Minimum Energy Consumption Research Articles

Air gap membrane distillation unit operated by thermoelectric module

Membrane Distillation (MD) is a promising and evolving technology with substantial potential for efficient freshwater production. However, most of the traditional MD systems typically incorporate several components, including a coolant chamber, coolant stream, coolant pump, chiller, and coolant lines. Eliminating these key components offers numerous benefits to MD systems. Therefore, this work presents an experimental investigation of a novel hybrid air gap membrane distillation (AGMD) unit coupled with thermoelectric modules (TEMs). The thermoelectric module acts as a heat pump by simultaneously providing both the heating and the cooling demands of the air gap membrane distillation unit. In the TEM-AGMD prototype, the hot surface of the TEM is deployed to heat the feed stream to be treated, while the cold side of the TEM is in close contact with the AGMD condensation plate, thereby eliminating the need for the cooling stream, coolant line, coolant pump, chiller, and coolant chamber. Thus, the investigated system exhibited fewer components and needed no pumping power for the cooling stream, resulting in a compact and an energy efficient membrane distillation (MD) system. Results from the experiment indicate that optimal system performance can be achieved by increasing the number of thermoelectric modules, implementing multi-stage membrane distillation, and intensifying the circulating feed flowrate. Furthermore, operating the thermoelectric modules at high power input boosts unit productivity but worsens the unit's specific energy consumption. Moreover, the proposed TEM-AGMD unit can achieve a minimal specific energy consumption of 962 kWh/m3. The proposed prototype boasts an easy design that enables outstanding water desalination with exceptional salt rejection and minimal power consumption. The combination of thermoelectric module with membrane distillation, capitalizing on recent advancements in MD technology, holds great promise for developing a hybrid system for decentralized water treatment and desalination.

Design and analysis of low power sense amplifier for static random access memory

<p>Today’s era is a digital world where each and every section of the society is experiencing and encountering with semiconductor chips. In very large-scale integration (VLSI) circuits the design of static random-access memory (SRAM) plays a crucial role in ensuring both low-power consumption and high-speed performance. The sense amplifiers (SA) are integral parts for information accessing storage in SRAM IC design. This paper introduces a dual voltage latch sense amplifier (DVLSA) for SRAM integrated circuits (IC). The comparative analyses of various SA are studied and then design a low-power SA through the implementation of energy-efficient technique. Further, we have elucidated the causes of delay and power dissipation in different SA with useful solutions and performance evaluation is conducted by comparing the proposed design with existing SA reported in the literature. The performance parameters such as power 1.604 uw, energy 470.50 fJ, delay 80.04 ps, and current 5.406 are scrutinized to assess the efficiency of the designs. The cell outcomes have been validated with cadence tool on 180 nm technology and operate at 1.8 V. The proposed design, namely, DVLSA demonstrates minimal energy consumption and low power dissipation, making it a promising advancement in SRAM IC technology.</p>

Energy Consumption Minimization for Hybrid Federated Learning and Offloadable Tasks in UAV-Enabled WPCN

Energy Consumption Minimization for Hybrid Federated Learning and Offloadable Tasks in UAV-Enabled WPCN

A heuristic approach to energy efficient user association in ultra‐dense HetNets using intermittent scheduling strategies

AbstractThe ultra‐dense deployment of pico cells in 5G heterogeneous networks (HetNets) has raised serious concerns regarding interference and energy consumption. Both industry and academia are focusing on enhancing network energy efficiency (EE) while maintaining satisfactory quality of service (QoS) levels. However, finding an optimal solution to NEE is very challenging, especially in ultra‐dense HetNets. Here, a user association and power management algorithm is presented that follows a heuristic approach and aims to maximize EE while satisfying other network requirements. The proposed algorithm associates users based on criteria that consider the users’ EE and minimizes energy consumption by intermittently switching into sleep mode base stations with the highest impact on overall network EE. The performance of this solution is evaluated in a realistic multi‐cell two‐tier scenario considering both co‐tier and cross‐tier interference by comparing it with two other solutions: a heuristic approach based on standardized eICIC, and an optimization approach based on Lagrangian dual decomposition. The simulation results show that our solution outperforms benchmarking solutions in terms of EE, average user rate, and network throughput while minimizing energy consumption.

