Model Test Results Research Articles

Using supervised machine learning and ICD10 to identify non-accidental trauma in pediatric trauma patients in the Maryland Health Services Cost Review Commission dataset.

Identifying non-accidental trauma (NAT) in pediatric trauma patients is challenging. We developed a machine learning model that uses demographic characteristics and ICD10 codes to detect the first diagnosis of NAT. We analyzed data from the Maryland Health Services Cost Review Commission (2015-2020) for patients aged 0-19years. Relevant ICD10 codes associated with NAT and trauma were identified. Health records preceding the patients' first trauma diagnosis were analyzed. Random forest models were built using covariates selected through penalized regularization. Models were developed for confirmed and suspected NAT. Data was divided into 80/20 split for model training and testing. We conducted analysis in R. We analyzed 128,351 non-NAT trauma patients, 522 confirmed NAT patients, and 2128 suspected NAT patients totaling 364,217 encounters. Variable selection identified 55 covariates for confirmed NAT and 65 for suspected NAT for model development. These covariates were primarily musculoskeletal injuries of the head and extremities. Model testing results are summarized in Table 1. Our study uses machine learning to identify NAT within the pediatric trauma cohort. Analyzing ICD10 categories before the first traumatic diagnosis may allow for earlier detection of NAT. Additional research in building learning models with ICD10 codes is needed to better understand how clinician and billing biases may impact predictive models. Supervised machine learning can potentially augment clinical decision-making and enhance pediatric trauma care.

Experimental study and numerical simulation on the bearing behavior of the modified suction caisson under misalignment lateral cyclic and monotonic loadings

Suction caissons for offshore wind turbines are subjected to lateral misalignment wind and wave loads during service life, leading to the occurrence of accumulate deflection and changes in lateral bearing capacity. Experimental studies and numerical simulations were performed to investigate the motion mode, accumulated lateral deflection, and bearing capacity of a modified suction caisson (MSC) under misalignment lateral cyclic and monotonic loadings. Under misalignment lateral cyclic and monotonic loadings, the motion behavior of the MSC is combined with the translation, rotation, and torsion. The direction of MSC motion lies between cyclic and monotonic loading directions. The angle between the motion direction and cyclic loading direction is far less than that between the motion direction and monotonic loading direction. Under the same cyclic and monotonic load values, the maximum accumulated deflection was obtained when the angle between lateral cyclic and monotonic loading directions (which is defined as the misalignment angle) equals 30°. In addition, the lateral bearing capacity of the MSC after misalignment cyclic and monotonic loading was found to decrease with increasing the misalignment angle. The minimum lateral bearing capacity of the MSC after misalignment loading was obtained when the misalignment angle equals 180°. Based on the model test and simulation results, the method applying the model test results to the practical engineering is proposed.

Mechanical mechanism and theoretical analysis of anchor net support based on model test and numerical simulation

The control of broken rock mass roadways has always been a difficult problem in metal hard rock mines. In this paper, the mechanical mechanism of anchor net support is characterized and simulated through the physical model test of the prestressed support self-bearing structure of the broken rock mass. The deformation characteristics and interaction relationships of the surrounding rock and the support body under different dynamic impact effects are obtained by using the embedded anchor strain gauge and rock micro-strain sensors. The stress evolution process and deformation characteristics of the anchor and rock mass of the prestressed support self-bearing structure of the broken rock mass under different loads are simulated by applying Phase2. The results are in good agreement with the results of the physical model test. Based on the theory of surrounding rock compression arch and the Hoek-Brown criterion, the minimum anchorage force of the prestressed anchor to maintain the stability of the surrounding rock is derived and calculated by the limit equilibrium rule. The research results explain the mechanical mechanism of the broken rock mass support from the aspects of physical experiments, numerical simulations and theoretical derivations, which can provide theoretical guidance for the support design of practical engineering.

