Search results

Many practical control problems require achieving multiple objectives, and these objectives often conflict with each other. The existing multi-objective evolutionary reinforcement learning algorithms cannot achieve good search results when solving such problems. It is necessary to design a new multi-objective evolutionary reinforcement learning algorithm with a stronger searchability.

The multi-objective reinforcement learning algorithm proposed in this paper is based on the evolutionary computation framework. In each generation, this study uses the long-short-term selection method to select parent policies. The long-term selection is based on the improvement of policy along the predefined optimization direction in the previous generation. The short-term selection uses a prediction model to predict the optimization direction that may have the greatest improvement on overall population performance. In the evolutionary stage, the penalty-based nonlinear scalarization method is used to scalarize the multi-dimensional advantage functions, and the nonlinear multi-objective policy gradient is designed to optimize the parent policies along the predefined directions.

The penalty-based nonlinear scalarization method can force policies to improve along the predefined optimization directions. The long-short-term optimization method can alleviate the exploration-exploitation problem, enabling the algorithm to explore unknown regions while ensuring that potential policies are fully optimized. The combination of these designs can effectively improve the performance of the final population.

A multi-objective evolutionary reinforcement learning algorithm with stronger searchability has been proposed. This algorithm can find a Pareto policy set with better convergence, diversity and density.

The prolonged training time of the neural network (NN) has sparked considerable debate regarding their application in the field of optimization. The purpose of this paper is to explore the beneficial assistance of NN-based alternative models in inductance design, with a particular focus on multi-objective optimization and uncertainty analysis processes.

Under Gaussian-distributed manufacturing errors, this study predicts error intervals for Pareto points and select robust solutions with minimal error margins. Furthermore, this study establishes correlations between manufacturing errors and inductance value discrepancies, offering a practical means of determining permissible manufacturing errors tailored to varying accuracy requirements.

The NN-assisted methods are demonstrated to offer a substantial time advantage in multi-objective optimization compared to conventional approaches, particularly in scenarios where the trained NN is repeatedly used. Also, NN models allow for extensive data-driven uncertainty quantification, which is challenging for traditional methods.

Three objectives including saturation current are considered in the multi-optimization, and the time advantages of the NN are thoroughly discussed by comparing scenarios involving single optimization, multiple optimizations, bi-objective optimization and tri-objective optimization. This study proposes direct error interval prediction on the Pareto front, using extensive data to predict the response of the Pareto front to random errors following a Gaussian distribution. This approach circumvents the compromises inherent in constrained robust optimization for inductance design and allows for a direct assessment of robustness that can be applied to account for manufacturing errors with complex distributions.

This study aims to address the inherent uncertainties within closed-loop supply chain (CLSC) networks through the application of a multi-objective approach, specifically focusing on the optimization of integrated production and transportation processes. The primary purpose is to enhance decision-making in supply chain management by formulating a robust multi-objective model.

In dealing with uncertainty, this study uses Pythagorean fuzzy numbers (PFNs) to effectively represent and quantify uncertainties associated with various parameters within the CLSC network. The proposed model is solved using Pythagorean hesitant fuzzy programming, presenting a comprehensive and innovative methodology designed explicitly for handling uncertainties inherent in CLSC contexts.

The research findings highlight the effectiveness and reliability of the proposed framework for addressing uncertainties within CLSC networks. Through a comparative analysis with other established approaches, the model demonstrates its robustness, showcasing its potential to make informed and resilient decisions in supply chain management.

This study successfully addressed uncertainty in CLSC networks, providing logistics managers with a robust decision-making framework. Emphasizing the importance of PFNs and Pythagorean hesitant fuzzy programming, the research offered practical insights for optimizing transportation routes and resource allocation. Future research could explore dynamic factors in CLSCs, integrate real-time data and leverage emerging technologies for more agile and sustainable supply chain management.

This research contributes significantly to the field by introducing a novel and comprehensive methodology for managing uncertainty in CLSC networks. The adoption of PFNs and Pythagorean hesitant fuzzy programming offers an original and valuable approach to addressing uncertainties, providing practitioners and decision-makers with insights to make informed and resilient decisions in supply chain management.

The purpose of this paper is to introduce a double-stator switched reluctance machine (DS-SRM) for electric vehicles (EVs) and to propose multi-mode operations for this machine.

