Supply Air Flow Rate Research Articles

Energy performance evaluation of the ASHRAE Guideline 36 control and reinforcement learning–based control using field measurements

This study evaluates the energy performance of ASHRAE Guideline 36–compliant control (ASHRAE 36 control) and reinforcement learning (RL)–based control through experimental field tests and a simulation study. Three field tests were conducted at Oak Ridge National Laboratory’s commercial building test facility in Oak Ridge, Tennessee: a baseline with a baseline conventional control, a test with ASHRAE 36 control, and a test with RL-based control. The selected ASHRAE 36 controls were trim and respond control, as well as variable air volume (VAV) box control. We compared the measured supply air temperature of the rooftop unit, VAV box supply air temperature, and VAV box supply airflow rate across the three test cases. The field data indicated that ASHRAE 36 controls operated as specified by ASHRAE Guideline 36. Based on these data, ASHRAE 36 control achieved a 45 % reduction in hourly averaged HVAC energy consumption compared with the baseline, and RL-based control achieved a 66 % reduction. These potential annual energy savings were confirmed using a calibrated whole-building energy model. Compared with the baseline, ASHRAE 36 control reduced HVAC energy consumption by 42 %, and RL-based control achieved a 54 % reduction. Furthermore, RL-based control reduced total HVAC energy consumption by 21 % more than ASHRAE 36 control.

The Prediction of the Leakage Airflow Rate Using the Supply and Return Airflow Rate in a Variable Air Volume System

Pressure differences in the envelope of a building result in leakage airflow (i.e., the unintended flow of air). This can lead to increased building heating and cooling energy, decreased thermal comfort for occupants, and the spread of moisture. To address this problem, it is necessary to know the leakage airflow in a building. Generally, the leakage airflow in a building is calculated by determining the leakage function through fan pressurization methods, such as the blower door test, and substituting the pressure difference measured by the pressure sensor. However, it is difficult to install continuous pressure sensors in an operating building. Therefore, this study proposes a method to utilize the supply and return airflow of an air conditioning system to predict the variation in the leakage airflow with changing indoor and outdoor airflow, and the efficacy of this approach was verified through experiments. The experiment measured the indoor and outdoor pressure difference of the building with a change in the speed of the supply and return fans and the opening rate of the variable air volume (VAV) damper. As a result of the experiment, the indoor–outdoor pressure difference is proportional to the difference between the indoor supply airflow and the ventilation airflow. In addition, the relationship between the pressure difference and the leakage airflow was derived through the pressurization/decompression method using an air handler, and the leakage airflow from the pressure difference generated by the operation of the air conditioning system was calculated. Lastly, the relationship between the supply and return airflow difference and the leakage airflow was derived based on the experimental results, and the leakage airflow was predicted based on the relationship.

A new personalized environment control system for hospital beds with design optimization by Taguchi-based grey relational analysis

The current ward environments consume excessive energy and fail to meet the personal comfort and health needs of patients. A promising solution is to create a personalized bed micro-environment and then extend the ward set-point temperature range. However, there is currently no suitable bed environment control system. This study proposes a novel bedside integrated system with three perforated panels that supplies conditioned air from different directions and prevents direct airflow towards the patient's head region. The system design was optimized using Taguchi-based grey relational analysis (GRA), with predicted mean vote (PMV), draft risk (DR), and personal exposure effectiveness (PEE) considered as response variables. The design variables included supply air temperature, airflow rate, and supply air angles. Taguchi's L16 (44) orthogonal array was employed for the experimental design. The results demonstrate that a low-velocity cold air lake can form above the bed, with the maximum velocity near the patient's head at only 0.2 m/s. In a 28 °C ward, the PMV, maximum DR, and PEE at the bed micro-environment are 0.13, 14.1 %, and 0.67, respectively. This implies that the proposed bed environment control system has the potential to provide both comfort and health benefits while reducing energy consumption. After optimization, the optimal supply air temperature, airflow rate, angles of top panel and side panels are 22 °C, 25 L/s, 0° and 45°, respectively, with an improvement of 5.8 % in the grey relational grade. This study provides a new solution for creating a comfortable and healthy ward environment in an energy-efficient manner.

