随着我国冷藏运输设备的快速增长，货物运输安全性和新鲜度要求的提高，冷链运输监测系统成为冷藏运输设备的必配系统。现有的冷链运输监测系统主要监测运输车辆位置，信息采集单一，信息传输采用短信息方式，信息处理简单，难以满足现代冷链运输监测的需要。所以利用现代信息技术研究和开发一种信息采集全面、信息传输及时、信息处理先进的冷链运输监测系统具有重要的作用。

针对当前城市生鲜农产品冷链运输环境难以得到有效保证这一问题，设计了一种冷链运输监测系统，对数据采集、数据传输和数据处理技术进行研究，从车载监测终端、监测中心两个层面对监测系统进行设计。车载监测终端通过低功耗处理器连接多种传感器以及定位模块采集冷链车厢内的环境参数和车辆位置信息，通过NB-IoT技术进行数据传输。监测中心的设计主要利用了Node.js、HTML、CSS、JavaScript和数据库技术，包含后端服务器、数据库和前端管理平台三大部分，实现对数据的接收处理、存储和显示。此外，在系统功能实现的基础上，为了实现对车厢内环境数据的预测，本文利用两种预测算法：自回归平均算法和BP神经网络算法，构建预测模型，并通过实验仿真对比两种算法的预测性能，实验结果表明，BP神经网络的预测模型更接近真实值，其平均绝对误差、均方根误差、相关系数分别为0.1353、0.1660、0.9667，具有更好的预测效果。

最后对冷链运输监测系统进行功能测试和功耗测试，测试结果表明，该系统能够实现冷链车厢环境数据的采集与传输，数据传输时间均在3s以内，具有良好的实时性。监测中心对车厢内温度、湿度、二氧化碳浓度、气压数据变化进行监测，并能够完成数据图表显示、用户注册登录、历史记录查询、地图定位等预期功能。

With the rapid growth of refrigerated transportation equipment in our country and the improvement of cargo transportation safety and freshness requirements, the cold chain transportation monitoring system has become a necessary system for refrigerated transportation equipment. The existing cold chain transportation monitoring system mainly monitors the location of transportation vehicles, with single information collection, short message method for information transmission, simple information processing, and it is difficult to meet the needs of modern cold chain transportation monitoring. Therefore, the use of modern information technology to research and develop a cold chain transportation monitoring system with comprehensive information collection, timely information transmission, and advanced information processing has an important role.

Aiming at the problem that the cold chain transportation environment of urban fresh agricultural products is difficult to be effectively guaranteed, a cold chain transportation monitoring system is designed. The data acquisition, transmission and processing technology are researched, and the monitoring system is designed from the two levels of on-board monitoring terminal and monitoring center. The on-board monitoring terminal is connected to a variety of sensors and positioning modules through a low-power processor to collect environmental parameters and vehicle location information in the cold chain compartment, and data transmission is carried out through the NB-IoT module.The design of the monitoring center mainly uses Node.js, HTML, CSS, JavaScript and database technology, including three parts: back-end server, database and front-end management platform to realize the receiving, processing, storage and display of data. In addition, based on the realization of system functions, in order to realize the prediction of the environment data in the cabin, this paper uses two prediction algorithms: ARMA autoregressive average algorithm and BP neural network algorithm to construct a prediction model. The prediction performance of the two algorithms is compared through experimental simulation. The experimental results show that the prediction model of BP neural network is closer to the real value, and its mean absolute error, root mean square error, and correlation coefficient are 0.1353, 0.1660, and 0.9667 respectively. It shows that BP neural network has better prediction effect.

Finally, the cold chain transportation monitoring system is tested for function and power consumption. The test results show that the system can realize the collection and transmission of environmental data of cold chain carriages. The data transmission time is within 3s, and it has good real-time performance. The monitoring center monitors the temperature, humidity, carbon dioxide concentration, and air pressure data changes in the cabin. The expected functions such as data chart display, user registration and login, historical record query, and map positioning have been completed.

[1]Zhao H, Liu S, Tian C, et al. An overview of current status of cold chain in China[J]. International Journal of Refrigeration, 2018, 88: 483-495.

[2]Badia-Melis R, Mc Carthy U, Ruiz-Garcia L, et al. New trends in cold chain monitoring applications-A review[J]. Food Control, 2018, 86: 170-182.

[3]Xiao X, He Q, Li Z, et al. Improving traceability and transparency of table grapes cold chain logistics by integrating WSN and correlation analysis[J]. Food Control, 2017, 73: 1556-1563.

