Efficient Multi-objective Optimization Research Articles

Efficient multi-objective Bayesian optimization of gas–liquid photochemical reactions using an automated flow platform

We developed an automated platform capable of performing photochemical gas–liquid reactions. The platform was augmented with a state-of-the-art Bayesian optimization algorithm and was tested on the decatungstate-catalyzed aerobic oxidation of ethyl benzene, to optimize both yield and productivity, and identify the Pareto front of these objectives. Although photochemical gas–liquid systems are highly complex due to numerous interactions between the parameters, including effects on mass-transfer, gas solubility and light absorption, the algorithm demonstrated impressive speed to navigate the parameter space towards optimal conditions. Furthermore, this approach also proved highly flexible, allowing for modification of objectives and parameter ranges on the fly. The identified conditions were then tested on a select scope of substrates, to better understand the generality of these conditions, especially on molecules where selectivity comes into play. The results show the platform to be a useful tool for reaction optimization and process intensification.

Efficient multi-objective optimization approach for solving optimal DG placement and sizing problem in distribution systems

Incorporating distributed generations (DGs) like wind turbines (WTs) and solar photovoltaic (SPV) arrays into radial distribution systems (RDSs) has become increasingly important due to their benefits in enhancing system performance. This requires determining appropriate DG locations and their optimal power output when injected into the RDS. To this end, this paper introduces a novel application of a recent multi-objective optimization technique called multi-objective grey wolf optimization (MOGWO) to allocate multiple DG units into the RDS optimally. The primary objectives are to minimize total real power losses (RPL), reduce voltage deviation (VD), and enhance the voltage stability index (VSI) across the entire system while adhering to operational constraints. Various DG operational power factor (PF) scenarios are considered, including unity-PF, fixed-PF, and optimal-PF. The proposed approach generates a Pareto-optimal set of solutions to address the multi-objective problem, after which a fuzzy decision-making method is adopted to select the best trade-off solution from the set. The technique has been implemented on 69-bus and the actual Portuguese 94-bus RDS. Numerical results are compared with other recent well-known algorithms from the literature, highlighting the efficacy of the suggested MOGWO method in handling multi-objective problems. Comparatively speaking, it provides superior solutions than other methods in selecting appropriate control parameters.

Efficient multi-objective design method for optical coatings

The modern design of high-performance optical coatings demands a comprehensive consideration of multiple properties. We propose an efficient multi-objective optimization method utilizing an adaptive weighted sum method, exploring the lexicographic optimization and geometry-based adaptive weights determination method. Broadband negative dispersive mirrors have been designed that demonstrates notable improvements in performances of spectrum, group delay dispersion and electric field distribution. In addition, we employ Deep-learning method to enhance the optimization. The mapping between different design parameters and results has been learned, which helps the optimization to directly approach the optimal design. It extends the novel method to diverse designs utilizing the similar kinds of merit functions and subsequently accelerates the design by 120 times.

Efficient multi-objective optimization and operational analysis of amine scrubbing CO2 capture process with artificial neural network

Amine scrubbing processes for post-combustion CO2 capture have been extensively studied and significantly improved via various novel designs. However, the amine scrubbers implemented nowadays were usually not optimized according to a number of different evaluation criteria. This is often due to the fact that, for high dimensional design spaces, the rigorous simulation runs needed to facilitate process optimization always calls for huge numbers of simulation software accesses and overwhelming iterative calculations. Therefore, in this study, the well-trained surrogate model was adopted to replace its rigorous counterpart for the purpose of ensuring efficient optimization runs in practical applications. In current study, two objectives, i.e., the specific equivalent work and the CO2 capture level, were both rapidly and effectively optimized in various practical scenarios with different flue gas CO2 concentrations. The corresponding operational parameters and utility consumptions were also easily obtained without additional effort. The computation results obtained so far showed that the proposed surrogate-assisted approach can be utilized to significantly reduce the computational load in practice.

