A Fast Unsupervised Online Learning Algorithm to Detect Structural Damage in Time-Varying Environments

2021 ◽  
Author(s):  
Karthik Gopalakrishnan ◽  
V. John Mathews
Keyword(s):  
Online Learning ◽  
Damage Detection ◽  
Structural Damage ◽  
Learning Algorithm ◽  
Operating Conditions ◽  
Training Data ◽  
Support Vector ◽  
Support Vector Data Description ◽  
Time Varying ◽  
Varying Environments

Abstract Machine learning based health monitoring techniques for damage detection have been widely studied. Most such approaches suffer from two main problems, time-varying environmental and operating conditions, and the difficulty in acquiring training data from damaged structures. Recently, our group presented an unsupervised learning algorithm using support vector data description (SVDD) and an autoencoder to detect damage in time-varying environments without training on data from damaged structures. Though the preliminary experiments produced promising results, the algorithm was computationally expensive. This paper presents an iterative algorithm that learns the state of a structure in time-varying environments online in a computationally efficient manner. This algorithm combines the fast, incremental SVDD (FISVDD) algorithm with signal features based on wavelet packet decomposition (WPD) to create a method that is efficient and provides more accurate detection of smaller damage than the autoencoder-based method. The use of FISVDD has created the possibility of online learning and adaptive damage detection in time-varying environmental and operating conditions (EOC). The WPD-based features also have the potential to provide explainability for the learning algorithm.

scholarly journals Structural Damage Detection Using Supervised Nonlinear Support Vector Machine

2021 ◽  
Vol 5 (11) ◽  
pp. 303
Author(s):  
Kian K. Sepahvand
Keyword(s):  
Support Vector Machine ◽  
Damage Detection ◽  
Structural Damage ◽  
Natural Frequencies ◽  
Training Data ◽  
Support Vector ◽  
Lightweight Structures ◽  
Straightforward Method ◽  
Classification Boundary ◽  
Nonlinear Support

Damage detection, using vibrational properties, such as eigenfrequencies, is an efficient and straightforward method for detecting damage in structures, components, and machines. The method, however, is very inefficient when the values of the natural frequencies of damaged and undamaged specimens exhibit slight differences. This is particularly the case with lightweight structures, such as fiber-reinforced composites. The nonlinear support vector machine (SVM) provides enhanced results under such conditions by transforming the original features into a new space or applying a kernel trick. In this work, the natural frequencies of damaged and undamaged components are used for classification, employing the nonlinear SVM. The proposed methodology assumes that the frequencies are identified sequentially from an experimental modal analysis; for the study propose, however, the training data are generated from the FEM simulations for damaged and undamaged samples. It is shown that nonlinear SVM using kernel function yields in a clear classification boundary between damaged and undamaged specimens, even for minor variations in natural frequencies.

Unsupervised deep learning approach using a deep auto-encoder with an one-class support vector machine to detect structural damage

2020 ◽  
pp. 147592172093405
Author(s):  
Zilong Wang ◽  
Young-Jin Cha
Keyword(s):  
Support Vector Machine ◽  
Deep Learning ◽  
Damage Detection ◽  
Structural Damage ◽  
Training Data ◽  
Support Vector ◽  
Acceleration Response ◽  
Damage Scenarios ◽  
Response Data ◽  
Unsupervised Deep Learning

This article proposes an unsupervised deep learning–based approach to detect structural damage. Supervised deep learning methods have been proposed in recent years, but they require data from an intact structure and various damage scenarios of monitored structures for their training processes. However, the labeling work on the training data is typically time-consuming and costly, and sometimes collecting sufficient training data from various damage scenarios of infrastructures in service is impractical. In this article, the proposed unsupervised deep learning method based on a deep auto-encoder with an one-class support vector machine only uses the measured acceleration response data acquired from intact or baseline structures as training data, which enables future structural damage to be detected. The major contributions and novelties of the proposed method are as follows. First, an appropriate deep auto-encoder is carefully designed through comparative studies on the depth of neural networks. Second, the designed deep auto-encoder is taken as an extractor to obtain damage-sensitive features from the measured acceleration response data, and an one-class support vector machine is used as a damage detector. Third, experimental and numerical studies validate the high accuracy of the proposed method for damage detection: a 97.4% mean average for a 12-story numerical building model and a 91.0% accuracy for a laboratory-scaled steel bridge. Fourth, the proposed method also detects light damage (i.e. a 10% reduction in stiffness) with 96.9% to 99.0% accuracy, which shows its superior performance compared with the current state of the art. Fifth, it provides stable and more robust damage detection performance with reduced tuning parameters.