Indoor environmental quality assessment in passively ventilated classrooms in Germany and estimation of ventilation energy losses

In this field study we present an approach for the comprehensive and room-specific assessment of parameters with the overall aim to realize energy-efficient provision of hygienically harmless and thermally comfortable indoor environmental quality in naturally ventilated non-residential buildings. The approach is based on (i) conformity assessment of room design parameters, (ii) empirical determination of theoretically expected occupant-specific supply air flow rates and corresponding air exchange rates, (iii) experimental determination of real occupant-specific supply air flow rates and corresponding air exchange rates, (iv) measurement of indoor environmental exposure conditions of T, RH, cCO2, cPM2.5 and cTVOC, and (v) determination of real energy demands for the prevailing ventilation scheme. Underlying assessment criteria comprise the indoor environmental parameters of category II of EN 16798-1: Temperature T = 20 °C–24 °C, and relative humidity RH = 25 %–60 % as well as the guide values of the German Federal Environment Agency for cCO2cPM2.5 and cTVOC of 1000 ppm, 15 μg m−3, and 1 mg m−3, respectively.Investigation objects are six naturally ventilated classrooms of a German secondary school. Major factors influencing indoor environmental quality in these classrooms are the specific room volume per occupant and the window opening area. It is concluded that the rigorous implementation of ventilation recommendations laid down by the German Federal Environment Agency is ineffective with respect to anticipated indoor environmental parameters and inefficient with respect to ventilation energy losses on the order of about 10 kWh m−2 a−1 to 30 kWh m−2 a−1.

Multi-scale collaborative modeling and deep learning-based thermal prediction for air-cooled data centers: An innovative insight for thermal management

Investigating the data center (DC) thermal environment and temperature distribution is crucial to responding to unforeseen events such as equipment failure or environmental changes. However, building full-scale simulation models from DC room level to chip level faces significant challenges. In this paper, we propose a distinctive approach that combines multi-scale collaborative modeling with deep learning techniques for thermal prediction in air-cooled DCs. By taking the simulation results of the parent model as the boundary conditions of the child model, we constructed the DC multi-scale simulation model, which significantly reduces the model complexity and computational resources. Leveraging experimental data, the models at different scales were validated separately. The effects of different cooling strategies, air supply temperatures and air supply flow rates on multi-scale simulation models were investigated. Based on the parametric simulation approach, datasets for training data-driven models are constructed. Simultaneously, we propose the CNN-BiLSTM-Attention neural network model to predict the maximum CPU temperature and optimize the hyperparameters of the neural network through by Bayesian optimization. The prediction results of the coupled multi-scale model and the deep learning prediction model show that the absolute error is controlled within ±0.1 K, and the R2 value of the model evaluation metric is as high as 0.9899. Herein, the results provide valuable insights for enhancing thermal management in air-cooled DCs, paving the way for more efficient and resilient DC operations in the future.

Experimental comparison of aerosol transmission in displacement ventilation and mixing ventilation in a meeting scenario

The performance of displacement ventilation (DV) and mixing ventilation (MV) in aerosol contamination control was compared. The considered contamination was an aerosol emitted from a person in meeting scenarios of two and four persons. The experiments were carried out in a full-scale room measuring 4.4 m × 5.2 m × 2.9 m. Particle counting was carried out at 41 measurement points in the room to assess the concentration field of particles in the room and in the inhalation zone. The influence of the supply airflow rate and the number of activated thermal mannequins on the contaminant removal effectiveness were examined. The main conclusion is that the DV system was superior to the MV system in reducing contamination. An enhanced contaminant removal effectiveness of displacement ventilation was observed for all supply air flow rates and increased with higher airflow rates. At lower airflow rates, contamination in the inhalation zone was reduced by 40% compared to mixing ventilation, while at higher flow rates, the reduction surpassed 50%. This study highlights the advantages of displacement ventilation in terms of contamination control, infection prevention and energy efficiency, emphasising the importance of ventilation system selection for indoor environments, particularly those where airborne transmission risks are prevalent.

