|本期目录/Table of Contents|

[1]郭 齐.面向矿区的太阳能智慧路灯系统设计与实现[J].工业仪表与自动化装置,2023,(03):37-43.[doi:10.19950/j.cnki.cn61-1121/th.2023.03.008]
　GUO Qian.Design and implementation of solar street lamp system for mining area[J].Industrial Instrumentation & Automation,2023,(03):37-43.[doi:10.19950/j.cnki.cn61-1121/th.2023.03.008]
点击复制

面向矿区的太阳能智慧路灯系统设计与实现

《工业仪表与自动化装置》[ISSN:1000-0682/CN:61-1121/TH]

卷:
期数:
2023年03期
页码:
37-43
栏目:
出版日期:
2023-06-15

文章信息/Info

Title:
Design and implementation of solar street lamp system for mining area
文章编号:
1000-0682（2023）02-0037-05
作者:
郭 齐
中煤科工集团常州研究院有限公司销售总公司, 江苏 常州 213000
Author(s):
GUO Qian
CCTEG Changzhou Research Institute, Changzhou,213000,China
关键词:
智慧路灯; LSTM预测模型; 自适应; 系统设计
Keywords:
intelligent street lamps;  LSTM prediction model;  adaptivity; system design
分类号:
TP13
DOI:
10.19950/j.cnki.cn61-1121/th.2023.03.008
文献标志码:
A
摘要:
在“智慧矿山”发展战略的推动下，该文旨在对矿区路灯照明系统进行研究。太阳能路灯在矿区的应用成为响应国家“碳达峰、碳中和”政策的一种节能降耗方式。然而，太阳能无可避免地受到天气、季节、昼夜等因素的影响，需要进行节能控制。因此，面向矿区的太阳能智慧路灯系统在传统太阳能路灯技术的基础上进行改进，首先，通过神经网络算法LSTM建立能见度预测模型，从而根据预测值切换照明方式，实现节能的目的；其次，搭建完整可靠的软硬件系统及远程控制平台，利用无线通信的方式实现局部组网，使其远程可靠控制；最后，通过设计模拟实验验证本系统的可实施性。面向矿区的太阳能智慧路灯系统以深度学习的方式对未来一段时间内的能见度进行预测，可以根据预测值提前分配电能使用，最大限度解决自然因素的影响，对矿区的照明和节能具有重要意义。
Abstract:
Driven by the development strategy of "smart mine", this paper aims to study the street lighting system in mining area. The application of solar street lamp in mining area has become a way to save energy and reduce consumption in response to the national policy of "carbon peak and carbon neutrality". However, solar energy is inevitably affected by weather, season, day and night and other factors, so it needs to be controlled for energy conservation. Therefore, the intelligent solar street lamp system for mining area is improved on the basis of the traditional solar street lamp technology. Firstly, the visibility prediction model is established through the neural network algorithm LSTM, so that the lighting mode can be switched according to the predicted value to achieve the purpose of energy saving. Secondly, build a complete and reliable software and hardware system and remote control platform, and use wireless communication to realize local networking, so that the remote and reliable control; Finally, the feasibility of this system is verified by designing simulation experiments. The intelligent solar street lamp system facing the mining area predicts the visibility in the future period of time by means of deep learning. It can allocate the electricity use in advance according to the predicted value and solve the influence of natural factors to the maximum extent, which is of great significance for the lighting and energy saving of the mining area.

参考文献/References:

[1]魏星.矿井采煤区照明系统节能与安全控制技术研究[J].机电信息,2014(36):140-141.

[2]李保君.LED公共照明系统在渤海石油矿区的应用及节能效果分析[J].资源节约与环保,2015,162(05):70-71.
[3]徐先荣.矿区站场照明节能降消系统应用[J].科技传播,2016,8(02):87+113.
[4]李高伟,李响初.基于MCS-51单片机的矿区住宅智能应急照明控制系统设计[J].世界有色金属,2016(19):29-30.
[5]SAADATSERESHT M, VARSHOSAZ M. Visibility prediction based on artificial neural networks used in automatic network design[J]. Photogrammetric Record, 2007, 22(120): 336-355.
[6]DUDDU V R , PULUGURTHA S S , MANE A S , et al. Back-propagation neural network model to predict visibility at a road link-level[J]. Transportation Research Interdisciplinary Perspectives, 2020, 8:100250.
[7]WANG H , SHEN K , YU P , et al. Multimodal Deep Fusion Network for Visibility Assessment With a Small Training Dataset[J]. IEEE Access, 2020(99):1-1.
[8]顾阔,焦瑞莉,薄宇,等.基于复合LSTM模型的PM2.5浓度预测[J/OL].中国环境监测:1-11[2023-03-01].
[9]朱菊香,谷卫,钱炜,等.基于IF-SVMD-BWO-LSTM的空气质量预测建模[J/OL].中国测试:1-12[2023-03-01].
[10]方楠,谢国权,阮小建,等.长短期记忆神经网络(LSTM)模型在低能见度预报中的应用[J].气象与环境学报,2022,38(05):34-41.
[11]张淑芬,董燕灵,徐精诚,等.基于目标扰动的AdaBoost算法[J].通信学报,2023,44(02):198-209.
[12]邹雯萧,郝润泽,吴令仪,等.基于AdaBoost-LSTM模型的语音情绪识别研究[J].数字通信世界,2022, 215(11):47-48+51.
[13]王勇. 基于多源数据和XGBoost算法的上海市能见度预测模型研究[D].上海:华东师范大学, 2019.
[14]YANG X, ZHUANG M A, YUAN S. Multi-class Adaboost algorithm based on the adjusted weak classifier[J]. Journal of Electronics & Information Technology, 2016, 38(2): 373-380.
[15]ZHANG X, DING J. An improved Adaboost face detection algorithm based on the different sample weights[C]// IEEE International Conference on Computer Supported Cooperative Work in Design.2016.
[16]王飞文. 基于物联网的城市路灯智慧照明控制系统研究[D]. 南昌：南昌航空大学, 2018.
[17]何沙. 基于云平台的智慧路灯管理系统关键技术研究[D]. 北京：北京邮电大学, 2018.
[18]江伟冲, 黄祖健, 谭小卫,等. 基于LoRa技术的冷却塔自组网远程监控系统[J]. 自动化与信息工程, 2019, 40(3): 16-19.

相似文献/References:

备注/Memo

备注/Memo:
收稿日期：2023-03-08

第一作者：郭齐
更新日期/Last Update: 1900-01-01