Evolutionary Optimization Method Research Articles

Simultaneous Optimization of Hydrogen Network with Pressure Swing Absorption Based on Evolutionary Response Surface Method

The simultaneous optimization of complex process units and hydrogen networks is a significant challenge in refinery hydrogen network integration. To address this, an evolutionary response surface-based collaborative optimization method is proposed, enabling the concurrent optimization of pressure swing adsorption (PSA) and the hydrogen network. This method develops a mechanistic model for PSA and alternates between random sampling and evolutionary response surface-based hydrogen network optimization to obtain diverse sampling points and potential optimal solutions. The PSA mechanistic model is then used to compute the accurate output parameters for the sampled points, and these parameters are incorporated into the hydrogen network optimization to obtain precise objective function values. An efficient optimization framework is presented to streamline the process. The proposed method is applied to a refinery hydrogen network integration case study, comprehensively considering both PSA costs and hydrogen utility costs. The results demonstrate that the method is computationally efficient and effectively reduces the refinery’s total annual costs. The accuracy of the optimization results is significantly improved compared to traditional methods, providing an effective solution for the collaborative optimization of the refinery hydrogen network and PSA.

Survey of interactive evolutionary decomposition-based multiobjective optimization methods.

Interactive methods support decision-makers in finding the most preferred solution for multiobjective optimization problems, where multiple conflicting objective functions must be optimized simultaneously. These methods let a decision-maker provide preference information iteratively during the solution process to find solutions of interest, allowing them to learn about the trade-offs in the problem and the feasibility of the preferences. Several interactive evolutionary multiobjective optimization methods have been proposed in the literature. In the evolutionary computation community, the so-called decomposition-basedmethods have been increasingly popular because of their good performance in problems with many objective functions. They decompose the multiobjective optimization problem into multiple sub-problems to be solved collaboratively. Various interactive versions of decomposition-based methods have been proposed. However, most of them do not consider the desirable properties of real interactive solution processes, such as avoiding imposing a high cognitive burden on the decision-maker, allowing them to decide when to interact with the method, and supporting them in selecting a final solution. This paper reviews interactive evolutionary decomposition-based multiobjective optimization methods and different methodologies utilized to incorporate interactivity in them. Additionally, desirable properties of interactive decomposition-based multiobjective evolutionary optimization methods are identified, aiming to make them easier to be applied in real-world problems.

Multiscale Concurrent Topology Optimization and Mechanical Property Analysis of Sandwich Structures.

Based on the basic theoretical framework of the Bi-directional Evolutionary Structural Optimization method (BESO) and the Solid Isotropic Material with Penalization method (SIMP), this paper presents a multiscale topology optimization method for concurrently optimizing the sandwich structure at the macro level and the core layer at the micro level. The types of optimizations are divided into macro and micro concurrent topology optimization (MM), macro and micro gradient concurrent topology optimization (MMG), and macro and micro layered gradient concurrent topology optimization (MMLG). In order to compare the multiscale optimization method with the traditional macroscopic optimization method, the sandwich simply supported beam is illustrated as a numerical example to demonstrate the functionalities and superiorities of the proposed method. Moreover, several samples are printed through micro-nano 3D printing technology, and then the static three-point bending experiments and the numerical simulations are carried out. The mechanical properties of the optimized structures in terms of deformation modes, load-bearing capacity, and energy absorption characteristics are compared and analyzed in detail. Finally, the multiscale optimization methods are extended to the design of 2D sandwich cantilever beams and 3D sandwich fully clamped beams.

