Air Quality Control System Research Articles

Air Quality Prediction and Control Systems Using Machine Learning and Adaptive Neuro-Fuzzy Inference System

Accurately predicting air quality concentrations is a challenging task due to the complex interactions of pollutants and their reliance on nonlinear processes. This study introduces an innovative approach in environmental engineering, employing artificial intelligence techniques to forecast air quality in Semnan, Iran. Comprehensive data on seven different pollutants was initially collected and analyzed. Then, several machine learning (ML) models were rigorously evaluated for their performance, and a detailed analysis was conducted. By incorporating these advanced technologies, the study aims to create a reliable framework for air quality prediction, with a particular focus on the case study in Iran. The results indicated that the adaptive neuro-fuzzy inference system (ANFIS) was the most effective method for predicting air quality across different seasons, showing high reliability across all datasets.

Use of wireless technologies in IoT projects

When it comes to creating projects based on the use of the Internet of Things (IoT), wireless sensor networks are often used. Edge computing in IoT technology reduces system response delays to sensor output signals and increases the network throughput. At the same time, a short-range sensor network can work locally without access to the Internet, while long-range networks, as a rule, require access to the Internet and use both edge and cloud computing. The paper shows the features of the application of both peripheral and cloud computing in the practical implementation of IoT projects with various methods of wireless data transmission. Specific examples show the possibility of data transmission over a short distance using ESP-NOW technology, nRF24L01 radio modules and creating a local Wi-Fi access point. The range of sensor data transmission between microcontrollers is practically determined for each proposed option. The calculation of the range of the LoRa radio line is carried out for the actual sensitivity values of the receiver. The Okamura-Hata radio wave propagation model is proposed to estimate the LoRa radio line’s total loss. The operational range of LoRa modules with different types of signal modulation is practically determined. The essence of edge computing combined with digital and analogue sensors is shown. Peculiarities of peripheral computing during the implementation of IoT projects for remote control of blood saturation of patients using wireless technologies are considered. An example of data transmission of the air quality control system through a gateway based on an ESP8266 microcontroller with a graphical display of measurements in the IoT cloud service ThingSpeak and Blynk was provided.

DEVELOPMENT AND RESEARCH OF THE FUNCTIONAL POSSIBILITIES OF THE AUTOMATED FUZZY INDOOR AIR QUALITY MANAGEMENT SYSTEM OF PRODUCTION PREMISES

Purpose. Development of a fuzzy indoor air quality control system and research of the efficiency of an automated complex for increasing the concentration of air ions, namely a small-sized ultrasonic generator of air ions and a pump unit in the conditions of a complex ventilated air environment of work premises. Design/methodology/approach. The comprehensive research carried out is important in the context of the development of measures and means and the research of their effectiveness in maintaining the aeroionic regime of industrial premises at the regulatory level. Conclusions. The structure of an intelligent indoor air quality control system is proposed, which implements a combined change in the rotation speed of the fan and pump and the power of the ultrasonic aeroion generator. For the first time, a formalized criterion for the optimality of the indoor air quality management system is proposed, which depends on individual preferences of people regarding the comfort of the production environment and standardized parameters of temperature, relative humidity, and concentration of air ions in the working space. The task of the intelligent control system is to minimize the proposed criterion. Limitations/consequences of research. The proposed recommendations are universal and can be used in various areas of business to create safe and harmless working conditions in production. Practical consequences. The use of the developed small-sized ultrasonic aeroion generator not only significantly increases the concentration of aeroions in the working area, but also due to the baloelectric effect minimizes the negative impact inherent in most existing ionizers, namely the generation of ozone and nitrogen oxide, which significantly improves indoor air quality and thereby increases the level of industrial safety and labor protection. Originality/meaning. The existing control systems assume that standard ionizers (corona discharges) are inserted in the room, so there was a need to develop and research a modern intelligent system for controlling the quality of the indoor air in the working area of industrial premises using an aeroion generator and automated displacement ventilation.

