Computational intelligence for preventive maintenance of power transformers

Wong, Shen Yuong; Ye, Xiaofeng; Guo, Fengkai; Goh, Hui Hwang

doi:10.1016/j.asoc.2021.108129

Cited by 19 publications

(6 citation statements)

References 198 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the status data collection was realized according to the IEC 61850-9-2 communication protocol. The IEC 61850-9-2 protocol provides a flexible communication mechanism and data model that supports a variety of transmission media and network architectures, such as fiber optics and Ethernet [5]. By using this protocol, the status data of the AC power supply in the substation can be obtained quickly and safely.…”

Section: Synchronous Sampling Of Ac Power Data In Substationmentioning

confidence: 99%

Research on the fault diagnosis method of AC power supply in substations based on a synchronous digital sampling technology

Fan,

Li,

Wang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In order to improve the accuracy and efficiency of AC power supply fault diagnosis in substations, a fault diagnosis method of AC power supply in substations based on synchronous digital sampling technology is proposed and designed in this study. Based on the IEC 61850-9-2 communication protocol, the same sampling of the status data of the substation AC power supply is realized first. Then, in order to improve the fault diagnosis effect, the data is pre-processed such as de-noising and de-redundancy. Finally, the substation AC power supply fault diagnosis is carried out based on Dempster/Shafer (D-S). The experimental results show that for different types of faults, the diagnosis accuracy of the proposed method is higher than 95.5%, and the diagnosis time is less than 1.31 ms.

show abstract

Section: Synchronous Sampling Of Ac Power Data In Substationmentioning

confidence: 99%

Research on the fault diagnosis method of AC power supply in substations based on a synchronous digital sampling technology

Fan,

Li,

Wang

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…This learning has helped to mitigate the errors in communication and sensor malfunction by addressing the missing data obtained from the sensor, which ensures a reliable predictive model [14]. Furthermore, ML models provide an effective technique for detecting, diagnosing and predicting transformer insulation status than the traditional approach [15]. Therefore, utilizing ML techniques for predicting the DP correlated parameters will offer a more cost-effective and readily accessible method for monitoring the health condition of transformers' paper insulation.…”

Section: Introductionmentioning

confidence: 99%

Analyzing Transformer Insulation Paper Prognostics and Health Management: A Modeling Framework Perspective

Adekunle,

Fofana,

Picher

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In the era of Industry 4.0, digital transformation has spurred the swift advancement of technologies, including intelligent predictive maintenance scheduling, prognostics and health management. The accurate prediction of remaining useful life plays a crucial role in these technologies as it extends power equipment's safe operational duration and decreases the maintenance costs associated with unforeseen shutdowns. Also, the increased accessibility of data for monitoring system conditions has paved the way for the more immense adoption of machine learning models in prognostics and health management for power transformers. At the moment, with the ever-increasing demand for electricity, there is a corresponding increase in the degradation processes of power transformers. Transformers insulation system and more importantly, the paper insulation happens to be the principal part where the degradation is prominent. Therefore, an accurate prediction of the insulating paper condition through its degree of polymerization is required to guarantee the reliability of power transformers. In this regard, the predictions, reliability, and health monitoring of this power equipment can be actualized by modeling the degradation of transformer insulation paper through several machine learning frameworks. In this view, this review paper has been drafted not only to serve as a guide for researchers interested in the fields of transformer insulation system fault prognosis but also to offer insights into potential research directions as existing literature in modeling and evaluating transformer paper insulation is presented.INDEX TERMS Insulating paper, ageing, degree of polymerization, prognostics and health management, machine learning model.

show abstract

“…Prior research in operations management (Awan et al 2018 ) and sustainability (Huang and Badurdeen 2018 ; Anser et al 2020 ) examined scenarios where factors and variables correlation were complex, requiring sophisticated analysis methods to identify phenomenon dynamics. In regards to preventive maintenance analysis and decisions, scholars and practitioners discuss the importance of considering the variable trade-offs and correlation, such as reliability and cost (Shi et al 2022 ), availability, economic losses, and environment impacts (Wong et al 2022 ), efficient production, production system complexity and performance (Su et al 2022 ), reliability and optimization of production scheduling (An et al 2022 ).…”

Section: Introductionmentioning

confidence: 99%

Straightening machine preventive maintenance intervention plan based on AHP: a case study in a steel company in Brazil

et al. 2023

View full text Add to dashboard Cite

Equipment failure and production shortfalls can cause significant impacts on companies. Preventive maintenance can potentially increase equipment reliability and availability, helping companies achieve their corporate goals while reducing operation and maintenance costs. However, determining the optimal interval between maintenance interventions involves balancing various factors such as maintenance costs, equipment availability, risk of failures, and the need for corrective maintenance, as well as potential operational and financial impacts. Under this context, this paper aims to define the interval between preventive maintenance interventions for a key production equipment in a steel company located in Southeast region of Brazil. Upon documental analysis and interviews with experts, an AHP was applied to hierarchize the maintenance periodicity, based on the following criteria: part replacement based on service life, downtime hours for preventive maintenance, equipment reliability, and cost of materials and labour. A biweekly preventive maintenance periodicity was identified as the most adequate for the analysed device. An implementation plan was approved and preliminary results indicate no availability deterioration, while maintenance costs are below historical average.

show abstract

Computational intelligence for preventive maintenance of power transformers

Cited by 19 publications

References 198 publications

Research on the fault diagnosis method of AC power supply in substations based on a synchronous digital sampling technology

Research on the fault diagnosis method of AC power supply in substations based on a synchronous digital sampling technology

Analyzing Transformer Insulation Paper Prognostics and Health Management: A Modeling Framework Perspective

Straightening machine preventive maintenance intervention plan based on AHP: a case study in a steel company in Brazil

Contact Info

Product

Resources

About