Felipe Lara-Rosano

Dynamic knowledge inference and learning under adaptive fuzzy Petri net framework

Since knowledge in an expert system is vague and modified frequently, expert systems are fuzzy and dynamic. It is very important to design a dynamic knowledge inference framework which is adjustable according to knowledge variation as human cognition and thinking. A generalized fuzzy Petri net model, called adaptive fuzzy Petri net (AFPN), is proposed with this object in mind. AFPN not only has the descriptive advantages of the fuzzy Petri net, it also has learning ability like a neural network. Just as other fuzzy Petri net (FPN) models, AFPN can be used for knowledge representation and reasoning, but AFPN has one important advantage: it is suitable for dynamic knowledge, i.e., the weights of AFPN are adjustable. Based on the AFPN transition firing rule, a modified backpropagation learning algorithm is developed to assure the convergence of the weights.

Adaptive fuzzy petri nets for dynamic knowledge representation and inference

Abstract Knowledge in some fields like Medicine, Science and Engineering is very dynamic because of the continuous contributions of research and development. Therefore, it would be very useful to design knowledge-based systems capable to be adjusted like human cognition and thinking, according to knowledge dynamics. Aiming at this objective, a more generalized fuzzy Petri net model for expert systems is proposed, which is called AFPN (Adaptive Fuzzy Petri Nets). This model has both the features of a fuzzy Petri net and the learning ability of a neural network. Being trained, an AFPN model can be used for dynamic knowledge representation and inference. After the introduction of the AFPN model, the reasoning algorithm and the weight learning algorithm are developed. An example is included as an illustration.

Model-reference adaptive control based on neurofuzzy networks

Model reference adaptive control (MRAC) is a popular approach to control linear systems, as it is relatively simple to implement. However, the performance of the linear MRAC deteriorates rapidly when the system becomes nonlinear. In this paper, a nonlinear MRAC based on neurofuzzy networks is derived. Neurofuzzy networks are chosen not only because they can approximate nonlinear functions with arbitrary accuracy, but also they are compact in their supports, and the weights of the network can be readily updated on-line. The implementation of the neurofuzzy network-based MRAC is discussed, and the local stability of the system controlled by the proposed controller is established. The performance of the neurofuzzy network-based MRAC is illustrated by examples involving both linear and nonlinear systems.

Modelling data uncertainty in growth forecasts

Abstract A probabilistic methodology within a dynamic framework is proposed for the study of moments of errors in growth forecasts resulting from data uncertainty. This methodology is applied to well-known evolutionary models of growth, namely exponential and logistic. Explicit expressions for moments of the stochastic variable are derived. The paper explores methods based on two-point distribution approach, second-moment analysis, and probability distribution of parameters. Of these, the two-point distribution is found to be computationally advantageous. An interesting feature emerging from the analysis is that the mean and relative fluctuations in the projected variable of interest are numerically not much different from the respective ones when the uncertainties in the growth parameters are characterized by Gaussian, uniform or two-point distribution. This, however, holds for forecasting periods which are short in comparison with the time-scale of the process under study.

Micro-facet solar concentrator

A low-cost micro-facet solar concentrator is proposed. A large number of small flat mirrors are situated in a parabolic surface to approximate a large parabolic mirror. Low-cost commercial flat mirrors can be used for manufacturing such concentrators. Geometrical analyses show that this concentrator will have a concentration rate of some hundreds of suns. The problems of production of micro mirrors, support components, and the automatic assembly of the concentrator are discussed. Rough estimations show that the cost of the concentrator should be ∼

Generalized minimum variance control of steam-boiler temperature using neuro-fuzzy approach

55 per square metre of concentrator surface.

A weighted fuzzy petri net model for knowledge learning and reasoning

A neuro-fuzzy network predictive approach is introduced to design a control system for nonlinear industrial process. While the nonlinear process is modeled by neuro-fuzzy technique containing local CARMA model, traditional generalized minimum variance predictive control method can be extended to a nonlinear case in a neuro-fuzzy fashion. Boiler steam temperature process is chosen as the realistic system for the demonstration of the techniques discussed and the neuro-fuzzy controller was found to provide a satisfactory performance over the complex system.

Analog processing for nonlinear fuzzy controller development

Fuzzy Petri net (FPN) theory can be used as a computational paradigm for intelligent systems. This specification and engineering language provides a graphical tool for visualization, communication and interpretation, and supports to manipulate imprecise and vague information. However, it is lack of adjustment (learning) mechanism being proposed to cope with potential numerical deficiencies of these models, and to adapt system inconstancy. This paper proposes a weighted approach which can overcome this shortage. A new FPN model with adaptive weights is proposed for knowledge learning and reasoning. Based on this model, fuzzy knowledge reasoning and weight learning algorithms are developed.

Dynamic Fuzzy Logic

In this work we present some analog circuits used in fuzzy control. We have done some modifications to conventional implementations and we present a new circuit for the inference stage. We have substituted the conventional method of rule aggregation for a simpler one, which results in a reduced number of transistors. We also present an example of an analog fuzzy controller applied to a nonlinear plant with multiplicity of stable and unstable equilibrium points, different operation regions and different operation modes.

Modeling an electronic component manufacturing system using Object Oriented Colored Petri Nets

Departing from the notion of a dynamical fuzzy set, we extend the concept of fuzzy logic, to introduce the dynamic fuzzy logic. The dynamic fuzzy logic is the base of the dynamic approximate reasoning, where the truth values and the inference rules are fuzzy, and change over time. The meaning of a dynamical fuzzy conditional proposition of the form IF A(t) THEN B(t), is clarified. We define also a dynamic linguistic variable as a variable whose truth value is represented as a word or sentence in a natural or artificial language whose meaning changes over time.