Non-dominated Sorting Genetic Algorithm III Research Articles

Design of 20 MW direct‐drive permanent magnet synchronous generators for wind turbines based on constrained many‐objective optimization

AbstractThis study introduces a constrained many‐objective optimization approach for the optimal design of 20 MW direct drive (DD) permanent magnet synchronous generators (PMSGs). Designing a high‐performance, competitive DD‐PMSG requires considering the generator's performance as well as its weight and material cost. Therefore, we focus on four main characteristics as our design objectives: (1) specific power (power per weight), (2) power‐per‐cost, (3) efficiency, and (4) power factor. To achieve this, we apply an advanced constrained nondominated sorting genetic algorithm III (NSGA‐III), a many‐objective optimization method utilizing evolutionary computation, capable of optimizing four or more objectives with constraints. Additionally, the electromagnetic finite element method is employed to evaluate the generator's characteristics. Through our proposed design process, we optimize three distinct 20 MW DD‐PMSG configurations: a 320‐pole/300‐slot, a 350‐pole/300‐slot, and a 350‐pole/336‐slot topology. Following this optimization, we perform additional multiphysics simulations (covering electromagnetic, structural, overload, and thermal aspects) and control response simulations on four selected models from the Pareto‐optimal solutions to validate their effectiveness as preliminary DD‐PMSG designs. Finally, we conduct a comprehensive analysis of all simulation results.

Uncertain programming model for designing multi-objective reverse logistics networks

Given the contradiction between the rapid growth of products and the modest recovery rate of end-of-life products, there is a pressing need to understand the societal significance of establishing a reverse logistics network for end-of-life products. This research constructs an open-loop five-tier reverse logistic network model encompassing customers, centres for collection, disassembly and inspection, remanufacturing, and disposal. A multi-objective mixed-integer nonlinear programming model under uncertainty has been developed. Unlike previous research, this model accounts for surrounding residents' disutility of facilities while simultaneously minimising economic costs and environmental impact. Besides, uncertainty theory is introduced in solving the proposed model. More specifically, the formulated model converts all uncertain variables into uncertain distributions by implementing the uncertain multi-objective programming method. Furthermore, a customised non-dominated sorting genetic algorithm III (NSGA-III) is proposed and is employed for the first time to address facility selection and recycling volume distribution within the network. The model is then validated using a real-life case study focusing on end-of-life vehicles in Changchun, China. This research could assist decision-makers in both governmental and private sectors in achieving a balanced approach to the interests of the economy, environment, and local communities comprehensively when designing reverse supply chains.

Elite Multi-Criteria Decision Making—Pareto Front Optimization in Multi-Objective Optimization

Optimization is a process of minimizing or maximizing a given objective function under specified constraints. In multi-objective optimization (MOO), multiple conflicting functions are optimized within defined criteria. Numerous MOO techniques have been developed utilizing various meta-heuristic methods such as Evolutionary Algorithms (EAs), Genetic Algorithms (GAs), and other biologically inspired processes. In a cooperative environment, a Pareto front is generated, and an MOO technique is applied to solve for the solution set. On other hand, Multi-Criteria Decision Making (MCDM) is often used to select a single best solution from a set of provided solution candidates. The Multi-Criteria Decision Making–Pareto Front (M-PF) optimizer combines both of these techniques to find a quality set of heuristic solutions. This paper provides an improved version of the M-PF optimizer, which is called the elite Multi-Criteria Decision Making–Pareto Front (eMPF) optimizer. The eMPF method uses an evolutionary algorithm for the meta-heuristic process and then generates a Pareto front and applies MCDM to the Pareto front to rank the solutions in the set. The main objective of the new optimizer is to exploit the Pareto front while also exploring the solution area. The performance of the developed method is tested against M-PF, Non-Dominated Sorting Genetic Algorithm-II (NSGA-II), and Non-Dominated Sorting Genetic Algorithm-III (NSGA-III). The test results demonstrate the performance of the new eMPF optimizer over M-PF, NSGA-II, and NSGA-III. eMPF was not only able to exploit the search domain but also was able to find better heuristic solutions for most of the test functions used.

