An Essay on Complex Valued Propositional Logic Pre-Processing of Hyperspectral Images Using Nonlinear Filters Model Predictive Control of a pH Maintaining Systems Reinforcement Learning for Predictive Maintenance of Industrial Plants Predictive Control of a Laboratory Time Delay Process Experiment
V. Sgurev
Key Words:
Propositional logic; logical equations; complex propositional logic; Boolean algebra; imaginary logical variable; lattice.
Abstract:
In decision making logic it is often necessary to solve logical equations for which, due to the features of disjunction and conjunction, no admissible solutions exist. In this paper an approach is suggested, in which by the introduction of Imaginary Logical Variables (ILV), the classical propositional logic is extended to a complex one. This provides a possibility to solve a large class of logical equations.The real and imaginary variables each satisfy the axioms of Boolean algebra and of the lattice. It is shown that the Complex Logical Variables (CLV) observe the requirements of Boolean algebra and the lattice axioms. Suitable definitions are found for these variables for the operations of disjunction, conjunction, and negation. A series of results are obtained, including also the truth tables of the operations disjunction, conjunction, negation, implication, and equivalence for complex variables. Inference rules are deduced for them analogous to Modus Ponens and Modus Tollens in the classical propositional logic. Values of the complex variables are obtained, corresponding to TRUE (T) and FALSE (F) in the classic propositional logic. A conclusion may be made from the initial assumptions and the results achieved, that the imaginary logical variable i introduced hereby is "truer" than condition "T" of the classic propositional logic and i – "falser" than condition "F", respectively. Possibilities for further investigations of this class of complex logical structures are pointed out.
S. Ilchev, Z. Ilcheva
Key Words:
Hyperspectral imaging; random field simulation; edgepreserving filtration.
Abstract:
In this paper the use of a set of nonlinear edge-preserving
filters is proposed as a pre-processing stage with the purpose to improve the quality of hyperspectral images before object detection. The capability of each nonlinear filter to improve images, corrupted by spatially and spectrally correlated Gaussian noise, is evaluated in terms of the average Improvement factor in the Peak Signal to Noise Ratio (IPSNR), estimated at the filter output. The simulation results demonstrate that this pre-processing procedure is efficient only in case the spatial and spectral correlation coefficients of noise do not exceed the value of 0.6.
A. Grancharova, L. Kostov
Key Words:
Model predictive control; nonlinear systems; constraints; pH maintaining system.
Abstract:
In this paper the problem of optimal regulation of a pH maintaining system is considered, where the outputs are the pH value and the liquid level in the system and the control inputs are the flow rates of the base input flow and the output flow. The optimal regulation problem is formulated as a nonlinear model predictive control problem in the presence of constraints. Two cases are considered: 1) presence of box constraints only on the control inputs and 2) considering also constraints on the rate of change of the inputs.
P. Koprinkova-Hristova
Key Words:
Reinforcement learning; temporal difference error; echo state network; predictive maintenance; industrial plant.
Abstract:
The reinforcement learning is a well-known approach for solving optimization problems having limited information about plant dynamics. Its key element, named "critic" is aimed at prediction of future "punish/reward" signals received as a result of undertaken control actions. The main idea in the present work is to use such a "critic" element for prediction of approaching alarm situations based on limited measurement information from the industrial plant. In order to train the critic network in real time it is proposed to use a special kind of a fast trainable recurrent neural network, called Echo State Network (ESN). The approach proposed is demonstrated on an example for predictive maintenance of a mill fan in Maritsa East 2 Thermal Power Plant.
S. Enev
Key Words:
Model predictive control; time delay process; experimental results.
Abstract:
The paper presents the design and implementation of a Model Predictive Control (MPC) scheme of a laboratory heatexchange
process with a significant time delay in the input-output path. The optimization problem formulation is given and an MPC control algorithm is designed, achieving integral properties. Details, related to the practical implementation of the control law are discussed and the first experimental results are presented.