Air Mass Flow Research Articles

Numerical simulation of an efficient circular solar air heater integrated with a CPC

A numerical analysis of a solar air heater is conducted to evaluate the thermal performance of the proposed solar collector under various situations for providing high-temperature airflows. The research investigates the design of a circular solar air heater including revolving airflow combined with a compound parabolic concentrator to enhance incident radiation. The two principal components of the circular heater and the applied concentrator possess compatible geometries and are well integrated. The numerical CFD study is conducted by solving the Navier-Stokes and energy equations for the primary forced convection airflow in the circular solar air heater and the free convection airflow within the cavity of the compound parabolic concentrator. Multiple test cases with varying solar irradiation and air mass flow rates are analyzed, incorporating surface-to-surface radiation. The CFD study of the circular solar air heater is compared with the experimental results. In the analyzed test cases with an air mass flow rate of 0.01 kg/s and a solar heat flux of 1000 W/m2, the thermal efficiency is calculated to be 70 %, despite the elevated outlet air temperature reaching 120 °C. This indicates a 100 % increase in efficiency compared to conventional smooth duct solar air heaters. The research concludes that the circular solar air heater with revolving airflow, combined with a compound parabolic concentrator, results in a highly efficient heat exchanger for generating high-temperature airflow suitable for many applications.

Numerical assessment on a hybrid axial throughflow cooling scheme applied to the thermal management of bump-type gas foil bearings

Axial throughflow cooling is a practical thermal management solution for gas foil bearings (GFBs) with ultrahigh rotational speeds and small bearing clearances. The present study conducted a numerical investigation to assess a hybrid axial-throughflow cooling design (both inner cooling flow passing through the hollow shaft and outer cooling flow passing through the rotor–stator gap) for a specific radial bump-type gas foil bearing using the fluid–solid coupled modelling methodology. First, the individual effects of each cooling flow (i.e., the outer cooling mode only and the inner cooling mode only) on the GFB thermal behaviours are directly compared under a fixed rotational speed of ω = 1 × 105 rpm with a preset eccentricity ratio of ε = 0.9. The outer cooling mode exhibited superior cooling efficiency compared with the inner cooling mode with the same cooling air usage, albeit at the cost of a significantly greater flow pressure drop. Second, the conjugate roles of the hybrid cooling flows on the GFB thermal behaviours are related to the total cooling air mass flow rate of mtotal = 10 kg/h. Nine flow distribution relationships were comparatively studied between the two cooling flows under the same preset static bearing load of F = 31 N, wherein the percentage of the outer cooling flow (mouter/mtotal) varied from 10 % to 90 %. The heat removal pathway of the outer cooling flow was found to be dominant. The outer cooling flow exhibited a heat removal proportion close to 60 % when its distribution percentage was 30 %. The results of a comprehensive performance evaluation that considered the peak temperature reduction and cooling air pressure drop suggest a favourable distribution percentage of the outer cooling flow in the range of 30–40 %.

Sensitivities of Geometric Parameters and Inlet Conditions on the Flow-Heat Characteristics of the Precooler in SABRE

A physical model for the precooler in a SABRE engine was established, and both the influencing degrees and physical mechanisms of inlet conditions and geometric parameters on the flow-heat transfer characteristics of the precooler unit were explored through parametric analysis and sensitivity analysis, respectively. The results demonstrated that the air massflow rate exerted the greatest influence on the total pressure loss coefficient of the precooler unit due to its significant impact on airflow velocity and thermal loading. The inlet total temperature had a dominant effect on heat transfer rate, owing to its substantial influence on air viscosity and thermal loading. Furthermore, both alone and in combination with air massflow rate, inlet total pressure exhibited a greater impact on total pressure loss of precooler unit compared to inlet total temperature and its coupling effects with air massflow rate. In contrast, both air massflow rate and its coupling effects with inlet total temperature significantly affected the heat transfer rate. On the other hand, tube spacing had the most significant impact on both the total pressure loss coefficient and heat transfer rate due to its substantial influence on air throughflow area and acceleration between microtubes. Moreover, the number of tube rows played a predominant role in determining the heat transfer rate of the precooler unit as it caused significant changes in the contact area between the hot air and the microtubes, as well as airflow velocity. However, only two geometric interaction terms (corresponding to interactions between the number of tube rows and tube spacing, as well as between tube spacing and tube diameter) significantly affected the total pressure loss coefficient, and no interaction term was found to be significant for influencing the heat transfer rate. Eventually, two optimal schemes involving inlet conditions and geometric parameters were established to enhance the flow-heat transfer characteristics of the precooler unit.

