Search

In the last decades, the majority of the existing infrastructure heritage is approaching the end of its nominal design life mainly due to aging, deterioration, and degradation phenomena, threatening the safety levels of these strategic routes of communications. For civil engineers and researchers devoted to assessing and monitoring the structural health (SHM) of existing structures, the demand for innovative indirect non-destructive testing (NDT) methods aided with artificial intelligence (AI) is progressively spreading. In the present study, the authors analyzed the exertion of various deep learning models in order to increase the productivity of classifying ground penetrating radar (GPR) images for SHM purposes, especially focusing on road tunnel linings evaluations. Specifically, the authors presented a comparative study employing two convolutional models, i.e. the ResNet-50 and the EfficientNet-B0, and a recent transformer model, i.e. the Vision Transformer (ViT). Precisely, the authors evaluated the effects of training the models with or without pre-processed data through the bi-dimensional Fourier transform. Despite the theoretical advantages envisaged by adopting this kind of pre-processing technique on GPR images, the best classification performances have been still manifested by the classifiers trained without the Fourier pre-processing.

Within seismology, geology, civil and structural engineering, deep learning (DL), especially via generative adversarial networks (GANs), represents an innovative, engaging, and advantageous way to generate reliable synthetic data that represent actual samples’ characteristics, providing a handy data augmentation tool. Indeed, in many practical applications, obtaining a significant number of high-quality information is demanding. Data augmentation is generally based on artificial intelligence (AI) and machine learning data-driven models. The DL GAN-based data augmentation approach for generating synthetic seismic signals revolutionized the current data augmentation paradigm. This study delivers a critical state-of-art review, explaining recent research into AI-based GAN synthetic generation of ground motion signals or seismic events, and also with a comprehensive insight into seismic-related geophysical studies. This study may be relevant, especially for the earth and planetary science, geology and seismology, oil and gas exploration, and on the other hand for assessing the seismic response of buildings and infrastructures, seismic detection tasks, and general structural and civil engineering applications. Furthermore, highlighting the strengths and limitations of the current studies on adversarial learning applied to seismology may help to guide research efforts in the next future toward the most promising directions.

This article presents a two-stage fault detection and classification scheme specifically designed for rotating electrical machines. The approach involves the use of new condition indicators that are specific to the frequency domain. The paper proposes two distinct features: one based on the extraction of peaks by using the prominence measure, a technique originating from the topology of mountains, and other based on the calculation of the occupied band power ratio for specific characteristic fault frequencies. A linear based feature reduction technique, the principal component analysis (PCA) has been employed to represent all the data. Afterwards, shallow neural networks have been used to detect and classify the three-phase current signals online. The effectiveness of the proposed scheme has been validated experimentally by using signals obtained with grid and inverter fed induction motors.

Detection of stator-based faults in Induction Machines (IMs) can be carried out in numerous ways. In particular, the shorted turns in stator windings of IM are among the most common faults in the industry. As a matter of fact, most IMs come with pre-installed current sensors for the purpose of control and protection. At this aim, using only the stator current for fault detection has become a recent trend nowadays as it is much cheaper than installing additional sensors. The three-phase stator current signatures have been used in this study to observe the effect of stator inter-turn fault with respect to the healthy condition of the IM. The pre-processing of the healthy and faulty current signatures has been done via the in-built DSP module of dSPACE after which, these current signatures are passed into the MATLAB® software for further analysis using AI techniques. The authors present a Growing Curvilinear Component Analysis (GCCA) neural network that is capable of detecting and follow the evolution of the stator fault using the stator current signature, making online fault detection possible. For this purpose, a topological manifold analysis is carried out to study the fault evolution, which is a fundamental step for calibrating the GCCA neural network. The effectiveness of the proposed method has been verified experimentally.

