Optimization of running-in surface morphology parameters based on the AutoML model.
Ontology highlight
ABSTRACT:
SUBMITTER: Ge G
PROVIDER: S-EPMC8489728 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:For staged multi-cluster fracturing, methods for controlling perforation friction to adjust the flow distribution of each cluster can effectively promote the uniform extension of multiple fractures but lacks a fast and quantitative optimization method for different perforation parameters of each cluster. By establishing a numerical model of single-stage three-cluster flow-limited fracturing under stress-seepage coupling, and based on the response surface optimization method, fully considering the impact of perforation parameters interaction among three perforation clusters, according to the regression equation fitted under the global response, the rapid optimization of perforation parameters of segmented multi-cluster fracturing model is realized. The results show that: in determining the three factors of the study, it is found that there is an obvious interaction between the number of intermediate cluster perforations and the number of cluster perforations on both sides, the number of cluster perforations on both sides and the diameter of intermediate cluster perforations, the response surface optimization method gives the optimal perforation parameter combination of three clusters of fractures under global response; When the perforation parameters were combined before optimization, the fracture length difference was 32.550m, and the intermediate perforation cluster evolved into invalid perforation cluster, when the perforation parameters were combined after optimization, the fracture length difference was 0.528m, the three perforation clusters spread uniformly, and there are no invalid clusters. At the same time, the regression equation under the response is optimized before and after the comparison between the predicted value of the equation and the actual simulation value. It is found that the estimated deviation rate of the equation before optimization is 1.2%, and the estimated deviation rate after optimization is 0.4%. The estimated deviation rates are all less, and the response regression equation based on the response surface optimization method can quickly optimize the perforation parameters. The response surface optimization method is suitable for the multi parameter optimization research of formation fracturing which is often affected by many geological and engineering factors. Combining with the engineering practice and integrating more factors to optimize the hydraulic fracturing parameters, it is of great significance to improve the success rate of hydraulic fracturing application.
| S-EPMC8372901 | biostudies-literature
Project description:ObjectiveThis study focuses on the innovative application of Automated Machine Learning (AutoML) technology in cardiovascular medicine to construct an explainable Coronary Artery Disease (CAD) prediction model to support the clinical diagnosis of CAD.MethodsThis study utilizes a combined data set of five public data sets related to CAD. An ensemble model is constructed using the AutoML open-source framework AutoGluon to evaluate the feasibility of AutoML in constructing a disease prediction model in cardiovascular medicine. The performance of the ensemble model is compared against individual baseline models. Finally, the disease prediction ensemble model is explained using SHapley Additive exPlanations (SHAP).ResultsThe experimental results show that the AutoGluon-based ensemble model performs better than the individual baseline models in predicting CAD. It achieved an accuracy of 0.9167 and an AUC of 0.9562 in 4-fold cross-bagging. SHAP measures the importance of each feature to the prediction of the model and explains the prediction results of the model.ConclusionThis study demonstrates the feasibility and efficacy of AutoML technology in cardiovascular medicine and highlights its potential in disease prediction. AutoML reduces the barriers to model building and significantly improves prediction accuracy. Additionally, the integration of SHAP enhances model transparency and explainability, which is critical to ensuring model credibility and widespread adoption in cardiovascular medicine.
| S-EPMC11246996 | biostudies-literature
Project description:Surface integrity has attracted the attention of researchers for improving the functional performance of engineering products. Improvement in surface finish, one of the important parameters in surface integrity, has been attempted by researchers through different processes. Grinding has been widely used for final machining of components requiring smooth surfaces coupled with precise tolerances. Proper selection of grinding wheel material and grade with grinding parameters can result in an improved surface finish and improved surface characteristics. The present work reports the study of the effect of grinding parameters on surface finish of EN8 steel. Experiments were performed on surface grinding and cylindrical grinding for optimization of grinding process parameters for improved surface finish. Grinding wheel speed, depth of cut, table feed, grinding wheel material and table travel speed for surface grinding operation, and work speed for cylindrical grinding operation were taken as the input parameters with four types of grinding wheels (Al2O3 of grades K and L, and white alumina of grades J and K). The surface roughness was taken as an output parameter for experimentation. The grinding wheel material and grade have been observed to be the most significant variables for both cylindrical grinding and surface grinding. Surface roughness in the case of surface grinding is better compared to that of cylindrical grinding, which can be attributed to vibrations produced in the cylindrical grinding attachment. Surface roughness (Ra) values of 0.757 µm in cylindrical grinding and 0.66 µm in surface grinding have been achieved.
