As far as the present state is concerned in detecting the behavioral pattern of humans(subject)using morphological image processing,a considerable portion of the study has been conducted utilizing frontal vision data ...As far as the present state is concerned in detecting the behavioral pattern of humans(subject)using morphological image processing,a considerable portion of the study has been conducted utilizing frontal vision data of human faces.The present research work had used a side vision of human-face data to develop a theoretical framework via a hybrid analytical model approach.In this example,hybridization includes an artificial neural network(ANN)with a genetic algorithm(GA).We researched the geometrical properties extracted from side-vision human-face data.An additional study was conducted to determine the ideal number of geometrical characteristics to pick while clustering.The close vicinity ofminimum distance measurements is done for these clusters,mapped for proper classification and decision process of behavioral pattern.To identify the data acquired,support vector machines and artificial neural networks are utilized.A method known as an adaptiveunidirectional associative memory(AUTAM)was used to map one side of a human face to the other side of the same subject.The behavioral pattern has been detected based on two-class problem classification,and the decision process has been done using a genetic algorithm with best-fit measurements.The developed algorithm in the present work has been tested by considering a dataset of 100 subjects and tested using standard databases like FERET,Multi-PIE,Yale Face database,RTR,CASIA,etc.The complexity measures have also been calculated under worst-case and best-case situations.展开更多
The stochastic paralld gradient descent （SPGD） algorithm is widely used in wavefront sensor-less adaptive optics （WSAO） systems. However, the convergence is relatively slow. Modal-based algorithms usually provide ...The stochastic paralld gradient descent （SPGD） algorithm is widely used in wavefront sensor-less adaptive optics （WSAO） systems. However, the convergence is relatively slow. Modal-based algorithms usually provide much faster convergence than SPGD; however, the limited actuator stroke of the deformable mirror （DM） often prohibits the sensing of higher-order modes or renders a closed-loop correction inapplicable. Based on a comparative analysis of SPGD and the DM-modal-based algorithm, a hybrid approach involving both algorithms is proposed for extended image-based WSAO, and is demonstrated in this experiment. The hybrid approach can achieve similar correction results to pure SPGD, but with a dramatically decreased iteration number.展开更多
The problem of maximizing system reliability through component reliability choices and component redundancy is called tell-ability-redundancy allocation problem （RAP）, and it is a difficult but realistic nonlinear m...The problem of maximizing system reliability through component reliability choices and component redundancy is called tell-ability-redundancy allocation problem （RAP）, and it is a difficult but realistic nonlinear mixed-integer optimization prob- lem. For the RAP. we pay attention to an improved particle swarm optimization （IPSO）, and introduce four hybrid approaches for combining the IPSO with other conventional search techniques, such as harmony search （HS） and LXPM （a real coded GA）. The basic structure of the hybrid approaches includes two phases. After devising an initial solution by the HS or LXPM technique in the first phase, the IPSO performs an optimal search in the next phase. In addition, a new procedure by using golden search, named GS, is developed for further improving the solutions obtained by IPSO. Consequently, four ISPO-based hybrid approaches are proposed including HS-IPSO, LXPM-IPSO, HS-IPSO-GS, and LXPM-IPSO-GS. In order to validate the per-formance of proposed approaches, five nonlinear mixed-integer RAPs are investigated where both the number of re- dundancy components and the corresponding component reliability in each subsystem are to be decided simultaneously. As shown, the proposed approaches are all superior in terms of both optimal solutions and robustness to those by IPSO. Especially the pro-posed LXPM-IPSO-GS has shown more excellent performance than other typical approaches in the literature.展开更多
Based on the domain reduction idea and artificial boundary substructure method,this paper proposes an FK-FEM hybrid approach by integrating the advantages of FK and FEM(i.e.,FK can efficiently generate high-frequency ...Based on the domain reduction idea and artificial boundary substructure method,this paper proposes an FK-FEM hybrid approach by integrating the advantages of FK and FEM(i.e.,FK can efficiently generate high-frequency three translational motion,while FEM has rich elements types and constitutive models).An advantage of this approach is that it realizes the entire process simulation from point dislocation source to underground structure.Compared with the plane wave field input method,the FK-FEM hybrid approach can reflect the spatial variability of seismic motion and the influence of source and propagation path.This approach can provide an effective solution for seismic analysis of underground structures under scenario of earthquake in regions where strong earthquakes may occur but are not recorded,especially when active faults,crustal,and soil parameters are available.Taking Daikai subway station as an example,the seismic response of the underground structure is simulated after verifying the correctness of the approach and the effects of crustal velocity structure and source parameters on the seismic response of Daikai station are discussed.In this example,the influence of velocity structure on the maximum interlayer displacement angle of underground structure is 96.5%and the change of source parameters can lead to the change of structural failure direction.展开更多