Hydrogen energy conversion using Fuel Cells is very promising for standalone power as well as transportation applications. Hydrogen gas production using renewable energy sources is possible through the use of electrolyzers in which DC-DC converters play an important role. This paper presents an accurate and robust method of fault diagnosis and condition monitoring applied to an interleaved DC/DC buck converter that supplies a proton exchange membrane (PEM) electrolyzer. This work mainly focuses on power switch open-circuit failures. The study gives excellent results in the early detection of faults to improve the reliability of PEM electrolyzers. A suitable experimental test bench has been realized to obtain data under healthy and faulty operating conditions. A preliminary exploratory analysis of the data has been carried out using a linear approach to understand the geometry of the data and suggest a suitable tool for classifying the system’s condition. The paper then proposes a shallow configuration Long Short Term Memory (LSTM) based neural network capable of detecting and localizing the fault at every time step without any preprocessing. The experimental results presented in this paper show that, after a detailed comparison with other 25 neural and non-neural based techniques for classification, the shallow LSTM neural network gives the best results.

Fault detection in electrical drives can be really challenging, especially when the input data is collected from an operational electrical machine. In order to prevent machine damages and downtimes, it is really important to detect pre-fault conditions. This paper presents the detection of stator inter-turn fault for Synchronous Reluctance Motor (SynRM) with a severity as low as 1.3%. After the transformation of the three-phase currents using Extended Park Vector (EPV) approach, the temporal features were calculated. Thereafter, the geometry of the features has been studied by using the Principal Component Analysis (PCA) and the Curvilinear Component Analysis (CCA) to estimate the best intrinsic dimensionality and extract the most significant features. Finally, a variety of classifiers have been trained with this feature-set (FS) and the shallow neural network has proved to give the best performance.

In recent years, the scientific community has focused on the development of CAD tools that could improve bone fractures' classification, mostly based on Convolutional Neural Network (CNN). However, the discerning accuracy of fractures' subtypes was far from optimal. This paper proposes a modified version of a very recent and powerful deep learning technique, the Vision Transformer (ViT), outperforming CNNs based approaches and consequently increasing specialists' diagnosis accuracy. 4207 manually annotated images were used and distributed, by following the AO/OTA classification, in different fracture types, the largest labeled dataset of proximal femur fractures used in literature. The ViT architecture was used and compared with a classic CNN and a multistage architecture composed of successive CNNs in cascade. To demonstrate the reliability of this approach, 1) the attention maps were used to visualize the most relevant areas of the images, 2) the performance of a generic CNN and ViT was compared through unsupervised learning techniques, and 3) 11 specialists were asked to evaluate and classify 150 proximal femur fractures' images with and without the help of the ViT, then results were compared for potential improvement. The ViT was able to correctly predict 83% of the test images. Precision, recall and F1-score were 0.77 (CI 0.64-0.90), 0.76 (CI 0.62-0.91) and 0.77 (CI 0.64-0.89), respectively. The average specialists' diagnostic improvement was 29% when supported by ViT's predictions, outperforming the algorithm alone. This paper showed the potential of Vision Transformers in bone fracture classification. For the first time, good results were obtained in sub-fractures classification, with the largest and richest dataset ever. Accordingly, the assisted diagnosis yielded the best results, proving once again the effectiveness of a coordinated work between neural networks and specialists., Comment: Under consideration at Artificial Intelligence in Medicine

Parkinson’s is a disease of the central nervous system characterized by neuronal necrosis. Patients at the time of diagnosis have already lost up to 70% of the neurons. It is essential to define early detection techniques to promptly intervene with an appropriate therapy. Handwriting analysis has been proven as a reliable method for Parkinson’s disease diagnose and monitoring. This paper presents an analysis of a Parkinson’s disease handwriting dataset in which neural networks are used as a tool for analyzing the problem space. The goal is to check the validity of the selected features. For estimating the data intrinsic dimensionality, a preliminary analysis based on PCA is performed. Then, a comparative analysis about the classification performances of a multilayer perceptron (MLP) has been conducted in order to determine the discriminative capabilities of the input features. Finally, fifteen temporal features, capable of a more meaningful discrimination, have been extracted and the classification performances of the MLP trained on these new datasets have been compared with the previous ones for selecting the best features.

