Integrating Bayesian Optimization with Volume of Fluid (VOF) simulations, this work aims to optimize the operational conditions and geometric parameters of T-junction microchannels for target droplet sizes. Bayesian O...Integrating Bayesian Optimization with Volume of Fluid (VOF) simulations, this work aims to optimize the operational conditions and geometric parameters of T-junction microchannels for target droplet sizes. Bayesian Optimization utilizes Gaussian Process (GP) as its core model and employs an adaptive search strategy to efficiently explore and identify optimal combinations of operational parameters within a limited parameter space, thereby enabling rapid optimization of the required parameters to achieve the target droplet size. Traditional methods typically rely on manually selecting a series of operational parameters and conducting multiple simulations to gradually approach the target droplet size. This process is time-consuming and prone to getting trapped in local optima. In contrast, Bayesian Optimization adaptively adjusts its search strategy, significantly reducing computational costs and effectively exploring global optima, thus greatly improving optimization efficiency. Additionally, the study investigates the impact of rectangular rib structures within the T-junction microchannel on droplet generation, revealing how the channel geometry influences droplet formation and size. After determining the target droplet size, we further applied Bayesian Optimization to refine the rib geometry. The integration of Bayesian Optimization with computational fluid dynamics (CFD) offers a promising tool and provides new insights into the optimal design of microfluidic devices.展开更多
With the European Union(EU)introducing the Carbon Border Adjustment Mechanism(CBAM),accurately forecasting EU carbon price is crucial for exporters to estimate export costs,plan low-carbon strategies,and mitigate trad...With the European Union(EU)introducing the Carbon Border Adjustment Mechanism(CBAM),accurately forecasting EU carbon price is crucial for exporters to estimate export costs,plan low-carbon strategies,and mitigate trade risks.In the petroleum sector,carbon pricing directly influences upstream investment returns and carbon intensity targets,thereby closely linking emissions markets with fossil energy strategies.Existing models often fail to fully capture the nonlinear,non-stationary nature of carbon prices and their dependence on external factors.This study proposes a novel hybrid framework that combines improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN)with gated recurrent unit-convolutional neural network-long short-term memory network-Bayesian optimization(GRU-CNN-LSTM-BO).Empirical results based on the EU emissions trading system(ETS)market demonstrate that the proposed model significantly improves forecasting accuracy.Among all experiments,the proposed GRU-CNN-LSTM-BO framework achieves the best performance,yielding the lowest MAE(1.3872),RMSE(1.7038),MAPE(0.0166),and MSPE(0.0004),as well as the highest R2(0.9400).Compared to all benchmark models,the GRU-CNN-LSTM-BO model achieves reductions in MAE and RMSE ranging from 5.38%to 63.65%and 8.97%to 64.41%,respectively.To further validate the generalization ability and predictive performance of the proposed model,it is also applied to China's ETS.The results show that the GRU-CNN-LSTM-BO model also performs very well in China's ETS.展开更多
Advanced programmable metamaterials with heterogeneous microstructures have become increasingly prevalent in scientific and engineering disciplines attributed to their tunable properties.However,exploring the structur...Advanced programmable metamaterials with heterogeneous microstructures have become increasingly prevalent in scientific and engineering disciplines attributed to their tunable properties.However,exploring the structure-property relationship in these materials,including forward prediction and inverse design,presents substantial challenges.The inhomogeneous microstructures significantly complicate traditional analytical or simulation-based approaches.Here,we establish a novel framework that integrates the machine learning(ML)-encoded multiscale computational method for forward prediction and Bayesian optimization for inverse design.Unlike prior end-to-end ML methods limited to specific problems,our framework is both load-independent and geometry-independent.This means that a single training session for a constitutive model suffices to tackle various problems directly,eliminating the need for repeated data collection or training.We demonstrate the efficacy and efficiency of this framework using metamaterials with designable elliptical holes or lattice honeycombs microstructures.Leveraging accelerated forward prediction,we can precisely customize the stiffness and shape of metamaterials under diverse loading scenarios,and extend this capability to multi-objective customization seamlessly.Moreover,we achieve topology optimization for stress alleviation at the crack tip,resulting in a significant reduction of Mises stress by up to 41.2%and yielding a theoretical interpretable pattern.This framework offers a general,efficient and precise tool for analyzing the structure-property relationships of novel metamaterials.展开更多
The packaging quality of coaxial laser diodes(CLDs)plays a pivotal role in determining their optical performance and long-term reliability.As the core packaging process,high-precision laser welding requires precise co...The packaging quality of coaxial laser diodes(CLDs)plays a pivotal role in determining their optical performance and long-term reliability.As the core packaging process,high-precision laser welding requires precise control of process parameters to suppress optical power loss.However,the complex nonlinear relationship between welding parameters and optical power loss renders traditional trial-and-error methods inefficient and imprecise.To address this challenge,a physics-informed(PI)and data-driven collaboration approach for welding parameter optimization is proposed.First,thermal-fluid-solid coupling finite element method(FEM)was employed to quantify the sensitivity of welding parameters to physical characteristics,including residual stress.This analysis facilitated the identification of critical factors contributing to optical power loss.Subsequently,a Gaussian process regression(GPR)model incorporating finite element simulation prior knowledge was constructed based on the selected features.By introducing physics-informed kernel(PIK)functions,stress distribution patterns were embedded into the prediction model,achieving high-precision optical power loss prediction.Finally,a Bayesian optimization(BO)algorithm with an adaptive sampling strategy was implemented for efficient parameter space exploration.Experimental results demonstrate that the proposedmethod effectively establishes explicit physical correlations between welding parameters and optical power loss.The optimized welding parameters reduced optical power loss by 34.1%,providing theoretical guidance and technical support for reliable CLD packaging.展开更多
Miniature air quality sensors are widely used in urban grid-based monitoring due to their flexibility in deployment and low cost.However,the raw data collected by these devices often suffer from low accuracy caused by...Miniature air quality sensors are widely used in urban grid-based monitoring due to their flexibility in deployment and low cost.However,the raw data collected by these devices often suffer from low accuracy caused by environmental interference and sensor drift,highlighting the need for effective calibration methods to improve data reliability.This study proposes a data correction method based on Bayesian Optimization Support Vector Regression(BO-SVR),which combines the nonlinear modeling capability of Support Vector Regression(SVR)with the efficient global hyperparameter search of Bayesian Optimization.By introducing cross-validation loss as the optimization objective and using Gaussian process modeling with an Expected Improvement acquisition strategy,the approach automatically determines optimal hyperparameters for accurate pollutant concentration prediction.Experiments on real-world micro-sensor datasets demonstrate that BO-SVR outperforms traditional SVR,grid search SVR,and random forest(RF)models across multiple pollutants,including PM_(2.5),PM_(10),CO,NO_(2),SO_(2),and O_(3).The proposed method achieves lower prediction residuals,higher fitting accuracy,and better generalization,offering an efficient and practical solution for enhancing the quality of micro-sensor air monitoring data.展开更多
