scispace - formally typeset
Search or ask a question
Book ChapterDOI

Structural Health Monitoring of Cantilever Beam, a Case Study—Using Bayesian Neural Network and Deep Learning

01 Jan 2020-arXiv: Learning (Springer, Singapore)-pp 749-761
TL;DR: A Bayesian-multilayer-perceptron and deep-learning-based approach for damage detection and location identification in beam-like structures is presented, showing the effectiveness of the above approaches to predict bending rigidity with an acceptable error rate.
Abstract: The advancement of machine learning algorithms has opened a wide scope for vibration-based Structural Health Monitoring (SHM). Vibration-based SHM is based on the fact that damage will alter the dynamic properties, viz., structural response, frequencies, mode shapes, etc. of the structure. The responses measured using sensors, which are high dimensional in nature, can be intelligently analysed using machine learning techniques for damage assessment. Neural networks employing multilayer architectures are expressive models capable of capturing complex relationships between input–output pairs, but do not account for uncertainty in network outputs. A Bayesian Neural Network (BNN) refers to extending standard networks with posterior inference. It is a neural network with a prior distribution on its weights. Deep learning architectures like Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) are good candidates for representation learning from high-dimensional data. The advantage of using CNN over multilayer neural networks is that they are good feature extractors as well as classifiers, which eliminates the need for generating hand-engineered features. LSTM networks are mainly used for sequence modelling. This paper presents both a Bayesian-multilayer-perceptron and deep-learning-based approach for damage detection and location identification in beam-like structures. Raw frequency response data simulated using finite element analysis is fed as input of the network. As part of this, frequency response was generated for a series of simulations in the cantilever beam involving different damage scenarios (at different locations and different extents). These frequency responses can be studied without any loss of information, as no manual feature engineering is involved. The results obtained from the models are highly encouraging. This case study shows the effectiveness of the above approaches to predict bending rigidity with an acceptable error rate.
Citations
More filters
Book ChapterDOI
18 Aug 2020
TL;DR: An overview of ML algorithms used for smart monitoring is presented, providing an overview of categories ofML algorithms for smart Monitoring that may be modified to achieve explainable artificial intelligence in civil engineering.
Abstract: Recent developments in artificial intelligence (AI), in particular machine learning (ML), have been significantly advancing smart city applications. Smart infrastructure, which is an essential component of smart cities, is equipped with wireless sensor networks that autonomously collect, analyze, and communicate structural data, referred to as “smart monitoring”. AI algorithms provide abilities to process large amounts of data and to detect patterns and features that would remain undetected using traditional approaches. Despite these capabilities, the application of AI algorithms to smart monitoring is still limited due to mistrust expressed by engineers towards the generally opaque AI inner processes. To enhance confidence in AI, the “black-box” nature of AI algorithms for smart monitoring needs to be explained to the engineers, resulting in so-called “explainable artificial intelligence” (XAI). However, when aiming at improving the explainability of AI algorithms through XAI for smart monitoring, the variety of AI algorithms requires proper categorization. Therefore, this review paper first identifies objectives of smart monitoring, serving as a basis to categorize AI algorithms or, more precisely, ML algorithms for smart monitoring. ML algorithms for smart monitoring are then reviewed and categorized. As a result, an overview of ML algorithms used for smart monitoring is presented, providing an overview of categories of ML algorithms for smart monitoring that may be modified to achieve explainable artificial intelligence in civil engineering.

38 citations

Journal ArticleDOI
TL;DR: This study develops uncertainty‐aware deep learning models for the assessment of post‐disaster damage using aerial imaging within the framework of variational Bayesian inference, Monte Carlo dropout sampling technique is used to propagate epistemic uncertainty in model predictions.
Abstract: Accurate damage assessment is a critical step in post‐disaster risk assessment, mitigation, and recovery. Current practices performed by experts and reconnaissance teams in the form of field evaluation require considerable time and resources. Recent advances in remote sensing imagery, artificial intelligence (AI), and computer vision have enhanced automated and rapid disaster damage assessment. Recent literature has shown promising progress in AI‐assisted aerial damage assessment. However, accounting for the uncertainty in the outcome for improved quantification of confidence and enhanced model explainability for human decision‐makers remains one of the key challenges. Overlooking uncertainty can lead to erroneous decisions, especially in highly‐consequential tasks such as damage assessment. The aim of this study is to develop uncertainty‐aware deep learning models for the assessment of post‐disaster damage using aerial imaging. Within the framework of variational Bayesian inference, Monte Carlo dropout sampling technique is used to propagate epistemic uncertainty in model predictions. With this stochastic setting, the model produces damage prediction labels with softmax as random variables, which helps quantify confidence in the model outcome using appropriate measures of uncertainty. Two networks are implemented and trained separately on two different disaster damage datasets consisting of unmanned aerial vehicle building footage as well as satellite‐captured post‐disaster imagery. The first network attains 59.4% accuracy in building classification, and the second network gives an accuracy of 55.1%. Results from uncertainty analysis, model confidence quantification, and analyzing model attention zone can lead to more explainable and risk‐informed automated damage assessment outcomes using AI technology.

