Design constraints verification is the most computationally expensive task in evolutionary structural optimization due to a large number of structural analyses thatmust be conducted.Building a surrogatemodel to approx...Design constraints verification is the most computationally expensive task in evolutionary structural optimization due to a large number of structural analyses thatmust be conducted.Building a surrogatemodel to approximate the behavior of structures instead of the exact structural analyses is a possible solution to tackle this problem.However,most existing surrogate models have been designed based on regression techniques.This paper proposes a novel method,called CaDE,which adopts a machine learning classification technique for enhancing the performance of the Differential Evolution(DE)optimization.The proposed method is separated into two stages.During the first optimization stage,the original DE is implemented as usual,but all individuals produced in this phase are stored as inputs of the training data.Based on design constraints verification,these individuals are labeled as“safe”or“unsafe”and their labels are saved as outputs of the training data.When collecting enough data,an AdaBoost model is trained to evaluate the safety state of structures.This model is then used in the second stage to preliminarily assess new individuals,and unpromising ones are rejected without checking design constraints.This method reduces unnecessary structural analyses,thereby shortens the optimization process.Five benchmark truss sizing optimization problems are solved using the proposed method to demonstrate its effectiveness.The obtained results show that the CaDE finds good optimal designs with less structural analyses in comparison with the original DE and four other DE variants.The reduction rate of five examples ranges from 18 to over 50%.Moreover,the proposed method is applied to a real-size transmission tower design problem to exhibit its applicability in practice.展开更多
Vanadium-based electrodes are regarded as attractive cathode materials in aqueous zinc ion batteries(ZIBs)caused by their high capacity and unique layered structure.However,it is extremely challenging to acquire high ...Vanadium-based electrodes are regarded as attractive cathode materials in aqueous zinc ion batteries(ZIBs)caused by their high capacity and unique layered structure.However,it is extremely challenging to acquire high electrochemical performance owing to the limited electronic conductivity,sluggish ion kinetics,and severe volume expansion during the insertion/extraction process of Zn^(2+).Herein,a series of V_(2)O_(3)nanospheres embedded N-doped carbon nanofiber structures with various V_(2)O_(3)spherical morphologies(solid,core-shell,hollow)have been designed for the first time by an electrospinning technique followed thermal treatments.The N-doped carbon nanofibers not only improve the electrical conductivity and the structural stability,but also provides encapsulating shells to prevent the vanadium dissolution and aggregation of V_(2)O_(3)particles.Furthermore,the varied morphological structures of V_(2)O_(3)with abundant oxygen vacancies can alleviate the volume change and increase the Zn^(2+)pathway.Besides,the phase transition between V_(2)O_(3)and Zn_XV_(2)O_(5-m)·n H_(2)O in the cycling was also certified.As a result,the as-obtained composite delivers excellent long-term cycle stability and enhanced rate performance for coin cells,which is also confirmed through density functional theory(DFT)calculations.Even assembled into flexible ZIBs,the sample still exhibits superior electrochemical performance,which may afford new design concept for flexible cathode materials of ZIBs.展开更多
With the change of geopolitical pattern of the world, pacific rim area increases economic cooperation, instead of military antagonism. After reform and open to outside world, the southern China takes in an amount of i...With the change of geopolitical pattern of the world, pacific rim area increases economic cooperation, instead of military antagonism. After reform and open to outside world, the southern China takes in an amount of investment from Hongkong, Macao and Taiwan, taking advantage of superior geo environment and thus forms a topical model of core periphery in the southern China. The core periphery model in the southern China is territorially made of three parts: core area — Hong Kong, Macao and Taiwan; peripherial area — Zhujiang delta; second core area — parts of Hunan Province, Jiangxi Province, Fujian Province and Hainan Province and Guangxi Zhuang Autonomous Region. Its evolutional stage of this model can be divided into four stages: (1) the stage of polarization of core area; (2) the stage of the second core area strongly controlled by core area; (3) the transitional stage of the second area; (4) the stage of