Automated electrocardiogram analysis and classification is nowadays a fundamental tool for monitoring patient heart activity and, consequently, his state of health. Indeed, the main interest is detecting the arise of cardiac pathologies such as arrhythmia. This paper presents a novel approach for automatic arrhythmia classification based on a 1D convolutional neural network. The input is given by the combination of several databases from Physionet and is composed of two leads, LEAD1 and LEAD2. Data are not preprocessed, and no feature extraction has been performed, except for the medical evaluation in order to label it. Several 1D network configurations are tested and compared in order to determine the best one w.r.t. heart-beat classification. The test accuracy of the proposed neural approach is very high (up to 95%). However, the goal of this work is also the interpretation not only of the results, but also of the behavior of the neural network, by means of confusion matrix analysis w.r.t. the different arrhythmia classes.

This paper presents a comparison between two recurrent neural networks (RNN) for arterial blood pressure (ABP) estimation. ABP is a parameter closely related to the cardiac activity, for this reason its monitoring implies decreasing the risk of heart disease. In order to predict the ABP values (both systolic and diastolic), electrocardiographic (ECG) and photoplethysmographic (PPG) signals are used, separately, as inputs of the networks. To train the artificial neural networks, the synchronized signals are extracted from the Physionet MIMIC database. The output-error Neural networks (NNOE) and the Long Short Term Memory (LSTM) architectures are compared in terms of RMSE and absolute error. NNOE neural network, with ECG signal as input, results the best configuration in terms of both the proposed metrics. The predicted ABP falls within the values of the normative ANSI/AAMI/ ISO 81060-2:2013 for sphygmomanometer certification.

Despite all the progress made in biomedical field, the Electrocardiogram (ECG) is still one of the most commonly used signal in medical examinations. Over the years, the problem of ECG classification has been approached in many different ways, most of which rely on the extraction of features from the signal in the form of temporal or morphological characteristics. Although feature engineering can led to adequately good results, it mostly relies on human ability and experience in selecting the correct feature set. In the last decade, a growing class of techniques based on Convolutional Neural Network (CNN) has been proposed in opposition to feature engineering. The efficiency and accuracy of CNN-based approaches is indisputable, however their ability in extracting and using temporal features from raw signal is poorly understood. The main objective of this work was to uncover the differences and the relationships between CNN feature maps and human-curated temporal features, towards a deeper understanding of neural-based approaches for ECG. In fact, the proposed study succeeded in finding a similarity between the output stage of the first layers of a deep 1D-CNN with several temporal features, demonstrating that not only that the engineered features effectively works in ECG classification tasks, but also that CNN can improve those features by elaborating them towards an higher level of abstraction.

In recent years, due to the high availability of omic data, data driven biology has greatly expanded. However, the analysis of different data sources is still an open challenge. A few multi-omic approaches have been proposed in literature. However, none of them take into consideration the intrinsic topology of each omic. In this work, an unsupervised learning method based on a deep neural network is proposed. For each omic, a separate network is trained, whose outputs are fused into a single graph; for this purpose, an innovative loss function has been designed to better represent the data cluster manifolds. A graph adjacency matrix is exploited to determine similarities among samples. With this approach, omics having a different number of features are merged into a unique representation. Quantitative and qualitative analyses show that the proposed method has results comparable to the state of the art. The method has a great intrinsic flexibility as it can be customized according to the complexity of the tasks and it has a lot of room for future improvements compared to more fine-tuned methods, opening the way for future research.

Due to the huge amount of available omic data, classifying samples according to various omics is a complex process. One of the most common approaches consists of creating a classifier for each omic and subsequently making a consensus among the classifiers that assigns to each sample the most voted class among the outputs on the individual omics.

Cardiovascular Diseases represent the leading cause of deaths in the world. Arterial Blood Pressure (ABP) is an important physiological parameter that should be properly monitored for the purposes of prevention. This work applies the neural network output-error (NNOE) model to ABP forecasting. Three input configurations are proposed based on ECG and PPG for estimating both systolic and diastolic blood pressures. The double channel configuration is the best performing one by means of the mean absolute error w.r.t the corresponding invasive blood pressure signal (IBP); indeed, it is also proven to be compliant with the ANSI/AAMI/ISO 81060-2:2013 regulation for non invasive ABP techniques. Both ECG and PPG correlations to IBP signal are further analyzed using Spearman’s correlation coefficient. Despite it suggests PPG is more closely related to ABP, its regression performance is worse than ECG input configuration one. However, this behavior can be explained looking to human biology and ABP computation, which is based on peaks (systoles) and valleys (diastoles) extraction.

