汽车怠速工况NVH性能预测模型研究  

Research on NVH performance prediction model for vehicle idle conditions

作　　者：陈岩 杨晋 裴永生[2] 刘壮 CHEN Yan;YANG Jin;PEI Yongsheng;LIU Zhuang(China Automotive Technology and Research Center Co.,Ltd.,Tianjin 300399,China;School of Vehicle and Energy,Yanshan University,Qinhuangdao 066004,China)

机构地区：[1]中国汽车技术研究中心有限公司,天津300399 [2]燕山大学车辆与能源学院,河北秦皇岛066004

出　　处：《重庆理工大学学报（自然科学）》2022年第11期69-75,共7页Journal of Chongqing University of Technology：Natural Science

基　　金：河北省自然科学基金项目(E2015203002);秦皇岛市科学技术研究与发展计划项目(201701B039)。

摘　　要：针对传统NVH主观评价方法人力成本较高的问题,提出了一种怠速工况下基于阶次和频率分析的整车NVH性能预测模型,可替代NVH评测员进行怠速工况下的车内NVH性能主观评价。采集42辆乘用车怠速工况下的车内噪声和振动信号,基于信号的阶次和频率提取客观评价参量,同时选择专业评测员对42辆乘用车进行NVH性能主观评价。将客观评价参量和主观评价分数汇总建立神经网络数据库,并基于BP神经网络建立整车NVH性能预测模型,预测准确率能够达到90%以上,说明怠速工况下车内的NVH性能与车内声振信号的阶次和频率特征有关,基于BP神经网络建立的预测模型能够准确反映NVH性能预测的非线性问题。Aiming at the high labor cost in traditional NVH subjective evaluation methods,this paper proposes a vehicle NVH performance prediction model based on an order and frequency analysis under idle conditions.This model can replace subjective evaluation of vehicle NVH performance conducted by NVH evaluators under idle conditions.This paper collects noise and vibration signals of 42 passenger cars under idle conditions,and extracts objective evaluation parameters based on the order and frequency of the signals.At the same time,professional evaluators are selected to conduct subjective evaluation of the NVH performance of 42 passenger cars.The objective evaluation parameters and the subjective evaluation scores are aggregated to establish a neural network database,and a vehicle NVH performance prediction model is established based on the BP neural network.The prediction accuracy of the training model can reach more than 90%,indicating the NVH performance in the vehicle under idle conditions is related to the order and frequency characteristics of the acoustic and vibration signals in the vehicle.The prediction model based on the BP neural network can accurately reflect the nonlinear problem of NVH performance prediction.

关 键 词：NVH性能 主观评价 阶次 频率 BP神经网络 

分 类 号：U461.99[机械工程—车辆工程]