Comparative Analysis of Evolutionary Methods in Topological Optimization of Truss Structures: Progressive Directional Selection versus Evolutionary Structural Optimization

The main difference between evolutionary methods and traditional structural topological optimization methods is that the former may not always converge to an optimized solution and can be challenging to implement. This work presents two heuristic and evolutionary methods, which aim to analyze truss structures obtained by the topological optimization process using the PDS and ESO methods, employing a ground structure type structure as the initial design domain. The Progressive Directional Selection (PDS) method is based on selecting a certain number of elements, established by the user, that most contribute to supporting the loads applied in an initial design domain. The selection stages involve a progressive number of selection steps, each eliminating a certain number of less efficient elements. Convergence occurs when the selected elements are the same in a certain number of consecutive selection stages, also pre-established by the user. The Evolutionary Structural Optimization (ESO) method is a technique where elements that contribute less to supporting loads in an initial domain are removed through a rejection rate. If removing elements with the same rejection rate value is no longer possible, an evolution rate value can be added to remove more inefficient elements. ESO convergence is achieved when the rejection rate evolves to a user-established value. The optimized structures obtained by both methods efficiently support the applied loads. The PDS method stands out for reaching optimized truss structures with a specific number of elements that ESO cannot obtain, but the former stands out for its shorter processing time.

Design and modelling of a novel dual-type reactor for ammonia production

The ammonia production is one of the most essential petrochemical processes. This article focuses on the heart of this process, the ammonia synthesis reactor. First, an industrial fixed bed reactor for ammonia production, designed by Kellogg's company, is modeled and simulated. Next, a dual-type reactor is proposed to overcome the equilibrium limitations of the exothermic ammonia synthesis reaction. The rules of similar industrial reactor design methodology and the Particle Swarm Optimization (PSO)- Differential evolution (DE) optimization method are used to obtain the reactors' best design parameters and operational conditions. The length of the reactors, the number of tubes in each reactor, the diameter of the gas-cooled reactor, and the cooling water temperature are considered decision variables for the optimization. These variables are optimized to maximize the ammonia yield. Furthermore, the effect of co-current and countercurrent flow patterns on the efficiency of the proposed reactor is investigated. A one-dimensional pseudo-heterogeneous model is applied to simulate the reactor at steady-state conditions. The governing differential equations form a boundary value problem and are solved by the shooting method. The results show that the developed dual-type reactor satisfies all the design limitations. Furthermore, this novel reactor increases the ammonia production capacity by 574 tons per day compared to the conventional Kellogg reactor.

A new evolutionary topology optimization method for truss structures towards practical design applications

This paper presents a new topology optimization method and a comprehensive workflow for the practical design of truss structures. It begins with discussing practical design requirements for truss topology optimization and then introduces a technique for creating arbitrarily shaped ground structures suitable for complex geometries. To address limitations in current truss optimization methods, we propose a dual-material truss-bidirectional evolutionary structural optimization (DMT-BESO) method. This approach utilizes two materials that differ significantly in tensile and compressive allowable stresses and moduli of elasticity. The DMT-BESO method integrates the minimum energy principle with the full-stress design criterion, using bar cross-sectional areas as design variables to achieve simultaneous topology and size optimization. By considering stress constraints, this method ensures compliance with industry standards, enhancing both safety and material utilization. Additionally, a structural complexity control strategy is proposed to generate a near-optimal truss design and simplify the optimized design while maintaining efficiency, making it more suitable for practical applications. The effectiveness of the DMT-BESO method and its complexity control strategy is validated through numerical examples and the design of an arch bridge of composite materials.

Evolutionary topology optimization with stress control for composite laminates using Tsai-Wu criterion

In this study, a topology optimization technique with stress control is proposed for the composite laminates. The bi-directional evolutionary structural optimization (BESO) method is selected to avoid the stress singularity. The technique expresses the failure index based on the Tsai-Wu criterion, thereby ensuring a comprehensive consideration of the anisotropy. To address the local nature of stress and multi-layer structure of laminates, a nested p-norm is employed, providing a global approximation of the local maximum failure index. To mitigate the highly non-linear stress behaviors, filter schemes are applied to both sensitivity numbers and design variables. Sensitivity numbers are derived via adjoint sensitivity analysis and Lagrange multipliers to address stress-based and stress-constrained problems. The proposed framework is validated through systematic numerical studies across various examples and conditions, offering insights into the topological behaviors of composite laminates. This study underscores the importance of considering distinct tensile and compressive strength in composite materials, which represents a key innovation. Additionally, the relationships among stiffness-based, stress-constrained, and stress-based designs are explored in depth.

