Ontology-based reconfiguration agent for intelligent mechatronic systems in flexible manufacturing

This paper proposes a novel approach to achieving fast reconfiguration of modular manufacturing systems, based on an ontology-based reconfiguration agent. The agent uses ontological knowledge of the manufacturing environment for the purpose of reconfiguration without human intervention. The current mass customization era requires increased flexibility and agility in the manufacturing systems to adapt changes in manufacturing requirements and environments. Our configuration agent minimises the overheads of the current reconfiguration process by automating it. It infers facts about the manufacturing environment from the ontological knowledge model and then decides whether the current environment can support the given manufacturing requirements. This paper proposes the agent architecture enabling the integration between the high level planning with the distributed low level control compliant with the upcoming IEC 61499 function blocks standard.     

An intelligent multi-agent e-services method—An international telecommunication example

The online services of B2B e-commerce have had to face a challenge resulting from the diverse services built on heterogeneous platforms that must work together in an integrated and seamless manner. Today, businesses have accumulated large numbers of online services that run and reside on a variety of environments. Furthermore, they have different workflows and operational support systems that need to interact with their legacy systems. The result has been chaotic and disruptive.We developed a new framework, artifact, and performance model with which to address this problem. A multi-agent e-service system was developed to cope with dynamics and upheaval. We used a customer-centric viewpoint with supply chains both upstream and downstream. An implementation was performed to determine problems in its development. Two simple live case studies were conducted to illustrate the model's feasibility and validity.     

面向CMMI的软件度量分析过程研究与应用

为了辅助软件组织有效实施符合CMMI模型的软件度量过程,提出了一种GREDR过程框架模型,以指导软件度量的目标策划与过程实施。在实际软件项目过程中的应用结果表明：GREDR模型能够提高软件度量过程的系统性与效用。     

多智能体协作方法及其应用研究

将复杂系统分解成由多个智能体构成的合作多智能体系统，建立了多智能体系统的决策模型，能动态实时地计算每一时刻智能体的决策局势，适应环境的动态变化．采用多智能体方法对半导体生产进行调度，提高了半导体生产线设备的利用率，缩短了单位工件的加工时间．     

采用MSBN多智能体协同推理的智能农业车辆环境识别

为了解决智能农业车辆对所处复杂农田环境的识别信度定量分析困难的问题,提出了基于多连片贝叶斯网(MSBN)多智能体协同推理的目标识别算法.该方法把多智能体图像采集系统的局部信息表征在MSBN模型中,在观测不完备条件下,虽然单个智能体仅拥有目标的局部观测信息,但利用重叠子域信息的更新可以进行子网间消息的传播.利用MSBN局部推理和子网间信度通信的全局推理对多源信息进行融合,以提高识别性能.实验结果表明,与传统神经网络或BN方法相比,基于MSBN目标识别算法有效地对多源信息进行了补充,可以提高农业车辆在复杂环境进行识别的准确性.     

CMMI体系建立过程及在项目管理中的作用

详细介绍了CMMI的来源、CMMI的5个等级、不同等级的特点以及不同的CMMI等级在控制项目进度和避免项目终止的概率。介绍了基于CMMI模型建立适合组织的体系,以及完成的体系框架和最终的成果情况。最后说明了基于CMMI的体系在项目管理中的作用,并以同行评审为例,详细介绍其在项目计划、项目预算和项目成果的把控方面的有益之处。     

A multi-agent approach to intelligent monitoring in smart grids

In this paper, we propose a scalable multi-agent architecture to give support to smart grids, paying special attention to the intelligent monitoring of distribution substations. The data gathered by multiple sensors are used by software agents that are responsible for monitoring different aspects or events of interest, such as normal voltage values or unbalanced intensity values that can end up blowing fuses and decreasing the quality of service of end consumers. The knowledge bases of these agents have been built by means of a formal model for normality analysis that has been successfully used in other surveillance domains. The architecture facilitates the integration of new agents and can be easily configured and deployed to monitor different environments. The experiments have been conducted over a power distribution network.     