A brain tumor is a disease in which abnormal cells form a tumor in the brain.They are rare and can take many forms,making them difficult to treat,and the survival rate of affected patients is low.Magnetic resonance im...A brain tumor is a disease in which abnormal cells form a tumor in the brain.They are rare and can take many forms,making them difficult to treat,and the survival rate of affected patients is low.Magnetic resonance imaging(MRI)is a crucial tool for diagnosing and localizing brain tumors.However,themanual interpretation of MRI images is tedious and prone to error.As artificial intelligence advances rapidly,DL techniques are increasingly used in medical imaging to accurately detect and diagnose brain tumors.In this study,we introduce a deep convolutional neural network(DCNN)framework for brain tumor classification that uses EfficientNet-B6 as the backbone architecture and adds additional layers.The model achieved an accuracy of 99.10%on the public Brain Tumor MRI datasets,and we performed an ablation study to determine the optimal batch size,optimizer,loss function,and learning rate to maximize the accuracy and robustness of the model,followed by K-Fold cross-validation and testing the model on an independent dataset,and tuning Hyperparameters with Bayesian Optimization to further enhance the performance.When comparing our model to other deep learning(DL)models such as VGG19,MobileNetv2,ResNet50,InceptionV3,and DenseNet201,aswell as variants of the EfficientNetmodel(B1–B7),the results showthat our proposedmodel outperforms all othermodels.Our investigational results demonstrate superiority in terms of precision,recall/sensitivity,accuracy,specificity,and F1-score.Such innovations can potentially enhance clinical decision-making and patient treatment in neurooncological settings.展开更多
Machine learning(ML)has strong potential for soil settlement prediction,but determining hyperparameters for ML models is often intricate and laborious.Therefore,we apply Bayesian optimization to determine the optimal ...Machine learning(ML)has strong potential for soil settlement prediction,but determining hyperparameters for ML models is often intricate and laborious.Therefore,we apply Bayesian optimization to determine the optimal hyperparameter combinations,enhancing the effectiveness of ML models for soil parameter inversion.The ML models are trained using numerical simulation data generated with the modified Cam-Clay(MCC)model in ABAQUS software,and their performance is evaluated using ground settlement monitoring data from an airport runway.Five optimized ML models—decision tree(DT),random forest(RF),support vector regression(SVR),deep neural network(DNN),and one-dimensional convolutional neural network(1D-CNN)—are compared in terms of their accuracy for soil parameter inversion and settlement prediction.The results indicate that Bayesian optimization efficiently utilizes prior knowledge to identify the optimal hyperparameters,significantly improving model performance.Among the evaluated models,the 1D-CNN achieves the highest accuracy in soil parameter inversion,generating settlement predictions that closely match real monitoring data.These findings demonstrate the effectiveness of the proposed approach for soil parameter inversion and settlement prediction,and reveal how Bayesian optimization can refine the model selection process.展开更多
Designing compositions and processing of biodegradable magnesium(Mg)alloys to synergistically en-hance mechanical properties and corrosion resistance using conventional trial-and-error method is a challenging task.Thi...Designing compositions and processing of biodegradable magnesium(Mg)alloys to synergistically en-hance mechanical properties and corrosion resistance using conventional trial-and-error method is a challenging task.This study presents a Bayesian optimization(BO)-based multi-objective framework inte-grated with explainable machine learning(ML)to efficiently explore and optimize the high-dimensional design space of biodegradable Mg alloys.Using ultimate tensile strength(UTS),elongation(EL)and cor-rosion potential(E_(corr))as objective properties,the framework balances these conflicting objectives and identifies optimal solutions.A novel biodegradable Mg alloy(Mg-4.6Zn-0.3Y-0.2Mn-0.1Nd-0.1Gd,wt.%)was successfully designed,demonstrating a UTS of 320 MPa,EL of 22%and E_(corr) of−1.60 V(tested in 37℃ simulated body fluid).Compared to JDBM,the UTS has increased by 13 MPa,the EL has improved by 6.1%,and the E_(corr) has risen by 0.02 V.The experimental results presented close agreement with predicted values,validating the proposed framework.The Shapley Additive Explanation method was em-ployed to interpret the ML models,revealing extrusion temperature and Zn content as key parameters driving the optimization design.The strategy provided in this study is universal and offers a potential approach for addressing high-dimensional multi-objective optimization challenges in material develop-ment.展开更多
The application of Low Earth Orbit(LEO)satellite navigation can enhance geometric structure,increase observations and contribute to navigation and positioning.To improve the performance of the navigation constellation...The application of Low Earth Orbit(LEO)satellite navigation can enhance geometric structure,increase observations and contribute to navigation and positioning.To improve the performance of the navigation constellation in China,this study proposes an optimized method of LEO-enhanced navigation constellation for BDS based on Bayesian optimization algorithm.In this paper,four different optimal LEO constellation configurations are designed,and their enhancements to BDS3 navigation performance are analyzed,including Geometric Dilution of Precision(GDOP),the numbers of visible satellites,and the rapid convergence of precision point positioning(PPP).Additionally,the enhancement advantages in China compared to other regions are further discussed.The results demonstrate that regional enhanced constellations with 70,72,80,and 81 satellites at an altitude of 1000 km can significantly improve the navigation performance of the navigation constellation.Globally,the addition of optimized LEO constellations has reduced the hybrid constellation GDOP by 19.0%,18.3%,19.9%,and 20.3%.Similar results can be obtained using the genetic algorithm(GA),but the computational efficiency of Bayesian optimization algorithm is 53.9%higher than that of the genetic algorithm.The number of visible satellites of enhanced constellations in China has increased by more than four on average,which is better than that in other regions.In the PPP experiment,the convergence time of the stations in China and other regions is shortened by 83.0%and 76.2%,respectively,and the navigation performance of hybrid constellations in China is better.展开更多
In laser wakefield acceleration,injecting an external electron beam at a certain energy is a promising approach for achieving a high-quality electron beam with low energy spread and low emittance.In this paper,the pro...In laser wakefield acceleration,injecting an external electron beam at a certain energy is a promising approach for achieving a high-quality electron beam with low energy spread and low emittance.In this paper,the process of laser wakefield acceleration with an external injection at 10 pC has been studied in simulations.A Bayesian optimization method is used to optimize the key laser and plasma parameters so that the electron beam is accelerated to the expected energy with a small emittance and energy spread growth.The effect of the rising edge of the plasma on the transverse properties of the electron beam is simulated and optimized in order to ensure that the external electron beam is injected into the plasma without significant emittance growth.Finally,a high-quality electron beam with an energy of 1.5 GeV,a normalized transverse emittance of 0.5 mm·mrad and a relative energy spread of 0.5%at 10 pC is obtained.展开更多
