scholarly journals Real-Time Leak Detection for a Gas Pipeline Using a k-NN Classifier and Hybrid AE Features

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 367
Author(s):  
Thang Bui Quy ◽  
Jong-Myon Kim
Keyword(s):  
Embedded System ◽  
Real Time ◽  
Leak Detection ◽  
Detection Algorithm ◽  
Time Characteristic ◽  
Gas Pipeline ◽  
Occurrence Rate ◽  
Hybrid Features ◽  
The Real ◽  
Ae Signals

This paper introduces a technique using a k-nearest neighbor (k-NN) classifier and hybrid features extracted from acoustic emission (AE) signals for detecting leakages in a gas pipeline. The whole algorithm is embedded in a microcontroller unit (MCU) to detect leaks in real-time. The embedded system receives signals continuously from a sensor mounted on the surface of a gas pipeline to diagnose any leak. To construct the system, AE signals are first recorded from a gas pipeline testbed under various conditions and used to synthesize the leak detection algorithm via offline signal analysis. The current work explores different features of normal/leaking states from corresponding datasets and eliminates redundant and outlier features to improve the performance and guarantee the real-time characteristic of the leak detection program. To obtain the robustness of leak detection, the paper normalizes features and adapts the trained k-NN classifier to the specific environment where the system is installed. Aside from using a classifier for categorizing normal/leaking states of a pipeline, the system monitors accumulative leaking event occurrence rate (ALEOR) in conjunction with a defined threshold to conclude the state of the pipeline. The entire proposed system is implemented on the 32F746G-DISCOVERY board, and to verify this system, numerous real AE signals stored in a hard drive are transferred to the board. The experimental results show that the proposed system executes the leak detection algorithm in a period shorter than the total input data time, thus guaranteeing the real-time characteristic. Furthermore, the system always yields high average classification accuracy (ACA) despite adding a white noise to input signal, and false alarms do not occur with a reasonable ALEOR threshold.

The Method for Real-Time Length Measurement of Fiber Winding

2013 ◽  
Vol 380-384 ◽  
pp. 919-922
Author(s):  
Chen Xia Guo ◽  
Rui Feng Yang
Keyword(s):  
Real Time ◽  
Detection Algorithm ◽  
Moving Target ◽  
Fiber Optic Gyroscope ◽  
Optical Encoder ◽  
The Real ◽  
Time Length ◽  
Fiber Coil ◽  
Fiber Winding ◽  
Coil Winding

The paper discusess mainly how to accurately measure the real-time length of fiber optic gyroscope sensing coil (fiber coil) in the process of FOG coil winding. First, using the improved moving target detection algorithm to process the fiber images collected by machine vision. Secondly, using software algorithm to calculate the real-time radius of fiber winding. Finaly, combining the incremental optical encoder with real-time radius to calculate real-time winding length of fiber coil.

An Optimized Collision Detection Algorithm Based on Dynamic Bounding Volume Tree

2013 ◽  
Vol 846-847 ◽  
pp. 1372-1375
Author(s):  
Wei Zhao ◽  
Li Ming Ye
Keyword(s):  
Real Time ◽  
Collision Detection ◽  
Detection Algorithm ◽  
The Real ◽  
Bounding Volume

An optimized collision detection algorithm based on dynamic bounding volume tree is proposed in this paper. First this algorithm adopts spatial division to exclude objects which cant intersect to define the potential intersection areas. Then use a new dynamic OBB bounding volume tree to test whether the intersection happened between the objects in the same grid. At last, this algorithm improves the traditional overlapping test between the primitives for accurate collision detection to accelerate the detection between objects. Compared to the traditional collision detection algorithm based on OBB bounding volume. This algorithm can effectively improve the real-time of the collision detection without affecting the accuracy of original collision detection.

scholarly journals Multivariate-Time-Series-Driven Real-time Anomaly Detection Based on Bayesian Network

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3367 ◽  
Author(s):  
Nan Ding ◽  
Huanbo Gao ◽  
Hongyu Bu ◽  
Haoxuan Ma ◽  
Huaiwei Si
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Bayesian Network ◽  
Real Time ◽  
Multivariate Time Series ◽  
Research Direction ◽  
Detection Algorithm ◽  
The Real ◽  
Hierarchical Temporal Memory ◽  
Sensing Time

Anomaly detection is an important research direction, which takes the real-time information system from different sensors and conditional information sources into consideration. Based on this, we can detect possible anomalies expected of the devices and components. One of the challenges is anomaly detection in multivariate-sensing time-series in this paper. Based on this situation, we propose RADM, a real-time anomaly detection algorithm based on Hierarchical Temporal Memory (HTM) and Bayesian Network (BN). First of all, we use HTM model to evaluate the real-time anomalies of each univariate-sensing time-series. Secondly, a model of anomalous state detection in multivariate-sensing time-series based on Naive Bayesian is designed to analyze the validity of the above time-series. Lastly, considering the real-time monitoring cases of the system states of terminal nodes in Cloud Platform, the effectiveness of the methodology is demonstrated using a simulated example. Extensive simulation results show that using RADM in multivariate-sensing time-series is able to detect more abnormal, and thus can remarkably improve the performance of real-time anomaly detection.