Performance analysis of precooling systems for cryogenic carbon capture: A comparative study of theoretical, numerical, and experimental methods

The urgency of addressing climate change has necessitated innovative and practical approaches to reducing greenhouse gas emissions. Cryogenic Carbon Capture (CCC) technology has emerged as a promising solution for capturing CO2 from industrial emissions. This study investigates a simplified design for a precooling system within CCC technology, focusing on optimizing the efficiency and reliability of the system while minimizing energy consumption. The research examines the effects of CO2 concentration in a gas mixture (simulated flue gas, nitrogen and carbon dioxide), cooling bath temperature, and gas mixture flow rate on the performance of heat exchangers in the precooling system. Theoretical, numerical, and experimental analyses were conducted to assess the system's performance. The use of liquid nitrogen at −196 °C in the cooling bath was found unsuitable due to CO2 freezing within the pipes. Instead, a mixture of dry ice and isopropyl alcohol at −78.5 °C proved effective in maintaining consistent temperature and pressure conditions without causing CO2 blockages. Numerical simulations highlighted the importance of optimizing pipe length to balance temperature control and pressure dynamics, with a 140 cm pipe length identified as optimal for heat exchanger design. Experimental results revealed that longer pipes enhance cooling performance due to increased heat exchange surface area, while higher CO2 compositions and flow rates result in higher outlet temperatures and pressures. The study emphasizes the need for further research and simulation work to refine heat exchanger designs for industrial applications, aiming to develop systems that maximize cooling efficiency while ensuring reliable operation.

Fine-scale movement response of juvenile brown trout to hydropeaking

Juvenile fish are known to be the most impacted during hydropeaking events due to stranding or uncontrolled drift resulting from changes to water depth and flow velocity. To shed light on their response to such hydraulic alterations, we coupled flume experiments with image-based fish tracking and quantified the fine-scale movement behavior of wild (n = 30) and hatchery-reared (n = 38) brown trout (Salmo trutta) parr. We exposed fish to two distinct hydropeaking treatments in a laterally inclined (14 %) flume section stocked with real cobbles to create refuge and heterogeneous hydraulic conditions. Fish were individually acclimated (20 min) to baseflow (Q = 1.6 L s-1) and then exposed to three consecutive hydropeaking events, reaching peakflows tenfold larger than baseflow (Q = 16 L s-1). We found that, within just minutes, fish exhibited fine-scale movement responses to cope with the change of hydrodynamic conditions. Fish moved perpendicular to the main flow direction to shallow areas as these became submerged during discharge increase, holding position at low velocity zones. This resulted in a significant difference (p < 0.001) in lateral occupancy of the experimental section between baseflow and peakflow. During peakflow, fish occupied specific positions around cobbles and exhibited swimming behaviors, including bow-riding and entraining, that allowed them to hold position while likely minimizing energy expenditure. As a result, swimming distance reduced 60–70 % compared to baseflow. During the decrease in discharge following peakflow, fish abandoned areas falling dry by moving laterally. In the treatment with the larger down-ramping rate, the time to initiate relocation was lower while the relocation speed was higher. This study shows that, for the conditions investigated here, brown trout parr is capable of swiftly deploying multiple behavioral responses to navigate rapid changes in hydrodynamic conditions. These findings can be incorporated into habitat modeling and improve our capacity to inform hydropeaking mitigation efforts.

Joint differential evolution algorithm in RIS-assisted multi-UAV IoT data collection system

This paper investigates a Reconfigurable Intelligent Surface (RIS)-assisted multi-UAV data collection system, in which unmanned aerial vehicles (UAVs) collect data from Internet of Things (IoT) devices. The RIS, mounted on building surfaces, plays a vital role in preventing obstruction and improving the communication quality of the IoT-UAV transmission link. Our aim is to minimize the energy consumption of this system, including the transmission energy consumption of IoT devices and the hovering energy consumption of UAVs, by optimizing the deployment of UAVs and the phase shifts of RIS. To achieve this goal, a multi-UAV deployment and phase shift of RIS optimization algorithm (MUDPRA) is proposed that consists of two phases. In the first phase, a joint differential evolution (DE) algorithm with a two-layer structure featuring a variable population size, namely DEC-ADDE, is proposed to optimize the UAV deployment. Specifically, each UAV’s location is encoded as an individual, with the whole UAV deployment is considered as the population in DEC-ADDE. Thus, a differential evolution clustering (DEC) algorithm is employed initially to initialize the population, which allows for obtaining better initial UAV deployment without the need for a predefined number of UAVs. Subsequently, an adaptive and dynamic DE algorithm (ADDE) is employed to produce offspring population to further optimize UAV deployment. Finally, an adaptive updating strategy is adopted to adjust the population size to optimize the number of UAVs. In the second phase, a low-complexity method is proposed to optimize the phase shift of RIS with the aim of enhancing the IoT-UAV data transmission rate. Experimental results conducted on eight instances involving IoT devices ranging from 60 to 200 demonstrate the effectiveness of MUDPRA in minimizing energy consumption of this system compared to six alternative algorithms and three benchmark systems.