Rancang Bangun Sistem Pemantauan dan Pengendali Kualitas Udara Pada Aplikasi Welding Habitat Proses Welding Pipeline Sistem Dengan Data Logger

Abstract
 Air Quality Monitoring and Control System is a method of monitoring and controlling air quality in an area or place where air contamination may occur in an activity or work. In this case, the Air Quality Monitoring and Control System is applied to the welding habitat or the welding house in the system pipe welding process. At this time, the welding habitat in the welding pipe pipeline system with the shielding gas process has not been monitored and controlled for air quality during the welding process, this condition causes the welder in the welding habitat to become uncomfortable which can affect the quality of the welding and endanger the welder's health. For this reason, an air quality monitoring and control system is needed that can unite and control the air quality in the welding habitat during the welding process. The purpose of the design of this Air Quality Monitoring and Control System is to make the welding process in the welding habitat of the system pipe welding process more comfortable and safer for the welder's health. So that the welder can concentrate fully on the welding process and produce good and quality welding production. With the application of this system, it can provide a level of weld repair that can reduce welding repair costs incurred by the Company.
 Keywords: Air Quality; Data Logger; ESP32; ISPU (Air Pollution Standards Index); Sensors

Comparison of Personal or Indoor PM2.5 Exposure Level to That of Outdoor: Over Four Seasons in Selected Urban, Industrial, and Rural Areas of South Korea: (K-IOP Study).

This study aimed to compare the distribution of indoor, outdoor, and personal PM2.5 (particulate matter ≤ 2.5 μm) hourly concentrations measured simultaneously among 81 nonsmoking elderly participants (65 years or older) living in urban, industrial, or rural areas over 4 seasons (2 weeks per season) from November 2021 to July 2022). PM2.5 measurements were conducted using low-cost sensors with quality control and quality assurance tests. Seasonal outdoor PM2.5 levels were 16.4 (9.1-29.6) μg/m3, 20.5 (13.0-38.0) μg/m3, 18.2 (10.2-31.8) μg/m3, and 9.5 (3.8-18.7) μg/m3 for fall, winter, spring, and summer, respectively. For indoor PM2.5, the median seasonal range was 5.9-7.5 μg/m3, and the median personal PM2.5 exposure concentration was 8.0-9.4 μg/m3. This study provided seasonal distributions of IO (ratio of indoor to outdoor PM2.5 concentration) and PO (ratio of personal to outdoor PM2.5 concentration) using a total of 94,676 paired data points. The median seasonal IO ranged from 0.30 to 0.51 in fall, winter, and spring; its value of summer was 0.70. The median PO by season and study area were close to 1.0 in summer while it ranged 0.5 to 0.7 in other seasons, statistically significantly lower (p < 0.05) than that in summer. Our study has revealed that the real-world exposure level to PM2.5 among our elderly study participants might be lower than what was initially expected based on the outdoor data for most of the time. Further investigation may need to identify the reasons for the discrepancy, personal behavior patterns, and the effectiveness of any indoor air quality control system.

Perceived air quality and satisfaction during implementation of an automated indoor air quality monitoring and control system

Cooking and cleaning are among the largest sources of home pollutant emissions. To reduce these emissions, we developed an automated indoor air quality (IAQ) control intervention that operated based on real-time sensor readings of particulate matter (PM2.5) and evaluated the perceptual differences between this intervention and a baseline condition. We employed a 14-participant crossover study design in a one-bedroom apartment module. Participants experienced one of two conditions: (1) Advanced Control–automated IAQ interventions including a stove hood, two portable air cleaners, and a bathroom exhaust powered on/off based on predefined PM2.5 thresholds measured by environmental sensors; and (2) Standard Control–participants controlling IAQ interventions (e.g., stove hood) manually. Each condition lasted two weeks. Participants followed standardized cooking and cleaning protocols and filled out surveys assessing psychosocial and perceptual outcomes. Observations indicated that weekly IAQ satisfaction, perception, and preferences were similar between the two conditions—despite lower PM2.5 concentrations during cooking and cleaning for the Advanced Control versus Standard Control Condition. When pairing IAQ complaints with PM2.5 concentrations during cooking, we observed participants made complaints when PM2.5 concentrations >∼80 μg/m3 but few complaints when <∼60 μg/m3. Lower PM2.5 concentrations were observed for the Advanced Control versus Standard Control Condition during cleaning, but these lower concentrations did not appear perceivable by participants due to far lower PM2.5 concentrations during cleaning overall. Our observations suggest a connection between PM2.5 concentration and IAQ complaints made by participants, thereby providing possible thresholds for perceivable IAQ changes.

