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
Global Navigation Satellite System(GNSS)imaging method(GIM)has been successfully applied to global regions to investigate vertical land motion(VLM)of the Earth's surface.GNSS images derived from conventional GIM m...Global Navigation Satellite System(GNSS)imaging method(GIM)has been successfully applied to global regions to investigate vertical land motion(VLM)of the Earth's surface.GNSS images derived from conventional GIM method may present fragmented patches and encounter problems caused by excessive smoothing of velocity peaks,leading to difficulty in short-wavelength deformation detection and improper geophysical interpretation.Therefore,we propose a novel GNSS imaging method based on Gaussian process regression with velocity uncertainty considered(GPR-VU).Gaussian processing regression is introduced to describe the spatial relationship between neighboring site pairs as a priori weights and then reweight velocities by known station uncertainties,converting the discrete velocity field to a continuous one.The GPR-VU method is applied to reconstruct VLM images in the southwestern United States and the eastern Qinghai-Xizang Plateau,China,using the GNSS position time series in vertical direction.Compared to the traditional GIM method,the root-mean-square(RMS)and overall accuracy of the confusion matrix of the GPR-VU method increase by 5.0%and 14.0%from the 1°×1°checkerboard test in the southwestern United States.Similarly,the RMS and overall accuracy increase by 33.7%and 15.8%from the 6°×6°checkerboard test in the eastern Qinghai-Xizang Plateau.These checkerboard tests validate the capability to effectively capture the spatiotemporal variations characteristics of VLM and show that this algorithm outperforms the sparsely distributed network in the Qinghai-Xizang Plateau.The images from the GPR-VU method using real data in both regions show significant subsidence around Lassen Volcanic in northern California within a 30 km radius,slight uplift in the northern Sichuan Basin,and subsidence in its central and southern sections.These results further qualitatively illustrate consistency with previous findings.The GPR-VU method outperforms in diminishing the effect by fragmented patches,excessive smoothing of velocity peaks,and detecting potential short-wavelength deformations.展开更多
The performance of lithium-ion batteries(LIBs)gradually declines over time,making it critical to predict the battery’s state of health(SOH)in real-time.This paper presents a model that incorporates health indicators ...The performance of lithium-ion batteries(LIBs)gradually declines over time,making it critical to predict the battery’s state of health(SOH)in real-time.This paper presents a model that incorporates health indicators and ensemble Gaussian process regression(EGPR)to predict the SOH of LIBs.Firstly,the degradation process of an LIB is analyzed through indirect health indicators(HIs)derived from voltage and temperature during discharge.Next,the parameters in the EGPR model are optimized using the gannet optimization algorithm(GOA),and the EGPR is employed to estimate the SOH of LIBs.Finally,the proposed model is tested under various experimental scenarios and compared with other machine learning models.The effectiveness of EGPR model is demonstrated using the National Aeronautics and Space Administration(NASA)LIB.The root mean square error(RMSE)is maintained within 0.20%,and the mean absolute error(MAE)is below 0.16%,illustrating the proposed approach’s excellent predictive accuracy and wide applicability.展开更多
The metastable retained austenite(RA)plays a significant role in the excellent mechanical performance of quenching and partitioning(Q&P)steels,while the volume fraction of RA(V_(RA))is challengeable to directly pr...The metastable retained austenite(RA)plays a significant role in the excellent mechanical performance of quenching and partitioning(Q&P)steels,while the volume fraction of RA(V_(RA))is challengeable to directly predict due to the complicated relationships between the chemical composition and process(like quenching temperature(Qr)).A Gaussian process regression model in machine learning was developed to predict V_(RA),and the model accuracy was further improved by introducing a metallurgical parameter of martensite fraction(fo)to accurately predict V_(RA) in Q&P steels.The developed machine learning model combined with Bayesian global optimization can serve as another selection strategy for the quenching temperature,and this strategy is very effcient as it found the"optimum"Qr with the maximum V_(RA) using only seven consecutive iterations.The benchmark experiment also reveals that the developed machine learning model predicts V_(RA) more accurately than the popular constrained carbon equilibrium thermodynamic model,even better than a thermo-kinetic quenching-partitioning-tempering-local equilibrium model.展开更多
Concentrate copper grade(CCG)is one of the important production indicators of copper flotation processes,and keeping the CCG at the set value is of great significance to the economic benefit of copper flotation indust...Concentrate copper grade(CCG)is one of the important production indicators of copper flotation processes,and keeping the CCG at the set value is of great significance to the economic benefit of copper flotation industrial processes.This paper addresses the fluctuation problem of CCG through an operational optimization method.Firstly,a density-based affinity propagationalgorithm is proposed so that more ideal working condition categories can be obtained for the complex raw ore properties.Next,a Bayesian network(BN)is applied to explore the relationship between the operational variables and the CCG.Based on the analysis results of BN,a weighted Gaussian process regression model is constructed to predict the CCG that a higher prediction accuracy can be obtained.To ensure the predicted CCG is close to the set value with a smaller magnitude of the operation adjustments and a smaller uncertainty of the prediction results,an index-oriented adaptive differential evolution(IOADE)algorithm is proposed,and the convergence performance of IOADE is superior to the traditional differential evolution and adaptive differential evolution methods.Finally,the effectiveness and feasibility of the proposed methods are verified by the experiments on a copper flotation industrial process.展开更多
The noise that comes from finite element simulation often causes the model to fall into the local optimal solution and over fitting during optimization of generator.Thus,this paper proposes a Gaussian Process Regressi...The noise that comes from finite element simulation often causes the model to fall into the local optimal solution and over fitting during optimization of generator.Thus,this paper proposes a Gaussian Process Regression(GPR)model based on Conditional Likelihood Lower Bound Search(CLLBS)to optimize the design of the generator,which can filter the noise in the data and search for global optimization by combining the Conditional Likelihood Lower Bound Search method.Taking the efficiency optimization of 15 kW Permanent Magnet Synchronous Motor as an example.Firstly,this method uses the elementary effect analysis to choose the sensitive variables,combining the evolutionary algorithm to design the super Latin cube sampling plan;Then the generator-converter system is simulated by establishing a co-simulation platform to obtain data.A Gaussian process regression model combing the method of the conditional likelihood lower bound search is established,which combined the chi-square test to optimize the accuracy of the model globally.Secondly,after the model reaches the accuracy,the Pareto frontier is obtained through the NSGA-II algorithm by considering the maximum output torque as a constraint.Last,the constrained optimization is transformed into an unconstrained optimizing problem by introducing maximum constrained improvement expectation(CEI)optimization method based on the re-interpolation model,which cross-validated the optimization results of the Gaussian process regression model.The above method increase the efficiency of generator by 0.76%and 0.5%respectively;And this method can be used for rapid modeling and multi-objective optimization of generator systems.展开更多