Accurate assessment of undrained shear strength(USS)for soft sensitive clays is a great concern in geotechnical engineering practice.This study applies novel data-driven extreme gradient boosting(XGBoost)and random fo...Accurate assessment of undrained shear strength(USS)for soft sensitive clays is a great concern in geotechnical engineering practice.This study applies novel data-driven extreme gradient boosting(XGBoost)and random forest(RF)ensemble learning methods for capturing the relationships between the USS and various basic soil parameters.Based on the soil data sets from TC304 database,a general approach is developed to predict the USS of soft clays using the two machine learning methods above,where five feature variables including the preconsolidation stress(PS),vertical effective stress(VES),liquid limit(LL),plastic limit(PL)and natural water content(W)are adopted.To reduce the dependence on the rule of thumb and inefficient brute-force search,the Bayesian optimization method is applied to determine the appropriate model hyper-parameters of both XGBoost and RF.The developed models are comprehensively compared with three comparison machine learning methods and two transformation models with respect to predictive accuracy and robustness under 5-fold cross-validation(CV).It is shown that XGBoost-based and RF-based methods outperform these approaches.Besides,the XGBoostbased model provides feature importance ranks,which makes it a promising tool in the prediction of geotechnical parameters and enhances the interpretability of model.展开更多
It is difficult to rapidly design the process parameters of copper alloys by using the traditional trial-and-error method and simultaneously improve the conflicting mechanical and electrical properties.The purpose of ...It is difficult to rapidly design the process parameters of copper alloys by using the traditional trial-and-error method and simultaneously improve the conflicting mechanical and electrical properties.The purpose of this work is to develop a new type of Cu-Ni-Co-Si alloy saving scarce and expensive Co element,in which the Co content is less than half of the lower limit in ASTM standard C70350 alloy,while the properties are as the same level as C70350 alloy.Here we adopted a strategy combining Bayesian optimization machine learning and experimental iteration and quickly designed the secondary deformation-aging parameters(cold rolling deformation 90%,aging temperature 450℃,and aging time 1.25 h)of the new copper alloy with only 32 experiments(27 basic sample data acquisition experiments and 5 iteration experiments),which broke through the barrier of low efficiency and high cost of trial-and-error design of deformation-aging parameters in precipitation strengthened copper alloy.The experimental hardness,tensile strength,and electrical conductivity of the new copper alloy are HV(285±4),(872±3)MPa,and(44.2±0.7)%IACS(international annealed copper standard),reaching the property level of the commercial lead frame C70350 alloy.This work provides a new idea for the rapid design of material process parameters and the simultaneous improvement of mechanical and electrical properties.展开更多
Target distribution in cooperative combat is a difficult and emphases. We build up the optimization model according to the rule of fire distribution. We have researched on the optimization model with BOA. The BOA can ...Target distribution in cooperative combat is a difficult and emphases. We build up the optimization model according to the rule of fire distribution. We have researched on the optimization model with BOA. The BOA can estimate the joint probability distribution of the variables with Bayesian network, and the new candidate solutions also can be generated by the joint distribution. The simulation example verified that the method could be used to solve the complex question, the operation was quickly and the solution was best.展开更多
To maximize the maintenance willingness of the owner of transmission lines,this study presents a transmission maintenance scheduling model that considers the energy constraints of the power system and the security con...To maximize the maintenance willingness of the owner of transmission lines,this study presents a transmission maintenance scheduling model that considers the energy constraints of the power system and the security constraints of on-site maintenance operations.Considering the computational complexity of the mixed integer programming(MIP)problem,a machine learning(ML)approach is presented to solve the transmission maintenance scheduling model efficiently.The value of the branching score factor value is optimized by Bayesian optimization(BO)in the proposed algorithm,which plays an important role in the size of the branch-and-bound search tree in the solution process.The test case in a modified version of the IEEE 30-bus system shows that the proposed algorithm can not only reach the optimal solution but also improve the computational efficiency.展开更多
Magnesium(Mg),being the lightest structural metal,holds immense potential for widespread applications in various fields.The development of high-performance and cost-effective Mg alloys is crucial to further advancing ...Magnesium(Mg),being the lightest structural metal,holds immense potential for widespread applications in various fields.The development of high-performance and cost-effective Mg alloys is crucial to further advancing their commercial utilization.With the rapid advancement of machine learning(ML)technology in recent years,the“data-driven''approach for alloy design has provided new perspectives and opportunities for enhancing the performance of Mg alloys.This paper introduces a novel regression-based Bayesian optimization active learning model(RBOALM)for the development of high-performance Mg-Mn-based wrought alloys.RBOALM employs active learning to automatically explore optimal alloy compositions and process parameters within predefined ranges,facilitating the discovery of superior alloy combinations.This model further integrates pre-established regression models as surrogate functions in Bayesian optimization,significantly enhancing the precision of the design process.Leveraging RBOALM,several new high-performance alloys have been successfully designed and prepared.Notably,after mechanical property testing of the designed alloys,the Mg-2.1Zn-2.0Mn-0.5Sn-0.1Ca alloy demonstrates exceptional mechanical properties,including an ultimate tensile strength of 406 MPa,a yield strength of 287 MPa,and a 23%fracture elongation.Furthermore,the Mg-2.7Mn-0.5Al-0.1Ca alloy exhibits an ultimate tensile strength of 211 MPa,coupled with a remarkable 41%fracture elongation.展开更多
Many scholars have focused on applying machine learning models in bottom hole pressure (BHP) prediction. However, the complex and uncertain conditions in deep wells make it difficult to capture spatial and temporal co...Many scholars have focused on applying machine learning models in bottom hole pressure (BHP) prediction. However, the complex and uncertain conditions in deep wells make it difficult to capture spatial and temporal correlations of measurement while drilling (MWD) data with traditional intelligent models. In this work, we develop a novel hybrid neural network, which integrates the Convolution Neural Network (CNN) and the Gate Recurrent Unit (GRU) for predicting BHP fluctuations more accurately. The CNN structure is used to analyze spatial local dependency patterns and the GRU structure is used to discover depth variation trends of MWD data. To further improve the prediction accuracy, we explore two types of GRU-based structure: skip-GRU and attention-GRU, which can capture more long-term potential periodic correlation in drilling data. Then, the different model structures tuned by the Bayesian optimization (BO) algorithm are compared and analyzed. Results indicate that the hybrid models can extract spatial-temporal information of data effectively and predict more accurately than random forests, extreme gradient boosting, back propagation neural network, CNN and GRU. The CNN-attention-GRU model with BO algorithm shows great superiority in prediction accuracy and robustness due to the hybrid network structure and attention mechanism, having the lowest mean absolute percentage error of 0.025%. This study provides a reference for solving the problem of extracting spatial and temporal characteristics and guidance for managed pressure drilling in complex formations.展开更多
