Accelerating Manufacturing Decisions using Bayesian Optimization: An Optimization and Prediction Perspective

pBO-2GP-3B: A batch parallel known/unknown constrained Bayesian optimization with feasibility classification and its applications in computational fluid dynamics

Radiation therapy treatment planning is inherently a multiobjective problem, aiming to obtain the best tradeoffs between irradiating the tumor with the prescribed dose and sparing as much as possible the surrounding healthy organs. Many different multiobjective approaches have been proposed for the optimization of radiation intensities for fixed beam irradiation directions. However, multiobjective beam angle optimization is seldom considered. The purpose of this paper is to introduce a new multiobjective optimization framework that explicitly and simultaneously considers the optimization of intensities and also beam directions. Whilst multiobjective optimization of radiation intensities considering a fixed set of beam directions gives rise to a single Pareto front, beam angle optimization gives rise to the appearance of multiple Pareto fronts, each one associated with a given beam angle set. Our framework proposes a beam angle set choice based on the evaluation of non-dominated solutions belonging to different Pareto fronts, using a tree-based approach and a performance indicator to assess the quality of each Pareto front. The proposed approach, illustrated by head-and-neck cancer cases, allows for more flexibility in the calculation of solutions and a better understanding of the existing compromises between different objectives.

A Tchebycheff-based multi-objective combined with a PSO–SQP dynamic real-time optimization framework for cycling energy systems

Multilateral wells (MLWs) equipped with multiple flow control devices (FCDs) are becoming increasingly favored within the oil sector due to their ability to enhance well-to-reservoir exposure and effectively handle unwanted fluid breakthrough. However, combining various types of FCDs in multilateral wells poses a complex optimization problem with a large number of highly correlated control variables and a computationally expensive objective function. Consequently, standard optimization algorithms, including metaheuristic and gradient-based approaches, may struggle to identify an optimal solution within a limited computational resource. This paper introduces a novel hybrid optimization (HO) framework combining particle swarm optimization (PSO) and Simultaneous Perturbation Stochastic Approximation (SPSA). It is developed to efficiently optimize the completion design of MLWs with various FCDs while overcoming the individual limitations of each optimization algorithm. The proposed framework is further enhanced by employing surrogate modelling and global sensitivity analysis to identify critical parameters (i.e., highly sensitive) that greatly affect the objective function. This allows for a focused optimization effort on these key parameters, ultimately enhancing global optimization performance. The performance of the novel optimization framework is evaluated using the Olympus benchmark reservoir model. The model is developed by three intelligent dual-lateral wells, with inflow control devices (ICDs) installed within the laterals and interval control valves (ICVs) positioned at the lateral junctions. The results show that the proposed hybrid optimization framework outperforms all industry-standard optimization techniques, achieving a Net Present Value of approximately USD 1.94 billion within a limited simulation budget of 2500 simulation runs. This represents a substantial 26% NPV improvement compared to the open-hole case (USD 1.54 billion NPV). This improvement is attributed to more efficient water breakthrough management, leading to a notable 24% reduction in cumulative water production and, consequently, a 26% increase in cumulative oil production.

This article introduces a framework for Bayesian Optimization (BO) with metric movement costs, addressing a critical challenge in practical applications where input alterations incur varying costs. Our approach is a convenient plug-in that seamlessly integrates with the existing literature on batched algorithms, where designs within batches are observed following the solution of a Traveling Salesman Problem. The proposed method provides a theoretical guarantee of convergence in terms of movement costs for BO. Empirically, our method effectively reduces average movement costs over time while maintaining comparable regret performance to conventional BO methods. This framework also shows promise for broader applications in various bandit settings with movement costs.

To maintain a sufficient chlorine residual in water distribution systems (WDSs), chlorine dosage needs to be regulated. The majority of previous studies that aimed to optimize chlorine dosage in WDSs considered single-species water quality (WQ) models featuring chlorine decay with simple reaction kinetics. Recent efforts have proposed using multi-species water quality (MS-WQ) models to account for chlorine interactions with various chemical and microbiological species, thus providing a comprehensive and accurate evaluation of the WQ within WDSs. Nevertheless, the key challenge of implementing MS-WQ models within optimization frameworks is their high computational cost and poor scalability for larger WDSs. Furthermore, previous optimization studies generally relied on evolutionary algorithms (EAs), which require conducting a significant number of WQ simulations. Bayesian optimization (BO) has been recently suggested as an efficient alternative to EAs for the optimization of computationally expensive functions. This study aims to present a systematic comparison between BO and other widely used EAs for the optimization of MS-WQ in WDSs. A case study featuring a real-life, midsized benchmark WDS was implemented to comprehensively evaluate all three optimization techniques. The results revealed that BO is notably more computationally efficient and less sensitive to changes in the constraints than EAs.