Experimental thermal analysis of brake cooling relative to mass flow of air through a ventilated brake disc

Individual component testing is an integral part of vehicle development and can be performed in multiple stages of the product development process. One such component assembly that often requires extensive testing is the brake system. The brake system is crucial for vehicle safety and, thus, needs to be validated from a functional perspective.A test rig setup to accommodate a brake caliper fixture, as well as a funnel housing an anemometer, was purposefully designed and manufactured. This arrangement allows for measuring brake disc performance, surface temperature and quantifying mass airflow through the disc. The results show that the mass flow of air through the disc vanes highly depends on the disc temperature, but can also vary by more than 10 % for discs with the same specifications. Furthermore, the results highlight non-negligible differences in disc cool-down behaviour based on the braking scenario used to heat the disc up.

Study of a Cavitation Treatment in Kaplan Hydro-turbine

Abstract This research proposes an air-injection treatment for the cavitation phenomena in the Kaplan turbine. An unsteady numerical model is created to predict the cavitating flow through a 3-inch axial hydro turbine before and after the air injection. Pressurized air [jet-in-crossflow] injection is set to be through the turbine housing, and the configuration was altered between 1, 2, 4, and 12 circumferential jets to test the effects of air mass flow rate and injection distribution. Interactions between three fluids (liquid water, water vapor, and air) were considered by utilizing the physics models of Volume of Fluid (VOF) multiphase, Cavitation, and Large Eddy Simulation (LES) turbulence. Surface and time-average results are to be compared with a baseline case of pure cavitation. With the vapor volume fraction created on the rotor components during the cavitation, the absolute pressure scenes clarified the connection between the air treatment and cavitation reduction. While rotation causes negative pressure in the system, the injected air is sucked to such low-pressure zones, and consequently, increasing the absolute pressure above the vapor limit reduces the vapor formation. Preliminary outcomes at 1000 rpm show a 55 percent reduction in the formed vapor on the blades after air injection by a time corresponding to 6 cycles of the turbine. A corresponding mechanical power of 12 percent increase was observed. Moreover, the curve fitting of the data shows that the vapor reduction and power regain are in 2nd order correlation with the increased air volume.

A Comprehensive Literature Review on the Resolution of Turbine Engine Performances' Inverse Problems

Abstract Turbine engine monitoring is a well-known and well-studied subject that proves to be essential for the aeronautic industry. A popular approach in engine monitoring is constructing indicators that reflect systems' health states by leveraging operational measurements (i.e., sensors' data during flights)—this is known as the engine performance's inverse problem. There exists an extensive literature on this topic, especially revolving around two well-used types of performance indicators of aircraft engines: efficiencies and air mass flow rates of engine's modules. This review aims to provide a comprehensive survey of this particular literature, which so far has not been properly organized and structured. Our first contribution is to propose a novel taxonomy of the relevant methods. In particular, we consider the role of physics-based models—an element that provides specific advantages and challenges in the context of aircraft engines monitoring—and see if each method exploits such models inside or outside the main algorithmic process (or not exploiting them at all). Our second contribution is to identify the pros and cons of each method, along with additional insights with respect to two commonly encountered challenges: under-determined scenarios and time-series data. Finally, we give some guidelines for selecting appropriate strategies in practical situations and perspectives for future works.