AN INTEGRATED APPROACH TO DESIGNING ROBUST GAS-BEARING SUPPORTED TURBOCOMPRESSORS THROUGH SURROGATE MODELING AND CONSTRAINED ALL-AT-ONCE MULTI-OBJECTIVE OPTIMIZATION

Abstract This research introduces an innovative framework to engineering design to tackle the challenges of robustness against manufacturing deviations and holistic optimization simultaneously in a multi-disciplinary, multi-subsystems context. The methodology is based on an application of ensemble artificial neural networks, which significantly accelerates computational processes. Coupled with the Non-dominated Sorting Genetic Algorithm III, this approach facilitates efficient multi-objective optimization, yielding a comprehensive Pareto front and high-quality design solutions. Here, the framework is applied to the design of gas-bearing-supported turbocompressors. These systems are challenging due to their sensitivity to manufacturing variations, particularly in the gas-bearing geometry, which can lead to rotordynamic instability. Additionally, the interdependencies between the subsystems, such as axial and journal bearings, rotor, compressor impellers, and magnets, necessitate a multidisciplinary approach that spans aerodynamics, structural dynamics, rotordynamics, mechanics, loss analyses, and more. A clear tradeoff between system efficiency, mass-flow range, and robustness has been identified for the compressor design. Higher nominal compressor mass-flows, i.e. increased nominal power, is suggested to decrease the hypervolume of feasible manufacturing deviations. Hence, there is a sweet power spot for gas-bearing supported turbomachinery. Further, the framework's computational efficiency is on par with that of a university cluster, while only employing a desktop computer equipped with a consumer-grade graphics card. This work demonstrates a significant advancement in the design of complex engineering systems and sets a new standard for speed and efficiency in computational engineering design.

Heuristic algorithms for design of integrated monitoring of geologic carbon storage sites

Designs for Risk Evaluation and Management (DREAM) is a tool developed under the National Risk Assessment Partnership (NRAP) to enhance geologic carbon storage safety and efficiency. Using potential leakage scenarios generated externally by the users preferred history-matching approach, DREAM constructs ideal combinations of sensor locations in the right place at the right time to detect as many leaks as possible, detect them as early as possible, and minimize cost. This user-friendly tool, developed in Java, features a window-based GUI for input and a 3D visualization tool for viewing the domain space and optimized monitoring plans. DREAM's latest version accommodates real-world usage by allowing for joint optimization of wellbore point sensor placements and surface geophysics survey geometries, and by using more efficient multi-objective optimization algorithms. In an example shown here, these two improvements combined allow us to support containment assurance and go from detecting 80–90 % of the potential CO2 leakage to +99.7 %, a step-change improvement that can make the deciding difference in whether a site is suitable for geologic carbon storage. Though developed for geologic carbon storage, this tool would be equally applicable in many surface or offshore environmental monitoring projects.

Dynamic optimization of die-less spinning process through autonomous modeling of time-varying forming law

Die-less spinning is a typical incremental forming technology with flexible processing parameters, including the roller path and loading parameters, whose forming law changes dynamically and easy-to-produce defects of excessive thinning and flange wrinkling. This brings a great challenge to the process design of die-less spinning. In this study, we proposed a novel dynamic optimization approach and system considering the time-varying forming law for the processing parameters in die-less spinning. The idea of proposed approach is that simulating the spinning process step by step through autonomous finite element modeling, real-time extracting and modeling the simulated spinning status at each forming step to capture the time-varying forming law, then gradually optimizing the processing parameters through efficient multi-objective optimization algorithm. By conducting the proposed dynamic optimization approach to the first spinning pass of die-less spinning, series of polynomial response surface models (PRSM) of wall thickness and flange wrinkling at various forming steps were developed to describe the time-varying forming law. On this basis, the roller path and matching loading parameters in each step were gradually optimized through a differential evolution algorithm with the multi-objective of minimizing wall thickness reduction, reducing flange wrinkling and maximizing forming efficiency. The optimized process produced better spun part than the traditional spinning process, presenting the wall thickness reduction ≤5 % and the flange wrinkling ≤2.5 mm. Furthermore, the time-varying influence of processing parameters on the wall thickness and flange wrinkling were elucidated based on the PRSM of spinning status at various forming steps.

Directional multiobjective optimization of metal complexes at the billion-system scale.

