本文關(guān)鍵詞：基于改進灰色神經(jīng)網(wǎng)絡的液壓泵壽命預測，由筆耕文化傳播整理發(fā)布。

基于改進灰色神經(jīng)網(wǎng)絡的液壓泵壽命預測

Life Prediction of Hydraulic Pump Based on an Improved Grey Neural Network

[1] [2] [3] [4]

He Qingfei Chen Guiming Chen Xiaohu Yao Chunjiang （ The Second Artillery Engineering College, Xi＇ an, 710025）

第二炮兵工程學院,西安,710025

文章摘要：改進了GM（1，1）模型，提高了其精度和適應范圍；將改進的GM（1，1）模型與神經(jīng)網(wǎng)絡預測模型相結(jié)合來構(gòu)建灰色神經(jīng)網(wǎng)絡組合預測模型；提出了基于支持向量機的液壓泵壽命特征啟發(fā)式搜索策略，以液壓泵壽命特征參數(shù)特征集的交叉驗證錯誤率為評價指標，從液壓泵的特征參數(shù)（振動、壓力、流量、溫度、油液信息等）中選取壽命特征因子；運用小波閾值降噪法進行降噪處理，提取典型的小波包能量特征作為模型的輸入。以齒輪泵為例，將改進的灰色神經(jīng)網(wǎng)絡預測模型與原始GM（1，1）模型和改進GM（1，1）模型比較可知，灰色神經(jīng)網(wǎng)絡預測模型預測精度最高，，達到98．42％。

Abstr：A life prediction method of hydraulic pump based on improved grey neural network was presented for the shortcomings of low precision forecasting model. Firstly, a new model was proposed based on the combination of the initial condition and the background value to improve the precision of the grey forecasting model. A SVM- based hydraulic pump lifetime feature heuristic elimination strategy was put forward, and the evaluation criterion of cross—validating error rate was adopted to select life feature form hydraulic pump features（vibration, pressure, flux, temperature, oil, and so on）. Feature signals were de—noised by wavelet threshold de—noising method. Then representative energy features were selected by wavelet pocket energy spectrum algorithm. Taking gear pump as an example, the improved grey neural network model has higher precision than original GM（1,1） model and improved GM（1,1） model.

文章關(guān)鍵詞：

Keyword：:hydraulic pump life prediction GM （1,1） model neural network support vectormachine（SVM）

課題項目：國防預研基金資助項目（9140A27020309JB4701）;第二炮兵工程學院科技創(chuàng)新基金資助項目（XY2010JJB38）

  本文關(guān)鍵詞：基于改進灰色神經(jīng)網(wǎng)絡的液壓泵壽命預測，由筆耕文化傳播整理發(fā)布。