| S-EPMC5990843 | biostudies-literature
Project description:Trajectory optimization with musculoskeletal models can be used to reconstruct measured movements and to predict changes in movements in response to environmental changes. It enables an exhaustive analysis of joint angles, joint moments, ground reaction forces, and muscle forces, among others. However, its application is still limited to simplified problems in two dimensional space or straight motions. The simulation of movements with directional changes, e.g. curved running, requires detailed three dimensional models which lead to a high-dimensional solution space. We extended a full-body three dimensional musculoskeletal model to be specialized for running with directional changes. Model dynamics were implemented implicitly and trajectory optimization problems were solved with direct collocation to enable efficient computation. Standing, straight running, and curved running were simulated starting from a random initial guess to confirm the capabilities of our model and approach: efficacy, tracking and predictive power. Altogether the simulations required 1 h 17 min and corresponded well to the reference data. The prediction of curved running using straight running as tracking data revealed the necessity of avoiding interpenetration of body segments. In summary, the proposed formulation is able to efficiently predict a new motion task while preserving dynamic consistency. Hence, labor-intensive and thus costly experimental studies could be replaced by simulations for movement analysis and virtual product design.
| S-EPMC7573630 | biostudies-literature
Project description:PURPOSE: The objectives of this study were to describe the distribution of all runners' performances in the largest marathons worldwide and to determine which environmental parameters have the maximal impact. METHODS: We analysed the results of six European (Paris, London, Berlin) and American (Boston, Chicago, New York) marathon races from 2001 to 2010 through 1,791,972 participants' performances (all finishers per year and race). Four environmental factors were gathered for each of the 60 races: temperature (°C), humidity (%), dew point (°C), and the atmospheric pressure at sea level (hPA); as well as the concentrations of four atmospheric pollutants: NO(2)-SO(2)-O(3) and PM(10) (?g x m(-3)). RESULTS: All performances per year and race are normally distributed with distribution parameters (mean and standard deviation) that differ according to environmental factors. Air temperature and performance are significantly correlated through a quadratic model. The optimal temperatures for maximal mean speed of all runners vary depending on the performance level. When temperature increases above these optima, running speed decreases and withdrawal rates increase. Ozone also impacts performance but its effect might be linked to temperature. The other environmental parameters do not have any significant impact. CONCLUSIONS: The large amount of data analyzed and the model developed in this study highlight the major influence of air temperature above all other climatic parameter on human running capacity and adaptation to race conditions.
| S-EPMC3359364 | biostudies-other
Project description:Process-based models are effective tools to predict the phenotype of an individual in different growing conditions. Combined with a quantitative trait locus (QTL) mapping approach, it is then possible to predict the behavior of individuals with any combinations of alleles. However the number of simulations to explore the realm of possibilities may become infinite. Therefore, the use of an efficient optimization algorithm to intelligently explore the search space becomes imperative. The optimization algorithm has to solve a multi-objective problem, since the phenotypes of interest are usually a complex of traits, to identify the individuals with best tradeoffs between those traits. In this study we proposed to unroll such a combined approach in the case of peach fruit quality described through three targeted traits, using a process-based model with seven parameters controlled by QTL. We compared a current approach based on the optimization of the values of the parameters with a more evolved way to proceed which consists in the direct optimization of the alleles controlling the parameters. The optimization algorithm has been adapted to deal with both continuous and combinatorial problems. We compared the spaces of parameters obtained with different tactics and the phenotype of the individuals resulting from random simulations and optimization in these spaces. The use of a genetic model enabled the restriction of the dimension of the parameter space toward more feasible combinations of parameter values, reproducing relationships between parameters as observed in a real progeny. The results of this study demonstrated the potential of such an approach to refine the solutions toward more realistic ideotypes. Perspectives of improvement are discussed.
