From process experts to a real-time knowledge-based system

This paper describes the development and implementation of a real-time knowledge-based system (RTKBS) carried out in collaboration with Eli Lilly in the UK. The RTKBS was developed in order to provide consistent advice to the operators of a large-scale antibiotic production plant in real time. The ultimate objective was to reduce variability and improve the process yield. A wealth of process information exists in the experience of the process operators, engineers and scientists, and it was capitalized upon in this application. However, this information tends primarily to be qualitative in nature and its elicitation traditionally represents a bottleneck in developing an RTKBS. The paper demonstrates that this type of process knowledge can be effectively and rapidly captured and then coded within an RTKBS. The project was undertaken in two stages. During the knowledge elicitation stage the specific application area was identified in consultation with the industrial partner and qualitative knowledge in the selected area was extracted from experts/operators using KAT™ (a structured technique for knowledge elicitation). Subsequently this knowledge was converted into a rule base and implemented within G2, which then acted as an advisory/decision support system.     

化工过程实时状态监测与模糊诊断系统研究与实现

过程监测与故障诊断是化工过程工程中的一项重要任务,是保证生产过程安全运行、降低废品率的重要环节。本文在分析各种诊断方法的基础上,结合数据分析、专家系统、模糊逻辑以及面向对象分析等技术,提出并开发了一个化工过程实时监测与模糊诊断系统。该系统由数据校正、过程监测和模糊专家系统三部分组成,采用开放式结构,具有良好的易维护性和可扩充性。     

Dynamic route planning with real-time traffic predictions

Situation aware route planning gathers increasing interest as cities become crowded and jammed. We present a system for individual trip planning that incorporates future traffic hazards in routing. Future traffic conditions are computed by a Spatio-Temporal Random Field based on a stream of sensor readings. In addition, our approach estimates traffic flow in areas with low sensor coverage using a Gaussian Process Regression. The conditioning of spatial regression on intermediate predictions of a discrete probabilistic graphical model allows us to incorporate historical data, streamed online data and a rich dependency structure at the same time. We demonstrate the system with a real-world use-case from Dublin city, Ireland.     

Compositional verification of real-time systems with Explicit Clock Temporal Logic

To specify and verify real-time systems, we consider a real-time version of temporal logic called Explicit Clock Temporal Logic. Timing properties are specified by extending the classical framework of temporal logic with a special variable which explicitly refers to a global notion of time. Programs are written in an Occam-like real-time language with synchronous message passing. To show that a program satisfies a specification, we formulate a proof system which is proved to be sound and relatively complete. The proof system is compositional, which makes it possible to decompose the design of a large system into the design of subsystems. This is shown by the verification of a small part of an avionics system.This research was supported by ESPRIT-BRA project 3096 Formal Methods and Tools for the Development of Distributed and Real-Time Systems (SPEC).     

Intelligent process monitoring by interfacing knowledge-based systems and multivariate statistical monitoring

An intelligent process monitoring and fault diagnosis environment has been developed by interfacing multivariate statistical process monitoring (MSPM) techniques and knowledge-based systems (KBS) for monitoring multivariable process operation. The real-time KBS developed in G2 is used with multivariate SPM methods based on canonical variate state space (CVSS) process models. Fault detection is based on T ² charts of state variables. Contribution plots in G2 are used for determining the process variables that have contributed to the out-of-control signal indicated by large T ² values, and G2 Diagnostic Assistant (GDA) is used to diagnose the source causes of abnormal process behavior. The MSPM modules developed in Matlab are linked with G2. This intelligent monitoring and diagnosis system can be used to monitor multivariable processes with autocorrelated, crosscorrelated, and collinear data. The structure of the integrated system is described and its performance is illustrated by simulation studies.     

复杂过程的故障诊断技术

对于具有控制复杂,难以精确描述数学模型的复杂过程,介绍了智能化故障诊断方法。故障检测由基于知识系统实现,通过过程的深层浅层知识获得故障检测产生式规则。通过智能故障诊断技术实现故障诊断功能。     

实时故障诊断专家系统知识库的建造

知识库是专家系统的核心部件,知识库的建造质量直接决定着专家系统解决实际问题的能力,因而,建造知识库是建造专家系统的关键工作。该文介绍对某钢厂冷轧生产线进行状态监测和故障诊断的实时故障诊断专家系统知识库的建造过程,对研究和建造类似专家系统,将具有某些实际参考价值。     

Communications-oriented development of component-based vehicular distributed real-time embedded systems

We propose a novel model- and component-based technique to support communications-oriented development of software for vehicular distributed real-time embedded systems. The proposed technique supports modeling of legacy nodes and communication protocols by encapsulating and abstracting the internal implementation details and protocols. It also allows modeling and performing timing analysis of the applications that contain network traffic originating from outside of the system such as vehicle-to-vehicle, vehicle-to-infrastructure, and cloud-based applications. Furthermore, we present a method to extract end-to-end timing models to support end-to-end timing analysis. We also discuss and solve the issues involved during the extraction of these models. As a proof of concept, we implement our technique in the Rubus Component Model which is used for the development of software for vehicular embedded systems by several international companies. We also conduct an application-case study to validate our approach.     