the southern China space integrity. Taking the core periphrial model in the southern China as an integrity of interrelational and rational division, its whole functional organized system is “input product assemble output”, core area is mainly then as the managed and transported center, the second area plays a product and productive control function and becomes center of manufacturing, study and development, periphrial area constructs as the center of material and raw material and the base of agricultural and side line products. Based on the analysis of the formative structure, evolutional law and the design of territorial function, we suggust the way of territerial optimazation as follows: (1) establishing the large hinterland which takes Xijiang basin as its core; (2) construct the high and renewed technological corridor; (3) constructing stable and varied material and raw material base; (4) reinforcing the organization and adjustment and managment between core area, periphrial area and second periphrial area. (5) constucting the varied corridor among core area, the second area and perphrial area.展开更多
Due to the insufficiency of utilizing knowledge to guide the complex optimal searching, existing genetic algorithms fail to effectively solve excavator boom structural optimization problem. To improve the optimization...Due to the insufficiency of utilizing knowledge to guide the complex optimal searching, existing genetic algorithms fail to effectively solve excavator boom structural optimization problem. To improve the optimization efficiency and quality, a new knowledge-based real-coded genetic algorithm is proposed. A dual evolution mechanism combining knowledge evolution with genetic algorithm is established to extract, handle and utilize the shallow and deep implicit constraint knowledge to guide the optimal searching of genetic algorithm circularly. Based on this dual evolution mechanism, knowledge evolution and population evolution can be connected by knowledge influence operators to improve the conflgurability of knowledge and genetic operators. Then, the new knowledge-based selection operator, crossover operator and mutation operator are proposed to integrate the optimal process knowledge and domain culture to guide the excavator boom structural optimization. Eight kinds of testing algorithms, which include different genetic operators, arc taken as examples to solve the structural optimization of a medium-sized excavator boom. By comparing the results of optimization, it is shown that the algorithm including all the new knowledge-based genetic operators can more remarkably improve the evolutionary rate and searching ability than other testing algorithms, which demonstrates the effectiveness of knowledge for guiding optimal searching. The proposed knowledge-based genetic algorithm by combining multi-level knowledge evolution with numerical optimization provides a new effective method for solving the complex engineering optimization problem.展开更多
基金funded by Hanoi University of Civil Engineering(HUCE)in Project Code 35-2021/KHXD-TD.
文摘Design constraints verification is the most computationally expensive task in evolutionary structural optimization due to a large number of structural analyses thatmust be conducted.Building a surrogatemodel to approximate the behavior of structures instead of the exact structural analyses is a possible solution to tackle this problem.However,most existing surrogate models have been designed based on regression techniques.This paper proposes a novel method,called CaDE,which adopts a machine learning classification technique for enhancing the performance of the Differential Evolution(DE)optimization.The proposed method is separated into two stages.During the first optimization stage,the original DE is implemented as usual,but all individuals produced in this phase are stored as inputs of the training data.Based on design constraints verification,these individuals are labeled as“safe”or“unsafe”and their labels are saved as outputs of the training data.When collecting enough data,an AdaBoost model is trained to evaluate the safety state of structures.This model is then used in the second stage to preliminarily assess new individuals,and unpromising ones are rejected without checking design constraints.This method reduces unnecessary structural analyses,thereby shortens the optimization process.Five benchmark truss sizing optimization problems are solved using the proposed method to demonstrate its effectiveness.The obtained results show that the CaDE finds good optimal designs with less structural analyses in comparison with the original DE and four other DE variants.The reduction rate of five examples ranges from 18 to over 50%.Moreover,the proposed method is applied to a real-size transmission tower design problem to exhibit its applicability in practice.