The simultaneous design of processes and enabling materials such as solvents, catalysts, and adsorbents is challenging because molecular‐ and process‐level decisions are strongly interdependent. Sequential approaches often yield suboptimal results since improvements in material properties may not translate into superior process performance. We propose a multiscale Bayesian Optimization (BO) framework that explicitly couples molecular‐ and process‐level design in a bi‐level structure. The inner loop solves deterministic process models, while the outer BO loop explores molecular descriptors, reducing dimensionality, improving sample efficiency, and handling process constraints. A case study on multiscale reactor and catalyst codesign demonstrates that this hybrid strategy achieves optimal performance with substantially lower computational effort than direct BO over the full decision space. BO, when aligned with the natural process—material hierarchy—thus provides an efficient methodology for multiscale design.

This paper presents a modeling framework for fast design space exploration and optimization of equalized on-chip interconnects. The exploration is enabled by cross-layer modeling that connects the transistor and wire parameters to link performance, equalization coefficients, and architecture-friendly metrics (delay, energy-per-bit, and throughput density). Appropriate models are derived to speed-up the search by more than two orders of magnitude and make a million point design space searchable in less than two hours on a standard machine. With this approach we are able to find the best link design for target throughput, power and area constraints, thus enabling the architectural optimization of energy-efficient on-chip networks. For the same latency and throughput density, equalized interconnects optimized using the new methodology have up to 10times better energy-efficiency than optimized repeater interconnects.

Estimation of internal states in a Li-ion battery using BiLSTM with Bayesian hyperparameter optimization

The paper presents a novel approach to applying Bayesian Optimization (BO) in predicting an unknown constraint boundary, also representing the discontinuity of an unknown function, for a feasibility check on the design space, thereby representing a classification tool to discern between a feasible and infeasible region. Bayesian optimization is a low-cost black-box global optimization tool in the Sequential Design Methods where one learns and updates knowledge from prior evaluated designs, and proceeds to the selection of new designs for future evaluation. However, BO is best suited to problems with the assumption of a continuous objective function and does not guarantee true convergence when having a discontinuous design space. This is because of the insufficient knowledge of the BO about the nature of the discontinuity of the unknown true function. In this paper, we have proposed to predict the location of the discontinuity using a BO algorithm on an artificially projected continuous design space from the original discontinuous design space. The proposed approach has been implemented in a thin tube design with the risk of creep-fatigue failure under constant loading of temperature and pressure. The stated risk depends on the location of the designs in terms of safe and unsafe regions, where the discontinuities lie at the transition between those regions; therefore, the discontinuity has also been treated as an unknown creep-fatigue failure constraint. The proposed BO algorithm has been trained to maximize sampling toward the unknown transition region, to act as a high accuracy classifier between safe and unsafe designs with minimal training cost. The converged solution has been validated for different design parameters with classification error rate and function evaluations at an average of <1% and ∼150, respectively. Finally, the performance of our proposed approach in terms of training cost and classification accuracy of thin tube design is shown to be better than the existing machine learning (ML) algorithms such as Support Vector Machine (SVM), Random Forest (RF), and Boosting.

We present a comparison of 6T and 8T SRAM design spaces for low-power 65 nm and 45 nm CMOS technologies based on simulations using a multi-objective optimization framework. The influence of a bit-line column multiplexer (MUX) on the 8T design space is shown. We demonstrate that 6T and 8T cells show differing area scaling behavior across the whole design space. We identify points on the area-performance trade-off curves that bound regions where either 6T or 8T SRAM cells are optimal.KeywordsDesign SpaceMultiobjective OptimizationDesign Space ExplorationVLSI CircuitSRAM CellThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

When designing a fusion power plant, many first-of-a-kind components are required. This presents a large potential design space across as many dimensions as the component’s parameters. In addition, multiphysics, multiscale, high-fidelity simulations are required to reliably capture a component’s performance under given boundary conditions. Even with high performance computing (HPC) resources, it is not possible to fully explore a component’s design space. Thus, effective interpolation between data points via machine learning (ML) techniques is essential. With sequential learning engineering optimisation, ML techniques inform the selection of simulation parameters which give the highest expected improvement for the model: balancing exploitation of the current best design with exploration of uncertain areas in the design space. In this paper, the application of an ML-driven design of experiment procedure for the sequential learning engineering design optimisation of a fusion component is shown. A parameterised divertor monoblock is taken as a typical example of a fusion component requiring HPC simulation to model. The component’s geometry is then optimised using Bayesian optimisation, seeking the design which minimises the stress experienced by the component under operational conditions.