An artificial neural network based approach to air supply control in large indoor spaces considering occupancy dynamics

Occupancy dynamics can significantly influence indoor thermal environments, especially in large indoor spaces. It is difficult for conventional feedback control systems to respond promptly to occupancy dynamics because of the substantial thermal inertia of large spaces, which leads to unfavorable thermal conditions in environments regulated by such systems. To address this challenge, this study proposes an air supply control approach based on artificial neural networks (ANNs). In the proposed approach, a large space is divided into multiple zones and an ANN model is used to characterize the relationship between occupancy dynamics and the supply air flow rates of each zone, thereby expediting the response of the air-conditioning system to occupancy dynamics. First, a multi-zone thermal environment model was developed to accurately emulate the thermal behavior of each zone. Next, employing the developed model of the environment, the optimal air flow rates required for each zone to maintain the desired thermal environment were estimated for various boundary conditions, which were used as pretraining data for four candidate ANNs. Finally, the best-performing ANN candidate, Long Short-Term Memory (LSTM), was adopted in a case study building via a comparison against several conventional air supply control methods. The results from the case studies demonstrate that the proposed approach can effectively expedite the system response to occupancy dynamics, thereby minimizing the occurrence of overcooling and overheating, and lowering the occupancy-weighted thermal discomfort level by 73.1 %. The proposed approach holds promise for real-time applications based on digital twin architecture.

Research on Thermal Environment of Container Farms: Key Factor Identification and Priority Analysis

Container farms (CFs), a controlled environment agricultural technology designed to solve food insecurity, are receiving increasing attention from researchers. However, the complex geometric structures and artificial lighting used in CFs present challenges in effectively controlling the thermal environment. This study aims to identify the primary factors that impact the thermal environment of CFs while conducting factor ranking and significance analysis, providing a theoretical basis for future thermal environment optimization. The research method of theoretical analysis, CFD simulation, and an orthogonal experimental design were adopted to achieve the above objectives. Theoretical analysis revealed that factors influencing the thermal environment are the HVAC system’s supply air temperature, humidity, flow rate, and the light source used. Four evaluation indices, including the mean value and range between layers of temperature and moisture content, were used. The results revealed that supply air temperature and light source are significant for mean temperature, while supply air temperature and humidity are significant for mean moisture content. In the case of range between layers, supply air flow rate and light source display a significant correlation. These findings suggest that future optimization should prioritize the regulation of the HVAC system’s supply air and light source.

PM reduction performance according to filter grade and diffuser position in a school classroom

Ventilation performance for indoor air quality (IAQ) in schools has emerged as an important social issue due to the high concentrations of particulate matter (PM). The PM reduction performance is analyzed according to filter grade and the location of return diffusers, upper and floor return, selected based on indoor airflow distribution. Performance evaluation has been experimentally analyzed in the full-scale school environmental performance test-bed equipped with a fan filter unit (FFU). Through the experimental measurements in the classroom, it is found that the PM reduction time of the floor return is relatively shorter than that of the upper return. This is due to the increased ventilation efficiency by decreasing the stagnation flow inside the classroom. Although the supply air flowrate is relatively small at 800 cubic meter per hour (CMH), it has a PM reduction effect similar to 1200 CMH for all particle sizes due to the replacement of the conventional upper return with a floor return. Considering that the energy consumption of the Minimum Efficiency Reporting Value (MERV) 16 filter is approximately 1.7 times that of the MERV13 filter, a MERV13 filter is sufficient to demonstrate the performance of a MERV16 filter with the optimal installation of return diffusers.

Design of convertible patient care unit for both non-pandemic and pandemic times: Prototype, building spatial layout, and ventilation design

Convertible patient care units can accommodate non-respiratory infectious disease patients in non-pandemic times and provide isolated treatment for respiratory infectious disease patients during pandemic times. A prototype convertible patient care unit covering a floor area of 1518 m2, featuring 16 wards, and accommodating 40 beds was developed to examine the impact of building spatial layout and ventilation design on the inter-zonal airborne transmission and energy use intensity (EUI) during both non-pandemic and pandemic times. Building spatial layout referred to the presence of patient corridors and anterooms, while ventilation design referred to the location of air terminals and the calculation method of residual air volume (namely, difference between supply and exhaust airflow rates). Adding anterooms provided an 18 % reduction in pressure gradient fluctuations during door-opening events. The absence of exhaust in the medical corridor, anterooms, and wards increased contamination leakages to the patient corridors. Using the differential pressure method to calculate residual air volume was more effective in controlling the inter-zonal pressure gradient than the fixed residual air volume method. Various conversion methods resulted in an 84%–134 % increase of EUI compared to non-pandemic times, without, however, corresponding reduction in inter-zonal airborne transmission risk. The condition of adding both patient corridors and anterooms, exhaust-only patient corridors, anterooms with balanced supply-exhaust airflow rates, and differential pressure method to calculate residual air volume were effective conversion strategies to simultaneously address both the inter-zonal airborne transmission and EUI. These findings provide fundamental information for designing convertible patient care units and revising related guidelines in China.

