Engineering Model Research Articles

Sensitivity Analysis and Application of the Shanghai Model in Ultra-Deep Excavation Engineering

In deep foundation pit engineering, the soil undergoes a complex stress path, encompassing both loading and unloading phases. The Shanghai model, an advanced constitutive model, effectively accounts for the soil’s deformation characteristics under these varied stress paths, which is essential for accurately predicting the horizontal displacement and surface settlement of the foundation pit’s enclosure structure. This model comprises eight material parameters, three initial state parameters, and one small-strain parameter. Despite its sophistication, there is a scarcity of numerical studies exploring the correlation between these parameters and the deformation patterns in foundation pit engineering. This paper initially establishes the superiority of the Shanghai model in ultra-deep circular vertical shaft foundation pit engineering by examining a case study of a nursery circular ultra-deep vertical shaft foundation pit, which is part of the Suzhou River section’s deep drainage and storage pipeline system pilot project in Shanghai. Subsequently, utilizing an idealized foundation pit engineering model, a comprehensive sensitivity analysis of the Shanghai model’s multi-parameter values across their full range was performed using orthogonal experiments. The findings revealed that the parameter most sensitive to the lateral displacement of the underground continuous wall was κ, with an increase in κ leading to a corresponding increase in displacement. Similarly, the parameter most sensitive to surface subsidence outside the pit was λ, with an increase in λ resulting in greater subsidence. Lastly, the parameter most sensitive to soil uplift at the bottom of the pit was also κ, with an increase in κ leading to more significant uplift.

Zipper Pattern: An Investigation into Psychotic Criminal Detection Using EEG Signals

Background: Electroencephalography (EEG) signal-based machine learning models are among the most cost-effective methods for information retrieval. In this context, we aimed to investigate the cortical activities of psychotic criminal subjects by deploying an explainable feature engineering (XFE) model using an EEG psychotic criminal dataset. Methods: In this study, a new EEG psychotic criminal dataset was curated, containing EEG signals from psychotic criminal and control groups. To extract meaningful findings from this dataset, we presented a new channel-based feature extraction function named Zipper Pattern (ZPat). The proposed ZPat extracts features by analyzing the relationships between channels. In the feature selection phase of the proposed XFE model, an iterative neighborhood component analysis (INCA) feature selector was used to choose the most distinctive features. In the classification phase, we employed an ensemble and iterative distance-based classifier to achieve high classification performance. Therefore, a t-algorithm-based k-nearest neighbors (tkNN) classifier was used to obtain classification results. The Directed Lobish (DLob) symbolic language was used to derive interpretable results from the identities of the selected feature vectors in the final phase of the proposed ZPat-based XFE model. Results: To obtain the classification results from the ZPat-based XFE model, leave-one-record-out (LORO) and 10-fold cross-validation (CV) methods were used. The proposed ZPat-based model achieved over 95% classification accuracy on the curated EEG psychotic criminal dataset. Moreover, a cortical connectome diagram related to psychotic criminal detection was created using a DLob-based explainable artificial intelligence (XAI) method. Conclusions: In this regard, the proposed ZPat-based XFE model achieved both high classification performance and interpretability. Thus, the model contributes to feature engineering, psychiatry, neuroscience, and forensic sciences. Moreover, the presented ZPat-based XFE model is one of the pioneering XAI models for investigating psychotic criminal/criminal individuals.

Numerical investigation of thermal barrier coating on performance and emissions of HPDI dual-fuel engine

