Realisation of neural network controllers in integrated process supervision

Recent developments in neural network controllers have focused mainly on either primary or adaptive control techniques. To date, there has been little attempt to integrate and schedule them within a common control framework on the basis of the system behaviour. An architecture for integrated process supervision, IPS, has been proposed by Leitch and Quek (IEE Proc.-D, Control Theory and Application, 39(3) (1992) 317-27) as a general meta-level supervisory system which automatically schedules between generic control tasks according to the system performance. The IPS scheme was successfully validated using various classical and adaptive controllers (Leitch and Quek, IEE Proc. 3rd Int. Conf. Control, Vol. 1, March, 1991, pp. 127-33; Ho and Goh, Final Year Dissertation, Nanyang Technological University, 1993). This paper demonstrates how the IPS scheme can be used to integrate and schedule between the neural network primary and adaptive control regimes. The cerebellar model articulation controller (Conforth & Elliman, in Techniques and Applications of Neural Networks, ed. M. Taylor & P. Lisboa. Prentice Hall, UK, 1993, pp. 35–46), CMAC, is chosen for this purpose. Its structure is modified and integrated within the IPS scheme. The modification results in better system performances than the standard PI controllers. Moreover the realisation of the modified CMAC and its associated learning algorithm within the IPS illustrates the generality of the IPS as a generic meta-level supervisory control architecture.     

Integration strategy for distributed intelligent systems

In this article, we describe a new framework for designing real-time intelligent control systems. An integrated intelligent system is a large knowledge integration environment that consists of both symbolic reasoning systems (expert systems) and numerical computation packages. These modular software programs are controlled by a meta-system which manages the selection, operation, and communication of these programs. This new architecture can serve as a universal configuration to develop high-performance intelligent systems for many complicated application domains in the real-time manufacturing process. As an example, an intelligent optimal control is utilized to illustrate the integrated intelligent control system.     

Development of expert control systems: A pattern classification and recognition approach

In this paper, a pattern classification and recognition approach to expert control systems is developed for use in the on-line analysis and design of dynamic systems. The approach used is based on the tuning of a three-term PID controller and, hence, it is not dependent on a specific form of the process model. A real-time experiment of implementing the developed controller using a microcomputer and associated hardware is presented. A sample set of production rules is discussed. The expert system reaches appropriate tuning parameters, using extracted features, such as oscillatory, underdamped, and exponentially monotonic properties.     

Study of predictive controller tuning methods

Several tuning guidelines for model predictive control proposed in literature have been converted into suitable tuning rules and investigated with the help of simulations of two typical transfer functions and a nonlinear unstable chemical reactor as well as a real-time laboratory turbogenerator control application. A modified version of a supervisory performance tuning procedure has also been applied to explore the possibility of application of auto-tuning in model predictive control. A new tuning procedure is finally presented on the basis of the results obtained using several previously existing tuning guidelines.     

MASE-BDI: agent-based simulator for environmental land change with efficient and parallel auto-tuning

This paper presents an agent-based simulator for environmental land change that includes efficient and parallel auto-tuning. This simulator extends the Multi-Agent System for Environmental simulation (MASE) by introducing rationality to agents using a mentalistic approach—the Belief-Desire-Intention (BDI) model—and is thus named MASE-BDI. Because the manual tuning of simulation parameters is an error-prone, labour and computing intensive task, an auto-tuning approach with efficient multi-objective optimization algorithms is also introduced. Further, parallelization techniques are employed to speed up the auto-tuning process by deploying it in parallel systems. The MASE-BDI is compared to the MASE using the Brazilian Cerrado biome case. The MASE-BDI reduces the simulation execution times by at least 82 × and slightly improves the simulation quality. The auto-tuning algorithms, by evaluating less than 0.00115 % of a search space with 6 million parameter combinations, are able to quickly tune the simulation model, regardless of the objective used. Moreover, the experimental results show that executing the tuning in parallel leads to speedups of approximately 11 × compared to sequential execution in a hardware setting with 16-CPU cores.     

Use of neural networks for quick and accurate auto-tuning of PID controller

With reference to a real industrial application of process control, some considerations are discussed concerning the accuracy of methods for auto-tuning of proportional, integral and derivative factor (PID). In particular, a theoretical–experimental approach is described, that allows to evaluate the adequateness of new methods for auto-tuning of PID, able to significantly reduce the time duration for auto-tuning with respect to traditional ones. This result has been achieved by using suitable techniques of experimental data processing, based on neural-networks algorithms, set for this specific application. The effect on described methodology of environmental and operating disturbances is also described.     

