In this paper, we develop a common cellular neural network framework for various adaptive non-linear filters based on robust statistic and geometry-driven diffusion paradigms. The base models of both approaches are de...
详细信息
In this paper, we develop a common cellular neural network framework for various adaptive non-linear filters based on robust statistic and geometry-driven diffusion paradigms. The base models of both approaches are defined as difference-controlled non-linear CNN templates, while the self-adjusting property is ensured by simple analogic (analog and logic) CNN algorithms. Two adaptive strategies are shown for the order statistic class. When applied to the images distorted by impulse noise both give more visually pleasing results with lower-frequency weighted mean square error than the median base model. Generalizing a variational approach we derive the constrained anisotropic diffusion, where the output of the geometry-driven diffusion model is forced to stay close to a pre-defined morphological constraint. We propose a coarse-grid CNN approach that is capable of calculating an acceptable noise-level estimate (proportional to the variance of the Gaussian noise) and controlling the fine-grid anisotropic diffusion models. A combined geometrical–statistical approach has also been developed for filtering both the impulse and additive Gaussian noise while preserving the image structure. We briefly discuss how these methods can be embedded into a more complex algorithm performing edge detection and image segmentation. The design strategies are analysed primarily from VLSI implementation point of view; therefore all non-linear cell interactions of the CNN architecture are reduced to two fundamental non-linearities, to a sigmoid type and a radial basis function. The proposed non-linear characteristics can be approximated with simple piecewise-linear functions of the voltage difference of neighbouring cells. The simplification makes it possible to convert all space-invariant non-linear templates of this study to a standard instruction set of the CNN Universal Machine, where each instruction is coded by at most a dozen analog numbers. Examples and simulation results are given t
In this paper we show a method of time series prediction with neural networks. In the first section we present the main elements of the problem and two standard methods that can be used for predictions. In the second ...
详细信息
Introduces a first proposal on how to use semiotics in order to improve software engineering methods, when intelligent autonomous systems are targeted. First we investigate the current flaws in software engineering, c...
详细信息
Introduces a first proposal on how to use semiotics in order to improve software engineering methods, when intelligent autonomous systems are targeted. First we investigate the current flaws in software engineering, concerning intelligent autonomous systems. Then we propose a knowledge taxonomy, based on semiotic ideas, aiming at a tool to understand the information domain of intelligent autonomous systems. Further, we illustrate how to use the notion of knowledge types during the development of a simple intelligent autonomous system, emphasizing the relationship between the described types of knowledge aiming at the understanding on how they are organized into an intelligent autonomous system. After that we review the idea of the generalized subsistence machine (GSM) proposed by Meystel (1996) as a possible tool (not the unique nor the best one) to represent the information domain of intelligent autonomous systems. Finally, it is shown how both ideas might be used in the requirement analysis step of any software engineering method when an intelligent autonomous system is targeted. As a conclusion, we discuss the future works and trends of semiotic intelligent autonomous systems engineering.
A dynamical mathematical model of a water supply plant based on lumped parameters is described. A concept of its control system is proposed that ensures output pressure stabilisation under conditions of variable water...
详细信息
A dynamical mathematical model of a water supply plant based on lumped parameters is described. A concept of its control system is proposed that ensures output pressure stabilisation under conditions of variable water consumption and variable water recourses. The control system consists of inner control loops which control the flow of each pump station and of a superimposed control loop that controls the output pressure of the water supply plant. The pressure controller calculates the cumulative reference value of the water flow for all controlled pumps and from this value an algorithm for the flow distribution calculates the reference flow for each inner loop, taking into account the level of water accumulation in each water well. Control performances of output pressure obtained by a conventional PI controller and a fuzzy logic based controller are compared.
The model based fault detection and identification scheme for the rudder servo system as the actuator in the closed loop course keeping control system is presented. The nonlinear process model that enables description...
详细信息
The model based fault detection and identification scheme for the rudder servo system as the actuator in the closed loop course keeping control system is presented. The nonlinear process model that enables description of a wide class of fault types is given and the fault function as the residual for detecting and identifying the fault is introduced. A fault detection scheme with variable thresholds is suggested and its performance has been tested via simulation in the presence of modeling uncertainty and noise. A fault identification scheme based on comparison between the fault function estimate and the output of a predefined analytical fault model is suggested.
The basic principles of the self-tuning generalized predictive controller (GPC) and the self-tuning pole placement controller are presented. A laboratory shell-and-tube heat exchanger is used to test the properties of...
详细信息
The basic principles of the self-tuning generalized predictive controller (GPC) and the self-tuning pole placement controller are presented. A laboratory shell-and-tube heat exchanger is used to test the properties of the presented controllers. The self-tuning GPC were compared with the self-tuning pole placement controller regarding their parameter adjustment complexity, reference and disturbance step responses and robustness to differences between the real process and its mathematical model.
作者：
Zoran VukićEdin OmerdićLjubomir KuljacaUniversity of Zagreb
Faculty of Electrical Engineering and Computing Department of Control and Computer Engineering in Automation Unska 3 HR-10000 Zagreb Croatia University of Tuzla
Faculty of Electrical and Mechanical Engineering Department of Control Engineering in Automation Franjevačka 2 BH-75000 Tuzla Bosnia and Herzegovina
Improved 2-input fuzzy autopilot for ship course control and 3-input fuzzy autopilot for track-keeping are proposed. Nonlinear model of a ship and a steering subsystem is used. The 3-input fuzzy autopilot uses heading...
详细信息
Improved 2-input fuzzy autopilot for ship course control and 3-input fuzzy autopilot for track-keeping are proposed. Nonlinear model of a ship and a steering subsystem is used. The 3-input fuzzy autopilot uses heading signal, yaw rate signal and lateral offset from the nominal track to produce a command rudder angle. Input variable fuzzyfication, fuzzy associative memory rules and output set defuzzyfication are described. Obtaining of FAM rules for 3-input fuzzy is described. Dynamical behavior of 2 and 3-input fuzzy autopilot is compared. The influence of wave disturbance, sea current and external disturbance from a passing ship on track-keeping performance was analyzed.
Based on the research at the location "Middle Adriatic", the analysis of the noise spectrum of the Adriatic Sea is presented. The applied measurement method and necessary instrumentation, followed by the bas...
详细信息
Based on the research at the location "Middle Adriatic", the analysis of the noise spectrum of the Adriatic Sea is presented. The applied measurement method and necessary instrumentation, followed by the basic scheme of the measurement channel, are given. A representative Adriatic Sea noise spectrum for the particular location is given, with the sea state as a parameter. A regression analysis is made that led to an appropriate approximation polynomial of the spectrum.
In order to apply a model based control strategy such as flexible recipes control to an industrial batch process, a model of the process dynamics is needed. This paper presents the modelling procedure for two such mod...
详细信息
In order to apply a model based control strategy such as flexible recipes control to an industrial batch process, a model of the process dynamics is needed. This paper presents the modelling procedure for two such models: a semi-empirical and an artificial neural network model. Both models predict precipitation rates of TiO 2 particles in an industrial hydrolysis process. Model properties and their prediction accuracy is compared. The artificial neural network is trained using the augmented training data set approach. A simulator has been designed to study the application Of flexible recipe instructions.
暂无评论