An intelligent method to block e-mail bombs

It is hard to block e-mail bombs because they are usually sent by normal SMTP (Simple Mail Transfer Protocol) applications with fake mail sender addresses and IP addresses. Fortunately, original network packets contain real IP address information anyway. Collecting and analyzing these packet contents can help an administrator to realize where the e-mail bombs are coming from and block them. This article presents a simple method that uses a bandwidth manager device to collect and analyze packets to get e-mail bombs information as well as to block e-mail bomb source IP addresses in routers. In practical application experiences at the computer center in a university, this method blocked e-mail bombs simply and effectively. Furthermore, a fuzzy inference system was also designed to help identify e-mail bombs. Its fuzzy membership functions could be adapted using the fuzzy neural network learning method. In brief, the proposed method affords an automatic and adaptable alarm to find e-mail bombs.     

Student modeling and assessment in intelligent tutoring of software patterns

This paper presents the design, implementation, and evaluation of a student model in DEPTHS (Design Pattern Teaching Help System), an intelligent tutoring system for learning software design patterns. There are many approaches and technologies for student modeling, but choosing the right one depends on intended functionalities of an intelligent system that the student model is going to be used in. Those functionalities often determine the kinds of information that the student model should contain. The student model used in DEPTHS is a result of combining two widely known modeling approaches, namely, stereotype and overlay modeling. The model is domain independent and can be easily applied in other learning domains as well. To keep student model update during the learning process, DEPTHS makes use of a knowledge assessment method based on fuzzy rules (i.e., a combination of production rules and fuzzy logics). The evaluation of DEPTHS performed with the aim of assessing the system’s overall effectiveness and the accuracy of its student model, indicated several advantages of the DEPTHS system over the traditional approach to learning design patterns, and encouraged us to move on further with this research.     

分布式约束满足问题及其在MAS任务分配中的应用*

针对多智能体系统(MAS)任务分配问题中多个任务与MAS两者的分布式特征,将任务分配问题形式化为分布式约束满足问题(DCSP)进行求解,分别建立了以任务为中心和以agent为中心两种MAS任务分配模型,基于改进的DCSP分布式并行求解算法,提出了基于DCSP的MAS任务分配问题求解框架。该方法适合求解agent间通信有随机延迟以及agent间存在多约束的问题,应用实例的求解表明了其实用性与有效性。     

正交M ult i-agen t 遗传算法及其性能分析

将Multi—agent系统、遗传算法与正交试验设计方法相结合，提出一种新的遗传算法——正交Multi—agent遗传算法，其主要思想是：利用正交设计的方法产生初始化种群；用正交交叉算子代替传统的算术交叉算子；利用agent间的竞争作用与每个agent所具有的知识和自学习能力进行启发式搜索，以提高进化的速度，仿真试验和性能分析表明，正交Multi—agent遗传算法不但具有很强的全局优化能力和较快的收敛速度，而且具有很强的鲁棒性。     

An agent-oriented approach to resolve scheduling optimization in intelligent manufacturing

Agent technology is considered as a promising approach for developing optimizing process plans in intelligent manufacturing. As a bridge between computer aided design (CAD) and computer aided manufacturing (CAM), the computer aided scheduling optimization (CASO) plays an important role in the computer integrated manufacturing (CIM) environment. In order to develop a multi-agent-based scheduling system for intelligent manufacturing, it is necessary to build various functional agents for all the resources and an agent manager to improve the scheduling agility. Identifying the shortcomings of traditional scheduling algorithm in intelligent manufacturing, the architecture of intelligent manufacturing system based on multi-agent is put forward, among which agent represents the basic processing entity. Multi-agent-based scheduling is a new intelligent scheduling method based on the theories of multi-agent system (MAS) and distributed artificial intelligence (DAI). It views intelligent manufacturing as composed of a set of intelligent agents, who are responsible for one or more activities and interacting with other related agents in planning and executing their responsibilities. In this paper, the proposed architecture consists of various autonomous agents that are capable of communicating with each other and making decisions based on their knowledge. The architecture of intelligent manufacturing, the scheduling optimization algorithm, the negotiation processes and protocols among the agents are described in detail. A prototype system is built and validated in an illustrative example, which demonstrates the feasibility of the proposed approach. The experiments prove that the implementation of multi-agent technology in intelligent manufacturing system makes the operations much more flexible, economical and energy efficient.     