A novel real-time fuzzy adaptive auto-tuning scheme for cascade PID controllers

This paper presents a novel fuzzy auto-tuning methodology to continuously adapt PID control actions without interrupting the normal process operation. New auto-tuning rules are introduced to schedule a gradual and guided activation of each individual P, I and D control mode in three adjustable functional control zones. An auto-scaling procedure has been incorporated to generalize the autotuning scheme to efficiently respond to any set-point change outside a pre-defined operating span. In contrast to existing auto-tuning algorithms, the proposed scheme is not an on-demand auto-tuning methodology and hence does not require alertness of an experienced engineer to initiate and supervise its initial operation in a separate commissioning identification pre-test. This interesting feature provides a new perspective on PID auto-tuning approaches. Performance of the proposed auto-tuning scheme is practically evaluated in a real pilot plant within a networked control system (NCS) configuration, realized by industrial Ethernet and Foundation Fieldbus technologies. An extensive series of test scenarios has been conducted to explore efficiency of the proposed auto-tuning methodology to cope with fixed and varying operating set-points under uncertain and variable network transmission time delays and external disturbance.     

基于现场总线的RFID生产线集成控制系统

提出基于现场总线的无线射频识别技术(RFID)与生产线控制系统的集成架构,分析了该架构中RFID数据采集单元的功能组成,开发了具有CAN总线接口的RFID数据采集单元,建立了一个基于CAN总线的RFID生产线集成控制实验系统。与现有的RFID在生产线上的应用相比,该系统结构简单,RFID标签所承载的信息更加丰富,信息交互更为直接、快捷,具有更高的可靠性和实时性。     

An integrated approach of MAS-CommonKADS,Model–View–Controller and web application optimization strategies for web-based expert system development

Web-based expert system development has been considered as complex, multidisciplinary and knowledge driven process. This paper presents a framework for development of web-based expert system with integrated approach of MAS-CommonKADS agent-oriented methodology, Model–View–Controller (MVC) architecture and web applications optimization strategies to deal with complexity of development and to achieve high usability. Study will guide in software engineering of developing such system with respect to Internet Technologies. Application of proposed framework for developing web-based expert system in sugarcane disorder diagnosis has been demonstrated. Results indicate that proposed methodology better deal with complexity of web-based expert system development and usability.     

基于PLC的PID参数自整定

PID控制在过程工业控制中应用广泛,但在实际工业现场运行的PID回路的控制性能差异较大,有许多系统长期置于手动控制。一部分由于系统过程特性使PID调节不能满足控制要求,还有一部分却是由于PID回路参数整定的不合理。针对控制系统现场实施中PID参数整定繁琐、整定质量差异大、经验不易移植的问题,采用了基于PLC的PID参数自整定方法。该方法概念清晰,实施方便,在某锅炉的恒压供水控制中应用效果良好。该方法基于继电器反馈自整定,具有一定的普适性,对工程实施人员要求低,易于推广。     

An intelligent control and decision approach for adaptive systems

An intelligent control and decision-making (ICD) approach that integrates expert systems technology with adaptive algorithms is presented. The controller parameters of adaptive systems can be determined using human expertise and knowledge, and they can also be adjusted based on active monitoring and identification. Decision-making, fine tuning and inexact reasoning provide the end-user and the control engineers with a natural and integrated methodology for use with intelligent control systems. Computer simulation results demonstrate the utility of the proposed technique that is an effective intelligent control and decision approach. The ICD system is implemented using a Lisp based expert system shell on an IBM PC.     

A real-time computer controller for a Robotic Filament Winding system

This paper presents an integrated real-time control system for a Robotic Filament Winding manufacturing cell. The architecture is based on a multiprocessor system employing four processor boards. The system incorporates a hierarchical control layout with the task specification at the highest level and the robot and winder set point tracking at the lowest. Eventual design goals include a PC front-end unit capable of winding path generation and testing prior to actual part production. Preliminary experimental results on cylindrical, elbow and T-shaped pipe-fittings are included.     

