Search

In the present magnetically confined plasmas, the prediction of particle loading on material surfaces is a primary concern in view of the protection of plasma facing components for next step devices. Thus, an understanding of filament dynamics is needed. In this context, this work aims to develop an automatic detector for filaments arising in the MAST-U plasma. The identification of the filaments has been done starting from 2D images acquired with a fast visible camera. Therefore, it can be faced as an image object recognition problem. Currently, the object recognition is a key output of deep learning and machine learning algorithms. In this paper, a database of several thousands of images generated by a synthetic diagnostic, which reproduces the statistical properties of experimental filaments in terms of position, size and intensity has been used. The synthetic images are pre-processed by mapping them onto the toroidal midplane of the machine. Then a Faster R-CNN is customized to the problem of identifying the filaments. In particular, in order to enhance the performance of the detector, a suitable definition of the target-boxes defining the filament positions and sizes is adopted with good results.

In this paper, a disruption prediction system for ASDEX Upgrade has been proposed that does not require disruption terminated experiments to be implemented. The system consists of a data-based model, which is built using only few input signals coming from successfully terminated pulses. A fault detection and isolation approach has been used, where the prediction is based on the analysis of the residuals of an auto regressive exogenous input model. The prediction performance of the proposed system is encouraging when it is applied to the same set of campaigns used to implement the model. However, the false alarms significantly increase when we tested the system on discharges coming from experimental campaigns temporally far from those used to train the model. This is due to the well know aging effect inherent in the data-based models. The main advantage of the proposed method, with respect to other data-based approaches in literature, is that it does not need data on experiments terminated with a disruption, as it uses a normal operating conditions model. This is a big advantage in the prospective of a prediction system for ITER, where a limited number of disruptions can be allowed.

The Self-Organizing Map is a computational method for the visualization and analysis of high-dimensional data. Self Organizing Maps have been applied to ASDEX Upgrade data to define an ordered mapping of an 8-dimensional plasma parameter space onto aregular, 2-dimensional grid. The map has been used to trackthe plasma trajectory during theexperiments andmonitorthedisruptionrisk. Inordertofacewithevernewoperationalconditions, aperiodicalupdatingoftheSelfOrganizing Map is proposed.

The mapping of the n-dimensional plasma parameter space of ASDEX Upgrade (AUG) has been performed using a 2-D self-organizing map (SOM), which reveals the map potentiality in data visualization. The proposed approach allows us the definition of simple displays capable of presenting meaningful information on the actual state of the plasma, but it also suggests to use the SOM as a disruption predictor. In this paper, various criteria have been studied to associate the risk of disruption of each cluster in the map to a disruption alarm threshold. The data for this study come from AUG experiments executed between July 2002 and November 2009. The prediction performance of the proposed system has been evaluated on a set of discharges different from those used for the map training, obtaining a good prediction success rate. A visual analysis of the predictor input signals has been performed for wrong predictions in order to identify possible common causes, and some criteria to increase prediction performance have been derived.

This paper concerns the problem of minimizing the maximum link utilization of IP telecommunication networks under the joint use of traditional IGP routing protocols, such as IS-IS and OSPF, and the more sophisticated MPLS-TE technology. It is shown that the problem of choosing the optimal routing, both under working conditions and under single link failure scenarios, can be cast as a linear program of reasonable size. The proposed model is validated by a computational experimentation performed on synthetic and real networks: the obtained results show that the new approach considerably reduces the maximum link utilization of the network with respect to simply optimizing the IGP weights, at the cost of adding a limited number of label switched paths (LSPs). Optimizing the set of IGP weights within the overall approach further improves performances. The computational time needed to solve the models matches well with real-time requirements, and makes it possible to consider network design problems.

In this paper, an adaptive neural system has been built to predict the risk of disruption at ASDEX Upgrade. The system contains a Self Organizing Map, which determines the ‘novelty’ of the input of a Multi Layer Perceptron predictor module. The answer of the MLP predictor will be inhibited whenever a novel sample is detected. Furthermore, it is possible that the predictor produces a wrong answer although it is fed with known samples. In this case, a retraining procedure will be performed to update the MLP predictor in an incremental fashion using data coming from both the novelty detection, and from wrong predictions. In particular, a new update is performed whenever a missed alarm is triggered by the predictor. The performance of the adaptive predictor during the more recent experimental campaigns until November 2009 has been evaluated.

Knowledge discovery consists of finding new knowledge from databases where dimension, complexity, or amount of data is prohibitively large for human observation alone. The need for efficient data visualization and clustering is often faced, for instance, in the analysis, monitoring, fault detection, or prediction of various engineering plants. In this paper, two clustering techniques, K-means and Self-Organizing Maps, are used for the identification of characteristic regions for plasma scenario in nuclear fusion experimental devices. The choice of the number of clusters, which heavily affects the performance of the mapping, is firstly faced. Then, the ASDEX Upgrade Tokamak high-dimensional operational space is mapped into lower-dimensional maps, allowing to detect the regions with high risk of disruption, and, finally, the current process state and its history in time are visualized as a trajectory on the Self-Organizing Map, in order to predict the safe or disruptive state of the plasma.

