發(fā)布時(shí)間：2018-04-30 05:20

  本文選題：球磨機(jī)料位 + 軟測(cè)量　； 參考：《中北大學(xué)學(xué)報(bào)(自然科學(xué)版)》2017年05期

【摘要】：針對(duì)采用傳統(tǒng)極限學(xué)習(xí)機(jī)在球磨機(jī)料位軟測(cè)量建模過程中,存在魯棒性差,預(yù)測(cè)精度不高等缺點(diǎn),提出一種基于最優(yōu)定界橢球(Optimal Bounding Ellipsoid,OBE)改進(jìn)極限學(xué)習(xí)機(jī)(Extreme Learning Machine,ELM)的建模方法.該方法以球磨機(jī)振動(dòng)信號(hào)為觀測(cè)變量,采用偏最小二乘法提取有效特征,將提取到的有效特征輸入到ELM中進(jìn)行模型訓(xùn)練,并利用OBE在模型誤差未知但有界的條件下,對(duì)網(wǎng)絡(luò)權(quán)值進(jìn)行約束優(yōu)化.通過小型球磨機(jī)實(shí)驗(yàn)表明,在對(duì)球磨機(jī)料位進(jìn)行回歸預(yù)測(cè)時(shí),該方法的評(píng)價(jià)指標(biāo)與其它方法相比有所提高,測(cè)量結(jié)果的箱線圖也直觀展示該方法具有更好的魯棒性.
[Abstract]:In view of the disadvantages of the traditional extreme learning machine in the soft sensor modeling of ball mill level, such as poor robustness and low prediction accuracy, a modeling method based on optimal bounded ellipsoid Bounding optimal Bounding Ellipsoid OBEBE-based improved extreme Learning Machine (ELM) is proposed. In this method, the vibration signal of ball mill is taken as the observation variable, the effective feature is extracted by partial least square method, the extracted effective feature is input into ELM for model training, and the model error is unknown but bounded by OBE. The network weights are optimized with constraints. The experimental results of small ball mill show that the evaluation index of this method is improved compared with other methods, and the box diagram of measurement results shows that the method has better robustness.
【作者單位】： 太原理工大學(xué)信息工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(61450011) 山西省煤基重點(diǎn)科技攻關(guān)項(xiàng)目(MD2014-07) 山西省自然科學(xué)基金資助項(xiàng)目(20150110052)
【分類號(hào)】：TH69

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 張德玉;;裝煤車料位控制器指示失靈的理論原因和應(yīng)采取的措施[J];鞍鋼技術(shù);1990年05期

2 于秉杰;圓盤給料機(jī)料倉最低料位的確定[J];機(jī)械工程師;1994年03期

，

本文編號(hào)：1823250