Interactive multiobjective evolutionary optimization model for dam management support

Dam management optimization is a complex multiobjective problem, whose current solutions struggle to spread in normal practice. Here, an interactive evolutionary multiobjective optimization method is proposed, which involves stakeholders by using multi-criteria decision analysis to embed a parsimonious elicitation of their preferences and expertise in the optimization process. Specifically: (i) one or more decision-makers are asked to rank a set of representative dam management strategies in order of preference; (ii) the ranking is used to build a preference model; and (iii) the preference model is used in an evolutionary multiobjective optimization algorithm to converge to the part of the Pareto front most preferred by the decision-makers. The inclusion of a user-friendly interaction in the optimization methodology makes the process more understandable for stakeholders and policy-makers, and it allows to address some of the key obstacles to the practical implementation of multiobjective dam management optimization, even when a large number of objectives is considered. The proposed methodology is applied to a case study (Lake Pozzillo, Sicily, Italy) with five objectives, where flood control is in contrast with irrigation water demand and hydropower production. Five simple and easy to implement optimal strategies are obtained by interacting with five decision-makers. The results are compared to the management practice currently used, indicating that the proposed approach can satisfy water demands while greatly improving flood attenuation.

Smart IoT-driven biosensors for EEG-based driving fatigue detection: A CNN-XGBoost model enhancing healthcare quality

Introduction: Drowsy driving is a significant contributor to accidents, accounting for 35 to 45% of all crashes. Implementation of an internet of things (IoT) system capable of alerting fatigued drivers has the potential to substantially reduce road fatalities and associated issues. Often referred to as the internet of medical things (IoMT), this system leverages a combination of biosensors, actuators, detectors, cloud-based and edge computing, machine intelligence, and communication networks to deliver reliable performance and enhance quality of life in smart societies. Methods: Electroencephalogram (EEG) signals offer potential insights into fatigue detection. However, accurately identifying fatigue from brain signals is challenging due to inter-individual EEG variability and the difficulty of collecting sufficient data during periods of exhaustion. To address these challenges, a novel evolutionary optimization method combining convolutional neural networks (CNNs) and XGBoost, termed CNN-XGBoost Evolutionary Learning, was proposed to improve fatigue identification accuracy. The research explored various subbands of decomposed EEG data and introduced an innovative approach of transforming EEG recordings into RGB scalograms. These scalogram images were processed using a 2D Convolutional Neural Network (2DCNN) to extract essential features, which were subsequently fed into a dense layer for training. Results: The resulting model achieved a noteworthy accuracy of 99.80% on a substantial driver fatigue dataset, surpassing existing methods. Conclusion: By integrating this approach into an IoT framework, researchers effectively addressed previous challenges and established an artificial intelligence of things (AIoT) infrastructure for critical driving conditions. This IoT-based system optimizes data processing, reduces computational complexity, and enhances overall system performance, enabling accurate and timely detection of fatigue in extreme driving environments.

Centroid opposition-based backtracking search algorithm for global optimization and engineering problems

Evolutionary algorithms (EAs) have a lot of potential to handle nonlinear and non-convex objective functions. Particularly, the backtracking search algorithm (BSA) is a popular nature-based evolutionary optimization method that has attracted many researchers due to its simple structure and efficiency in problem-solving across diverse fields. However, like other optimization algorithms, BSA is also prone to reduced diversity, local optima, and inadequate intensification capabilities. To overcome the flaws and increase the performance of BSA, this research proposes a centroid opposition-based backtracking search algorithm (CoBSA) for global optimization and engineering design problems. In CoBSA, specific individuals simultaneously acquire current and historical population knowledge to preserve population variety and improve exploration capability. On the other hand, other individuals execute the position from the current population's centroid opposition to progress convergence speed and exploitation potential. In addition, an elite process based on logistic chaotic local search was developed to improve the superiority of the current individuals. The suggested CoBSA was validated on a set of benchmark functions and then employed in a set of application examples. According to extensive numerical results and assessments, CoBSA outperformed the other state-of-the-art methods in terms of accurateness, reliability, and execution capability.