Evaluation of the Best Management Practices for Reducing Phosphorus Load in a Watershed in Terms of Cost and Greenhouse Gas Emissions

Effective management of water quality in watersheds is crucial because it is directly linked to the sustainability of aquatic ecosystems. In conventional watershed management, best management practices (BMPs) have been instrumental in addressing deteriorating water quality issues caused by non-point source pollution. Greenhouse gas (GHG) emissions have emerged as a global concern, necessitating immediate and diverse environmental actions to mitigate their impacts. This study aims to explore BMPs that maximize total phosphorus (TP) load removal efficiencies, while minimizing costs and GHG emissions within watersheds, using the Soil and Water Assessment Tool (SWAT) and non-dominated sorting genetic algorithm III (NSGA-III). The Yeongsan River Watershed between 2012 and 2021 was selected as the study area. Hydrological and BMP data were analyzed. Applying identical BMPs to the watershed showed that the BMPs with high TP removal efficiency may not be effective in terms of cost and GHG emissions. Therefore, the optimal combination of BMPs for the Yeongsan River Watershed was determined using NSGA-III considering TP removal efficiency, cost, and GHG emissions. This study is the first to consider GHG emissions at the watershed level when applying BMPs and is expected to contribute to the development of BMP implementation incorporating GHG emissions.

Cooperative constrained multi-objective dual-population evolutionary algorithm for optimal dispatching of wind-power integrated power system

Due to increasing uncertainty and multiple operational requirements of current power system, it brings great challenge to power dispatch of wind-power integrated power system. To address above problems, a cooperative constrained multi-objective dual-population evolutionary algorithm (CCMDEA) is proposed with uncertainty budget of wind power, which divides the intermittent power into different intervals with flexible uncertain parameters. On the basis of non-dominated sorting genetic algorithm III (NSGA-III), constraint violation (CV) is also involved to guide the population evolution combined with two defined populations: convergence population (CP) and diversity population (DP) to coordinate convergence and diversity performance of pareto-fronts, and a coordinated selection mechanism is designed to select suitable parents according to the state of evolutionary population, which can coordinate the convergence population and diversity population well. According to simulation results on two test systems, the efficiency and priority of the proposed algorithm is well verified, which also reveals that the proposed algorithm can be a viable way for solving power dispatching of wind-power integrated power system.

Developing a hybrid system for stock selection and portfolio optimization with many-objective optimization based on deep learning and improved NSGA-III

Portfolio management is a critical aspect of investment strategies, with the goal to balance the low-risk and high-return investments. Despite this, existing portfolios frequently overlook the integration of stock selection outcomes and underutilize data from listed companies, leading to suboptimal portfolio performance. Addressing these shortcomings, this paper introduces a hybrid system involving stock selection and portfolio optimization. In stock selection, the system employs a combination of convolutional neural network and bi-directional recurrent neural network to predict stock trends. This approach enables the identification of stocks likely to appreciate in value, setting the stage for their inclusion in the subsequent optimization process. For portfolio optimization, the study formulates a five-objective optimization problem that incorporates mean, variance, skewness, kurtosis, and distance-to-default as key considerations. To solve the many-objective constrained optimization problem, an advanced strategy employing a static penalty function and an improved Non-dominated Sorting Genetic Algorithm III (NSGA-III) based on tent chaotic mapping is utilized. The efficacy of the proposed hybrid system is rigorously tested through three sets of ablation experiments alongside two discussions focused on its robustness and computational efficiency. The findings from these investigations reveal that the hybrid system outperforms traditional approaches, reducing risks and improving returns for investors.

