Experimental verification of improved probability of detection model considering the effect of sensor’s location on low frequency electromagnetic monitoring signals

2020 ◽  
Vol 64 (1-4) ◽  
pp. 191-199
Author(s):  
Haicheng Song ◽  
Noritaka Yusa
Keyword(s):  
Monte Carlo Simulation ◽  
Health Monitoring ◽  
Low Frequency ◽  
Probability Of Detection ◽  
Detection Model ◽  
Proposed Model ◽  
Reasonable Approach ◽  
Multiple Defect ◽  
Electromagnetic Monitoring ◽  
Sensor Locations

Structural health monitoring (SHM) is a promising method for maintaining the integrity of structures. A reasonable approach is necessary to quantify its detection uncertainty by taking into account the effect of random sensor locations on inspection signals. Recent studies of the authors proposed a model that adopts Monte Carlo simulation to numerically obtain the distribution of inspection signals influenced by random sensor locations. This model can evaluate the effect not only of multiple defect dimensions but also of the placement of sensors on the detection uncertainty. However, its effectiveness has only been confirmed using pseudo-experimental signals generated by artificial pollution. This study aims to examine the effectiveness of the proposed model in quantifying the detection uncertainty of SHM methods using the experimental signals of low frequency electromagnetic monitoring for inspecting wall thinning in pipes. The results confirm the capability of the proposed model to correctly characterize the distribution of inspection signals affected by random sensor locations and to determine the reasonable probability of detection.

Damage Detectability Model of Pitch-Catch Configuration in Composite Plates

2017 ◽  
Vol 754 ◽  
pp. 387-390 ◽  
Author(s):  
Nan Yue ◽  
Zahra Sharif Khodaei ◽  
Ferri M.H. Aliabadi
Keyword(s):  
Wave Propagation ◽  
Damage Detection ◽  
Health Monitoring ◽  
Lamb Waves ◽  
Composite Plates ◽  
Detection Algorithm ◽  
Probability Of Detection ◽  
Operational Conditions ◽  
Proposed Model ◽  
Lamb Wave Propagation

Detectability of damage using Lamb waves depends on many factors such as size and severity of damage, attenuation of the wave and distance to the transducers. This paper presents a detectability model for pitch-catch sensors configuration for structural health monitoring (SHM) applications. The proposed model considers the physical properties of lamb wave propagation and is independent of damage detection algorithm, which provides a generic solution for probability of detection. The applicability of the model in different environmental and operational conditions is also discussed.

Probabilistic evaluation of the area of coverage of a probe used for eddy current non-destructive inspections

2020 ◽  
Vol 64 (1-4) ◽  
pp. 11-18
Author(s):  
Noritaka Yusa ◽  
Takuma Tomizawa ◽  
Haicheng Song
Keyword(s):  
Eddy Current ◽  
Gaussian Function ◽  
Probability Of Detection ◽  
Steel Plates ◽  
Detection Model ◽  
Probabilistic Evaluation ◽  
Proposed Model ◽  
Scanning Line ◽  
Non Destructive ◽  
Type 316L Stainless Steel

This study proposes a method to probabilistically evaluate the area of coverage of nondestructive inspections to detect defects on a surface of a structure. For the specific problem, this study considers the effect of the distance between two neighboring scanning lines on the detectability of eddy current testing against near-side cracks. Thirty-eight type 316L stainless steel plates having a fatigue crack were prepared, and eddy current examinations were performed with a sufficiently fine scanning pitch. The full width at half maximum of the spatial distribution of the amplitude of the signals was approximated using a Gaussian function. A probability of detection model considering the distance between two neighboring scanning lines is proposed because in actual inspections a scanning line does not always run directly above a crack. The results demonstrated that the proposed model enables a reasonable probabilistic evaluation of the effect of the distance between two neighboring scanning lines.

Hybrid Deep Neural Model for Duplicate Question Detection in Transliterated Bi-lingual Data

2019 ◽  
Vol 12 ◽  
Author(s):  
Seema Rani ◽  
Avadhesh Kumar ◽  
Naresh Kumar
Keyword(s):  
Question Answering ◽  
Neural Model ◽  
Manhattan Distance ◽  
Semantic Matching ◽  
English Only ◽  
Detection Model ◽  
Proposed Model ◽  
Reported Study ◽  
Social Media Platforms ◽  
Efficient Information

