Real-time Control System Research Articles

Advancing Manufacturing Efficiency through Real-time Production Monitoring and Control Systems

The advantages of both real-time production monitoring and control systems in enhancing the advancement of manufacturing efficiency cannot be overlooked. Manufacturing industries need to meet customers’ demand while still maximizing their profits via avoiding emergency shutdown of plants during production. Nonetheless, quality products with high purity level should be supplied uninterruptedly without breakage of supply chain. In recent times, failure of many of manufacturing industries to deliver their products to end users have been cited and reported. This was due to inadequate scheduling which was not being monitored via real-time production and control systems. There is need to tackle this problem which calls for the adoption of real-time production monitoring and control systems. In this paper, the concepts behind the use of real-time production monitoring and control systems were discussed. Consideration was given to how real-time production monitoring can be integrated in manufacturing. The features of real-time control systems were discussed alongside with their industrial applications in various disciplines of Engineering. Data analysis and prognostics, data collection, visualization module and data storage were identified as the relevant sequential steps in real time production monitoring in advancing manufacturing efficiency. In conclusion, the significance and importance of real-time production monitoring and control systems in advancing manufacturing efficiency have been revealed and discussed in this paper.

Bio-Inspired Robotic Exoskeletons with Adaptive Electrical Control for Enhanced Upper Extremity Rehabilitation

Robotic exoskeletons are a new and hopeful technology for rehabbing the upper limbs. They offer exact control and adjustable help to make traditional treatment more effective. This study suggests a new way to improve the recovery process that combines bio-inspired design with flexible electrical control. It is based on the way biological systems work. The suggested exoskeleton design is biomimetic, meaning that it looks and works like a human arm. This is done to make sure that the person can move naturally and comfortably. Lightweight, flexible materials make up the exoskeleton, which has sensors that track the user's movements and muscle activity. These monitors send input to the control system in real time, which lets it make changes that are more helpful for the user while they do different recovery routines. The control system uses an adaptable electrical treatment method that is based on how the human body controls its muscles. The control system constantly checks the user's muscle action and changes the amount of electrical stimulation to give the best support and help during recovery exercises. This flexible method makes sure that the exoskeleton's help is tailored to the person using it's wants and skills, which helps them recover more quickly. A bio-inspired robotic suit with adjustable electrical control is tested in a set of tests with healthy people and people who have had a stroke. The data show that the exoskeleton improves therapy for the upper limbs by giving individualized help and encouraging natural movement patterns. The adjustable electrical control makes it a lot easier for the user to do recovery exercises, which leads to better performance and a higher quality of life.

A piecewise inverse finite element method for shape sensing of the morphing wing fishbone

The shape sensing technology plays a significant role in enhancing the structural performance and flight efficiency of the morphing aircraft by providing feedback to actuation and control systems in real time. The inverse finite element method (iFEM) is a fast, accurate, and robust shape-sensing method based on in-situ surface strain measurements. However, the conventional iFEM becomes less effective when applied to real engineering structures. Thus, this paper proposes a piecewise iFEM (P-iFEM) based on a two-node inverse Hermite beam element (iHB2) for the load-bearing structure of the morphing wing. The P-iFEM method discretizes the structure into a combination of rigid and elastic parts, based on the geometry of the structure when assembling the inverse elements. The Hermite polynomial shape function in iHB2 is adopted to increase the reconstruction efficiency, as only one degree of freedom of deflection is required to achieve the C1-continuity to reconstruct the displacement fields. The high accuracy and efficiency of the proposed method are validated with a numerical fishbone model. Finally, the proposed method is applied to a fishbone structure of a real adaptive deformed wing with high accuracy.

Petri Net Model Predictive Control Method for Batch Chemical Systems

In order to address the problem of the real-time scheduling and control of batch chemical systems, this work proposes a model predictive control method based on Petri nets. First, a method is presented to construct a batch chemical system’s timed Petri net model. Second, a control structure is designed to augment the Petri net model to control the valves. This results in timed Petri nets that formally represent the process specifications of a batch chemical system. Third, a model predictive control method is developed to schedule and control timed Petri nets, where a proposed heuristic function is utilized to perform the optimization computation. The model parameters are dynamically adjusted using online data, and both scheduling and valve control instructions are calculated in real time. Finally, a series of experiments is carried out in a beer canning plant to verify the proposed method. According to the experimental results, the scheduling and control problem can be solved in real time, where the online computations can be performed in milliseconds, and the resulting scheduling strategies are optimal or near-optimal.