Multi-Objective Optimization of Tasks Scheduling Problem for Overlapping Multiple Tower Cranes

The scheduling of tower crane operations is a complex process. Overlapping areas between tower cranes often lead to increased collision possibilities, resulting in additional tower crane operation complexity. Single objectives related to time or economic aspects were always considered in dealing with this issue, which neglected other objectives and the relationships between different objectives. Therefore, this article proposes a novel method for the schedule of prefabricated component lifting tasks on the construction site, integrating the multi-objective optimization model with the decision-making method with the aim of minimizing energy consumption costs and minimizing the amplitude of the costs among multiple tower cranes. A non-dominated sorting genetic algorithm-III (NSGA-III) written in Python is used as the multi-objective optimization algorithm—which considers the selection of tasks for each tower crane and the order of lifting for each tower crane and technique for order preference by similarity to an ideal solution (TOPSIS), and is applied as the decision-making method for ranking the Pareto front. Then, a green construction production and education integration training building construction project located in Jinan, China is used as the case study to verify that the method is practical and reasonable. The results show that conflicts can be effectively avoided, energy consumption costs reduced, and equipment utilization increased by rationally distributing lifting tasks among multiple overlapping tower cranes. And among the top 11 solutions, the lifting tasks and priorities for tower crane 1 are close to the same. In contrast, the task lifting for tower crane 2 was assigned based on the balance of the energy consumption costs of the two tower cranes. The discovery of this article is helpful to eliminate collisions, interference, and frequent start and stop of several tower cranes, so as to realize the safe, stable, and efficient operation of the construction site.

Design principle, 4E analyses and optimization for onboard CCS system under EEDI framework: A case study of an LNG-fueled bulk carrier

With the accelerated implementation of Energy Efficiency Design Index (EEDI) phase 3 by the International Maritime Organization, shipping carbon reduction is urgently required. This paper explores the possibility to develop the onboard carbon capture and storage (OCCS) system unstraints between EEDI phases 3 and 4. The OCCS is particularly established with the utilization of exhaust gas waste heat and LNG cold energy. The proposed OCCS system is modelled in Aspen HYSYS, laying the foundation for energy, exder the EEDI framework. The OCCS system design principle for an LNG-fueled bulk carrier is determined with the conergy, economic and environment analyses. Furthermore, the multi-objective optimization is based on the energy and exergy efficiency of OCCS system (ηen,OCCS × ηen,OCCS), payback period (PBP) and metric of carbon capture efficiency degree (MCCED) by non-dominated sorting genetic algorithm-Ⅲ. The Pareto frontier indicates that the system is in optimal operation with the exhaust gas mass flow rate of 29,990 kg/h and the liquid-to-gas ratio of 1.04. The carbon capture is 1048.0 kg/h, which is 70.74% over EEDI phase 3 requirements. The optimized ηen,OCCS × ηen,OCCS is 2.92%, the PBP is 13.03 years and the MCCED is 23.00%. This study provides an important basis for the maritime post-combustion carbon reduction compliance.

Sustainable and Resilient Land Use Planning: A Multi-Objective Optimization Approach

Land use allocation (LUA) is of prime importance for the development of urban sustainability and resilience. Since the process of planning and managing land use requires balancing different conflicting social, economic, and environmental factors, it has become a complex and significant issue in urban planning worldwide. LUA is usually regarded as a spatial multi-objective optimization (MOO) problem in previous studies. In this paper, we develop an MOO approach for tackling the LUA problem, in which maximum economy, minimum carbon emissions, maximum accessibility, maximum integration, and maximum compactness are formulated as optimal objectives. To solve the MOO problem, an improved non-dominated sorting genetic algorithm III (NSGA-III) is proposed in terms of mutation and crossover operations by preserving the constraints on the sizes for each land use type. The proposed approach was applied to KaMavota district, Maputo City, Mozambique, to generate a proper land use plan. The results showed that the improved NSGA-III yielded better performance than the standard NSGA-III. The optimal solutions produced by the MOO approach provide good trade-offs between the conflicting objectives. This research is beneficial for policymakers and city planners by providing alternative land use allocation plans for urban sustainability and resilience.