In order to adapt to the changing battlefield situation and improve the combat effectiveness of air combat,the problem of air battle allocation based on Bayesian optimization algorithm(BOA)is studied.First,we discuss ...In order to adapt to the changing battlefield situation and improve the combat effectiveness of air combat,the problem of air battle allocation based on Bayesian optimization algorithm(BOA)is studied.First,we discuss the number of fighters on both sides,and apply cluster analysis to divide our fighter into the same number of groups as the enemy.On this basis,we sort each of our fighters'different advantages to the enemy fighters,and obtain a series of target allocation schemes for enemy attacks by first in first serviced criteria.Finally,the maximum advantage function is used as the target,and the BOA is used to optimize the model.The simulation results show that the established model has certain decision-making ability,and the BOA can converge to the global optimal solution at a faster speed,which can effectively solve the air combat task assignment problem.展开更多
A key question in flow control is that of the design of optimal controllers when the control space is high-dimensional and the experimental or computational budget is limited.We address this formidable challenge using...A key question in flow control is that of the design of optimal controllers when the control space is high-dimensional and the experimental or computational budget is limited.We address this formidable challenge using a particular flavor of machine learning and present the first application of Bayesian optimization to the design of open-loop controllers for fluid flows.We consider a range of acquisition functions,including the recently introduced output-informed criteria of Blanchard and Sapsis(2021),and evaluate performance of the Bayesian algorithm in two iconic configurations for active flow control:computationally,with drag reduction in the fluidic pinball;and experimentally,with mixing enhancement in a turbulent jet.For these flows,we find that Bayesian optimization identifies optimal controllers at a fraction of the cost of other optimization strategies considered in previous studies.Bayesian optimization also provides,as a by-product of the optimization,a surrogate model for the latent cost function,which can be leveraged to paint a complete picture of the control landscape.The proposed methodology can be used to design open-loop controllers for virtually any complex flow and,therefore,has significant implications for active flow control at an industrial scale.展开更多
We present a framework that couples a high-fidelity compositional reservoir simulator with Bayesian optimization(BO)for injection well scheduling optimization in geological carbon sequestration.This work represents on...We present a framework that couples a high-fidelity compositional reservoir simulator with Bayesian optimization(BO)for injection well scheduling optimization in geological carbon sequestration.This work represents one of the first at tempts to apply BO and high-fidelity physics models to geological carbon storage.The implicit parallel accurate reservoir simulator(IPARS)is utilized to accurately capture the underlying physical processes during CO_(2)sequestration.IPARS provides a framework for several flow and mechanics models and thus supports both stand-alone and coupled simulations.In this work,we use the compositional flow module to simulate the geological carbon storage process.The compositional flow model,which includes a hysteretic three-phase relative permeability model,accounts for three major CO_(2)trapping mechanisms:structural trapping,residual gas trapping,and solubility trapping.Furthermore,IPARS is coupled to the International Business Machines(IBM)Corporation Bayesian Optimization Accelerator(BOA)for parallel optimizations of CO_(2)injection strategies during field-scale CO_(2)sequestration.BO builds a probabilistic surrogate for the objective function using a Bayesian machine learning algorithm-the Gaussian process regression,and then uses an acquisition function that leverages the uncertainty in the surrogate to decide where to sample.The IBM BOA addresses the three weaknesses of standard BO that limits its scalability in that IBM BOA supports parallel(batch)executions,scales better for high-dimensional problems,and is more robust to initializations.We demonstrate these merits by applying the algorithm in the optimization of the CO_(2)injection schedule in the Cranfield site in Mississippi,USA,using field data.The optimized injection schedule achieves 16%more gas storage volume and 56%less water/surfactant usage compared with the baseline.The performance of BO is compared with that of a genetic algorithm(GA)and a covariance matrix adaptation(CMA)-evolution strategy(ES).The results demonstrate the superior performance of BO,in that it achieves a competitive objective function value with over 60%fewer forward model evaluations.展开更多
The optimization of process parameters in polyolefin production can bring significant economic benefits to the factory.However,due to small data sets,high costs associated with parameter verification cycles,and diffic...The optimization of process parameters in polyolefin production can bring significant economic benefits to the factory.However,due to small data sets,high costs associated with parameter verification cycles,and difficulty in establishing an optimization model,the optimization process is often restricted.To address this issue,we propose using a transfer learning Bayesian optimization strategy to improve the efficiency of parameter optimization while minimizing resource consumption.Specifically,we leverage Gaussian process(GP)regression models to establish an integrated model that incorporates both source and target grade production task data.We then measure the similarity weights of each model by comparing their predicted trends,and utilize these weights to accelerate the solution of optimal process parameters for producing target polyolefin grades.In order to enhance the accuracy of our approach,we acknowledge that measuring similarity in a global search space may not effectively capture local similarity characteristics.Therefore,we propose a novel method for transfer learning optimization that operates within a local space(LSTL-PBO).This method employs partial data acquired through random sampling from the target task data and utilizes Bayesian optimization techniques for model establishment.By focusing on a local search space,we aim to better discern and leverage the inherent similarities between source tasks and the target task.Additionally,we incorporate a parallel concept into our method to address multiple local search spaces simultaneously.By doing so,we can explore different regions of the parameter space in parallel,thereby increasing the chances of finding optimal process parameters.This localized approach allows us to improve the precision and effectiveness of our optimization process.The performance of our method is validated through experiments on benchmark problems,and we discuss the sensitivity of its hyperparameters.The results show that our proposed method can significantly improve the efficiency of process parameter optimization,reduce the dependence on source tasks,and enhance the method's robustness.This has great potential for optimizing processes in industrial environments.展开更多
基金support from National Key Research and Development Program of China(2023YFC3905400)the Strategic Priority Research Program of the Chinese Academy of Sciences(XDA0490102)National Natural Science Foundation of China(22178354,2242100322408374).