SP2D: Simplified pseudo 2D battery model by piecewise sinusoidal/quadratic functions of potential curves

The pseudo 2D battery model is a widely used tool for analysing the electrochemical behaviour of lithium-ion batteries. However, the high computational expense of solving the fully coupled governing equations is a significant challenge. In this study, a simplified pseudo 2D battery model has been developed to address this bottleneck. The model gets the electrolyte potential with relative potential plus reference potential, which are described by piecewise quadratic or sinusoidal function and determined by boundary conditions. Two electrodes are defined with uniform potentials. This approach provides a simple solution of charge transfer equations and decouples them from the governing equations of the pseudo 2D model. It shows excellent agreement with the original pseudo 2D battery model for a wide range of C-rates, drive cycles and is applicable to electrolytes with different conductivities. The proposed approach provides a simpler and faster solution than the pseudo 2D battery model, with negligible accuracy sacrifice. Consequently, this work is crucial for applying physics-based models to real-time battery control and management systems.

Model predictive control for real-time microstructure control in laser heat treatment

Metals’ surface microstructure can be altered through controlled heating and cooling of the surface using the laser heat treatment (LHT) method. Lasers have the advantage in this process of being able to heat treat specific regions of the workpiece without affecting the whole product. However, because a laser is being used, this process is extremely sensitive to changes in the process inputs and disturbances, which results in changes in the thermal dynamics and alterations in the peak temperature and cooling rate, in particular. These alterations have a direct effect on the material and its mechanical characteristics, such as hardness and hardening depth. Since these variations are caused by complex metallurgical phenomena, it is important to control the thermal dynamics in real-time. Real-time control systems are usually error-based and do not have the ability to predict the effect of the control action on the system, deal with constraints, or correlate the mechanical and material properties of the processed materials to LHT process parameters. Hence, the development of accurate model-based controllers is required. Therefore, a Model Predictive Control (MPC) algorithm is developed in this paper to control the thermal dynamics during the LHT process, e.g., the peak temperature, in real-time. This controller uses a finite difference thermal model to find the optimal process speed that results in the desired peak temperature. Moreover, consistent hardness and hardening depth will be obtained by closed-loop peak temperature control.

ADVANCING FOOD SAFETY THROUGH IOT: REAL-TIME MONITORING AND CONTROL SYSTEMS

This paper proposes the development of an Internet of Things (IoT)-based real-time monitoring and control system for food safety management. By leveraging IoT sensors and devices throughout the food production and distribution process, this system aims to continuously monitor food safety parameters, providing immediate data to prevent contamination and ensure compliance with safety standards. In response to the critical need for enhanced food safety measures, this concept paper proposes the implementation of IoT (Internet of Things) technology to advance food safety through real-time monitoring and control systems. The global food industry faces significant challenges in ensuring food safety throughout the supply chain, including inefficiencies, delays in response to potential hazards, and increased risks of contamination. Traditional methods of monitoring and controlling food safety often lack real-time capabilities and are prone to human error. The proposed solution focuses on introducing an IoT-based system for real-time monitoring of critical food safety parameters such as temperature, humidity, and the presence of pathogens. This system will leverage a combination of sensor technologies, data analytics, and communication protocols to continuously monitor environmental conditions and potential hazards throughout the food supply chain. Key components of the proposed system include IoT sensors and devices, a centralized monitoring platform, data transmission infrastructure, and integration with existing food safety management systems. Advanced data analytics techniques, including machine learning algorithms, will be employed to analyze collected data, identify patterns, trends, and anomalies, and develop predictive models to anticipate potential hazards. The implementation strategy outlined in this concept paper includes comprehensive assessment and planning, deployment of IoT sensors, establishment of data collection and transmission infrastructure, data analysis and insights, integration with existing systems, and training and capacity building. By following this strategy, stakeholders can proactively manage food safety risks and ensure the integrity and safety of the food supply chain. Advancing food safety through IoT-based real-time monitoring and control systems holds great promise in revolutionizing the way food safety is managed, safeguarding public health, enhancing consumer trust, and ensuring a safer and more reliable food supply for consumers worldwide.
 Keywords: Food Safety, Real Time, Monitoring, IoT.