ABSTRACT Thermal barrier coatings (TBC) represent a promising technology for enhancing the thermal efficiency of internal combustion engines. This study investigates the impact of TBC on in-cylinder combustion processes of a dual-fuel HPDI engine to achieve higher energy conservation with low heat transfer loss. In the present study, a one-dimensional conjugate heat transfer (1D CHT) model is constructed that incorporates TBC material features. By coupling the 1D CHT model with the three-dimensional combustion model of dual-fuel HPDI engines in CONVERGE software, the influences of TBC to the combustion process and temperature distribution within the engine cylinder is illustrated in details. Meanwhile, the adiabatic combustion characteristics of HPDI engines are investigated based on various adiabatic components or porosity. The results demonstrate that the reduction in heat transfer under P_TBC (TBC on top boundary of piston) conditions leads to an increase in the volume proportions of the high-temperature intervals within the cylinder, thus enhancing both mixture activity and heat release rate. The combination of these two factors lead to a 0.4% increase in indicated thermal efficiency under P_TBC conditions compared to the baseline. Under the current injection strategy, P_TBC conditions could effectively eliminate the heat flow area in the piston bowl and step area, thereby significantly reducing heat transfer loss. Since heat transfer loss is basically influenced by both temperature difference between fluid and wall as well as thermal conductivity of TBC, increasing porosity therefore is able to enhance thermal resistance by reducing thermal conductivity of TBC. However, when there is an increased temperature difference between fluid and wall, increasing porosity does not continually lead to a further reduction of heat transfer loss. Finally, it is observed that the utilization of P_TBC with a porosity of 0.1 resulted in an increase of 0.7% in the indicated thermal efficiency compared to the baseline, while marginally reducing CH4 and CO emissions.

Theoretical Analysis of Performance Characteristics of Non- road Spark Ignition Engines

Non-road spark ignition (SI) engines play a critical role in Nigeria, particularly in agriculture, construction, and small-scale power generation. Despite their extensive use, there is limited research on how Nigeria's unique environmental and operational conditions such as high ambient temperatures, poor fuel quality, and irregular maintenance practices affect the performance of these engines. This study presents a theoretical analysis of the performance characteristics of non-road SI engines under Nigerian conditions, focusing on fuel efficiency, power output, thermal efficiency, and emissions. The effect of engine speed, engine load and equivalence ratio on the performance characteristics of non-road spark ignition engines were studied in this research. Three operating parameters (engine load, engine speed, and equivalence ratio) and eight engine performance parameters which are Brake Specific Fuel Consumption (BSFC), Brake Power (BP), Thermal Efficiency (TE), Brake Mean Effective Pressure, Exhaust Gas Temperature (EGT), carbon monoxide emission, hydrocarbon emission, and nitrogen oxide were considered in this work. Theoretical analysis was performed using a two-zone SI engine model, the resulting equations were solved with the aid of a computer program developed by the authors and implemented in MATLAB software. The effect of the operating parameters on the performance parameters was simulated using the computer code developed which was implemented in MATLAB. The results show that the engine speed of 3000 rpm gave the optimum values of 250 g/kWh, 33 kW, 1070 kPa, 28% and 720 oC for BSFC, BP, BMEP, TE, and EGT respectively. Also, all performance parameters increased with an increase in engine load. The equivalence ratio of 0.9 gave the optimum values for all the parameters considered in this work. It can be concluded that for optimum performance of non-road SI engines, it should be operated at equivalence ratio of 0.9, engine speed of 3000 rpm and low engine loads.

Predicting transient performance of a heavy-duty gaseous-fuelled engine using combined phenomenological and machine learning models

Decarbonizing long-haul goods transportation poses a substantial challenge. High-efficiency natural gas (NG) engines, which retain the efficiency of a diesel engine but reduce the carbon content of the fuel, offer substantial potential for near-term greenhouse gas (GHG) reductions. A fast-running model that can predict engine performance, GHG and air pollutant emissions is critical to assessing this approach for different applications and vehicle drivetrain configurations. This paper presents the development, validation and application of an engine system model that adapts GT-SUITE™’s phenomenological DI-Pulse predictive model to predict the performance and emissions of a 6-cylinder NG engine using a high pressure direct-injection combustion process. The model includes the engine air exchange system, enabling the prediction of the engine and in-cylinder conditions and overall performance over transient drive cycles. The engine model with a fixed set of calibration parameters captures the complex high-pressure direct injection combustion process and generates time-resolved parameters that are fed into a coupled machine learning model to predict emissions, including nitrogen oxide (NOx) and methane (CH4) emissions. While the 1-D model’s predictions for CH4 were not accurate, coupling the 1-D engine model with a machine learning model has been shown to substantially improve the estimation of CH4 emissions and allow accurate prediction of engine total GHG emissions over different duty cycles. The model has been validated using transient engine dynamometer data and is then applied to assess performance and emissions over several regulatory and real-world long-haul drive cycles. The model showed an average error of less than 5% in steady operation. Cumulative errors of NOx and CH4 emissions in studied cycles were also less than 10%. The results showed that CH4 share in total GHG emissions ranges from 0.2% to 1.4% over various drive cycles. By predicting engine performance and emissions, the developed combined model has considerable potential for use in engine evaluation studies, especially when combined with new technologies across different duty cycles.

