scholarly journals IoT-платформа для вібраційної діагностики промислового обладнання

2021 ◽  
pp. 125-139
Author(s):  
Ігор Борисович Туркін ◽  
В'ячеслав Андрійович Лезновскій
Keyword(s):  
Artificial Intelligence ◽  
Learning Algorithm ◽  
Diagnostic System ◽  
Cloud Service ◽  
Measuring System ◽  
Industrial Equipment ◽  
Sensors And Actuators ◽  
Vibration Diagnostics ◽  
Iot Platform ◽  
Microsoft Azure

The subject of study in the article is a digital platform for vibration diagnostics of industrial equipment. The aim is to increase the informativeness of vibration diagnostics processes of industrial equipment by developing and implementing IoT-oriented solutions based on the concept of intelligent sensors and actuators according to the IEEE standard 1451.0-2007. Tasks: to substantiate the feasibility of using platform-oriented technologies for vibration diagnostics of industrial equipment and choose a cloud service for the implementation of the platform, to develop software and hardware solutions for IoT-platform for vibration diagnostics of industrial equipment; calibrate the vibration diagnostic system and check the accuracy of the measurement. The methods used are microservice approach, multilevel architecture, methods for assessing the condition of equipment by vibration indicators. The following results were obtained. The Microsoft Azure IoT platform, which provides the infrastructure for creating and managing cloud applications, was chosen as the cloud computing platform for the industrial equipment vibration diagnostic system. Azure Internet of Things Suite is a Microsoft Azure IoT service designed to integrate and organize data flows, analyze, and present data in a format that helps people make informed decisions. The architecture of the IoT-system of vibration diagnostics of industrial equipment developed and presented in the article is three-level. The level of autonomous sensors provides reading of vibration acceleration indicators and through the digital wireless data transmission channel BLE transmits data to the Hub level, which is implemented based on a single-board microcomputer BeagleBone. The computing power of BeagleBone provides work with artificial intelligence algorithms. At the third level of the server platform, the tasks of diagnosing and predicting the state of the equipment are solved, for which the Dictionary Learning algorithm implemented in the Python programming language is used. Conclusions. Tests of the IoT system for vibration diagnostics of industrial equipment were performed using a special stand, which allows the calibration of sensors and verification of the accuracy of the measuring system. The correctness of the entire system is confirmed by the coincidence of expected and measured results. The direction of development of the IoT-system for vibration diagnostics of industrial equipment is the development of additional microservices, which will add the possibility of using modern artificial intelligence technologies for complex diagnostics and forecasting of equipment status.

scholarly journals CAFD: Context-Aware Fault Diagnostic Scheme towards Sensor Faults Utilizing Machine Learning

Sensors ◽  
2021 ◽  
Vol 21 (2) ◽  
pp. 617
Author(s):  
Umer Saeed ◽  
Young-Doo Lee ◽  
Sana Ullah Jan ◽  
Insoo Koo
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Diagnostic System ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Context Aware ◽  
Sensor Faults ◽  
Training Time ◽  
Low Intensity ◽  
Fault Diagnostic

Sensors’ existence as a key component of Cyber-Physical Systems makes it susceptible to failures due to complex environments, low-quality production, and aging. When defective, sensors either stop communicating or convey incorrect information. These unsteady situations threaten the safety, economy, and reliability of a system. The objective of this study is to construct a lightweight machine learning-based fault detection and diagnostic system within the limited energy resources, memory, and computation of a Wireless Sensor Network (WSN). In this paper, a Context-Aware Fault Diagnostic (CAFD) scheme is proposed based on an ensemble learning algorithm called Extra-Trees. To evaluate the performance of the proposed scheme, a realistic WSN scenario composed of humidity and temperature sensor observations is replicated with extreme low-intensity faults. Six commonly occurring types of sensor fault are considered: drift, hard-over/bias, spike, erratic/precision degradation, stuck, and data-loss. The proposed CAFD scheme reveals the ability to accurately detect and diagnose low-intensity sensor faults in a timely manner. Moreover, the efficiency of the Extra-Trees algorithm in terms of diagnostic accuracy, F1-score, ROC-AUC, and training time is demonstrated by comparison with cutting-edge machine learning algorithms: a Support Vector Machine and a Neural Network.