ADVANCING FOOD SAFETY THROUGH IOT: REAL-TIME MONITORING AND CONTROL SYSTEMS

This paper proposes the development of an Internet of Things (IoT)-based real-time monitoring and control system for food safety management. By leveraging IoT sensors and devices throughout the food production and distribution process, this system aims to continuously monitor food safety parameters, providing immediate data to prevent contamination and ensure compliance with safety standards. In response to the critical need for enhanced food safety measures, this concept paper proposes the implementation of IoT (Internet of Things) technology to advance food safety through real-time monitoring and control systems. The global food industry faces significant challenges in ensuring food safety throughout the supply chain, including inefficiencies, delays in response to potential hazards, and increased risks of contamination. Traditional methods of monitoring and controlling food safety often lack real-time capabilities and are prone to human error. The proposed solution focuses on introducing an IoT-based system for real-time monitoring of critical food safety parameters such as temperature, humidity, and the presence of pathogens. This system will leverage a combination of sensor technologies, data analytics, and communication protocols to continuously monitor environmental conditions and potential hazards throughout the food supply chain. Key components of the proposed system include IoT sensors and devices, a centralized monitoring platform, data transmission infrastructure, and integration with existing food safety management systems. Advanced data analytics techniques, including machine learning algorithms, will be employed to analyze collected data, identify patterns, trends, and anomalies, and develop predictive models to anticipate potential hazards. The implementation strategy outlined in this concept paper includes comprehensive assessment and planning, deployment of IoT sensors, establishment of data collection and transmission infrastructure, data analysis and insights, integration with existing systems, and training and capacity building. By following this strategy, stakeholders can proactively manage food safety risks and ensure the integrity and safety of the food supply chain. Advancing food safety through IoT-based real-time monitoring and control systems holds great promise in revolutionizing the way food safety is managed, safeguarding public health, enhancing consumer trust, and ensuring a safer and more reliable food supply for consumers worldwide.
 Keywords: Food Safety, Monitoring, Real Time, Authority, Nigeria.

A deep reinforcement learning approach based energy management strategy for home energy system considering the time-of-use price and real-time control of energy storage system

To enhance the flexibility of the home load optimization dispatching strategy and ensure the safe operation of the energy storage system, an optimization dispatching strategy for home energy management system (HEMS) based on time-of-use pricing and real-time energy storage system control is proposed. Firstly, a HEMS dispatching model is established with the constraints of dispatchable load and energy storage system working status, aiming to minimize the total cost for home users. This dispatching strategy controls the energy storage system charging and discharging behavior based on time-of-use pricing and real-time battery state of charge, which helps to reduce the power cost for home users and ensure the safe operation of the battery. Then, the optimal dispatching problem of HEMS is modeled as a Markov decision process (MDP) and solved by a deep reinforcement learning algorithm called soft actor-critic (SAC). The example results verify the effectiveness and superiority of the proposed method compared with other benchmark methods, which the system cost can be reduced by 15.87% at least.

Modelling the unsteady lift of a pitching NACA 0018 aerofoil using state-space neural networks

The development of simple, low-order and accurate unsteady aerodynamic models represents a crucial challenge for the design optimisation and control of fluid dynamical systems. In this work, wind tunnel experiments of a pitching NACA 0018 aerofoil conducted at a Reynolds number $Re = 2.8 \times 10^5$ and at different free-stream turbulence intensities are used to identify data-driven nonlinear state-space models relating the time-varying angle of attack of the aerofoil to the lift coefficient. The proposed state-space neural network (SS-NN) modelling technique explores an innovative methodology, which brings the flexibility of artificial neural networks into a classical state-space representation and offers new insights into the construction of reduced-order unsteady aerodynamic models. The work demonstrates that this technique provides accurate predictions of the nonlinear unsteady aerodynamic loads of a pitching aerofoil for a wide variety of angle-of-attack ranges and frequencies of oscillation. Results are compared with a modified version of the Goman–Khrabrov dynamic stall model. It is shown that the SS-NN methodology outperforms the classical semi-empirical dynamic stall models in terms of accuracy, while retaining a fast evaluation time. Additionally, the proposed models are robust to noisy measurements and do not require any pre-processing of the data, thus involving only a limited user interaction. Overall, these features make the SS-NN technique an excellent candidate for the construction of accurate data-driven models from experimental fluid dynamics data, and pave the way for their adoption in applications entailing design optimisation and real-time control of systems involving lift.

