WITHDRAWN: Robust geophone string sensors fault detection and isolation using pattern recognition techniques based on Raspberry Pi4

Abed, Ahmed M.; Gitaffa, Sabah A.; Issa, Abbas H.

doi:10.1016/j.matpr.2021.04.360

Cited by 5 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We chose a Raspberry Pi4 single-board computer as the main node to collect, broadcast, and preprocess visual information to develop the proposed software and hardware tool to inspect pipeline weld surfaces. This choice was based on the availability of the board, its low power consumption, extensive plug-in and expansion card capabilities, the presence of a built-in wireless module, and adequate performance for computing procedures and imaging research experience [29][30][31][32][33]. Since our project involves the connection of two camera modules to be able to build a depth map of the surface of the control object and an inertial measurement unit to determine the location and spatial orientation of the video information acquisition device, there was a problem with the presence of only one scalable coherent interconnect (SCI) port.…”

Section: Methodsmentioning

confidence: 99%

Machine Learning and 3D Reconstruction of Materials Surface for Nondestructive Inspection

Kartashov

Чернов

Alexandrov

et al. 2022

Sensors

View full text Add to dashboard Cite

During the steel pipeline installation, special attention is paid to the butt weld control performed by fusion welding. The operation of the currently popular automated X-ray and ultrasonic testing complexes is associated with high resource and monetary costs. In this regard, this work is devoted to the development of alternative and cost-effective means of preliminary quality control of the work performed based on the visual testing method. To achieve this goal, a hardware platform based on a single board Raspberry Pi4 minicomputer and a set of available modules and expansion cards is proposed, and software whose main functionality is implemented based on the systemic application of computer vision algorithms and machine learning methods. The YOLOv5 object detection algorithm and the random forest machine learning model were used as a defect detection and classification system. The mean average precision (mAP) of the trained YOLOv5 algorithm based on extracted weld contours is 86.9%. A copy of YOLOv5 trained on the images of control objects showed a mAP result of 96.8%. Random forest identifying of the defect precursor based on the point clouds of the weld surface achieved a mAP of 87.5%.

show abstract

Section: Methodsmentioning

confidence: 99%

Machine Learning and 3D Reconstruction of Materials Surface for Nondestructive Inspection

Kartashov

Чернов

Alexandrov

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…According to Eq. ( 4), the number of true positives divided by the sum of true positives and false negatives equals the recall [8].…”

Section: Performance Evaluation Metricsmentioning

confidence: 99%

“…The implementation takes two forms: A software implementation that mimics the data using the Matlab software environment version (2020a) and a Raspberry Pi 4 implementation it's a solitary computer running Linux. Artificial Intelligence (AI) applications will be increasingly executed on small general-purpose CPUs [8]. These inexpensive systems are easy to establish, occupy a small area, and have the necessary computational power.…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network Technique Based Field Digitizing Units (FDUs) Instruments Fault Detection and Isolation

Gitaffa¹,

Issa²,

Ibrahem³

2022

JESA

View full text Add to dashboard Cite

Two significant motivations for continuing development in early process detection problems are technological plant safety and dependability. To avoid economic losses in oil exploration, faults in Field Digitizing Units (FDUs) instruments must be detected. The creation of algorithms that can detect process issues before they reach their threshold is a big task, and trend checks associated with a particular measured value are typical. The efficiency of the Deep Neural Network (DNN) technique employing Matlab and a lowcomputational power device, such as the Raspberry Pi 4, for drift fault detection in FDUs is evaluated in this article. The DNN classifier is among the deep learning algorithms being studied. The FDUs instruments provided the data for this experiment. In training and testing data, the six features (Distortion, Noise, Common-Mode Rejection (CMRR), Gain Error, Phase Error, and Crosstalk) were extracted from free fault and faulty FDUs. The trained model has been offline tested, with the model being used to detect drift faults using FDU performance. Accuracy, specification, precision, recall, and F-measure were used to determine the efficiency of the classifier, with 99.7% accuracy in the DNN with Matlab and 98% accuracy in the DNN with Python.

show abstract

“…If the water is below only water levels' threshold is checked (this usually indicates the existence of maintenance labors in the channel). The final aim, after collecting more data and managing patterns, is to change (or run in parallel) this algorithm by machine learning classification technics to implement lists of managing tasks according to specific patterns in the collected data, the Raspberry Pi based gateway, and Python language are excellent platforms for such purpose (e.g., [22][23][24]).…”

Section: Management Platformmentioning

confidence: 99%

A Custom Sensor Network for Autonomous Water Quality Assessment in Fish Farms

Fuentes‐Pérez

Sanz‐Ronda

2021

Electronics

View full text Add to dashboard Cite

The control of water quality is crucial to ensure the survival of fish in aquaculture production facilities. Today, the combination of sensors with communication technologies permits to monitor these crucial parameters in real-time, allowing to take fast management decisions. However, out-of-the-box solutions are expensive, due to the small market and the industrial nature of sensors, besides being little customizable. To solve this, the present work describes a low-cost hardware and software architecture developed to achieve the autonomous water quality assessment and management on a remote facility for fish conservation aquaculture within the framework of the Smart Comunidad Rural Digital (smartCRD) project. The developed sensor network has been working uninterruptedly since its installation (20 April 2021). It is based on open source technology and includes a central gateway for on-site data monitoring of water quality nodes as well as an online management platform for data visualization and sensor network configuration. Likewise, the system can detect autonomously water quality parameters outside configurable thresholds and deliver management alarms. The described architecture, besides low-cost, is highly customizable, compatible with other sensor network projects, machine-learning applications, and is capable of edge computing. Thus, it contributes to making open sensorization more accessible to real-world applications.

show abstract

WITHDRAWN: Robust geophone string sensors fault detection and isolation using pattern recognition techniques based on Raspberry Pi4

Cited by 5 publications

References 21 publications

Machine Learning and 3D Reconstruction of Materials Surface for Nondestructive Inspection

Machine Learning and 3D Reconstruction of Materials Surface for Nondestructive Inspection

Deep Neural Network Technique Based Field Digitizing Units (FDUs) Instruments Fault Detection and Isolation

A Custom Sensor Network for Autonomous Water Quality Assessment in Fish Farms

Contact Info

Product

Resources

About