A new method to improve the thermal performance of high-level water collecting cooling tower based on the migration of vortices

This study proposes a novel annular inlet hat structure designed to address internal vortex flow within high-level water collecting cooling towers (HCTs). To investigate the effect mechanism of inlet hat, a three-dimensional numerical model for an HCT equipped with inlet hat was developed, allowing for a comprehensive analysis of the flow and temperature fields, as well as several performance parameters. The results manifest that the inlet hat strengthens the tower thermal performance by migrating the longitudinal vortices from the interior to the exterior and reducing the number of longitudinal vortices induced by crosswinds. The strengthening effect of inlet hat shows minimal variation when its width exceeds 8 m. Under the studied water flow rates, an 8-m inlet hat results in increases in air mass flow rate, water temperature drop, Merkel number, and evaporation rate by a maximum of 4.3 %, 4.2 %, 6.4 %, and 1.5 %, respectively. In terms of crosswinds, the inlet hat operates with optimal efficiency at a direction of 0° and a velocity of 13 m/s, achieving maximum increases in air mass flow rate, water temperature drop, and Merkel number of 23.3 %, 25.4 %, and 33.6 %, respectively. These findings demonstrate the feasibility and practical value of the proposed inlet hat.

Bridging the gap: A comparative analysis of indoor and outdoor performance for photovoltaic-thermal-thermoelectric hybrid systems

This research evaluates the performance of a hybrid thermal-thermoelectric photovoltaic air collector system (PV/T-TE) through experimental investigations. By integrating photovoltaic (PV) panels with thermoelectric (TE) modules, the system aims to enhance efficiency and energy output by converting waste heat into additional electricity. The study examines the impact of radiation intensity, ranging from 455.65 to 795.18 W/m2, on the system's performance, utilizing output temperature (To) and plate temperature (Tp) as key metrics. Managing waste heat in PV technology remains a challenge, impacting efficiency. Traditional PV/T systems generate both electricity and thermal energy but suffer efficiency losses due to inadequate heat management. Integrating TE modules into PV/T systems offers a promising solution, but optimal configurations and performance impacts under varying conditions are underexplored. Limited research focuses on PV/T-TE hybrid systems, with most studies addressing PV-TE systems. The objectives of this research are to experimentally assess the impact of integrating TE modules on the thermal and electrical efficiency of PV/T systems under varying radiation intensities and air mass flow rates. The methodology involves setting up a PV/T-TE hybrid system, conducting experiments under controlled conditions, and analyzing key performance metrics. The study explores optimal TE module configurations and installation techniques to maximize heat transfer and electricity generation. Comparative analysis with conventional PV/T systems establishes the superiority of the hybrid system. Findings indicate significant benefits from incorporating TE modules, enhancing energy output and efficiency by maintaining optimal PV panel temperatures.

Effect of cavity depth on air-breathing rotating detonation engine fueled by liquid kerosene

In our recent experimental investigation, the feasibility of a liquid-kerosene-fueled air-breathing/ramjet rotating detonation engine featuring a cavity-based annular combustor has been experimentally demonstrated. Achieving stable operation and organized detonation combustion within the rotating detonation combustor presents significant challenges that demand further investigation. Thus, this study aimed to deepen our understanding of the optimal geometrical configuration of a cavity-based annular combustor operating in air-breathing mode. Numerous experiments were conducted to evaluate the impact of varying cavity depths on combustion performance under a supersonic incoming flow with a total temperature of 860 K. The findings indicate that adequate cavity depth is essential for the generation of kerosene-fueled rotating detonation waves in air-breathing mode. Notably, a kerosene–air rotating detonation wave was achieved in combustors with cavity depths ranging from 10 to 30 mm while maintaining a supersonic heated air mass flow rate of approximately 1000 g/s and a minimum equivalence ratio of 0.77. However, at a cavity depth of 10 mm, both the propagation velocity and peak pressure of the rotating detonation waves were significantly lower compared to those at 20 and 30 mm, thereby suggesting that the depth of 10 mm may require optimization. Additionally, optical observations revealed that the detonation reaction zone was located further from the combustor head as cavity depth increased. This indicates that deeper cavity depths allow for longer mixing and preheating times of the combustible mixture before detonation, thereby enhancing detonation performance. This study clarifies how cavity depth influences liquid-fueled rotating detonation and provides guidelines for designing cavity-based annular combustors in air-breathing rotating detonation engines.