Experimental and numerical investigation of abnormal combustion phenomena in high-performance hydrogen direct-injection engine operated in stochiometric conditions

Nowadays the use of Hydrogen (H2) within Internal Combustion Engine (ICE) represents a valuable solution also for high-performance applications since it allows carbon free combustion process preserving, at the same time, the driving experience of the engines fuelled with conventional fuels. On the other side, the low ignition energy and the high flammability range may lead to a high probability of abnormal combustion events especially at high engine loads. Therefore, this work aims at investigating the occurrence of knock and pre-ignition phenomena in a high-performance Direct Injection (DI) single cylinder Spark Ignition (SI) engine through the synergistic use of numerical simulations and experimental activities. A 3D-CFD model was calibrated against a set of experimental measurements. The engine model showed satisfactory predictive capabilities with a good matching with the experimental in-cylinder pressure traces. This virtual test rig was then used to investigate the impact of a different coolant temperature and different injector recess in terms of knock and pre-ignition tendency, and most of all, to define a robust simulation methodology to estimate the risk of hydrogen abnormal combustion events.

Formation of a set of parameters for assessing the technical condition of autonomous power plants

Abstract. Problem. The object of study is the problem of creating a relatively simple diagnostic model of a diesel engine for an autonomous power plant in terms of the number of required input parameters. Goal.The aim of the study is to develop a diesel engine diagnostic system for an autonomous power plant. Methodology. To achieve this goal, the following tasks were solved: - to develop a method for synthesising a diagnostic graph model of a diesel engine for an autonomous power plant; - to propose a method for selecting the initial parameters of the diagnostic graph model of a diesel engine.The subject of the study is the relationship between the selected set of input parameters of the diagnostic model of a diesel engine and the adequacy of the response of the resulting model to real emergency situations. Results. As a result of the study, a methodology for synthesising a diagnostic graph model of a diesel engine of an autonomous power plant has been developed. The resulting model allows monitoring the performance of a diesel engine and adjusting the relevant parameters to achieve the required operating state or localise an emergency. Originality. The proposed method of synthesis of a diagnostic graph model of a diesel engine of an autonomous power plant, based on the use of the graph theory method, allows obtaining results that correspond to the actual state of operation of a diesel engine of a power plant with relative simplicity of use. This is achieved by using specially selected groups of diesel power control parameters as diagnostic parameters of the graph model. These indicators are available for measurement without significant dismantling and installation work, the use of complex measuring instruments, but can be measured during routine maintenance and operation. A methodology for selecting the output parameters of a diagnostic graph model of a diesel engine is proposed, which includes the process of forming the minimum required sample of parameters of diesel engine operation. Practical value. The following parameters have been selected as parameters for assessing the technical condition of power plant diesel engines and functionally related systems and circuits: power plant capacity; diesel crankshaft rotation frequency; fuel consumption; and a group of thermal parameters. This minimum required set of system state parameters makes it possible to link the diagnostic scheme for the studied technical condition of power plant diesel engines with their operational performance

Improving Fuel Consumption Prediction for Marine Diesel Engines Using Hierarchical Neural Networks and Pulsating Exhaust Models