The present understanding of disruption physics has not gone so far as to provide a mathematical model describing the onset of this instability. A disruption prediction system, based on a statistical analysis of the diagnostic signals recorded during the experiments, would allow estimating the probability of a disruption to take place. A crucial point for a good design of such a prediction system is the appropriateness of the data set. This paper reports the details of the database built to train a disruption predictor based on neural networks for ASDEX Upgrade. The criteria of pulses selection, the analyses performed on plasma parameters and the implemented pre-processing algorithms, are described. As an example of application, a short description of the disruption predictor is reported.

The electro-dynamical analysis of the ITER blanket modules when subject to disruption loads has been performed. Several configurations have been analyzed, considering both the blanket module electrically insulated (this case is considered as a reference) and all toroidal rows of blanket modules (except those corresponding to the upper and equatorial ports levels) electrically connected for vertical stability improvement purposes. In particular the solution with a single strap placed in the equatorial plane of each blanket and the solution with two straps symmetric with respect to this plane have been analyzed. Moreover the influence of the radial position of the straps has been evaluated.

The design of Non-Destructive-Testing systems for fault detection in long and not accessible pipelines is an actual task in the industrial and civil environment. At this purpose, the diagnosis based on the propagation of guided ultrasonic waves along the pipes offers an attractive solution for the fault identification and classification. The authors studied this problem by means of suitable Artificial Neural Network models. Numerical techniques have been used to simulate the guided wave propagation in the pipes. In particular, the finite element method has been used to model different kinds of pipes and faults, and to obtain several returning echoes containing the faults information. Torsional wave modes have been used as excitation waves. The obtained signals have been processed in order to reduce the data dimensionality, and to extract suitable features. The features selected from the signals can be further processed in order to limit the size of the Neural Network models without loss of information. At this purpose, the principal component analysis has been investigated. Finally, the selected features have been used as input for the neural network models. In this paper, traditional feed-forward, multi-layer perceptron networks have been used to obtain the information on size and location of localized notches.

The evaluation of surface water resources is a necessary input to solving water management problems. Neural network models have been trained to predict monthly runoff for the Tirso basin, located in Sardinia (Italy) at the S. Chiara section. Monthly time series data were available for 69 years and are characterized by non-stationarity and seasonal irregularity, which is typical of a Mediterranean weather regime. This paper investigates the effects of data preprocessing on model performance using continuous and discrete wavelet transforms and data partitioning. The results showed that networks trained with pre-processed data performed better than networks trained on undecomposed, noisy raw signals. In particular, the best results were obtained using the data partitioning technique.

In this work, a neural-based approach for inverse problems in the field of electromagnetic devices design is presented. A multilayer perceptron neural network is first trained to solve the analysis problem of the studied system. As a design problem can be formulated as an inverse problem, i.e., starting from the design requirements the optimal values of the design parameters have to be obtained, the input of the neural network will correspond to the design parameters while the output is the objective function of the optimization problem. In this work, a procedure is presented which performs the inversion of the trained neural network when the design requirements are assigned to the output.

A fault diagnosis procedure for analog linear circuits is presented. It uses an off-line trained neural network as a classifier. The innovative aspect of the proposed approach is the way the information provided by testability and ambiguity group determination is exploited when choosing the neural network architecture. The effectiveness of the proposed approach is shown by comparing with similar work that has already appeared in the literature.

River flow forecasts are required to provide basic information for reservoir management in a multipurpose water system optimisation framework. An accurate prediction of flow rates in tributary streams is crucial to optimise the management of water resources considering extended time horizons. Moreover, runoff prediction is crucial in protection from water shortage and possible flood damages. In this paper, a neural approach is used to model the rainfall-runoff process when different time step durations have to be considered in reservoir management. Numerical comparisons with observed data are provided for runoff prediction in the Tirso basin at the S.Chiara section in Sardinia (Italy).

An original approach to the optimization of electromagnetic structures is presented that makes use of a neural network trained to capture the functional relationship between the design parameters and the objective function. The algebraic structure of the network is used to find the basins of attraction of the objective function of the optimization problem, avoiding the major drawbacks of the commonly used algorithms, i.e., the entrapment in local minima, and/or the huge amount of cost function evaluations.

A global optimization procedure based on Tabu Search metaheuristic is applied to solve electromagnetic inverse problems. In particular, some benchmark problems have been considered consisting of designing systems of Loney's solenoids. The results obtained implementing different Tabu Search strategies are compared to those presented in the literature. The comparison shows that the optimality of the solutions can be noticeably improved without increasing the computational effort. Moreover, the importance of using hybrid heuristics has been highlighted in the case of difficult problems.