Experimental investigation of a humidifier-dehumidifier desalination system with a hybrid air heater (solar-electric) and vapor absorption refrigeration (VAR) system in the dehumidifier

This study focuses on the experimental investigation of the efficiency of a humidifier-dehumidifier (HDH) desalination process. The system employs a closed-air cycle, utilizing a hybrid (solar-electric) air heater to increase the air temperature before entering the humidifier. Additionally, a Vapor Absorption Refrigeration (VAR) system is employed to decrease the temperature of the water before it enters the dehumidifier. The system is suitable for deployment in regions with high temperatures and humidity levels. Tests have been conducted under prevailing weather conditions. Temperature and relative humidity at various stages of the cycle are measured and recorded using a dedicated sensor. This study examines the effects of different parameters, including air mass flow rate (MFR) and air temperature at the humidifier inlet, on fresh water production (FWP), coefficient of performance (COP), and gained output ratio (GOR). The results section presents the experimental findings, which show that the maximum COP, GOR, and FWP achieved values of 2.1, 4.1, and 200 g/h, respectively. Furthermore, an increase in air MFR corresponds to an increase in both COP and FWP, while GOR values show a decrease. Based on the eco-analysis conducted for this investigation, the cost per liter (CPL) was calculated to be 0.022 $ per kilogram.

Multi-Disciplinary Optimization of UV-C Filter for Air Disinfection

Because of the recent COVID-19 pandemic, the problem of preventing and containing the diffusion of pathogens spread through air has become a main topic of research. The problem is particularly important for specific environments, such as dental or other medical practices, where the aerosol treatments in open-mouth patients, combined with closed and crowded rooms, raise the risk of infection. As an efficient countermeasure, in this study we propose a solution that is able to remove the risk at the source, through the aspiration of the aerosol and the neutralization of the bacterial load by means of a UV-C LED filter, which releases the sterilized air in the environment. To maximize the efficiency of the solution, in this study we performed a numerical multi-disciplinary optimization (MDO) of the filter, coupling numerical simulations of multiple disciplines (CFD and electromagnetics) by the process automation and optimization environment modeFRONTIER of ESTECO. Geometrical parameters of the filter are updated for each candidate solution proposed by the optimization algorithm, and their performance in terms of viral neutralization efficiency and air mass flow rate are evaluated by the simulations, until the optimal solution is found. The methodology and results of the study are presented.

Numerical simulation of an innovative design of solar air heater using spiral duct inserts for enhancing thermal efficiency

ABSTRACT An innovative design of solar air heater (SAH) with spiral shape is numerically analyzed in this paper. The spiral-shaped SAH hydro-thermal performance is studied for different air mass flow rates using CFD COMSOL Multiphysics software. The outlet air temperature difference, thermal efficiency, flow structure, thermal field and pressure drop are the main parameters which are considered to estimate the fluid flow and heat transfer behaviors of the SAH. The simulation is realized for 1000 W/m2 of solar heat flux and 25°C of ambient temperature as typical climatic conditions in a middle day. The results show that the maximum outlet temperature difference of the SAH reached 93.08°C with 0.0083 kg/s of air mass flow rate. For the range of 0.0083–0.0332 kg/s, the thermal efficiency is varied from 91.41% to 99.01%. The ambitious percentage of the thermal efficiency of 99.01% was observed for 0.012 kg/s. The proposed design provides high thermal efficiency of SAH compared to other configurations of SAH.