An Alternative Reinforcement Learning (ARL) control strategy for data center air-cooled HVAC systems

Energy efficiency of data center is of great concern globally due to their large amount of energy consumption and the foreseeable growth in the demand of digital services in the future. Advanced control strategies are needed to reduce energy consumption. However, the optimization of data center HVAC control is a challenge task due to the complexity of the thermal dynamic models of buildings and uncertainties associated with both server loads and outdoor temperature. In this paper, we propose a new control strategy called Alternately-Reinforcement Learning-control(ARL), which realizes the alternating control of RL and proportional, integral and derivative (PID) for optimizing the control of air-cooled HVAC systems in data centers. The control object of the ARL is the speed set of the compressor and the condensing fan, and the control goal is to minimize energy consumption while maintaining temperature stability. The applied RL algorithm is Deep deterministic policy gradient (DDPG) and Proximal policy optimization (PPO). We pre-train the ARL strategy in offline environment firstly and deploy it in real data center environment for online testing. The test results show that the ARL has significant advantages in maintaining temperature stability while reducing energy consumption, and the PPO algorithm performs better than the DDPG algorithm. Compared with the PID algorithm, the PPO algorithm can save energy by 5.27%, and the temperature control effect can be improved by 3.27%,which indicates the feasibility of the ARL for implementation in real data centers.

Multi-objective optimization of switchable suspended particle device vacuum glazing for comfort and energy efficiency in school typologies under hot climate

This study focuses on the multi-objective optimization of a switchable Suspended Particle Device (SPD) vacuum glazing system to reduce energy use while ensuring thermal and visual comfort in schools located in arid desert environments. A detailed synergy analysis was performed on a representative floor from three school classroom typologies, comparing suspended particle device vacuum glazing in its OFF and ON states against conventional double-glazing with air gaps windows. This analysis employed an advanced simulation framework integrating Rhino-Grasshopper with Open Studio Model, Colibri 2.0, and Design Explorer2 software to evaluate energy consumption, Adaptive Comfort Percentage (ACP), and Useful Daylight Illuminance (UDI). Thermal comfort varied across typologies and orientations, with the atrium with skylight typology frequently meeting or approaching the 80 % Adaptive Comfort Percentage benchmark. However, the southern and eastern classrooms in the enclosed atrium with clerestory typology did not exceed a 39 % adaptive comfort percentage. The comprehensive parametric and multi-objective optimization simulation revealed that suspended particle device vacuum glazing in its 'OFF' state did not fulfill the UDI300lux–1000lux criteria across all typologies, even with maximal Window to Wall Ratio (WWR) and skylight ratio (SR). However, the enclosed atrium with clerestory, integrating SPD vacuum glazing with a 40 % Window to Wall Ratio configuration, emerged as particularly effective in achieving optimal useful daylight illuminance distribution, minimizing energy consumption, and ensuring satisfactory adaptive comfort percentage across various orientations. These findings underscore the potential of multi-objective optimization of suspended particle device vacuum glazing, combined with strategic Window to Wall Ratio adjustments, as a viable alternative to traditional glazing systems in hot desert climates. The adaptability of suspended particle device vacuum glazing highlights its significant potential for achieving thermal comfort, enhancing sustainable architectural design, and improving energy efficiency in educational buildings within extreme climate zones.

Reducing Energy Demand in Concrete Pavements by the Use of Blended Cements

This research explores strategies to minimise energy consumption and enhance environmental sustainability in road construction. Focusing on concrete pavement structures, the study evaluates the impact of substituting Portland cement with environmentally friendly alternatives such as fly ash and blast furnace slag. A comprehensive model is employed to analyse the energy demands of different pavement types, considering various cement replacements over their lifetime, from the initial extraction of materials to the conclusion of construction. Results indicate an energy saving potential of 8.63% by substituting 10% of Portland cement with fly ash, while an impressive reduction of 58.63% in cement production energy is achieved by replacing Portland cement with 80% blast furnace slag. The study underscores the significant role of cement variations in mitigating energy consumption, emphasizes the potential of blast furnace slag as a sustainable alternative as well as highlights the significance of alternative cement types in reducing energy consumption in concrete pavement construction, aligning with environmental sustainability goals and offering insights for more eco-friendly infrastructure development.