In engineering practice,it is often necessary to determine functional relationships between dependent and independent variables.These relationships can be highly nonlinear,and classical regression approaches cannot al...In engineering practice,it is often necessary to determine functional relationships between dependent and independent variables.These relationships can be highly nonlinear,and classical regression approaches cannot always provide sufficiently reliable solutions.Nevertheless,Machine Learning(ML)techniques,which offer advanced regression tools to address complicated engineering issues,have been developed and widely explored.This study investigates the selected ML techniques to evaluate their suitability for application in the hot deformation behavior of metallic materials.The ML-based regression methods of Artificial Neural Networks(ANNs),Support Vector Machine(SVM),Decision Tree Regression(DTR),and Gaussian Process Regression(GPR)are applied to mathematically describe hot flow stress curve datasets acquired experimentally for a medium-carbon steel.Although the GPR method has not been used for such a regression task before,the results showed that its performance is the most favorable and practically unrivaled;neither the ANN method nor the other studied ML techniques provide such precise results of the solved regression analysis.展开更多
The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR...The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR） approach is developed for the quality prediction of nonlinear and multiphase batch processes. After the collected data is preprocessed through batchwise unfolding, the hidden Markov model （HMM） is applied to identify different operation phases. A GLDA algorithm is also presented to extract the appropriate process variables highly correlated with the quality variables, decreasing the complexity of modeling. Besides, the multiple local GPR models are built in the reduced- dimensional space for all the identified operation phases. Furthermore, the HMM-based state estimation is used to classify each measurement sample of a test batch into a corresponding phase with the maximal likelihood estimation. Therefore, the local GPR model with respect to specific phase is selected for online prediction. The effectiveness of the proposed prediction approach is demonstrated through the multiphase penicillin fermentation process. The comparison results show that the proposed GLDA-GPR approach is superior to the regular GPR model and the GPR based on HMM （HMM-GPR） model.展开更多
Lithium-ion batteries(LIBs)have been widely used in mobile energy storage systems because of their high energy density,long life,and strong environmental adaptability.Accurately estimating the state of health(SOH)for ...Lithium-ion batteries(LIBs)have been widely used in mobile energy storage systems because of their high energy density,long life,and strong environmental adaptability.Accurately estimating the state of health(SOH)for LIBs is promising and has been extensively studied for many years.However,the current prediction methods are susceptible to noise interference,and the estimation accuracy has room for improvement.Motivated by this,this paper proposes a novel battery SOH estimation method,the Beluga Whale Optimization(BWO)and Noise-Input Gaussian Process(NIGP)Stacked Model(BGNSM).This method integrates the BWO-optimized Gaussian Process Regression(GPR)with the NIGP.It combines their predictions using a stacked GPR model which reduces the problem of large input data noise and improves the prediction accuracy.The experimental results show that the BGNSM method has good accuracy,generalization ability,and robustness,and performs well in small sample situations.The Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)are as low as 0.218%and 0.164%,respectively,which is close to 0.At the same time,R-Square(R^(2))is as high as 0.9948,which is close to 1,indicating that the estimated results in this paper are highly consistent with the actual results.展开更多
Very few studies have benefited from the synergetic implementation of visible,near-infrared,and shortwave infrared(VNIR-SWIR)spectra and terrain attributes in predicting Pb content in agricultural soils.To fill this g...Very few studies have benefited from the synergetic implementation of visible,near-infrared,and shortwave infrared(VNIR-SWIR)spectra and terrain attributes in predicting Pb content in agricultural soils.To fill this gap,this study aimed to predict lead(Pb)contents in agricultural soils by combining machine learning algorithms(MLAs)with VNIR-SWIR spectra or/and terrain attributes under three distinct approaches.Six MLAs were tested,including artificial neural network(ANN),partial least squares regression,support vector machine(SVM),Gaussian process regression(GPR),extreme gradient boosting(EGB),and Cubist.The VNIR-SWIR spectral data were preprocessed by methods of discrete wavelet transformation,logarithmic transformation-Savitzky Golay smoothing,standard normal variate(SNV),multiplicative scatter correction,first derivative(Fi D),and second derivative.In approach 1,MLAs were combined with the preprocessed VNIR-SWIR spectral data.The Cubist-Fi D combination was the most effective,achieving a coefficient of determination(R2)of 0.63,a concordance correlation coefficient(CCC)of 0.51,a mean absolute error(MAE)of 6.87 mg kg^(-1),and a root mean square error(RMSE)of8.66 mg kg^(-1).In approach 2,MLAs were combined with both preprocessed VNIR-SWIR spectral data and terrain attributes,and the EGB-SNV combination yielded superior results with R2of 0.75,CCC of 0.65,MAE of 5.48 mg kg^(-1),and RMSE of 7.34 mg kg^(-1).Approach 3 combined MLAs and terrain attributes,and Cubist demonstrated the best prediction results,with R^(2) of 0.75,CCC of 0.66,MAE of 6.18 mg kg^(-1),and RMSE of 7.71 mg kg^(-1).The cumulative assessment identified the fusion of terrain properties,SNV-preprocessed VNIR-SWIR spectra,and EGB as the optimal method for estimating Pb content in agricultural soils,yielding the highest R2value and minimal error.Comparatively,GPR,ANN,and SVM techniques achieved higher R2values in approaches 2 and 3 but also exhibited higher estimation errors.In conclusion,the study underscores the significance of using relevant auxiliary datasets and appropriate MLAs for accurate Pb content prediction with minimal error in agricultural soils.The findings contribute valuable insights for developing successful soil management strategies based on predictive modeling.展开更多
An accurate and robust estimation of leaf chlorophyll content(LCC)is very important to better know the process of material and energy exchange between plants and the environment.Compared with traditional remote sensin...An accurate and robust estimation of leaf chlorophyll content(LCC)is very important to better know the process of material and energy exchange between plants and the environment.Compared with traditional remote sensing methods,abundant research has made progress in agronomic parameter retrieval using different CNN frameworks.Nevertheless,limited reports have paid attention to the problems,i.e.,limited measured data,hyperspectral redundancy,and model convergence issues,when concerning CNN models for parameter estimation.Therefore,the present study tried to analyze the effects of synthetic data size expansion employing aGaussian process regression(GPR)model for simulation,input feature optimization using different spectral indices with a competitive adaptive reweighted sampling(CARS)algorithm,model convergence issue combining transfer learning(TL)method for accurate and robust estimation of plant LCC with a deep learning framework(i.e.,ResNet-18)using the ANGERS data(a public dataset containing foliar biochemical parameters spectral data for various plant types).Results showed that ResNet-18 training using 800 simulated reflectances(400–1000 nm)and partial ANGERS data exhibited better results,with an R^(2)value of 0.89,an RMSE value of 6.98μg/cm^(2),an RPD value of 3.70,for LCC retrieval using remanent ANGERS data,thanmodels that using simulations with different amounts of data.The estimation accuracies obviously increased when nine spectral indexes,selected from the CARS algorithm,were used as model input for running the ResNet-18 model(R^(2)=0.96,RMSE=4.65μg/cm^(2),RPD=4.81).In addition,coupling transfer learning with ResNet-18 improved the model convergence rate,and TL-ResNet-18 exhibited accurate results for LCC estimation(R^(2)=0.94,RMSE=5.14μg/cm^(2),RPD=4.65).These results suggest that adding appropriate synthetic data,input features optimization,and transfer learning techniques could be effectively used for improved LCC retrieval with a ResNet-18 model.展开更多