多智能体技术发展及其应用综述

首先阐述了智能体技术的相关定义及特性,通过分析国内外多智能体技术的应用研究文献,对多智能体系统的基础研究进行分析并梳理了多智能体一致性及控制等方向的技术发展。接着选取了机器人控制和无线传感器网络两个领域重点,探讨了近年来多智能体技术在实际工程中的应用变化与最新成果。最后,总结了多智能体技术在工程应用中有待解决的主要问题,指出了未来多智能体技术应用的研究方向。     

Ontological fuzzy agent for electrocardiogram application

The electrocardiogram (ECG) signal is adopted extensively as a low-cost diagnostic procedure to provide information concerning the healthy status of the heart. However, the QRS complex must be calculated accurately before proceeding with the heart rate variability (HRV). In particular, the R peak needs to be detected reliably. This study presents an adaptive fuzzy detector to detect the R peak correctly. Additionally, an ontological fuzzy agent is presented to process the collection of ECG signals. The required knowledge is stored in the ontology, which comprises some personal ontologies and predefined by domain experts. The ontological fuzzy agent retrieves the ECG signals with R peaks marked for HRV analysis and ECG further applications. It contains a personal fuzzy filter, an HRV analysis mechanism, and a fuzzy normed inference engine. Moreover, the ECG fuzzy signal space and some important properties are presented to define the working environment of the agent. An experimental platform has been constructed to test the performance of the agent. The results indicate that the proposed method can work effectively.     

A research on intelligent fault diagnosis of wind turbines based on ontology and FMECA

Clean energy is an increasing concern as more and more countries pay attention to environmental protection, which brings the rapid development of wind power. More new wind farms and new wind turbines have been put into operation, this caused the problem that the diagnostic knowledge is lacking and diagnostic efficiency is low for new employed maintenance personnel. In order to meet the demands of fault diagnosis of wind turbines, a method of intelligent fault diagnosis based on ontology and FMECA (Failure Mode, Effects and Criticality Analysis) is proposed in this paper. In the proposed method, the FMECA of wind turbines is selected as the knowledge source, and deep knowledge and shallow knowledge extracted from this source are represented by ontology modeling. And then, the diagnosis knowledge base of wind turbines can be established. Reasoning on this knowledge base by virtue of JESS (Java Expert Shell System) rule engine, maintenance personnel can find the causes of faults of a wind turbine quickly, and choose the proper solutions. This method realizes the knowledge sharing between product design enterprises and wind farms. The knowledge base which combines the deep knowledge and the shallow knowledge can improve the capability of fault diagnosis and provide better supports for diagnostic decision making.     

一种基于模糊切换的模糊复合控制器及其应用

基于线性控制器与模糊控制器的特点，通过使两者并行结合，提出一种模糊复合控制器的设计方法，谈模糊复合控制器采用模糊推理完成两组控制器的平稳“切换”，而且其中模糊控制器的比例因子的初始整定可由PID控制器的整定参数获得，从而简化了模糊控制器的设计。在某电厂300MW机组的实际应用结果表明，采用谈方法设计的过热蒸汽温度控制系统具有较强的适应能力和良好的控制效果。     

Design and development of an intelligent controller for a pole-balancing robot

In this paper, an intelligent controller capable of static balancing as well as dynamic balancing of a pole mounted on a motorized robot is designed and developed. The brain of the intelligent controller lies in the Fuzzy Inference System, which receives as its input displacement, velocity and acceleration information. An embedded instrumentation system onboard the robot measures the displacement of the robot and the angle of inclination of the pole from the vertical position. For static balancing, the controller needs to maintain the pole in an upright position while the robot is free to move on a flat surface. For dynamic balancing, the robot needs to balance the pole while performing transitions up and down a ramp. Furthermore, the robot needs to steer itself back to the center to prevent it from falling off the ramp.     