In the last few years, the reduction of energy consumption and pollution became mandatory. It became also a common goal of many countries. Only in Europe, the building sector is responsible for the total 40% of energy consumption and 36% of $CO_{2}$ pollution. Therefore, new control policies based on the forecast of buildings energy behaviors can be developed to reduce energy waste (i.e. policies for Demand Response and Demand Side Management). This paper discusses an innovative methodology for smart building indoor air-temperature forecasting. This methodology is based on a Non-linear Autoregressive neural network. This neural network has been trained and validated with a dataset consisting of six years indoor air-temperature values of a building demonstrator. In detail, we have studied three characterizing rooms and the whole building. Experimental results of energy prediction are presented and discussed.

Three dimensional face analysis is being widely investigated since it appears as a robust solution to overcome the limits of two dimensional technologies. 3D methods allow to relate the recognition process on features not depending on lightning, head poses, make up and occlusions. This paper proposes a new approach to the problem consisting of a novel image representation, where specific facial descriptors replace the RGB traditional channels and a convolutional neural network performs the classification. We chose to use MobileNetV2, a relatively new network, as it has a low amount of parameters to train. The method has been evaluated on the Bosphorus database, and even though it is still a preliminary study, the results obtained with our method are extremely encouraging; the recognition rate achieved is 97.560% and it is comparable to the state of the art. This result, reached despite the fact that the Bosphorus database has a great number of subjects (105) but a low number of scans (4666), shows the effectiveness of this representation combined with convolutional neural networks.

Automated ECG analysis and classification are nowadays a fundamental tool for monitoring patient heart activity properly. The most important features used in literature are the raw data of a time window, the temporal attributes and the frequency information from the eigenvector techniques. This paper compares these approaches from a topological point of view, by using linear and nonlinear projections and a neural network for assessing the corresponding classification quality. The nonlinearity of the feature data manifold carries most of the QRS-complex information. Indeed, it yields high rates of classification with the smallest number of features. This is most evident if temporal features are used: Nonlinear dimensionality reduction techniques allow a very large data compression at the expense of a slight loss of accuracy. It can be an advantage in applications where the computing time is a critical factor. If, instead, the classification is performed offline, the raw data technique is the best one.

The analysis of complex systems, such as cancer resistance to drugs, requires flexible algorithms but also simple models, as they will be used by biologists in order to get insights on the underlying phenomenon. Exploiting the availability of the largest collection of patient-derived xenografts from metastatic colorectal cancer annotated for response to therapies, this manuscript aims to (i) forecast the response to treatments on human tissues using murine information; (ii) providing a trade-off between model accuracy and interpretability, evolving a shallow neural network using a genetic algorithm.

Fault diagnostics for electrical machines is a very difficult task because of the non-stationarity of the input information. Also, it is mandatory to recognize the pre-fault condition in order not to damage the machine. Only techniques like the principal component analysis (PCA) and its neural variants are used at this purpose, because of their simplicity and speed. However, they are limited by the fact they are linear. The GCCA neural network addresses this problem; it is nonlinear, incremental, and performs simultaneously the data quantization and projection by using the curvilinear component analysis (CCA), a distance-preserving reduction technique. Using bridges and seeds, it is able to fast adapt and track changes in the data distribution. Analyzing bridge length and density, it is able to detect a pre-fault condition. This paper presents an application of GCCA to a real induction machine on which a time-evolving stator fault in one phase is simulated.

Hierarchical clustering is an important tool for extracting information from data in a multi-resolution way. It is more meaningful if driven by data, as in the case of divisive algorithms, which split data until no more division is allowed. However, they have the drawback of the splitting threshold setting. The neural networks can address this problem, because they basically depend on data. The growing hierarchical GH-EXIN neural network builds a hierarchical tree in an incremental (data-driven architecture) and self-organized way. It is a top-down technique which defines the horizontal growth by means of an anisotropic region of influence, based on the novel idea of neighborhood convex hull. It also reallocates data and detects outliers by using a novel approach on all the leaves, simultaneously. Its complexity is estimated and an analysis of its user-dependent parameters is given. The advantages of the proposed approach, with regard to the best existing networks, are shown and analyzed, qualitatively and quantitatively, both in benchmark synthetic problems and in a real application (image recognition from video), in order to test the performance in building hierarchical trees. Furthermore, an important and very promising application of GH-EXIN in two-way hierarchical clustering, for the analysis of gene expression data in the study of the colorectal cancer is described.

