基于PCA-BP神经网络的装甲车辆柴油机状态评估  

Condition Evaluation for Armored Vehicle Diesel Engine Based on PCA and BP Nerual Network

作　　者：曹艳华[1] 陈春良[1] 齐蕴光[1] 宋敬华[1] 

机构地区：[1]装甲兵工程学院,北京100072

出　　处：《计算机测量与控制》2012年第7期1892-1894,共3页Computer Measurement &Control

摘　　要：针对装甲车辆柴油机摩托小时不能真实反映实际技术状况的问题,通过提取气缸压缩压力、加速时间、减速时间、供油提前角、振动能量和平均燃油流量等状态参数,运用主成分分析和BP神经网络相结合的方法构建了一种柴油机状态评估模型;该模型首先利用主成分分析方法将多个参数简化为两个综合参数,并根据综合参数的散点图对柴油机的状态进行初步划分,得到BP神经网络的训练数据;最后通过建立BP神经网络进行状态评估;评估结果表明,该模型准确度高,具有较好的应用和推广价值。Abstract： The motor hours of armored vehicle can ：not truly reflect technical condition of Diesel Engine. Aiming at this problem and choosing appropriate condition parameters which are cylinder compression pressures, acceleration time, deceleration time, average fuel flux, supply fuel advance angle, oscillation energy and so on, a condition evaluation model is devloped by combining PCA and BP nerual network methods. The model turns sveral parameters into two integrated parameters. The technical condition of Diesel Engine can be fuzzily parti- tioned by scatter plot of the two integrated parameters. And the training data for BP nerual network can be got. Finally, the BP nerual net- work will be built to evaluate conditions. The application shows that the model runs accurately. And it is practical and worthy of using a- broad.

关 键 词：装甲车辆 柴油机 主成分分析 BP神经网络 状态评估 

分 类 号：TK428[动力工程及工程热物理—动力机械及工程]