ID: 3526637 ARTIFICIAL INTELLIGENCE-ASSISTED DIAGNOSTIC SYSTEM FOR NARROW-BAND IMAGING FOR COLORECTAL LESIONS.

2021 ◽  
Vol 93 (6) ◽  
pp. AB198-AB199
Author(s):  
Masashi Misawa ◽  
Shinei Kudo ◽  
Yuichi Mori ◽  
Misaki Ishiyama ◽  
Yosuke Minegishi ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Narrow Band ◽  
Narrow Band Imaging ◽  
Diagnostic System

scholarly journals Automated Detection of Laryngeal Carcinoma in Laryngoscopic Images from a Multicenter Database using a Convolutional Neural Network

2021 ◽  
Author(s):  
Peikai Yan ◽  
Shaohua Li ◽  
Zhou Zhou ◽  
Qian Liu ◽  
Jiahui Wu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Laryngeal Carcinoma ◽  
Detection System ◽  
Tertiary Care ◽  
Diagnostic System ◽  
Intelligence System ◽  
Testing Dataset ◽  
Malignant Group ◽  
Automatic Detection System ◽  
Tertiary Care Centers

OBJECTIVE Little is known about the efficacy of using artificial intelligence to identify laryngeal carcinoma from images of vocal lesions taken in different hospitals with multiple laryngoscope systems. This multicenter study was aimed to establish an artificial intelligence system and provide a reliable auxiliary tool to screen for laryngeal carcinoma. Study Design: Multicentre case-control study Setting: Six tertiary care centers Participants: The laryngoscopy images were collected from 2179 patients with vocal lesions. Outcome Measures: An automatic detection system of laryngeal carcinoma was established based on Faster R-CNN, which was used to distinguish vocal malignant and benign lesions in 2179 laryngoscopy images acquired from 6 hospitals with 5 types of laryngoscopy systems. Pathology was the gold standard to identify malignant and benign vocal lesions. Results: Among 89 cases of the malignant group, the classifier was able to evaluate the laryngeal carcinoma in 66 patients (74.16%, sensitivity), while the classifier was able to assess the benign laryngeal lesion in 503 cases among 640 cases of the benign group (78.59%, specificity). Furthermore, the CNN-based classifier achieved an overall accuracy of 78.05% with a 95.63% negative prediction for the testing dataset. Conclusion: This automatic diagnostic system has the potential to assist clinical laryngeal carcinoma diagnosis, which may improve and standardize the diagnostic capacity of endoscopists using different laryngoscopes.

scholarly journals Research on machine learning Algorithm optimization based on 0-1 coding

2021 ◽  
Vol 2083 (4) ◽  
pp. 042086
Author(s):  
Yuqi Qin
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Manufacturing Industry ◽  
Learning Algorithm ◽  
Machine Learning Algorithm ◽  
Algorithm Optimization ◽  
The Core ◽  
Coding Method ◽  
Discrete Manufacturing

Abstract Machine learning algorithm is the core of artificial intelligence, is the fundamental way to make computer intelligent, its application in all fields of artificial intelligence. Aiming at the problems of the existing algorithms in the discrete manufacturing industry, this paper proposes a new 0-1 coding method to optimize the learning algorithm, and finally proposes a learning algorithm of “IG type learning only from the best”.

scholarly journals Artificial intelligence assisted electrocardiography for early diagnosis of thyrotoxic periodic paralysis

2021 ◽  
Author(s):  
Chin Lin ◽  
Chin-Sheng Lin ◽  
Ding-Jie Lee ◽  
Chia-Cheng Lee ◽  
Sy-Jou Chen ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Early Diagnosis ◽  
Validation Cohort ◽  
Laboratory Data ◽  
Diagnostic System ◽  
Periodic Paralysis ◽  
Medical Emergency ◽  
Diagnostic Process ◽  
Routine Laboratory ◽  
Thyrotoxic Periodic Paralysis