A Coupled Parameter Automation Calibration Module for Urban Stormwater Modelling

In the context of accelerating urbanisation, the issue of urban stormwater flooding security has garnered increasing attention. Further development of urban stormwater management techniques is imperative to achieve more stable, precise, and expeditious simulation outcomes. The calibration of model parameters, which is a pivotal phase in stormwater simulation endeavours, is hampered by challenges such as substantial subjectivity, time intensiveness, and low efficiency. Therefore, this study introduces a parameter calibration model coupled with the Non-dominated Sorting Genetic Algorithm III (NSGA-III). This model utilises the Nash–Sutcliffe efficiency (NSE) and peak relative error (PE) values for various rainfall events as objective functions to calibrate and assess the study target. The two rainfalls used for rate determination had NSE values greater than 0.9 and absolute PE values less than 0.17; the rainfall used for validation had NSE values greater than 0.9 and absolute PE values less than 0.27. Thus, the results of the model for the rate determination of the parameters are reliable. In addition, the inverted generation distance and hypervolume values indicate that the iterative process of the algorithm during population evolution demonstrated stable iterative outcomes and ensured sound population quality. Both reach relative stability after 40 iterations. In conclusion, the proposed multi-objective parameter calibration model integrated with NSGA-III offers dependable calibration results and robust computational efficacy, presenting novel avenues and perspectives for urban stormwater model parameter calibration and simulation.

A BIM-integrated multi objective optimization model for sustainable building construction management

Purpose The construction industry is tasked with creating sustainable, efficient and cost-effective buildings. This study aims to develop a building information modeling (BIM)-based multiobjective optimization (MOO) model integrating the nondominated sorting genetic algorithm III (NSGA-III) to enhance sustainability. The goal is to reduce embodied energy and cost in the design process. Design/methodology/approach Through a case study research method, this study uses BIM, NSGA-III and real-world data in five phases: literature review, identification of factors, BIM model development, MOO model creation and validation in the architecture, engineering and construction sectors. Findings The innovative BIM-based MOO model optimizes embodied energy and cost to achieve sustainable construction. A commercial building case study validation showed a reduction of 30% in embodied energy and 21% in cost. This study validates the model’s effectiveness in integrating sustainability goals, enhancing decision-making, collaboration, efficiency and providing superior assessment. Practical implications This model delivers a unified approach to sustainable design, cutting carbon footprint and strengthening the industry’s ability to attain sustainable solutions. It holds potential for broader application and future integration of social and economic factors. Originality/value The research presents a novel BIM-based MOO model, uniquely focusing on sustainable construction with embodied energy and cost considerations. This holistic and innovative framework extends existing methodologies applicable to various buildings and paves the way for additional research in this area.

Joint optimal operation of the South-to-North Water Diversion Project considering the evenness of water deficit

Abstract. Inter-basin water transfer projects are the main measure to address the water deficit crisis caused by uneven distribution of water resources. The current water transfer operation mainly tends to be present in areas with small water transfer costs and is prone to encounter the problem of spatial and temporal imbalances in water allocation. To address these issues, this paper defines a water deficit evenness index (WDEI), aimed at minimizing regional differences in water scarcity and sharing the pressure of water scarcity as a social demand objective. This index is incorporated into a joint optimization model for the Jiangsu section of the South-to-North Water Diversion Project (J-SNWDP), which comprises both the ecological objective of the total water deficit (TWD) and the economic objective of the pumping water (PW). Further, the Nondominated Sorting Genetic Algorithm III (NSGA-III) and multi-attribute decision-making were applied to solve the model and obtain an optimal operation strategy. The results showed the following: (1) the WDEI defined in this paper can mitigate the synchronized water scarcity in certain water users. In typical normal years (wet year and dry year), the WDEI shows a reduction of 94.2 % (81.8 %, 76.7 %) compared to the historical operation strategy. (2) The optimized operation strategy can significantly reduce TWD and PW by 82.06% (37.69 %, 52.36 %) and 45.13 % (3.25 %, 21.51 %) compared with the historical values, respectively, which can improve the water supply satisfaction and reduce the project cost. At the same time, the lake storage capacity of the optimal operation strategy performs well, and the water transfer efficiency of the river is significantly improved. (3) In this paper, targeted optimal operation strategies and potential ways to secure the project tasks are proposed for different natural flow. Overall, it is of great significance to study the water supply equity in the J-SNWDP to alleviate the concentrated water deficit in Jiangsu Province and other similar regions.

