Explore the vast range of titles available.

The prediction of global optima for non-convex and expensive objective functions is a pervasive challenge across many engineering applications and research areas. Bayesian optimization (BO) is a powerful method for solving optimization problems of this type, as it replaces the expensive search space of the objective function with a less expensive Gaussian process or alternative surrogate model. However, selecting the form and hyperparameters of this surrogate model to optimally represent the design space and maximize the convergence rate is a difficult and non-intuitive challenge. In this work, we conduct a systematic breakdown of the computational costs of the BO framework to reveal how these choices of surrogate formulation and hyperparameters influence overall convergence and prediction quality. We consider two qualitatively different modifications of BO to evaluate for improved performance, specifically gradient-enhanced BO (GEBO) and anisotropy-enhanced automatic relevance determination (ARD). GEBO utilizes available gradient information about the objective function to improve the quality of the surrogate representation and selection of the next evaluation point, but with the trade-off of additional expense. In contrast, ARD utilizes an anisotropic Gaussian process surrogate and relevancy criteria to reduce the search space of the surrogate model and improve convergence by solving a smaller problem. After a systematic analysis of the hyperparameters for both strategies, the methods were benchmarked by solving a fluid mechanics airfoil shape optimization problem and a structural mechanics origami actuator problem. These optimization problems involve 38 to 84 design variables. GEBO exhibited around 3 × speedup for all benchmark problems compared to BO without modification, while ARD-enriched BO exhibited a 1.55× speedup on select problems. Manifold analysis of the design space revealed that ARD performed best on problems with a contiguous reduced dimension. Collectively, these results highlight the trade-offs and cost distribution difference between GE and ARD modification for BO and provide guidelines for implementation in new problems.

This paper introduces a novel approach to speed-sensorless predictive torque control (PTC) in an autonomous wind energy conversion system, specifically utilizing an asymmetric double star induction generator (ADSIG). To achieve accurate estimation of non-linear quantities, the Gaussian Process Regression algorithm (GPR) is employed as a powerful machine learning tool for designing speed and flux estimators. To enhance the capabilities of the GPR, two improvements were implemented, (a) hyperparametric optimization through the Bayesian optimization (BO) algorithm and (b) curation of the input vector using the gray box concept, leveraging our existing knowledge of the ADSIG. Simulation results have demonstrated that the proposed GPR-PTC would remain robust and unaffected by the absence of a speed sensor, maintaining performance even under varying magnetizing inductance. This enables a reliable and cost-effective control solution.

Bayesian optimization (BO)-assisted screening was applied to identify improved reaction conditions toward a hundred-gram scale-up synthesis of 2,3,7,8-tetrathiaspiro[4.4]nonane (1), a key synthetic intermediate of 2,2-bis(mercaptomethyl)propane-1,3-dithiol [tetramercaptan pentaerythritol]. Starting from the initial training set (ITS) consisting of six trials sampled by random screening for BO, suitable parameters were predicted (78% conversion yield of spiro-dithiolane 1) within seven experiments. Moreover, BO-assisted screening with the ITS selected by Latin hypercube sampling (LHS) further improved the yield of 1 to 89% within the eight trials. The established conditions were confirmed to be satisfactory for a hundred grams scale-up synthesis of 1.

Piezoelectric fiber yarns produced by electrospinning offer a versatile platform for intelligent devices, demonstrating mechanical durability and the ability to convert mechanical strain into electric signals. While conventional methods involve twisting a single poly(vinylidene fluoride‐co‐trifluoroethylene)(P(VDF‐TrFE)) fiber mat to create yarns, by limiting control over the mechanical properties, an approach inspired by composite laminate design principles is proposed for strengthening. By stacking multiple electrospun mats in various sequences and twisting them into yarns, the mechanical properties of P(VDF‐TrFE) yarn structures are efficiently optimized. By leveraging a multi‐objective Bayesian optimization‐based machine learning algorithm without imposing specific stacking restrictions, an optimal stacking sequence is determined that simultaneously enhances the ultimate tensile strength (UTS) and failure strain by considering the orientation angles of each aligned fiber mat as discrete design variables. The conditions on the Pareto front that achieve a balanced improvement in both the UTS and failure strain are identified. Additionally, applying corona poling induces extra dipole polarization in the yarn state, successfully fabricating mechanically robust and high‐performance piezoelectric P(VDF‐TrFE) yarns. Ultimately, the mechanically strengthened piezoelectric yarns demonstrate superior capabilities in self‐powered sensing applications, particularly in challenging environments and sports scenarios, substantiating their potential for real‐time signal detection. Inspired by composite laminates, electrospun fiber mats are strategically stacked to create highly strengthened P(VDF‐TrFE) yarns, preserving their high piezoelectric performance. A multi‐objective Bayesian optimization‐based machine learning algorithm is developed to optimize the stacking sequence, ultimately yielding mechanically robust piezoelectric polymer yarn with simultaneously improved ultimate tensile strength and failure strain for real‐time self‐powered sensing applications in diverse environmental conditions.

