Multi-objective Function Research Articles

Runway Configuration Assistance: Offline Reinforcement Learning Method for Air Traffic Management

Runway configuration management deals with the optimal selection of runways and their direction of operation for aircraft arrivals and departures. The configurations are chosen based on the traffic, surface winds, and other meteorological conditions that are complex to model and difficult to predict. In this paper, we develop the runway configuration assistance tool, an automated approach based on offline model-free reinforcement learning (RL) that provides decision support for air traffic controllers (ATCOs). The proposed tool processes historical data of interest, including decisions made regarding the runway configuration, and their subsequent outcome, to identify a policy that encourages good decisions. The policy search is guided by an appropriately chosen weighted multi-objective utility function (e.g., based on maximizing traffic throughput, minimizing transit times on the surface of the airport, and mitigating safety issues such as go-arounds). The proposed tool is validated using data from two major U.S. airports based on performance metrics developed in collaboration with subject matter experts and is compared against several baseline approaches such as the most frequent configuration chosen by ATCOs, supervised learning, and other RL-based approaches.

Deep contextual bandits-based energy-efficient beamforming for integrated sensing and communication

In this paper, a transmit beamforming design is considered to jointly improve the communication and sensing functionalities in an integrated sensing and communication (ISAC) system, where a dual-functional base station (BS) serves a set of communication users (UEs) while sensing some potential targets (TGs). To this end, a multi-objective beamforming optimization problem is formulated to maximize the weighted linear combination of the communication energy efficiency (EE) and sensing beampattern gains. Using the normalized weighted sum method, the multi-objective problem is relaxed to a single-objective problem. For dealing with the non-convexity nature of the considered problem and the continuity of the beamforming space, a novel deep contextual bandits (DCB) scheme inspired by the soft actor-critic (S-DCB) method is proposed in which the channel state information of UEs is used as the context. Both the reward and policy functions are approximated to solve the problem. Simulation results indicate that the multi-objective function enables an adjustable trade-off between the communication and sensing functionalities. Besides, the effectiveness of the proposed S-DCB algorithm is verified through a comprehensive comparison with the state-of-the-art DCB-DDPG and the upper bound benchmarks.

Research on Cooperative Arrival and Energy Consumption Optimization Strategies of UAV Formations

The formation operation of unmanned aerial vehicles (UAVs) is a current research hotspot, particularly in specific mission scenarios where UAV formations are required to cooperatively arrive at designated task areas to meet the needs of coordinated operations. This paper investigates the issues of cooperative arrival and energy consumption optimization for UAV formations in such scenarios. First, focusing on rotorcraft UAVs, the flight energy consumption optimization model and cooperative arrival model are derived and constructed. Next, to address the challenges in solving these models, the multi-objective non-convex functions are transformed into single-objective continuous functions, thereby reducing computational complexity. Furthermore, an interior-point-method-based solving strategy is designed by estimating the initial values of the solving parameters. Finally, simulation experiments validate the feasibility and effectiveness of the proposed method. The experimental results show that when optimizing the energy consumption of a formation of five UAVs, the algorithm converges in just 16 iterations, demonstrating its suitability for practical applications.

Analysis of athletes’ technical action based on deep learning

In order to raise athletes’ technical proficiency and overall performance, this paper uses deep learning technology to precisely assess table tennis technical activities. The paper builds a hybrid neural network model for technical action analysis of table tennis players, based on Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) in deep learning. First, CNN extracts the spatial characteristics from the video frames. After that, an LSTM processes these data in a time series to accurately recognize and classify the movements of athletes. Lastly, through trials, the model is trained and evaluated using the Table Tennis Tracking Network (TTNET) dataset. The experimental findings demonstrate that: (1) In table tennis technical action analysis, the suggested deep learning model performs better than other comparative models. The efficacy of combining convolution with sequence learning is fully demonstrated by the CNN-LSTM hybrid model, which performs best in all indicators when compared to the CNN, LSTM, Multi-Objective Function (MOF), and Convolutional Neural Network—Long Short-Term Memory (CNN-LSTM) combined models. Its accuracy rate, precision rate, recall rate, and F1 score are 0.923, 0.918, 0.925, and 0.921, respectively. In contrast, the performances of LSTM and CNN are also excellent, but the performance of MOF model is relatively low; (2) In the classification of technical actions, the model has the highest classification accuracy of service, reaching 0.930, and the classification accuracy of other technical actions such as forehand stroke, backhand stroke and spike is also above 0.9, and the time sequence consistency index also maintains a high level, indicating that the model can effectively identify and analyze table tennis technical actions. In addition, the performance evaluation of real-time feedback shows that the model can achieve low processing time and feedback delay in video data processing with different lengths, which ensures the real-time and reliability in practical applications. These results show that the proposed model can not only provide accurate technical action recognition, but also provide timely and effective feedback in practical application, which has high practical value. The results of this paper prove the potential of deep learning technology in the analysis of athletes’ technical actions, and provide scientific basis and effective tools for the technical training and optimization of table tennis players.