This study presents a data-driven approach to predict tailplane aerodynamics in icing conditions,supporting the ice-tolerant design of aircraft horizontal stabilizers.The core of this work is a low-cost predictive mod...This study presents a data-driven approach to predict tailplane aerodynamics in icing conditions,supporting the ice-tolerant design of aircraft horizontal stabilizers.The core of this work is a low-cost predictive model for analyzing icing effects on swept tailplanes.The method relies on a multi-fidelity data gathering campaign,enabling seamless integration into multidisciplinary aircraft design workflows.A dataset of iced airfoil shapes was generated using 2D inviscid methods across various flight conditions.High-fidelity CFD simulations were conducted on both clean and iced geometries,forming a multidimensional aerodynamic database.This 2D database feeds a nonlinear vortex lattice method to estimate 3D aerodynamic characteristics,following a'quasi-3D'approach.The resulting reduced-order model delivers fast aerodynamic performance estimates of iced tailplanes.To demonstrate its effectiveness,optimal ice-tolerant tailplane designs were selected from a range of feasible shapes based on a reference transport aircraft.The analysis validates the model's reliability,accuracy,and limitations concerning 3D ice shapes and aerodynamic characteristics.Most notably,the model offers near-zero computational cost compared to high-fidelity simulations,making it a valuable tool for efficient aircraft design.展开更多
CO_(2)flooding for enhanced oil recovery(EOR)not only enables underground carbon storage but also plays a critical role in tertiary oil recovery.However,its displacement efficiency is constrained by whether CO_(2)and ...CO_(2)flooding for enhanced oil recovery(EOR)not only enables underground carbon storage but also plays a critical role in tertiary oil recovery.However,its displacement efficiency is constrained by whether CO_(2)and crude oil achieve miscibility,necessitating precise prediction of the minimum miscibility pressure(MMP)for CO_(2)-oil systems.Traditional methods,such as experimental measurements and empirical correlations,face challenges including time-consuming procedures and limited applicability.In contrast,artificial intelligence(AI)algorithms have emerged as superior alternatives due to their efficiency,broad applicability,and high prediction accuracy.This study employs four AI algorithms—Random Forest Regression(RFR),Genetic Algorithm Based Back Propagation Artificial Neural Network(GA-BPNN),Support Vector Regression(SVR),and Gaussian Process Regression(GPR)—to establish predictive models for CO_(2)-oil MMP.A comprehensive database comprising 151 data entries was utilized for model development.The performance of these models was rigorously evaluated using five distinct statistical metrics and visualized comparisons.Validation results confirm their accuracy.Field applications demonstrate that all four models are effective for predicting MMP in ultra-deep reservoirs(burial depth>5000 m)with complex crude oil compositions.Among them,the RFR and GA-BPNN models outperform SVR and GPR,achieving root mean square errors(RMSE)of 0.33%and 2.23%,and average absolute percentage relative errors(AAPRE)of 0.01%and 0.04%,respectively.Sensitivity analysis of MMP-influencing factors reveals that reservoir temperature(T_(R))exerts the most significant impact on MMP,while Xint(mole fraction of intermediate oil components,including C_(2)-C_(4),CO_(2),and H_(2)S)exhibits the least influence.展开更多
High-precision filtering estimation is one of the key techniques for strapdown inertial navigation system/global navigation satellite system(SINS/GNSS)integrated navigation system,and its estimation plays an important...High-precision filtering estimation is one of the key techniques for strapdown inertial navigation system/global navigation satellite system(SINS/GNSS)integrated navigation system,and its estimation plays an important role in the performance evaluation of the navigation system.Traditional filter estimation methods usually assume that the measurement noise conforms to the Gaussian distribution,without considering the influence of the pollution introduced by the GNSS signal,which is susceptible to external interference.To address this problem,a high-precision filter estimation method using Gaussian process regression(GPR)is proposed to enhance the prediction and estimation capability of the unscented quaternion estimator(USQUE)to improve the navigation accuracy.Based on the advantage of the GPR machine learning function,the estimation performance of the sliding window for model training is measured.This method estimates the output of the observation information source through the measurement window and realizes the robust measurement update of the filter.The combination of GPR and the USQUE algorithm establishes a robust mechanism framework,which enhances the robustness and stability of traditional methods.The results of the trajectory simulation experiment and SINS/GNSS car-mounted tests indicate that the strategy has strong robustness and high estimation accuracy,which demonstrates the effectiveness of the proposed method.展开更多
It remains challenging to effectively estimate the remaining capacity of the secondary lithium-ion batteries that have been widely adopted for consumer electronics,energy storage,and electric vehicles.Herein,by integr...It remains challenging to effectively estimate the remaining capacity of the secondary lithium-ion batteries that have been widely adopted for consumer electronics,energy storage,and electric vehicles.Herein,by integrating regular real-time current short pulse tests with data-driven Gaussian process regression algorithm,an efficient battery estimation has been successfully developed and validated for batteries with capacity ranging from 100%of the state of health(SOH)to below 50%,reaching an average accuracy as high as 95%.Interestingly,the proposed pulse test strategy for battery capacity measurement could reduce test time by more than 80%compared with regular long charge/discharge tests.The short-term features of the current pulse test were selected for an optimal training process.Data at different voltage stages and state of charge(SOC)are collected and explored to find the most suitable estimation model.In particular,we explore the validity of five different machine-learning methods for estimating capacity driven by pulse features,whereas Gaussian process regression with Matern kernel performs the best,providing guidance for future exploration.The new strategy of combining short pulse tests with machine-learning algorithms could further open window for efficiently forecasting lithium-ion battery remaining capacity.展开更多
Cutting tool condition directly affects machining quality and efficiency.In order to avoid severely worn tools used during machining process and fully release the remaining useful life in the meanwhile,a reliable eval...Cutting tool condition directly affects machining quality and efficiency.In order to avoid severely worn tools used during machining process and fully release the remaining useful life in the meanwhile,a reliable evaluation method of remaining useful life of cutting tools is quite necessary.Due to the variation of cutting conditions,it is a challenge to predict remaining useful life of cutting tools by a unified model.In order to address this issue,this paper proposes a method for predicting the remaining useful life of cutting tools in variable cutting conditions based on Gaussian process regression model incorporated with tool wear mechanism,where the predicted value at adjacent moments is constrained to a linear relationship by the covariance matrix of Gaussian model based on the assumption of progressive tool wear process,so the wear process under continuous changing conditions can be modelled.In addition to that,the input feature space and the output of the model are also enhanced by considering the tool wear mechanism for improving prediction accuracy.Machining experiments are performed to verify the proposed method,and the results show that the proposed could improve the prediction of tool remaining useful life significantly.展开更多
The dynamic soft sensor based on a single Gaussian process regression(GPR) model has been developed in fermentation processes.However,limitations of single regression models,for multiphase/multimode fermentation proce...The dynamic soft sensor based on a single Gaussian process regression(GPR) model has been developed in fermentation processes.However,limitations of single regression models,for multiphase/multimode fermentation processes,may result in large prediction errors and complexity of the soft sensor.Therefore,a dynamic soft sensor based on Gaussian mixture regression(GMR) was proposed to overcome the problems.Two structure parameters,the number of Gaussian components and the order of the model,are crucial to the soft sensor model.To achieve a simple and effective soft sensor,an iterative strategy was proposed to optimize the two structure parameters synchronously.For the aim of comparisons,the proposed dynamic GMR soft sensor and the existing dynamic GPR soft sensor were both investigated to estimate biomass concentration in a Penicillin simulation process and an industrial Erythromycin fermentation process.Results show that the proposed dynamic GMR soft sensor has higher prediction accuracy and is more suitable for dynamic multiphase/multimode fermentation processes.展开更多
The hot deformation behaviors of FGH98 nickel-based powder superalloy were experimentally investigated and theoretically analyzed by Arrhenius models and machine learning(ML).Hot compression tests were conducted with ...The hot deformation behaviors of FGH98 nickel-based powder superalloy were experimentally investigated and theoretically analyzed by Arrhenius models and machine learning(ML).Hot compression tests were conducted with a Gleeble-3800 thermo-mechanical simulation machine on the FGH98 superalloy at strain rates of 0.001–1 s–1 and temperatures of 1025–1175℃.The peak stresses under different deformation conditions were analyzed via the Sellars model and an ML-inspired Gaussian process regression(GPR)model.The prediction of the GPR model outperformed that from the Sellars model.In addition,the stress-strain responses were predicted by the GPR model and tested by experimentally measured stress-strain curves.The results indicate that the developed GPR model has great power with wide generalization capability in the prediction of hot deformation behaviors of FGH98 superalloy,as evidenced by the R2 value higher than 0.99 on the test dataset.展开更多
Due to the geological body uncertainty,the identification of the surrounding rock parameters in the tunnel construction process is of great significance to the calculation of tunnel stability.The ubiquitous-joint mode...Due to the geological body uncertainty,the identification of the surrounding rock parameters in the tunnel construction process is of great significance to the calculation of tunnel stability.The ubiquitous-joint model and three-dimensional numerical simulation have advantages in the parameter identification of surrounding rock with weak planes,but conventional methods have certain problems,such as a large number of parameters and large time consumption.To solve the problems,this study combines the orthogonal design,Gaussian process(GP)regression,and difference evolution(DE)optimization,and it constructs the parameters identification method of the jointed surrounding rock.The calculation process of parameters identification of a tunnel jointed surrounding rock based on the GP optimized by the DE includes the following steps.First,a three-dimensional numerical simulation based on the ubiquitous-joint model is conducted according to the orthogonal and uniform design parameters combing schemes,where the model input consists of jointed rock parameters and model output is the information on the surrounding rock displacement and stress.Then,the GP regress model optimized by DE is trained by the data samples.Finally,the GP model is integrated into the DE algorithm,and the absolute differences in the displacement and stress between calculated and monitored values are used as the objective function,while the parameters of the jointed surrounding rock are used as variables and identified.The proposed method is verified by the experiments with a joint rock surface in the Dadongshan tunnel,which is located in Dalian,China.The obtained calculation and analysis results are as follows:CR=0.9,F=0.6,NP=100,and the difference strategy DE/Best/1 is recommended.The results of the back analysis are compared with the field monitored values,and the relative error is 4.58%,which is satisfactory.The algorithm influencing factors are also discussed,and it is found that the local correlation coefficientσf and noise standard deviationσn affected the prediction accuracy of the GP model.The results show that the proposed method is feasible and can achieve high identification precision.The study provides an effective reference for parameter identification of jointed surrounding rock in a tunnel.展开更多
The resolution of ocean reanalysis datasets is generally low because of the limited resolution of their associated numerical models.Low-resolution ocean reanalysis datasets are therefore usually interpolated to provid...The resolution of ocean reanalysis datasets is generally low because of the limited resolution of their associated numerical models.Low-resolution ocean reanalysis datasets are therefore usually interpolated to provide an initial or boundary field for higher-resolution regional ocean models.However,traditional interpolation methods(nearest neighbor interpolation,bilinear interpolation,and bicubic interpolation)lack physical constraints and can generate significant errors at land-sea boundaries and around islands.In this paper,a machine learning method is used to design an interpolation algorithm based on Gaussian process regression.The method uses a multiscale kernel function to process two-dimensional space meteorological ocean processes and introduces multiscale physical feature information(sea surface wind stress,sea surface heat flux,and ocean current velocity).This greatly improves the spatial resolution of ocean features and the interpolation accuracy.The eff ectiveness of the algorithm was validated through interpolation experiments relating to sea surface temperature(SST).The root mean square error(RMSE)of the interpolation algorithm was 38.9%,43.7%,and 62.4%lower than that of bilinear interpolation,bicubic interpolation,and nearest neighbor interpolation,respectively.The interpolation accuracy was also significantly better in off shore area and around islands.The algorithm has an acceptable runtime cost and good temporal and spatial generalizability.展开更多
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.
基金supported by the National Natural Science Foundation of China(Grant No.42274035)the Major Science and Technology Program for Hubei Province(No.2022AAA002)the Hunan Provincial Land Surveying and Mapping Project(HNGTCH-2023-05)。
文摘Global Navigation Satellite System(GNSS)imaging method(GIM)has been successfully applied to global regions to investigate vertical land motion(VLM)of the Earth's surface.GNSS images derived from conventional GIM method may present fragmented patches and encounter problems caused by excessive smoothing of velocity peaks,leading to difficulty in short-wavelength deformation detection and improper geophysical interpretation.Therefore,we propose a novel GNSS imaging method based on Gaussian process regression with velocity uncertainty considered(GPR-VU).Gaussian processing regression is introduced to describe the spatial relationship between neighboring site pairs as a priori weights and then reweight velocities by known station uncertainties,converting the discrete velocity field to a continuous one.The GPR-VU method is applied to reconstruct VLM images in the southwestern United States and the eastern Qinghai-Xizang Plateau,China,using the GNSS position time series in vertical direction.Compared to the traditional GIM method,the root-mean-square(RMS)and overall accuracy of the confusion matrix of the GPR-VU method increase by 5.0%and 14.0%from the 1°×1°checkerboard test in the southwestern United States.Similarly,the RMS and overall accuracy increase by 33.7%and 15.8%from the 6°×6°checkerboard test in the eastern Qinghai-Xizang Plateau.These checkerboard tests validate the capability to effectively capture the spatiotemporal variations characteristics of VLM and show that this algorithm outperforms the sparsely distributed network in the Qinghai-Xizang Plateau.The images from the GPR-VU method using real data in both regions show significant subsidence around Lassen Volcanic in northern California within a 30 km radius,slight uplift in the northern Sichuan Basin,and subsidence in its central and southern sections.These results further qualitatively illustrate consistency with previous findings.The GPR-VU method outperforms in diminishing the effect by fragmented patches,excessive smoothing of velocity peaks,and detecting potential short-wavelength deformations.
基金supported by Fundamental Research Program of Shanxi Province(No.202203021211088)Shanxi Provincial Natural Science Foundation(No.202204021301049).
文摘The performance of lithium-ion batteries(LIBs)gradually declines over time,making it critical to predict the battery’s state of health(SOH)in real-time.This paper presents a model that incorporates health indicators and ensemble Gaussian process regression(EGPR)to predict the SOH of LIBs.Firstly,the degradation process of an LIB is analyzed through indirect health indicators(HIs)derived from voltage and temperature during discharge.Next,the parameters in the EGPR model are optimized using the gannet optimization algorithm(GOA),and the EGPR is employed to estimate the SOH of LIBs.Finally,the proposed model is tested under various experimental scenarios and compared with other machine learning models.The effectiveness of EGPR model is demonstrated using the National Aeronautics and Space Administration(NASA)LIB.The root mean square error(RMSE)is maintained within 0.20%,and the mean absolute error(MAE)is below 0.16%,illustrating the proposed approach’s excellent predictive accuracy and wide applicability.
基金The authors acknowledge financial support from the National Natural Science Foundation of China(Grant Nos.51771114 and 51371117).
文摘The metastable retained austenite(RA)plays a significant role in the excellent mechanical performance of quenching and partitioning(Q&P)steels,while the volume fraction of RA(V_(RA))is challengeable to directly predict due to the complicated relationships between the chemical composition and process(like quenching temperature(Qr)).A Gaussian process regression model in machine learning was developed to predict V_(RA),and the model accuracy was further improved by introducing a metallurgical parameter of martensite fraction(fo)to accurately predict V_(RA) in Q&P steels.The developed machine learning model combined with Bayesian global optimization can serve as another selection strategy for the quenching temperature,and this strategy is very effcient as it found the"optimum"Qr with the maximum V_(RA) using only seven consecutive iterations.The benchmark experiment also reveals that the developed machine learning model predicts V_(RA) more accurately than the popular constrained carbon equilibrium thermodynamic model,even better than a thermo-kinetic quenching-partitioning-tempering-local equilibrium model.
基金supported in part by the National Key Research and Development Program of China(2021YFC2902703)the National Natural Science Foundation of China(62173078,61773105,61533007,61873049,61873053,61703085,61374147)。
文摘Concentrate copper grade(CCG)is one of the important production indicators of copper flotation processes,and keeping the CCG at the set value is of great significance to the economic benefit of copper flotation industrial processes.This paper addresses the fluctuation problem of CCG through an operational optimization method.Firstly,a density-based affinity propagationalgorithm is proposed so that more ideal working condition categories can be obtained for the complex raw ore properties.Next,a Bayesian network(BN)is applied to explore the relationship between the operational variables and the CCG.Based on the analysis results of BN,a weighted Gaussian process regression model is constructed to predict the CCG that a higher prediction accuracy can be obtained.To ensure the predicted CCG is close to the set value with a smaller magnitude of the operation adjustments and a smaller uncertainty of the prediction results,an index-oriented adaptive differential evolution(IOADE)algorithm is proposed,and the convergence performance of IOADE is superior to the traditional differential evolution and adaptive differential evolution methods.Finally,the effectiveness and feasibility of the proposed methods are verified by the experiments on a copper flotation industrial process.
基金supported in part by the National Key Research and Development Program of China(2019YFB1503700)the Hunan Natural Science Foundation-Science and Education Joint Project(2019JJ70063)。
文摘The noise that comes from finite element simulation often causes the model to fall into the local optimal solution and over fitting during optimization of generator.Thus,this paper proposes a Gaussian Process Regression(GPR)model based on Conditional Likelihood Lower Bound Search(CLLBS)to optimize the design of the generator,which can filter the noise in the data and search for global optimization by combining the Conditional Likelihood Lower Bound Search method.Taking the efficiency optimization of 15 kW Permanent Magnet Synchronous Motor as an example.Firstly,this method uses the elementary effect analysis to choose the sensitive variables,combining the evolutionary algorithm to design the super Latin cube sampling plan;Then the generator-converter system is simulated by establishing a co-simulation platform to obtain data.A Gaussian process regression model combing the method of the conditional likelihood lower bound search is established,which combined the chi-square test to optimize the accuracy of the model globally.Secondly,after the model reaches the accuracy,the Pareto frontier is obtained through the NSGA-II algorithm by considering the maximum output torque as a constraint.Last,the constrained optimization is transformed into an unconstrained optimizing problem by introducing maximum constrained improvement expectation(CEI)optimization method based on the re-interpolation model,which cross-validated the optimization results of the Gaussian process regression model.The above method increase the efficiency of generator by 0.76%and 0.5%respectively;And this method can be used for rapid modeling and multi-objective optimization of generator systems.