Analysis of a multi-energy coupling model for rural energy under the rural digital economy

With the growth of the digital economy, the sustainable growth of rural energy has become crucial. However, traditional rural energy models have the drawback of not considering digital technology and renewable energy. Therefore, there is an urgent need for rational planning and development of rural energy. According to this, a multi-energy coupling model for rural energy systems was established by considering equipment capacity planning and operation scheduling optimization based on a multi-energy coupling structure. At the same time, considering the biomass resources in rural energy systems, an optimized configuration model for biomass coal-fired coupled power generation units was established. The results showed that the energy consumption cost in County A accounted for only 3.3%. County C focused mainly on tourism and emphasized economic efficiency, with investment costs 8.6% and 10.3% lower than other rural areas. The system utilized time of use electricity prices to optimize operation. The low storage stage was from 1:00 to 8:00, while the high incidence stage was from 12:00 to 14:00 and from 7:00 to 21:00. In the actual scenario, the multi-energy coupling model can be combined with intelligent technology to realize the real-time monitoring, prediction and optimal control of the energy system. Through the introduction of advanced digital technology, the model can be more flexible to deal with the diversified energy sources and complex operational scheduling situations involved in rural energy systems. This can improve the response speed and adaptability of the system, making the energy system more resilient and efficient.

What are the key stability challenges in high-bandwidth, non-minimum phase systems with time-varying, and non-smooth delays?

The analysis and control of stability in high-bandwidth systems characterized by non-minimum phase delays represent a formidable challenge within the realm of control theory and engineering. This research aims to address the pivotal question of whether it is feasible to enhance the stability of such intricate systems. These systems inherently possess uncertain and swiftly changing delay characteristics, rendering them exceptionally demanding to control effectively. In the course of this investigation, we embark on a comprehensive exploration of the theoretical underpinnings of the stability of high-bandwidth, non-minimum phase delay systems. This encompassing inquiry encompasses a meticulous consideration of both derivative-delay and piecewise continuous delay components. To underpin our analysis, we judiciously incorporate feedback mechanisms, drawing upon mathematical tools such as the Jensen inequality and Lyapunov-based methodologies to rigorously establish stability conditions. Furthermore, our exploration extends to encompass the concept of input-output stability and complements it with the notion of asymptotic stability, thereby ensuring that the systems in question exhibit uniform stability across diverse temporal domains. The outcomes of our investigation furnish compelling evidence that by harnessing the power of discrete-time Lyapunov-Krasovskii functionals, it becomes conceivable to circumscribe the maximum delay within predefined thresholds. This achievement holds the promise of enhancing stability in non-minimum phase delay systems characterized by high bandwidth. These findings have far-reaching implications, profoundly influencing the design and control paradigms across a spectrum of engineering applications. Notably, this impact extends to areas such as communication networks, real-time control systems, and robotics, where the mitigation of instability due to non-minimum phase delays has been an enduring challenge.

Implementing a digital twin for optimized real-time control of Gothenburg's regional sewage system

Abstract The emerging challenges facing the City of Gothenburg and surrounding municipalities include the impacts of a variable climate, rapid growth and urbanization, aging infrastructure and changing community values and customer expectations. A digital twin (DT), based on the Future City Flow (FCF) platform, was created for the catchment to address many of these challenges in terms of improved real-time sewerage performance and predictability in the face of storms, improved DT visualization of the regional sewage transport system for operators and greater responsiveness to avoid service interruption. The FCF-based DT provides a sound base for modelling, simulating, forecasting and controlling the catchment. The versatility of the FCF DT makes it useful for gaining insight into catchment dynamics and the simulator can be used to study the effects of different scenarios or changes in the catchment. The predictive control imbedded in the FCF DT recommends setpoints for controlling the catchment that can be used by the operators for decision support or even be directly applied in the control system as model-based predictive control. A DT requires good quality online data from the catchment and, perhaps most importantly, high-quality rain forecasts, especially when prognosing long time horizons.

Enhancing Camera Calibration for Traffic Surveillance with an Integrated Approach of Genetic Algorithm and Particle Swarm Optimization.

Recent advancements in sensor technologies, coupled with signal processing and machine learning, have enabled real-time traffic control systems to effectively adapt to changing traffic conditions. Cameras, as sensors, offer a cost-effective means to determine the number, location, type, and speed of vehicles, aiding decision-making at traffic intersections. However, the effective use of cameras for traffic surveillance requires proper calibration. This paper proposes a new optimization-based method for camera calibration. In this approach, initial calibration parameters are established using the Direct Linear Transformation (DLT) method. Then, optimization algorithms are applied to further refine the calibration parameters for the correction of nonlinear lens distortions. A significant enhancement in the optimization process is achieved through the integration of the Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) into a combined Integrated GA and PSO (IGAPSO) technique. The effectiveness of this method is demonstrated through the calibration of eleven roadside cameras at three different intersections. The experimental results show that when compared to the baseline DLT method, the vehicle localization error is reduced by 22.30% with GA, 22.31% with PSO, and 25.51% with IGAPSO.