Gas Pipeline Simulation: Use of a Single System for All Simulations

2006 ◽  
Author(s):  
Heribert Scheerer ◽  
Stewart Midwinter
Keyword(s):  
Steady State ◽  
Real Time ◽  
Simulation Models ◽  
Leak Detection ◽  
Gas Pipeline ◽  
Simulation Tools ◽  
Cost Of Energy ◽  
Time Simulation ◽  
Long Time ◽  
Training Simulation

Simulation tools have been used for a long time in the gas pipeline industry to do things like system planning and training simulation, using both steady state and transient simulators. Companies have also tried using simulation models in real time environments, to do applications such as line pack management and leak detection, with less than great results. With the increased cost of energy, more importance has been placed on use of simulation to optimize the operation of gas pipelines. One of the biggest problems with using simulation in so many areas is that many different models from potentially different suppliers had to be used. This resulted in a high cost to implement and maintain several systems. This paper will show a simulation system that is capable of performing steady state and transient simulation, off-line and real time simulation, leak detection and optimization, all using a single modeling platform. Examples of field use of the system will show the benefits that can be realized.

scholarly journals Real-Time Road Hazard Information System

2020 ◽  
Vol 5 (9) ◽  
pp. 75
Author(s):  
Carlos Pena-Caballero ◽  
Dongchul Kim ◽  
Adolfo Gonzalez ◽  
Osvaldo Castellanos ◽  
Angel Cantu ◽  
...  
Keyword(s):  
Embedded System ◽  
Real Time ◽  
Semantic Segmentation ◽  
Detection Algorithm ◽  
Classification Performance ◽  
Network Size ◽  
Road Accidents ◽  
Economic Productivity ◽  
Art Object ◽  
National Economies

Infrastructure is a significant factor in economic growth for systems of government. In order to increase economic productivity, maintaining infrastructure quality is essential. One of the elements of infrastructure is roads. Roads are means which help local and national economies be more productive. Furthermore, road damage such as potholes, debris, or cracks is the cause of many on-road accidents that have cost the lives of many drivers. In this paper, we propose a system that uses Convolutional Neural Networks to detect road degradations without data pre-processing. We utilize the state-of-the-art object detection algorithm, YOLO detector for the system. First, we developed a basic system working on data collecting, pre-processing, and classification. Secondly, we improved the classification performance achieving 97.98% in the overall model testing, and then we utilized pixel-level classification and detection with a method called semantic segmentation. We were able to achieve decent results using this method to detect and classify four different classes (Manhole, Pothole, Blurred Crosswalk, Blurred Street Line). We trained a segmentation model that recognizes the four classes mentioned above and achieved great results with this model allowing the machine to effectively and correctly identify and classify our four classes in an image. Although we obtained excellent accuracy from the detectors, these do not perform particularly well on embedded systems due to their network size. Therefore, we opted for a smaller, less accurate detector that will run in real time on a cheap embedded system, like the Google Coral Dev Board, without needing a powerful and expensive GPU.

Research on Improved Genetic Algorithm

2014 ◽  
Vol 635-637 ◽  
pp. 1760-1763
Author(s):  
Xiao Yu Wang ◽  
Yong Hui Yang ◽  
Shuo Li ◽  
Chuang Gao
Keyword(s):  
Genetic Algorithm ◽  
Embedded System ◽  
Real Time ◽  
Cost Reduction ◽  
Function Optimization ◽  
Improved Genetic Algorithm ◽  
The Real ◽  
Crossover Rate ◽  
Time Requirements ◽  
Improved Algorithm

An improved genetic algorithm for the function optimization of multi-core embedded system is proposed. A number of chromosomes that distribute uniformly in space are generated by the algorithm randomly. Each chromosome is randomly coded and a new one will be generated by mutual calculation. After continuous elimination and circulation, the optimized chromosomes can be selected. The improved algorithm makes the mutation offspring have the opportunity to be the next parent with the increase of mutation. It enhances the parent diversity, increases the crossover rate, activates crossover between the parents and has chance to access to the best solution. The efficiency and cost reduction performance are improved. The different tasks will be distributed in parallel to available processors so as to meet the real-time requirements.

General Concept of the EMG Controlled Bionic Hand

2020 ◽  
Vol 8 (1) ◽  
pp. 26-34
Author(s):  
Adam Pieprzycki ◽  
Daniel Król
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Control System ◽  
Embedded System ◽  
Real Time ◽  
General Concept ◽  
System Implementation ◽  
The Real ◽  
Emg Signal ◽  
Hand Control

The article presents a general concept of a bionic hand control system using a multichannel EMG signal, being under development at present. The method of acquisition and processing of multi-channel EMG signal and feature extraction for machine learning were described. Moreover, the design of the control system implementation in the real-time embedded system was discussed.

The Research of the Real-Time High-Resolution Image Acquisition Based on Embedded System

2014 ◽  
Vol 631-632 ◽  
pp. 508-511
Author(s):  
Xi Ye Feng ◽  
Xiu Qing Huang
Keyword(s):  
High Resolution ◽  
Embedded System ◽  
Real Time ◽  
Low Cost ◽  
Image Acquisition ◽  
Image Data ◽  
Image Sensor ◽  
High Definition ◽  
The Real ◽  
Embedded Linux System

This paper presents the design of a real-time high-definition image acquisition. The hardware platform combines Intel Xscale PXA270 processor, high-resolution camera and SAA7114H. The system is based on the embedded Linux system. Beetween the image sensor and the system memory,there is a quick capture interface.The interface receives the data from the image sensor,and converts the raw image data to a suitable format, and sends H.264 stream to the memory via the DMA channel. The result shows that the design can realize the real-time and high-definition image acquisition in a complicated environment. The advantage of this system is small volume, low power consumption and low cost. It can be widely used in agricultural and hydrological monitoring, intelligent transportation, security monitoring and intelligent home.

Sign in / Sign up

Export Citation Format

Share Document