This paper proposes an experimental analysis on the convergence of evolutionary algorithms (EAs). The effect introducing chaotic sequences instead random ones during all phases evolution process is investigated. approach based substitution number generator (RNG) with sequences. Several numerical examples are reported in order to compare performance EA using and generators as regards both results speed. obtained show that some always able increase value measured algorithm-performance indexes...

The design and application of Soft Sensors (SSs) in the process industry is a growing research field, which needs to mediate problems model accuracy with data availability computational complexity. Black-box machine learning (ML) methods are often used as an efficient tool implement SSs. Many efforts are, however, required properly select input variables, class, order needed hyperparameters. aim this work was investigate possibility transfer knowledge acquired SS for given similar one. This...

Here, this article reports about the design of a soft sensor (SS) able to monitor hazardous gases in industrial plants. The SS is designed estimate gas concentrations by means measurements coming from an array sensors, avoiding at same time humidity and temperature influence on outputs. has been with data-driven approach, using set experimental data acquired laboratory. methodologies two different SSs are compared, aim obtaining both good performance low computational complexity. As first...

The influence of weather conditions on sea state, and in particular the dynamic evolution waves, is an important issue that affects several areas, including maritime traffic planning coastal works. To collect relevant data, buoys are used to set up distributed sensor networks along areas. However, unfavourable can lead downtime, which be extended due maintenance issues. ability improve robustness these systems using predictive models, i.e. digital twins, interpolate extrapolate missing data...

This paper analyzes a number of strategies that are devoted to improving the generalization capabilities neural-network-based soft sensors when only small data sets available. The aim this is search for strategy able cope with problem scarcity experimental data, which often arises in industrial applications. considered based on manipulation training increase their diversity either by injecting noise into available or using bootstrap resampling approach. A new method, an aggregation neural...

Abstract Smart systems adapt to the surrounding environments in a number of ways. They are capable scavenge energy from available sources, sense and elaborate external stimuli adequately react. Electro Active Polymers playing main role realization smart for applications if fields such as bio inspired autonomous robotics, medicine, aerospace. This paper focus on possibility use Ionic Polymer Metal Composites class materials relevant post silicon systems. The three aspects this new technology,...

Soft Sensors (SSs) are inferential dynamical models employed in industries to perform prediction of process hard-to-measure variables based on their relation with easily accessible ones. They allow implementation real-time control and monitoring the plants present other advantages terms costs efforts. Given complexity industrial processes, these generally designed data-driven black-box machine learning (ML) techniques. ML methods work well only if data which is performed share same...

The methodology proposed in the paper applies artificial intelligence (AI) techniques to modeling and control of some climate variables within a greenhouse. nonlinear physical phenomena governing dynamics temperature humidity such systems are, fact, difficult model using traditional techniques. proposes framework for development soft computing-based controllers modern greenhouses.

In this paper, a virtual instrument for the estimation of octane number in gasoline produced by refineries is introduced. The was designed with aim replacing measuring hardware during maintenance operations. based on nonlinear moving average model, implemented using multilayer perceptron neural networks. Stacking approaches are adopted to improve performance instrument. Classical linear algorithms model aggregation compared paper strategy, combination set first-level estimators. validity...

This paper introduces a soft sensor (SS) for the estimation of deflection polymeric mechanical actuator. The actuator is based on ionic polymer-metal composites (IPMCs). Applications IPMCs have been proposed in fields such as robotics, surgery, and aerospace, to mention most interesting ones. In application fields, both complexity size actuating system are chief importance. An SS can be, therefore, preferred hardware measuring output, estimating motion. Also, low-order models interest limit...

In the paper a new structure of Multi-Layer Perceptron, able to deal with quaternion-valued signals, is proposed. A learning algorithm for proposed Quaternion MLP (QMLP) also derived. Such neural network allows one interpolate functions quaternion variable smaller number connections respect corresponding real valued MLP.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

In this paper an overview on Genetic Algorithms (GAs) is reported. GAs are described from a theoretical point of view, important implementation problems dealt with and wide variety GA applications reported in system engineering literature described. The survey also includes some studies at present progress our laboratories, regarding the use solving optimisation fields neural networks control theory.

Soft Sensors (SSs) are inferential models used in many industrial fields. They allow for real-time estimation of hard-to-measure variables as a function available data obtained from online sensors. SSs generally built using industries historical databases through data-driven approaches. A critical issue SS design concerns the selection input variables, among those candidate dataset. In case processes, inputs can reach great numbers, making computationally demanding and leading to poorly...