基金supported financially by the Natural Science Foundation of Shandong Province,China(grant numbers ZR2020QE067,ZR2020QB117,and ZR2022MB143)the New Colleges and Universities Twenty Foundational Projects of Jinan City,China(grant number 2021GXRC068)+2 种基金the National Natural Science Foundation of China,China(grant number 22208174)The Scientific Research Foundation in Qilu University of Technology(Shandong Academy of Sciences),China(grant numbers 2023PY002)The Talent research project of Qilu University of Technology(Shandong Academy of Sciences),China(grant numbers 2023RCKY013)。
文摘Vanadium-based electrodes are regarded as attractive cathode materials in aqueous zinc ion batteries(ZIBs)caused by their high capacity and unique layered structure.However,it is extremely challenging to acquire high electrochemical performance owing to the limited electronic conductivity,sluggish ion kinetics,and severe volume expansion during the insertion/extraction process of Zn^(2+).Herein,a series of V_(2)O_(3)nanospheres embedded N-doped carbon nanofiber structures with various V_(2)O_(3)spherical morphologies(solid,core-shell,hollow)have been designed for the first time by an electrospinning technique followed thermal treatments.The N-doped carbon nanofibers not only improve the electrical conductivity and the structural stability,but also provides encapsulating shells to prevent the vanadium dissolution and aggregation of V_(2)O_(3)particles.Furthermore,the varied morphological structures of V_(2)O_(3)with abundant oxygen vacancies can alleviate the volume change and increase the Zn^(2+)pathway.Besides,the phase transition between V_(2)O_(3)and Zn_XV_(2)O_(5-m)·n H_(2)O in the cycling was also certified.As a result,the as-obtained composite delivers excellent long-term cycle stability and enhanced rate performance for coin cells,which is also confirmed through density functional theory(DFT)calculations.Even assembled into flexible ZIBs,the sample still exhibits superior electrochemical performance,which may afford new design concept for flexible cathode materials of ZIBs.
文摘With the change of geopolitical pattern of the world, pacific rim area increases economic cooperation, instead of military antagonism. After reform and open to outside world, the southern China takes in an amount of investment from Hongkong, Macao and Taiwan, taking advantage of superior geo environment and thus forms a topical model of core periphery in the southern China. The core periphery model in the southern China is territorially made of three parts: core area — Hong Kong, Macao and Taiwan; peripherial area — Zhujiang delta; second core area — parts of Hunan Province, Jiangxi Province, Fujian Province and Hainan Province and Guangxi Zhuang Autonomous Region. Its evolutional stage of this model can be divided into four stages: (1) the stage of polarization of core area; (2) the stage of the second core area strongly controlled by core area; (3) the transitional stage of the second area; (4) the stage of the southern China space integrity. Taking the core periphrial model in the southern China as an integrity of interrelational and rational division, its whole functional organized system is “input product assemble output”, core area is mainly then as the managed and transported center, the second area plays a product and productive control function and becomes center of manufacturing, study and development, periphrial area constructs as the center of material and raw material and the base of agricultural and side line products. Based on the analysis of the formative structure, evolutional law and the design of territorial function, we suggust the way of territerial optimazation as follows: (1) establishing the large hinterland which takes Xijiang basin as its core; (2) construct the high and renewed technological corridor; (3) constructing stable and varied material and raw material base; (4) reinforcing the organization and adjustment and managment between core area, periphrial area and second periphrial area. (5) constucting the varied corridor among core area, the second area and perphrial area.
基金supported by National Natural Science Foundation of China(Grant No.51175086)
文摘Due to the insufficiency of utilizing knowledge to guide the complex optimal searching, existing genetic algorithms fail to effectively solve excavator boom structural optimization problem. To improve the optimization efficiency and quality, a new knowledge-based real-coded genetic algorithm is proposed. A dual evolution mechanism combining knowledge evolution with genetic algorithm is established to extract, handle and utilize the shallow and deep implicit constraint knowledge to guide the optimal searching of genetic algorithm circularly. Based on this dual evolution mechanism, knowledge evolution and population evolution can be connected by knowledge influence operators to improve the conflgurability of knowledge and genetic operators. Then, the new knowledge-based selection operator, crossover operator and mutation operator are proposed to integrate the optimal process knowledge and domain culture to guide the excavator boom structural optimization. Eight kinds of testing algorithms, which include different genetic operators, arc taken as examples to solve the structural optimization of a medium-sized excavator boom. By comparing the results of optimization, it is shown that the algorithm including all the new knowledge-based genetic operators can more remarkably improve the evolutionary rate and searching ability than other testing algorithms, which demonstrates the effectiveness of knowledge for guiding optimal searching. The proposed knowledge-based genetic algorithm by combining multi-level knowledge evolution with numerical optimization provides a new effective method for solving the complex engineering optimization problem.