Applying indirect evaporative chillers for comfort cooling in Northern European commercial buildings: A case study in Sweden

Indirect evaporative chiller (IEC) can produce chilled water below the wet-bulb temperature of outdoor air. To evaluate the potential of applying indirect evaporative chillers for covering the high indoor sensible cooling loads in commercial buildings of Northern European countries, a case study based on a real commercial building in Stockholm was carried out assuming renovation of the existing air-conditioning system by replacing district cooling with an indirect evaporative chiller as cooling source. Numerical models were built for the indirect evaporative chiller as well as for the entire space cooling system, and techno-economic performance evaluation as well as sensitivity analyses were conducted with a validated numerical model to comprehensively evaluate renovation benefits. The simulation results show that, an indirect evaporative chiller fulfilling 80 % of the total sensible cooling load of the design outdoor condition with a dry-bulb outdoor air temperature of 26 °C and a relative humidity of 45 %, can produce chilled water below the wet-bulb outdoor air temperature when the relative humidity is lower than 0.4 for hours in July of year 2015 and 2018. Sensitivity analyses show that reducing the supply air flow rate of the ventilation system from the default setpoint of 1.2 L/(m2·s) to the minimum hygienically required level of 0.35 L/(m2·s) would double the seasonal energy efficiency rating of the air-conditioning system from 6.3 to 12.8. Compared to the original district cooling-based system, the operational expenditure of the renovated system can be saved for optimally 54 k SEK, justifying a capital expenditure of 588 k SEK assuming operation of 15 years. The case study shows that indirect evaporative chiller can potentially be applied for commercial buildings under the and climatic and market context of Sweden, providing an alternative cooling solution for similar applications.

Return Air Grille Position in a Cleanroom for Medicinal Packaging Using CFD Method

A cleanroom is a highly controlled environment; therefore, air quality is of significant concern, and specific physical and microbiological requirements must meet the standard. In addition to the number of particles, another critical parameter in a cleanroom is temperature. USP (The United States Pharmacopeia) 797 recommends that the temperature of a cleanroom be around 20 °C. Air quality is achieved through several parameters and components, such as using a high-efficiency particulate air filter (HEPA), the amount of fresh air entering the room, temperature, pressure difference, and airflow direction. In this study, the cooling load of the room for the filling and sealing process was calculated, and the airflow and temperature distribution patterns between two parameters of the return air grille (RAG) position were compared using Computational Fluid Dynamics (CFD). The first parameter, RAG 1, was placed above the ceiling, while the second parameter, RAG 2, was set on the sidewall. Based on the results of the study, it was found that the heat load generated from the room was 6.99 kW with a cooling coil capacity amounting to 10.77 kW. Moreover, the supply airflow rate was 371.66 l/s. Based on the results of the simulation modelling, it was found that the RAG positioned on the sidewall was more ideal than the RAG positioned above the ceiling since the temperature was more evenly distributed in the room where the RAG was positioned on the sidewall.

A simple method and prediction model for calculating the cooling load of impinging jet ventilation system in office buildings

An appropriate thermal stratification environment can be formed in impinging jet ventilation (IJV) cooling rooms. In this scenario, the well-mixing hypothesis provided by the conventional mixing ventilation is not applicable to calculate the cooling load of IJV systems. In the present study, a simple method using the cooling load ratio (CLR, α) is proposed for calculating the cooling load in the thermal stratification environment of IJV. Numerical simulations are applied to investigate the effect of several influencing factors on the CLR. Univariate analysis results indicate that the key influencing factors of α are the thermal length scale (Lm), supply airflow rate (L) and total heat gain (q*). A prediction model of α (CLR model) is developed related to the three influencing factors of Lm, L and q*. The CLR model has a high prediction accuracy in low q* situations (q* ≤ 2.5), with a slightly reduced accuracy in high q* situations. Overall, the maximum relative error of the CLR model is lower than 12%. Moreover, contour plots of α illustrate that α achieves a minimum level of 0.55, and the values of α vary between 0.55 and 1.0 for all the values of Lm, L and q*. The CLR model can provide a theoretical basis for the determination of cooling load and energy saving potential of IJV systems during the design stage.