Predicting end-of-process variables in internal combustion engines, such as brake-specific fuel consumption or pollutant emissions, is crucial for engine design decisions. However, errors in common multi-layer-perceptron-based artificial neural network models often match the magnitude of the expected fuel consumption improvements, potentially leading to incorrect decisions. This study introduces a hybrid model where artificial neural networks replace engine block elements, while the 1D gas circuit and turbocharger models are retained. To enhance metamodel accuracy, two modifications are proposed: incorporating a pulsating mass flow rate in the exhaust line to capture pulsating effects missing in mean-value engine models and using a hierarchical arrangement of several multi-layer perceptrons instead of a parallel arrangement. The pulsating mass flow rate approach improves the accuracy of all tested configurations by replicating pulsating effects from a detailed 1D engine model. Meanwhile, the hierarchical arrangement refines predictions of end-of-process variables, such as fuel consumption, by increasing the total layers, with a minimal trade-off in the accuracy of other variables. These findings are validated using a metamodel derived from a calibrated 1D engine model in GT-Suite. The proposed methods are expected to enhance the accuracy of data-driven artificial neural network approaches, contributing to more reliable engine design optimization.

Study on Few-Shot Fault Diagnosis Method for Marine Fuel Systems Based on DT-SViT-KNN.

The fuel system serves as the core component of marine diesel engines, and timely and effective fault diagnosis is the prerequisite for the safe navigation of ships. To address the challenge of current data-driven fault-diagnosis-based methods, which have difficulty in feature extraction and low accuracy under small samples, this paper proposes a fault diagnosis method based on digital twin (DT), Siamese Vision Transformer (SViT), and K-Nearest Neighbor (KNN). Firstly, a diesel engine DT model is constructed by integrating the mathematical, mechanism, and three-dimensional physical models of the Medium-speed diesel engines of 6L21/31 Marine, completing the mapping from physical entity to virtual entity. Fault simulation calculations are performed using the DT model to obtain different types of fault data. Then, a feature extraction network combining Siamese networks with Vision Transformer (ViT) is proposed for the simulated samples. An improved KNN classifier based on the attention mechanism is added to the network to enhance the classification efficiency of the model. Meanwhile, a Weighted-Similarity loss function is designed using similarity labels and penalty coefficients, enhancing the model's ability to discriminate between similar sample pairs. Finally, the proposed method is validated using a simulation dataset. Experimental results indicate that the proposed method achieves average accuracies of 97.22%, 98.21%, and 99.13% for training sets with 10, 20, and 30 samples per class, respectively, which can accurately classify the fault of marine fuel systems under small samples and has promising potential for applications.

A Novel Approach for Aircraft Engine Modeling Considering the Energy Accumulation Effect Based on a Variable Mass System Thermodynamics Method

A Novel Approach for Aircraft Engine Modeling Considering the Energy Accumulation Effect Based on a Variable Mass System Thermodynamics Method

Metamodeling of turbofan engine compressor characteristics using SVM-based improved Kriging method

Purpose The purpose of this paper is to overcome the inherent lack of precision in commonly used interpolation procedures when solving the mathematical model of turbofan engines, as well as to address the issue that the theoretical variogram model in traditional Kriging models is prone to subjective selection bias, which makes it impossible to accurately capture the inherent fluctuation patterns in compressor data. Design/methodology/approach To mitigate this challenge, based on the spatial distribution characteristics of the compressor characteristic data of a certain type of turbofan engine, the input and output dimensions of the model are defined. By determining the stable operating region from the original component data, the authors use the proposed Kriging method improved with a support vector machine model to reconstruct the characteristics at unknown speeds within this region. The effectiveness of the proposed method is evaluated using the established assessment metrics. Findings Experimental results demonstrate that the proposed method exhibits significant advantages over the conventional Kriging approach. Specifically, it leads to a substantial reduction in root mean square error and mean absolute error by 0.0153/0.0118 (low speed), 0.1306/0.0362 (medium speed) and −0.0066/0.2366 (high speed). Originality/value This refined approach not only offers notable engineering applicability but also contributes significantly to the enhancement of aerospace engine model solutions’ precision.