Multisource information fusion for real-time optimization of shield construction parameters

This paper introduces a hybrid intelligent framework that combines Bayesian optimization (BO), a random forest (RF) model, and the nondominated sorting genetic algorithm-III (NSGA-III) for the optimization and control of tunnel shield construction parameters. The BO-RF method establishes a nonlinear mapping function between the input variables and three targets, surface settlement, cutter wear, and advance speed, serving as the fitness function for NSGA-III. Model interpretability analysis is conducted using Shapley Additive ExPlanations (SHAP). A multiobjective intelligent optimization model is formulated with NSGA-III, targeting surface settlement, cutter wear, and advance speed. A case study validates the applicability and effectiveness of this approach, leading to the following conclusions: (1) The BO-RF algorithm yields highly accurate prediction results, with R2 values ranging from 0.930 to 0.938, RMSE ranging from 0.138 to 0.172, and MAE ranging from 0.112 to 0.138 for the three targets. (2) The optimization results for surface settlement, cutter wear, and advance speed are outstanding, with an average improvement of 12.56 %. The simultaneous adjustment of the three shield construction parameters leads to the best optimization results, with an average improvement of 19.67 %. (3) The energy consumption of the shield drive system decreases by an average of 10.70 %, and the optimization improvement for the first three objectives decreases by an average of 1.82 %, 1.46 %, and 2.23 %, respectively. By introducing the integrated BO-RF-NSGA-III algorithm, this study contributes to the field of tunnel engineering optimization management.

Multi-objective ship weather routing method based on the improved NSGA-III algorithm

This study investigates a multi-objective weather routing problem for ships, aiming to minimize operational costs, sailing time, and CO2 emissions simultaneously. Departing from conventional graph search algorithms based on nodes, we incorporate the ship's operational context, utilizing heading angle and speed as direct variables. Employing the Non-Dominated Sorting Genetic Algorithm III (NSGA-III) to solve the above problem, we observed convergence difficulties due to the traditional random initial population strategy. To address this, an improved NSGA-III is proposed, generating the initial population based on a route from a combination of sampling and the A* algorithm. The proposed method is applied to routes in the North Atlantic and the North Pacific, revealing that, compared to the commonly used A* and 3D Dijkstra methods, it can achieve over a 1.5 % reduction in ship operating costs, surpassing 6 % in certain scenarios. Additionally, we conducted an analysis of set coverage and inverted generational distance. The findings indicate that the improved NSGA-III algorithm exhibits superior convergence and diversity compared to the traditional NSGA-III algorithm.

Ship pipe route design based on NSGA-III and multi-population parallel evolution

Ship pipe route design (SPRD) aims to generate pipe layouts while considering various objectives and constraints in a confined 3D space, leading to extremely high complexity. To solve the problem of SPRD, traditional methods often adopt weighted summation of sub-objectives, introduce penalty functions to convert it to a single-objective optimization problem. However, these methods tend to yield a single optimal pipe route design pattern, and some existing multi-objective pipe routing algorithms do not have high search performance or sufficient treatment of constraints. Based on the grid-space decomposition model, this paper establishes a multi-objective pipe routing optimization model with several sub-objectives including path length, bends number, path energy, number of air-pockets, and number of violated bending distance, which also considers pipe routing for different diameters and interface direction requirements. A ship pipe route design framework based on the NSGA-III (Non-dominated Sorting Genetic algorithm III) is proposed, and its embedded pathfinding algorithm can explore pipe route using heuristic information and failure retry strategy, which greatly reduces the algorithm complexity compared to the classical algorithms such as A* and LEE and also facilitates parallel implementation. By employing OpenMP technology to achieve parallel evolution of multiple populations, more Pareto optimal solutions can be obtained in approximately the same timeframe as single population evolution. Finally, through comparative experiments using simulated cases, the feasibility and advancement of the proposed method are verified.

