An improved artificial neural network using multi-source data to estimate food temperature during multi-temperature delivery
An improved artificial neural network using multi-source data to estimate food temperature during multi-temperature delivery
复制标题
改进的人工神经网络使用多源数据来估计多温度配送过程中的食品温度
DOI：
10.1016/j.jfoodeng.2023.111518
复制
发表时间：
2023
影响因子：
5.5
通讯作者：
Zou Y
中科院分区：
文献类型：
--
作者：
Zou Y
产品温度偏差是食品冷链管理和监控中的一个重要问题。现有的“基于规则”的监测解决方案仅限于直接使用用于运输的车辆的空气温度数据，这些数据可能与被评估食品的实际温度有很大差异。因此，本研究的重点是开发一种新的人工神经网络模型，以最小的传感器精确估计储存在多温度冷藏运输车辆中的食品的温度。除了识别车内温度外，该模型还接收来自多源数据集的输入，其中包括外部温度、食物初始温度、车门状态、装卸时间等各种信息。研究结果表明，该模型可以在减少运输车辆温度传感器的情况下大大提高估计精度和可靠性。结果表明，在冷藏区和冷冻区，基于该模型的食品温度估计均方根误差可分别降低77%和79%。此外，与反向传播神经网络相比，长短期记忆和深度神经网络可以避免过拟合，并将其估计误差降低约55%和48%。根据敏感性分析，食品温度估计受产品初始温度和门打开累计时间的显著影响。所提出的模型即使在环境突然变化的情况下也能精确跟踪实时食物温度，从而在需要时采取预防措施。
Product temperature deviation is an important concern in the cold chain management and monitoring of food. Existing “rule-based” monitoring solutions are limited to the direct use of air temperature data of the vehicle used for transport, which can differ significantly from the real temperature of the food being assessed. Thus, this study focuses on developing a new artificial neural network model to precisely estimate the temperature of food products that are stored in multi-temperature refrigerated transport vehicles with minimum sensors. In addition to identifying the temperature in the car, the model also receives input from a multi-source dataset that includes various information such as the outside temperature, initial food temperature, door status, loading and unloading times, etc. The result of the study suggests that the proposed model could substantially enhance estimation accuracy and reliability with fewer temperature sensors in the transport vehicle. It was found that the root mean square error of food temperature estimation based on this model could be decreased by 77% and 79% for chilled and frozen zones, respectively. Moreover, long short-term memory and deep neural networks could avoid overfitting and reduce their estimation errors by about 55% and 48%, when compared to a back propagation neural network. Based on sensitivity analysis, food temperature estimation is significantly influenced by the product's initial temperature and the cumulative time that a door is open. The proposed model could precisely track the real-time food temperature even with sudden ambient changes, thus enabling precautions to take place when required.
登录
查看更多内容
基于牛顿冷却定律的冷供应链实时温度预测
DOI：
10.1016/j.dss.2020.113451
发表时间：
2020
期刊：
Decis. Support Syst.
影响因子：
--
作者：
I. Konovalenko;André Ludwig;H. Leopold
通讯作者：
H. Leopold
一种新颖的图像处理方法，用于在线监测虾干燥过程中的视觉纹理
影响因子：
5.5
作者：
S. Hosseinpour;S. Rafiee;M. Aghbashlo;S. Mohtasebi
通讯作者：
S. Mohtasebi
利用物联网技术开发智能粮仓
DOI：
10.2139/ssrn.4141208
发表时间：
2022
期刊：
SSRN Electronic Journal
影响因子：
--
作者：
E.A Ajisegiri;A. Adediran;Timothy A. Adekanye;A. M. Salami;J. Audu
通讯作者：
J. Audu
影响因子：
5.1
作者：
Mercier, Samuel;Uysal, Ismail
通讯作者：
Uysal, Ismail
影响因子：
4.4
作者：
Koutsoumanis, Konstantinos;Pavlis, Athanasios;Xanthiakos, Konstantinos
通讯作者：
Xanthiakos, Konstantinos