Antonino Laudani

A Neural Network-Based Low-Cost Solar Irradiance Sensor

Measuring solar irradiance allows for direct maximization of the efficiency in photovoltaic power plants. However, devices for solar irradiance sensing, such as pyranometers and pyrheliometers, are expensive and difficult to calibrate and thus seldom utilized in photovoltaic power plants. Indirect methods are instead implemented in order to maximize efficiency. This paper proposes a novel approach for solar irradiance measurement based on neural networks, which may, in turn, be used to maximize efficiency directly. An initial estimate suggests the cost of the sensor proposed herein may be price competitive with other inexpensive solutions available in the market, making the device a good candidate for large deployment in photovoltaic power plants. The proposed sensor is implemented through a photovoltaic cell, a temperature sensor, and a low-cost microcontroller. The use of a microcontroller allows for easy calibration, updates, and enhancement by simply adding code libraries. Furthermore, it can be interfaced via standard communication means with other control devices, integrated into control schemes, and remote-controlled through its embedded web server. The proposed approach is validated through experimental prototyping and compared against a commercial device.

Spin-Hall nano-oscillator: A micromagnetic study

This Letter studies the dynamical behavior of spin-Hall nanoscillators from a micromagnetic point of view. The model parameters have been identified by reproducing recent experimental data quantitatively. Our results indicate that a strongly localized mode is observed for in-plane bias fields such as in the experiments, while predict the excitation of an asymmetric propagating mode for large enough out-of plane bias field similarly to what observed in spin-torque nanocontact oscillators. Our findings show that spin-Hall nanoscillators can find application as spin-wave emitters for magnonic applications where spin waves are used for transmission and processing information on nanoscale.

Shape Optimization of Multistage Depressed Collectors by Parallel Evolutionary Algorithm

In this paper a novel parallel meta-heuristic algorithm called MeTEO is presented, applied to the shape optimization of multistage depressed collectors, simulated by means of a Finite Element collector and electron gun simulator, COLLGUN, which uses the Constructive Solid Geometry for the description of the device shape. METEO is a hybrid algorithm composed by three different heuristics: FSO (Flock of Starlings Optimization), PSO (Particle Swarm Optimization), and BCA (Bacterial Chemotaxis Algorithm); it performs the optimization using both the topological and the metric rules and offers a natural parallel implementation that allows speeding up the whole process of optimization by the fitness modification (FM).

Bouc–Wen Hysteresis Model Identification by the Metric-Topological Evolutionary Optimization

From a computational point of view, the identification of Bouc-Wen (BW) hysteresis model is a hard task due to the large number of parameters to be found. This is one of the reasons for which it is rarely used for modeling magnetic hysteresis, where other hysteresis models are widely used (e.g., Preisach and Jiles-Atherton). However, the opportunities that the differential expression of BW model could offer for its use in more complex computation task (e.g., nonlinear inductors inserted into a circuit and so on) justify a deeper investigation on its adoption in ferromagnetism. In this paper, using a new hybrid heuristic called metric-topological-evolutionary optimization (MeTEO), the BW identification is presented. MeTEO is a powerful algorithm based on a synergic and strategic use of three evolutionary heuristics: 1) the flock-of-starlings optimization, which shows not only high exploration capability, but also a lack of convergence; 2) the particle swarm optimization, which has a good convergence capability; and 3) the bacterial chemotaxis algorithm, which has no collective behavior or exploration skill, but has high convergence capability. MeTEO is designed to use parallel architectures and exploits the fitness modification technique. Numerical validations are presented in comparison with the performances obtained using other approaches available in the literature.

CFSO3: A New Supervised Swarm-Based Optimization Algorithm

We present CFSO3, an optimization heuristic within the class of the swarm intelligence, based on a synergy among three different features of the Continuous Flock-of-Starlings Optimization. One of the main novelties is that this optimizer is no more a classical numerical algorithm since it now can be seen as a continuous dynamic system, which can be treated by using all the mathematical instruments available for managing state equations. In addition, CFSO3 allows passing from stochastic approaches to supervised deterministic ones since the random updating of parameters, a typical feature for numerical swam-based optimization algorithms, is now fully substituted by a supervised strategy: in CFSO3 the tuning of parameters is a priori designed for obtaining both exploration and exploitation. Indeed the exploration, that is, the escaping from a local minimum, as well as the convergence and the refinement to a solution can be designed simply by managing the eigenvalues of the CFSO state equations. Virtually in CFSO3, just the initial values of positions and velocities of the swarm members have to be randomly assigned. Both standard and parallel versions of CFSO3 together with validations on classical benchmarks are presented.

A neural approach for the numerical modeling of two-dimensional magnetic hysteresis

This paper deals with a neural network approach to model magnetic hysteresis at macro-magnetic scale. Such approach to the problem seems promising in order to couple the numerical treatment of magnetic hysteresis to FEM numerical solvers of the Maxwells equations in time domain, as in case of the non-linear dynamic analysis of electrical machines, and other similar devices, making possible a full computer simulation in a reasonable time. The neural system proposed consists of four inputs representing the magnetic field and the magnetic inductions components at each time step and it is trained by 2-d measurements performed on the magnetic material to be modeled. The magnetic induction B is assumed as entry point and the output of the neural system returns the predicted value of the field H at the same time step. A suitable partitioning of the neural system, described in the paper, makes the computing process rather fast. Validations with experimental tests and simulations for non-symmetric and minor loops are presented.

Swarm/flock optimization algorithms as continuous dynamic systems

A new general typology of optimization algorithms, inspired to classical swarm intelligence, is presented. They are obtained by translating the numerical swarm/flock-based algorithms into differential equations in the time domain and employing analytical closed-forms written in the continuum. The use of circulant matrices for the representation of the connections among elements of the flock allowed us to analytically integrate the differential equations by means of a time-windowing approach. The result of this integration provides functions of time that are closed-forms, suitable for describing the trajectories of the flock members: they are directly used to update the position and the velocity of each bird/particle at each step (time window) and consequently they substitute in the continuous algorithm the classical updating rules of the numerical algorithms. Thanks to the closed forms it is also possible to analyze the effects due to the tuning of parameters in terms of exploration or exploitation capabilities. In this way we are able to govern the behavior of the continuous algorithm by means of non stochastic tuning of parameters. The proposed continuous algorithms have been validated on famous benchmark functions, comparing the obtained results with the ones coming from the corresponding numerical algorithms.

A neural network approach for the differentiation of numerical solutions of 3-D electromagnetic problems

An innovative approach employing a neural network (NN) is presented to compute accurately derivatives and differential operators (such as Laplacian, gradient, divergence, curl, etc.) of numerical solutions of three-dimensional electromagnetic problems. The adopted NN is a multilayer perceptron, whose training is performed off-line by using a class of suitably selected polynomial functions. The desired degree of accuracy can be chosen by the user by selecting the appropriate order of the training polynomials. The on-line utilization of the trained NN allows us to obtain accurate results with a negligible computational cost. Comparative examples of differentiation performed both on analytical functions and finite element solutions are given in order to illustrate the computational advantages.

On training efficiency and computational costs of a feed forward neural network: a review

A comprehensive review on the problem of choosing a suitable activation function for the hidden layer of a feed forward neural network has been widely investigated. Since the nonlinear component of a neural network is the main contributor to the network mapping capabilities, the different choices that may lead to enhanced performances, in terms of training, generalization, or computational costs, are analyzed, both in general-purpose and in embedded computing environments. Finally, a strategy to convert a network configuration between different activation functions without altering the network mapping capabilities will be presented.

TWT magnetic focusing structure optimization by parallel evolutionary algorithm

Purpose – The purpose of this paper is to present the application of a novel hybrid algorithm, called MeTEO (Metric‐Topological‐Evolutionary‐Optimization), based on the combination of three heuristics inspired by artificial life to the solution of optimization problems of a real electronic vacuum device.Design/methodology/approach – The Particle Swarm Optimization (PSO), the Flock‐of‐Starlings Optimization (FSO) and the Bacterial Chemotaxis Algorithm (BCA) were adapted to implement a novel meta‐heuristic MeTEO the FSO has been powerfully employed for exploring the whole space of solutions, whereas the PSO is used to explore local regions where FSO had found solutions, and BCA to refine the solutions found by PSO, thanks its better performances in local search.Findings – The optimization of the focusing magnetic field of a Travelling Wave Tubes (TWT) collector is presented in order to show the effectiveness of MeTEO, in combination with COLLGUN FE simulator and equivalent source representation. The optimiz...