文摘Integrating Bayesian Optimization with Volume of Fluid (VOF) simulations, this work aims to optimize the operational conditions and geometric parameters of T-junction microchannels for target droplet sizes. Bayesian Optimization utilizes Gaussian Process (GP) as its core model and employs an adaptive search strategy to efficiently explore and identify optimal combinations of operational parameters within a limited parameter space, thereby enabling rapid optimization of the required parameters to achieve the target droplet size. Traditional methods typically rely on manually selecting a series of operational parameters and conducting multiple simulations to gradually approach the target droplet size. This process is time-consuming and prone to getting trapped in local optima. In contrast, Bayesian Optimization adaptively adjusts its search strategy, significantly reducing computational costs and effectively exploring global optima, thus greatly improving optimization efficiency. Additionally, the study investigates the impact of rectangular rib structures within the T-junction microchannel on droplet generation, revealing how the channel geometry influences droplet formation and size. After determining the target droplet size, we further applied Bayesian Optimization to refine the rib geometry. The integration of Bayesian Optimization with computational fluid dynamics (CFD) offers a promising tool and provides new insights into the optimal design of microfluidic devices.
基金supported by the National Natural Science Foundation of China(Grant No.72401011).
文摘With the European Union(EU)introducing the Carbon Border Adjustment Mechanism(CBAM),accurately forecasting EU carbon price is crucial for exporters to estimate export costs,plan low-carbon strategies,and mitigate trade risks.In the petroleum sector,carbon pricing directly influences upstream investment returns and carbon intensity targets,thereby closely linking emissions markets with fossil energy strategies.Existing models often fail to fully capture the nonlinear,non-stationary nature of carbon prices and their dependence on external factors.This study proposes a novel hybrid framework that combines improved complete ensemble empirical mode decomposition with adaptive noise(ICEEMDAN)with gated recurrent unit-convolutional neural network-long short-term memory network-Bayesian optimization(GRU-CNN-LSTM-BO).Empirical results based on the EU emissions trading system(ETS)market demonstrate that the proposed model significantly improves forecasting accuracy.Among all experiments,the proposed GRU-CNN-LSTM-BO framework achieves the best performance,yielding the lowest MAE(1.3872),RMSE(1.7038),MAPE(0.0166),and MSPE(0.0004),as well as the highest R2(0.9400).Compared to all benchmark models,the GRU-CNN-LSTM-BO model achieves reductions in MAE and RMSE ranging from 5.38%to 63.65%and 8.97%to 64.41%,respectively.To further validate the generalization ability and predictive performance of the proposed model,it is also applied to China's ETS.The results show that the GRU-CNN-LSTM-BO model also performs very well in China's ETS.
基金supported by the National Natural Science Foundation of China (Grant Nos.12102021,12372105,12172026,and 12225201)the Fundamental Research Funds for the Central Universities and the Academic Excellence Foundation of BUAA for PhD Students.
文摘Advanced programmable metamaterials with heterogeneous microstructures have become increasingly prevalent in scientific and engineering disciplines attributed to their tunable properties.However,exploring the structure-property relationship in these materials,including forward prediction and inverse design,presents substantial challenges.The inhomogeneous microstructures significantly complicate traditional analytical or simulation-based approaches.Here,we establish a novel framework that integrates the machine learning(ML)-encoded multiscale computational method for forward prediction and Bayesian optimization for inverse design.Unlike prior end-to-end ML methods limited to specific problems,our framework is both load-independent and geometry-independent.This means that a single training session for a constitutive model suffices to tackle various problems directly,eliminating the need for repeated data collection or training.We demonstrate the efficacy and efficiency of this framework using metamaterials with designable elliptical holes or lattice honeycombs microstructures.Leveraging accelerated forward prediction,we can precisely customize the stiffness and shape of metamaterials under diverse loading scenarios,and extend this capability to multi-objective customization seamlessly.Moreover,we achieve topology optimization for stress alleviation at the crack tip,resulting in a significant reduction of Mises stress by up to 41.2%and yielding a theoretical interpretable pattern.This framework offers a general,efficient and precise tool for analyzing the structure-property relationships of novel metamaterials.
基金funded by the National Key R&D Program of China,Grant No.2024YFF0504904.
文摘The packaging quality of coaxial laser diodes(CLDs)plays a pivotal role in determining their optical performance and long-term reliability.As the core packaging process,high-precision laser welding requires precise control of process parameters to suppress optical power loss.However,the complex nonlinear relationship between welding parameters and optical power loss renders traditional trial-and-error methods inefficient and imprecise.To address this challenge,a physics-informed(PI)and data-driven collaboration approach for welding parameter optimization is proposed.First,thermal-fluid-solid coupling finite element method(FEM)was employed to quantify the sensitivity of welding parameters to physical characteristics,including residual stress.This analysis facilitated the identification of critical factors contributing to optical power loss.Subsequently,a Gaussian process regression(GPR)model incorporating finite element simulation prior knowledge was constructed based on the selected features.By introducing physics-informed kernel(PIK)functions,stress distribution patterns were embedded into the prediction model,achieving high-precision optical power loss prediction.Finally,a Bayesian optimization(BO)algorithm with an adaptive sampling strategy was implemented for efficient parameter space exploration.Experimental results demonstrate that the proposedmethod effectively establishes explicit physical correlations between welding parameters and optical power loss.The optimized welding parameters reduced optical power loss by 34.1%,providing theoretical guidance and technical support for reliable CLD packaging.
文摘Miniature air quality sensors are widely used in urban grid-based monitoring due to their flexibility in deployment and low cost.However,the raw data collected by these devices often suffer from low accuracy caused by environmental interference and sensor drift,highlighting the need for effective calibration methods to improve data reliability.This study proposes a data correction method based on Bayesian Optimization Support Vector Regression(BO-SVR),which combines the nonlinear modeling capability of Support Vector Regression(SVR)with the efficient global hyperparameter search of Bayesian Optimization.By introducing cross-validation loss as the optimization objective and using Gaussian process modeling with an Expected Improvement acquisition strategy,the approach automatically determines optimal hyperparameters for accurate pollutant concentration prediction.Experiments on real-world micro-sensor datasets demonstrate that BO-SVR outperforms traditional SVR,grid search SVR,and random forest(RF)models across multiple pollutants,including PM_(2.5),PM_(10),CO,NO_(2),SO_(2),and O_(3).The proposed method achieves lower prediction residuals,higher fitting accuracy,and better generalization,offering an efficient and practical solution for enhancing the quality of micro-sensor air monitoring data.