| S-EPMC5167719 | biostudies-literature
Project description:Microparticle separation
| S-EPMC9835635 | biostudies-literature
Project description:The ant colony algorithm (ACA) is a heuristic algorithm that resolves the optimality problem by simulating an ant's foraging process, which finds the shortest path. The connotation of the ACA is to find the optimal solution. The Proportional Integral Derivative (PID) parameter tuning is an essential tool in the control field and includes three parameters, Kp, Ki, and Kd, to achieve the best control effect. Besides, tuning the PID parameters is closely related to finding the "optimal" solution that can be attained based on the feasible combination of the two. This article transforms the PID parameter tuning problem into an ACA that finds the optimal solution called ACA-based PID parameters tuning. Furthermore, PID control is simulated by setting the parameters of ACA, such as ant colony size, iteration times, nodes, paths, path evaluation criteria, pheromone concentration, heuristic function, weight factor, and decision function. Eventually, the two PID controller parameter tuning strategies are compared and analyzed, and the advantages and disadvantages of each are obtained. Compared with the 4:1 attenuation curve method, the proposed method can significantly reduce the MP score of the overshoot of the system, increase the time, and improve the dynamic and steady-state performance of the system, but reduce the steady-state error of the system. Therefore, the feasibility and effectiveness of the proposed method is verified.
| S-EPMC10703037 | biostudies-literature
Project description:This study investigates the use of microalgae as a biosorbent to eliminate heavy metals ions from wastewater. The Chlorella kessleri microalgae species was employed to biosorb heavy metals from synthetic wastewater specimens. FTIR, and SEM/XRD analyses were utilized to characterize the microalgal biomass (the adsorbent). The experiments were conducted with several process parameters, including initial solution pH, temperature, and microalgae biomass dose. In order to secure the best experimental conditions, the optimum parameters were estimated using an integrated response surface methodology (RSM), desirability function (DF), and crow search algorithm (CSA) modeling approach. A maximum lead(II) removal efficiency of 99.54% was identified by the RSM-DF platform with the following optimal set of parameters: pH of 6.34, temperature of 27.71 °C, and biomass dosage of 1.5 g L-1. The hybrid RSM-CSA approach provided a globally optimal solution that was similar to the results obtained by the RSM-DF approach. The consistency of the model-predicted optimum conditions was confirmed by conducting experiments under those conditions. It was found that the experimental removal efficiency (97.1%) under optimum conditions was very close (less than a 5% error) to the model-predicted value. The lead(II) biosorption process was better demonstrated by the pseudo-second order kinetic model. Finally, simultaneous removal of metals from wastewater samples containing a mixture of multiple heavy metals was investigated. The removal efficiency of each heavy metal was found to be in the following order: Pb(II) > Co(II) > Cu(II) > Cd(II) > Cr(II).
| S-EPMC7493913 | biostudies-literature
Project description:Endometriosis is a chronic gynecological disorder characterized by the growth of endometrial glands and stroma outside the endometrial cavity producing inflammation and pain. Previously we demonstrated that modulation of the hypothalamic pituitary adrenal (HPA) axis exacerbates the development and severity of this condition. A physically active lifestyle has been shown to confer health benefits in many chronic conditions by potentially acting as a stress buffer, thus we hypothesized that voluntary physical exercise can 'realign/reset' the HPA axis resulting in reduced endometriosis symptoms in an animal model.MethodsEndometriosis was induced in female Sprague Dawley rats by implanting uterine tissue next to the intestinal mesentery on day 0. Sham controls received sutures only. One group of endometriosis animals had access to a running wheel for 2 weeks prior to endometriosis induction until time of sacrifice at day 60. Sham and endometriosis controls received no exercise. All animals were examined for developed vesicles which were collected and measured. Uterine tissue was analyzed for cellular infiltration. Brain, liver, spleen, adrenal glands, leg muscles and fat were collected, along with peritoneal fluid and blood.ResultsEndometriosis animals developed vesicles in 86.96% of the implants with significantly increased mesenteric fat compared to sham (p<0.05). Exposure to exercise significantly decreased the size (p<0.01) and number (p<0.05) of vesicles that developed, as well as the mesenteric fat (p<0.01). Exercised animals had higher levels of lactoferrin in peritoneal fluid, and decreased serum fractalkine and leptin. Exercise significantly increased estrogen alpha receptor expression levels (p<0.01), while significantly decreasing estrogen receptor beta expression (p<0.01) and macrophage infiltration (p<0.05) in vesicles compared to non- exercised animals.ConclusionsOur results suggest that voluntary physical activity might protect against endometriosis and alleviate the associated inflammation via immune modulation of the HPA axis. This offers the potential for further exploration of exercise as a complementary therapy in endometriosis patients.
| S-EPMC9580825 | biostudies-literature