Perturbation approaches to achieving diverse and competitive designs in topology optimisation

Utilising topology optimisation to generate diverse and competitive structures enables designers to create elegant and efficient designs according to their aesthetic intuition and functional needs. This study proposes load and support perturbation approaches based on the bi-directional evolutionary structural optimisation (BESO) method to achieve diverse designs. During the optimisation process, noise is introduced to the sensitivity calculations by randomly perturbing the load angles or material properties near the supports, leading to a variety of local optima. Numerical results demonstrate that the proposed approaches are capable of creating designs with similar stiffness but distinct geometries. In addition, the diversity of the obtained solutions can be controlled by utilising different perturbation functions. This work is of significant practical importance in both architecture and engineering, where multiple design options of high structural performance are in demand.

Manifold-assisted coevolutionary algorithm for constrained multi-objective optimization

In constrained multi-objective optimization problems (CMOPs), constraints often fragment the Pareto solution space into multiple feasible and infeasible regions. This fragmentation presents a challenge for evolutionary optimization methods as feasible regions can be discrete and isolated by infeasible areas, making exploration difficult and leading to populations getting trapped in local optima. To address these issues, this paper introduces a manifold assisted coevolutionary algorithm for solving CMOPs. Firstly, a guided feasible search strategy is proposed to explore feasible regions, especially those isolated by infeasible barriers. This is achieved by estimating directions to the Constrained Pareto Set (CPS). Secondly, a manifold learning-based exploration strategy is employed to spread the population along the Pareto Set (PS) manifold by estimating the manifold distribution. Moreover, two populations are exploited, where the first population serves as the primary population, considering both constraints and objectives to explore the feasible region and search along the CPS. The second population, on the other hand, does not consider constraints and serves as an auxiliary population to explore the Unconstrained PS. By cooperating, these two populations effectively approach and cover separated CPS segments. The proposed algorithm is evaluated against seven state-of-the-art algorithms on 37 CMOP test functions and 5 CMOPs with fraudulent constraints. The experimental results clearly demonstrate that our algorithm can reliably locate multiple CPSs and is considered state-of-the-art in handling CMOPs.

Dynamic Resistance and Energy Absorption of Sandwich Beam via a Micro-Topology Optimization

The current research of sandwich structures under dynamic loading mainly focus on the response characteristic of structure. The micro-topology of core layers would sufficiently influence the property of sandwich structure. However, the micro deformation and topology mechanism of structural deformation and energy absorption are unclear. In this paper, based on the bi-directional evolutionary structural optimization method and periodic base cell (PBC) technology, a topology optimization frame work is proposed to optimize the core layer of sandwich beams. The objective of the present optimization problem is to maximize shear stiffness of PBC with a volume constraint. The effects of the volume fraction, filter radius, and initial PBC aspect ratio on the micro-topology of the core were discussed. The dynamic response process, core compression, and energy absorption capacity of the sandwich beams under blast impact loading were analyzed by the finite element method. The results demonstrated that the over-pressure action stage was coupled with the core compression stage. Under the same loading and mass per unit area, the sandwich beam with a 20% volume fraction core layer had the best blast resistance. The filter radius has a slight effect on the shear stiffness and blast resistances of the sandwich beams. But increasing the filter radius could slightly improve the bending stiffness. Upon changing the initial PBC aspect ratio, there are three ways for PBC evolution: The first is to change the angle between the adjacent bars, the second is to further form holes in the bars, and the third is to combine the first two ways. However, not all three ways can improve the energy absorption capacity of the structure. Changing the aspect ratio of the PBC arbitrarily may lead to worse results. More studies are necessary for further detailed optimization. This research proposes a new topology sandwich beam structure by micro-topology optimization, which has sufficient shear stiffness. The micro mechanism of structural energy absorption is clarified, it is significant for structural energy absorption design.