Prediction of Performance and Emission of Gasoline Engine Fueled with a Gasoline-Ethanol-Methanol Mixture Using One Dimensional Engine Modelling Based on Engine Test Results

The depletion of petroleum reserves as the basic raw material for gasoline production has driven studies into alternative fuels. One of the alternative fuels is alcohol, both ethanol and methanol. Due to their liquid form and physical-chemical properties similar to gasoline, small modifications to the engine are required. This paper will explain the effect of using a mixture of gasoline (in this case, RON 98 gasoline with methanol or methanol on engine performance and emissions. The fuel mixtures are as follows: G100, E10, E20, E30, M10, M20, M30. AVL Boost simulation software was used as a tool for 1-dimensional engine modelling, where the modeling is based on engine testing with G100 fuel. The results show that with increasing ethanol-methanol composition, torque and power decrease, and SFC increases. On the emission side, CO, CO2, and HC were decreased and NOx increased.

Utilization of Augmented and Mixed Reality in Training Mining Machines

Augmented reality (AR) and mixed reality (MR) are used in many disciplines, especially education, science, health, safety and engineering. It is based on the visualization and interaction of virtual graphic designs in the natural environment with its own hardware and software. In this study, the effect of augmented and mixed reality applications in the training of open-pit mining machines is examined. In the application called AR Book, a booklet containing machine visuals and technical information was created. In the project developed in the Unity real-time development engine, the database created in the Vuforia AR engine and 3D machine models matched with them were used. An image-target-based augmented reality application was implemented in this booklet using Android devices. In another application, a ground-plane-based application was developed for the mixed reality device MS Hololens 2. With the Hand Interactions feature, machines positioned in the natural environment can be controlled with drag, rotate and scale operations, enlarged to gigantic sizes and examined. The evaluations of the training group regarding the use of AR and MR applications together with traditional education were sought. They were also asked to make comparisons between the mobile device and Hololens 2. There have been highly positive results in integrating imaging technologies into education.

Shaft-grouted bored pile – a practical engineering approach to the bearing capacity

ABSTRACT The paper investigates various static load test results on both shaft-grouted and non-shaft-grouted (plain) bored piles at eight project sites in Vietnam. A practical engineering model for shaft-grouted bored piles is proposed to determine the side friction of the shaft-grouted bored piles (drilled shafts), with consideration of shaft friction distribution on instrumented bored piles. The improved ratio of bored pile skin resistance after shaft grouting, compared to non-shaft grouting, ranges from 1.058 to 1.323. The application of shaft grouting is beneficial for the soils of gravel, sand, clayey sand, and silty sand, which have the permeability ranging from 1.00 × 10–5 to 8.60 × 10–5 m/s, while it is not sufficient for clayey soils. Moreover, the possibly mobilised side friction for these shaft-grouted bore piles can be up to 250 kPa. The results derived from the proposed model agree well with the static load test data of the shaft-grouted piles in term of side friction, bearing capacity, and load transfer mechanism.

A Practical Approach to Modeling and Performance Analysis of a Turboshaft Engine Using Matlab

This article presents a detailed approach to constructing a numerical model of a free power turbine engine specifically designed for performance analysis in the Matlab R2024b environment. The core innovation of this model lies in its integration of precise engine geometry parameters, calculated at the design point, and performance characteristics of key components such as the compressor and power turbine. These components are modeled to reflect significant variations in their performance based on changing operational conditions, including rotor speed and environmental factors. To validate the model’s assumptions, data from the PZL-3W engine were used. The model was created by meticulously incorporating the engine’s specific design characteristics, allowing for an in-depth examination of how performance characteristics shift with adjustments to high-pressure rotor settings or changes in ambient conditions. The resulting calculations demonstrated a high level of agreement between the model’s output and empirical data available for the PZL-3W engine, as well as with data found in the relevant scientific literature. This alignment underscores the model’s robustness and reliability in simulating engine performance across a range of operating scenarios, making it a valuable tool for further engineering analyses and optimization of free power turbine engines and their possible application.