A Virtual Supply Airflow Rate Sensor Based on Original Equipment Manufacturer Data for Rooftop Air Conditioners

A Virtual Supply Airflow Rate Sensor Based on Original Equipment Manufacturer Data for Rooftop Air Conditioners

Potential of a bed ventilation system in reducing the risk of exposure to contaminants in infectious wards

A proposed bed ventilation system named Hospital Bed Integrated Ventilation Cleansing Unit (HBIVCU) has shown its great potential in reducing the risk of airborne cross-infection. However, the key operating parameters are still unclear, restricting its practical application. This study numerically investigated the performance of the HBIVCU under various operating parameters (supply and exhaust airflow rates increased from 0 L/s to 5 L/s and 0 L/s to 40 L/s, respectively) in a four-bed infectious ward with different background ventilation rates. Both tracer gas CO2, (simulating aerosols smaller than 5 μm) and particles (mean diameter of 80 μm) in the exhaled by one of the patients were considered. Compared to the ward without the HBIVCU, the concentration of CO2 at the bed microenvironment and breathing height of standing and sitting persons are reduced by more than half when the HBIVCU operates with supply and exhaust airflow rates of 5 L/s and 40 L/s, respectively. For this case, the highest draught risk of 13% at the patients’ head region is obtained. Increasing the supply and exhaust airflow rates of the HBIVCU are both helpful for removing the exhaled gaseous contaminants from the room due to increased induction effect of the local bed ventilation flow. The removal efficiency is around twice higher when the HBIVCU is operating at background ventilation at 6 air changes per hour (ACH) when compared to when it is not operating at background ventilation of 12 ACH. Finally, the HBIVCU can efficiently remove the exhaled gaseous contaminants, though it has no discernible effect on the removal of coughing droplets. The HBIVCU has great potential to reduce the risk of cross-infection and save energy by lowering the background ventilation rate.

Subzone division optimization with probability analysis-based K-means clustering for coupled control of non-uniform thermal environments and individual thermal preferences

Collective air distribution is widely used for thermally comfortable indoor environments but is limited to unified thermal comfort requirements. Advanced collective air distribution has the potential to generate non-uniform thermal environments for individual thermal preferences. This study proposes a subzone division optimization method for nonuniform thermal environments to improve thermal preference satisfaction. The proposed method divided non-uniform thermal environments into subzones using probability analysis-based K-means clustering, minimizing and maximizing the thermal environment differences within and among the subzones, respectively. The number of subzones was determined to maximize thermal preference satisfaction with the coupled control between the nonuniform environments and individual thermal preferences while limiting the percentage of thermal discomfort. The results based on experiments of advanced collective air distribution, i.e., stratum ventilation, showed that thermal preference satisfaction and the percentage of thermal discomfort increased with an increasing number of subzones. Compared with the conventional method (i.e., uncoupled control without subzone division optimization) and recent method (i.e., coupled control without subzone division optimization), the proposed method improved the thermal preference satisfaction by 34.7 % and 11.7 %, respectively, for four subzones. Moreover, with the proposed method, increasing the system control flexibility increased thermal preference satisfaction. Compared with the variable air volume system, the constant air volume system and the system with variable supply airflow rate and temperature improved thermal preference satisfaction by 5.8 % and 22.5 %, respectively. The proposed method contributes to extending the capability of collective air distribution for individual thermal preferences.

Performance boost of a commercial air-to-air plate heat recovery unit by mesh-net insert; thermal-frictional, economic, and effectiveness-NTU analysis

This research proposes, tests, and comprehensively investigates the application of mesh-net to increase the efficiency of any air-to-air plate heat exchanger (mainly as a building heat recovery unit). The idea is tested through a commercial heat-recovery unit and all parameters including Nusselt number, pressure drop, friction factor, thermal performance factor, effectiveness, number of thermal units, pumping power and economical profitability are comprehensively investigated and reported with and without mesh-net insert. In economic evaluation the price of electricity and type of building heating system (resistance heater, heat pump and so on) are considered. In the maximum air flow rates, the overall heat transfer coefficient is enhanced from 24 to 36 W/m2K. Nusselt number increases up to 75 % depending on air flow rate. The economic results were found very interesting, and even by paying further fan power due to the higher pressure drop, the economic profitability is positive when the building heating system is resistance heater or heat pump with lower coefficient of performance. The profitability of the mesh net insert is higher for the region with higher electricity price. This means the gained recovered heat overcomes the further energy required for pumping power. Nonetheless, final decision making from pure economic viewpoint depends on the desired supply air flow rate, type of heating system and local price of electricity.

