基于IFWA-PNN的變壓器故障診斷研究

打開文本圖片集

摘  要：為克服概率神經(jīng)網(wǎng)絡(luò)在判斷變壓器的故障類型方面的不足，文章采用改進(jìn)的煙花算法優(yōu)化概率神經(jīng)網(wǎng)絡(luò)（IFWA-PNN）的平滑因子。實(shí)例分析表明，提出的變壓器故障診斷模型診斷準(zhǔn)確率達(dá)到91.7%，相比傳統(tǒng)的支持向量機(jī)診斷模型有較大提升，以此證明故障診斷模型的有效性和實(shí)用性。

關(guān)鍵詞：概率神經(jīng)網(wǎng)絡(luò);平滑因子;改進(jìn)煙花算法;變壓器;故障診斷

中圖分類號(hào)：TP3      文獻(xiàn)標(biāo)志碼：A          文章編號(hào)：2095-2945（2022）06-0086-04

Abstract： In order to overcome the deficiency of probabilistic neural network in judging the fault type of transformer， this paper adopts the smoothing factor of an improved fireworks algorithm optimized probabilistic neural network（IFWA-PNN）. The analysis of examples shows that the diagnosis accuracy of the proposed transformer fault diagnosis model reaches 91.7%， which is greatly improved compared with the traditional support vector machine diagnosis model. This proves the effectiveness and practicability of the fault diagnosis model.

Keywords： probabilistic neural network; smoothing factor; improved fireworks algorithm; transformer; fault diagnosis

變壓器是電力系統(tǒng)中的關(guān)鍵設(shè)備[1]。（剩余4343字）