Utility-Driven End-to-End Network Slicing for Diverse IoT Users in MEC: A Multi-Agent Deep Reinforcement Learning Approach.

Mobile Edge Computing (MEC) is crucial for reducing latency by bringing computational resources closer to the network edge, thereby enhancing the quality of services (QoS). However, the broad deployment of cloudlets poses challenges in efficient network slicing, particularly when traffic distribution is uneven. Therefore, these challenges include managing diverse resource requirements across widely distributed cloudlets, minimizing resource conflicts and delays, and maintaining service quality amid fluctuating request rates. Addressing this requires intelligent strategies to predict request types (common or urgent), assess resource needs, and allocate resources efficiently. Emerging technologies like edge computing and 5G with network slicing can handle delay-sensitive IoT requests rapidly, but a robust mechanism for real-time resource and utility optimization remains necessary. To address these challenges, we designed an end-to-end network slicing approach that predicts common and urgent user requests through T distribution. We formulated our problem as a multi-agent Markov decision process (MDP) and introduced a multi-agent soft actor-critic (MAgSAC) algorithm. This algorithm prevents the wastage of scarce resources by intelligently activating and deactivating virtual network function (VNF) instances, thereby balancing the allocation process. Our approach aims to optimize overall utility, balancing trade-offs between revenue, energy consumption costs, and latency. We evaluated our method, MAgSAC, through simulations, comparing it with the following six benchmark schemes: MAA3C, SACT, DDPG, S2Vec, Random, and Greedy. The results demonstrate that our approach, MAgSAC, optimizes utility by 30%, minimizes energy consumption costs by 12.4%, and reduces execution time by 21.7% compared to the closest related multi-agent approach named MAA3C.

Numerical study on solar heating system with different auxiliary heat sources

In recent years, extensive research has focused on leveraging solar energy as a primary contributor to renewable energy applications, emphasizing the optimization of energy systems tailored to regional demands and resources. This study proposes a solar energy-based heating system and evaluates the impacts of various auxiliary heat sources in Zhengzhou, China (latitude 34.75°). The research evaluates the influence of different auxiliary heat sources on system performance and investigates the optimal tilt and azimuth angles for solar collectors to maximize thermal efficiency. Results indicate that integrating a heat pump as an auxiliary heat source minimizes energy consumption and enhances economic viability. Notably, the optimal tilt angle of the solar collector deviates by approximately 5° from the geographical latitude. Moreover, analysis reveal consistent trends in azimuth and installation angles, particularly when the optimal azimuth angle is 0°, thereby impacting solar collector efficiency.

Numerical Investigation of Inlet Height and Width Variations on Separation Performance and Pressure Drop of Multi-Inlet Cyclone Separators

Multi-inlet cyclone separators can play a vital role in industrial processes by enhancing particle separation efficiency and minimizing energy consumption. This numerical study investigates multi-inlet cyclone separators to enhance their performance using a constant flow rate with a varying inlet height and width. By systematically varying the inlet height and width, three-inlet and four-inlet cyclone separators are developed and evaluated, termed 3 inlet-a, 4 inlet-a, 3 inlet-b, and 4 inlet-b. The findings reveal that increasing the number of inlets without changing the total inlet area does not improve the separation performance. However, strategic modifications to the inlet height and width significantly enhance the separation efficiency. Notably, the 3 inlet-a and 4 inlet-a designs achieve higher separation efficiencies at a 1.22 m3/s flow rate without increasing the pressure drop. Meanwhile, the 3 inlet-b and 4 inlet-b models demonstrate superior performances, with a higher separation efficiency and a pressure drop only marginally higher than the two-inlet design. This study provides valuable insights into the impact of inlet variations on cyclone separator performance, guiding future efforts to enhance the separation efficiency in multi-inlet designs.

Energy Consumption Minimization with SNR Constraint for Wireless Powered Communication Networks.

The article addresses the energy consumption minimization problem in wireless powered communication networks (WPCNs) and proposes a time allocation scheme, named DaTA, which is based on the Different Target Simultaneous Wireless Information and Power Transfer (DT-SWIPT) scheme such that the wireless station can share the remaining energy after transmission to the Hybrid Access Point (HAP) to those who have not transmitted to the HAP to minimize the energy consumption of the WPCN. In addition to proposing a new frame structure, the article also considers the Signal-to-Noise (SNR) constraint to guarantee that the HAP can successfully receive data from wireless stations. In the article, the problem of minimization of energy consumption is formulated as a nonlinear programming model. We employ the SQP (Sequential Quadratic Programming) algorithm to figure out the optimal solution. Moreover, a heuristic method is proposed as well to obtain a near-optimal solution in a shorter time. The simulation results showed that the proposed scheme outperforms the related work in terms of energy consumption and energy efficiency.