An ontological intelligent agent platform to establish an ecological virtual enterprise

A virtual enterprise (VE) is a dynamic alliance of companies collaborating for the accomplishment of a specific business goal. To establish a VE, it is very important for the VE initiator to select appropriate partners. General criteria such as price, lead time, quality, etc. are the major concerns for most VE initiators. However, in today’s environmentally conscious society, environmental issues such as enterprise green image, product eco-design, etc. are increasingly receiving attention. Thus, it is worth to research on how to select the appropriate collaborative partners to establish an ecological VE.The objective of this paper is to establish a multi-agent system platform for individual companies to form an ecological VE based on ontology theory and intelligent agents. The ontological approaches include shared ontology construction, ontology matching, ontology integration, ontology storage and ontology reasoning. In the generalized case that the VE initiator is a manufacturer and the collaborating partner are suppliers, the multi-agent system comprises three types of intelligent agents, namely, knowledge manager agent (KMrA), manufacturer agent (MA) and supplier agent (SA). MA and SA represent the capabilities and interests of the VE initiator and the VE partners, respectively. KMrA is in charge of functioning sub-tasks of the ontological approach. To select partners for the ecological VE, the VE initiator will also consider the environmental criteria, in addition to the general supplier selection criteria such as price, quantity, quality and lead time. The environmental criteria may include factors such as environmental management, green image, green product and pollution control. The complete set of selection criteria, including the environmental criteria, are categorised into quantitative or qualitative criteria. The formation of ecological VE is then divided into two stages, that is, candidate supplier selection based on qualitative criteria, and ultimate supplier selection based on quantitative criteria. A simplified example is introduced to illustrate and justify the proposed ontological approaches and intelligent agent platform.     

An intelligent method for selecting optimal materials and its application

Material selection is associated with all design and manufacturing problems. This paper presents an intelligent method to deal with the materials selection problems wherein the design configurations, working conditions, as well as the design-relevant information are not precisely known. The presented method is applied to select optimal materials for robotic components at an early stage of design. A computing tool is developed in order to implement the method. Unlike other materials selection methods, the presented method does not require derivation of material indices, extraction of “if … then …” rules, or cumbersome inference calculations. However, like material index based selection method, it uses widely available material property charts as material-relevant information. This way the method is made more user-friendly and realistic.     

An ontology-based framework to support intelligent data analysis of sensor measurements

In the past years, the large availability of sensed data highlighted the need of computer-aided systems that perform intelligent data analysis (IDA) over the obtained data streams. Temporal abstractions (TAs) are key to interpret the principle encoded within the data, but their usefulness depends on an efficient management of domain knowledge. In this article, an ontology-based framework for IDA is presented. It is based on a knowledge model composed by two existing ontologies (Semantic Sensor Network ontology (SSN), SWRL Temporal Ontology (SWRLTO)) and a new developed one: the Temporal Abstractions Ontology (TAO). SSN conceptualizes sensor measurements, thus enabling a full integration with semantic sensor web (SSW) technologies. SWRLTO provides temporal modeling and reasoning. TAO has been designed to capture the semantic of TAs. These ontologies have been aligned through DOLCE Ultra-Lite (DUL) upper ontology, boosting the integration with other domains. The resulting knowledge model has a modular design that facilitates the integration, exchange and reuse of its constitutive parts. The framework is sketched in a chemical plant case study. It is shown how complex temporal patterns that combine several variables and representation schemes can be used to infer process states and/or conditions.