Efficient Global Sensitivity Analysis of Model-Based Ultrasonic Nondestructive Testing Systems using Machine Learning and Sobol' Indices (Invited)

2021 ◽  
pp. 1-12
Author(s):  
Jethro Nagawkar ◽  
Leifur Leifsson
Keyword(s):  
Machine Learning ◽  
Sensitivity Analysis ◽  
Nondestructive Testing ◽  
Mean Squared Error ◽  
Spherical Inclusion ◽  
Fixed Number ◽  
Ultrasonic Nondestructive Testing ◽  
Sobol Indices ◽  
Void Defect ◽  
Model Based

Abstract The objective of this work is to reduce the cost of performing model-based sensitivity analysis for ultrasonic nondestructive testing systems by replacing the accurate physics-based model with machine learning (ML) algorithms and quickly compute Sobol' indices. The ML algorithms considered in this work are neural networks (NN), convolutional NN (CNN), and deep Gaussian processes (DGP). The performance of these algorithms is measured by the root mean squared error on a fixed number of testing points and by the number of high-fidelity samples required to reach a target accuracy. The algorithms are compared on three ultrasonic testing benchmark cases with three uncertainty parameters, namely, spherically-void defect under a focused and a planar transducer and spherical-inclusion defect under a focused transducer. The results show that NN required 35, 100, and 35 samples for the three cases, respectively. CNN required 35, 100, and 56, respectively, while DGP required 84, 84, and 56, respectively.

scholarly journals Combined Multilateration with Machine Learning for Enhanced Aircraft Localization

Proceedings ◽  
2020 ◽  
Vol 59 (1) ◽  
pp. 2
Author(s):  
Benoit Figuet ◽  
Raphael Monstein ◽  
Michael Felux
Keyword(s):  
Machine Learning ◽  
Sensitivity Analysis ◽  
Real World ◽  
Mean Squared Error ◽  
Accurate Estimate ◽  
Regression Technique ◽  
Gradient Boosting ◽  
Root Mean Squared Error ◽  
Squared Error ◽  
Using Data

In this paper, we present an aircraft localization solution developed in the context of the Aircraft Localization Competition and applied to the OpenSky Network real-world ADS-B data. The developed solution is based on a combination of machine learning and multilateration using data provided by time synchronized ground receivers. A gradient boosting regression technique is used to obtain an estimate of the geometric altitude of the aircraft, as well as a first guess of the 2D aircraft position. Then, a triplet-wise and an all-in-view multilateration technique are implemented to obtain an accurate estimate of the aircraft latitude and longitude. A sensitivity analysis of the accuracy as a function of the number of receivers is conducted and used to optimize the proposed solution. The obtained predictions have an accuracy below 25 m for the 2D root mean squared error and below 35 m for the geometric altitude.

scholarly journals Visualization of internal defects using a deep generative neural network model and ultrasonic nondestructive testing

2021 ◽  
Vol 21 (2) ◽  
pp. 143-153
Author(s):  
Р. V. Vasiliev ◽  
А. V. Senichev ◽  
I. Giorgio
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Inverse Problems ◽  
Nondestructive Testing ◽  
Convolutional Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Ultrasonic Nondestructive Testing ◽  
Internal Defect ◽  
Machine Learning Methods