基金supported by the SP2024/089 Project by the Faculty of Materials Science and Technology,VˇSB-Technical University of Ostrava.
文摘In engineering practice,it is often necessary to determine functional relationships between dependent and independent variables.These relationships can be highly nonlinear,and classical regression approaches cannot always provide sufficiently reliable solutions.Nevertheless,Machine Learning(ML)techniques,which offer advanced regression tools to address complicated engineering issues,have been developed and widely explored.This study investigates the selected ML techniques to evaluate their suitability for application in the hot deformation behavior of metallic materials.The ML-based regression methods of Artificial Neural Networks(ANNs),Support Vector Machine(SVM),Decision Tree Regression(DTR),and Gaussian Process Regression(GPR)are applied to mathematically describe hot flow stress curve datasets acquired experimentally for a medium-carbon steel.Although the GPR method has not been used for such a regression task before,the results showed that its performance is the most favorable and practically unrivaled;neither the ANN method nor the other studied ML techniques provide such precise results of the solved regression analysis.
基金The Fundamental Research Funds for the Central Universities(No.JUDCF12027,JUSRP51323B)the Scientific Innovation Research of College Graduates in Jiangsu Province(No.CXLX12_0734)
文摘The conventional single model strategy may be ill- suited due to the multiplicity of operation phases and system uncertainty. A novel global-local discriminant analysis （GLDA） based Gaussian process regression （GPR） approach is developed for the quality prediction of nonlinear and multiphase batch processes. After the collected data is preprocessed through batchwise unfolding, the hidden Markov model （HMM） is applied to identify different operation phases. A GLDA algorithm is also presented to extract the appropriate process variables highly correlated with the quality variables, decreasing the complexity of modeling. Besides, the multiple local GPR models are built in the reduced- dimensional space for all the identified operation phases. Furthermore, the HMM-based state estimation is used to classify each measurement sample of a test batch into a corresponding phase with the maximal likelihood estimation. Therefore, the local GPR model with respect to specific phase is selected for online prediction. The effectiveness of the proposed prediction approach is demonstrated through the multiphase penicillin fermentation process. The comparison results show that the proposed GLDA-GPR approach is superior to the regular GPR model and the GPR based on HMM （HMM-GPR） model.
基金supported by the National Natural Science Foundation of China(Project No.62273176)“Joint Laboratory Project of Intelligent Power and Control Applications”(Project No.1003-KFA24090)the National Key Research and Development Program of China(Project No.2024YFB3311401).
文摘Lithium-ion batteries(LIBs)have been widely used in mobile energy storage systems because of their high energy density,long life,and strong environmental adaptability.Accurately estimating the state of health(SOH)for LIBs is promising and has been extensively studied for many years.However,the current prediction methods are susceptible to noise interference,and the estimation accuracy has room for improvement.Motivated by this,this paper proposes a novel battery SOH estimation method,the Beluga Whale Optimization(BWO)and Noise-Input Gaussian Process(NIGP)Stacked Model(BGNSM).This method integrates the BWO-optimized Gaussian Process Regression(GPR)with the NIGP.It combines their predictions using a stacked GPR model which reduces the problem of large input data noise and improves the prediction accuracy.The experimental results show that the BGNSM method has good accuracy,generalization ability,and robustness,and performs well in small sample situations.The Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)are as low as 0.218%and 0.164%,respectively,which is close to 0.At the same time,R-Square(R^(2))is as high as 0.9948,which is close to 1,indicating that the estimated results in this paper are highly consistent with the actual results.
基金supported by an institutional Ph.D.grant(No.21130/1312/3131)from the Faculty of Agrobiology,Food,and Natural Resources at the Czech University of Life Sciences Prague(CZU),Czech Republic。
文摘Very few studies have benefited from the synergetic implementation of visible,near-infrared,and shortwave infrared(VNIR-SWIR)spectra and terrain attributes in predicting Pb content in agricultural soils.To fill this gap,this study aimed to predict lead(Pb)contents in agricultural soils by combining machine learning algorithms(MLAs)with VNIR-SWIR spectra or/and terrain attributes under three distinct approaches.Six MLAs were tested,including artificial neural network(ANN),partial least squares regression,support vector machine(SVM),Gaussian process regression(GPR),extreme gradient boosting(EGB),and Cubist.The VNIR-SWIR spectral data were preprocessed by methods of discrete wavelet transformation,logarithmic transformation-Savitzky Golay smoothing,standard normal variate(SNV),multiplicative scatter correction,first derivative(Fi D),and second derivative.In approach 1,MLAs were combined with the preprocessed VNIR-SWIR spectral data.The Cubist-Fi D combination was the most effective,achieving a coefficient of determination(R2)of 0.63,a concordance correlation coefficient(CCC)of 0.51,a mean absolute error(MAE)of 6.87 mg kg^(-1),and a root mean square error(RMSE)of8.66 mg kg^(-1).In approach 2,MLAs were combined with both preprocessed VNIR-SWIR spectral data and terrain attributes,and the EGB-SNV combination yielded superior results with R2of 0.75,CCC of 0.65,MAE of 5.48 mg kg^(-1),and RMSE of 7.34 mg kg^(-1).Approach 3 combined MLAs and terrain attributes,and Cubist demonstrated the best prediction results,with R^(2) of 0.75,CCC of 0.66,MAE of 6.18 mg kg^(-1),and RMSE of 7.71 mg kg^(-1).The cumulative assessment identified the fusion of terrain properties,SNV-preprocessed VNIR-SWIR spectra,and EGB as the optimal method for estimating Pb content in agricultural soils,yielding the highest R2value and minimal error.Comparatively,GPR,ANN,and SVM techniques achieved higher R2values in approaches 2 and 3 but also exhibited higher estimation errors.In conclusion,the study underscores the significance of using relevant auxiliary datasets and appropriate MLAs for accurate Pb content prediction with minimal error in agricultural soils.The findings contribute valuable insights for developing successful soil management strategies based on predictive modeling.
基金supported by the National Natural Science Foundation of China(Project Nos.41901268 and 42371385)Zhejiang Provincial Natural Science Foundation of China(Grant No.LTGN23D010002).