Research on BP Neural Network Prediction of Financial Transformation and Upgrading Potential of Enterprises in the Digital and Intelligent Era

In order to reduce the operational risks of enterprises and help enterprises improve their core competitiveness, this paper studies the BP neural network prediction method for the financial transformation and upgrading potential of enterprises in the age of digital intelligence. Select the sample data of enterprises from Shanghai and Shenzhen Stock Exchanges, use the financial data of these enterprises to build an indicator of the potential for financial transformation and upgrading of enterprises, and use the nonparametric test method to eliminate the duplicate content in the indicator, and provide the tested indicators as input to the BP neural network model. Under the prediction of the model, obtain the potential for financial transformation and upgrading of different enterprises. The model test results show that the prediction method has a high fitting effect, which can divide the company’s financial transformation and upgrading potential into three states: poor, ordinary, and high, while maintaining accurate prediction ability.

A novel leg design for reducing consolidation settlement of deeply embedded spudcan foundations in clayey seabed soils

Field monitoring data has demonstrated excessive spudcan settlement during jack-up rig operation. However, there are no methods available for operators to reduce the consolidation settlement development. This paper presents a centrifuge and numerical model investigation aimed at reducing spudcan settlement. Initially, two centrifuge model tests were carried out to realistically replicate spudcan "penetration-unloading-consolidation" stages in an offshore field. The test results show that the spudcan consolidation settlement was partially reduced by the presence of an existing lattice leg extending from the top of spudcan footing. Based on this, it is suspected that a sleeve of a certain length extending from the top of the spudcan footing could be used to further reduce spudcan consolidation settlement. This work was accomplished by conducting small strain finite element analysis, the feasibility and reliability of the numerical model were first verified by comparing with centrifuge model test results. Subsequently, numerical models of spudcan installation and consolidation were conducted for both plain and sleeved-spudcan footings, under various soil strengths, operational loads, and embedment depths. Numerical results show that the top-mounted sleeve helped to prevent soil above the spudcan footing from moving downward, thereby reducing spudcan settlement. Based on the numerical results, an explicit equation assessing sleeved-spudcan consolidation settlement was established, as a function of sleeve area ratio and correlated well with that of a plain spudcan. This study provides a feasible and reliable numerical method for assessing spudcan consolidation settlement as well as an effective leg design to reduce settlement.

Decoding the synergy: unveiling gradient boosting regression model for multivariate quantitation of pioglitazone, alogliptin and glimepiride in pure and tablet dosage forms

This study represents a comparison among the performances of four multivariate procedures: partial least square (PLS) and artificial neural networks (ANN) in addition to support vector regression (SVR) and extreme gradient boosting (XG Boost) algorithm for the determination of the anti-diabetic mixture of pioglitazone (PIO), alogliptin (ALG) and glimepiride (GLM) in pharmaceutical formulations with aid of UV spectrometry. Key wavelengths were selected using knowledge-based variable selection and various preprocessing methods (e.g., mean centering, orthogonal scatter correction, and principal component analysis) to minimize noise and improve model precision. XG Boost effectively enhanced computing speed and accuracy by focusing on specific spectral features rather than the entire spectrum, demonstrating its advantages in resolving complex, overlapping spectral data. The independent test results of different models demonstrated that XG Boost outperformed other methods. XG Boost achieved the lowest root mean squared error of prediction (RMSEP) and standard deviation (SD) values across all compounds, indicating minimal prediction error and variability. For PIO, XG Boost recorded an RMSEP of 0.100 and SD of 0.369, significantly better than PLS and ANN. For ALG, XG Boost showed near-perfect performance with an RMSEP of 0.001 and SD of 0.005, outperforming SVR and PLS, which had higher error rates. In the case of GLM, XG Boost also excelled with an RMSEP of 0.001 and SD of 0.018, demonstrating superior precision compared to the much higher errors seen in PLS and ANN. These results highlight XG Boost’s exceptional ability to handle complex, overlapping spectral data, making it the most reliable and accurate model in this study.

Upper bound solution of the vertical bearing capacity of the pile-bucket composite foundation of offshore wind turbines

Pile-bucket composite foundations are regarded as a promising solution for offshore wind power infrastructure. However, accurately assessing their vertical ultimate bearing capacity remains a technical challenge. Therefore, establishing an upper bound solution of the ultimate bearing capacity of the composite foundations is of significant importance for their promotion and application. This study begins with small-scale model tests, using Abaqus for modeling based on the relevant test conditions. Next, following model validation, the vertical bearing capacity of the composite foundations under different H/D ratios and the corresponding soil failure modes are investigated. According to the upper limit method and the ultimate equilibrium theory, the kinematic velocity field is subsequently constructed to derive the upper bound solution of the vertical bearing capacity. Finally, the effectiveness and accuracy of the proposed theoretical upper bound solution are verified against the results of model tests, and this study hopes to provide a reference for the future design of vertical bearing capacity of pile-bucket composite foundations.

