Identification of abnormal events by data monitoring: Application to complex systems

Bect, Pierre; Simeu-Abazi, Zineb; Maisonneuve, Pierre-Loic

doi:10.1016/j.compind.2014.12.008

Cited by 9 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, Bect, Simeu-Abazi, and Maisonneuve (2015) proposed an approach based on data mining techniques to identify anomalies from the flight data of a helicopter including 1,224,000 records and 136 parameters. In this approach, the dimensions of the data were first reduced by PCA, and then clustering was performed by k-means.…”

Section: Hybrid Methodsmentioning

confidence: 99%

An integrated approach for aircraft turbofan engine fault detection based on data mining techniques

et al. 2019

View full text Add to dashboard Cite

The present study proposes an algorithm for fault detection in terms of condition‐based maintenance with data mining techniques. The proposed algorithm is applied on an aircraft turbofan engine using flight data and consists of two main sections. In the first section, the relationship between engine exhaust gas temperature (EGT) as the main engine health monitoring criterion and other operational and environmental parameters of the engine was modelled using the data‐driven models. In the second section, a data set including EGT residuals, that is, the difference between the actual EGT of the system and the EGT estimated by the developed model in the health conditions of the engine, was created. Finally, faults occurring in each flight were detected based on the identification of abnormal events by a one‐class support vector machine trained by the health condition EGT residual data set. The results indicated that the proposed algorithm was an effective approach for inspecting aircraft engine conditions and detecting faults, with no need for technical knowledge on the interior characteristics of the aircraft engine.

show abstract

Section: Hybrid Methodsmentioning

confidence: 99%

An integrated approach for aircraft turbofan engine fault detection based on data mining techniques

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Bect et al [51] adopted several data mining methods, such as PCA, k-means, and canonical discriminant analysis, to detect abnormal events for helicopters. Flath and Stein [11] developed a defect prediction system for a manufacturing environment by using data mining technology.…”

Section: B Applying Big Data and Data Mining To Enhance Product Yieldmentioning

confidence: 99%

A Data-Driven Approach for Identifying Possible Manufacturing Processes and Production Parameters That Cause Product Defects: A Thin-Film Filter Company Case Study

2020

View full text Add to dashboard Cite

A semiconductor or photoelectric manufacturer faces a more competitive market with small quantities of many products. These products require hundreds of processes for production, thereby generating huge manufacturing data. With the help of the Internet of Things (IoT) technology, the manufacturer can collect manufacturing process data in a timely manner. Due to the massive quantities of manufacturing process data, it has become difficult for manufacturers to determine the causes of product defects, by which machine, and by what manufacturing process (or recipe) parameters. This research proposes a six-step datadriven solution to this problem. The chi-square test of independence, the Apriori algorithm, and the decision tree method identify the process that is generating the defective products and extract rules to identify the lot identification of product defects and their associated manufacturing process parameters. An empirical study was conducted at an optical thin-film filter (TFF) company in Taiwan. Based on the data of the optical TFF production lines, the coating process was identified as the source of the defective products, and the extracted rules were validated and implemented. The product defect rate decreased from 20% to 5%. Hence, the proposed data-driven solution was found to be capable of helping manufacturers enhance their product yield. INDEX TERMS Data-driven, data mining, process improvement, association rule mining, decision tree, thin-film filter (TFF).

show abstract

“…High competition on the global market makes high flexibility and efficiency of the producer the key to success. Meeting the changing needs of customers in the long term, the constant need to keep production at the highest level, and to deliver the highest quality products to the market is only possible with business strategies based on modern technologies [ 9 ]. More efficient new generation machines are becoming a key element of competitive advantage for manufacturing plants.…”

Section: Introductionmentioning

confidence: 99%

Controlling an Industrial Robot Using a Graphic Tablet in Offline and Online Mode

Kaczmarek

Lotys²,

Borys

et al. 2021

Sensors

View full text Add to dashboard Cite

The article presents the possibility of using a graphics tablet to control an industrial robot. The paper presents elements of software development for offline and online control of a robot. The program for the graphic tablet and the operator interface was developed in C# language in Visual Studio environment, while the program controlling the industrial robot was developed in RAPID language in the RobotStudio environment. Thanks to the development of a digital twin of the real robotic workstation, tests were carried out on the correct functioning of the application in offline mode (without using the real robot). The obtained results were verified in online mode (on a real production station). The developed computer programmes have a modular structure, which makes it possible to easily adapt them to one’s needs. The application allows for changing the parameters of the robot and the parameters of the path drawing. Tests were carried out on the influence of the sampling frequency and the tool diameter on the quality of the reconstructed trajectory of the industrial robot. The results confirmed the correctness of the application. Thanks to the new method of robot programming, it is possible to quickly modify the path by the operator, without the knowledge of robot programming languages. Further research will focus on analyzing the influence of screen resolution and layout scale on the accuracy of trajectory generation.

show abstract

Identification of abnormal events by data monitoring: Application to complex systems

Cited by 9 publications

References 11 publications

An integrated approach for aircraft turbofan engine fault detection based on data mining techniques

An integrated approach for aircraft turbofan engine fault detection based on data mining techniques

A Data-Driven Approach for Identifying Possible Manufacturing Processes and Production Parameters That Cause Product Defects: A Thin-Film Filter Company Case Study

Controlling an Industrial Robot Using a Graphic Tablet in Offline and Online Mode

Contact Info

Product

Resources

About