Active learning-based machine learning approach for enhancing environmental sustainability in green building energy consumption

Green building (GB) techniques are essential for reducing energy waste in the construction sector, which accounts for almost 40% of global energy consumption. Despite their importance, challenges such as occupant behavior and energy management gaps often result in GBs consuming up to 2.5 times more energy than intended. To address this, Building Automation Systems (BAS) play a crucial role in enhancing energy efficiency. This research develops a predictive model for GB design using machine learning to minimize energy consumption and improve indoor sustainability. The dataset is utilized to predict cooling and heating individually, with data visualization by graphically illustrating dataset features and preprocessing through Z-Score normalization and dataset splitting. The proposed model, based on active learning and utilizing ML regressors such as Random Forest (RF), Decision Tree (DT), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), CatBoost (CB), Light Gradient Boosting Machine (LGBM), K-Nearest Neighbor (KNN), and Logistic Regressor (LR), shows significant performance improvements. The CBR-AL model achieves impressive results with values of 0.9975 for cooling (Y1) and 0.9883 for heating (Y2), indicating a high level of accuracy. The model’s success in reducing energy consumption and improving sustainability has potential ripple effects, including substantial cost savings, reduced carbon footprints, and improved operational efficiency in green buildings. This approach not only enhances environmental sustainability but also sets a benchmark for future advancements in predictive modelling for energy management.

Real-Time Optimal Scheduling of a Water Diversion System Using an Improved Wolf-Pack Algorithm and Scheme Library

A water diversion system (WDS) with cascade pumping stations (CPSs) plays an important role in the application of water resources. However, high energy consumption is reported due to unreasonable scheduling schemes and long decision times. Herein, this paper presents a new method to achieve optimal scheduling schemes effectively, including the head allocation of CPSs, the number of running pumps, and pump blade angles. A double-layer mathematical model for a WDS was established with the goal of achieving minimal energy consumption, considering the constraints of flow rate, water level, and the characteristics of pump units. The inner-layer model was used to obtain scheduling schemes of single-stage pumping stations, as well as the water levels and flow rates of water channels, while the outer-layer model was used to optimize inter-stage head allocation. An improved wolf-pack algorithm (IWPA) was proposed to solve the model, using a Halton sequence to obtain the uniform initial population distribution and introducing simulated annealing (SA) to improve the global searchability. Moreover, an idea for a pre-established scheme library was suggested for inner-layer models to obtain the solutions in real time with less calculation workload. Taking an actual project as a case, in contrast with the actual schemes, the optimal scheduling method could result in energy savings of 14.37–20.39%, a CO2 emission reduction of 13–32 tons per day, and water savings of 0.14–18.34%. Moreover, the time complexity decreased to square order, and the CPU time of the optimal method was about 1% that of the traditional method. This study provides an efficient method for the high-value utilization of energy and water resources for a WDS.

Novel hybrid BTMS by considering safety and driving cycle under extreme fast charge/discharge rates

A battery thermal management system integrating phase change material and mini-channels, with a focus on safety and economic considerations, is proposed to enhance thermal performance across various working conditions, safety scenarios, and realistic driving cycles while minimizing energy consumption. A battery thermal model and PCM simulation model were developed and validated using experimental data. Numerical analyses were conducted to compare the combination of PCM and liquid cooling (hybrid cooling) with fully liquid cooling under different charge/discharge rates and realistic driving cycles, evaluating their safety characteristics, power consumption, and thermal efficiency. The results demonstrated that the hybrid cooling approach can effectively maintain both the maximum temperature and the temperature difference within a desirable range, even when the inlet velocity is reduced from 0.12 to 0.05 m/s compared to liquid cooling. Additionally, the hybrid BTMS provides better working conditions for the battery pack, requiring only 4 × 10−5 W of pumping power compared to 16 × 10−5 W in the liquid cooling system. This underscores the capability of the designed BTMS to cool high-capacity battery packs with significantly lower fluid flow rates. Furthermore, the performance of the proposed cooling system was examined in the event of liquid channel failure, with results showing that the hybrid BTMS can successfully maintain the battery's maximum temperature within an allowable range during fast charge/discharge processes. Lastly, evaluations under realistic driving conditions revealed the superiority of hybrid cooling in reducing peak temperatures and minimizing battery temperature variation.