Prediction of Blast Vibration Velocity of Buried Steel Pipe Based on PSO-LSSVM Model.

In order to ensure the safe operation of adjacent buried pipelines under blast vibration, it is of great practical engineering significance to accurately predict the peak vibration velocity ofburied pipelines under blasting loads. Relying on the test results of the buried steel pipe blast model test, a sensitivity analysis of relevant influencing factors was carried out by using the gray correlation analysis method. A least squares support vector machine (LS-SVM) model was established to predict the peak vibration velocity of the pipeline and determine the best parameter combination in the LS-SVM model through a local particle swarm optimization (PSO), and the results of the PSO-LSSVM model were predicted. These were compared with BP neural network model and Sa's empirical formula. The results show that the fitting correlation coefficient (R2), root mean square error (RMSE), average relative error (MRE), and Nash coefficient (NSE) of the PSO-LSSVM model for the prediction of pipeline peak vibration velocity are 91.51%, 2.95%, 8.69%, and 99.03%, showing that the PSO-LSSVM model has a higher prediction accuracy and better generalization ability, which provides a new idea for the vibration velocity prediction of buried pipelines under complex blasting conditions.

Recognition of Maize Tassels Based on Improved YOLOv8 and Unmanned Aerial Vehicles RGB Images

The tasseling stage of maize, as a critical period of maize cultivation, is essential for predicting maize yield and understanding the normal condition of maize growth. However, the branches overlap each other during the growth of maize seedlings and cannot be used as an identifying feature. However, during the tasseling stage, its apical ear blooms and has distinctive features that can be used as an identifying feature. However, the sizes of the maize tassels are small, the background is complex, and the existing network has obvious recognition errors. Therefore, in this paper, unmanned aerial vehicle (UAV) RGB images and an improved YOLOv8 target detection network are used to enhance the recognition accuracy of maize tassels. In the new network, a microscale target detection head is added to increase the ability to perceive small-sized maize tassels; In addition, Spatial Pyramid Pooling—Fast (SPPF) is replaced by the Spatial Pyramid Pooling with Efficient Layer Aggregation Network (SPPELAN) in the backbone network part to connect different levels of detailed features and semantic information. Moreover, a dual-attention module synthesized by GAM-CBAM is added to the neck part to reduce the loss of features of maize tassels, thus improving the network’s detection ability. We also labeled the new maize tassels dataset in VOC format as the training and validation of the network model. In the final model testing results, the new network model’s precision reached 93.6% and recall reached 92.5%, which was an improvement of 2.8–12.6 percentage points and 3.6–15.2 percentage points compared to the mAP50 and F1-score values of other models. From the experimental results, it is shown that the improved YOLOv8 network, with high performance and robustness in small-sized maize tassel recognition, can accurately recognize maize tassels in UAV images, which provides technical support for automated counting, accurate cultivation, and large-scale intelligent cultivation of maize seedlings.

Blockchain-inspired intelligent framework for logistic theft control

The smart logistics industry utilizes advanced software and hardware technologies to enhance efficient transmission. By integrating smart components, it identifies vulnerabilities within the logistics sector, making it more susceptible to physical attacks aimed at theft and control. The main goal is to propose an effective logistics monitoring system that automates theft prevention. Specifically, the suggested model analyzes logistics transmission patterns through secure surveillance enabled by IoT-based blockchain technology. Additionally, a bi-directional convolutional neural network is employed to evaluate real-time theft vulnerabilities, aiding optimal decision-making. The proposed method has been shown to provide accurate real-time analysis of risky behaviors. Experimental simulations indicate that the proposed solution significantly improves logistics monitoring. The system’s performance is assessed using various statistical metrics, including latency rate (7.44 s), a data processing cost (O((n−1)logn)), and model training and testing results (precision (94.60%), recall (95.67%), and F-Measure (96.64%)), statistical performance (error reduction (48%)) and reliability (94.48%).