The discovery of transition metal complexes (TMCs) with optimal properties requires large ligand libraries and efficient multiobjective optimization algorithms. Here we provide the tmQMg-L library, containing 30k diverse and synthesizable ligands with robustly assigned charges and metal coordination modes. tmQMg-L enabled the generation of 1.37 million palladium TMCs, which were used to develop and benchmark the Pareto-Lighthouse multiobjective genetic algorithm (PL-MOGA). With fine control over aim and scope, this algorithm maximized both the polarizability and highest occupied molecular orbital-lowest unoccupied molecular orbital gap of the TMCs within selected regions of the Pareto front, without requiring prior knowledge on the objective limits. Instead of genetic operations on small ligand fragments, the PL-MOGA did whole-ligand mutation and crossover operations, which in chemical spaces containing billions of systems, yielded thousands of highly diverse TMCs in an interpretable manner.

Multi-objective optimization of electrical discharge machining parameters using particle swarm optimization

This manuscript presents an efficient multi-objective optimization method based on using particle swarm optimization together with a desirability function that can be applied where the response variables may have an opposite behavior and where the range of variation of the independent variables as well as those of the responses are subjected to constraints, which has a great deal of industrial interest. For example, maintaining roughness and dimensional tolerances within a tolerance range is determined by the design requirements of the manufactured parts (shape errors, microgeometry errors, etc.) and these requirements must be met in the manufacture of parts. It is demonstrated that it is possible to obtain optimal results in the ranges of variation considered for the independent variables, with regard to those obtained by experimentation. Similarly, models based on Adaptive Network-based Fuzzy Inference Systems are used to solve the problem that may arise from the inadequate fitting of the regression models. Thus, thanks to this present study a fast and efficient method is available for the multiple-optimization of response variables, subject to constraints on both response and independent variables, which are obtained from experiments and modelled by means of soft computing techniques. Furthermore, it is also demonstrated that it is possible to obtain technology tables for various manufacturing processes, which is of great interest from a technological point of view so as to obtain the most suitable processing conditions.

Efficient Multiobjective Optimization Framework for Induction Heating Systems Design

Efficient Multiobjective Optimization Framework for Induction Heating Systems Design

Multi-objective optimization of transfer line balancing problem considering cycle time and energy expenditure

The transfer lines are among highly complex automated production systems that manufacture a large volume of identical or similar products with high demand. Recently, the design of environmentally friendly production systems has become the focus of more and more enterprises as one of the sustainable manufacturing strategies. In light of the recent energy-efficient manufacturing trends, this paper investigates the transfer line balancing problem (TLBP), considering both efficiency and energy aspects. The problem arises in the automated transfer lines equipped with dedicated machining centers and automated material handling systems, producing a large volume of specific products. The operations are performed at machines by realizing particular processing requirements, including machining features, inclusions, and exclusions considerations. The objectives to be minimized are the cycle time and the total energy consumption. The latter objective consists of machines’ operating and non-operating energy costs. The problem is first formulated as a mixed-integer linear programming model. Due to the problem’s complexity, an efficient multi-objective optimization algorithm based on the non-dominated sorting genetic algorithm (NSGA-II) is also proposed. The performance of the proposed algorithm is compared with the e-constraint method in terms of the Pareto-front metrics while solving various test problems and a case study. The computational results show the effectiveness of the proposed algorithm in dealing with the TLBP.

Data-driven product-process optimization of N-isopropylacrylamide microgel flow-synthesis

Microgels are cross-linked, colloidal polymer networks with great potential for stimuli-response release in drug-delivery applications, as their small size allows them to pass human cell boundaries. For applications with specified requirements regarding size, producing tailored microgels in a continuous flow reactor is advantageous because the microgel properties can be controlled tightly. However, no fully-specified mechanistic models are available for continuous microgel synthesis, as the physical properties of the included components are only studied partly. To address this gap and accelerate tailor-made microgel development, we propose a data-driven optimization in a hardware-in-the-loop approach to efficiently synthesize microgels with defined sizes. We optimize the synthesis regarding conflicting objectives (maximum production efficiency, minimum energy consumption, and the desired microgel radius) by applying Bayesian optimization via the solver “Thompson sampling efficient multi-objective optimization” (TS-EMO). We validate the optimization using the deterministic global solver “McCormick-based Algorithm for mixed-integer Nonlinear Global Optimization” (MAiNGO) and verify three computed Pareto optimal solutions via experiments. The proposed framework can be applied to other desired microgel properties and reactor setups and has the potential of efficient development by minimizing number of experiments and modeling effort needed.