基金funded by the King Saud University,Riyadh,Saudi Arabia,for funding this work through the Researchers Supporting Research Funding program,(ORF-2025-1268).
文摘A brain tumor is a disease in which abnormal cells form a tumor in the brain.They are rare and can take many forms,making them difficult to treat,and the survival rate of affected patients is low.Magnetic resonance imaging(MRI)is a crucial tool for diagnosing and localizing brain tumors.However,themanual interpretation of MRI images is tedious and prone to error.As artificial intelligence advances rapidly,DL techniques are increasingly used in medical imaging to accurately detect and diagnose brain tumors.In this study,we introduce a deep convolutional neural network(DCNN)framework for brain tumor classification that uses EfficientNet-B6 as the backbone architecture and adds additional layers.The model achieved an accuracy of 99.10%on the public Brain Tumor MRI datasets,and we performed an ablation study to determine the optimal batch size,optimizer,loss function,and learning rate to maximize the accuracy and robustness of the model,followed by K-Fold cross-validation and testing the model on an independent dataset,and tuning Hyperparameters with Bayesian Optimization to further enhance the performance.When comparing our model to other deep learning(DL)models such as VGG19,MobileNetv2,ResNet50,InceptionV3,and DenseNet201,aswell as variants of the EfficientNetmodel(B1–B7),the results showthat our proposedmodel outperforms all othermodels.Our investigational results demonstrate superiority in terms of precision,recall/sensitivity,accuracy,specificity,and F1-score.Such innovations can potentially enhance clinical decision-making and patient treatment in neurooncological settings.
基金supported by the National Natural Science Foundation of China(Nos.52378419 and 52478368).
文摘Machine learning(ML)has strong potential for soil settlement prediction,but determining hyperparameters for ML models is often intricate and laborious.Therefore,we apply Bayesian optimization to determine the optimal hyperparameter combinations,enhancing the effectiveness of ML models for soil parameter inversion.The ML models are trained using numerical simulation data generated with the modified Cam-Clay(MCC)model in ABAQUS software,and their performance is evaluated using ground settlement monitoring data from an airport runway.Five optimized ML models—decision tree(DT),random forest(RF),support vector regression(SVR),deep neural network(DNN),and one-dimensional convolutional neural network(1D-CNN)—are compared in terms of their accuracy for soil parameter inversion and settlement prediction.The results indicate that Bayesian optimization efficiently utilizes prior knowledge to identify the optimal hyperparameters,significantly improving model performance.Among the evaluated models,the 1D-CNN achieves the highest accuracy in soil parameter inversion,generating settlement predictions that closely match real monitoring data.These findings demonstrate the effectiveness of the proposed approach for soil parameter inversion and settlement prediction,and reveal how Bayesian optimization can refine the model selection process.
基金financially supported by the National Natu-ral Science Foundation of China(No.52301133)the China Post-doctoral Science Foundation(No.2023M730276)+1 种基金the Young Elite Scientists Sponsorship Program by China Association for Science and Technology(No.YESS20210415)the Graduate Innovation Pro-gram of Chongqing University of Science and Technology(No.YKJCX2320218).
文摘Designing compositions and processing of biodegradable magnesium(Mg)alloys to synergistically en-hance mechanical properties and corrosion resistance using conventional trial-and-error method is a challenging task.This study presents a Bayesian optimization(BO)-based multi-objective framework inte-grated with explainable machine learning(ML)to efficiently explore and optimize the high-dimensional design space of biodegradable Mg alloys.Using ultimate tensile strength(UTS),elongation(EL)and cor-rosion potential(E_(corr))as objective properties,the framework balances these conflicting objectives and identifies optimal solutions.A novel biodegradable Mg alloy(Mg-4.6Zn-0.3Y-0.2Mn-0.1Nd-0.1Gd,wt.%)was successfully designed,demonstrating a UTS of 320 MPa,EL of 22%and E_(corr) of−1.60 V(tested in 37℃ simulated body fluid).Compared to JDBM,the UTS has increased by 13 MPa,the EL has improved by 6.1%,and the E_(corr) has risen by 0.02 V.The experimental results presented close agreement with predicted values,validating the proposed framework.The Shapley Additive Explanation method was em-ployed to interpret the ML models,revealing extrusion temperature and Zn content as key parameters driving the optimization design.The strategy provided in this study is universal and offers a potential approach for addressing high-dimensional multi-objective optimization challenges in material develop-ment.
基金founded by the National Natural Science Foundation of China(42030109)the Startup Foundation for Doctors of Liaoning Province(2021-BS-275)+4 种基金the Scientific Study Project for Institutes of Higher LearningMinistry of EducationLiaoning Province(LJKMZ20220673)the Project supported by the State Key Laboratory of Geodesy and Earths'DynamicsInnovation Academy for Precision Measurement Science and Technology(SKLGED2023-3-2)。
文摘The application of Low Earth Orbit(LEO)satellite navigation can enhance geometric structure,increase observations and contribute to navigation and positioning.To improve the performance of the navigation constellation in China,this study proposes an optimized method of LEO-enhanced navigation constellation for BDS based on Bayesian optimization algorithm.In this paper,four different optimal LEO constellation configurations are designed,and their enhancements to BDS3 navigation performance are analyzed,including Geometric Dilution of Precision(GDOP),the numbers of visible satellites,and the rapid convergence of precision point positioning(PPP).Additionally,the enhancement advantages in China compared to other regions are further discussed.The results demonstrate that regional enhanced constellations with 70,72,80,and 81 satellites at an altitude of 1000 km can significantly improve the navigation performance of the navigation constellation.Globally,the addition of optimized LEO constellations has reduced the hybrid constellation GDOP by 19.0%,18.3%,19.9%,and 20.3%.Similar results can be obtained using the genetic algorithm(GA),but the computational efficiency of Bayesian optimization algorithm is 53.9%higher than that of the genetic algorithm.The number of visible satellites of enhanced constellations in China has increased by more than four on average,which is better than that in other regions.In the PPP experiment,the convergence time of the stations in China and other regions is shortened by 83.0%and 76.2%,respectively,and the navigation performance of hybrid constellations in China is better.
基金supported by Science and Technology Major Project of Hubei Province in China(No.2021AFB001)。
文摘In laser wakefield acceleration,injecting an external electron beam at a certain energy is a promising approach for achieving a high-quality electron beam with low energy spread and low emittance.In this paper,the process of laser wakefield acceleration with an external injection at 10 pC has been studied in simulations.A Bayesian optimization method is used to optimize the key laser and plasma parameters so that the electron beam is accelerated to the expected energy with a small emittance and energy spread growth.The effect of the rising edge of the plasma on the transverse properties of the electron beam is simulated and optimized in order to ensure that the external electron beam is injected into the plasma without significant emittance growth.Finally,a high-quality electron beam with an energy of 1.5 GeV,a normalized transverse emittance of 0.5 mm·mrad and a relative energy spread of 0.5%at 10 pC is obtained.