In the multi-objective optimization design of automotive seats based on Approximation-Based Design Optimization, a single approximation model may not adequately address the requirement of accurately fitting highly nonlinear feature data. For this reason, the Hybrid Approximation Models based on the Multi-Species Approximation Model (HAM-MSAM) is proposed to meet the requirement for high fitting accuracy. Subsequently, this study introduces a HAM-MSAM-based Approximation-Based Global Multi-Objective Optimization Design (ABGMOOD) strategy. This strategy is employed in the multi-objective optimization of the rear seat of a passenger car. HAM-MSAM was constructed from an experimentally validated finite element model and a training set generated through experimental design. The advantages of HAM-MSAM in capturing the highly nonlinear response under seat crash conditions were validated through comparison with hybrid model construction methods reported in existing literature. Finally, the optimization results obtained by the ABGMOOD strategy were compared to those of the classical local multi-objective optimization strategy, demonstrating the substantial advantages of the ABGMOOD optimization scheme in economy and weight reduction. In addition, the safety of the rear seats is slightly lower than that of the local optimization scheme but remains in compliance with regulatory requirements. The final optimized rear seat demonstrates notable improvements in safety, economy, and weight reduction, validating the feasibility of the ABGMOOD strategy and providing valuable insights for similar engineering optimization challenges.

Optimizing multiple, non-preferential objectives for mixed-variable, expensive black-box problems is important in many areas of engineering and science. The expensive, noisy, black-box nature of these problems makes them ideal candidates for Bayesian optimization (BO). Mixed-variable and multi-objective problems, however, are a challenge due to BO's underlying smooth Gaussian process surrogate model. Current multi-objective BO algorithms cannot deal with mixed-variable problems. We present MixMOBO, the first mixed-variable, multi-objective Bayesian optimization framework for such problems. Using MixMOBO, optimal Pareto-fronts for multi-objective, mixed-variable design spaces can be found efficiently while ensuring diverse solutions. The method is sufficiently flexible to incorporate different kernels and acquisition functions, including those that were developed for mixed-variable or multi-objective problems by other authors. We also present HedgeMO, a modified Hedge strategy that uses a portfolio of acquisition functions for multi-objective problems. We present a new acquisition function, SMC. Our results show that MixMOBO performs well against other mixed-variable algorithms on synthetic problems. We apply MixMOBO to the real-world design of an architected material and show that our optimal design, which was experimentally fabricated and validated, has a normalized strain energy density $10^4$ times greater than existing structures.

A novel multiobjective adaptive surrogate modeling-based optimization (MO-ASMO) framework is proposed to utilize a minimal number of training samples efficiently for sequential model updates. All the sample points are enforced to be feasible, and to provide coverage of sparsely explored sparse design regions using a new optimization subproblem. The MO-ASMO method only evaluates high-fidelity functions at feasible sample points. During an exploitation sample phase, samples are selected to enhance solution accuracy rather than the global exploration. Sampling tasks are especially challenging for multiobjective optimization; for an n-dimensional design space, a strategy is required for generating model update sample points near an (n − 1)-dimensional hypersurface corresponding to the Pareto set in the design space. This is addressed here using a force-directed layout algorithm, adapted from graph visualization strategies, to distribute feasible sample points evenly near the estimated Pareto set. Model validation samples are chosen uniformly on the Pareto set hypersurface, and surrogate model estimates at these points are compared to high-fidelity model responses. All high-fidelity model evaluations are stored for later use to train an updated surrogate model. The MO-ASMO algorithm, along with the set of new sampling strategies, are tested using two mathematical and one realistic engineering problems. The second mathematical test problems is specifically designed to test the limits of this algorithm to cope with very narrow, non-convex feasible domains. It involves oscillatory objective functions, giving rise to a discontinuous set of Pareto-optimal solutions. Also, the third test problem demonstrates that the MO-ASMO algorithm can handle a practical engineering problem with more than 10 design variables and black-box simulations. The efficiency of the MO-ASMO algorithm is demonstrated by comparing the result of two mathematical problems to the results of the NSGA-II algorithm in terms of the number of high fidelity function evaluations, and is shown to reduce total function evaluations by several orders of magnitude when converging to the same Pareto sets.