Modified Tasmanian devil optimization for solving single and multi-objective optimal power flow in conventional and advanced power systems

This paper presents two modified versions of the Tasmanian Devil Optimization (TDO) for dealing with the optimal power flow (OPF) problem in both conventional and advanced power systems. The original TDO is enhanced with two distinct constraint handling techniques: weighted factors (WF) in addition to the superiority of feasible solutions (SF).The two developed algorithms (TDO-WF and TDO-SF) are applied to tackle both single and multi-objective functions of the OPF problem. Two test systems are used for verifying the two developed algorithms in different case studies. The first test system is the IEEE-30 bus system in its conventional form, while the second system is an advanced version of the IEEE-30 bus system that contains three distinct sorts of renewable energy plants and a variable load. The MATLAB software is used for simulation purposes. The two developed algorithms overcame the problem of violating the system’s constraints in the original TDO and achieved better results than alternative approaches in the related research. A statistical analysis and a Wilcoxon signed rank test are carried out to define the best one of the two developed techniques. The results of the two suggested techniques are quite similar, and we verified the validity of both of them to tackle the OPF problem in both conventional and advanced power systems.

Optimal sizing and placement of STATCOM, TCSC and UPFC using a novel hybrid genetic algorithm-improved particle swarm optimization

The increase in global power demand has caused most of today's power networks to become overloaded especially in Sub-Saharan Africa. The increased load demand can be met through expansion of existing generation and transmission system. However, construction of new power infrastructure is limited by financing and technical constraints. Thus, power networks have been left to operate at overload conditions with high power losses and many power quality (PQ) problems. Flexible AC Transmission System (FACTS) devices can improve the power transfer capability of the existing transmission networks without the need of constructing new power infrastructure. In this paper, a multi-objective function comprising of minimization of power loss (PL), voltage deviation (VD) and operational cost (OC) was formulated and solved using a novel algorithm. A novel Genetic Algorithm-Improved Particle Swarm Optimization (GA-IPSO) technique is proposed in this paper for optimization of size and location of FACTS devices. Static Synchronous Compensator (STATCOM), Thyristor Controlled Series Capacitor (TCSC) and Unified Power Flow Controller (UPFC) are the three FACTS devices considered. The proposed technique was validated using IEEE-33 Bus Test System, which is a popular benchmark Radial Distribution System (RDS). The three FACTS devices were optimized separately and also in a combined manner. Under the separate optimization, the size and location of individual FACTS devices were optimized. For combined optimization, the sizes and locations of more than one device were optimized in the same test system. For separate optimization, UPFC produced the best results by reducing the active power losses by 38.44 % and OC from $1.59×105 to $ 1.15×105. Under the combined optimization, combination of TCSC, STATCOM and UPFC gave better results by achieving active power loss reduction of 56.09 % and reducing OC from $1.59×105 to $ 1.03×105. Comparison of GA-IPSO technique with other algorithms such as Particle Swarm Optimization (PSO), Genetic Algorithm (GA), Improved Grey Wolf Optimization (IGWO) and Differential Evolution Algorithm (DEA) showed that the proposed hybrid technique was superior and more efficient in solving the FACTS optimization problem.

