This paper presents an innovative approach to self-adaptation of the structure of a fuzzy controller in real time. Without any off-line pretraining, the algorithm achieves very high control performance through the ite...
详细信息
This paper presents an innovative approach to self-adaptation of the structure of a fuzzy controller in real time. Without any off-line pretraining, the algorithm achieves very high control performance through the iteration of a three-stage algorithm. In the first stage, coarse tuning of the fuzzy rules (both rule consequents and membership functions of the premises) is accomplished using the sign of the dependency of the plant output with respect to the control signal and an overall analysis of the main operating regions. In stage two, fine tuning of the fuzzy rules is achieved based on the controller output error using a gradient-based method. Finally, the third stage is responsible of modifying the structure of the fuzzy controller, proposing that input variable which should get a new membership function in order to improve the control policy in an optimum way.
This paper describes an algorithm of PID-parameter tuning with correlation-coefficient identification, which is applied in the auto-tuner of PID-parameters based on an embedded MCU. We have optimized the algorithm acc...
详细信息
This paper describes an algorithm of PID-parameter tuning with correlation-coefficient identification, which is applied in the auto-tuner of PID-parameters based on an embedded MCU. We have optimized the algorithm according to the features of the MCU.
Maintenance and evolution of complex software systems (such as large telecom embedded devices) involve activities such as reverse engineering (RE) and software visualization. Although several RE tools exist, we found ...
详细信息
Maintenance and evolution of complex software systems (such as large telecom embedded devices) involve activities such as reverse engineering (RE) and software visualization. Although several RE tools exist, we found their architecture hard to adapt to the domain specific requirements posed by our current practice in Nokia. We present an open architecture which allows easy prototyping of RE data exploration and visualization scenarios for a large range of domain models. We pay special attention to the visual and interactive requirements of the reverse engineering process. The article describes the basic architecture of our toolkit, compares it to the existing RE environments and present several visualizations taken from real cases.
Aboard current ships, such as the DDG 51, engineering control and damage control activities are manpower intensive. It is anticipated that, for future combatants, the workload demand arising from operation of systems ...
详细信息
Aboard current ships, such as the DDG 51, engineering control and damage control activities are manpower intensive. It is anticipated that, for future combatants, the workload demand arising from operation of systems under conditions of normal steaming and during casualty response will need to be markedly reduced via automated monitoring, autonomous control, and other technology initiatives. Current DDG 51 class ships can be considered as a manpower baseline and under Condition III typical engineering control involves seven to eight watchstanders at manned stations in the Central Control Station, the engine rooms and other machinery spaces. In contrast to this manning level, initiatives such as DD 21 and the integrated engineering plant (IEP) envision a partnership between the operator and the automation system, with more and more of the operator's functions being shifted to the automation system as manning levels decrease. This paper describes some human systems integration studies of workload demand reduction and, consequently, manning reduction that can be achieved due to application of several advanced technology concepts. Advanced system concept studies in relation to workload demand are described and reviewed including. Piecemeal applications of diverse automation and remote control technology concepts to selected high driver tasks in current DDG 51 activities. Development of the reduced ship's crew by virtual presence system that will provide automated monitoring and display to operators of machinery health, compartment conditions, and personnel health. The IEP envisions the machinery control system as a provider of resources that are used by various consumers around the ship. Resource needs and consumer priorities are at all times dependent upon the ship's current mission and the availability of equipment pawnbrokers.
The behavior of a Boltzmann Machine (BM) according to changes in the parameters that determine its convergence is experimentally analyzed to find a way to accelerate the convergence towards a solution for the given op...
详细信息
A major trend in recent cluster communication systems is to circumvent the operating system during the actual data transfers. That, on the one hand, reduces latency since there is no user-kernel transition needed and,...
详细信息
This paper compares some mntationoperators containing expert knowledge about the problem of optimizing the parameters of a Radial Basis Function Neural Network. It is shown that the expert kno wledge is not always abl...
详细信息
This paper presents the problem of optimizing a radial basis function neural network from training examples as a nulti objective problem and proposes an evolutionary algorithm to solve it properly. This algorithm inco...
详细信息
Soft w are visualization is an area of computer science dented to supporting the understanding and effective use of algorithms. The application of softw are visualization to Evolutionary Computation has been receiving...
详细信息
A hybrid method, based on evolutionary computation, Monte Carlo simulation, and neural networks for functional approximation and time series prediction, is proposed to reduce the high computational cost usually requir...
详细信息
暂无评论