Metamaterial design, encompassing both microstructure topology selection and geometric parameter optimization, constitutes a high‐dimensional optimization problem, with computationally expensive and time‐consuming design evaluations. Bayesian optimization (BO) offers a promising approach for black‐box optimization involved in various material designs, and this work presents several advanced techniques to adapt BO to address the challenges associated with metamaterial design. First, variational autoencoders (VAEs) are employed for efficient dimensionality reduction, mapping complex, high‐dimensional metamaterial microstructures into a compact latent space. Second, mutual information maximization is incorporated into the VAE to enhance the quality of the learned latent space, ensuring that the most relevant features for optimization are retained. Third, trust region‐based Bayesian optimization (TuRBO) dynamically adjusts local search regions, ensuring stability and convergence in high‐dimensional spaces. The proposed techniques are well incorporated with conventional Gaussian processes (GP)‐based BO framework. We applied the proposed method for the design of electromagnetic metamaterial microstructures. Experimental results show that we achieve a significantly high probability of finding the ground‐truth topology types and their geometric parameters, leading to high accuracy in matching the design target. Moreover, our approach demonstrates significant time efficiency compared with traditional design methods. This study presents advanced Bayesian optimization approaches to tackle the challenging problem of metamaterial design, which involves both microstructure topology selection and geometric parameter optimization. By utilizing variational autoencoders and the information bottleneck principle for effective dimensionality reduction, as well as trust region‐based Bayesian optimization for stable optimization, the design process for electromagnetic metamaterial microstructures is significantly streamlined.

Bayesian Optimization (BO) provides an efficient framework for optimizing expensive black-box functions by employing a surrogate model (typically a Gaussian Process) to approximate the objective function and an acquisition function to guide the search for optimal points. Batch BO extends this paradigm by selecting and evaluating multiple candidate points simultaneously, which improves computational efficiency but introduces challenges in optimizing the resulting high-dimensional acquisition functions. Among existing acquisition functions for batch Bayesian Optimization, entropy-based methods are considered to be state-of-the-art methods due to their ability to enable more globally efficient while avoiding redundant evaluations. However, they often fail to fully capture the dependencies and interactions among the selected batch points. In this work, we propose a Multi-Objective Batch Energy–Entropy acquisition function for Bayesian Optimization (MOBEEBO), which adaptively exploits the correlations among batch points. In addition, MOBEEBO incorporates multiple types of acquisition functions as objectives in a unified framework to achieve more effective batch diversity and quality. Empirical results demonstrate that the proposed algorithm is applicable to a wide range of optimization problems and achieves competitive performance.

Bayesian optimization is a sequential method that can optimize a single and costly objective function based on a surrogate model. In this work, we propose a Bayesian optimization system dedicated to monitoring and estimating multiple water quality parameters simultaneously using a single autonomous surface vehicle. The proposed work combines different strategies and methods for this monitoring task, evaluating two approaches for acquisition function fusion: the coupled and the decoupled techniques. We also consider dynamic parametrization of the maximum measurement distance traveled by the ASV so that the monitoring system balances the total number of measurements and the total distance, which is related to the energy required. To evaluate the proposed approach, the Ypacarai Lake (Paraguay) serves as the test scenario, where multiple maps of water quality parameters, such as pH and dissolved oxygen, need to be obtained efficiently. The proposed system is compared with the predictive entropy search for multi-objective optimization with constraints (PESMOC) algorithm and the genetic algorithm (GA) path planning for the Ypacarai Lake scenario. The obtained results show that the proposed approach is 10.82% better than other optimization methods in terms of R2 score with noiseless measurements and up to 17.23% better when the data are noisy. Additionally, the proposed approach achieves a good average computational time for the whole mission when compared with other methods, 3% better than the GA technique and 46.5% better than the PESMOC approach.