Proposal for a usability engineering model applicable to the requirements analysis phase of mobile applications

Usability is frequently evaluated in the final phases of development or when the application is finished, although it is true that this evaluation provides important information to improve new versions of products, it is much more important to have elements that allow obtaining relevant information that allows incorporating usability attributes in the requirements analysis phase in order to obtain quality software products and even more so when it comes to applications intended for use on mobile devices, we must consider that usability is not only about reducing the size of a website to adapt to mobile devices, but on the contrary, considering this element means thinking about how people use mobile devices and understanding that the mobile experience is so unique. as the user, which is why to obtain quality mobile applications, adequate usability engineering must be carried out in the requirements phase. In this work, the proposal for a Usability Engineering Model applicable to the application requirements analysis phase is presented. This proposal integrates the usability models and criteria in the Software Engineering process

A Novel Friction Mean Effective Pressure Model for a Heavy-Duty Diesel Engine by Neural Network and Its Applications to Heat Release Rate Profile Optimization

<div>The prediction of friction mean effective pressure (FMEP) is important when engine performance is estimated in the model-based development process. The Chen–Flynn model as a function of the maximum in-cylinder pressure (P<sub>max</sub>) and mean piston speed (C<sub>m</sub>) is often used to predict FMEP because of its simplicity to utilize; however, this study inferred from the results of multiple regression analysis between FMEP and factors related to combustion phase and rate of heat release profile (ROHR) that the Chen–Flynn model may be difficult to accurately estimate FMEP in a modern diesel engine with common rail fuel injection system, which allows the control of fuel injection pressure (P<sub>inj</sub>) and combustion phase. In this study, a neural network with machine learning was applied to predict FMEP based on the expectation that the ROHR profile, which allows the reduction of FMEP may be possible to be found. 7666 points experimental results that include FMEP and combustion parameters in the heavy-duty single-cylinder diesel engine were utilized as training and validation data for machine learning. The pre-trained neural network prediction model for FMEP can predict the tendency of FMEP better than the Chen–Flynn model when start of combustion (SOC) and P<sub>inj</sub> were varied. The error between the predicted FMEP results by the pre-trained neural network and the experimental results of FMEP were within 4% of the experimental results when SOC was advanced from top dead center to −7 deg. ATDC. Whereas, the predicted FMEP by Chen-–Flynn model had a maximum error of 15% compare to the experimental results. Furthermore, the predicted FMEP by Chen–Flynn model had a maximum error of 9% compare to the experimental results when P<sub>inj</sub> was varied from 120 MPa to 200 MPa, whereas the error between the predicted FMEP results by the pre-trained neural network and the experimental results of FMEP were within 4% of the experimental results. The pre-trained neural network model was confirmed to be predictive better than the Chen–Flynn under the conditions that the combustion phase and P<sub>inj</sub> are changing. In addition, the parameter study using the pre-trained neural network prediction model for FMEP and a one-dimensional engine performance simulation tool was conducted to find the ideal ROHR profile that improve brake thermal efficiency (BTE). The result of parameter study suggests that the optimum ROHR profile to improve BTE under the same conditions of P<sub>max</sub> and the degree of constant volume combustion is to shorten combustion duration and to retard the peak of ROHR away from top dead center.</div>

Analytical formulations for nitrogen oxides emissions estimation of a hydrogen fueled Synergetic Air-Breathing Rocket Engine (SABRE) in air-breathing mode