A varied-width path planning method for multiple AUV formation

Multiple autonomous underwater vehicle (AUV) systems are widely used for various ocean missions. With the continuous improvement of formation control capabilities, path planning performance has gradually become an essential factor limiting the efficiency of AUV formations. To ensure the optimality of formation trajectories under different circumstances, this paper proposes a varied-width A* (VWA*) algorithm for global path planning of multiple AUV formations. Different from the conventional methods that consider formation control and global path planning separately or focus on solving fixed-formation path planning problems, VWA* searches for optimal navigation schemes composed of collision-free paths and formation control scenarios. In the presented strategy, an additional dimension related to formation structure is added to the state space, and the state space is constructed according to the environment and the predefined available formations. Then, with a multi-objective function applied to guide the searching process, VWA* searches in the state space in a manner similar to conventional A*. Moreover, a path generation method based on VWA* is proposed to plan paths for each AUV in the formation. In numerical simulations, the path quality of VWA* is validated in comparison with the optimal global fixed-width path. The performance of varied-formation AUV formation trajectories is compared with fixed-formation trajectories guided by state-of-the-art path planning algorithms. The results demonstrate that VWA* can effectively ensure the optimality of the navigation schemes, and the varied-formation path planning outperforms various fixed-formation path planning techniques. Finally, a test is conducted to verify the feasibility of the proposed methods further.

Performance comparison of battery cold plates designed using topology optimization across laminar and turbulent flow regime

Liquid cooling with cold plates offers an efficient solution for battery thermal management. However, conventional cold plates in turbulent regime often result in inadequate temperature uniformity within battery modules and generate significant pressure drops. In this study, we employ the turbulent conjugate heat transfer topology optimization method based on the k-ε turbulent model for cold plate design. Then we derive two novel cold plate designs based on the laminar and turbulent topology optimization method, respectively, and the effectiveness of the two design methods are compared. A multi-objective function which minimizes pressure drop and average temperature is established to balance the thermal and hydraulic performance of the cold plates. The electrochemical-thermal coupled model is utilized to simulate heat production of the battery pack. The fluid flow and heat transfer performance of turbulent topology-optimized cold plate (TTCP) during constant rate discharging is analyzed and compared with that of laminar topology-optimized cold plate (LTCP), serpentine cold plate (SCP), and rectangular cold plate (RCP). Numerical simulation results show that TTCP gives the best overall cooling results among all the designs despite a slight disadvantage against LTCP at very low flow rates. At high-speed turbulent flow (8.488 × 10−2 kg/s), the performance evaluation criterion (PEC) number improvements for TTCP, LTCP, and SCP compared with RCP are 86.7 %, 78.5 %, and 85.4 %, respectively. Hence, cold plate topology optimization using turbulent conditions and methods is recommended for power battery systems, especially those with fast charging/discharging requirements.

Optimal allocation of electric vehicle charging stations and distributed generation in radial distribution networks

The widespread spread of electric vehicles requires the establishment of charging stations (EVCSs), and this is considered a large load on the network. This gives priority to distributing the stations in a way that reduces the load on the network, and in parallel, re-planning the network and supplying it with the necessary energy to maintain energy efficiency and power quality. Total energy loss minimization, voltage deviation minimization, and voltage stability index improvement are the considered power quality indices in the multi-objective function. Vehicle to grid (V2G) feature, distributed generation units (DG), and capacitor banks are used for improving system performance, by injecting the required active and reactive power. In addition, the initial and running costs of V2G, DG units, and capacitor banks are considered in the multi-objective function. The optimal sizing and allocation of charging stations, V2G, DG units, and capacitor banks are performed using a proposed Self-Adaptive Multi-Population Elitist JAYA (SAMPE-JAYA) algorithm and checked using the genetic algorithm (GA). The proposed algorithm is tested using various scenarios, two standard IEEE test systems. To emphasize the effectiveness and applicability of the proposed algorithm, it is applied on a real-world distribution system. To accommodate the optimal allocation of EVCS, which constitute 80.7 % and 78.9 % of the base active load for the IEEE 33 and 69 bus systems, respectively. Integrating DG amounting to 17.35 % and 18.25 % of the base load is necessary. Additionally, capacitor banks, contributing 36.84 % and 31.166 % of the reactive power load, are also required for effective voltage support and system reliability in each respective case.

Optimal operation of the smart electrical network considering energy management of demand side

The smart electrical grid represents a significant advancement in generating, distributing, and consuming electricity. This sophisticated system integrates modern technology and communication tools to enhance energy management efficiency and improve demand costuming within the power network. In this paper, optimal operation of the electrical network with energy management and demand response program (DRP) is implemented. The implementation of the optimal operation is done via multi-stage and multi-objective functions modeling. The DRP modeling is done in first stage to optimal management of consumption in demand side. In second stage, operating cost, emission, power losses and voltage profile are optimized as multi-objective functions modeling with attention to optimal management of consumption in demand side. The solving optimal operation of the electrical network is carried out by using elephant herding optimization (EHO). This problem is implemented on 33-bus test system with hybrid energy resources. Finally, DRP leads to reducing costs, emissions and losses and improving voltage profile in proposed electrical network. Hence, operation costs, emission, power losses, and voltage deviation with the participation of DRP are minimized by 39.15%, 9.94%, 33.35%, and 30.73%, respectively. On the other side, voltage stability is enhanced by 3.66% without considering DRP.