[4]Sultania A K, Mahfoudhi F, Famaey J. Real-Time demand response using NB-IoT[J]. IEEE Internet of Things Journal, 2020, 7(12): 11863-11872.

[5]Ashok A, Brison M, LeTallec Y. Improving cold chain systems: Challenges and solutions[J]. Vaccine, 2017, 35(17): 2217-2223.

[6]Leng K, Jin L, Shi W, et al. Research on agricultural products supply chain inspection system based on internet of things[J]. Cluster Computing, 2019, 22(4): 8919-8927.

[7]Ou C M, Tu J F. The WSN and 3G/NFC embedded into IoV (Internet-of-Vehicle) fulfill cold chain logistics[J]. Microsystem Technologies, 2018, 24(10): 3977-3983.

[8]Urbano O, Perles A, Pedraza C, et al. Cost-effective implementation of a temperature traceability system based on smart RFID Tags and IoT services[J]. Sensors, 2020, 20(4): 1-19.

[9]齐林, 韩玉冰, 张小栓, 等. 基于WSN的水产品冷链物流实时监测系统[J]. 农业机械学报, 2012, 43(8): 134-140.

[10]Li X, Yang L, Duan Y, et al. Developing a real-time monitoring traceability system for cold chain of Tricholoma matsutake[J]. Electronics, 2019, 8(4): 423-442.

[11]Luo H, Zhu M, Ye S, et al. An intelligent tracking system based on internet of things for the cold chain[J]. Internet Research: Electronic Networking Applications and Policy, 2016, 26(2): 435-445.

[12]冯旭, 李志刚. 基于ZigBee的羊肉冷链温度监测系统的设计[J]. 石河子大学学报(自然科学版), 2018, 36(5): 644-650.

[13]Wang W, He G, Wan J. Research on Zigbee wireless communication technology[C]// In Proceeding of 2011 International Conference on Electrical and Control Engineering. IEEE, 2011: 1245-1249.

[14]王想, 张旭, 李林, 等. 基于WSN的北美冬青鲜切枝冷链全过程监测系统[J]. 农业机械学报, 2017, 48(S1): 394-400.

[15]Liu P, Dong L, Cao A. Design of medical cold chain information acquisition system based on linear prediction[J]. Wireless Personal Communications, 2020, 115(2): 1197-1209.

[16]Habiyaremye J, Zennaro M, Mikeka C, et al. GPRS sensor node battery life span prediction based on received signal quality: experimental study[J]. Information, 2020, 11(11): 524-534.

[17]Martinez B, Adelantado F, Bartoli A, et al. Exploring the performance boundaries of NB-IoT[J]. IEEE Internet of Things Journal, 2019, 6(3): 5702-5712.

[18]Ribeiro L E, Tokikawa D W, Rebelatto J L, et al. Comparison between LoRa and NB-IoT coverage in urban and rural Southern Brazil regions[J]. Annals of Telecommunications, 2020, 75(11): 755-766.

[19]李晓鹏,袁涛.冷链物流实时监控系统设计[J]. 传感器与微系统, 2014, 33(2): 131-133+137.

[20]Huan J, Liu X, Chong Q. Design of an aquaculture monitoring system based on android and GPRS[J]. Applied Engineering in Agriculture, 2014, 30(4): 681-687.

[21]Ghribi B, Logrippo L. Understanding GPRS: the GSM packet radio service[J]. Computer Networks, 2000, 34(5): 763-779.

[22]Qiu B. Design of mobile 4G gateway based on Zigbee wireless sensor network[J]. International Journal of Online and Biomedical Engineering, 2018, 14(11): 117-132.

[23]Miles B, Bourennane E B, Boucherkha S, et al. A study of LoRaWAN protocol performance for IoT applications in smart agriculture[J]. Computer Communications, 2020, 164: 148-157.

[24]Rashmi Sharan Sinha, Yiqiao Wei, Seung-Hoon Hwang. A survey on LPWA technology: LoRa and NB-IoT[J]. ICT Express,2017, 3(1): 14-21.

[25]Hao Wang, Hong Sui, Xing Liao, et al. Comparative analysis of the application of different Low Power Wide Area Network techologies in power grid[J]. IOP Conference Series: Materials Science and Engineering, 2018, 322(7): 855-873.

[26]Rastogi E, Saxena N, Roy A, et al. Narrowband internet of things: a comprehensive study[J]. Computer Networks, 2020, 173: 1-41.

