首頁(yè) 資訊基于RUN

基于RUN

來(lái)源：泰然健康網(wǎng) 時(shí)間：2024年12月16日 06:19

摘要：

實(shí)車動(dòng)力電池的健康狀態(tài)(state of health，SOH)評(píng)估存在數(shù)據(jù)質(zhì)量差、工況不統(tǒng)一、數(shù)據(jù)利用率低等問(wèn)題，本文面向階梯倍率充電工況構(gòu)建多源特征提取及SOH估計(jì)模型。首先，通過(guò)數(shù)據(jù)清洗、切割、填充，獲取獨(dú)立的充電片段；其次，基于不同電流階段計(jì)算容量，實(shí)現(xiàn)原始數(shù)據(jù)利用率達(dá)96.9%，并與單獨(dú)限定SOC范圍計(jì)算容量的方法相比，誤差降低48.1%以上；然后，從當(dāng)前工況、歷史累積兩個(gè)維度提取多個(gè)健康因子，對(duì)于當(dāng)前工況特征值，通過(guò)灰色關(guān)聯(lián)度及干擾性隨機(jī)森林重要度分析雙重篩選。對(duì)于歷史累積特征值，利用Spearson相關(guān)性分析和核主成分分析方法(kernel principal component analysis，KPCA)降低信息冗余；最后，對(duì)門(mén)控循環(huán)單元網(wǎng)絡(luò)模型(gated recurrent unit，GRU)引入注意力機(jī)制和龍格庫(kù)塔優(yōu)化算法(Runge Kutta optimizer，RUN)，建立RUN-GRU-attention模型，基于實(shí)車運(yùn)行數(shù)據(jù)集與現(xiàn)有5種模型進(jìn)行對(duì)比，實(shí)驗(yàn)結(jié)果表明，無(wú)論是包含單階段還是多階段電流的測(cè)試樣本，優(yōu)化模型的估計(jì)精度更佳，誤差不高于0.0086，并且隨著充電循環(huán)次數(shù)增加表現(xiàn)出良好的誤差收斂性，可有效預(yù)測(cè)SOH波動(dòng)趨勢(shì)。

關(guān)鍵詞: 實(shí)車動(dòng)力電池, 階梯倍率充電, 健康狀態(tài)估計(jì), 多源特征提取, 龍格庫(kù)塔優(yōu)化算法, 機(jī)器學(xué)習(xí)

Abstract:

The evaluation of the state of health (SOH) for real-vehicle batteries is challenging owing to poor data quality, inconsistent operating conditions, and limited data utilization. This paper presents a multisource feature extraction and SOH estimation model specifically designed for step-rate charging conditions. First, charging segments are obtained through data cleaning, segmenting, and filling processes. Next, capacity is calculated using data from various current stages, achieving a raw data utilization rate of 96.9%. Compared to methods that calculate capacity within a restricted state of charge (SOC) range, this approach reduces error by over 48.1%. Finally, health factors are extracted based on current operating conditions and historical data accumulation. For current operating condition feature values, dual screening is performed using grey correlation analysis and random forest importance analysis to manage interference. For historical cumulative feature values, Spearman correlation analysis and Kernel Principal Component Analysis (KPCA) are employed to reduce information redundancy. Finally, an attention mechanism and Runge-Kutta optimizer (RUN) are integrated into the Gated Recurrent Unit (GRU) network model. The performance of this optimized model is then compared with five existing models using an actual vehicle operation dataset. The experimental results demonstrate that the optimized model achieves superior estimation accuracy, with an error margin of no more than 0.0086, regardless of whether the test samples include single-stage or multi-stage currents. Additionally, the model shows excellent error convergence as the number of charging cycles increases and effectively predicts the trend of SOH fluctuations.

Key words: real-vehicle battery, step rate charging, SOH estimation, multisource features extraction, Runge Kutta optimization algorithm, machine learning

中圖分類號(hào):

TM 911

網(wǎng)址: 基于RUN http://www.u1s5d6.cn/newsview561902.html