Background: Duplicate content often corrupts the filtering mechanism in online question answering. Moreover, as users are usually more comfortable conversing in their native language questions, transliteration adds to the challenges in detecting duplicate questions. This compromises with the response time and increases the answer overload. Thus, it has now become crucial to build clever, intelligent and semantic filters which semantically match linguistically disparate questions. Objective: Most of the research on duplicate question detection has been done on mono-lingual, majorly English Q&A platforms. The aim is to build a model which extends the cognitive capabilities of machines to interpret, comprehend and learn features for semantic matching in transliterated bi-lingual Hinglish (Hindi + English) data acquired from different Q&A platforms. Method: In the proposed DQDHinglish (Duplicate Question Detection) Model, firstly language transformation (transliteration & translation) is done to convert the bi-lingual transliterated question into a mono-lingual English only text. Next a hybrid of Siamese neural network containing two identical Long-term-Short-memory (LSTM) models and Multi-layer perceptron network is proposed to detect semantically similar question pairs. Manhattan distance function is used as the similarity measure. Result: A dataset was prepared by scrapping 100 question pairs from various social media platforms, such as Quora and TripAdvisor. The performance of the proposed model on the basis of accuracy and F-score. The proposed DQDHinglish achieves a validation accuracy of 82.40%. Conclusion: A deep neural model was introduced to find semantic match between English question and a Hinglish (Hindi + English) question such that similar intent questions can be combined to enable fast and efficient information processing and delivery. A dataset was created and the proposed model was evaluated on the basis of performance accuracy. To the best of our knowledge, this work is the first reported study on transliterated Hinglish semantic question matching.

scholarly journals A Robust Lane Detection Model Using Vertical Spatial Features and Contextual Driving Information

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 708
Author(s):  
Wenbo Liu ◽  
Fei Yan ◽  
Jiyong Zhang ◽  
Tao Deng
Keyword(s):  
Information Exchange ◽  
Information Transfer ◽  
Spatial Information ◽  
Contextual Information ◽  
Great Influence ◽  
Light Condition ◽  
Lane Detection ◽  
Detection Model ◽  
Spatial Features ◽  
Proposed Model

The quality of detected lane lines has a great influence on the driving decisions of unmanned vehicles. However, during the process of unmanned vehicle driving, the changes in the driving scene cause much trouble for lane detection algorithms. The unclear and occluded lane lines cannot be clearly detected by most existing lane detection models in many complex driving scenes, such as crowded scene, poor light condition, etc. In view of this, we propose a robust lane detection model using vertical spatial features and contextual driving information in complex driving scenes. The more effective use of contextual information and vertical spatial features enables the proposed model more robust detect unclear and occluded lane lines by two designed blocks: feature merging block and information exchange block. The feature merging block can provide increased contextual information to pass to the subsequent network, which enables the network to learn more feature details to help detect unclear lane lines. The information exchange block is a novel block that combines the advantages of spatial convolution and dilated convolution to enhance the process of information transfer between pixels. The addition of spatial information allows the network to better detect occluded lane lines. Experimental results show that our proposed model can detect lane lines more robustly and precisely than state-of-the-art models in a variety of complex driving scenarios.

Health monitoring sensor placement optimization based on initial sensor layout using improved partheno-genetic algorithm

2020 ◽  
pp. 136943322094719
Author(s):  
Xianrong Qin ◽  
Pengming Zhan ◽  
Chuanqiang Yu ◽  
Qing Zhang ◽  
Yuantao Sun
Keyword(s):  
Genetic Algorithm ◽  
Health Monitoring ◽  
Large Scale ◽  
Complex Structure ◽  
Sensor Placement ◽  
Placement Problem ◽  
Optimal Sensor Placement ◽  
Placement Optimization ◽  
Sensor Placement Optimization ◽  
Sensor Locations

Optimal sensor placement is an important component of a reliability structural health monitoring system for a large-scale complex structure. However, the current research mainly focuses on optimizing sensor placement problem for structures without any initial sensor layout. In some cases, the experienced engineers will first determine the key position of whole structure must place sensors, that is, initial sensor layout. Moreover, current genetic algorithm or partheno-genetic algorithm will change the position of the initial sensor locations in the iterative process, so it is unadaptable for optimal sensor placement problem based on initial sensor layout. In this article, an optimal sensor placement method based on initial sensor layout using improved partheno-genetic algorithm is proposed. First, some improved genetic operations of partheno-genetic algorithm for sensor placement optimization with initial sensor layout are presented, such as segmented swap, reverse and insert operator to avoid the change of initial sensor locations. Then, the objective function for optimal sensor placement problem is presented based on modal assurance criterion, modal energy criterion, and sensor placement cost. At last, the effectiveness and reliability of the proposed method are validated by a numerical example of a quayside container crane. Furthermore, the sensor placement result with the proposed method is better than that with effective independence method without initial sensor layout and the traditional partheno-genetic algorithm.