Purpose: Lockdown and movement restrictions that imposed by governments have significantly changed customers behavior, making the planning and decision-making processes more challenging. Providing accurate estimation of the demand, enable managers to take more successful decisions and allow optimizing inventory and resources; this is the main purpose of this study.Design/methodology/approach: An ensemble model that based on combining Bayesian-optimized Long Short-Term Memory (BO-LSTM) and Gated Recurrent Unit (BO-GRU). Experiments were carried out on actual dataset obtained from company specialized in food industries during the volatile situation of Covid-19.Findings: The proposed model significantly outperformed all hand-tuned ones and reduced the mean Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE) by 2.80% and 4.74% compared to BO-LSTM and 3.14% and 3.60% compared to BO-GRU respectively. Furthermore, using BO algorithm for hyperparameters tuning improved the forecasting accuracy.Originality/value: The suggested model was statistically compared to its members in addition to other machine learning models using the t-test. Findings demonstrated the superiority of the proposed method over all benchmark models.

Optimizing process outcomes by tuning parameters through an automated system is common in industry. Ideally, this optimization is performed as efficiently as possible, using the minimum number of steps to achieve an optimal configuration. However, care must often be taken to ensure that, in pursuing the optimal solution, the process does not enter an “unsafe” state (for the process itself or its surroundings). Safe Bayesian optimization is a viable method in such contexts, as it guarantees constraint fulfillment during the optimization process, ensuring the system remains safe. This method assumes the constraints are real-valued and continuous functions. However, in some cases, the constraints are binary (true/false) or classification-based (safe/unsafe), limiting the direct application of safe Bayesian optimization. Therefore, a slight modification of safe Bayesian optimization allows for applying the method using a probabilistic classifier for learning classification constraints. However, violation of constraints may occur during the optimization process, as the theoretical guarantees of safe Bayesian optimization do not apply to discontinuous functions. This paper addresses this limitation by introducing an enhanced version of safe Bayesian optimization incorporating a simulation-informed Gaussian process (GP) for handling classification constraints. The simulation-informed GP transforms the classification constraint into a piece-wise function, enabling the application of safe Bayesian optimization. We applied this approach to optimize the parameters of a computational model for the isotope separator online (ISOL) at the MYRRHA facility (Multipurpose Hybrid Research Reactor for High-Tech Applications). The results revealed a significant reduction in constraint violations—approximately 80%—compared to safe Bayesian optimization methods that directly learn the classification constraints using Laplace approximation and expectation propagation. The sensitivity to the accuracy of the simulation model was analyzed to determine the extent to which it is advantageous to use the proposed method. These findings suggest that incorporating available information into the optimization process is valuable for reducing the number of unsafe outcomes in constrained optimization scenarios.

Cavitation damage on a mercury target vessel for a pulsed spallation neutron source is induced by a proton beam injection in mercury. Cavitation damage is one of factors affecting the allowable beam power and the life time of a mercury target vessel. The prediction method of the cavitation damage using Monte Carlo simulations was proposed taking into account the uncertainties of the core position of cavitation bubbles and impact pressure distributions. The distribution of impact pressure attributed to individual cavitation bubble collapsing was assumed to be Gaussian distribution and the probability distribution of the maximum value of impact pressures was assumed to be three kinds of distributions: the delta function and Gaussian and Weibull distributions. Two parameters in equations describing the distribution of impact pressure were estimated using Bayesian optimization by comparing the distribution of the cavitation damage obtained from the experiment with the distribution of the accumulated plastic strain obtained from the simulation. Regardless of the distribution type, the estimated maximum impact pressure was 1.2–2.9 GPa and existed in the range of values predicted by the ratio of the diameter and depth of the pit. The estimated dispersion of the impact pressure distribution was 1.0–1.7 μm and corresponded to the diameter of major pits. In the distribution of the pits described by the accumulated plastic strain, which was assumed in three cases, the delta function and Gaussian and Weibull distributions, the Weibull distribution agreed well with the experimental results, particularly including relatively large pit size. Furthermore, the Weibull distribution reproduced the depth profile, i.e., pit shape, better than that using the delta function or Gaussian distribution. It can be said that the cavitation erosion phenomenon is predictable by adopting the Weibull distribution. This prediction method is expected to be applied to predict the cavitation damage in fluid equipment such as pumps and fluid parts.