Multiobjective Optimization of a Traction Motor in Driving Cycles Using a Coupled Electromagnetic–Thermal 1D Simulation

This paper proposes an electric propulsion system model for computationally efficient multiobjective optimization considering overall driving cycles using coupled electromagnetic–thermal 1D simulation. The proposed system model uses equivalent circuit networks rather than finite element method to obtain high computational efficiency because considering both driving cycles and motor temperature change during optimization requires considerable computational cost. The magnetic saturation effect and temperature change of traction motor during operation are examined by constructing look-up tables. This study first integrated the lumped parameter thermal network into the system model to consider the motor temperature change without any iterative process. The 1D simulation results over urban and highway driving cycles indicate that the changes in the induced current, efficiency, and motor temperature could be predicted while driving. The Pareto optimal solution of traction motor cross-sectional geometry including reduction ratio is successfully obtained by multiobjective optimization with the maximum output torque constraint. Constructing the proposed system model once, optimal design for multiple target driving cycles can be obtained without any driving cycle analysis. In addition, high computational efficiency indicates that the proposed system model is practical in the early design stage of various electric propulsions.

Multiobjective optimization framework for designing a steering system considering structural features and full vehicle dynamics

Vehicle handling and stability performance and ride comfort is normally assessed through standard field test procedures, which are time consuming and expensive. However, the rapid development of digital technologies in the automotive industry have enabled to properly model and simulate the full-vehicle dynamics, thus drastically reducing design and manufacturing times and costs while enhancing the performance, safety, and longevity of vehicle systems. This paper focus on a computationally efficient multi-objective optimization framework for developing an optimal design of a vehicle steering system, which is carried out by coupling certain computer-aided design tools (CAD) and computer-aided engineering (CAE) software. The 3D CAD model of the steering system is made using SolidWorks, the Finite Element Analysis (FEA) is modelled using Ansys Workbench, while the multibody kinematic and dynamic is analysed using Adams/Car. They are embedded in a multidisciplinary optimization design framework (modeFrontier) with the aim of determining the optimal hardpoint locations of the suspension and steering systems. This is achieved by minimizing the Ackermann error and toe angle deviations, together with the volume, mass, and maximum stresses of the rack-and-pinion steering mechanism. This enhances the vehicle stability, safety, manoeuvrability, and passengers’ comfort, extends the vehicle systems reliability and fatigue life, while reducing the tire wear. The method has been successfully applied to different driving scenarios and vehicle maneuvers to find the optimal Pareto front and analyse the performance and behaviour of the steering system. Results show that the design of the steering system can be significantly improved using this approach.

An efficient multi-objective optimization framework for thin-walled tubular deployable composite boom

As a crucial structural component in space applications such as solar sails and solar arrays, the thin-walled tubular deployable composite booms (DCBs) demonstrate extensive utilization by employing stored elastic strain energy to achieve folding and deploying functions. This paper introduces a multi-objective optimization framework that integrates an analytical model with a genetic algorithm. By utilizing a multi-objective evolutionary algorithm based on de-composition (MOEA/D), the optimization objectives of minimizing folding moment and maximizing bending stiffness are pursued. Multiple constraints associated with failure avoidance, laminate stacking sequence design principles, and the folding moment range of actuator in the folding mechanism are considered in the optimization. The multi-objective optimization design of the tubular DCBs is performed to obtain the optimal combinations of cross-sectional radius, central angle, and ply scheme. Experimental validation confirms the efficacy of the optimization results. Additionally, an in-depth analysis on the influence of genetic algorithm types, hyperparameters, and different design variables on the optimization outcomes is thoroughly discussed. The findings of this study offer significantly insights for the practical engineering applications of tubular DCBs.