A Review of Crack Detection In-Line Inspection Case Studies

2010 ◽  
Author(s):  
Neil Bates ◽  
David Lee ◽  
Clifford Maier
Keyword(s):  
Crack Growth ◽  
Case Studies ◽  
Crack Detection ◽  
Growth Parameters ◽  
Probability Distributions ◽  
Low Frequency ◽  
Probability Of Failure ◽  
Probability Of Detection ◽  
Inspection Data

This paper describes case studies involving crack detection in-line inspections and fitness for service assessments that were performed based on the inspection data. The assessments were used to evaluate the immediate integrity of the pipeline based on the reported features and the long-term integrity of the pipeline based on excavation data and probabilistic SCC and fatigue crack growth simulations. Two different case studies are analyzed, which illustrate how the data from an ultrasonic crack tool inspection was used to assess threats such as low frequency electrical resistance weld seam defects and stress corrosion cracking. Specific issues, such as probability of detection/identification and the length/depth accuracy of the tool, were evaluated to determine the suitability of the tool to accurately classify and size different types of defects. The long term assessment is based on the Monte Carlo method [1], where the material properties, pipeline details, crack growth parameters, and feature dimensions are randomly selected from certain specified probability distributions to determine the probability of failure versus time for the pipeline segment. The distributions of unreported crack-related features from the excavation program are used to distribute unreported features along the pipeline. Simulated crack growth by fatigue, SCC, or a combination of the two is performed until failure by either leak or rupture is predicted. The probability of failure calculation is performed through a number of crack growth simulations for each of the reported and unreported features and tallying their respective remaining lives. The results of the probabilistic analysis were used to determine the most effective and economical means of remediation by identifying areas or crack mechanisms that contribute most to the probability of failure.

An Opcode-Based Malware Detection Model Using Supervised Learning Algorithms

2021 ◽  
Vol 15 (4) ◽  
pp. 18-30
Author(s):  
Om Prakash Samantray ◽  
Satya Narayan Tripathy
Keyword(s):  
Supervised Learning ◽  
Learning Algorithms ◽  
Malware Detection ◽  
Support Vector ◽  
Detection Accuracy ◽  
Detection Techniques ◽  
Detection Model ◽  
Proposed Model ◽  
Tree Classifier ◽  
Supervised Learning Algorithms

There are several malware detection techniques available that are based on a signature-based approach. This approach can detect known malware very effectively but sometimes may fail to detect unknown or zero-day attacks. In this article, the authors have proposed a malware detection model that uses operation codes of malicious and benign executables as the feature. The proposed model uses opcode extract and count (OPEC) algorithm to prepare the opcode feature vector for the experiment. Most relevant features are selected using extra tree classifier feature selection technique and then passed through several supervised learning algorithms like support vector machine, naive bayes, decision tree, random forest, logistic regression, and k-nearest neighbour to build classification models for malware detection. The proposed model has achieved a detection accuracy of 98.7%, which makes this model better than many of the similar works discussed in the literature.

Federal Aviation Administration’s Probability of Detection Testing Results for Structural Health Monitoring (SHM)

2021 ◽  
Author(s):  
Paul Swindell ◽  
Danielle Stephens
Keyword(s):  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Federal Aviation Administration ◽  
Steering Committee ◽  
Probability Of Detection ◽  
The Other ◽  
Atlantic City ◽  
Commercial Aviation ◽  
Structural Health ◽  
Set Up

Abstract The Federal Aviation Administration (FAA) has been participating with the Society of Automotive Engineers (SAE) Aerospace Industry Steering Committee (AISC) to develop a methodology for calculating the Probability of Detection (POD) for Structural Health Monitoring (SHM) for damage detection on commercial aviation. Two POD methodologies were developed: one by Dr. William Meeker, Iowa State University, and the other by Dennis Roach, Sandia National Laboratories (SNL). With Dr. Seth Kessler, Metis Design Corp, a test program of 24 samples of aluminum strips to be fatigued on MTS machines was developed. The samples were designed to meet the ASTM E647. Twelve samples had two SHM modalities on the front and back from Metis (PZT and carbon nanotubes), and the other twelve had SHM sensors from Structural Monitoring Systems (SMS) (comparative vacuum monitoring – CVM) and Acellent Technologies (PZT). The tests were performed at the FAA William J Hughes Technical Center in Atlantic City, NJ. The samples were cycled every 1500 cycles and then stopped for SHM data collection. Once the crack exceeded 0.125 inches and provided for a minimum of 15 inspections, a new sample was tested until all 12 samples were completed. The data was provided to each company to be set up in the format needed to run through the POD methodologies. Then the data was provided to Dr. Meeker and Dr. Roach for analysis. This paper will provide the results of those tests.

Sign in / Sign up

Export Citation Format

Share Document