Indoor Environmental Quality Monitoring,Evaluation And Prediction System

With the rapid development of China’s economy,the environmental pollution caused by industrial production and human activities is becoming more and more serious.In the past,people’s attention to environmental quality mainly focused on the outdoors.With the global pandemic of Corona Virus Disease 2019(COVID-19),people spend more than 80% of their time indoors,and the indoor environment has brought serious impacts on people’s life and physical health.Therefore,it is necessary to monitor the indoor environmental quality to understand the pollution level of various environmental factors,and use the evaluation method to evaluate and predict the indoor environmental quality,so as to determine the pollution level and take preventive measures,which is of great significance to protect the health of indoor personnel.Based on the background of school classrooms and dormitories,this paper carries out the research on the monitoring,evaluation and prediction of indoor environmental quality.The main research contents are as follows:Aiming at the shortcomings of the traditional fuzzy comprehensive evaluation algorithm being too subjective or objective in weight assignment,an improved fuzzy comprehensive evaluation algorithm based on combined weighting method is constructed.Through the measured data in the classroom,the improved fuzzy comprehensive evaluation algorithm is used to evaluate the environmental quality,and compared with the traditional fuzzy comprehensive evaluation algorithm based on the subjective questionnaire survey results.The results show that the improved fuzzy comprehensive evaluation algorithm has higher accuracy and the evaluation results are more in line with the feelings of indoor personnel.Based on the improved fuzzy comprehensive evaluation algorithm to calculate the environmental quality evaluation score,CEEMDAN-PCA-LSTM model is constructed to predict the indoor environmental quality.Taking the indoor environment of the dormitory as the research object,firstly,the time series of environmental quality evaluation scores are preprocessed by Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN),and then the features are extracted by Principal Component Analysis(PCA).Finally,the extracted principal components are used as the input of Long Short-Term Memory(LSTM)neural network to predict the indoor environment quality evaluation score at a moment in the future.Compared with other models,it shows that the CEEMDAN-PCA-LSTM model constructed in this paper has higher prediction accuracy and better prediction effect.Based on the Message Queuing Telemetry Transport(MQTT)communication protocol,an MQTT server is built and an MQTT client is developed,which realizes the reception and storage of data collected by the environmental monitoring equipment.Using front-end and back-end and database technology,a Web system for indoor environmental quality monitoring,evaluation and prediction is developed,which realizes the functions of real-time data monitoring,historical data query,environmental quality evaluation and prediction,email and SMS alarm push.Finally,the system is deployed on Alibaba cloud server to realize remote access.