[27]Zhang X, Zhang M, Meng F, et al. A low-power wide-area network information monitoring system by combining NB-IoT and LoRa[J]. IEEE Internet of Things Journal, 2018, 6(1): 590-598.

[28]Chen J, Ota K, Wang L, et al. Guest editorial special issue on theories and applications of NB-IoT[J]. IEEE Internet of Things Journal, 2018, 5(3): 1435-1435.

[29]杨观止, 陈鹏飞, 崔新凯, 等. NB-IoT综述及性能测试[J]. 计算机工程, 2020, 46(1): 1-14.

[30]Lee Jinseong,Lee Jaiyong.Prediction-Based energy saving mechanism in 3GPP NB-IoT networks[J]. Sensor(Basel,Switzerland), 2017, 17(9):1-22.

[31]Bello H, Jian X, Wei Y, et al. Energy-delay evaluation and optimization for NB-IoT PSM with periodic uplink reporting[J]. IEEE Access, 2018, 7: 3074-3081.

[32]Agiwal M, Maheshwari M K, Jin H. Power efficient random access for massive NB-IoT connectivity[J]. Sensors, 2019, 19(22): 4944-4951.

[33]Andres-Maldonado P, Ameigeiras P, Prados-Garzon J, et al. An analytical performance evaluation framework for NB-IoT[J]. IEEE Internet of Things Journal, 2019, 6(4): 7232-7240.

[34]Sultania A K, Blondia C, Famaey J. Optimizing the energy-latency trade-off in NB-IoT with PSM and eDRX[J]. IEEE Internet of Things Journal, 2021:1-19.

[35]Chen M, Miao Y, Hao Y, et al. Narrow band internet of things[J]. IEEE access, 2017, 5: 20557-20577.

[36]Chen J, Ota K, Wang L, et al. Guest editorial special issue on theories and applications of NB-IoT[J]. IEEE Internet of Things Journal, 2018, 5(3): 1435-1435.

[37]Fu T. A review on time series data mining[J]. Engineering Applications of Artificial Intelligence, 2011, 24(1): 164-181.

[38]杨海民, 潘志松, 白玮. 时间序列预测方法综述[J]. 计算机科学, 2019, 46(1): 21-28.

[39]Yong W, Lingyun P, Jia W. Statistical analysis and ARMA modeling for the big data of marathon score[J]. Science & Sports, 2020, 35(6): 375-385.

[40]Saxena H, Anurag A V, Chirayath N, et al. Stock prediction using ARMA[J]. International Journal of Engineering and Management Research (IJEMR), 2018, 8(2): 1-4.

[41]彭红星, 郑楷航, 黄国彬, 等. 基于BP、LSTM和ARIMA模型的蔬菜价格预测[J]. 中国农机化学报, 2020, 41(04): 193-199.

[42]Shuran L, Shujin L. Applying BP neural network model to forecast peak velocity of blasting ground vibration[J]. Procedia Engineering, 2011, 26: 257-263.

[43]Yu W, Guan G, Li J, et al. Claim amount forecasting and pricing of automobile insurance based on the BP neural network[J]. Complexity, 2021: 1-17.

[44]侯建设, 田莹, 郑先章, 等. 减压冷藏短时处理对冷链断链条件下果蔬保鲜期影响的初步研究[J]. 中华航海医学与高气压医学杂志, 2016, 23(6): 442-445.

[45]肖皓洋, 罗萍, 杨朋博, 等. 一种高电源抑制比LDO[J]. 微电子学, 2020, 50(1): 60-64.

[46]葛海波, 李彩虹, 安文喆, 等. 一种基于LwM2M协议的智慧农业信息系统设计[J]. 西安邮电大学学报, 2019, 24(5): 88-94.

[47]段金见, 李立生, 梁春燕, 等. 基于CoAP协议的智能配电台区研究[J]. 现代电子技术, 2020, 43(5): 116-120.

[48]Ancona D, Franceschini L, Delzanno G, et al. Towards runtime monitoring of Node. js and its application to the internet of things[J]. Electronic Proceedings in Theoretical Computer Science2018, 264(264):27-42.

[49] Andri Sunardi, Suharjito. MVC Architecture: a comparative study between laravel framework and slim framework in freelancer project monitoring system web based[J]. Procedia Computer Science, 2019, 157: 134-141.

[50]Lee S Y, Paik J H. An asynchronous-driven Node. js based intermediary-free direct deal distribution platform converged with cloud service[J]. KSII Transactions on Internet & Information Systems, 2019, 13(8): 1-15.