Evolutionary topology optimization of fiber reinforced composite laminates for maximum stiffness

In this study, a topology optimization technique based on the bi-directional evolutionary structural optimization (BESO) method is developed to maximize the stiffness of fiber reinforced composite laminates. The elastic properties of single-layer and multi-layer composite laminates are characterized and a composite material interpolation scheme is introduced. The effectiveness of the developed BESO method for the single-layer and multi-layer composite laminates are verified by three classical examples, namely a cantilever, a Michell-type structure, and an L-bracket. Then, based on the analysis of the topological results, a selection suggestion and verification criteria for layers with appropriately matched fiber angles are proposed and verified by two additional examples. This study proves that the BESO method is an effective technique for the topology optimization of composite laminates for maximum stiffness, and the proposed suggestion and criteria are useful for avoiding large computational costs and empirical selection of layers.

Применение эволюционных и роевых методов для оптимизации многопараметрического управления процессом нанесения гальванического покрытия

One of the key parameters of the quality of ceramic coatings is its thickness, which must meet technical requirements and provide the necessary degree of corrosion protection, wear resistance and appearance of the coating. Ensuring the uniformity of the galvanic coating is one of the most important and complex tasks of high-tech machine-building production, for which a number of methods have been proposed, such as controlling current modes, the location of electrodes in the bath, and the electrolyte flow rate. However, in most cases, these methods require solving the problem of optimal multiparametric control. Prompt and accurate optimization when changing the conditions of electrolysis (electrode potentials, composition and properties of the electrolyte), as well as, if necessary, taking into account the multi-extreme nature of the dependence of the uniformity coefficient on the process parameters (current density, interelectrode distance, electrolyte flow rate) is a rather complex and ambiguous multifactorial task that limits the use of classical methods for- the claim of a global extreme. The article explores the possibility and expediency of using intelligent heuristic methods, such as evolutionary and swarm methods, to solve this problem. Objective. The objective of this study is to determine the effectiveness of using genetic algorithms and the particle swarm method to solve the problem of optimizing the multiparametric control of the electroplating process. Materials and methods. Methods of mathematical modeling, methods and software environment of numerical modeling and optimization were used to conduct the study. Results. The article investigates the effectiveness of the application of evolutionary and swarm optimization methods in relation to the process of applying chrome plating in a galvanic bath with many anodes with multiparametric control of current density, interelectrode distance and electrolyte flow rate. The best approximation to the extreme of the uniformity coefficient can be achieved by genetic algorithms using the mutation operation and the particle swarm method, while achieving the extreme using the particle swarm method is achieved in fewer iterations. Conclusion. The results of the study substantiate the expediency of using evolutionary and swarm methods to solve the problem of optimizing the multiparametric control of the electroplating process, while it is possible to increase the efficiency of these methods due to additional tuning.

Enhancing structural stability in civil structures using the bi-directional evolutionary structural optimization method

Topology optimization techniques are increasingly utilized in structural design to create efficient and aesthetically pleasing structures while minimizing material usage. Many existing topology optimization methods may generate slender structural members under compression, leading to significant buckling issues. Consequently, incorporating buckling considerations is essential to ensure structural stability. This study investigates the capabilities of the bi-directional evolutionary structural optimization method, particularly its extension to handle multiple load cases in buckling optimization problems. The numerical examples presented focus on three classical cases relevant to civil engineering: maximizing the buckling load factor of a compressed column, performing buckling-constrained optimization of a frame structure, and enhancing the buckling resistance of a high-rise building. The findings demonstrate that the algorithm can significantly improve structural stability with only a marginal increase in compliance. The detailed mathematical modeling, sensitivity analyses, and optimization procedures discussed provide valuable insights and tools for engineers to design structures with enhanced stability and efficiency.

Multi-level guided evolution algorithm for solving fuzzy flexible job shop problem

Traditional flexible job shop scheduling problems (FJSP) are mostly limited to deterministic environments. In actual production, some uncertain factors lead to changes in job processing time. When solving multi-objective fuzzy flexible job shop scheduling problems (MOFFJSP), the existing evolutionary algorithms do not fully utilize information transfer between levels during the population evolution process. Therefore, a multi-level guided evolutionary (MLGE) optimization method is proposed to solve MOFFJSP. In the proposed MLGE method, decomposition and dominance techniques are combined to balance the diversity and convergence performance of the algorithm. Meanwhile, the idea of the Jaya algorithm approaching good individuals and distancing poor individuals is introduced. Combined with improved Jaya operator operations, it is used to guide individual evolution, preserving and inheriting solutions that perform well in terms of convergence and diversity. Finally, numerous experiments are carried out to evaluate the effectiveness of MLGE. The results show that MLGE can provide promising results for MOFFJSP. Additionally, it shows how MLGE outperforms other comparison algorithms in terms of convergence and variety of solutions.