Introducing fairness in network visualization

Motivated by the need for decision-making systems that avoid bias and discrimination, the concept of fairness recently gained traction in the broad field of artificial intelligence, stimulating new research also within the information visualization community. In this paper, we introduce a notion of fairness in network visualization, specifically for orthogonal and for straight-line drawings of graphs, two foundational paradigms in the field. We investigate the following research questions: (i) What is the price, in terms of global readability, of incorporating fairness constraints in graph drawings? (ii) How unfair is a graph drawing that does not optimize fairness as a primary objective? We present both theoretical and empirical results. In particular, we design and implement two optimization algorithms for multi-objective functions, one based on an ILP model for orthogonal drawings, and one based on gradient descent for straight-line drawings. In a nutshell, we experimentally show that it is possible to significantly increase the fairness of a drawing by paying a relatively small amount in terms of reduced global readability. Also, we present a use case in which we qualitatively evaluate our approach on a practical scenario.

Dynamic power allocation for the new energy hybrid hydrogen production system based on WOA-VMD: Improving fluctuation balance and optimizing control strategy

The new energy hydrogen production system is subject to intermittent fluctuations, which compromise efficiency and equipment lifespan. This study proposes a new dynamic power allocation and control strategy for hybrid hydrogen production systems. By using the Whale Algorithm Optimized Variable Modal Decomposition (WOA-VMD), the fluctuating power of new energy is quantitatively decomposed and reconstructed. Based on a multi-objective optimization function, low-frequency variation components and high-frequency fluctuation components are accurately allocated between alkaline electrolyzers (ALK) and proton exchange membrane electrolyzers (PEM). The strategy effectively improves the source-load balancing capability, reducing the low-frequency fluctuation rate by 60% and reducing the high-frequency power amplitude by 70%, significantly reducing the operational demands on ALK electrolyzers, the capacity requirements of PEM electrolyzers, and the need for energy storage configuration, while also increasing hydrogen production efficiency by 7%. Compared to existing methods, the strategy has a transparent analysis process, strong interpretability, and good data reusability, making it valuable for engineering applications.

Simultaneous optimization approach for UV-C radiator to enhance mechanical properties of semi-finished potato tuber (Innovator) for extended storage period

The efficacy of surface treatment technology is highly dependent on the dimensional and operational parameters. UV-C as a commonly used surface treatment technology required fine-tuning to achieve maximum storability of semi-finished products. This study therefore applied a simultaneous optimization approach for the multi-objective function to obtain the best possible combination of variables in the irradiation process (dose (15–45mJ/cm2, storage period (3–9d), and distance from the light (40–80 cm)) that offer maintained properties of semi-finished potato tuber for extended storage life. The optimum values are obtained at the ∼40.5mJ/cm2, 7 days, and 48 cm granting a 756 N, 6.7 N, and 9 N for compressive, bending, and cutting force resistance, respectively. Further insight into the surface functionality was studied using FT-IR and SEM analysis as a result similar spectral makeup was noted but a shift of absorption peak was observed in the irradiated sample at 30 and 45mJ/cm2. Also, a similar granular structure was observed from the morphologies.

Optimizing grid-dependent and islanded network operations through synergic active-reactive power integration

DG integration improves distribution network performance and also enables microgrid (MG) formation for islanded operation. However, existing studies assume an isolated operation approach for islanded mode, which is unrealistic and increases overall system costs while adding complexity to the grid. This paper presents a dual-stage methodology for the efficient operation of distributed generation (DG) and shunt capacitor banks (SCBs) in radial distribution networks (RDNs) for both grid-integrated and islanded modes. The first stage proposes an improved Jaya algorithm (IJaya) to optimize DG and SCB allocation during grid-connected operation, aiming to reduce power loss and improve voltage profiles. IJaya employs a dynamic weight-based grid search to address premature convergence. The second stage formulates a multiobjective function for the islanded operation to minimize power loss and underutilization of DG-SCB capacity. Case studies on IEEE 33- and 69-bus RDNs show IJaya reduces power loss by 38.84 % and improves voltage by 3.26 % in grid-connected networks compared to existing methods. The proposed analytical approach for islanded operation tunes the source power factor, reducing DG-SCB underutilization by up to 15.83 % for power factors between 0.8 and 0.93. The results demonstrate that operating distributed resources near optimal capacities meets a larger portion of the island network's energy needs.