Contact Stiffness Identification Method for Joint Surface and the Effect of Contact Stiffness on the Dynamic Response of the Cable Bracket

The cable bracket is one of the crucial components of high-speed Electric Multiple Units (EMUs), which is fixed to the axle box by bolts to support the cable. As an important parameter of the joint surface, contact stiffness significantly affects the dynamic response and service life of the cable bracket. However, it is difficult to directly measure the contact stiffness of the joint surface. As a result, an identification method is proposed in this investigation to identify the contact stiffness. A finite element model incorporating both normal and tangential stiffness parameters is developed. According to the finite element model and modal testing results, an improved particle swarm optimization algorithm is employed to identify the contact stiffness of the joint surface. The effect of the contact stiffness on the vibrations of the cable bracket is investigated. The findings indicate that pre-tightening torque significantly influences the contact stiffness of the cable bracket. The contact stiffness has a great effect on the vibrations of the cable bracket. Optimal contact stiffness notably reduces vibrations of the cable bracket, thereby extending its service life.

A Restoring Force Correction Model for Enveloped Steel Jacket-Confined Seismic-Damaged Rectangular Recycled Aggregate Concrete-Filled Steel Tubular Columns

In order to establish a suitable restoring force correction model for enveloped steel jacket (ESJ)-confined seismic-damaged rectangular recycled aggregate concrete-filled steel tubular (RRACFST) columns, based on experimental research, a study of the seismic performance and parameters of ESJ-confined seismic-damaged RRACFST columns was carried out. The restoring force theory, model test, and OpenSees simulation of ESJ-confined seismic-damaged RRACFST columns were conducted. Firstly, a trilinear model of the skeleton curve and a suitable restoring force model for ESJ-confined seismic-damaged RRACFST columns were established. The results were compared with the model test results, and it was found that the two results had good consistency. Secondly, the initial damage of the RRACFST column was simulated by the reducing material properties method, and a correct numerical model for ESJ-confined seismic-damaged RRACFST columns was proposed. The influence mechanism of seismic parameters of the RRACFST column was clarified. Finally, the seismic parameter combination with the best seismic performance for ESJ-confined seismic-damaged RRACFST columns was established; namely, the replacement rate of recycled coarse aggregate is 50%, the concrete strength is C40, the axial compression ratio is 0.3, the strength of the rectangular steel tube is Q345, the wall thickness of the steel tube is 4 mm, and the slenderness ratio is 7.5.

Influence of labyrinth clearance on the hydrodynamic performance of a high head Francis turbine

Abstract Francis turbines have a leakage loss from the corresponding labyrinth seals i.e., crown side and a skirt side labyrinth clearance. Therefore, the labyrinth clearance between the runner and turbine cover plays an important role in the hydrodynamic characteristics of the hydro turbine. Generally, the geometrical details of labyrinth clearance are not considered in the numerical model due to complexity involved in modelling and requirement of high computational power that may lead inaccurate prediction of performance of the turbine. In the present investigation, steady-state numerical simulations have been performed on a high head Francis turbine, under different operating conditions, ranging from part load to overload condition, to assess the influence of labyrinth clearance on the hydrodynamic performance of the turbine. FVM method (as discretization method) along with SST k-omega turbulence model has been adopted for computational modelling. The simulation results such as hydraulic efficiency and power output are validated with model test results which was done as per IEC 60193 standard and found satisfactory agreement. Further, the axial thrust force is also computed for different operating conditions and compared with model test results. Based on the simulation results, it has been found that the hydraulic efficiency of turbine with labyrinth clearance was found 0.4% - 1.1% lower than the turbine without labyrinth clearance. The influence of labyrinth clearance on the turbine performance is higher at part-load condition compared to other operating conditions. It is observed that the leakage loss is almost same for all loading conditions at a particular head and fall in the range of 0.61% - 0.81%. Further, the value of axial thrust increases with the increases in discharge value and value of maximum axial thrust was found as 203 kN at overload condition.