Classification prediction model of indoor PM2.5 concentration using CatBoost algorithm

It is increasingly important to create a healthier indoor environment for office buildings. Accurate and reliable prediction of PM2.5 concentration can effectively alleviate the delay problem of indoor air quality control system. The rapid development of machine learning has provided a research basis for the indoor air quality system to control the PM2.5 concentration. One approach is to introduce the CatBoost algorithm based on rank lifting training into the classification and prediction of indoor PM2.5 concentration. Using actual monitoring data from office building, we consider previous indoor PM2.5 concentration, indoor temperature, relative humidity, CO2 concentration, and illumination as input variables, with the output indicating whether indoor PM2.5 concentration exceeds 25 μg/m3. Based on the CatBoost algorithm, we construct an intelligent classification prediction model for indoor PM2.5 concentration. The model is evaluated using actual data and compared with the multilayer perceptron (MLP), gradientboosting decision tree (GBDT), logistic regression (LR), decision tree (DT), and k-nearest neighbors (KNN) models. The CatBoost algorithm demonstrates outstanding predictive performance, achieving an impressive area under the ROC curve (AUC) of 0.949 after hyperparameters optimition. Furthermore, when considering the five input variables, the feature importance is ranked as follows: previous indoor PM2.5 concentration, relative humidity, CO2, indoor temperature, and illuminance. Through verification, the prediction model based on CatBoost algorithm can accurately predict the indoor PM2.5 concentration level. The model can be used to predict whether the indoor concentration of PM2.5 exceeds the standard in advance and guide the air quality control system to regulate.

Accurate evaluation of inhalation exposure based on CFD predicted concentration in the breathing zone towards personalized and smart control

Considering pollutants sourced from one's own exhaled air and skin as well as ambient air, this study adopts CFD technology to explore accurate evaluation method of inhalation exposure based on the pollutant concentration in the breathing zone. To do so, the concentration data extracted from the surfaces of mouth/nose openings and various sampling points close to mouth/nose openings is analyzed. The distribution of exhaled pollutants on one's own face is subsequently revealed and the re-inhalation ratio is quantified. If only point data is available (e.g., experimental context), the inhalation exposure to one's own exhaled pollutants can be evaluated based on the data at the center of the upper lip when inhaled through the mouth and at a location of 0.005 m away from the center of the nose openings when inhaled through the nose. If surface data is available (e.g., numerical context), the data on the whole mouth/nose openings should be used to evaluate the exposure. The distribution of exhaled pollutant concentration on one's own face changes periodically and asymmetrically over time. Based on the data obtained on face, the inhalation exposure to pollutants from one's own exhaled air would be underestimated. Depending on breathing mode, the re-inhalation ratio is mostly in a range of 0.3–1.0%. These findings can contribute to a more accurate evaluation of inhalation exposure and provide information for the development of personalized air quality control systems and smart wearable devices.

Artificial intelligence for ambient air quality control

Air quality, integral to public health and environmental stability, necessitates innovative solutions for effective monitoring and control. Existing methodologies are often limited in their predictive accuracy, scalability, and cost-effectiveness. This paper explores the potential of Artificial Intelligence (AI) in transforming ambient air quality control. We conduct an in-depth review of current AI applications, examining various models’ strengths and weaknesses in predicting and controlling air quality. These include machine learning, deep learning, and other AI methodologies. Real-world case studies are analyzed to assess the practicality and effectiveness of AI applications. While AI presents promising capabilities, its implementation is not without challenges such as data requirements, interpretability, and scalability. We discuss these issues, propose possible solutions, and explore future prospects for AI in air quality control. The aim is to provide a comprehensive understanding of the role AI can play in environmental management and a pathway towards its enhanced application. This paper invites further research in harnessing AI’s potential to create sustainable and effective air quality control systems.