Adaptive hierarchical tuning of fuzzy controllers

Fuzzy controller design includes both linear and non-linear dynamic analysis. The knowledge base parameters associated within the fuzzy rule base influence the non-linear control dynamics while the linear parameters associated within the fuzzy output signal influence the overall control dynamics. For distinct identification of tuning levels, an equivalent linear controller output and a normalized non-linear controller output are defined. A linear proportional-integral-derivative (PID) controller analogy is used for determining the linear tuning parameters. Non-linear tuning is derived from the locally defined control properties in the non-linear fuzzy output. The non-linearity in the fuzzy output is then represented in a graphical form for achieving the necessary non-linear tuning. Three different tuning strategies are evaluated. The first strategy uses a genetic algorithm to simultaneously tune both linear and non-linear parameters. In the second strategy the non-linear parameters are initially selected on the basis of some desired non-linear control characteristics and the linear tuning is then performed using a trial and error approach. In the third method the linear tuning is initially performed off-line using an existing linear PID law and an adaptive non-linear tuning is then performed online in a hierarchical fashion. The control performance of each design is compared against its corresponding linear PID system. The controllers based on the first two design methods show superior performance when they are implemented on the estimated process system. However, in the presence of process uncertainties and external disturbances these controllers fail to perform any better than linear controllers. In the hierarchical control architecture, the non-linear fuzzy control method adapts to process uncertainties and disturbances to produce superior performance.     

Integrated knowledge acquisition architectures

An architecture for knowledge acquisition systems is proposed based upon the integration of existing methodologies, techniques and tools which have been developed within the knowledge acquisition, machine learning, expert systems, hypermedia and knowledge representation research communities. Existing tools are analyzed within a common framework to show that their integration can be achieved in a natural and principled fashion. A system design is synthesized from what already exists, putting a diversity of well-founded and widely used approaches to knowledge acquisition within an integrative framework. The design is intended to be clean and simple, easy to understand, and easy to implement. A detailed architecture for integrated knowledge acquisition systems is proposed that also derives from parallel cognitive and theoretical studies.     

智能PID参数自整定技术在伺服系统中的应用

针对常规PID控制参数整定困难,且受时变、非线性等因素影响而不能达到预期控制效果的实际情况,提出了RBF网络动态辨识的BP神经网络PID参数自整定算法.此算法可实现PID控制参数的在线自整定和优化;同时,将算法应用于伺服控制系统中,以VC++6.0和Matlab为开发和仿真工具,对动态辨识神经网络智能PID参数自整定方法进行仿真研究.仿真结果表明,控制算法鲁棒性强、响应速度快,可用于控制参数时变的非线性系统.     

ABC2 an Agenda Based Multi-Agent Model for Robots Control and Cooperation

This paper presents a model for the control of autonomous robots that allows cooperation among them. The control structure is based on a general purpose multi-agent architecture using a hybrid approach made up by two levels. One level is composed of reactive skills capable of achieving simple actions by their own. The other one uses an agenda used as an opportunistic planning mechanism to compound, activate and coordinate the basic skills. This agenda handles actions both from the internal goals of the robot or from other robots. This two level approach allows the integration of real-time response of reactive systems needed for robot low-level behavior, with a classical high level planning component that permits a goal oriented behavior. The paper describes the architecture itself, and its use in three different domains, including real robots, as well as the issues arising from its adaptation to the RoboCup simulator domain.     

Dealing with limited data in ballistic impact scenarios: an empirical comparison of different neural network approaches

In the domain of high-speed impact between solids, the simulation of one trial entails the use of large resources and an elevated computational cost. The objective of this research is to find the best neural network associated with a new problem of ballistic impact, maximizing the quantity of trials available and simplifying their architecture. To achieve this goal, this paper proposes a tuning performance process based on four stages. These stages include existing statistical techniques, a combination of proposals to improve the performance and analyze the influence of each variable. To measure the quality of the different networks, two criteria based on information theory have been incorporated to reflect the fit of the data with respect to their complexity. The results obtained show that the application of an integrated tuning process in this domain permits improvement in the performance and efficiency of a neural network in comparison with different machine learning alternatives     

基于Intranet的企业管控一体化技术研究

本文以某煤业集团Intranet瓦斯实时监控信息集成系统为例,研究了实现企业管控一体化的技术。文中介绍了铁煤集团Intranet瓦斯实时监控信息集成系统的体系结构、系统组成。为了保证系统的实时性能,系统在B／S架构的基础上提出了分布式存储、分布式发布的系统集成解决方案。