的网络，因此，在２０世纪７０年代，美国加利福尼亚大学柏克莱分校就开始开发用于集成电路的电路分析程序ＳＰＩＣＥ。随着计算机技术的发展，其版本不断更新，电路分析的功能也得到扩充，算法也更加完善，器件模型也在不断地更新和增加。Ｐｒｏｔｅｌ ９９ＳＥ的仿真模块就是在ＳＰＩＣＥ３ｆ５／ＸＳＰＩＣＥ的基础上发展而来的，支持所有的标准ＳＰＩＣＥ模型。 由于Ｐｒｏｔｅｌ ９９ＳＥ的仿真引擎直接作用于电路原理图，…     

扁球壳的边界元分析的一种简便方法

扁球壳的边界元分析的一种简便方法龙述尧，蒯行成，李家宝，陈军（湖南大学）ＡＣＯＮＣＩＳＥＭＥＴＨＯＤＯＦＢＯＵＮＤＡＲＹＥＬＥＭＥＮＴＡＮＡＬＹＳＩＳＦＯＲＳＨＡＬＬＯＷＳＰＨＥＲＩＣＡＬＳＨＥＬＬＳ￥ＬｏｎｇＳｈｕ－ｙａｏ；ＫｕａｉＸｉｎｇ－ｃｈｅ...     

A real-time expert control system

A new developed and designed real-time expert intelligent control system (REICS) for industrial process control has been introduced. The global architectures of the hardware and software of the system have been proposed. A multi-level method of knowledge representation based on the combination of frame, production rules and real-time procedures has been discussed, and used to represent the control knowledge and algorithms of the control system. Meanwhile, the reasoning mechanism, control strategy and its flow chart have been presented. The simulation and the practical application of an industrial rotary kiln furnace for the proposed tool and method have been described.     

汉语未登录词的词义知识表示及语义预测

在此前的汉语未登录词语义预测中,构词相关的知识一直被当做预测的手段,而没有被视为一种有价值的知识表示方式,该文在“语素概念”基础上,深入考察汉语的语义构词知识,给出未登录词的“多层面”的词义知识表示方案。针对该方案,该文采用贝叶斯网络方法,构建面向汉语未登录词的自动语义构词分析模型,该模型能有效预测未登录词的“多层面”的词义知识。这种词义知识表示简单、直观、易于拓展,实验表明对汉语未登录词的语义预测具有重要的价值,可以满足不同层次的应用需求。     

面向重用的产品设计过程知识建模与检索

针对传统的产品设计过程知识模型与知识检索方法在提高产品设计过程知识重用性上的不足,提出了多层次多粒度的知识模型以及基于语义的智能检索算法。首先通过分析产品设计过程知识重用的需求,将产品设计过程知识分为项目管理知识、领域知识、产品设计对象知识三类,并建立对应的多层次知识模型。然后在运用本体技术建立产品设计过程知识本体库的基础上,提出了一种基于语义的智能检索算法。最后给出了产品设计过程知识重用模型,并以柴油发动机方案设计为例,证明了该模型的有效性。     

Multi-level knowledge discovery from rule bases

The discovery of multi-level knowledge is important to allow queries at and across different levels of abstraction. While there are some similarities between our research and that of others in this area, the work reported in this paper does not directly involve databases and is differently motivated. Our research is interested in taking data in the form of rule-bases and finding multi-level knowledge. This paper describes our motivation, our preferred technique for acquiring the initial knowledge known as Ripple-Down Rules, the use of Formal Concept Analysis to develop an abstraction hierarchy, and our application of these ideas to knowledge bases from the domain of chemical pathology. We also provide an example of how the approach can be applied to other prepositional knowledge bases and suggest that it can be used as an additional phase to many existing data mining approaches.     

基于RuleML的多级知识单元知识表示方法

文章针对农业领域的知识表示问题探讨了一种基于RuleML格式的多级知识单元的知识表示方法。RuleML和多级知识单元的有机结合使得知识预处理的效率获得提高,并体现出数据库和知识库融合的一定优势,还实现了知识表示的标准化、规范化和通用化。     

A multi-level ant-colony mining algorithm for membership functions

Fuzzy data mining is used to extract fuzzy knowledge from linguistic or quantitative data. It is an extension of traditional data mining and the derived knowledge is relatively meaningful to human beings. In the past, we proposed a mining algorithm to find suitable membership functions for fuzzy association rules based on ant colony systems. In that approach, precision was limited by the use of binary bits to encode the membership functions. This paper elaborates on the original approach to increase the accuracy of results by adding multi-level processing. A multi-level ant colony framework is thus designed and an algorithm based on the structure is proposed to achieve the purpose. The proposed approach first transforms the fuzzy mining problem into a multi-stage graph, with each route representing a possible set of membership functions. The new approach then extends the previous one, using multi-level processing to solve the problem in which the maximum quantities of item values in the transactions may be large. The membership functions derived in a given level will be refined in the subsequent level. The final membership functions in the last level are then outputted to the rule-mining phase to find fuzzy association rules. Experiments are also performed to show the performance of the proposed approach. The experimental results show that the proposed multi-level ant colony systems mining approach can obtain improved results.     

面向研究性项目文档的知识画像模型

为提高科研活动产生的研究性项目文档的知识要点的精准智能识别和检索能力,通过分析文档行文结构,提出建立文档知识画像的方法。设计精准贴合研究性项目文档结构的多层次的知识画像,自动识别文档知识要点,并按语义段落多粒度提取知识要点。采用知识表达准确率对模型的知识提取精确度进行检验,实验结果表明模型比传统方法对文档知识描述更准确,可在实际工作中使用。     

Optimal multi-level thresholding with membrane computing

The conventional methods are not effective and efficient for image multi-level thresholding due to time-consuming and expensive computation cost. The multi-level thresholding problem can be posed as an optimization problem, optimizing some thresholding criterion. In this paper, membrane computing is introduced to propose an efficient and robust multi-level thresholding method, where a cell-like P system with the nested structure of three layers is designed as its computing framework. Moreover, an improved velocity-position model is developed to evolve the objects in membranes based on the special membrane structure and communication mechanism of objects. Under the control of evolution-communication mechanism of objects, the cell-like P system can efficiently exploit the best multi-level thresholds for an image. Simulation experiments on nine standard images compare the proposed multi-level thresholding method with several state-of-the-art multi-level thresholding methods and demonstrate its superiority.     

Squeezing More Past Knowledge for Online Class-Incremental Continual Learning

Continual learning (CL) studies the problem of learning to accumulate knowledge over time from a stream of data. A crucial challenge is that neural networks suffer from performance degradation on previously seen data, known as catastrophic forgetting, due to allowing parameter sharing. In this work, we consider a more practical online class-incremental CL setting, where the model learns new samples in an online manner and may continuously experience new classes. Moreover, prior knowledge is unavailable during training and evaluation. Existing works usually explore sample usages from a single dimension, which ignores a lot of valuable supervisory information. To better tackle the setting, we propose a novel replay-based CL method, which leverages multi-level representations produced by the intermediate process of training samples for replay and strengthens supervision to consolidate previous knowledge. Specifically, besides the previous raw samples, we store the corresponding logits and features in the memory. Furthermore, to imitate the prediction of the past model, we construct extra constraints by leveraging multi-level information stored in the memory. With the same number of samples for replay, our method can use more past knowledge to prevent interference. We conduct extensive evaluations on several popular CL datasets, and experiments show that our method consistently outperforms state-of-the-art methods with various sizes of episodic memory. We further provide a detailed analysis of these results and demonstrate that our method is more viable in practical scenarios.