变压器油色谱在线监测周期动态调整策略研究

发布时间：2018-04-18 22:07

本文选题：在线监测周期 + 相空间重构　；参考：《中国电机工程学报》2014年09期

【摘要】：变压器油色谱在线监测装置的运行成本与其监测周期密切相关,如何根据设备的运行情况调整监测周期,在保证运行效率的同时兼顾经济性,是该文研究的核心问题,在此背景下,提出一种动态调整在线监测周期的方法。首先在理论论述监测周期影响油色谱在线监测装置寿命的基础上,对平稳过程短时监测周期的时间序列数据进行相空间重构,得到最优时延和嵌入维数,并以最优时延作为相对最优监测周期。然后基于引力搜索优化方法和快速相关向量机建立气体浓度自适应预测模型,并设定预警标准,根据预测结果以及其他监测设备监测结果保持或缩短监测周期。仿真计算结果证明:所提气体浓度预测模型具有良好的预测精度;相比较依据产气率注意值,基于气体浓度预测技术的预警方法更适用于短时间间隔、含量较低的气体浓度数据;相比气体含量注意值方法,所提方法能够有效地发现可能出现的异常情况。文中研究提供了一种在不影响监测有效性的前提下,实现油色谱在线监测装置经济效益更大化的可行方法。
[Abstract]:The operating cost of on-line monitoring device for transformer oil chromatography is closely related to its monitoring cycle. How to adjust the monitoring period according to the operation condition of the equipment, and how to ensure the operation efficiency and give consideration to the economy are the core problems studied in this paper.Under this background, a method of dynamically adjusting the period of online monitoring is proposed.Firstly, on the basis of discussing the influence of monitoring period on the life of oil chromatographic on-line monitoring device, the phase space reconstruction of the time series data of the short time monitoring period of stationary process is carried out, and the optimal delay and embedding dimension are obtained.The optimal time delay is taken as the relative optimal monitoring period.Then an adaptive prediction model of gas concentration is established based on gravity search optimization method and fast correlation vector machine, and an early warning standard is set up to maintain or shorten the monitoring period according to the prediction results and the monitoring results of other monitoring equipment.The simulation results show that the proposed gas concentration prediction model has good prediction accuracy, compared with the attention value of gas production rate, the early warning method based on gas concentration prediction technology is more suitable for short time intervals.Compared with the method of attention value of gas content, the proposed method can effectively detect possible anomalies.In this paper, a feasible method to realize greater economic benefit of on-line oil chromatographic monitoring device without affecting the effectiveness of monitoring is proposed.
【作者单位】：电网智能化调度与控制教育部重点实验室(山东大学);国网技术学院;
【分类号】：TM41

【参考文献】