This paper presents a subspace-based approach to identify and extract harmonics of interest for the diagnosis of stator and rotor related faults in induction machines. The maj or goal of this paper is firstly to introduce and highlight the effectiveness of prominence measure upon preparing features for classification of faults. Secondly, a new approach is presented here to retrieve harmonics by using prominence measure of the peaks for each case of the fault. Finally, a hierarchical multi-layer perceptron neural network has been used as the classifier and compared with other existing classification algorithms to deduce the best model. The effectiveness of the developed scheme is verified experimentally.

International audience; This paper presents the temperature distribution on a PEMFC stack which can be used for fault diagnosis. The effect of the temperature is considered on the performance of one single fuel cell both theoretically and experimentally. In order to validate the effect of temperature distribution, several tests were carried out with different operating conditions in one single cell. Thus, according to the variation of temperature, different parameters vary linked to the voltage losses and current density, recognized in the FC thermocouples installed in three different regions of stack FC. The results show good recognition for the considered faults in a stack PEMFC on the basis of temperature distribution.

This paper proposes a methodology to assess the discriminative capabilities of geometrical descriptors referring to the public Bosphorus 3D facial database as testing dataset. The investigated descriptors include histogram versions of Shape Index and Curvedness, Euclidean and geodesic distances between facial soft-tissue landmarks. The discriminability of these features is evaluated through the analysis of single block of features and their meanings with different techniques. Multilayer perceptron neural network methodology is adopted to evaluate the relevance of the features, examined in different test combinations. Principle component analysis (PCA) is applied for dimensionality reduction.

Non-stationary topological representation can be addressed in two ways, according to the application: life-long modeling or by forgetting the past. Life-long learning requires neural networks equipped with a tool for judging if a neuron has to be created for tracking the input distribution. It is always implemented as an isotropic criterion (a hypersphere centered at the winner weight vector represents the domain of the neuron). Instead, the G-EXIN neural network, presented here, uses an anisotropic convex polytope, which, models the shape of the neuron neighborhood. This idea allows to consider the boundaries of the Voronoi sets of data and controls the extent of the extrapolation. It also employs a novel kind of edge, called bridge, which carries information on the extent of the distribution time change. Indeed, the analysis of bridges, mainly their density, yields a deeper insight to the kind of non-stationarity. Both artificial and real examples are given of the advantages of this approach with regard to the ESOINN neural network, which is the best existing approach to life-long modeling.

Dealing with time-varying high dimensional data is a big problem for real time pattern recognition. Only linear projections, like principal component analysis, are used in real time while nonlinear techniques need the whole database (offline). Their incremental variants do no work properly. The onCCA neural network addresses this problem; it is incremental and performs simultaneously the data quantization and projection by using the Curvilinear Component Analysis (CCA), a distance-preserving reduction technique. However, onCCA requires an initial architecture, provided by a small offline CCA. This paper presents a variant of onCCA, called growing CCA (GCCA), which has a self-organized incremental architecture adapting to the nonstationary data distribution. This is achieved by introducing the ideas of “seeds”, pairs of neurons which colonize the input domain, and “bridge”, a different kind of edge in the manifold graph, which signal the data nonstationarity. Some examples from artificial problems and a real application are given.

Fault detection of shorted turns in the stator windings of Induction Motors (IMs) is possible in a variety of ways. As current sensors are usually installed together with the IMs for control and protection purposes, using stator current for fault detection has become a common practice nowadays, as it is much cheaper than installing additional sensors. In this study, stator currents from the healthy and faulty IMs are obtained and analysed via MATLAB® software. The current signatures from healthy and faulty IMs are conditioned using the inbuilt DSP module of the dSPACE prior to analysis using AI techniques. This paper presents a Growing Curvilinear Component Analysis (GCCA) neural network which is able to correctly identify anomalies in the IM and follow the evolution of the stator fault using its current signature, making on-line early fault detection possible.