The space sector is undergoing rapid expansion due to the transformations it is experiencing, evolving from government-funded traditional space initiatives to commercially driven NewSpace activities. The surge of government and private investments in the space domain has positioned it as one of the world's fastest-growing sectors, making it crucial to assess the impact of already operational launch assets and to adopt design-to-sustainability strategies for under-development and future launchers. To actively contribute to this transition, this paper proposes a methodology for deriving novel analytical formulations to estimate nitrogen oxide (NOx) emissions of a hydrogen-fueled reusable access-to-space vehicle. Throughout the paper, the Skylon spaceplane and its Synergetic Air Breathing Rocket Engine are used as a case study. In particular, the SABRE engine presents a highly integrated dual propulsion architecture supporting both air-breathing and rocket modes. This study specifically focuses on the former, enabling the Single Stage To Orbit (SSTO) Skylon reaching the hypersonic speed regime before transitioning to rocket mode. This paper proposes novel analytical formulations to be integrated into the Fuel Flow (FF) and P3-T3 methods for estimating NOx Emission Index (EINOx), since the early design phase. These estimation techniques currently enable the calculation of the emission index of pollutants and GreenHouse Gases (GHGs) produced by any subsonic aero-engines powered by traditional fuels (i.e. kerosene) only. The methodology presented in this paper allows for upgrading the original mathematical formulations of the methods to ensure the applicability to high-speed flight and hydrogen fuel conditions. This involves the propulsive modelling of the engine and the chemical-kinetic modelling of the combustion process, representative of various on-ground and in-flight operating conditions, to generate updated and reliable propulsive and emissive databases for the engine. To this end, 0D chemical-kinetic air/hydrogen combustion numerical simulations are employed. The results of the performance analysis and emission modeling of the SABRE engine are reported and discussed. Regarding the calculated EINOx trend for the air-breathing phase of the engine operation, it reaches a peak of 45 gNOx/kgH2burnt under hypersonic conditions. Through the analysis of correlations between the propulsive characteristics of the SABRE and its NOx production, a series of parameters (such as Mach Number, Fuel to Air Ratio, Water to Fuel Ratio, and others) are selected to be integrated into the original formulations of the P3-T3 and FF methods via mathematical interpolation to adapt them to the case study. Finally, the EINOx trends resulting from the application of the new H2-P3T3 and H2-FF methods to the SABRE are graphically reported, along with the corresponding estimation errors relative to the reference trend from the engine emission database. Additionally, a discussion regarding the chemical-physical justifications for the mathematical contributions to the formulations for EINOx of the newly introduced parameters is provided.

Automated Detection of Gastrointestinal Diseases Using Resnet50*-Based Explainable Deep Feature Engineering Model with Endoscopy Images.

This work aims to develop a novel convolutional neural network (CNN) named ResNet50* to detect various gastrointestinal diseases using a new ResNet50*-based deep feature engineering model with endoscopy images. The novelty of this work is the development of ResNet50*, a new variant of the ResNet model, featuring convolution-based residual blocks and a pooling-based attention mechanism similar to PoolFormer. Using ResNet50*, a gastrointestinal image dataset was trained, and an explainable deep feature engineering (DFE) model was developed. This DFE model comprises four primary stages: (i) feature extraction, (ii) iterative feature selection, (iii) classification using shallow classifiers, and (iv) information fusion. The DFE model is self-organizing, producing 14 different outcomes (8 classifier-specific and 6 voted) and selecting the most effective result as the final decision. During feature extraction, heatmaps are identified using gradient-weighted class activation mapping (Grad-CAM) with features derived from these regions via the final global average pooling layer of the pretrained ResNet50*. Four iterative feature selectors are employed in the feature selection stage to obtain distinct feature vectors. The classifiers k-nearest neighbors (kNN) and support vector machine (SVM) are used to produce specific outcomes. Iterative majority voting is employed in the final stage to obtain voted outcomes using the top result determined by the greedy algorithm based on classification accuracy. The presented ResNet50* was trained on an augmented version of the Kvasir dataset, and its performance was tested using Kvasir, Kvasir version 2, and wireless capsule endoscopy (WCE) curated colon disease image datasets. Our proposed ResNet50* model demonstrated a classification accuracy of more than 92% for all three datasets and a remarkable 99.13% accuracy for the WCE dataset. These findings affirm the superior classification ability of the ResNet50* model and confirm the generalizability of the developed architecture, showing consistent performance across all three distinct datasets.

Research on dynamic penetration of shaped charge jet under the condition of projectile and target rendezvous

Abstract To explore the penetration behavior of jets under dynamic impact conditions and to predict and assess the dynamic penetration power of shaped charge jets, finite element methods were employed to numerically simulate shaped charge warheads under various impact conditions. Combined with theoretical analysis, the simulations analyzed the variations in perforation and dynamic penetration depth of the jet into target plates. Using a random forest algorithm, the influence weights of different factors on the dynamic penetration depth of the jet were obtained. Furthermore, an engineering model for predicting the dynamic penetration depth of shaped charge jets was established through a linear regression model. The research results indicate that the impact velocity is the most critical factor affecting the dynamic penetration depth of shaped charge jets. The dynamic penetration depth of the jet into targets within a certain range of impact velocities is approximately linear. The established engineering model can effectively predict the penetration power of jets under dynamic impact conditions.