Introduction. The development of machine learning methods has given a new impulse to solving inverse problems in mechanics. Many studies show that along with well-behaved techniques of ultrasonic, magnetic, and thermal nondestructive testing, the latest methods are used, including those based on neural network models. In this paper, we demonstrate the potential application of machine learning methods in the problem of two-dimensional ultrasound imaging. Materials and Methods. We have developed an experimental model of acoustic ultrasonic non-destructive testing, in which the probing of the object under study takes place, followed by the recording of the response signals. The propagation of an ultrasonic wave is modeled by the finite difference method in the time domain. An ultrasonic signal received at the internal points of the control object is applied to the input of the convolutional neural network. At the output, an image that visualizes the internal defect is generated.Results. In the course of the performed complex of numerical experiments, a data set was generated for training a convolutional neural network. A convolutional neural network model, which is developed to solve the problem of visualizing internal defects based on methods of ultrasonic nondestructive testing, is presented. This model has a small size, which is 3.8 million parameters. Its simplicity and versatility provide high-speed learning and a wide range of applications in the class of related problems. The presented results show a high degree of information content of the ultrasonic response and its correspondence to the real form of an internal defect located inside the test object. The effect of geometric parameters of defects on the accuracy of the neural network model is investigated.Discussion and Conclusion. The results obtained have established that the proposed model shows a high operating accuracy (F1 > 0.95) in cases when the wavelength of the probe pulse is tens of times less than the size of the defect. We believe that the combination of the proposed methods in this approach can serve as a good starting point for future research in solving flaw defection problems and inverse problems in general. 

A Brief Survey on Text Classification Using Various Machine Learning Techniques

2018 ◽  
Vol 8 (1) ◽  
pp. 14
Author(s):  
Padmavathi .S ◽  
M. Chidambaram
Keyword(s):  
Machine Learning ◽  
Text Classification ◽  
Fixed Number ◽  
Machine Learning Techniques ◽  
Online Information ◽  
Rule Based ◽  
Learning Techniques ◽  
Machine Learning Approach ◽  
Rule Based Approach

Text classification has grown into more significant in managing and organizing the text data due to tremendous growth of online information. It does classification of documents in to fixed number of predefined categories. Rule based approach and Machine learning approach are the two ways of text classification. In rule based approach, classification of documents is done based on manually defined rules. In Machine learning based approach, classification rules or classifier are defined automatically using example documents. It has higher recall and quick process. This paper shows an investigation on text classification utilizing different machine learning techniques.

Electromagnetic methods in nondestructive testing of materials

2003 ◽  
Vol 16 (1) ◽  
pp. 1-23
Author(s):  
Konstanty Gawrylczyk
Keyword(s):  
Sensitivity Analysis ◽  
Finite Elements ◽  
Nondestructive Testing ◽  
Eddy Current ◽  
Quality Evaluation ◽  
Leakage Flux ◽  
Electromagnetic Methods ◽  
Conducting Materials ◽  
Inductive Methods ◽  
Flux Probe

The article deals with progress in electromagnetic methods used for quality evaluation of conducting materials. The term "electromagnetic methods" covers the following areas: magneto-inductive methods, magnetic leakage flux probe method, magnetometer principle and eddy-current methods. For the aim of numerical cracks recognition the sensitivity analysis with finite elements was shown.

scholarly journals A Model for the Thermal Behaviour of an Offshore Cable Installed in a J-Tube

Proceedings ◽  
2020 ◽  
Vol 58 (1) ◽  
pp. 31
Author(s):  
Jeremy Arancio ◽  
Ahmed Ould El Moctar ◽  
Minh Nguyen Tuan ◽  
Faradj Tayat ◽  
Jean-Philippe Roques
Keyword(s):  
Sensitivity Analysis ◽  
Numerical Model ◽  
Thermal Behaviour ◽  
Energy Production ◽  
Power Transmission ◽  
Temperature Fields ◽  
Sobol Indices ◽  
Lumped Element ◽  
Thermal Phenomena ◽  
The Impact

In the race for energy production, supplier companies are concerned by the thermal rating of offshore cables installed in a J-tube, not covered by IEC 60287 standards, and are now looking for solutions to optimize this type of system. This paper presents a numerical model capable of calculating temperature fields of a power transmission cable installed in a J-tube, based on the lumped element method. This model is validated against the existing literature. A sensitivity analysis performed using Sobol indices is then presented in order to understand the impact of the different parameters involved in the heating of the cable. This analysis provides an understanding of the thermal phenomena in the J-tube and paves the way for potential technical and economic solutions to increase the ampacity of offshore cables installed in a J-tube.