In this paper the Parameters of a Double Layer Super Capacitor (DLC) Bank are experimentally identified online using Recursive Least Squares (RLS). In order to extract the signals suitable for the RLS a proper signal processing system has been implemented. Results have been verified with those obtained with an off-line common technique applied to the 2-branch model of the DLC.

This contribution wants to show some recent applications of neural networks in the field of power electronics, with particular emphasis on the sensorless control of AC drives and examines improvements that can be attained when using linear neural networks. At first it presents some theoretical aspects of linear neural networks, particularly the TLS EXIN neuron. Then it describes some original applications in electrical drives and power quality as follows: 1) least square and neural identification of electrical machines 2) neural sensorless control of AC drives 3)neural enhanced single-phase DG system with APF capability Simulation and experimental results are provided to validate the theories.

This paper presents a neural network (NN) based wind estimator and related Maximum Power Point Tracking (MPPT) technique for high performance wind generator with induction machine. The target is to develop an MPPT system, embedding an adaptive virtual anemometer which is able to correctly estimate the wind speed even in presence of variations of the wind turbine characteristic, caused by aging or even damages. This paper proposes the use of the adaptive properties of feed-forward neural networks to address the on-line estimation of the wind speed even in case of slowly time-varying wind-turbine parameters. The method is inspired to the inverse adaptive control but it is used for parameter estimation and not for control purposes. Once the wind speed is estimated, the machine reference speed is then computed by the optimal tip speed ratio. For the experimental application, a suitably developed test setup has been used, with a back-to-back configuration with two voltage source converters, one on the machine side and the other on the grid side.

This paper presents a fast and computationally efficient algorithm based on the combination of both zoom-MUSIC and zoom-FFT methods for gear tooth localized fault detection in induction machine-based systems. This method relies mainly on the zoom-MUSIC technique for rotor speed estimation at a primary stage and the application of the zoom-FFT to notch filtered instantaneous frequencies of the stator current space vector for the computation of a fault index. It computes the energy of fault-related frequencies in a predefined bandwidth. It will be demonstrated that the fault can be well detected by using only 100 data samples associated with one second data collection of three stator currents. A test-rig based on a 250W three-phase squirrel-cage induction machine shaft-connected to a single-stage helical gearbox has been used for experimental verifications.

This paper proposes a sensorless technique for an induction machine Flywheel Energy Storage System (FESS) based on a non-linear observer integrated with a total least-squares speed estimator taking into consideration the IM (Induction Machine) saturation effects. The nonlinear observer is based on an original formulation of the dynamic model of the IM including the magnetic saturation, rearranged in a space-state form, after assuming as state variables the stator current and the rotor magnetizing current space-vectors in the stator reference frame. The choice of the observer gain has been made by the use of Lyapunov's method. The speed signal needed by the non-linear observer for the flux estimation is provided by the Total Least Square (TLS) based speed estimator, which itself takes into consideration the magnetic saturation for the speed estimation. The proposed nonlinear observer has been tested in numerical simulation and verified experimentally on a suitably developed test set-up, demonstrating its applicability as far as FESS is concerned.

This paper proposes a technological solution with a scroll compressor driven by a high performance induction machine drive for the air management of PEMFC (proton exchange membrane fuel cells) for automotive applications. The torque-speed characteristics of a real scroll compressor have been measured and then emulated by a brushless IMPM (internal mounted permanent magnets) machine controlled in torque. This emulated scroll compressor has been driven by a field oriented controlled (FOC) induction motor drive. The whole car model as well as the PEMFC have been implemented by software on the same DSP which implements the drive control algorithm; in this way the hardware-in-the-loop structure has been employed for emulating the behaviour of a real car including the electrical supply of the PEMFC. The whole system has been tested with a classic European driving cycle. Two experimental rigs have been setup, one for characterizing the scroll compressor and the other for emulating the entire vehicle. The experimental results have shown that the speed reference profile, obtained during a urban driving cycle, is followed correctly and that the tank-to-wheel efficiency remains at quite high values confirming the goodness of the proposed technological solution. The hardware-in-the-loop approach of the experimental rig allows tests to be performed to verify the operation in steady and transient states with low cost and reduced employment of the Fuel Cell stack, with resulting increased durability.

