1,720,987 research outputs found
A Numerical Feed-Forward Scheme for the Augmented Kalman Filter
No full textIn this paper we present a numerical feed-forward strategy for the Augmented Kalman Filter and show its application to a diffusion-dominated inverse problem: heat source reconstruction from boundary measurements. The method is applicable in general to forcing term estimation in lumped and distributed parameters models and gives a significant contribution where, in industry and science, probing signals are used through a diffusive material-body to estimate its localized internal properties in a non-destructive test, like in ultrasound or thermographic inspection
Accurate detection of hidden material changes as fictitious heat sources
No full textIn this article we present a numerical method for the estimation of hidden material changes, interpreted as fictitious source terms. The method adapts the parameters of its reference model in order to cancel the estimated fictitious source terms and thus it indirectly estimates the hidden material changes. The novelty of this method is triple: first, a parsimonious minimization strategy that effectively avoids local minima, by using the maximum principle as a barrier against falling into; second, an error indicator based on estimates of fictitious heat sources, instead of the temperatures-prediction-error, because it is smeared by diffusion; third, the adaptation of model parameters is computed without the problematic matrix inversion which would arise in Newton-based procedures. As a particular example application, we show that, in thermographic experiments for hidden corrosion detection, the gradient of the temperatures-prediction-error, often used in the literature, is quite inefficient, while the fictitious-source-term estimation behaves intrinsically better. Its accuracy and moderate computational demand are highlighted in the numerical tests. Moreover, this approach is applicable to general hidden material change problems
Hit detection in audio mixtures by means of a physics-aware Deep-NMF algorithm
No full textIn this paper we present the Physics-Aware Deep-NMF (PAD-NMF) algorithm and we apply it to hit detection in mechanical systems from audio mixtures. The algorithm accurately extracts the acoustic emission made by the physical source to be monitored, to be properly used in engineering analysis, like e.g. the hit detection here considered. This is mainly a source separation problem where sources have a precise physical meaning, that should be retained by the processing algorithm. For this reason we call this algorithm a Physics-aware soft-sensor. We give a detailed description of the algorithm and show its results on a general application with critical signal-to-noise ratios, where the noise is a mixture of random and deterministic acoustic sources
State Estimation of Partially Unknown Dynamical Systems with a Deep Kalman Filter
No full textIn this paper we present a novel scientific machine learning reinterpretation of the well-known Kalman Filter, we explain its flexibility in dealing with partially-unknown models and show its effectiveness in a couple of situations where the classic Kalman Filter is problematic
State, parameters and hidden dynamics estimation with the Deep Kalman Filter: Regularization strategies
No full textIn this paper we present in detail the various regularization strategies adopted for a novel scientific machine learning extension of the well known Kalman Filter (KF) that we call the Deep Kalman Filter (DKF), briefly presented in the conference paper (Chinellato and Marcuzzi 2024) . It is based on a recent scientific machine learning paradigm, called algorithm unfolding/unrolling, that allows to create a neural network from the algebraic structure dictated by an analytical method of scientific computing. We show the interpretable consistency of DKF with the classic KF when this is optimal, and its improvements against the KF with both linear and nonlinear models in general. Indeed, the DKF learns parameters of a quite general reference model, comprising: corrector gains, predictor model parameters and eventual unmodeled dynamics. This goes well beyond the ability of the KF and its known extensions
Deviation maximization for rank-revealing QR factorizations
Full text linkIn this paper, we introduce a new column selection strategy, named here “Deviation Maximization”, and apply it to compute rank-revealing QR factorizations as an alternative to the well-known block version of the QR factorization with the column pivoting method, called QP3 and currently implemented in LAPACK’s xgeqp3 routine. We show that the resulting algorithm, named QRDM, has similar rank-revealing properties of QP3 and better execution times. We present experimental results on a wide data set of numerically singular matrices, which has become a reference in the recent literature
Stochastic geometry for the analysis of small radio cells and PLC back-hauling
No full textAlthough powerlines have not been designed for data transmission, recent technical developments in Power Line Communication (PLC) have pushed the offered capacity much higher than expected, making PLC an interesting technology for last mile connections like the back-hauling considered in this work. On the other hand, cellular traffic is doubling every year, and this growth trend is not expected to end soon. Small cells have been advocated as a solution to fragment the network and increase the local capacity; in addition, new generation of mobile communication is likely to employ high frequency bands that will cover smaller areas, hence, an increase in cell density is expected. This will increase the challenge for the realization of a cost effective high performance back-haul to bridge the small cell network with the core network. Nowadays, the back-haul portion of the network is either wireless or high speed wireline (ADSL, optical fiber). This paper introduces the idea of employing PLC to support back-hauling for small radio cells. To assess the back-haul requirements and the performance of the integrated radio-PLC network, a topology model is proposed to describe both the small radio cell network layout and the power delivery grid used to both power and”data” connect the base stations. Then, a parametric cell traffic model is considered to measure the overall traffic to be transported through the PLC network and determine whether (under the power grid topology constraints) the PLC back-haul can meet the traffic demands
Artificial-Intelligence-Based Performance Enhancement of the G3-PLC LOADng Routing Protocol for Sensor Networks
No full textPowerline Communications (PLC) is a popular technology providing infrastructure for applications related to IoT, smart grids, smart cities, in-home networking and has been experimentally considered for broadband access. Sensor networks and Automatic Meter Reading applications are closely related to this technology, as it provides free infrastructure and sustains the data rate requirements. The application here considered consists in the implementation of the G3-PLC LOADng routing protocol in the nodes of a sensor/meter network, where the nodes share all the same medium. G3-PLC is a powerline communication standard, employing OFDM at the physical layer and oriented at enabling the smart grid vision. The Medium Access Control implements CSMA/CA, while the Logical Link Control implements LOADng routing, which is the ITU-T G.9903 recommended specification for Lossy and Low-power Networks (LLNs).In this paper, we consider the mapping phase of the routing protocol, in which the central element of the network establishes the routes to reach any node. By simulating this process via a physical simulation tool, it is possible to synthetically train an Artificial Neural Network and teach it how the optimally established routes correlate to the topological and geometrical properties of the network. Eventually, we discuss how, by employing this AI approach, it is possible to speed-up the routing mapping process
- …
