یکپارچه سازی سیستم های هوشمند در توسعه سیستم های تطبیقی هوشمند
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|5503||2004||31 صفحه PDF||سفارش دهید|
نسخه انگلیسی مقاله همین الان قابل دانلود است.
هزینه ترجمه مقاله بر اساس تعداد کلمات مقاله انگلیسی محاسبه می شود.
این مقاله تقریباً شامل 10215 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
- تولید محتوا با مقالات ISI برای سایت یا وبلاگ شما
- تولید محتوا با مقالات ISI برای کتاب شما
- تولید محتوا با مقالات ISI برای نشریه یا رسانه شما
پیشنهاد می کنیم کیفیت محتوای سایت خود را با استفاده از منابع علمی، افزایش دهید.
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : International Journal of Approximate Reasoning, Volume 35, Issue 3, March 2004, Pages 307–337
Different combinations of fuzzy logic and neural networks provide various ingredients for smart adaptive applications. Both expertise and data can be integrated in the development of intelligent systems. Evolutionary computation is also widely used in tuning of these systems. For small, specialised systems there is a large number of feasible solutions, but developing truly adaptive, and still understandable, systems for highly complex systems require more compact approaches in the basic level. Linguistic equation (LE) approach originating from fuzzy logic is an efficient technique for these problems. Insight to the process operation is maintained since all the modules can be assessed by expert knowledge and membership definitions relate measurements to appropriate operating areas. The LE approach increases the performance by combining various specialised models in a case-based approach: models can be generated automatically from data. The LE approach is also successfully extended to dynamic simulation and used in intelligent controller design. The integration of intelligent systems is based on understanding the different tasks of smart adaptive systems: modelling, intelligent analysers, detection of operating conditions, control and intelligent actuators. The system integration leads to a hybrid system: fuzzy set systems move gradually to higher levels, neural networks and evolutionary computing are used for tuning, and the whole system reinforced with efficient statistical analysis, signal processing and mechanistic modelling and simulation.
Development of smart adaptive systems for non-linear, complex, multivari- able and highly interactive industrial processes is a challenging task. Usually, the important quality variables can be estimated only from other measured variables. Physical limitations of actuators must be taken into account. Sig- nificant interactions between process variables cause interactions between the controllers. Various time delays depend strongly on operating conditions and can dramatically limit the performance and even destabilise the closed-loop system. For overall production processes, control systems take care of several subprocesses. There are many and long time-varying delays, process feedbacks at several levels, closed control loops, factors that exist and cannot be measured and interactions between physical and chemical factors. Uncertainty is an un- avoidable part of the process control in real-world applications since there al- ways are some unknown factors affecting to the process conditions. Successful applications require integration of data-based methods and expertise, especially if fast reactions to changing operating conditions are needed. Smart adaptive systems are based on intelligent methods, i.e. individual subsystems are intelligent systems. The smartness of the overall systems de- pends on integration of these intelligent systems. A smart system needs a de- cision making unit: in Fig. 1 this is the control block. Putting everything in this block would result too complicated systems. A better alternative is to make a generic and configurable control block whose inputs are (calculated) variables related system properties which really should be controlled. This can be done with software sensors type intelligent analysers. This part is especially impor- tant in connection to continuous on-line analysers. Intelligent analysers may also include trend analysers. If operating conditions are changing, intelligent analysers are also needed for detection of the operating conditions. Measure- ment should be handled with digital signal processing. Also operation of ac- tuators can be improved with intelligent modelling. Dynamic modelling and simulation is needed for comparing alternatives in controller design. On-line analysers facilitate new measurements which also need new calcu- lation modules to be used in everyday process control. Intelligent analysers provide solutions for this, but part of the work could be done also in digital signal processing. Possibilities of using intelligent techniques are improving also in actuators. Moving close to the process brings new challenges for the implementation of the intelligent systems.n this paper different intelligent methods are evaluated on basis of their possible contributions to the smart adaptive systems. Linguistic equation ap- proach originating from fuzzy set systems is introduced as a integrating methodology in developing smart adaptive systems for complex applications.
نتیجه گیری انگلیسی
Different combinations of fuzzy logic and neural networks provide various ingredients for smart adaptive applications. Linguistic equation (LE) approach originating from fuzzy logic is an efficient technique for these problems. Insight to the process operation is maintained since all the modules can be assessed by expert knowledge and membership definitions relate measurements to appro- priate operating areas. The LE approach increases the performance by com- bining various specialised models in a case-based approach: models can be generated automatically from data. The system integration leads to a hybrid system: fuzzy set systems move gradually to higher levels, neural networks and evolutionary computing are used for tuning, and the whole system reinforced with efficient statistical analysis, signal processing and mechanistic modelling and simulation.