Early detection of failures from vehicle equipment data using K-means clustering design. (October 2022)

• Record Type: Journal Article
• Authors: Mohamed, Ehsan; Celik, Tahir
• Is Part Of: Computers & electrical engineering. Volume 103(2022)
• Publication Date: 2022-10
• Subjects: Equipment management -- K-means algorithm -- WEKA application -- Accuracy density factor (ADF) -- Decision support system -- Data warehouse; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108351
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Through data mining from vehicle construction equipment, the paper presents a unique approach to the early diagnosis of machinery failures. We used an effective K-means clustering algorithm to discover inconsistencies in field data. Data is stored in a warehouse using the Structural Query Language (SQL). The vehicle equipment data is processed using the K-means algorithm. During K-means clustering, we applied the Waikato Environment for Knowledge Analysis (WEKA) application dataset to represent the correct information, which enables risk detection based on the stored warehouse. The K-means clustering performs early defects identification in a dataset of construction equipment supplied by a Libyan organization. The clustering mechanism is based on the Euclidean distance, which is used to calculate the correctness of files in a large dataset. The tests make use of real-world equipment datasheets spanning five years. The results show that the K-means algorithm produces more accurate results than other methods.