ExAq-MSPP: An Energy-Efficient Mobile Sink Path Planning Using Extended Aquila Optimization Algorithm

Wireless sensor networks play a crucial role in gathering data from remote or hard-to-reach locations, enabling real-time monitoring and decision-making in a wide range of industries and applications. The mobile sink path planning (MSPP) enables mobile sinks (e.g., drones or rovers) to navigate through the environment, collecting data from different sensor nodes, ensuring comprehensive coverage, and adaptively addressing changing conditions. Still, the energy-efficient routing with minimal delay is the challenging aspect. This research focuses on improving data gathering in wireless sensor networks by introducing an efficient routing protocol. In this proposed protocol, sensor nodes are initially deployed using Voronoi diagrams to ensure uniform network coverage. The network is then divided into clusters using the low-energy adaptive clustering hierarchy (LEACH) algorithm for energy-efficient routing. To optimize the path planning of a mobile sink for data collection, we introduce the extended Aquila (ExAq) optimization algorithm, which uses a multi-objective fitness function considering factors such as delay, residual energy, link quality, priority, and distance. Simulation results demonstrate the effectiveness of the proposed ExAq-MSPP protocol in terms of reduced delay, improved network lifetime, higher packet delivery ratio, enhanced residual energy, and increased throughput compared to existing protocols with the values of 1.169, 99.857, 99.920, 0.997, and 255.306, respectively. Thus, the energy-efficient routing and optimizing path planning for mobile sinks, the proposed ExAq-MSPP protocol can extend network lifetime, increase data accuracy, and provide more robust performance under changing environmental conditions.

Design and Test of a Traction Side-Pull Square Straw Bale Pick-Up-and-Stack Truck

To address the issues of limited one-time loading capacity, single functionality, and low automation level in existing square straw bale pickers, a large automated square straw bale pick-up-and-stack truck that integrates picking, stacking, transporting, and bundling functions has been developed, combining the technical advantages of one-time field removal and storage of bales. We innovatively designed a side-pulling traction mechanism that can realize the rapid transition between the transporting state and working state of the machine; a picking device that can complete the continuous action of forking, lifting, turning positioning, and de-forking; and a bundling device that can realize the adjustment of the attitude of square straw bales. Response surface tests were conducted on the prototype to determine the key structural and operational parameters, using the bundle completion rate and regular bale rate as evaluation indicators. Regression and significance tests were performed on the machine’s forward speed, chassis frame offset, and the ground clearance of the fork tine to determine the influence and priority of these factors on the evaluation indicators. Through multi-objective function optimization of the regression model, the optimal parameter combination was found to be a machine forward speed of 15.5 km/h, a chassis frame offset of 2126 mm, and a fork tine ground clearance of 225 mm, resulting in a bundle completion rate of 98.85% and a regular bale rate of 96.96%. Subsequent field tests with the optimized parameters showed that at a machine forward speed of 15.5 km/h, a chassis frame offset of 2126 mm, and a fork tine ground clearance of 225 mm, the bundle completion rate was 98.37% and the regular bale rate was 95.83%, meeting the relevant design requirements. This study can provide a reference for the design and development of straw collection and storage machinery.

Dynamic energy management and control of networked microgrids based on load to grid services and incentive-based demand response programs: A multi-agent deep reinforcement learning approach

This study has presented the energy management paradigm in a networked microgrid structure based on L2G services and considering incentive-based load response (IBDR) programs and energy market requirements to reduce operating costs, control and restore voltage and frequency index, providing the benefits of subscribers and distribution system operators. In this study, multi-objective functions such as optimal operation based on IBDR structure and energy market requirements, risk assessment, and L2G service approach are configured in the framework of central and local controllers. Optimal operation and risk assessment are analyzed by a multi-task learning algorithm based on multi-objective function and L2G service policies are evaluated based on multi-agent deep reinforcement learning. Control policies are sent by the communication system to the components affecting the optimal power distribution as well as the voltage and frequency controllers. L2G services have been evaluated in different scenarios such as plug-and-play operating conditions, load fluctuations, and operating in island mode. The results of optimal operation based on L2G services show that the IBDR program implementation reduces the total operation cost by 21%. Also, the total operating cost of the proposed framework is 13.97% less than the RL method and 27.8% less than the ANN method.