This paper presents a tabu search based strategy which is applied to optimize the objective function associated with the design of a solenoid system. The strategies used to apply tabu search in a continuous domain are developed without increasing computational effort with respect to the corresponding discrete problem. Algorithms developed for discrete problems used to self-tune tabu search parameters have also been applied, achieving improvements in terms of the quality of the solutions.

This paper presents a Tabu Search based strategy which has been applied to optimize the objective function associated to the design of a solenoids system. For this kind of problem, Tabu Search strategies are able to find the global minimum with considerably better performance than that obtained using a Simulated Annealing algorithm. Algorithms used to perform the self-tuning of Tabu Search parameters have also been developed, achieving interesting improvements in terms of computing time and quality of the solutions. Such algorithms are an original development of Reactive Tabu Search and they are based on the past history of the search. Tabu Search strategies have also been applied in continuous optimization of the same problem with encouraging results.

A greedy genetic algorithm for continuous variables electromagnetic optimization problems is presented. The presented algorithm is characterized by the use of a nonlinear simplex method as a principal optimizer, and of a greedy genetic algorithm to explore the search space, realizing a balance between diversity and a bias toward fitter individuals. The resulting algorithm merges the efficiency typical of calculus-based search with the robustness typical of random methods. A detailed comparison of the performance obtained implementing several strategies is presented, using an electromagnetic design test problem.

Oddand even-mode capacitances are computed by a variational method. Trial functions for the charge density distributions are supplied by conformal mapping calculations. Comparison is made with values derived from different methods, and resulting accuracies are discussed.

A variational procedure is proposed to accurately analyze the electrical quasi-TEM parameters of coplanar waveguides, taking into account finite-extent as well as semiinfinite lateral ground planes. The procedure leads to accurate calculations and allows comparison with results already presented for coplanar waveguides. Data for geometries incompletely analyzed in the technical literature are provided.

We describe ACDS, an automatic diagnostic system. ACDS is capable of diagnosing faults on analog circuits in dynamic conditions. The circuit's dynamic behavior is studied by means of a series of intrastate simulations during which the qualitative state of the circuit does not change. An acquistion board collects the value of a set of quantities corresponding to accessible test points. These measurements are converted into qualitative values and are used for two purposes: first, to determine the state of the circuit components; second, to trigger the diagnostic procedure whenever a discrepancy between observed and predicted behavior is found. The main difficulty in this phase of measurement interpretation is in obtaining meaningful numerical-qualitative data conversion for values of quantities approaching a boundary between two different qualitative intervals. System performance has been verified through a number of simulations, which have shown the proposed approach to be efficient both in terms of localized faults and of flexibility in adapting to different circuits.

Accurate solutions for impedances and charge distributions in slab lines and rectangularly shielded lines are obtained by numerical inversion of the Schwarz-Christoffel conformal transformation. Circular inner conductors are considered, putting to the test the relatively simple numerical methods utilized, and results are successfully compared to the best data available from the literature. The method, besides supplying accurate global parameters, such as capacitances and impedances, is also shown to provide good evaluations for local charge densities. Equipotential and field lines can be easily derived, and accurate calculation of local field maps is shown to be possible, even from approximate geometries, when boundary conditions are not completely known. >

Numerical algorithms are utilized to design nontraditional transversal sections of TEM cells, leading to large areas of almost uniform electric field within small dimensions. Numerical inversion of the Schwarz-Christoffel formula and predictor-corrector mapping of equipotential lines are, utilized. © 1994 John Wiley & Sons, Inc.

In this paper, the dynamic characteristics of type-I edge-localized modes (ELM) time series from the JET tokamak, the world’s largest magnetic confinement plasma physics experiment, have been investigated through recurrence plots (RPs). The analysis has been focused on RPs of pedestal temperature, line averaged electron density, and outer divertor $D_{ {\alpha }}$ time series during experiments with a carbon wall. The analysis of RPS shows the patterns similar to those characteristics of signals exhibiting type-2 intermittency, in particular, a characteristic kite-like shape; this gives useful hints to model the temperature signal as well as the $D_{ {\alpha }}$ radiation time series, with simple nonlinear maps capturing the nearly periodic behavior of type-I ELMs.

Convolutional neural networks (CNNs) have found applications in many image processing tasks, such as feature extraction, image classification, and object recognition. It has also been shown that the inverse of CNNs, so- called deconvolutional neural networks, can be used for inverse problems such as plasma tomography. In essence, plasma tomography consists in reconstructing the 2D plasma profile on a poloidal cross-section of a fusion device, based on line-integrated measurements from multiple radiation detectors. Since the reconstruction process is computationally intensive, a deconvolutional neural network trained to produce the same results will yield a significant computational speedup, at the expense of a small error which can be assessed using different metrics. In this work, we discuss the design principles behind such networks, including the use of multiple layers, how they can be stacked, and how their dimensions can be tuned according to the number of detectors and the desired tomographic resolution for a given fusion device. We describe the application of such networks at JET and COMPASS, where at JET we use the bolometer system, and at COMPASS we use the soft X-ray diagnostic based on photodiode arrays.