Efficient Monitoring and Adaptive Control of Indoor Air Quality Based on IoT Technology and Fuzzy Inference

In recent years, more and more occupants have suffered from respiratory illness due to poor indoor air quality (IAQ). In order to address this issue, this paper presents a method to achieve efficient monitoring and adaptive control of IAQ. Firstly, an indoor air quality monitoring and control system (IAQMCS) is developed using IoT technology. Then, based on fuzzy inference, a novel fuzzy air quality index (FAQI) model is proposed to effectively assess IAQ. Furthermore, a simple adaptive control mechanism, called SACM, is designed to automatically control the IAQMCS according to a real-time FAQI value. Finally, extensive experiments are performed by comparing with regular control (time-based control), which show that our proposed method effectively measures various air parameters (CO2, VOC, HCHO, PM2.5, PM10, etc.) and has good performance in terms of evaluation accuracy, average FAQI value, and overall IAQ.

Evaluation of chlorides in fly ash for use in concrete

This paper investigates the use of fly ash with various levels of chlorides as a supplementary cementitious material for use in portland cement concrete. The varying levels of chlorides in the fly ashes originated from the air-quality control systems used during collection, rather than chlorides admixed into the fly ashes. Reducing mercury emissions of the thermoelectric power plant resulted in higher concentrations of chlorides in the fly ash. Three different concentrations of chloride (approximately 0.20%, 0.10%, and 0.01%) in fly ash were measured and incorporated into concrete at 25% and 50% replacement. Specimens cured for 7 days in a 73 °F (23 °C) 100% RH fog room followed by 21 days submerged in limewater in a 100 °F (38 °C) environmental chamber resulted in concrete that has similar maturity to concrete cured at ambient conditions for 1 year. Surface resistivity, chloride-ion penetration resistance, and impressed current testing were used to evaluate performance and durability. Acid and water-soluble chloride content were determined to elucidate the binding capacity of the concrete amended fly ashes with different chloride contents. The research clearly indicates that incorporating fly ash with varying levels of chlorides do not reduce the durability; it outweighed the performance as compared to concrete without fly ash. Additionally, increasing the fly ash replacement from 25% to 50% resulted in concretes exhibiting increased durability properties.

Biomimetic Light-Driven Aerogel Passive Pump for Volatile Organic Pollutant Removal.

Inspired by the solar‐light‐driven oxygen transportation in aquatic plants, a biomimetic sustainable light‐driven aerogel pump with a surface layer containing black manganese oxide (MnO2) as an optical absorber is developed. The flow intensity of the pumped air is controlled by the pore structure of nanofilbrillated cellulose, urea‐modified chitosan, or polymethylsilsesquioxane (PMSQ) aerogels. The MnO2‐induced photothermal conversion drives both the passive gas flow and the catalytic degradation of volatile organic pollutants. All investigated aerogels demonstrate superior pumping compared to benchmarked Knudsen pump systems, but the inorganic PMSQ aerogels provide the highest flexibility in terms of the input power and photothermal degradation activity. Aerogel light‐driven multifunctional gas pumps offer a broad future application potential for gas‐sensing devices, air‐quality mapping, and air quality control systems.

Andritz expands in air pollution control through acquisition

Andritz has acquired parts of GE Steam Power's Air Quality Control System (AQCS) business, including the technology centre in Växjö, Sweden.

Community-Friendly and Cost-Effective Monitoring Device for Environmental Pollution Using IoT

Air contamination is today the world’s toughest problem for the environment and public health. Air contamination has a detrimental effect on the wellbeing of humans, the atmosphere and the biodiversity. Factory air pollution continues caused by leaked toxic gases, vehicle waste and increasing accumulation of unhealthy gases and particulate matter. Particular materials are among the principal parameters of elevated air emissions, including real-time air quality monitoring to be monitored and analysed to determine correctly in a prompt manner. A standalone air quality control system with many parameters in operation in real-time is introduced in this article: CO2, temperature, humidity, air quality PM 2.5 and carbon monoxide. In reality, in every sector, the Internet of Things is commonly used and is also a key factor in air quality management. The Internet of Things Cloud Computing is a new way of improving the data processing of multiple sensors obtained and transmitted by the low-cost Raspberry pi ARM minicomputer.