This paper presents for the first time the analytical solution of the constrained minimization for the on‐line estimation of the electrical parameters of an induction motor. The method is fully described mathematically and its goodness is verified experimentally on a suitably set up test bench. This methodology permits the almost correct computation of all the so called K‐parameters, which is not always the case in current literature, thus resulting in the correct estimation of the electrical parameters.

The neural solids are novel neural networks devised for solving optimization problems. They are dual to Hopfield networks, but with a quartic energy function. These solids are open architectures, in the sense that different choices of the basic elements and interfacings solve different optimization problems. The basic element is the neural resonator (triangle for the three dimensional case), composed of resonant neurons underlying a self-organizing learning. This module is able to solve elementary optimization problems such as the search for the nearest orthonormal matrix to a given one. Then, an example of a more complex solid, the neural decomposer, whose architecture is composed of neural resonators and their mutual connections, is given. This solid can solve more complex optimization problems such as the decomposition of the essential matrix, which is a very important technique in computer vision.

The paper presents a neural approach for the parameter estimation of adaptive IIR filters for linear system identification. It is based on a novel neuron, the TLS EXIN neuron, capable of resolving the TLS problem present in this kind of estimation, where noisy errors affect not only the observation vector but also the data matrix. After a survey of other techniques for solving such parameters estimations, the TLS EXIN neuron is compared both theoretically and numerically with the former techniques, resulting in improved performance. Moreover, it is also proved that the TLS EXIN neuron permits some powerful acceleration techniques, unlike the other approaches. These results are also shown numerically.

Condition monitoring schemes, able to deal with different sources of fault are, nowadays, required by the industrial sector to improve their manufacturing control systems. Pattern recognition approaches, allow the identification of multiple system's scenarios by means the relations between numerical features. The numerical features are calculated from acquired physical magnitudes, in order to characterize its behavior. However, only a reduced set of numerical features are used in order to avoid computational performance limitations of the artificial intelligence techniques. In this sense, feature reduction techniques are applied. Classical approaches analyze the features significance from a global data discrimination point of view. This paper, however, proposes a novel and reliable methodology to exploit the information contained in the original features set, by means a dedicated hierarchy of neural networks.

This paper deals with a simple, computationally not demanding, low cost scalar sensorless control of induction motor drives. The speed estimation has been performed on the basis of a PLL (Phase Locked Loop) algorithm, whose centre bandwith is tuned on-line on the basis of the reference values of the supply and slip frequencies provided to the PWM. This results in the PLL to track properly the machine speed in a very wide speed range. The proposed approach has been tested experimentally on a test set-up. Results show a good behaviour of the scalar sensorless drive in a very wide speed range from rated speed down to as much as 6% of the rated speed.

A neural network based diagnosis system is presented for fully controlled converters. The system. by monitoring the current harmonics. is able to recognise the fault conditions and represents them in a 2D and 3D space. After describing the VQP algorithm a case study regarding three-phase converters is presented. By use of the VQP algorithm two different representations of normal and fault conditions have been obtained. The benefits of such approach are then discussed.

Detection and identification of induction machine faults through the stator current signal using higher order spectra analysis is presented. This paper proposes two higher order spectra techniques, namely the power spectrum and the slices of bi-spectrum used for the analysis of induction machine stator current leading to the detection of electrical failures within the rotor. Experimental signals have been analyzed highlighting that bi-spectrum results show their superiority in the accurate detection of rotor broken bars. Even when the induction machine is rotating at a low level of shaft load, the rotor fault detection is efficient.

This chapter contains sections titled: Introduction Generalized Total Least Squares (GeTLS EXIN) Approach GeTLS Stability Analysis Neural Nongeneric Unidimensional TLS Scheduling Accelerated MCA EXIN Neuron (MCA EXIN+) Further Considerations Simulations for the GeTLS EXIN Neuron ]]>

This chapter contains sections titled: GeMCA Approach Analysis of Matrix K Analysis of the Derivative of the Eigensystem of GeTLS EXIN Rank One Analysis Around the TLS Solution GeMCA spectra Qualitative Analysis of the Critical Points of the GeMCA EXIN Error Function Conclusions