多温冷藏车导风槽故障的智能识别

Intelligent Identification for Air Guide Groove Fault of Multi-temperature Refrigerated Truck

针对多温冷藏车配送过程中导风槽(送风槽和回风槽)故障智能识别问题,通过模拟试验采集配送过程中车厢内的环境和食品温度变化,利用人工神经网络和监督学习算法构建一个基于温度数据的导风槽故障智能识别模型,以有效监控多温冷藏车在配送过程中导风槽的工作状态。结果表明,系统在仅采用冷藏区2个厢内温度传感器和1个车厢外温度传感器的布局条件下,应用精细树算法能实现对导风槽三种故障模式(回风槽堵塞、送风槽堵塞、导风槽风机关闭)的精准识别,识别准确度达到99.9%,这为构建多温冷藏车智能监控系统提供了重要支撑。

Aiming at the problem of intelligent identification of air guide groove(air supply groove and air return groove)fault in the operation of multi-temperature refrigerated truck,the environmental and food temperature changes in the compartment during the distribution process are collected through simulation experiments.The artificial neural network and supervised learning algorithm was used to construct an intelligent fault identification model of air guide groove based on temperature data,which could effectively predict the working state of air guide groove during the operation of multi-temperature refrigerated truck.The results show that the system can accurately identify the three fault modes of the air guide groove(the blockage of the return air groove,the blockage of the air supply groove and the closure of the air groove fan)with the accuracy of 99.9% under the condition of only using two temperature sensors inside the compartment and one temperature sensor outside the compartment by using the precision tree algorithm.This study provides an important support for the construction of intelligent monitoring system for multi-temperature refrigerated trucks.