文摘An accurate and robust estimation of leaf chlorophyll content(LCC)is very important to better know the process of material and energy exchange between plants and the environment.Compared with traditional remote sensing methods,abundant research has made progress in agronomic parameter retrieval using different CNN frameworks.Nevertheless,limited reports have paid attention to the problems,i.e.,limited measured data,hyperspectral redundancy,and model convergence issues,when concerning CNN models for parameter estimation.Therefore,the present study tried to analyze the effects of synthetic data size expansion employing aGaussian process regression(GPR)model for simulation,input feature optimization using different spectral indices with a competitive adaptive reweighted sampling(CARS)algorithm,model convergence issue combining transfer learning(TL)method for accurate and robust estimation of plant LCC with a deep learning framework(i.e.,ResNet-18)using the ANGERS data(a public dataset containing foliar biochemical parameters spectral data for various plant types).Results showed that ResNet-18 training using 800 simulated reflectances(400–1000 nm)and partial ANGERS data exhibited better results,with an R^(2)value of 0.89,an RMSE value of 6.98μg/cm^(2),an RPD value of 3.70,for LCC retrieval using remanent ANGERS data,thanmodels that using simulations with different amounts of data.The estimation accuracies obviously increased when nine spectral indexes,selected from the CARS algorithm,were used as model input for running the ResNet-18 model(R^(2)=0.96,RMSE=4.65μg/cm^(2),RPD=4.81).In addition,coupling transfer learning with ResNet-18 improved the model convergence rate,and TL-ResNet-18 exhibited accurate results for LCC estimation(R^(2)=0.94,RMSE=5.14μg/cm^(2),RPD=4.65).These results suggest that adding appropriate synthetic data,input features optimization,and transfer learning techniques could be effectively used for improved LCC retrieval with a ResNet-18 model.
基金funding from the Department of Industrial Engineering,University of Naples FedericoⅡ,Italy。
文摘This study presents a data-driven approach to predict tailplane aerodynamics in icing conditions,supporting the ice-tolerant design of aircraft horizontal stabilizers.The core of this work is a low-cost predictive model for analyzing icing effects on swept tailplanes.The method relies on a multi-fidelity data gathering campaign,enabling seamless integration into multidisciplinary aircraft design workflows.A dataset of iced airfoil shapes was generated using 2D inviscid methods across various flight conditions.High-fidelity CFD simulations were conducted on both clean and iced geometries,forming a multidimensional aerodynamic database.This 2D database feeds a nonlinear vortex lattice method to estimate 3D aerodynamic characteristics,following a'quasi-3D'approach.The resulting reduced-order model delivers fast aerodynamic performance estimates of iced tailplanes.To demonstrate its effectiveness,optimal ice-tolerant tailplane designs were selected from a range of feasible shapes based on a reference transport aircraft.The analysis validates the model's reliability,accuracy,and limitations concerning 3D ice shapes and aerodynamic characteristics.Most notably,the model offers near-zero computational cost compared to high-fidelity simulations,making it a valuable tool for efficient aircraft design.
文摘CO_(2)flooding for enhanced oil recovery(EOR)not only enables underground carbon storage but also plays a critical role in tertiary oil recovery.However,its displacement efficiency is constrained by whether CO_(2)and crude oil achieve miscibility,necessitating precise prediction of the minimum miscibility pressure(MMP)for CO_(2)-oil systems.Traditional methods,such as experimental measurements and empirical correlations,face challenges including time-consuming procedures and limited applicability.In contrast,artificial intelligence(AI)algorithms have emerged as superior alternatives due to their efficiency,broad applicability,and high prediction accuracy.This study employs four AI algorithms—Random Forest Regression(RFR),Genetic Algorithm Based Back Propagation Artificial Neural Network(GA-BPNN),Support Vector Regression(SVR),and Gaussian Process Regression(GPR)—to establish predictive models for CO_(2)-oil MMP.A comprehensive database comprising 151 data entries was utilized for model development.The performance of these models was rigorously evaluated using five distinct statistical metrics and visualized comparisons.Validation results confirm their accuracy.Field applications demonstrate that all four models are effective for predicting MMP in ultra-deep reservoirs(burial depth>5000 m)with complex crude oil compositions.Among them,the RFR and GA-BPNN models outperform SVR and GPR,achieving root mean square errors(RMSE)of 0.33%and 2.23%,and average absolute percentage relative errors(AAPRE)of 0.01%and 0.04%,respectively.Sensitivity analysis of MMP-influencing factors reveals that reservoir temperature(T_(R))exerts the most significant impact on MMP,while Xint(mole fraction of intermediate oil components,including C_(2)-C_(4),CO_(2),and H_(2)S)exhibits the least influence.
基金supported by the National Natural Science Foundation of China(61873275,61703419,425317829).
文摘High-precision filtering estimation is one of the key techniques for strapdown inertial navigation system/global navigation satellite system(SINS/GNSS)integrated navigation system,and its estimation plays an important role in the performance evaluation of the navigation system.Traditional filter estimation methods usually assume that the measurement noise conforms to the Gaussian distribution,without considering the influence of the pollution introduced by the GNSS signal,which is susceptible to external interference.To address this problem,a high-precision filter estimation method using Gaussian process regression(GPR)is proposed to enhance the prediction and estimation capability of the unscented quaternion estimator(USQUE)to improve the navigation accuracy.Based on the advantage of the GPR machine learning function,the estimation performance of the sliding window for model training is measured.This method estimates the output of the observation information source through the measurement window and realizes the robust measurement update of the filter.The combination of GPR and the USQUE algorithm establishes a robust mechanism framework,which enhances the robustness and stability of traditional methods.The results of the trajectory simulation experiment and SINS/GNSS car-mounted tests indicate that the strategy has strong robustness and high estimation accuracy,which demonstrates the effectiveness of the proposed method.
基金support from Shenzhen Municipal Development and Reform Commission(Grant Number:SDRC[2016]172)Shenzhen Science and Technology Program(Grant No.KQTD20170810150821146)Interdisciplinary Research and Innovation Fund of Tsinghua Shenzhen International Graduate School,and Shanghai Shun Feng Machinery Co.,Ltd.
文摘It remains challenging to effectively estimate the remaining capacity of the secondary lithium-ion batteries that have been widely adopted for consumer electronics,energy storage,and electric vehicles.Herein,by integrating regular real-time current short pulse tests with data-driven Gaussian process regression algorithm,an efficient battery estimation has been successfully developed and validated for batteries with capacity ranging from 100%of the state of health(SOH)to below 50%,reaching an average accuracy as high as 95%.Interestingly,the proposed pulse test strategy for battery capacity measurement could reduce test time by more than 80%compared with regular long charge/discharge tests.The short-term features of the current pulse test were selected for an optimal training process.Data at different voltage stages and state of charge(SOC)are collected and explored to find the most suitable estimation model.In particular,we explore the validity of five different machine-learning methods for estimating capacity driven by pulse features,whereas Gaussian process regression with Matern kernel performs the best,providing guidance for future exploration.The new strategy of combining short pulse tests with machine-learning algorithms could further open window for efficiently forecasting lithium-ion battery remaining capacity.
