储能科学与技术 ›› 2025, Vol. 14 ›› Issue (5): 2010-2012.doi: 10.19799/j.cnki.2095-4239.2025.0419

• 储能系统与工程 • 上一篇    下一篇

大数据支持下的储能系统智能运维模式研究

鄢冰(), 许浒, 李震领   

  1. 中广核风电有限公司,北京 100071
  • 收稿日期:2025-04-29 修回日期:2025-05-10 出版日期:2025-05-28 发布日期:2025-05-21
  • 通讯作者: 鄢冰 E-mail:ggdypr@163.com
  • 作者简介:鄢冰(1987—),男,硕士,高级工程师,研究方向:大数据,E-mail:ggdypr@163.com
  • 基金资助:
    中广核风电有限公司科研项目(020-BJI-F120-2022-042)

Research on intelligent operation and maintenance model of energy storage systems supported by big data

Bing YAN(), XU Hu, Zhenling LI   

  1. Cgn Wind Energy Limited, Beijing 100071, China
  • Received:2025-04-29 Revised:2025-05-10 Online:2025-05-28 Published:2025-05-21
  • Contact: Bing YAN E-mail:ggdypr@163.com

摘要:

随着新能源技术的快速发展和广泛应用,储能系统在电网中的作用也愈加重要。传统的储能系统运维通常依赖人工经验,存在效率低下、响应滞后和故障诊断不准确等问题。本工作提出了一种基于大数据的储能系统智能运维模式,该模式通过集成多种数据源进行信息采集与监控,实现对海量数据的实时收集和深入分析。结合机器学习和深度学习算法对实时数据和历史数据进行融合分析,系统能够识别故障的规律和模式,进而预测设备性能与健康状态。通过这种智能运维模式,可以有效预判潜在故障并提前采取干预措施,从而提升设备的可靠性和运行效率。

关键词: 大数据, 储能系统, 智能运维, 机器学习

Abstract:

With the rapid development and widespread application of new energy technologies, the role of energy storage systems in the power grid has become increasingly important. Traditional energy storage system operation and maintenance usually relies on manual experience, which has problems such as low efficiency, delayed response, and inaccurate fault diagnosis. This paper proposes an intelligent operation and maintenance model for energy storage systems based on big data. This model integrates multiple data sources for information collection and monitoring to achieve real-time collection and in-depth analysis of massive data. Combining machine learning and deep learning algorithms to conduct fusion analysis of real-time data and historical data, the system can identify fault patterns and patterns, and then predict equipment performance and health status. Through this intelligent operation and maintenance model, potential faults can be effectively predicted and intervention measures taken in advance, thereby improving equipment reliability and operating efficiency.

Key words: big data, energy storage systems, intelligent operation and maintenance, machine learning

中图分类号: