Isotope Separator On-Line system tuning: Bayesian optimization applied to the transport beamline case

To address the problems of local optima and insufficient convergence accuracy in parameter identification of primary frequency regulation (PFR) for steam turbines, this paper proposed a hybrid identification method that integrated an Improved Bayesian Optimization (IBO) algorithm and an Improved Whale Optimization Algorithm (IWOA). By initializing the Bayesian parameter population using Tent chaotic mapping and the reverse learning strategy, employing a radial basis kernel function hyperparameter training mechanism based on the Adam optimizer and optimizing the Expected Improvement (EI) function using the Limited-memory Broyden–Fletcher– Goldfarb–Shanno with Bounds (L-BFGS-B) method, IBO was proposed to obtain the optimal candidate set with the smallest objective function value. By introducing a nonlinear convergence factor and the adaptive Levy flight perturbation strategy, IWOA was proposed to obtain locally optimized optimal solutions. By using the reverse-guided optimization mechanism and employing a fitness-oriented selection strategy, the optimal solution was chosen to complete the closed-loop process of reverse learning feedback. Nine standard test functions and the Proportional Integral Derivative (PID) parameter identification of the electro-hydraulic servo system in a 330 MW steam turbine were presented as examples. Compared with Particle Swarm Optimization (PSO), Whale Optimization Algorithm (WOA), Bayesian Optimization (BO) and Particle Swarm Optimization-Grey Wolf Optimizer (PSO-GWO), the Improved Bayesian Optimization-Whale Optimization Algorithm (IBO-WOA) proposed in this paper has been validated to effectively avoid the problem of getting stuck in local optima during complex optimization and has high parameter recognition accuracy. Meanwhile, an Out-Of-Distribution (OOD) Test based on noise injection had demonstrated that IBO-WOA had good robustness. The time constant identification of the steam turbine were carried out using IBO-WOA under two experimental conditions, and the identification results were input into the PFR model. The simulated power curve can track the experimental measured curve well, proving that the parameter identification results obtained by IBO-WOA have high accuracy and can be used for the modeling and response characteristic analysis of the steam turbine PFR.

Bayesian optimization (BO) is a versatile and robust global optimization method under uncertainty. However, most of the BO algorithms were developed for problems with only continuous variables. For practical engineering optimization, discrete variables are also prevalent. BO methods based on Gaussian process (GP) surrogates also suffers from the curse-of-dimensionality problem. To address these challenges, in this paper, a Bayesian discrete optimization algorithm is introduced to solve permutation-based combinatorial problems. A new kernel function is developed based on position distances for permutation. To improve the efficiency and scalability of the algorithm, a sparse GP model based on inducing points is further developed, where the simulated annealing algorithm is applied to select inducing points. The new algorithm is demonstrated and tested with the production scheduling problem for additive manufacturing. Experimental results show that the proposed algorithm can find a better solution with limited evaluations than state-of-the-art algorithms.

Electrochemical machining is a promising non-traditional manufacturing process to make high-quality parts. The benefits of minimal thermally and mechanically induced stresses, free of burr, and a low surface roughness are appealing for industry and research institutes. However, the combined chemical reaction, electric field, fluid mechanics, and material properties involve a significant number of independent parameters which are difficult to analyze in order to draw comprehensive conclusions. To our current knowledge, process responses such as the material removal rate, optimal feed rate, and cutting profile cannot be represented accurately by analytical solutions. In recent years, deep learning has had tremendous success in analyzing sophisticated systems. The improved computation efficiency and reduced size of the training dataset required for deep learning have enabled various prediction models in the manufacturing industry. In this paper, a new approach is developed using the deep convolutional network with the Bayesian optimization algorithm to predict the diameters of the drilled hole from an electrochemical machining process. The Keras application programming interface (API) was used to build the deep convolutional network; the feed rate, pulse-on time, and voltage were used as input parameters to provide a fair comparison with a neural network from previous research. Random dropout layers were added to prevent overfitting of the network. Instead of tuning the network parameter by trial and error, the Bayesian parameter optimization algorithm was implemented to find the optimal set of parameters of the deep convolutional network that yields the minimum mean square error. The proposed algorithm was compared with a previously developed neural network with partially embedded physical knowledge. Improved training speed and accuracy were observed in comparison with the traditional neural network. The prediction model using the proposed deep learning algorithm demonstrated better prediction accuracy and provided a more systematic way to select the hyperparameter for the deep convolutional network.

Key-frame extraction is a key technique of video retrieval. In view of the low accuracy of currently traditional key-frame extraction algorithm, and low recall level and accuracy of video retrieval, a kind of model of network video retrieval of dynamic Bayesian network optimization for the mobile terminal was put forward. First of all, the study of dynamic Bayesian network optimization algorithm was conducted, and by using a Bayesian algorithm, the real data were used as the characteristic of the center of clustering, then the condensed coarsening and the condensed refining that are two important processes for network video retrieval model algorithm were improved, used to replace the top core set obtained in the original coarsening process, thereby designing a kind of new dynamic Bayesian network optimization algorithm, so as to realize the rapid and accurate positioning of the top core set, which can decrease the number of condensed layer and simplify the computational complexity of the algorithm. Then, the improved network video retrieval model algorithm was applied to the key-frame extraction of the video. The experimental results show that the proposed algorithm can more effectively extract key frames of video compared with the original algorithm.

Revolutionizing biochar synthesis for enhanced heavy metal adsorption: Harnessing machine learning and Bayesian optimization

We propose a highly efficient searching algorithm in crystal structure prediction. The searching algorithm is a hybrid of the evolutionary algorithm and Bayesian optimization. The evolutionary algorithm is widely used in crystal structure prediction, and the Bayesian optimization is one of the selection-type algorithms we have developed. We have performed simulations of crystal structure prediction to compare the success rates of the random search, evolutionary algorithm, Bayesian optimization, and hybrid algorithm for up to ternary systems such as Si, Y2Co17, Al2O3, and CuGaS2, using the CrySPY code. These results demonstrate that the evolutionary algorithm can generate structures more efficiently than random structure generation, and the Bayesian optimization can efficiently select potential candidates from a large number of structures. Moreover, the hybrid algorithm, which has the advantages of both, is proved to be the most efficient searching algorithm among them.

Load forecasting impacts directly financial returns and information in electrical systems planning. A promising approach to load forecasting is the Echo State Network (ESN), a recurrent neural network for the processing of temporal dependencies. The low computational cost and powerful performance of ESN make it widely used in a range of applications including forecasting tasks and nonlinear modeling. This paper presents a Bayesian optimization algorithm (BOA) of ESN hyperparameters in load forecasting with its main contributions including helping the selection of optimization algorithms for tuning ESN to solve real-world forecasting problems, as well as the evaluation of the performance of Bayesian optimization with different acquisition function settings. For this purpose, the ESN hyperparameters were set as variables to be optimized. Then, the adopted BOA employs a probabilist model using Gaussian process to find the best set of ESN hyperparameters using three different options of acquisition function and a surrogate utility function. Finally, the optimized hyperparameters are used by the ESN for predictions. Two datasets have been used to test the effectiveness of the proposed forecasting ESN model using BOA approaches, one from Poland and another from Brazil. The results of optimization statistics, convergence curves, execution time profile, and the hyperparameters’ best solution frequencies indicate that each problem requires a different setting for the BOA. Simulation results are promising in terms of short-term load forecasting quality and low error predictions may be achieved, given the correct options settings are used. Furthermore, since there is not an optimal global optimization solution known for real-world problems, correlations among certain values of hyperparameters are useful to guide the selection of such a solution.

This paper incorporates Bayesian estimation and optimization into a portfolio selection framework, particularly for high-dimensional portfolios in which the number of assets is larger than the number of observations. We leverage a constrained minimization approach, called the linear programming optimal (LPO) portfolio, to directly estimate effective parameters appearing in the optimal portfolio. We propose two refinements for the LPO strategy. First, we explore improved Bayesian estimates, instead of sample estimates, of the covariance matrix of asset returns. Second, we introduce Bayesian optimization (BO) to replace traditional grid-search cross-validation (CV) in tuning hyperparameters of the LPO strategy. We further propose modifications in the BO algorithm by (1) taking into account the time-dependent nature of financial problems and (2) extending the commonly used expected improvement acquisition function to include a tunable trade-off with the improvement’s variance. Allowing a general case of noisy observations, we theoretically derive the sublinear convergence rate of BO under the newly proposed EIVar and thus our algorithm has no regret. Our empirical studies confirm that the adjusted BO results in portfolios with higher out-of-sample Sharpe ratio, certainty equivalent, and lower turnover compared to those tuned with CV. This superior performance is achieved with a significant reduction in time elapsed, thus also addressing time-consuming issues of CV. Furthermore, LPO with Bayesian estimates outperforms the original proposal of LPO, as well as the benchmark equally weighted and plugin strategies.

A Multiobjective Optimization Problem (MOP) requires the optimization of several objective functions simultaneously, usually in conflict with each other. One of the most efficient algorithms for solving MOPs is MOEA/D (Multiobjective Evolutionary Algorithm Based on Decomposition), which decomposes a MOP into single-objective optimization subproblems and solves them using information from neighboring subproblems. MOEA/D variants with other evolutionary operators have emerged over the years, improving their efficiency in various MOPs. Recently, the IWOA (Improved Whale Optimization Algorithm) was proposed, an optimization algorithm bioinspired by the whale hunting method hybridized with Differential Evolution, which presented excellent results in single-objective optimization problems. This work proposes the MOEA/D-IWOA algorithm, which associates characteristics of the evolutionary operators of the IWOA to MOEA/D. Computational experiments were accomplished to analyze the performance of the MOEA/D-IWOA in benchmark MOPs suites. The results were compared with those obtained by the MOEA/D, Non-dominated Sorting Genetic Algorithm II (NSGA-II), Third Evolution Step of Generalized Differential Evolution (GDE3), Improving the Strength Pareto Evolutionary Algorithm (SPEA2), and Indicator-Based Evolutionary Algorithm (IBEA) algorithms in the Hypervolume and Inverted Generational Distance Plus (IGD+) indicators. The MOEA/D-IWOA proved to be competitive, with a good performance profile, in addition to presenting the best results in some POMs.

Due to the adversarial limitations between the output solutions in the multi-objective optimization stage, the energy efficiency optimization of large pumping stations has the disadvantage of difficult coordination between power consumption and efficiency. Therefore, a multi-objective Bayesian hyperparameter optimization algorithm design for energy efficiency optimization of large pumping stations has been carried out. A multi-objective optimization model for energy efficiency of large pumping stations was constructed by combining the input power of the main motor, transmission energy loss, transformer loss, and energy consumption of auxiliary equipment, with efficiency as the constraint. We extract sequence features that affect pump water demand, and use feature labels as hyperparameters for the multi-objective optimization model of energy efficiency in large pumping stations. We transform the multi-objective optimization problem into a hyperparameter optimization problem, avoiding adversarial output solutions. We iterate the query points collected by EI, so the output model reaches a convergent optimal solution. The test results show that the designed algorithm can improve the pumping efficiency of the pump station while controlling the power consumption of the pump station, achieving collaborative optimization of efficiency.

A two-stage online remaining useful life prediction framework for supercapacitors based on the fusion of deep learning network and state estimation algorithm

In many recent works, the potential of Exploratory Landscape Analysis (ELA) features to numerically characterize single-objective continuous optimization problems has been demonstrated. These numerical features provide the input for all kinds of machine learning tasks in the domain of continuous optimization problems, ranging, for example, from High-level Property Prediction to Automated Algorithm Selection and Automated Algorithm Configuration. Without ELA features, analyzing and understanding the characteristics of single-objective continuous optimization problems is-to the best of our knowledge-very limited. Yet, despite their usefulness, as demonstrated in several past works, ELA features suffer from several drawbacks. These include, in particular, (1) a strong correlation between multiple features, as well as (2) its very limited applicability to multiobjective continuous optimization problems. As a remedy, recent works proposed deep learning-based approaches as alternatives to ELA. In these works, among others, point-cloud transformers were used to characterize an optimization problem's fitness landscape. However, these approaches require a large amount of labeled training data. Within this work, we propose a hybrid approach, Deep-ELA, which combines (the benefits of) deep learning and ELA features. We pre-trained four transformers on millions of randomly generated optimization problems to learn deep representations of the landscapes of continuous single- and multiobjective optimization problems. Our proposed framework can either be used out of the box for analyzing single- and multiobjective continuous optimization problems, or subsequently fine-tuned to various tasks focusing on algorithm behavior and problem understanding.

PHYSBO (optimization tools for PHYSics based on Bayesian Optimization) is a Python library for fast and scalable Bayesian optimization. It has been developed mainly for application in the basic sciences such as physics and materials science. Bayesian optimization is used to select an appropriate input for experiments/simulations from candidate inputs listed in advance in order to obtain better output values with the help of machine learning prediction. PHYSBO can be used to find better solutions for both single and multi-objective optimization problems. At each cycle in the Bayesian optimization, a single proposal or multiple proposals can be obtained for the next experiments/simulations. These proposals can be obtained interactively for use in experiments. PHYSBO is available at https://github.com/issp-center-dev/PHYSBO. Program summaryProgram Title: PHYSBOCPC Library link to program files:https://doi.org/10.17632/22d72yb6k6.1Developer's repository link:https://github.com/issp-center-dev/PHYSBOLicensing provisions: GNU General Public License version 3Programming language: Python3External routines/libraries: NumPy, SciPy, MPI for Python.Nature of problem: Bayesian optimization (BO) can be used to select inputs that will yield better outputs from a list of candidate inputs with the help of machine learning prediction through a Gaussian process. Although BO is a powerful tool, two of its components, training the Gaussian process regression and optimizing the acquisition function, are generally computationally expensive. Moreover, hyperparameter tuning is necessary for the former process.Solution method: PHYSBO is a Python library for performing fast and scalable Bayesian optimization. To avoid the computationally expensive training process, PHYSBO uses a random feature map, Thompson sampling, and a one-rank Cholesky update. In addition, PHYSBO performs hyperparameter tuning automatically by maximizing the Type II likelihood, and MPI parallelization is used to reduce the calculation time for optimizing the acquisition function.

Achromatic and isochronous lattice design of P2DT bending section in RAON accelerator

With accelerating climate change and urbanization, regional carbon balance faces increasing uncertainty. Terrestrial carbon sinks play a crucial role in advancing China’s sustainable development under the dual-carbon strategy. This study quantitatively modeled China’s terrestrial carbon sink capacity and analyzed the multidimensional relationships between impact factors and carbon sinks. After preprocessing multi-source raster data, we introduced kernel normalized the difference vegetation index (kNDVI) to the Carnegie–Ames–Stanford approach (CASA) model, together with a heterotrophic respiration (Rh) empirical equation, to simulate pixel-level net ecosystem productivity (NEP) across China. A light gradient-boosting machine (LightGBM) model, optimized via Bayesian algorithms, was trained to regress NEP drivers, categorized into atmospheric components (O3, NO2, and SO2) and subsurface properties (a digital elevation model (DEM), enhanced vegetation index (EVI), soil moisture (SM)), and human activities (land use/cover change (LUCC), POP, gross domestic product (GDP)). Shapley Additive Explanation (SHAP) values were used for model interpretation. The results reveal significant spatial heterogeneity in NEP across geographic and climatic contexts. The pixel-level mean and total NEP in China were 268.588 gC/m2/yr and 2.541 PgC/yr, respectively. The north tropical zone (NRZ) exhibited the highest average NEP (828.631 gC/m2/yr), while the middle subtropical zone (MSZ) and south subtropical zone (SSZ) demonstrated the most stable NEP distributions. LightGBM achieved high simulation accuracy, further enhanced by Bayesian optimization. SHAP analysis identified EVI as the most influential factor, followed by SM, NO2, DEM, and POP. Additionally, LightGBM effectively captured nonlinear relationships and variable interactions.