The Influence of the Intake Geometry on the Performance of a Four-Stroke SI Engine for Aeronautical Applications

In this work, the influence of plenum and port geometry on the performance of the intake process in a four-stroke spark ignition engine for ultralight aircraft applications is analyzed. Three intake systems are considered: the so-called “standard plenum”, with a relatively small plenum volume, the “V1 plenum”, with a larger plenum volume, and the “standard plenum” equipped with a large curvature manifold called the “G2 port”. Both measurements and 3D CFD simulations, by using Ansys® Academic Fluent, Release 20.2, are performed to characterize and analyze the steady-flow field in the intake system for selected valve lifts. The experimental data and the numerical results are in excellent agreement with each other. The results show that at the maximum valve lift, i.e., 12 mm, the V1 plenum allows an increase in the air mass flow rate of 9.1% and 9.4% compared to the standard plenum and the standard plenum with the “G2 port”, respectively. In addition, the volumetric efficiency has been estimated under unsteady-flow conditions for all geometries at relatively high engine rpms. The difference between numerical results and measurements is less than 1% for the standard plenum, thus proving the accuracy of the model, which is then used to study the other configurations. The V1 plenum shows a fairly constant volumetric efficiency as the engine speed increases, although such an efficiency is lower than that of the other two geometries considered in this work. Specifically, the use of the “G2 port” leads to an increase of 1.5% in terms of volumetric efficiency with respect to the configuration with the original manifold. Furthermore, for the “G2 port” configuration, higher turbulent kinetic energy and higher swirl and tumble ratios are observed. This is expected to result in an improvement of air–fuel mixing and flame propagation.

Improving sustainability: Exergy, energy analysis and CO2 mitigation of greenhouse integrated with thin-film photovoltaic and earth-to-air heat exchanger

Adopting passive cooling systems has become especially vital due to the high energy consumption and adverse impacts of conventional air conditioning systems on the environment. Sustainable green energy structure development includes a periodic thermal model of a greenhouse integrated with thin-film photovoltaics (GiTPV) and the earth-to-air heat exchanger (EAHE). The system can provide plants in the greenhouse with air from extreme weather conditions: 5 °C in the winter and 45 °C in the summer, corresponding to thermal comfort standards in structures. According to the results, at 0.5 kg/s air mass flow rates of EAHE, the air temperature in the greenhouse room rises by 5 °C in the winter and falls by 17 °C in the summer. The greenhouse can save 9864 kWh/year before and 41,587 kWh/year after integrating EAHE. The seasonal energy efficiency ratio (SEER) for EAHE varies between 1 and 3. The yearly carbon credit of a greenhouse is expected to be 3166 US dollars, and EAHE reduces CO2 emissions by around 65.68 tons per year. Finally, the Quonset GiTPV system generates 29.22 kWh and 17.6 kWh of electrical energy per day on extremely hot and cold days respectively, making the system self-sustainable.

Heat Propagation Across Turbocharger Unit with Variable Turbine Inlet Temperature

Currently, issues about emission gains serious attention among the lawmakers and governments. Multiple regulation and enforcements have been applied to reduce the level of emission that released to the environment. Vehicle emissions have been identified as one of the major polluters thus forcing the carmakers to explore new technology to reduce the vehicle emissions. One of the technologies that have been preferred by the carmakers is the applications of forced induction system to the internal combustion engine. By using the forced induction system where currently turbocharger system is more often used compared to supercharger, two benefits can be achieved which are improvements of engine efficiency and engine size reduction. However, the ability of turbocharger unit to deliver compressed air can be affected by the amount of heat that travels along the turbocharger unit itself. In this paper, the effect of heat that originated from the exhaust gas that enters the turbine inlet towards the turbocharger performance was measured and analysed. An automotive turbocharger unit manufactured by Garrett Turbocharger model GT2056 was used in the study. The rotational speed is set between 20 000 rpm to 70 000 rpm and the temperature at turbine inlet is set between 40℃ to 100℃. The parameters that measured are the temperature difference at internal turbine, internal bearing temperature difference, internal compressor temperature difference, turbine casing temperature difference, bearing housing temperature difference and compressor housing temperature difference. From the results obtained, it can be observed that the heat travels from turbine towards the compressor side through the conduction between the contacting parts between the turbine casing, bearing housing and lastly at compressor casing. The heat that arrives at the compressor side through the casing will give small effect to the air mass flow that delivered by the compressor.

Enhancing building energy efficiency: Numerical analysis of a hybrid thermoelectric ventilation system and earth-air heat exchange with photovoltaic-thermoelectric power integration for heating and cooling loads

The lack of studies on hybrid systems combining thermoelectric ventilation (TEV) and earth-air heat exchangers with a photovoltaic-thermoelectric generator (PV-TEG) as the power supply for the hybrid system is addressed in this research. This study aims to investigate the effectiveness and performance of such a combined system in providing the required thermal load of a building. To simulate the performance of TEV and PV-TEG systems, energy conservation equations for various components of the system were formulated for the quasi-state mode. The performance of the earth-air heat exchanger system was evaluated using the effectiveness-number of transfer units method. The resulting set of algebraic equations was then solved using a MATLAB code. Results indicated significant preheating (5.41–15.03 °C) and precooling (0.7–10.22 °C) effects during the daily hours of 15-February and 15-July, respectively. Additionally, the TEG component effectively reduced PV temperatures by 3.54 °C–16.99 °C in 15-February and 3.99 °C–21.54 °C in 15-July. The system also demonstrated a high monthly useful thermal energy output (1215–1584 kWh) in the cold months (December to March), contrasting with higher monthly useful thermal exergy (712–763 kWh) in the summer months. Furthermore, increasing the number of TEGs from 10 to 50 resulted in significant improvements in the yearly average energy and exergy proficiency indexes (PIya,en and PIya,ex) by 164.97 % and 459.82 %, respectively. The supply air mass flow rate and the length and depth of the earth-air duct were identified as the second and third most influential parameters affecting these indexes. Moreover, the system at CPV concentration ratio of 3 provided the highest PIya,en and PIya,ex of 1.512 and 14.65, respectively.

Engine Mass Flow Estimation through Neural Network Modeling in Semi-Transient Conditions: A New Calibration Approach

Nowadays, engine experimental research represents a very expensive field within the automotive industry, but it remains fundamental for engine and vehicle development. The present work aims to investigate a novel approach for engine control system calibration, by adopting machine learning techniques to model physical parameters of the engine starting from experimental data measured at the test bench. The main goal is to create a methodology which accelerates the calibration process without losing accuracy. A model that estimates air mass flow is created by adopting either a tree ensemble model or an artificial neural network trained on a small dataset, which was previously acquired at the test bench using a random calibration of the volumetric efficiency map. The model’s performance is first validated on a larger, random dataset. Then, the volumetric efficiency calculated from the air mass flow model estimation is used to calibrate the transfer function of the Engine Control Unit. Finally, the sensitivity of the model error correlated with the number of data points acquired is used in order to determine the best practice for a Design Of Experiment, which minimizes data acquisition. The methodology proposed can lead to reduced time and costs of the whole calibration process of the engine, without losing accuracy. The analysis was conducted on the entire vehicle, which is crucial for drivability, especially in motorcycles since they are highly sensitive to air-to-fuel ratio adjustments. This work demonstrates that machine learning models can be adopted for the fine-tuning of the calibration process, which is normally performed manually.

Influence of Dilution and Effusion Flows in Generating Variable Inlet Profiles for a High-Pressure Turbine