scholarly journals Earthquake Prediction using Machine Learning Algorithm

2020 ◽  
Vol 8 (6) ◽  
pp. 4684-4688
Keyword(s):  
Machine Learning ◽  
Structural Damage ◽  
Data Science ◽  
Learning Algorithm ◽  
Economic Loss ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Support Vector ◽  
Science Data ◽  
Data Set

Per the statistics received from BBC, data varies for every earthquake occurred till date. Approximately, up to thousands are dead, about 50,000 are injured, around 1-3 Million are dislocated, while a significant amount go missing and homeless. Almost 100% structural damage is experienced. It also affects the economic loss, varying from 10 to 16 million dollars. A magnitude corresponding to 5 and above is classified as deadliest. The most life-threatening earthquake occurred till date took place in Indonesia where about 3 million were dead, 1-2 million were injured and the structural damage accounted to 100%. Hence, the consequences of earthquake are devastating and are not limited to loss and damage of living as well as nonliving, but it also causes significant amount of change-from surrounding and lifestyle to economic. Every such parameter desiderates into forecasting earthquake. A couple of minutes’ notice and individuals can act to shield themselves from damage and demise; can decrease harm and monetary misfortunes, and property, characteristic assets can be secured. In current scenario, an accurate forecaster is designed and developed, a system that will forecast the catastrophe. It focuses on detecting early signs of earthquake by using machine learning algorithms. System is entitled to basic steps of developing learning systems along with life cycle of data science. Data-sets for Indian sub-continental along with rest of the World are collected from government sources. Pre-processing of data is followed by construction of stacking model that combines Random Forest and Support Vector Machine Algorithms. Algorithms develop this mathematical model reliant on “training data-set”. Model looks for pattern that leads to catastrophe and adapt to it in its building, so as to settle on choices and forecasts without being expressly customized to play out the task. After forecast, we broadcast the message to government officials and across various platforms. The focus of information to obtain is keenly represented by the 3 factors – Time, Locality and Magnitude.

A Combined Method Based on SVM and Online Learning with HOG for Hand Shape Recognition

2012 ◽  
Vol 16 (6) ◽  
pp. 687-695 ◽  
Author(s):  
Kazutaka Shimada ◽  
◽  
Ryosuke Muto ◽  
Tsutomu Endo
Keyword(s):  
Online Learning ◽  
Learning Algorithm ◽  
Shape Recognition ◽  
Input Image ◽  
Training Data ◽  
Support Vector ◽  
Combined Method ◽  
Hand Shape ◽  
Vector Machines ◽  
Online Learning Algorithm

In this paper, we propose a combined method for hand shape recognition. It consists of Support Vector Machines (SVMs) and an online learning algorithm based on the perceptron. We apply HOG features to each method. First, our method estimates the hand shape of an input image by using SVMs. Here, an online learning method with the perceptron uses an input image as new training data if the image is effective in relearning in the recognition process. Next, we select a final hand shape from the outputs of SVMs and perceptrons by using the score from SVMs. The combined method with the online perceptron is robust against unknown users because it contains a relearning process for the current user. Therefore applying the online perceptron leads to an improvement in accuracy. We compare the combined method with a method that uses only SVMs. Experimental results show the effectiveness of the proposed method.

scholarly journals Applying Deep Learning to Continuous Bridge Deflection Detected by Fiber Optic Gyroscope for Damage Detection

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 911 ◽  
Author(s):  
Sheng Li ◽  
Xiang Zuo ◽  
Zhengying Li ◽  
Honghai Wang
Keyword(s):  
Deep Learning ◽  
Damage Detection ◽  
Structural Damage ◽  
Fiber Optic ◽  
Learning Algorithm ◽  
Support Vector ◽  
Engineering Practice ◽  
Fiber Optic Gyroscope ◽  
Deep Convolutional Neural Networks ◽  
Bridge Model

Improving the accuracy and efficiency of bridge structure damage detection is one of the main challenges in engineering practice. This paper aims to address this issue by monitoring the continuous bridge deflection based on the fiber optic gyroscope and applying the deep-learning algorithm to perform structural damage detection. With a scale-down bridge model, three types of damage scenarios and an intact benchmark were simulated. A supervised learning model based on the deep convolutional neural networks was proposed. After the training process under ten-fold cross-validation, the model accuracy can reach 96.9% and significantly outperform that of other four traditional machine learning methods (random forest, support vector machine, k-nearest neighbor, and decision tree) used for comparison. Further, the proposed model illustrated its decent ability in distinguishing damage from structurally symmetrical locations.

scholarly journals Transfer Learning with Deep Recurrent Neural Networks for Remaining Useful Life Estimation

2018 ◽  
Vol 8 (12) ◽  
pp. 2416 ◽  
Author(s):  
Ansi Zhang ◽  
Honglei Wang ◽  
Shaobo Li ◽  
Yuxin Cui ◽  
Zhonghao Liu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Recurrent Neural Networks ◽  
Prediction Models ◽  
Learning Algorithm ◽  
Remaining Useful Life ◽  
Operating Conditions ◽  
Training Data ◽  
Good Prediction ◽  
Useful Life

