Title: A hierarchical outlier detection method for spare parts transaction

Authors: Haiming Zeng; Hongzhi Xie; Kai Yuan; Biwei Liu; Xiaolin Deng; Li Wang

Addresses: National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060, China ' Spare Parts Center, China Nuclear Power Operations Co., Ltd, 518124, China ' Spare Parts Center, China Nuclear Power Operations Co., Ltd, 518124, China ' National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060, China ' Spare Parts Center, China Nuclear Power Operations Co., Ltd, 518124, China ' National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, 518060, China

Abstract: In nuclear power production, seamless equipment maintenance is integral, significantly achieved through spare parts transactions. Yet, abnormal transaction data can obstruct operational efficiency. Traditional anomaly detection methods, often subjective and non-scalable, struggle to handle these abnormalities effectively. Addressing these shortcomings, this paper presents a Hierarchical Outlier Detection Method, specifically for nuclear power spare parts transaction data. This method integrates data cleansing, probability statistics, and model recognition modules, offering an innovative, robust approach to anomaly detection. Leveraging statistical and neural network approaches, our method exhibits superior adaptability, computational efficiency, and detection performance, substantiated through a real-world dataset of nuclear power plant spare parts transaction records. Its versatile design suggests potential applicability to other industrial scenarios.

Keywords: anomaly detection; spare parts transactions; data cleansing; probability statistics; model recognition.

DOI: 10.1504/IJSSC.2023.133245

International Journal of Space-Based and Situated Computing, 2023 Vol.9 No.3, pp.173 - 181

Received: 30 May 2023
Accepted: 06 Jun 2023
Published online: 03 Sep 2023 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article