A staged diversity enhancement method for constrained multiobjective evolutionary optimization

Optimizing the convergence and diversity of solutions simultaneously under constraints is a challenge in solving constrained multiobjective optimization problems. In existing multiobjective optimization algorithms, general diversity maintenance mechanisms have difficulty determining all optimal solutions in discrete feasible regions. This paper proposes a staged constrained multiobjective optimization algorithm with a diversity enhancement method (SDEM), which can explore potential discrete feasible regions by retaining well-distributed offspring. Specifically, after solutions have converged to optimal feasible regions by niching-based constraint dominance in the early stage, the SDEM improves the diversity of solutions through a proposed diversity enhancement dominance principle in the mid-term. Finally, the optimize objective functions and constraints of all solutions are optimized under constraint dominance to balance convergence, diversity, and feasibility during the three stages. Experiments on four well-known test suites and six real-world case studies demonstrate that the SDEM is competitive with or comparable to seven state-of-the-art constrained multiobjective evolutionary algorithms.

An Evolutionary Multitasking Ant Colony Optimization Method Based on Population Diversity Control for Multimodal Transport Problems

Multimodal transport is a challenging, NP-hard problem in combinational optimization and has been solved using evolutionary algorithms, which excel at solving large-scale problems. However, few studies have used evolutionary algorithms, particularly swarm intelligence algorithms, to concurrently handle multiple multimodal transport instances. Ant colony optimization (ACO), which is a population intelligence technique that is adept at identifying the optimal paths in graphs, has been primarily used to address tasks separately rather than concurrently. Therefore, in this study, we introduce a multipopulation-based multitask environment where task-specific populations run in parallel, and ACO serves as the optimizer for each task. A variance-based population diversity measure is then calculated to characterize the distribution differences among individuals. If the population diversity of a specific task falls below a predetermined threshold, the valuable routing traits extracted from other tasks are transferred to the stagnant population. Our method is called population diversity-controlled multitask ACO (PDMTACO). We use multiple benchmark traveling salesman problem (TSP) instances at different scales to validate the efficacy of PDMTACO. Subsequently, we extend PDMTACO to address a series of multimodal transport problems. Our experimental results demonstrate that the use of information transferred by our method significantly reduces its logistics costs and carbon emissions in all multimodal transport tasks.

An improved evolutionary structure optimization method considering stress minimization and smooth design

AbstractThe design of continuum structures often presents challenges related to stress concentration, which can cause significant structural damage. To address this issue, the current study presents a new stress minimization method that utilizes the Windowed Evolutionary Structural Optimization (WESO) framework. The method aims to improve algorithm stability by optimizing design variables with an intermediate density. The use of a P‐norm stress aggregation method improves the assessment of global stress levels and enhances computational efficiency. Furthermore, a stable element sensitivity formulation, derived from the adjoint sensitivity analysis of the global stress measure, effectively handles the nonlinear stress behavior. Mesh filtering techniques are utilized to convert sensitivity from elements to nodes, and the structural topological solution is represented using the level set function (LSF) based on element‐node sensitivity. This method addresses the singularity issue commonly found in density‐based optimization methods and facilitates the achievement of smooth topological solutions. Through 2D and 3D benchmark designs, the proposed method's feasibility, stability, and superiority are thoroughly demonstrated. A parametric study is conducted to identify the optimal parameter range for the algorithm, leading to the development of a rational method for parameter selection. The optimized topology, with its smooth boundaries, can guide the design of structures without the need for redesign or post‐processing, helping to drive innovation and development in engineering.