Prognostics, such as remaining useful life (RUL) prediction, is a crucial task in condition-based maintenance. A major challenge in data-driven prognostics is the difficulty of obtaining a sufficient number of samples of failure progression. However, for traditional machine learning methods and deep neural networks, enough training data is a prerequisite to train good prediction models. In this work, we proposed a transfer learning algorithm based on Bi-directional Long Short-Term Memory (BLSTM) recurrent neural networks for RUL estimation, in which the models can be first trained on different but related datasets and then fine-tuned by the target dataset. Extensive experimental results show that transfer learning can in general improve the prediction models on the dataset with a small number of samples. There is one exception that when transferring from multi-type operating conditions to single operating conditions, transfer learning led to a worse result.

scholarly journals UAV-BASED STRUCTURAL DAMAGE MAPPING – RESULTS FROM 6 YEARS OF RESEARCH IN TWO EUROPEAN PROJECTS

2019 ◽  
Vol XLII-3/W8 ◽  
pp. 187-194 ◽  
Author(s):  
N. Kerle ◽  
F. Nex ◽  
D. Duarte ◽  
A. Vetrivel
Keyword(s):  
Damage Detection ◽  
Structural Damage ◽  
Point Cloud ◽  
Feature Fusion ◽  
Texture Features ◽  
Mobile App ◽  
Detection Methods ◽  
Support Vector ◽  
3D Point Cloud ◽  
Damage Mapping

<p><strong>Abstract.</strong> Structural disaster damage detection and characterisation is one of the oldest remote sensing challenges, and the utility of virtually every type of active and passive sensor deployed on various air- and spaceborne platforms has been assessed. The proliferation and growing sophistication of UAV in recent years has opened up many new opportunities for damage mapping, due to the high spatial resolution, the resulting stereo images and derivatives, and the flexibility of the platform. We have addressed the problem in the context of two European research projects, RECONASS and INACHUS. In this paper we synthesize and evaluate the progress of 6 years of research focused on advanced image analysis that was driven by progress in computer vision, photogrammetry and machine learning, but also by constraints imposed by the needs of first responder and other civil protection end users. The projects focused on damage to individual buildings caused by seismic activity but also explosions, and our work centred on the processing of 3D point cloud information acquired from stereo imagery. Initially focusing on the development of both supervised and unsupervised damage detection methods built on advanced texture features and basic classifiers such as Support Vector Machine and Random Forest, the work moved on to the use of deep learning. In particular the coupling of image-derived features and 3D point cloud information in a Convolutional Neural Network (CNN) proved successful in detecting also subtle damage features. In addition to the detection of standard rubble and debris, CNN-based methods were developed to detect typical façade damage indicators, such as cracks and spalling, including with a focus on multi-temporal and multi-scale feature fusion. We further developed a processing pipeline and mobile app to facilitate near-real time damage mapping. The solutions were tested in a number of pilot experiments and evaluated by a variety of stakeholders.</p>

Adapting SVM for data sparseness and imbalance: a case study in information extraction

2009 ◽  
Vol 15 (2) ◽  
pp. 241-271 ◽  
Author(s):  
YAOYONG LI ◽  
KALINA BONTCHEVA ◽  
HAMISH CUNNINGHAM
Keyword(s):  
Active Learning ◽  
Language Learning ◽  
Information Extraction ◽  
Language Processing ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Support Vector ◽  
Passive Learning ◽  
Wide Range

AbstractSupport Vector Machines (SVM) have been used successfully in many Natural Language Processing (NLP) tasks. The novel contribution of this paper is in investigating two techniques for making SVM more suitable for language learning tasks. Firstly, we propose an SVM with uneven margins (SVMUM) model to deal with the problem of imbalanced training data. Secondly, SVM active learning is employed in order to alleviate the difficulty in obtaining labelled training data. The algorithms are presented and evaluated on several Information Extraction (IE) tasks, where they achieved better performance than the standard SVM and the SVM with passive learning, respectively. Moreover, by combining SVMUM with the active learning algorithm, we achieve the best reported results on the seminars and jobs corpora, which are benchmark data sets used for evaluation and comparison of machine learning algorithms for IE. In addition, we also evaluate the token based classification framework for IE with three different entity tagging schemes. In comparison to previous methods dealing with the same problems, our methods are both effective and efficient, which are valuable features for real-world applications. Due to the similarity in the formulation of the learning problem for IE and for other NLP tasks, the two techniques are likely to be beneficial in a wide range of applications1.

Sign in / Sign up

Export Citation Format

Share Document