Optimization Method of Mine Ventilation Network Regulation Based on Mixed-Integer Nonlinear Programming

Mine ventilation is crucial for ensuring safe production in mines, as it is integral to the entire underground mining process. This study addresses the issues of high energy consumption, regulation difficulties, and unreasonable regulation schemes in mine ventilation systems. To this end, we construct an optimization model for mine ventilation network regulation using mixed-integer nonlinear programming (MINLP), focusing on objectives such as minimizing energy consumption, optimal regulation locations and modes, and minimizing the number of regulators. We analyze the construction methods of the mathematical optimization model for both selected and unselected fans. To handle high-order terms in the MINLP model, we propose a variable discretization strategy that introduces 0-1 binary variables to discretize fan branches’ air quantity and frequency regulation ratios. This transformation converts high-order terms in the constraints of fan frequency regulation into quadratic terms, making the model suitable for solvers based on globally accurate algorithms. Example analysis demonstrate that the proposed method can find the optimal solution in all cases, confirming its effectiveness. Finally, we apply the optimization method of ventilation network regulation based on MINLP to a coal mine ventilation network. The results indicate that the power of the main fan after frequency regulation is 71.84 kW, achieving a significant energy savings rate of 65.60% compared to before optimization power levels. Notably, ventilation network can be regulated without adding new regulators, thereby reducing management and maintenance costs. This optimization method provides a solid foundation for the implementation of intelligent ventilation systems.

Neuron-astrocyte interaction-inspired percolative networks with metal microdendrites and nanostars for ultrasensitive and transparent electronic skins

Biological systems provide innovative designs for electronic devices, optimizing network configurations for high-performance signal transmission with minimal energy consumption. The brain, as one of the most complex biological structures, demonstrates efficient network design through the multiscale radial networks of neurons and astrocytes. Emulating these brain networks offers a blueprint for the development of ultrasensitive pressure sensors for electronic skin, aiming to provide a more intuitive and sensitive mode of interaction between humans and machines. Herein, we propose a neuromorphic percolative network inspired by neuron-astrocyte interactions for ultrasensitive pressure sensors employing metal microdendrites and nanostars. Electromechanical investigation through representative volume elements simulation reveals that the optimized arrangement of microdendrites and nanostars in the neuromorphic percolative system enhances the percolation threshold and probability. Following these simulation results, we developed a neuromorphic percolative polyurethane (NP-PU) matrix utilizing the metal microdendrite-nanostar networks. The augmented quantum tunneling effect in the NP-PU matrix was investigated through electrochemical impedance spectroscopy and capacitance analysis. The fabricated piezoresistive pressure sensor with the NP-PU matrix shows ultrahigh sensitivity (160.3 kPa−1) at a low pressure range and a low limit of detection resolution (4 Pa), enabled by multi-channel quantum tunneling in the metal particle networks. Furthermore, the sensor maintains excellent mechanical flexibility and high optical transparency (75.4 %), improving its efficacy in applications like electronic skin and force touch panel. Our study highlights the potential of leveraging biological system-inspired network designs for crafting advanced electronic devices.

Air pollutant removal performance using a BiLSTM-based demand-controlled ventilation method after tunnel blasting

Efficient tunnel ventilation is essential for ensuring construction safety and protecting personnel health during tunnel construction. This study proposes a demand-controlled ventilation (DCV) method on the basis of deep learning algorithm to both improve pollutant removal efficiency and reduce energy consumption. The DCV method utilizes a two-layer bidirectional long short-term memory algorithm (BiLSTM) to predict pollutant concentrations. The air volume is dynamically adjusted based on the gaseous pollutant removal requirements. The coefficient of ventilation performance (COVP) is proposed to evaluate the performance of two ventilation methods (DCV and constant air-volume ventilation (CAV)) through computational fluid dynamics (CFD) simulations. The results show that the DCV results in a lower maximum average CO concentration and higher removal efficiency in the heading area (372.3 mg/m3) than the CAV does (404.1 mg/m3). The fan's energy consumption of DCV is 64.6% lower than that of CAV during a 1000 s ventilation period. The COVPs for both methods exhibit temporal variation and achieves their maximums (2.25 for DCV and 0.741 for CAV) after reaching the constraint conditions (air volume threshold). The DCV method expedites pollutant elimination, reduces construction waiting period, and minimizes energy consumption, providing a novel application of a deep learning algorithm in construction engineering.