基金National Natural Science Foundation Project of China(Nos.51925505,51921003)。
文摘Cutting tool condition directly affects machining quality and efficiency.In order to avoid severely worn tools used during machining process and fully release the remaining useful life in the meanwhile,a reliable evaluation method of remaining useful life of cutting tools is quite necessary.Due to the variation of cutting conditions,it is a challenge to predict remaining useful life of cutting tools by a unified model.In order to address this issue,this paper proposes a method for predicting the remaining useful life of cutting tools in variable cutting conditions based on Gaussian process regression model incorporated with tool wear mechanism,where the predicted value at adjacent moments is constrained to a linear relationship by the covariance matrix of Gaussian model based on the assumption of progressive tool wear process,so the wear process under continuous changing conditions can be modelled.In addition to that,the input feature space and the output of the model are also enhanced by considering the tool wear mechanism for improving prediction accuracy.Machining experiments are performed to verify the proposed method,and the results show that the proposed could improve the prediction of tool remaining useful life significantly.
基金Supported by the Natural Science Foundation of Jiangsu Province of China(BK20130531)the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD[2011]6)Jiangsu Government Scholarship
文摘The dynamic soft sensor based on a single Gaussian process regression(GPR) model has been developed in fermentation processes.However,limitations of single regression models,for multiphase/multimode fermentation processes,may result in large prediction errors and complexity of the soft sensor.Therefore,a dynamic soft sensor based on Gaussian mixture regression(GMR) was proposed to overcome the problems.Two structure parameters,the number of Gaussian components and the order of the model,are crucial to the soft sensor model.To achieve a simple and effective soft sensor,an iterative strategy was proposed to optimize the two structure parameters synchronously.For the aim of comparisons,the proposed dynamic GMR soft sensor and the existing dynamic GPR soft sensor were both investigated to estimate biomass concentration in a Penicillin simulation process and an industrial Erythromycin fermentation process.Results show that the proposed dynamic GMR soft sensor has higher prediction accuracy and is more suitable for dynamic multiphase/multimode fermentation processes.
基金supported by the National Natural Science Foundation of China(No.91860115)the Science,Technology,and Innovation Commission of Shenzhen Municipality(No.JSGG20210802093205015).
文摘The hot deformation behaviors of FGH98 nickel-based powder superalloy were experimentally investigated and theoretically analyzed by Arrhenius models and machine learning(ML).Hot compression tests were conducted with a Gleeble-3800 thermo-mechanical simulation machine on the FGH98 superalloy at strain rates of 0.001–1 s–1 and temperatures of 1025–1175℃.The peak stresses under different deformation conditions were analyzed via the Sellars model and an ML-inspired Gaussian process regression(GPR)model.The prediction of the GPR model outperformed that from the Sellars model.In addition,the stress-strain responses were predicted by the GPR model and tested by experimentally measured stress-strain curves.The results indicate that the developed GPR model has great power with wide generalization capability in the prediction of hot deformation behaviors of FGH98 superalloy,as evidenced by the R2 value higher than 0.99 on the test dataset.
基金This work was supported by the National Natural Science Foundation of China(Nos.51678101,52078093)Liaoning Revitalization Talents Program(No.XLYC1905015).
文摘Due to the geological body uncertainty,the identification of the surrounding rock parameters in the tunnel construction process is of great significance to the calculation of tunnel stability.The ubiquitous-joint model and three-dimensional numerical simulation have advantages in the parameter identification of surrounding rock with weak planes,but conventional methods have certain problems,such as a large number of parameters and large time consumption.To solve the problems,this study combines the orthogonal design,Gaussian process(GP)regression,and difference evolution(DE)optimization,and it constructs the parameters identification method of the jointed surrounding rock.The calculation process of parameters identification of a tunnel jointed surrounding rock based on the GP optimized by the DE includes the following steps.First,a three-dimensional numerical simulation based on the ubiquitous-joint model is conducted according to the orthogonal and uniform design parameters combing schemes,where the model input consists of jointed rock parameters and model output is the information on the surrounding rock displacement and stress.Then,the GP regress model optimized by DE is trained by the data samples.Finally,the GP model is integrated into the DE algorithm,and the absolute differences in the displacement and stress between calculated and monitored values are used as the objective function,while the parameters of the jointed surrounding rock are used as variables and identified.The proposed method is verified by the experiments with a joint rock surface in the Dadongshan tunnel,which is located in Dalian,China.The obtained calculation and analysis results are as follows:CR=0.9,F=0.6,NP=100,and the difference strategy DE/Best/1 is recommended.The results of the back analysis are compared with the field monitored values,and the relative error is 4.58%,which is satisfactory.The algorithm influencing factors are also discussed,and it is found that the local correlation coefficientσf and noise standard deviationσn affected the prediction accuracy of the GP model.The results show that the proposed method is feasible and can achieve high identification precision.The study provides an effective reference for parameter identification of jointed surrounding rock in a tunnel.
基金Supported by the National Natural Science Foundation of China(Nos.41675097,41375113)。
文摘The resolution of ocean reanalysis datasets is generally low because of the limited resolution of their associated numerical models.Low-resolution ocean reanalysis datasets are therefore usually interpolated to provide an initial or boundary field for higher-resolution regional ocean models.However,traditional interpolation methods(nearest neighbor interpolation,bilinear interpolation,and bicubic interpolation)lack physical constraints and can generate significant errors at land-sea boundaries and around islands.In this paper,a machine learning method is used to design an interpolation algorithm based on Gaussian process regression.The method uses a multiscale kernel function to process two-dimensional space meteorological ocean processes and introduces multiscale physical feature information(sea surface wind stress,sea surface heat flux,and ocean current velocity).This greatly improves the spatial resolution of ocean features and the interpolation accuracy.The eff ectiveness of the algorithm was validated through interpolation experiments relating to sea surface temperature(SST).The root mean square error(RMSE)of the interpolation algorithm was 38.9%,43.7%,and 62.4%lower than that of bilinear interpolation,bicubic interpolation,and nearest neighbor interpolation,respectively.The interpolation accuracy was also significantly better in off shore area and around islands.The algorithm has an acceptable runtime cost and good temporal and spatial generalizability.