Abstract The elevated flow temperatures and pressures exiting gas turbine combustors affect the efficiency and durability of the high-pressure turbine stage. Understanding the effects that result from the upstream dilution and effusion flow interaction in creating the combustor exit profiles is important to advancing gas turbines. Understanding how common combustor features, such as dilution jets and effusion cooling, interact based on computational predictions guided the design of a non-reacting profile simulator capable of producing a wide range of non-uniform temperature profiles representative of those entering high-pressure turbines. The mechanical design of a new simulator device, which will be experimentally tested in the future, is presented in this paper along with computational predictions of flow and thermal fields. The simulator was designed for modular installation into the Steady Thermal Aero Research Turbine (START), which is a continuous-duration, steady-state turbine facility that houses a single-stage test turbine. Features of the simulator included interchangeable liner panels with multiple rows of dilution jets and wall effusion cooling to study various hole diameters and patterns. The dilution jets generate elevated turbulence intensities and tailor the temperature profiles in the radial and circumferential directions. The air mass flow distribution and source flow temperatures are independently controlled. To aid in the simulator design, computational fluid dynamics (CFD) simulations using Reynolds-averaged Navier–Stokes modeling were conducted with a two-level Design of Experiments (DOE) approach to determine a number of engine-representative target profiles with temperature shapes that are mid-radius peaked, outer-diameter peaked, inner-diameter peaked, and uniform. A sensitivity analysis of the CFD DOE results determined which factors significantly affected the profile shape so that the target profiles could be produced. The analysis indicated that the main contributor to the temperature profile shape at near-wall vane radial span locations of 0–15% and 85–100% was the injection temperature of the effusion flow. The main contributor at radial span locations of 15–40% and 60–85% was the injection temperature of the third-row dilution jets, and at the mid-radius location of 40–60% vane radial span, the main contributor was the diameter of the first-row dilution holes.

A semi-empirical model for online real-time control of NOX generation in diesel engines

Diesel NOX emission control is the main control content of diesel engines. Real-time high-precision NOX emission prediction model is the basic guarantee for (1) Diesel combustion management, (2) SCR after-treatment control, (3) OBD system. Existing models that rely exclusively on physical processes or data-driven artificial intelligence models fail to meet real-time requirements, while MAP look-up table-based models are poorly adapted and require extensive experiments for calibration. In this study, a new semi-empirical model for NOX emission prediction was developed, and the variables of the model were identified as exhaust temperature, engine speed, injected fuel mass flow rate, air intake mass flow rate, and exhaust oxygen mass flow rate, taking into account the mechanism of NOX generation in diesel engines as well as the requirement of real-time and direct measurability of the variables for on-line control. The influence of each variable on NOX was analyzed, the model structure of the NOX prediction model was determined, and the parameters of the prediction model were identified by least squares. The model is applied to real operating vehicles for validation and compared with a previous semiempirical model taken from the literature, and the results show that the overall accuracy of the proposed model is improved. Finally, the effect of variable uncertainty on the proposed model was assessed and it was found that the relative uncertainty in predicting NOX emissions ranged between 0 and 8% for sensor accuracies of [Formula: see text] and [Formula: see text] for exhaust temperature and intake air mass flow, respectively, suggesting that the sensor accuracy has a significant effect on the uncertainty of the model.

Research on input parameter optimization for NOx deep learning prediction model

Optimizing the input parameters for NOx prediction model is instrumental in enhancing the precision and efficacy of the prediction model. This paper focuses on the input variables of the data-driven diesel engine NOx prediction model. According to the diesel engine NOx generation mechanism, at first relevant variables are selected, then the similarity method and parameter sensitivity method are compared to optimize the input variables. Firstly, this paper conducted a real-road emission test of a heavy-duty diesel vehicle, and proposed a data-driven deep learning model for predicting diesel engine NOx emissions based on the experimental data. The experimental data were processed using an Attention-Mechanism based Convolutional Neural Networks-Long Short-Term Memory (AM-CNN-LSTM) model. Subsequently, input parameters were selected according to the sensitivity weights assigned to each parameter in the preliminary model. This approach refined the modeling data and excluded variables not pertinent to NOx emission prediction. The AM-CNN-LSTM model prediction performance has been improved with 2% increase of model R2 as well as the model training time is reduced by 23%, and the types of parameters required to train the model are reduced by 50%. It accomplished this by effectively reducing data dimensions, discarding non-essential variables for NOx prediction, and diminishing computational complexity. Six input parameters were identified as pivotal in reconstructing the modeling data for accurate NOx prediction: engine speed, torque, EGR valve position, exhaust flow rate, air mass flow rate, and oil temperature. In optimizing the NOx prediction model, it is crucial to determine an optimal number of input parameters. Excessive parameters do not enhance model accuracy, while an insufficient number impairs the model’s ability to precisely emulate the NOx generation process, leading to diminished predictive accuracy.