Many-objective coevolutionary learning algorithm with extreme learning machine auto-encoder for ensemble classifier of feedforward neural networks

In artificial neural network (ANN) learning, empirical risk can be expressed by training error, while structural risk can be expressed by network complexity. Learning from data is often seen as a tradeoff between these two risks. Additionally, balancing training error and validation error can overcome the overfitting problem to some extent. It is known that the network performance is also related to regularization term. In order to consider four factors, i.e. training error, validation error, network complexity and regularization term simultaneously in the training process of a single-hidden layer feedforword neural network (SLFN), a many-objective coevolutionary learning algorithm (MOCELA) integrated with extreme learning machine auto-encoder (ELMAE), called MOCELA-ELMAE is presented. In MOCELA, the non-dominated sorting genetic algorithm III (NSGA-III) is improved for handling the many-objective optimization model with hybrid variables, where binary coding is used for structure learning and real coding is utilized for representing input parameters, referring to all input weights and hidden biases of the AE network. Output parameters of AE, i.e. output weights are analytically calculated by the non-iterative learning rule. The network structure and connection parameters of SLFN are determined based on those of AE. A set of Pareto optimal solutions are eventually collected by the MOCELA-ELMAE, which represents multiple optimal SLFNs. To make the final decision, three best SLFNs with minimum validation errors are selected as the base classifiers for selective ensemble learning. Extensive experiments are implemented on the benchmark classification data sets of UCI machine learning repository, and obvious improvements have been observed when the proposed MOCELA-ELMAE is compared with the NSGA-III based on hybrid coding and completely non-iterative learning of SLFN respectively. The experimental results also illustrate that the MOCELA-ELMAE performs much better than other state-of-the-art learning algorithms on many data sets.

GPU-accelerated non-dominated sorting genetic algorithm III for maximizing protein production

<abstract><p>Maximizing protein expression levels poses a major challenge in bioengineering. To increase protein expression levels, numerous factors, including codon bias, codon context bias, hidden stop codons, homologous recombination, suitable guanine-cytosine ratio, and hairpin loop structure, are crucial and quantified by six objective functions: CAI, CPB, HSC, HD, GC3, and SL. Optimizing these six objectives simultaneously constitutes a multi-objective optimization problem, aiming to identify the favorable Pareto solutions rather than a singular optimal solution. However, achieving satisfactory solutions requires numerous cycles and solutions, thus leading to a large number of functional evaluations. While there are frameworks for multi-objective optimization problems, they often lack efficient support for objective function computation in protein encoding. In this paper, we proposed a method to design a set of coding sequences (CDSs) based on non-dominated sorting genetic algorithm III (NSGA-III), accelerated using NVIDIA graphical processing units (GPUs). Experimental results indicated that our method is 15,454 times faster than the Pymoo framework and is evaluated using 100 solutions and 100 cycles. Since our GPU implementation facilitated the use of larger solutions and more cycles, we were able to design a superior set of CDSs by increasing solutions to 400 and cycles to 12,800. In addition, our NSGA-III-based method consistently surpassed the NSGA-II approach when the number of cycles exceeded 3200 by utilizing 100 solutions. Finally, we observed that a gradual reduction of the mutation probability as the number of cycles increased yielded better quality results than maintaining a fixed mutation probability.</p></abstract>

Hybrid Flow Shop Scheduling Problem with Energy Utilization using Non-Dominated Sorting Genetic Algorithm-III (NSGA-III) Optimization