학교교실 미세먼지 저감을 위한 공기환경조절시스템 현황분석

In this study, we examined the standards for indoor fine dust concentration and investigate the design of an indoor air conditioning system that could remove indoor fine dust. Based on contents taken from the Nara Market Site, we collected, organized, and analyzed data on air purifiers and air circulators (the representative indoor air quality control systems). Additionally, we also investigated and analyzed the current status and statistics of the maintenance of school air quality control systems in Gyeonggi-Do. According to the current status of maintenance for school air quality management systems among 397 schools in Gyeonggi-do, this study found that air quality control measures were applied the most often in elementary schools, and that the MERV15 grade filter was used the most.

Development of an Automatic Low-Cost Air Quality Control System: A Radon Application

Air pollution is the fourth-largest overall risk factor for human health worldwide. Ambient air pollution (outdoors) and household air pollution (indoors) cause about 6.5 million premature deaths. The World Health Organization has established that between 3% and 14% of lung cancer cases are due to radon gas, making it the most important cause of lung cancer after smoking. This work presents a fully automated, low-cost indoor air quality control system that can monitor temperature, pressure, humidity, total volatile organic compounds (TOVC), and radon concentration. Using the radon concentration as an air quality measure, we created a prediction algorithm. The system uses those predictions to control a ventilation system automatically. We tested the algorithm for different prediction windows and compared the results with those without the ventilation system in a radon research room. In this room, the radon concentration is high 100% of the time, reaching a level eleven times higher than the recommended limit. The results show that the system can achieve an 86% reduction of the radon concentration, maintaining it low 90% of the time while having the ventilation system on during only 34% of the time. This work demonstrates that we can control air quality using low-cost resources, keeping a household or workplace safe but comfortable.

Dynamic forecasting model for indoor pollutant concentration using recurrent neural network

Accurate and reliable indoor pollutant concentration prediction is essential to solve the time-lag problem of indoor air quality control systems. Thus, the representation of time in pollutant forecasting models is very important. One approach is to introduce an Elman neural network using a direct inference strategy into the time series forecast of indoor pollutant concentration. In this study, measurements of CO2 (ppm), total volatile organic compounds (mg/m3), particulate matter with a diameter smaller than 2.5 µm (PM2.5; µg/m3), the indoor dry bulb temperature (°C) and relative humidity (%) were carried out in a classroom at a middle school in Beijing, China. To identify air pollution antecedents, input selection was conducted based on correlation analysis. The results show that the information provided by the PM2.5 time series can better simulate the dynamic relationship between input and output data ([Formula: see text]= 0.963 and R2 = 0.928). In addition to the overall goodness of fit ([Formula: see text] = 0.982) of the CO2 time series, the peak and valley prediction capability of the model was evaluated using the relative peak error ( RPE) metric. Information from the valleys of the CO2 time series gives good results ([Formula: see text]). Therefore, a dynamic forecasting model with a direct inference strategy is a capable tool for identifying proper air pollution antecedents.

IoT based Real-time Air Quality Monitoring and Control System to Improve the Health and Safety of Industrial Workers