A refined nonlinear theoretical model for mechanical analysis of tunnels subjected to strike-slip faulting with multiple fault planes

During strike-slip fault dislocation, multiple fault planes are commonly observed. The resulting permanent ground deformation can lead to profound structural damage to tunnels. However, existing analytical models do not consider multiple fault planes. Instead, they concentrate the entire fault displacement onto a single fault plane for analysis, thereby giving rise to notable errors in the calculated results. To address this issue, a refined nonlinear theoretical model was established to analyze the mechanical responses of the tunnels subjected to multiple strike-slip fault dislocations. The analytical model considers the number of fault planes, nonlinear soil‒tunnel interactions, geometric nonlinearity, and fault zone width, leading to a significant improvement in its range of applicability and calculation accuracy. The results of the analytical model are in agreement, both qualitatively and quantitatively, with the model test and numerical results. Then, based on the proposed theoretical model, a sensitivity analysis of parameters was conducted, focusing on the variables such as the number of fault planes, fault plane distance (d), fault displacement ratio (η), burial depth (C), crossing angle (β), tunnel diameter (D), fault zone width (Wf), and strike-slip fault displacement (Δfs). The results show that the peak shear force (Vmax), bending moment (Mmax), and axial force (Nmax) decrease with increasing d. The Vmax of the tunnel is found at the fault plane with the largest fault displacement. C, D, and Δfs contribute to the increases in Vmax, Mmax, and Nmax. Additionally, increasing the number of fault planes reduces Vmax and Mmax, whereas the variation in Nmax remains minimal.

Practical 6-DoF Manoeuvring Simulation of a BB2 Submarine Near the Free Surface

It is necessary to predict the manoeuvring performance of a submarine accurately at the early design stage for its safe and effective operations. In this paper, the practical 6-DoF simulation models of an X-form stern plane submarine operating near the free surface are proposed. A 1/15 scaled model of ‘BB2 submarine’ is constructed, the captive model tests are performed in a towing tank of Korea Research Institute of Ships and Ocean Engineering (KRISO) at the full-scale depths, 30, 15.4 (snorkel depth), and 4.5 metres (surfaced depth). Resistance and propulsion tests are performed at the deepest depth, 30 metres. The vertical planar motion mechanism (PMM) tests including the forced rolling motions are also carried out at the depth of 30 metres. The horizontal PMM tests are conducted at three kinds of depths, respectively. The depth-varying horizontal plane coefficients in the model are identified, and the coefficients which are little influenced by the depths are treated as the constant values for the practical purpose. Some of velocity coupled terms are approximated by using the added mass coefficients on the assumption that the viscous components are negligible. In addition, the resistance increases, vertical suction forces and moments are measured in the straight-ahead tests with varying the submergence depths. The free surface effects are considered as the exponential function terms in the proposed models. Based on the present tests and the previous studies about the free surface effects on the submerged bodies, it is practically assumed that the free surface effects are exponentially decayed with the depths, and are already negligible when the submergence depth is 30 metres, approximately three times the hull depth. Horizontal and vertical plane manoeuvring motions as well as the neutral flights are simulated with the control plane deflections less than 15 degrees. The present simulations are in good agreements with existing free-running model test results.

Simulation and experimental analysis of traveling wave resonance of flexible spiral bevel gear system

Considering the traveling wave resonance (TWR) phenomenon of the spiral bevel gear system in the aero engine accessory casing, the flexible spiral bevel gear model is established by three-dimensional (3D) shell element and beam element. The dynamic model of flexible bevel gear system considering the change of meshing teeth pairs in the operating process is established by component mode synthesis (CMS) method and rotational modal projection method. The proposed model is verified by finite element (FE) solid model and experiment test results. On this basis, the TWR phenomenon of the bevel gear system is studied in combination with dynamic response and vibration stress experimental test. The results show that the bevel gear system has 3 nodal diameter resonance speeds within the actual operating speed range, which are one 1st nodal diameter resonance of pinion and two 1st nodal diameter resonance of gear. When the bevel gear system operates at TWR state, the amplitude corresponding to fm ± m·fr (fm is meshing frequency, m is nodal diameter number, fr is shaft rotational frequency) is larger than that corresponding to fm in the Fast Fourier transform (FFT) spectrum of the of the gear foundation vibration stress, and the vibration stress cloud map of the gear foundation shows the corresponding nodal diameter vibration shape. The research results provide a theoretical basis for feature recognition and influence law evaluation of TWR of bevel gear system.

