%0 Journal Article
%T 面向煤炭清洁利用的港口煤垛含水率预测研究<br>Research on Forecast of Moisture Content of Port Coal Stacks for Clean Coal Utilization
%A 刘强
%A 李娜
%A 张淼
%A 李昊
%A 张崇进
%A 张帆
%J Clean Coal and Energy
%P 1-8
%@ 2334-3516
%D 2021
%I Hans Publishing
%R 10.12677/CCE.2021.91001
%X 煤炭洒水降尘对煤炭清洁利用和实现绿色能源港口意义重大，而港口堆场风速、湿度和温度等是影响煤垛含水分含量变化的主要因素。本文基于影响煤炭含水率变化的温湿度和风力等主要天气因素，研究了一种基于深度学习的含水率预测方法，该方法通过建立LSTM循环神经网络煤炭含水率预测模型，通过收集和处理黄骅港的气象数据，通过对采集到的港口天气数据和不同煤种煤堆的表层含水率数据融合处理，使用LSTM模型对训练数据集进行训练之后用来测试测试数据集。研究结果表明，通过使用这种数据驱动的方法，可以制定出节省人力和水资源的智能洒水计划，既能节约港口用水、减少污水量，又能提高煤炭清洁利用效率，对绿色生态港口建设具有重要意义。<br />
Coal watering and dust reduction are of great significance to the clean utilization of coal and the realization of green energy ports, and the wind speed, humidity and temperature of the port sto-rage yard are the main factors that affect the change of the moisture content of the coal stacks. Based on the main weather factors such as temperature, humidity and wind that affect the change of coal moisture content, this paper studies a moisture content prediction method based on deep learning. This method establishes a LSTM recurrent neural network coal moisture content predic-tion model, and collects and processes the Huanghua Port. Through the fusion processing of the collected port weather data and the surface water content data of different coal piles, the LSTM model is used to train the training data set to test the test data set. The research results show that by using this data-driven method, a smart sprinkling plan that saves manpower and water re-sources can be developed, which can save port water, reduce sewage, and improve the efficiency of clean coal utilization, which is beneficial to the construction of a green ecological port. important meaning.
%K 煤炭清洁利用，煤垛抑尘，含水率预测，LSTM，深度学习
%K Clean Utilization of Coal
%K Coal Stack Dust Suppression
%K Moisture Content Prediction
%K LSTM
%K Deep Learning
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=41160