Optimization and evaluation of a neural network based policy for real-time control of construction factory processes

This paper focuses on the development, optimization, and evaluation of an intelligent real-time control system for the fabrication of precast reinforced concrete components. The study addresses the unique challenges associated with real-time control in the construction manufacturing industry, including high customization, uncertain work demand, and limited stockpiling opportunities. A production system model is built based on a real construction manufacturing factory to simulate real-world precast reinforced concrete component fabrication, and acts as the basis for the development and validation of the control system. A review of alternative decision-making techniques is presented to identify the most suitable for the control of construction manufacturing factories. Ultimately, an artificial neural network approach trained using a reinforcement learning strategy is selected as a promising technique for effective real-time control. The controller is developed and validated, and its performance is optimized using sensitivity analysis, which takes into account both the structure of the artificial neural network and the parameters of the reinforcement learning algorithm. The ANN-based control policy is applied to the sequencing of precast reinforced concrete component production, while a rule-of-thumb policy is used as a benchmark for comparison. The study demonstrates that the optimized ANN-based control policy significantly outperforms the standard rule-of-thumb policy. The paper concludes by providing suggestions for further advancement of the ANN-based approach and potential avenues to increase the control policy's scope of application in construction manufacturing.

Reynolds-number scaling of wall-pressure–velocity correlations in wall-bounded turbulence

Wall-pressure fluctuations are a practically robust input for real-time control systems aimed at modifying wall-bounded turbulence. The scaling behaviour of the wall-pressure–velocity coupling requires investigation to properly design a controller with such input data so that it can actuate upon the desired turbulent structures. A comprehensive database from direct numerical simulations (DNS) of turbulent channel flow is used for this purpose, spanning a Reynolds-number range$Re_\tau \approx 550\unicode{x2013}5200$. Spectral analysis reveals that the streamwise velocity is most strongly coupled to the linear term of the wall pressure, at a Reynolds-number invariant distance-from-the-wall scaling of$\lambda _x/y \approx 14$(and$\lambda _x/y \approx 8$for the wall-normal velocity). When extending the analysis to both homogeneous directions in$x$and$y$, the peak coherence is centred at$\lambda _x/\lambda _z \approx 2$and$\lambda _x/\lambda _z \approx 1$for$p_w$and$u$, and$p_w$and$v$, respectively. A stronger coherence is retrieved when the quadratic term of the wall pressure is concerned, but there is only little evidence for a wall-attached-eddy type of scaling. An experimental dataset comprising simultaneous measurements of wall pressure and velocity complements the DNS-based findings at one value of$Re_\tau \approx 2$k, with ample evidence that the DNS-inferred correlations can be replicated with experimental pressure data subject to significant levels of (acoustic) facility noise. It is furthermore shown that velocity-state estimations can be achieved with good accuracy by including both the linear and quadratic terms of the wall pressure. An accuracy of up to 72 % in the binary state of the streamwise velocity fluctuations in the logarithmic region is achieved; this corresponds to a correlation coefficient of$\approx$0.6. This thus demonstrates that wall-pressure sensing for velocity-state estimation – e.g. for use in real-time control of wall-bounded turbulence – has merit in terms of its realization at a range of Reynolds numbers.

Optimization of Stable Energy PV Systems Using the Internet of Things (IoT)

The modern power grid faces rapid growth in load demand due to industrialization, leading to an unregulated environment and increasing adoption of renewable energy sources, which presents technical challenges, particularly in terms of stability. Hydrogen conversion technology revolutionizes clean electricity storage with renewable energy, and solar hydrogen is now available in autonomous solar systems. The efficiency of solar photovoltaic systems is closely related to using digital electronic maximum peak power tracking (MPPT) technology. The Internet of Things (IoT) is crucial for performance monitoring and real-time control of PV systems, enhancing the understanding of real-time operating parameters. IoT and wireless sensor networks for distributed solar energy devices and joint building design are essential for developing the photovoltaic construction industry. In this paper, the monitoring system that has been proposed offers a potentially effective solution for the intelligent remote and real-time monitoring of solar photovoltaic (PV) systems. It demonstrated a high level of accuracy, reaching 98.49%, and can transmit graphical representations to a smartphone application within a time frame of 52.34 seconds. Consequently, the battery's longevity was extended, energy consumption was diminished, and the quality of service (QoS) for real-time applications inside the Internet of Things (IoT) was enhanced.