Analysis of flux linkage distributions and torque characteristics using finite element method (FEM). Building a dynamic simulation model based on electromagnetic characteristics, mathematical equations and mechanical motion equations of the DS-SRM drive system. The paper proposes multi-mode operations (inner-stator excitation mode, outer-stator excitation mode and double-stator excitation mode) based on motor working regions. It also conducts simulation and experimental results to verify the effectiveness of the proposed multi-mode operations strategies and control schemes.

There is almost no electromagnetic coupling between the inner and outer stators due to the specially designed rotor structure and optimized windings polarity configuration. Analysis of flux linkage distributions and torque characteristics verified the independence of inner and outer stators. Proposal of multi-mode operations and corresponding control rules achieved the smooth switching between different modes.

The paper introduced the DS-SRM for EVs and proposed multi-mode operations, along with control rules, to optimize its performance. The specially designed rotor structure, optimized winding polarity configuration, and the proposed multi-mode operations contribute to the originality of the research.

This paper aims to study the influence of cylindrical texture parameters on the lubrication performance of static and dynamic pressure thrust bearings (hereinafter referred to as thrust bearings) and to optimize their lubrication performance using multiobjective optimization.

The influence of texture parameters on the lubrication performance of thrust bearings was studied based on the modified Reynolds equation. The objective functions are predicted through the BP neural network, and the texture parameters were optimized using the improved multiobjective ant lion algorithm (MOALA).

Compared with smooth surface, the introduction of texture can improve the lubrication properties. Under the optimization of the improved algorithm, when the texture diameter, depth, spacing and number are approximately 0.2 mm, 0.5 mm, 5 mm and 34, respectively, the loading capacity is increased by around 27.7% and the temperature is reduced by around 1.55°C.

This paper studies the effect of texture parameters on the lubrication properties of thrust bearings based on the modified Reynolds equation and performs multiobjective optimization through an improved MOALA.

Untimely responses to emergency situations in urban areas contribute to a rising mortality rate and impact society's primary capital. The efficient dispatch and relocation of ambulances pose operational and momentary challenges, necessitating an optimal policy based on the system's real-time status. While previous studies have addressed these concerns, limited attention has been given to the optimal allocation of technicians to respond to emergency situation and minimize overall system costs.

In this paper, a bi-objective mathematical model is proposed to maximize system coverage and enable flexible movement across bases for location, dispatch and relocation of ambulances. Ambulances relocation involves two key decisions: (1) allocating ambulances to bases after completing services and (2) deciding to change the current ambulance location among existing bases to potentially improve response times to future emergencies. The model also considers the varying capabilities of technicians for proper allocation in emergency situations.

The Augmented Epsilon-Constrained (AEC) method is employed to solve the proposed model for small-sized problem. Due to the NP-Hardness of the model, the NSGA-II and MOPSO metaheuristic algorithms are utilized to obtain efficient solutions for large-sized problems. The findings demonstrate the superiority of the MOPSO algorithm.

This study can be useful for emergency medical centers and healthcare companies in providing more effective responses to emergency situations by sending technicians and ambulances.

In this study, a two-objective mathematical model is developed for ambulance location and dispatch and solved by using the AEC method as well as the NSGA-II and MOPSO metaheuristic algorithms. The mathematical model encompasses three primary types of decision-making: (1) Allocating ambulances to bases after completing their service, (2) deciding to relocate the current ambulance among existing bases to potentially enhance response times to future emergencies and (3) considering the diverse abilities of technicians for accurate allocation to emergency situations.

Nature’s evolution has shaped intelligent behaviors in creatures like insects and birds, inspiring the field of Swarm Intelligence. Researchers have developed bio-inspired algorithms to address complex optimization problems efficiently. These algorithms strike a balance between computational efficiency and solution optimality, attracting significant attention across domains.

Bio-inspired optimization techniques for feature engineering and its applications are systematically reviewed with chief objective of assessing statistical influence and significance of “Bio-inspired optimization”-based computational models by referring to vast research literature published between year 2015 and 2022.

The Scopus and Web of Science databases were explored for review with focus on parameters such as country-wise publications, keyword occurrences and citations per year. Springer and IEEE emerge as the most creative publishers, with indicative prominent and superior journals, namely, PLoS ONE, Neural Computing and Applications, Lecture Notes in Computer Science and IEEE Transactions. The “National Natural Science Foundation” of China and the “Ministry of Electronics and Information Technology” of India lead in funding projects in this area. China, India and Germany stand out as leaders in publications related to bio-inspired algorithms for feature engineering research.