Abstract CONTEXT Thyrotoxic periodic paralysis (TPP) characterized by acute weakness, hypokalemia and hyperthyroidism is a medical emergency with a great challenge in early diagnosis since most TPP patients do not have overt symptoms. OBJECTIVE To assess artificial intelligence (AI)-assisted electrocardiography (ECG) combined with routine laboratory data in the early diagnosis of TPP. METHODS A deep learning model (DLM) based on ECG12Net, an 82-layer convolutional neural network, was constructed to detect hypokalemia and hyperthyroidism. The development cohort consisted of 39 ECGs from patients with TPP and 502 ECGs of hypokalemic control; the validation cohort consisted of 11 ECGs of TPP and 36 ECGs of non-TPP with weakness. The AI-ECG based TPP diagnostic process was then consecutively evaluated in 22 male patients with TTP-like features. RESULTS In the validation cohort, the DLM-based ECG system detected all cases of hypokalemia in TPP patients with a mean absolute error of 0.26 mEq/L and diagnosed TPP with an area under curve (AUC) of ~80%, surpassing the best standard ECG parameter (AUC=0.7285 for the QR interval). Combining the AI predictions with the estimated glomerular filtration rate (eGFR) and serum chloride (Cl -) boosted the diagnostic accuracy of the algorithm to AUC 0.986. In the prospective study, the integrated AI and routine laboratory diagnostic system had a PPV of 100% and F-measure 87.5%. CONCLUSIONS An AI-ECG system reliably identifies hypokalemia in patients with paralysis and integration with routine blood chemistries provides valuable decision support for the early diagnosis of TPP.

scholarly journals A Q-Learning Rescheduling Approach to the Flexible Job Shop Problem Combining Energy and Productivity Objectives

2021 ◽  
Vol 13 (23) ◽  
pp. 13016
Author(s):  
Rami Naimi ◽  
Maroua Nouiri ◽  
Olivier Cardin
Keyword(s):  
Artificial Intelligence ◽  
Energy Consumption ◽  
Job Shop ◽  
Learning Algorithm ◽  
Minimum Energy ◽  
Flexible Job Shop ◽  
Q Learning ◽  
Minimum Energy Consumption ◽  
Machine Failure ◽  
Flexible Job Shop Problem

The flexible job shop problem (FJSP) has been studied in recent decades due to its dynamic and uncertain nature. Responding to a system’s perturbation in an intelligent way and with minimum energy consumption variation is an important matter. Fortunately, thanks to the development of artificial intelligence and machine learning, a lot of researchers are using these new techniques to solve the rescheduling problem in a flexible job shop. Reinforcement learning, which is a popular approach in artificial intelligence, is often used in rescheduling. This article presents a Q-learning rescheduling approach to the flexible job shop problem combining energy and productivity objectives in a context of machine failure. First, a genetic algorithm was adopted to generate the initial predictive schedule, and then rescheduling strategies were developed to handle machine failures. As the system should be capable of reacting quickly to unexpected events, a multi-objective Q-learning algorithm is proposed and trained to select the optimal rescheduling methods that minimize the makespan and the energy consumption variation at the same time. This approach was conducted on benchmark instances to evaluate its performance.

Introduction to Machine Learning and Its Application

2020 ◽  
pp. 262-290
Author(s):  
Ladly Patel ◽  
Kumar Abhishek Gaurav
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Learning Algorithm ◽  
Machine Learning Algorithms ◽  
Human Interaction ◽  
Machine Learning Algorithm ◽  
Past Data ◽  
Applications Of Machine Learning ◽  
Learning Frameworks ◽  
Learning Data

In today's world, a huge amount of data is available. So, all the available data are analyzed to get information, and later this data is used to train the machine learning algorithm. Machine learning is a subpart of artificial intelligence where machines are given training with data and the machine predicts the results. Machine learning is being used in healthcare, image processing, marketing, etc. The aim of machine learning is to reduce the work of the programmer by doing complex coding and decreasing human interaction with systems. The machine learns itself from past data and then predict the desired output. This chapter describes machine learning in brief with different machine learning algorithms with examples and about machine learning frameworks such as tensor flow and Keras. The limitations of machine learning and various applications of machine learning are discussed. This chapter also describes how to identify features in machine learning data.

Sign in / Sign up

Export Citation Format

Share Document