基金financial support from High-end Foreign Expert Introduction program(No.G20190022002)Chongqing Construction Science and Technology Plan Project(2019-0045)as well as Chongqing Engineering Research Center of Disaster Prevention&Control for Banks and Structures in Three Gorges Reservoir Area(Nos.SXAPGC18ZD01 and SXAPGC18YB03)。
文摘Accurate assessment of undrained shear strength(USS)for soft sensitive clays is a great concern in geotechnical engineering practice.This study applies novel data-driven extreme gradient boosting(XGBoost)and random forest(RF)ensemble learning methods for capturing the relationships between the USS and various basic soil parameters.Based on the soil data sets from TC304 database,a general approach is developed to predict the USS of soft clays using the two machine learning methods above,where five feature variables including the preconsolidation stress(PS),vertical effective stress(VES),liquid limit(LL),plastic limit(PL)and natural water content(W)are adopted.To reduce the dependence on the rule of thumb and inefficient brute-force search,the Bayesian optimization method is applied to determine the appropriate model hyper-parameters of both XGBoost and RF.The developed models are comprehensively compared with three comparison machine learning methods and two transformation models with respect to predictive accuracy and robustness under 5-fold cross-validation(CV).It is shown that XGBoost-based and RF-based methods outperform these approaches.Besides,the XGBoostbased model provides feature importance ranks,which makes it a promising tool in the prediction of geotechnical parameters and enhances the interpretability of model.
基金supported by the National Key Research and Development Program of China(No.2021YFB 3803101)the National Natural Science Foundation of China(Nos.52090041,52022011,and 51974028)。
文摘It is difficult to rapidly design the process parameters of copper alloys by using the traditional trial-and-error method and simultaneously improve the conflicting mechanical and electrical properties.The purpose of this work is to develop a new type of Cu-Ni-Co-Si alloy saving scarce and expensive Co element,in which the Co content is less than half of the lower limit in ASTM standard C70350 alloy,while the properties are as the same level as C70350 alloy.Here we adopted a strategy combining Bayesian optimization machine learning and experimental iteration and quickly designed the secondary deformation-aging parameters(cold rolling deformation 90%,aging temperature 450℃,and aging time 1.25 h)of the new copper alloy with only 32 experiments(27 basic sample data acquisition experiments and 5 iteration experiments),which broke through the barrier of low efficiency and high cost of trial-and-error design of deformation-aging parameters in precipitation strengthened copper alloy.The experimental hardness,tensile strength,and electrical conductivity of the new copper alloy are HV(285±4),(872±3)MPa,and(44.2±0.7)%IACS(international annealed copper standard),reaching the property level of the commercial lead frame C70350 alloy.This work provides a new idea for the rapid design of material process parameters and the simultaneous improvement of mechanical and electrical properties.
基金This project was supported by the Fund of College Doctor Degree (20020699009)
文摘Target distribution in cooperative combat is a difficult and emphases. We build up the optimization model according to the rule of fire distribution. We have researched on the optimization model with BOA. The BOA can estimate the joint probability distribution of the variables with Bayesian network, and the new candidate solutions also can be generated by the joint distribution. The simulation example verified that the method could be used to solve the complex question, the operation was quickly and the solution was best.
基金supported by the National Key Research and Development Program of China(Basic Research Class)(No.2017YFB0903000)the National Natural Science Foundation of China(No.U1909201).
文摘To maximize the maintenance willingness of the owner of transmission lines,this study presents a transmission maintenance scheduling model that considers the energy constraints of the power system and the security constraints of on-site maintenance operations.Considering the computational complexity of the mixed integer programming(MIP)problem,a machine learning(ML)approach is presented to solve the transmission maintenance scheduling model efficiently.The value of the branching score factor value is optimized by Bayesian optimization(BO)in the proposed algorithm,which plays an important role in the size of the branch-and-bound search tree in the solution process.The test case in a modified version of the IEEE 30-bus system shows that the proposed algorithm can not only reach the optimal solution but also improve the computational efficiency.
基金supported by the National Natural the Science Foundation of China(51971042,51901028)the Chongqing Academician Special Fund(cstc2020yszxjcyj X0001)+1 种基金the China Scholarship Council(CSC)Norwegian University of Science and Technology(NTNU)for their financial and technical support。
文摘Magnesium(Mg),being the lightest structural metal,holds immense potential for widespread applications in various fields.The development of high-performance and cost-effective Mg alloys is crucial to further advancing their commercial utilization.With the rapid advancement of machine learning(ML)technology in recent years,the“data-driven''approach for alloy design has provided new perspectives and opportunities for enhancing the performance of Mg alloys.This paper introduces a novel regression-based Bayesian optimization active learning model(RBOALM)for the development of high-performance Mg-Mn-based wrought alloys.RBOALM employs active learning to automatically explore optimal alloy compositions and process parameters within predefined ranges,facilitating the discovery of superior alloy combinations.This model further integrates pre-established regression models as surrogate functions in Bayesian optimization,significantly enhancing the precision of the design process.Leveraging RBOALM,several new high-performance alloys have been successfully designed and prepared.Notably,after mechanical property testing of the designed alloys,the Mg-2.1Zn-2.0Mn-0.5Sn-0.1Ca alloy demonstrates exceptional mechanical properties,including an ultimate tensile strength of 406 MPa,a yield strength of 287 MPa,and a 23%fracture elongation.Furthermore,the Mg-2.7Mn-0.5Al-0.1Ca alloy exhibits an ultimate tensile strength of 211 MPa,coupled with a remarkable 41%fracture elongation.
基金The authors express their appreciation to National Key Research and Development Project“Key Scientific Issues of Revolutionary Technology”(2019YFA0708300)Strategic Cooperation Technology Projects of CNPC and CUPB(ZLZX2020-03)+1 种基金Distinguished Young Foundation of National Natural Science Foundation of China(52125401)Science Foundation of China University of Petroleum,Beijing(2462022SZBH002).