Hybrid flow shop scheduling (HFS) is an on sought problem modelling for production manufacturing. Due to its impact on productivity, researchers from different backgrounds have been attracted to solve its optimum solution. The HFS is a complex dilemma and provides ample solutions, thus inviting researchers to propose niche optimization methods for the problem. Recently, researchers have moved on to multi-objective solutions. In real-world situations, HFS is known for multi-objective problems, and consequently, the need for optimum solutions in multi-objective HFS is a necessity. Regarding sustainability topic, energy utilization is mainly considered as one of the objectives, including the common makespan criteria. This paper presents the existing multi-objective approach for solving energy utilization and makespan problems in HFS scheduling using Non-Dominated Sorting Genetic Algorithm-III (NSGA-III), and a comparison to other optimization models was subjected for analysis. The model was compared with the most sought algorithm and latest multi-objective algorithms, Strength Pareto Evolutionary Algorithm 2 (SPEA -II), Multi-Objective Algorithm Particle Swarm Optimization (MOPSO), Pareto Envelope-based Selection Algorithm II (PESA-II) and Multi-objective Evolutionary Algorithm based on Decomposition (MOEA/D). The research interest starts with problem modelling, followed by a computational experiment with an existing multi-objective approach conducted using twelve HFS benchmark problems. Then, a case study problem is presented to assess all models. The numerical results showed that the NSGA-III obtained 50% best overall for distribution performance metrics and 42% best in convergence performance metrics for HFS benchmark problems. In addition, the case study results show that NSGA-III obtained the best overall convergence and distribution performance metrics. The results show that NSGA-III can search for the best fitness solution without compromising makespan and total energy utilization. In the future, these multi-objective algorithms’ potential can be further investigated for hybrid flow shop scheduling problems.

Optimization of agricultural planting structure in irrigation areas of Heilongjiang province considering the constraints of water resource system resilience

From the perspective of sustainable development in irrigation areas, imperfect constraints, which have negatively impacted previous agricultural planting structure optimization models, tend to produce unreasonable optimization results. Thus, in this paper, attempts are made to incorporate the resilience of water resource systems into the constraint set and explore the optimal layout of agricultural planting structures in irrigation areas. We selected 12 sample irrigation areas in Heilongjiang Province, China, including Chahayang, Fuyu, and Tailai, as the research areas and considered their actual situations. Then, we established a multiobjective optimization model for an agricultural planting structure with rice, soybean, and corn planting areas as decision variables; socioeconomic benefits, agricultural production benefits, ecological benefits, and water resource benefits as objective functions; and water resource system resilience and net crop output value and other factors as constraints. Fifteen scenarios were assessed through the combination of objective functions, and the nondominated sorting genetic algorithm III (NSGA-III) was used to optimize and analyze the agricultural planting structure of typical irrigation areas in Heilongjiang Province and to determine the optimal planting plan. The research results found that the function values adjusted by planting area have significantly improved compared to those before optimization. The adjustment trend of agricultural planting area is to increase the planting area of rice and soybean and reduce the planting area of corn. The introduction of constraints on water resource system resilience ensures that other benefits remain basically unchanged; thus, the water resource objective function is significantly better with resilience constraints than without them. Therefore, water resource system resilience can act as an effective constraint; this finding enriches and expands the theoretical and methodological system for optimizing the management of agricultural planting structures in irrigation areas and thus provides important technological support for ensuring regional food security, ecological security, and water security, which has substantial practical significance.

Multi-objective optimization of gradient gas diffusion layer structures for enhancing proton exchange membrane fuel cell performance based on response surface methodology and non-dominated sorting genetic algorithm-III

The gas diffusion layer structure has a significant impact on water and gas transport in proton exchange membrane fuel cell (PEMFC). In this study, a multi-objective optimization (MOO) method is applied to optimize the PEMFC gas diffusion layer (GDL) structures for performance enhancement. Nine design parameters are studied to analyses the output performance of the fuel cell and the average water content of the membrane, oxygen concentration non-uniformity, power density and system efficiency are used as performance indexes. The MOO forms the response surface regression model based on the three-dimensional numerical model of PEMFC, and the response surface methodology after processing through the non-dominated sorting genetic algorithm-III (NSGA-III) to obtain the Pareto frontier, and prioritizes the best operating conditions and structures based on technique for order preference by similarity to an ideal solution (TOPSIS). Compared with the reference point, the performance indexes of the decision point obtained by the NSGA-III algorithm and TOPSIS algorithm is enhanced by 0.45 %, 42.06 %, 2.99 % and 0.25 %, respectively. This study presents a new multi-objective optimization method for optimizing operating conditions combine with GDL structures for building efficient PEMFC, which provides a solution for achieving higher performance. The optimal results in this paper can provide some guidance for fuel cell performance improvement and control optimization.