Multiobjective Bayesian Optimization for Aeroengine Using Multiple Information Sources

Aero-engine performance optimization remains significant for both efficiency and safety during specific operating conditions. Previous works usually solve this optimization problem under a single-objective optimization framework, while multiple objectives need to be optimized simultaneously. Besides, the underlying optimization process requires a variety of function evaluations, and the evaluation cost for an aero-engine is expensive. In reality, the aero-engine model has multiple information sources with different costs and accuracy. The different costs and accuracy of the multiple information sources should be traded off to guide the search for the optimal in a cost-efficient way. Therefore, we propose a multi-information source framework for enabling efficient multi-objective Bayesian optimization. We construct the surrogate model with a multi-fidelity Gaussian process and choose the location-source pair with a modified acquisition function. Finally, we apply the proposed method to improve the performance indexes of the aero-engine, which confirms the efficiency of the proposed algorithm.

Performance prediction of the centrifugal air compressor for fuel cells considering degradation characteristics based on the hierarchical evolutionary model

The performance of the centrifugal air compressor is closely related to the efficiency and energy density of the fuel cell system, and extensive work has been done in this study to achieve precise performance predictions of the compressor considering degradation characteristics. The durability test of the compressor was carried out for 5000 h, and degradation characteristics with break-in time were discussed in detail. On this basis, the hierarchical evolutionary model was constructed to perform the performance predictions based on the Light Gradient Boosting Machine (LightGBM) and Multi-objective Whale Optimization Algorithm (MOWOA). The results demonstrate that the outlet pressure of the compressor decreases by 9.4 kPa and the power consumption increases by 0.71 kW at rated volume flow rate after the break-in of 5000 h, with attenuation ratios of 4.7 % and 12.2 %, respectively. The final non-dominated solution sets have excellent uniformity, diversity and convergence, proving that the developed MOWOA has high adaptability and strong optimization capability. The hierarchical evolutionary model achieves exact predictions for the outlet temperature, flow rate and pressure of the compressor, with absolute relative errors (AREs) below 1 % in outlet temperature and pressure while 5 % in outlet flow rate. All of these provide an efficient multi-objective optimization algorithm and an auto-calibrated hierarchical evolutionary model for further performance optimization of the air compressor.

A novel efficient multi-objective optimization algorithm for expensive building simulation models

A novel efficient multi-objective optimization algorithm for expensive building simulation models

Research on a surrogate model updating-based efficient multi-objective optimization framework for supertall buildings

Research on a surrogate model updating-based efficient multi-objective optimization framework for supertall buildings

Adaptive Basis Function Selection Enhanced Multisurrogate-Assisted Evolutionary Algorithm for Production Optimization

Summary Surrogate-assisted evolutionary algorithms (SAEAs) have become a popular approach for solving reservoir production optimization problems. The radial-basis-function network (RBFN) is a robust surrogate model technology suitable for reservoir development with numerous wells and a long production lifetime. There are several types of basis functions for constructing RBFN models. However, existing research shows that selecting the basis function with competitive performance for the current optimization problem is challenging without prior knowledge. In conventional SAEAs, the basis function is often predetermined, but its prediction accuracy for the problem at hand cannot be guaranteed. Furthermore, canonical SAEAs usually employ only one surrogate model for the entire optimization process. However, relying on a single surrogate model for optimization increases the probability of search direction misdirection due to prediction deviations. In this paper, a novel method named adaptive basis function selection enhanced multisurrogate-assisted evolutionary algorithm (ABMSEA) is introduced for production optimization. This method mainly includes two innovations. First, by training and testing different types of basis functions, the one with the best prediction performance is adaptively selected. Second, the ensemble model is constructed using the bootstrap sampling method, comprising multiple global surrogate models based on the selected best basis function. To search for a set of solutions that perform well on multiple surrogates, we employ an efficient multiobjective optimization (MOO) algorithm called nondominated sorting genetic algorithm II (NSGA-II). This algorithm uses the surrogates themselves as objective functions, aiming to find solutions that yield favorable results across multiple surrogates. The proposed method improves the efficiency of production optimization while enhancing global search capabilities. To evaluate the effectiveness of ABMSEA, we conduct tests on four 100D benchmark functions, a three-channel model, and an egg model. The obtained results are compared with those obtained from differential evolution (DE) and three other surrogate-model-based methods. The experimental results demonstrate that ABMSEA exhibits an accurate selection of competitive basis functions for the current optimization period while maintaining high optimization efficiency and avoiding local optima. Consequently, our method enables optimal well control, leading to the attainment of the highest net present value (NPV).