文摘Many scholars have focused on applying machine learning models in bottom hole pressure (BHP) prediction. However, the complex and uncertain conditions in deep wells make it difficult to capture spatial and temporal correlations of measurement while drilling (MWD) data with traditional intelligent models. In this work, we develop a novel hybrid neural network, which integrates the Convolution Neural Network (CNN) and the Gate Recurrent Unit (GRU) for predicting BHP fluctuations more accurately. The CNN structure is used to analyze spatial local dependency patterns and the GRU structure is used to discover depth variation trends of MWD data. To further improve the prediction accuracy, we explore two types of GRU-based structure: skip-GRU and attention-GRU, which can capture more long-term potential periodic correlation in drilling data. Then, the different model structures tuned by the Bayesian optimization (BO) algorithm are compared and analyzed. Results indicate that the hybrid models can extract spatial-temporal information of data effectively and predict more accurately than random forests, extreme gradient boosting, back propagation neural network, CNN and GRU. The CNN-attention-GRU model with BO algorithm shows great superiority in prediction accuracy and robustness due to the hybrid network structure and attention mechanism, having the lowest mean absolute percentage error of 0.025%. This study provides a reference for solving the problem of extracting spatial and temporal characteristics and guidance for managed pressure drilling in complex formations.
基金the National Natural Science Foundation of China(No.61074090)。
文摘In order to adapt to the changing battlefield situation and improve the combat effectiveness of air combat,the problem of air battle allocation based on Bayesian optimization algorithm(BOA)is studied.First,we discuss the number of fighters on both sides,and apply cluster analysis to divide our fighter into the same number of groups as the enemy.On this basis,we sort each of our fighters'different advantages to the enemy fighters,and obtain a series of target allocation schemes for enemy attacks by first in first serviced criteria.Finally,the maximum advantage function is used as the target,and the BOA is used to optimize the model.The simulation results show that the established model has certain decision-making ability,and the BOA can converge to the global optimal solution at a faster speed,which can effectively solve the air combat task assignment problem.
文摘A key question in flow control is that of the design of optimal controllers when the control space is high-dimensional and the experimental or computational budget is limited.We address this formidable challenge using a particular flavor of machine learning and present the first application of Bayesian optimization to the design of open-loop controllers for fluid flows.We consider a range of acquisition functions,including the recently introduced output-informed criteria of Blanchard and Sapsis(2021),and evaluate performance of the Bayesian algorithm in two iconic configurations for active flow control:computationally,with drag reduction in the fluidic pinball;and experimentally,with mixing enhancement in a turbulent jet.For these flows,we find that Bayesian optimization identifies optimal controllers at a fraction of the cost of other optimization strategies considered in previous studies.Bayesian optimization also provides,as a by-product of the optimization,a surrogate model for the latent cost function,which can be leveraged to paint a complete picture of the control landscape.The proposed methodology can be used to design open-loop controllers for virtually any complex flow and,therefore,has significant implications for active flow control at an industrial scale.
基金supported under the Center for Subsurface Modeling Affiliates Program,United States of America and the National Science Foundation,United States of America(1911320,Collaborative Research:High-Fidelity Modeling of Poromechanics with Strong Discontinuities)。
文摘We present a framework that couples a high-fidelity compositional reservoir simulator with Bayesian optimization(BO)for injection well scheduling optimization in geological carbon sequestration.This work represents one of the first at tempts to apply BO and high-fidelity physics models to geological carbon storage.The implicit parallel accurate reservoir simulator(IPARS)is utilized to accurately capture the underlying physical processes during CO_(2)sequestration.IPARS provides a framework for several flow and mechanics models and thus supports both stand-alone and coupled simulations.In this work,we use the compositional flow module to simulate the geological carbon storage process.The compositional flow model,which includes a hysteretic three-phase relative permeability model,accounts for three major CO_(2)trapping mechanisms:structural trapping,residual gas trapping,and solubility trapping.Furthermore,IPARS is coupled to the International Business Machines(IBM)Corporation Bayesian Optimization Accelerator(BOA)for parallel optimizations of CO_(2)injection strategies during field-scale CO_(2)sequestration.BO builds a probabilistic surrogate for the objective function using a Bayesian machine learning algorithm-the Gaussian process regression,and then uses an acquisition function that leverages the uncertainty in the surrogate to decide where to sample.The IBM BOA addresses the three weaknesses of standard BO that limits its scalability in that IBM BOA supports parallel(batch)executions,scales better for high-dimensional problems,and is more robust to initializations.We demonstrate these merits by applying the algorithm in the optimization of the CO_(2)injection schedule in the Cranfield site in Mississippi,USA,using field data.The optimized injection schedule achieves 16%more gas storage volume and 56%less water/surfactant usage compared with the baseline.The performance of BO is compared with that of a genetic algorithm(GA)and a covariance matrix adaptation(CMA)-evolution strategy(ES).The results demonstrate the superior performance of BO,in that it achieves a competitive objective function value with over 60%fewer forward model evaluations.
基金supported by National Natural Science Foundation of China(62394343)Major Program of Qingyuan Innovation Laboratory(00122002)+1 种基金Major Science and Technology Projects of Longmen Laboratory(231100220600)Shanghai Committee of Science and Technology(23ZR1416000)and Shanghai AI Lab.
文摘The optimization of process parameters in polyolefin production can bring significant economic benefits to the factory.However,due to small data sets,high costs associated with parameter verification cycles,and difficulty in establishing an optimization model,the optimization process is often restricted.To address this issue,we propose using a transfer learning Bayesian optimization strategy to improve the efficiency of parameter optimization while minimizing resource consumption.Specifically,we leverage Gaussian process(GP)regression models to establish an integrated model that incorporates both source and target grade production task data.We then measure the similarity weights of each model by comparing their predicted trends,and utilize these weights to accelerate the solution of optimal process parameters for producing target polyolefin grades.In order to enhance the accuracy of our approach,we acknowledge that measuring similarity in a global search space may not effectively capture local similarity characteristics.Therefore,we propose a novel method for transfer learning optimization that operates within a local space(LSTL-PBO).This method employs partial data acquired through random sampling from the target task data and utilizes Bayesian optimization techniques for model establishment.By focusing on a local search space,we aim to better discern and leverage the inherent similarities between source tasks and the target task.Additionally,we incorporate a parallel concept into our method to address multiple local search spaces simultaneously.By doing so,we can explore different regions of the parameter space in parallel,thereby increasing the chances of finding optimal process parameters.This localized approach allows us to improve the precision and effectiveness of our optimization process.The performance of our method is validated through experiments on benchmark problems,and we discuss the sensitivity of its hyperparameters.The results show that our proposed method can significantly improve the efficiency of process parameter optimization,reduce the dependence on source tasks,and enhance the method's robustness.This has great potential for optimizing processes in industrial environments.