scholarly journals Field-Scale Soil Moisture Retrieval Using PALSAR-2 Polarimetric Decomposition and Machine Learning

Agronomy ◽  
2020 ◽  
Vol 11 (1) ◽  
pp. 35
Author(s):  
Xiaodong Huang ◽  
Beth Ziniti ◽  
Michael H. Cosh ◽  
Michele Reba ◽  
Jinfei Wang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Soil Moisture ◽  
Canopy Cover ◽  
The United States ◽  
Optical Data ◽  
Study Region ◽  
Model Based ◽  
Key Indicator ◽  
Ground Measurement ◽  
L Band

Soil moisture is a key indicator to assess cropland drought and irrigation status as well as forecast production. Compared with the optical data which are obscured by the crop canopy cover, the Synthetic Aperture Radar (SAR) is an efficient tool to detect the surface soil moisture under the vegetation cover due to its strong penetration capability. This paper studies the soil moisture retrieval using the L-band polarimetric Phased Array-type L-band SAR 2 (PALSAR-2) data acquired over the study region in Arkansas in the United States. Both two-component model-based decomposition (SAR data alone) and machine learning (SAR + optical indices) methods are tested and compared in this paper. Validation using independent ground measurement shows that the both methods achieved a Root Mean Square Error (RMSE) of less than 10 (vol.%), while the machine learning methods outperform the model-based decomposition, achieving an RMSE of 7.70 (vol.%) and R2 of 0.60.

scholarly journals MODES: model-based optimization on distributed embedded systems

2021 ◽  
Author(s):  
Junjie Shi ◽  
Jiang Bian ◽  
Jakob Richter ◽  
Kuan-Hsun Chen ◽  
Jörg Rahnenführer ◽  
...  
Keyword(s):  
Machine Learning ◽  
Embedded Systems ◽  
Learning Model ◽  
Black Box ◽  
Distributed Embedded Systems ◽  
Data Set ◽  
Individual Model ◽  
Model Based ◽  
Machine Learning Model ◽  
Distributed Machine Learning

AbstractThe predictive performance of a machine learning model highly depends on the corresponding hyper-parameter setting. Hence, hyper-parameter tuning is often indispensable. Normally such tuning requires the dedicated machine learning model to be trained and evaluated on centralized data to obtain a performance estimate. However, in a distributed machine learning scenario, it is not always possible to collect all the data from all nodes due to privacy concerns or storage limitations. Moreover, if data has to be transferred through low bandwidth connections it reduces the time available for tuning. Model-Based Optimization (MBO) is one state-of-the-art method for tuning hyper-parameters but the application on distributed machine learning models or federated learning lacks research. This work proposes a framework $$\textit{MODES}$$ MODES that allows to deploy MBO on resource-constrained distributed embedded systems. Each node trains an individual model based on its local data. The goal is to optimize the combined prediction accuracy. The presented framework offers two optimization modes: (1) $$\textit{MODES}$$ MODES -B considers the whole ensemble as a single black box and optimizes the hyper-parameters of each individual model jointly, and (2) $$\textit{MODES}$$ MODES -I considers all models as clones of the same black box which allows it to efficiently parallelize the optimization in a distributed setting. We evaluate $$\textit{MODES}$$ MODES by conducting experiments on the optimization for the hyper-parameters of a random forest and a multi-layer perceptron. The experimental results demonstrate that, with an improvement in terms of mean accuracy ($$\textit{MODES}$$ MODES -B), run-time efficiency ($$\textit{MODES}$$ MODES -I), and statistical stability for both modes, $$\textit{MODES}$$ MODES outperforms the baseline, i.e., carry out tuning with MBO on each node individually with its local sub-data set.

Sign in / Sign up

Export Citation Format

Share Document