Numerical modeling of non-uniform indoor temperature distribution for coordinated air flow control

The indoor thermal environment is usually non-uniformly distributed in parameters such as temperature and velocity. For precise control of indoor environment, it is necessary to figure out the indoor non-uniform temperature distribution (INUTD) that empowers independently zone control according to the different requirements of occupants. Computational Fluid Dynamics (CFD) tool is usually used to obtain the INUTD, but it consumes huge computational resources and time, which may not be suitable for coupling with control system. To address this research question, this study proposes a numerical modeling method for predicting the INUTD and air flowrate response of multiple diffusers for coordinated air flow control. Firstly, we establish a dataset with 5000 cases, along with the results of INUTD for each case. Then two models, namely room thermal response model (RTRModel) and air flowrate prediction model (AFPModel), are developed by machine learning algorithms to predict indoor temperature and supply air flowrate, respectively. The results show that proposed models are both fast in prediction, less than 1 s for each case. The standard deviation of error in RTRModel developed with support vector machine algorithm is 0.0041 while that in AFPModel developed with Convolutional Neural Network algorithm is 0.0198. Further, a comparative analysis has been conducted between the AFPModel with and without optimization algorithm. The results reveal that using optimization algorithm is more accurate, but it takes more time. While numerical modeling can instantaneous response with qualified accuracy. The proposed method can contribute to independently zonal environment control and occupant-centered micro-environment control.

Pseudo-optimal discharge pressure analysis of different CO2 electric vehicle heat pumps based on cabin thermal model

The discharge pressure of electric vehicle heat pumps, aiming for peak COP values, is termed the pseudo-optimal discharge pressure for dynamic regulation, distinguishing it from the optimal discharge pressure at a constant compressor speed. A theoretical model was presented to analyze the impacts of operational parameters considering the variation of cabin loads with operating conditions. Based on simulation results, the effects of ambient temperature, cabin temperature, drive speed, and supply air flow rate on the pseudo-optimal discharge pressure were investigated for single-stage and two-stage compression systems, respectively. Among them, the ambient temperature had the highest degree of influence, more than 45 % in different systems. Heat recovery in electrical systems introduced slight variations, less than 1 bar, to the pseudo-optimal discharge pressure by affecting the evaporation temperature. While the trend remains consistent across the different systems, the values of pseudo-optimal discharge pressure are higher for the two-stage compression. At −10/20 °C, two-stage compression provides a 49.42 % higher COP compared to single-stage while maintaining a safe discharge temperature. In addition, the heating efficiency under the improved prediction can be increased by 18.49 % compared to the existing research. Predictions for the pseudo-optimal discharge pressure provide a basis for effective and cleaner control of electric vehicle heat pumps.

Assessing the impact of particulate fouling on the long-term performance of energy recovery ventilators

Energy recovery ventilators (ERVs), which integrate fresh air supply, air purification, and energy recovery, are prominently employed in buildings. Particulate fouling and dynamic climate conditions in real-time scenarios could cause the deviation of operating parameters from the designed values, impacting the long-term performance of ERVs. In this study, a non-linear regression model of energy exchanger involving imbalanced airflow rate conditions was derived based on experimental data, considering the decreased supply air volume caused by dust-loading of fresh air filter. Model validation presented errors within ±10 %. Furthermore, an ERV model was established by integrating the energy exchanger, filter, and fan. Simulation results indicate that particulate fouling could decrease the instant supply airflow rate and recovered energy to maximums of 15 % and 12 % respectively, compared to the ideal performance in the clean state. Analysis throughout the heating season concludes that, the reduced recovered energy together with the unorganized air infiltration consequent on the imbalanced airflow rates could increase the seasonal fresh air load by 10.9 %, 13.1 %, and 24.1 % in three typical cities, Shanghai, Beijing, and Harbin, respectively. The proposed model provides a reliable platform for evaluating the performance and analyzing the maintenance strategies of ERVs, contributing to improving their practical effects.