Pollution is adding contaminants into the nature that causes an adverse change in the environment. Air pollution is one of the highest mortality risk factors globally. The sources of air pollution in the industries are power plants, chamber process, cleaning, burning of materials, etc. A variety of pollutants emitted into the air such as sulfur dioxide, carbon monoxide, carbon dioxide, ammonia and volatile organic compounds. Particulate Matter (PM) is an air pollutant that is the mixture of solid dust or pollen and liquid droplets with air. Air pollution in industrial workplaces is a major concern and monitoring and management of it to be addressed to protect the industrial workers health from the air pollution effects. The people are suffering from several respiratory and heart issues along with cancer due to increasing air pollution. This device is composed of ESP32 MCU, MQ135 gas sensor, SDS011 optical dust particle sensor, and BME280 humidity and temperature sensor for monitoring the air quality. The gas sensor MQ135 senses the harmful gases present in the environment. SDS011 optical dust sensor senses the PM levels (PM10 and PM2.5) in the atmosphere. The sensor values are evaluated for the Air Quality Index (AQI) and display it on the ThingSpeak IoT platform. Vrituino app has used for a virtual screen with widgets on the mobile phone to monitor the system using the web. In order to improve the real-time performance of the system, an IoT and a cloud computing technology are being used. The ESP32 turns on the fan units to maintain the pollutants within the safe limit when the presence of harmful gases and PM levels exceeds a certain threshold level. This system is essential for industrial work places to adopt measures and control air pollution which increase industrial workers safety.

IoT based Real-time Air Quality Monitoring and Control System to Improve the Health and Safety of Industrial Workers

Pollution is adding contaminants into the nature that causes an adverse change in the environment. Air pollution is one of the highest mortality risk factors globally. The sources of air pollution in the industries are power plants, chamber process, cleaning, burning of materials, etc. A variety of pollutants emitted into the air such as sulfur dioxide, carbon monoxide, carbon dioxide, ammonia and volatile organic compounds. Particulate Matter (PM) is an air pollutant that is the mixture of solid dust or pollen and liquid droplets with air. Air pollution in industrial workplaces is a major concern and monitoring and management of it to be addressed to protect the industrial workers health from the air pollution effects. The people are suffering from several respiratory and heart issues along with cancer due to increasing air pollution. This device is composed of ESP32 MCU, MQ135 gas sensor, SDS011 optical dust particle sensor, and BME280 humidity and temperature sensor for monitoring the air quality. The gas sensor MQ135 senses the harmful gases present in the environment. SDS011 optical dust sensor senses the PM levels (PM10 and PM2.5) in the atmosphere. The sensor values are evaluated for the Air Quality Index (AQI) and display it on the ThingSpeak IoT platform. Vrituino app has used for a virtual screen with widgets on the mobile phone to monitor the system using the web. In order to improve the real-time performance of the system, an IoT and a cloud computing technology are being used. The ESP32 turns on the fan units to maintain the pollutants within the safe limit when the presence of harmful gases and PM levels exceeds a certain threshold level. This system is essential for industrial work places to adopt measures and control air pollution which increase industrial workers safety.

Development of the method of forecasting the atmospheric air pollution parameters based on error correction by neural-like structures of the model of successive geometric transformations

The article describes the importance of improving existing and exploring new algorithms for predicting environmental parameters to improve the quality of environmental monitoring. Because the organization and management of production require the development of new approaches to the problem of control and management of industrial sources of harmful substances based on new information technologies. One of the most problematic places in industrial air quality control and management systems is the development of advanced prospective air pollution forecasting algorithms. These algorithms must take into account t situational changes in data distribution and do not require retraining of atmospheric air pollution parameters. With the advent of neural-like structures, there is a need for their study, including the task of predicting the parameters of air pollution. The object of research is the neural-like structures of the Model of Successive Geometric Transformations. A method for predicting the parameters of atmospheric air pollution based on error correction with the help of a committee of different types of neural-like structures is proposed. In the course of the study, three methods for predicting the parameters of atmospheric air pollution were analyzed: a Generalized Regression Neural Network, a Radial Basis Function, and a neural-like structure of Sequential Geometric Transformations Model. A combination of these methods was performed and the results of the three methods were compared. It is experimentally determined that the prediction of atmospheric air pollution parameters based on the error correction using the committee of neural-like structures of the Sequential Geometric Transformations Model provides a prediction error reduction by 7 % of the General Regression Neural Network and by 2.6 % of the Radial Basis Function with extended General Regression Network. The obtained results increase the reliability and speed of forecasting of atmospheric air parameters to improve the quality of monitoring of emissions of harmful impurities in production and to make environmental management decisions.