含控制时滞系统的实时故障诊断和最优容错控制

研究含有控制时滞的线性系统的故障诊断方法和最优容错控制问题.给出了最优容错控制律的存在唯一性条件,提出了最优容错控制律的设计算法.通过构造增广的降维状态观测器,设计了在线诊断故障的故障诊断器并同时实现了系统状态的观测,解决了最优容错控制的物理不可实现问题.利用观测器的输出得到物理可实现的动态最优容错控制律.仿真实例验证了故障诊断方法和动态最优容错控制律的有效性.     

A Knowledge-based System with Audio-Visual Aids

A Knowledge-based System with Audio-Visual Aids (KS/AV) is presented. KS/AV is a knowledge-based system that has multiple types of knowledge represented not only in symbols but in audio-visual (AV) images, and it provides an environment for humanmachine communication through AV media. We define a predicate logic based on objects for knowledge representation in KS/AV. It is a first order predicate logic in which every individual is regarded as an object. All of the individuals including AV images are regarded as objects. Their definitions are based on the class concepts of Smalltalk-80. AV image objects presented in this paper include not only simple video and graphic images, but also composite images that consist of several component images. This paper presents the KS/AV system developed on a small computer system with various AV equipment. As a case study, we developed a reading advisory system for children on KS/AV, which communicates with children through AV images and gives their favourite picture books.     

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.     

螺旋模型在开发网络可存活性系统中的应用

介绍了网络可存活性系统的概念及其开发特点，阐述了螺旋模型适合开发网络可存活性系统的理由，介绍了采用螺旋模型开发网络可存活性系统的过程，包括需求分析、设计、编码验证、测试和维护进化等5个阶段。     

基于Petri网诊断器的离散事件系统模式故障的在线诊断

本文研究基于Petri网诊断器的离散事件系统模式故障的在线诊断问题.先构建一种用于模式故障在线诊断的自动机,给出了基于这种自动机的在线诊断方法.然后将自动机转换为Petri网并进一步构造了可用于S型模式故障或T型模式故障在线诊断的Petri网诊断器,提出了基于Petri网诊断器的模式故障在线诊断算法.通过分析算法的复杂性,得到了该算法具有多项式空间复杂性的结论.     

宝钢冷轧过程故障诊断模糊专家系统

本设计了并实施了一个用于冷轧过程的故障诊断的实时专家系统。通过模糊理论和专家系统相结合解决了诊断中的不确定性问题。     

Hercules — A modeling system with knowledge about economics

The paper is concerned with the effectiveness of economic modeling. It argues that the key problems of economic modeling are the time and effort it takes to implement a model, the problems of detecting and correcting errors, and the difficulties involved in communicating assumptions. The logical consequence is to improve the model representation and the error detection capabilities of modeling systems. The paper discusses information content and error detection in models that use conventional mathematical notation and argues that we need a model representation with more information than is usually available in mathematical representations. HERCULES, a modeling systems for large economywide static models is then presented. The system uses a model representation in which all economic assumptions are directly available. This makes model implementation much faster and prevents certain types of errors. In other cases, error detection and error messages are far superior to those of general purpose mathematical modeling systems. The technical implementation of HERCULES, designed to allow maximum flexibility for future enhancements is discussed.     

化工设备故障诊断仿真模型设计及计算分析

通过化工设备的结构模型、功能模型建立仿真模型,在对仿真模型分析的基础上得到症状与故障之间的数量关系并进行分析计算,推断出潜在的故障模式,为设计化工设备故障诊断专家系统奠定基础。     

不完备多模型混合系统故障诊断的粒子滤波算法

针对模型不完备的混合动态系统故障诊断问题提出了一种粒子滤波算法. 系统未建模动态利用未知故障模式描述, 当存在未知模式时, 常规的粒子滤波器算法存在发散现象. 本文分析了常规粒子滤波器发散的原因, 提取了两个基于粒子集合的统计量: 粒子集的规格化因子 W 以及最大后验概率估计状态的信度 B. 在此基础上设计了检测未知故障模式的阈值逻辑, 即当 W 几乎为0且 B 较小时离散状态为未知故障模式. 在一定假设下从理论上证明了算法的正确性. 通过不完备的非线性混合系统诊断问题验证了算法的有效性.     

基于贝叶斯网络的车辆电源系统故障诊断方法

针对车辆电源系统测试点少且测试数据不完备的问题,提出一种多信号流图模型和贝叶斯网络相结合的故障诊断方法。利用多信号流图模型建立电源系统的故障诊断模型,得到系统故障源与测试信号对应的故障依赖矩阵,在此基础上,建立用于故障诊断的贝叶斯网络结构,根据历史数据完成网络的参数学习,并以故障后验概率最大为准则,实现电源系统的故障诊断。仿真实验验证了该方法的有效性。