本文選題：在線監(jiān)測周期 + 相空間重構(gòu)　； 參考：《中國電機(jī)工程學(xué)報(bào)》2014年09期

【摘要】：變壓器油色譜在線監(jiān)測裝置的運(yùn)行成本與其監(jiān)測周期密切相關(guān),如何根據(jù)設(shè)備的運(yùn)行情況調(diào)整監(jiān)測周期,在保證運(yùn)行效率的同時(shí)兼顧經(jīng)濟(jì)性,是該文研究的核心問題,在此背景下,提出一種動(dòng)態(tài)調(diào)整在線監(jiān)測周期的方法。首先在理論論述監(jiān)測周期影響油色譜在線監(jiān)測裝置壽命的基礎(chǔ)上,對平穩(wěn)過程短時(shí)監(jiān)測周期的時(shí)間序列數(shù)據(jù)進(jìn)行相空間重構(gòu),得到最優(yōu)時(shí)延和嵌入維數(shù),并以最優(yōu)時(shí)延作為相對最優(yōu)監(jiān)測周期。然后基于引力搜索優(yōu)化方法和快速相關(guān)向量機(jī)建立氣體濃度自適應(yīng)預(yù)測模型,并設(shè)定預(yù)警標(biāo)準(zhǔn),根據(jù)預(yù)測結(jié)果以及其他監(jiān)測設(shè)備監(jiān)測結(jié)果保持或縮短監(jiān)測周期。仿真計(jì)算結(jié)果證明:所提氣體濃度預(yù)測模型具有良好的預(yù)測精度;相比較依據(jù)產(chǎn)氣率注意值,基于氣體濃度預(yù)測技術(shù)的預(yù)警方法更適用于短時(shí)間間隔、含量較低的氣體濃度數(shù)據(jù);相比氣體含量注意值方法,所提方法能夠有效地發(fā)現(xiàn)可能出現(xiàn)的異常情況。文中研究提供了一種在不影響監(jiān)測有效性的前提下,實(shí)現(xiàn)油色譜在線監(jiān)測裝置經(jīng)濟(jì)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.
【作者單位】： 電網(wǎng)智能化調(diào)度與控制教育部重點(diǎn)實(shí)驗(yàn)室(山東大學(xué));國網(wǎng)技術(shù)學(xué)院;
【分類號】：TM41

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 趙彤;李慶民;陳平;;OLTC振動(dòng)信號特征提取的動(dòng)力學(xué)分析方法[J];電工技術(shù)學(xué)報(bào);2007年01期

2 肖燕彩;朱衡君;陳秀海;;用灰色多變量模型預(yù)測變壓器油中溶解的氣體濃度[J];電力系統(tǒng)自動(dòng)化;2006年13期

3 朱永利,吳立增,李雪玉;貝葉斯分類器與粗糙集相結(jié)合的變壓器綜合故障診斷[J];中國電機(jī)工程學(xué)報(bào);2005年10期

4 孫丹;孟o，

本文編號：1770278