3 citations

Journal ArticleDOI
TL;DR: In this article, the natural frequencies and roots of the transcendental equation in a cantilever steel beam for transverse vibration with clamped free (CF) boundary conditions are estimated using a LSTM-RNN approach.
Abstract: In this study, the natural frequencies and roots (Eigenvalues) of the transcendental equation in a cantilever steel beam for transverse vibration with clamped free (CF) boundary conditions are estimated using a long short-term memory-recurrent neural network (LSTM-RNN) approach. The finite element method (FEM) package ANSYS is used for dynamic analysis and, with the aid of simulated results, the Euler–Bernoulli beam theory is adopted for the generation of sample datasets. Then, a deep neural network (DNN)-based LSTM-RNN technique is implemented to approximate the roots of the transcendental equation. Datasets are mainly based on the cantilever beam geometry characteristics used for training and testing the proposed LSTM-RNN network. Furthermore, an algorithm using MATLAB platform for numerical solutions is used to cross-validate the dataset results. The network performance is evaluated using the mean square error (MSE) and mean absolute error (MAE). Finally, the numerical and simulated results are compared using the LSTM-RNN methodology to demonstrate the network validity.

2 citations

Book ChapterDOI
01 Jan 2022
TL;DR: In this paper, a review of ML and XAI approaches relevant to structural health monitoring (SHM) applications and a conceptual XAI framework pertinent to SHM applications is proposed.
Abstract: In recent years, structural health monitoring (SHM) applications have significantly been enhanced, driven by advancements in artificial intelligence (AI) and machine learning (ML), a subcategory of AI. Although ML algorithms allow detecting patterns and features in sensor data that would otherwise remain undetected, the generally opaque inner processes and black-box character of ML algorithms are limiting the application of ML to SHM. Incomprehensible decision-making processes often result in doubts and mistrust in ML algorithms, expressed by engineers and stakeholders. In an attempt to increase trust in ML algorithms, explainable artificial intelligence (XAI) aims to provide explanations of decisions made by black-box ML algorithms. However, there is a lack of XAI approaches that meet all requirements of SHM applications. This chapter provides a review of ML and XAI approaches relevant to SHM and proposes a conceptual XAI framework pertinent to SHM applications. First, ML algorithms relevant to SHM are categorized. Next, XAI approaches, such as transparent models and model-specific explanations, are presented and categorized to identify XAI approaches appropriate for being implemented in SHM applications. Finally, based on the categorization of ML algorithms and the presentation of XAI approaches, the conceptual XAI framework is introduced. It is expected that the proposed conceptual XAI framework will provide a basis for improving ML acceptance and transparency and therefore increase trust in ML algorithms implemented in SHM applications.

2 citations

Journal ArticleDOI
TL;DR: In this paper, the authors proposed a new parameter using signals of real vibration, which is called viscosity resistance coefficient (IC), which is determined by adding the material's viscoity to the linear equation of Hooke's law.
Abstract: Assessing change in mechanical properties of a material has constantly been a topic drawing great attention and bringing great applications in recent years. This article proposes a new parameter using signals of real vibration, which is called viscosity resistance coefficient (IC). It is determined by adding the material’s viscosity to the linear equation of Hooke’s law. The set of IC values derived from converting equation is presented on the plane of regression using deep learning and the balancing composite motion optimization (BCMO). The article collects a set of IC values in different states of real vibration signals via a training process using deep learning. By BCMO method, these values regress to a plane with determined areas. This research is applied to two main structures of different materials and operating time namely prestressed concrete and composite concrete bridge spans by surveying four big bridges in Ho Chi Minh city, Vietnam. The result reveals that the IC values assess not only material changes over time but also work for various types of materials. This method will open new opportunities for researches and studies in future.
References
More filters
Proceedings Article
03 Dec 2012
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

73,978 citations

Proceedings Article
04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

55,235 citations

Proceedings Article
01 Jan 2015
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

49,914 citations

Journal ArticleDOI
28 May 2015-Nature
TL;DR: Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.
Abstract: Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visual object recognition, object detection and many other domains such as drug discovery and genomics. Deep learning discovers intricate structure in large data sets by using the backpropagation algorithm to indicate how a machine should change its internal parameters that are used to compute the representation in each layer from the representation in the previous layer. Deep convolutional nets have brought about breakthroughs in processing images, video, speech and audio, whereas recurrent nets have shone light on sequential data such as text and speech.

46,982 citations


Additional excerpts

  • ...error rate. Keywords: Bayesian neural network, Deep learning 1.0 INTRODUCTION Deep learning models are being used on a daily basis to solve different tasks in vision, linguistics and signal processing[1, 2, 3, 4, 5]. Understanding whether the model is under-confident or falsely over-confident can help get better performance out of the model. Recognizing that test data is far from training data, one could easily ...

    [...]

Book
18 Nov 2016
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

38,208 citations