Design of PM2.5 monitoring and forecasting system for opencast coal mine road based on internet of things and ARIMA Mode

Abstract

The dust produced by transportation roads is the primary source of PM2.5 pollution in opencast coal mines. However, China’s opencast coal mines lack an efficient and straightforward construction scheme of monitoring and management systems and a short-term prediction model to support dust control. In this study, by establishing a PM2.5 and other real-time environmental information to monitor, manage, visualize and predict the Internet of things monitoring and prediction system to solve these problems. This study solves these problems by establishing an Internet of things monitoring and prediction system, which can monitor PM2.5 and other real-time environmental information for monitoring, management, visualization, and prediction. We use Lua language to write interface protocol code in the APRUS adapter, which can simplify the construction of environmental monitoring system. The Internet of things platform has a custom visualization scheme, which is convenient for managers without programming experience to manage sensors and real-time data. We analyze real-time data using a time series model in Python, and RMSE and MAPE evaluate cross-validation results. The evaluation results show that the average RMSE of the ARIMA (4,1,0) and Double Exponential Smoothing models are 12.68 and 8.34, respectively. Both models have good generalization ability. The average MAPE of the fitting results are 10.5% and 1.7%, respectively, and the relative error is small. Because the ARIMA model has a more flexible prediction range and strong expansibility, and ARIMA model shows good adaptability in cross-validation, the ARIMA model is more suitable as the short-term prediction model of the prediction system. The prediction system can continuously predict PM2.5 dust through the ARIMA model. The monitoring and prediction system is very suitable for managers of opencast coal mines to prevent and control road dust.

Forecasting market demand using ARIMA and Holt - Winter method: A case study on canned fruit production company

“…Three core parameters of the ARIMA model are p, d and q, which symbolize the number of autoregressive terms (AR), the number of nonseasonal differences, and the number of lagged forecast errors (MA) in the predic on equa on, respec vely. On the other hand, the SARIMA(p,d,q) (P,D,Q)[s] model considers the seasonality according to three aforemen oned indexes [10]. By iden fying the op mal parameters and selec ng a model based on the informa on criteria (AIC), the model for the study is determined as ARIMA [(1,0,0), (0,1,1)] [7].…”

Research on fault diagnosis system for belt conveyor based on internet of things and the LightGBM model

“…At the same time, it provides data collection, data processing, data storage, and data application interfaces; besides, it also supports business applications such as message push, fault alarm, data report, operation and maintenance, and work order processing. More importantly, it supports a standard API interface and provides third-party development [32]. In addition, MixIoT has a complete security protection system, with security mechanisms in data collection, transmission and application stages to prevent data from flowing to malware [33].…”