Lightweight Machine Learning Method for Real-Time Espresso Analysis

Coffee crema plays a crucial role in assessing the quality of espresso. In recent years, in response to the rising labor costs, aging population, remote security/authentication needs, civic awareness, and the growing preference for non-face-to-face interactions, robot cafes have emerged. While some people seek sentiment and premium coffee, there are also many who desire quick and affordable options. To align with the trends of this era, there is a need for lightweight artificial intelligence algorithms for easy and quick decision making, as well as monitoring the extraction process in these automated cafes. However, the application of these technologies to actual coffee machines has been limited. In this study, we propose an innovative real-time coffee crema control system that integrates lightweight machine learning algorithms. We employ the GrabCut algorithm to segment the crema region from the rest of the image and use a clustering algorithm to determine the optimal brewing conditions for each cup of espresso based on the characteristics of the crema extracted. Our results demonstrate that our approach can accurately analyze coffee crema in real time. This research proposes a promising direction by leveraging computer vision and machine learning technologies to enhance the efficiency and consistency of coffee brewing. Such an approach enables the prediction of component replacement timing in coffee machines, such as the replacement of water filters, and provides administrators with Before Service. This could lead to the development of fully automated artificial intelligence coffee making systems in the future.

Monitoring and Controlling System of Smart Mini Greenhouse Based on Internet of Things (IoT) for Spinach Plant (Amaranthus sp.)

Greenhouses, often composed of plastic or glass structures, play a fundamental role in optimizing the environmental conditions essential for successful plant cultivation, ultimately resulting in higher-quality crop yields. The study aims to develop a real-time monitoring and control system for a smart mini greenhouse utilizing the Internet of Things (IoT), with a specific focus on cultivating spinach. The monitoring system is constructed around an ESP32 microcontroller, complemented by a DHT22 sensor for accurate air temperature and humidity measurements, and an RTC DS3231 timer for scheduling tasks. The DHT22 sensor's set point values trigger the fan and misting system operations. The fan activates when the air temperature reaches 32°C, while the misting system turns on when humidity levels (RH) reach 55%. The ESP32 is the central processing unit, enabling internet connectivity through Wi-Fi for real-time data monitoring via the Blynk application. Sensor calibration confirms the system's precision, with regression analyses producing impressive R2 values of 0.989 and 0.952. The shading net control system operates four hours daily, from 11:00 to 15:00 WIB (Western Indonesian Time), optimizing the greenhouse environment. This well-executed system leads to the robust growth of spinach plants, reaching a height of 23.02 cm, sprouting nine leaves, and attaining a weight of 10 grams. The findings from this study highlight the efficiency and effectiveness of the smart mini greenhouse's monitoring and control system, offering promising applications in broader greenhouse management and crop cultivation practices.

Zonal demand-controlled ventilation strategy to minimize infection probability and energy consumption: A coordinated control based on occupant detection

Due to the outbreak of COVID-19, an increased risk of airborne transmission has been experienced in buildings, particularly in confined public places. The need for ventilation as a means of infection prevention has become more pronounced given that some basic precautions (like wearing masks) are no longer mandatory. However, ventilating the space as a whole (e.g., using a unified ventilation rate) may lead to situations where there is either insufficient or excessive ventilation in localized areas, potentially resulting in localized virus accumulation or large energy consumption. It is of urgent need to investigate real-time control of ventilation systems based on local demands of the occupants to strike a balance between infection risk and energy saving. In this work, a zonal demand-controlled ventilation (ZDCV) strategy was proposed to optimize the ventilation rates in sub-zones. A camera-based occupant detection method was developed to detect occupants (with eight possible locations in sub-zones denoted as ‘A’ to ‘H’). Linear ventilation model (LVM), dimension reduction, and artificial neural network (ANN) were integrated for rapid prediction of pollutant concentrations in sub-zones with the identified occupants and ventilation rates as inputs. Coordinated ventilation effects between sub-zones were optimized to improve infection prevention and energy savings. Results showed that rapid prediction models achieved an average prediction error of 6 ppm for CO2 concentration fields compared with the simulation under different occupant scenarios (i.e., occupant locations at ABH, ABCFH, and ABCDEFH). ZDCV largely reduced the infection risk to 2.8% while improved energy-saving efficiency by 34% compared with the system using constant ventilation rate. This work can contribute to the development of building environmental control systems in terms of pollutant removal, infection prevention, and energy sustainability.