Techno-Economic Analysis of Hybrid Pv-Battery-Diesel Power System for Rural Electrification: A Case Study of Ibudo Ora, Ogbomoso

Fossil-fueled generators and electrical grid extensions are the most popular energy sources for supplying electricity to rural areas. However, the high cost of running and maintenance, noise pollution, and a need for decarbonization necessitate the hybridization of different energy sources as a viable solution. Using the conventional technique for the optimal design of a Hybrid Power System (HPS), such as the Hybrid of Multiple Energy Resources (HOMER), is inefficient regarding electricity cost and carbon emission reduction. Hence, this research conducted a technical and economic analysis of an optimal photovoltaic (PV), battery, and diesel generator-based power system to electrify Ibudo Ora, a rural community in Ogbomoso. A feasibility study on electricity demand was conducted on the Ibudo Ora community by conducting an onsite survey, and the community load profile was estimated. Mathematical modeling of the HPS component was formulated. A multi-objective function was developed to minimize the Net Present Cost (NPC), Levelized Cost of Electricity (LCOE), and Total Carbon Emission (TCE) and maximize the System Reliability (SR) of the proposed HPS and optimized using the Energy Valley Optimizer (EVO). MATLAB R2021a was used to simulate the developed model. The performance of the developed EVO-based HPS was evaluated using NPC, LCOE, TCE, and SR as metrics and compared with HOMER, which was used for the same purpose. The NPC of the developed EVO-based HPS and HOMER-based HPS were $998702.87 and $1011984.27, respectively, while the LCOE were $0.4889 and $0.4954. The loss of power supply probabilities of the developed EVO-based and HOMER-based HPS was zero, while in terms of TCE, EVO-based HPS and HOMER-based HPS had 775958.15 kg and 832912.49 kg, respectively. The results showed an appreciable reduction in the NPC, LCOE, and TCE using EVO compared with HOMER for an optimized HPS. This research will assist the government, investors, and policymakers in making decisions on rural electrification using HPS.

Effect of surface square textures on the physical field of static and dynamic pressure thrust bearings and multi-objective optimization

PurposeThe lubrication performance of static and dynamic pressure thrust bearings is improved by introducing texture on the sealing edge.Design/methodology/approachThrough model building, meshing and boundary condition setting, the influence of square texture on oil film lubrication performance was simulated and analyzed, and an improved algorithm was applied to perform optimization of lubrication performance.FindingsThe findings of this study reveal that the optimum lubrication performance is attained when adjusting the parameters of the square texture to 0.12 mm, 0.1 mm, 1 mm and 34 mm. In such circumstances, the thrust bearing with square textures demonstrates an increase in loading capacity of around 19% and a temperature reduction of about 2ºC compared to a smooth thrust bearing.Originality/valueThe original Reynolds equation is revised, and the influence of square texture on the physical field of oil film is analyzed, considering the turbulence state and cavitation phenomenon. The multi-objective function under square texture parameters was established using BP neural network, and the improved multi-objective salp swarm algorithm was used to optimize the process parameters.

Multi-objective optimization of switched reluctance motor driving electric vehicles based on vehicle operating condition

To improve the comprehensive performance of the switched reluctance motor (SRM) for electric vehicles (EVs) under actual driving conditions, a novel geometrical optimization method based on the time-varying phase current characteristics and the comprehensive indicator with justified weight coefficients is proposed in this paper. First, based on the established dynamic models of EV and SRM, the actual operating phase currents of the motor working under the New European Driving Cycle (NEDC) are extracted and classified to develop the representative optimization conditions. Then, considering the requirements of EV, five indicators are defined to evaluate the comprehensive performance of SRM, and a new multi-objective synchronization optimization function is proposed with five weight coefficients obtained by the statistical analysis method for the sample data of the indicators. Furthermore, the geometrical optimization for a four-phase 8/6 SRM is carried out by the combination of Particle Swarm Optimization (PSO) and BP neural network algorithms, after analyzing the effects of key geometrical parameters on the indicators. Finally, the work performance of the optimized SRM is evaluated and compared with that of the initial prototype, and the results show that the optimized SRM with the proposed multi-objective synchronization optimization method can improve the comprehensive indicator by 59.59%, and can significantly enhance the vehicle actual working economy by 50.74% under NEDC cycle.