Admission Prediction for Freshmen Students Using Low-cost Data Analytics Tool

This research paper tackles the admission prediction of enrollment for the tertiary level using the Naïve Bayes classification technique. Using data mining, the Naïve Bayes algorithm is simulated using Data Analytics Tool (DAT) and Weka data mining to provide the classifier model in evaluating if the given college freshmen applicant will continue or discontinue to be admitted to college. In line with the method, the researcher used gender, senior high school average grade, senior high school type, senior high school strand, and college entrance exam result. The training data set used for this machine learning model comprises 750 records from the different freshmen applications. As a result of the classifier model testing in Weka, the correct instances captured from the original 750 records is 86.27%, which is significantly higher and makes the classifier model reliable. In addition, a confusion matrix is performed and computed with an accuracy of 86.27%, precision of 83.13%, recall of 95.34%, and F1 score of 88.82%. Thus, the model test result is favorable to the reliability of the classifier model using Naïve Bayes technique.

Studying the Stability of Anthocyanin Pigments Isolated from Juices of Colored-Fleshed Potatoes

The aim of this study was to obtain extracts of anthocyanin pigments from red and purple-fleshed potato juices characterized by stable color. For this purpose, potato juices were pasteurized at different temperatures or fruit and vegetable concentrates were added to them. Color stability tests of the obtained pigments were carried out in model pH and temperature conditions and after adding to natural yogurt. Both the pasteurization process and the addition of fruit and vegetable concentrates to the potato juices positively affected their color and its stability in time. However, the pasteurization of the potato juices had a negative effect on the content of biologically active compounds, in contrast to the juices stabilized with the addition of fruit and vegetable concentrates. Anthocyanin pigments from red-fleshed potato juices were more stable than those isolated from the purple-fleshed potato juices. The results of model tests of the anthocyanin pigment concentrates from the colored-flesh potatoes and natural yoghurts with their addition confirmed the high stability of the tested concentrates.

Numerical Analysis and Safety Assessment of the Former Site of Shanghai South Downtown Library Reinforced by U-Steel During Integral Translation

ABSTRACT The utilization of overall translation techniques in buildings offers numerous advantages, including cost-effectiveness, shortened construction timelines, and environmental sustainability. These techniques are increasingly being employed for the conservation and renovation of existing historic structures. Taking the former site project of the South Downtown Library in Shanghai, which requires the overall translation due to the requirements of urban renewal, as an example, a systematic detection and identification of the damage and safety states of the overall structure were conducted. The damaged condition and overall structural safety were evaluated, and the corresponding reinforcement and repair suggestions were proposed. The former site of the library, a brick-timber mixed structure, was reinforced using U-steel through internal support and external pulling. The structure was also lifted and translated using the overall translation technique. The displacement responses of the key parts of the structure were monitored using the displacement sensors during the translation. The detailed finite element model of the former site of the Shanghai south downtown library, strengthened by U-steel, was established using the ABAQUS. The displacement responses of the structure’s key components during the jacking and translation were analyzed, and compared with the actual monitoring results. Good agreements were observed between the model predictions and test results. Utilizing the validated finite element model, parametric analyses were carried out. The effects of the rate of jacking and translation as well as the ground flatness on the displacement responses of a structure were analyzed, the mechanical and safety states of the structure reinforced with U-steel were further evaluated. This study can provide a reference for the overall translation technique and safety assessment of similar historic buildings in the urban renewal processes.

Construction of Solid-Liquid Two-Phase Flow and Wear Rate Prediction Model in Multiphase Pump Based on Mixture Model-Discrete Phase Model Combination Method

Blade wear is the critical problem in the operation of multiphase pump. This paper presents a numerical study of the multiphase flow of multiphase pump. The trajectory of particles in the pump is calculated by the discrete phase model. Then, the simulation results are compared with the model test results of the pump to verify the correctness of the simulation method. The results show that the particles in the impeller domain are mainly near the hub, and the particles in the diffuser domain form a agglomerated area in the middle of the flow channel. The average wear rate of the impeller is more affected by the particle size than that of the diffuser. The maximum wear rate of blade surface increases first and then decreases with the increase of particle size. According to the wear data under different particle sizes, the regression model between particle size and wear rate is fitted to predict the wear of mixed transport pump in actual operation. The research results have important reference value for the prediction of the wear performance of the multiphase pump.