The review findings integrate various bio-inspired algorithm selection techniques over a diverse spectrum of optimization techniques. Anti colony optimization contributes to decentralized and cooperative search strategies, bee colony optimization (BCO) improves collaborative decision-making, particle swarm optimization leads to exploration-exploitation balance and bio-inspired algorithms offer a range of nature-inspired heuristics.

Pre-positioning and distributing relief items are important parts of disaster management as it simultaneously considers activities from both pre- and post-disaster stages. This study aims to address this problem with a novel mathematical model.

In this research, a bi-objective mixed-integer linear programming model is developed to tackle pre-positioning and distributing relief items, and it is formulated as an integrated location-allocation-routing problem with uncertain parameters. The humanitarian supply chain consists of relief facilities (RFs) and demand points (DPs). Perishable and imperishable relief commodities (RCs), different types of vehicles, different transportation modes, a time window for delivering perishable commodities and the occurrence of unmet demand are considered. A scenario-based game theory is applied for purchasing RCs from different suppliers and an integrated best-worst method-technique for order of preference by similarity to ideal solution technique is implemented to determine the importance of DPs. The proposed model is used to solve several random test problems for verification, and to validate the model, Iran’s flood in 2019 is investigated as a case study for which useful managerial insights are provided.

Managers can effectively adjust their preferences towards response time and total cost of the network and use sensitivity analysis results in their decisions.

The model locates RFs, allocates DPs to RFs in the pre-disaster stage, and determines the routing of RCs from RFs to DPs in the post-disaster stage with respect to minimizing total costs and response time of the humanitarian logistics network.

The six-axis force/torque sensor based on a Y-type structure has the advantages of simple structure, small space volume, low cost and wide application prospects. To meet the overall structural stiffness requirements and sensor performance requirements in robot engineering applications, this paper aims to propose a Y-type six-axis force/torque sensor.

The performance indicators such as each component sensitivities and stiffnesses of the sensor were selected as optimization objectives. The multiobjective optimization equations were established. A multiple quadratic response surface in ANSYS Workbench was modeled by using the central composite design experimental method. The optimal manufacturing structural parameters were obtained by using multiobjective genetic algorithm.

The sensor was optimized and the simulation results show that the overload resistance of the sensor is 200%F.S., and the axial stiffness, radial stiffness, bending stiffness and torsional stiffness are 14.981 kN/mm, 16.855 kN/mm, 2.0939 kN m/rad and 6.4432 kN m/rad, respectively, which meet the design requirements, and the sensitivities of each component of the optimized sensor have been well increased to be 2.969, 2.762, 4.010, 2.762, 2.653 and 2.760 times as those of the sensor with initial structural parameters. The sensor prototype with optimized parameters was produced. According to the calibration experiment of the sensor, the maximum Class I and II errors and measurement uncertainty of each force/torque component of the sensor are 1.835%F.S., 1.018%F.S. and 1.606%F.S., respectively. All of them are below the required 2%F.S.

Hence, the conclusion can be drawn that the sensor has excellent comprehensive performance and meets the expected practical engineering requirements.

This study aims to investigate the daily performance of the proposed microgrid (MG) that comprises photovoltaic, wind turbines and is connected to the main grid. The load demand is a residential area that includes 20 houses.

The daily operational strategy of the proposed MG allows to vend and procure utterly between the main grid and MG. The smart metre of every consumer provides the supplier with the daily consumption pattern which is amended by demand side management (DSM). The daily operational cost (DOC) CO2 emission and other measures are utilized to evaluate the system performance. A grey wolf optimizer was employed to minimize DOC including the cost of procuring energy from the main grid, the emission cost and the revenue of sold energy to the main grid.

The obtained results of winter and summer days revealed that DSM significantly improved the system performance from the economic and environmental perspectives. With DSM, DOC on winter day was −26.93 ($/kWh) and on summer day, DOC was 10.59 ($/kWh). While without considering DSM, DOC on winter day was −25.42 ($/kWh) and on summer day DOC was 14.95 ($/kWh).

As opposed to previous research that predominantly addressed the long-term operation, the value of the proposed research is to investigate the short-term operation (24-hour) of MG that copes with vital contingencies associated with selling and procuring energy with the main grid considering the environmental cost. Outstandingly, the proposed research engaged the consumers by smart meters to apply demand-sideDSM, while the previous studies largely focused on supply side management.