基于数据挖掘的发动机频率测试系统设计

Design of Engine Frequency Test System Based on Data Mining

为了提升发动机频率测试系统的检测率准确率,降低其虚警率,基于数据挖掘设计一种新的发动机频率测试系统,系统整体架构分为数据采集板、图形界面、数据处理软件三部分,利用CAN总线连接上位机和下位机,通过传感器、供电电源、采集模块、存储器组成数据采集板;由16通道高速数据采集模块、FPGA、LabIVIEWFPGA开发平台组成图形界面,实现系统硬件设计;分别设计了传感器信号调理电路、A/D转换电路、C8051F040单片机及其CAN通讯电路,通过数据挖掘对发动机频率测试系统频率数据进行聚类,实现测试显示以及测试结果的保存;通过CAN通信程序、HT程序、主机程序组成将测试数据传输至图形显示界面,完成基于数据挖掘的发动机频率测试系统设计;实验结果表明,基于数据挖掘的发动机频率测试系统的数据检测率平均值为89.21%,虚警率平均值为10.24%,有效提高了发动机频率测试的检测率,降低系统虚警率,减小发动机频率测量误报。

In order to improve the detection rate accuracy of the engine frequency test system and reduce its false alarm rate,a new engine frequency test system is designed based on data mining.The overall system architecture is divided into three parts:data acquisition board,graphical interface,and data processing software.The CAN bus connects the upper computer and the lower computer,and forms a data acquisition board through sensors,power supply,acquisition modules,and memory.The graphic interface is composed of 16-channel high-speed data acquisition module,FPGA,and LabIVIEWFPGA development platform to realize the system hardware design.The sensor signal conditioning circuit,A/D conversion circuit,C8051F040 single-chip microcomputer and its CAN communication circuit are designed separately,and the frequency data of the engine frequency test system is clustered through data mining to realize test display and save test results.The test data is transmitted to the graphic display interface through the CAN communication program,HT program,and host program to complete the design of the engine frequency test system based on data mining.Experimental results show that the average data detection rate of the engine frequency test system based on data mining is 89.21%,and the average false alarm rate is 10.24%,which effectively improves the detection rate of the engine frequency test,reduces the system false alarm rate,and reduces the engine Frequency measurement false alarm.