Building prototyping has regularly been used in building performance analyses with statistically feasible models.The novelty of this research involves a new hybrid approach combining stratified sampling and k-means cl...Building prototyping has regularly been used in building performance analyses with statistically feasible models.The novelty of this research involves a new hybrid approach combining stratified sampling and k-means clustering to establish building geometry prototypes.The research focuses on residential buildings in Ningbo,China.Seventeen small residential districts(SRDs)containing 367 residential buildings were systemically selected for survey and data collection.The stratified sampling used building construction year as the main parameter to generate stratification.Floor numbers,shape coefficients,floor areas,and window-to-wall ratios were used as the four observations for k-means clustering.Based on this new approach,nine building geometry prototypes were identified and modelled.These statistically representative prototypes provide building geometrical information and characteristic-based evaluations for subsequent building performance analysis.展开更多
Purpose-Software defect prediction(SDP)is a critical aspect of software quality assurance,aiming to identify and manage potential defects in software systems.In this paper,we have proposed a novel hybrid approach that...Purpose-Software defect prediction(SDP)is a critical aspect of software quality assurance,aiming to identify and manage potential defects in software systems.In this paper,we have proposed a novel hybrid approach that combines Grey Wolf Optimization with Feature Selection(GWOFS)and multilayer perceptron(MLP)for SDP.The GWOFS-MLP hybrid model is designed to optimize feature selection,ultimately enhancing the accuracy and efficiency of SDP.Grey Wolf Optimization,inspired by the social hierarchy and hunting behavior of grey wolves,is employed to select a subset of relevant features from an extensive pool of potential predictors.This study investigates the key challenges that traditional SDP approaches encounter and proposes promising solutions to overcome time complexity and the curse of the dimensionality reduction problem.Design/methodology/approach-The integration of GWOFS and MLP results in a robust hybrid model that can adapt to diverse software datasets.This feature selection process harnesses the cooperative hunting behavior of wolves,allowing for the exploration of critical feature combinations.The selected features are then fed into an MLP,a powerful artificial neural network(ANN)known for its capability to learn intricate patterns within software metrics.MLP serves as the predictive engine,utilizing the curated feature set to model and classify software defects accurately.Findings-The performance evaluation of the GWOFS-MLP hybrid model on a real-world software defect dataset demonstrates its effectiveness.The model achieves a remarkable training accuracy of 97.69%and a testing accuracy of 97.99%.Additionally,the receiver operating characteristic area under the curve(ROC-AUC)score of 0.89 highlights themodel’s ability to discriminate between defective and defect-free software components.Originality/value-Experimental implementations using machine learning-based techniques with feature reduction are conducted to validate the proposed solutions.The goal is to enhance SDP’s accuracy,relevance and efficiency,ultimately improving software quality assurance processes.The confusion matrix further illustrates the model’s performance,with only a small number of false positives and false negatives.展开更多
This letter reports a study of a hybrid burst assembly and a hybrid burst loss recovery scheme （delay-based burst assembly and hybrid loss recovery （DBAHLR）） which selectively employs proactive or reactive loss re...This letter reports a study of a hybrid burst assembly and a hybrid burst loss recovery scheme （delay-based burst assembly and hybrid loss recovery （DBAHLR）） which selectively employs proactive or reactive loss recovery techniques depending on the classification of traffic into short term and long term, respectively. Traffic prediction and segregation of optical burst switching network flows into the long term and short term are conducted based on predicted link holding times using the hidden Markov model （HMM）. The hybrid burst assembly implemented in DBAHLR uses a consecutive average-based burst assembly to handle jitter reduction necessary in real-time applications, with variations in burst sizes due to the non-monotonic nature of the average delay handled by additional burst length thresholding. This dynamic hybrid approach based on HMM prediction provides overall a lower blocking probability and delay and more throughput when compared with forward segment redundancy mechanism or purely HMM prediction-based adaptive burst sizing and wavelength allocation （HMM-TP）.展开更多
A hybrid grid generation technique and a multigrid/parallel algorithm are presented in this paper for turbulence flow simulations over three-dimensional （3D） complex geometries. The hybrid grid generation technique ...A hybrid grid generation technique and a multigrid/parallel algorithm are presented in this paper for turbulence flow simulations over three-dimensional （3D） complex geometries. The hybrid grid generation technique is based on an agglomeration method of anisotropic tetrahedrons. Firstly, the complex computational domain is covered by pure tetrahedral grids, in which anisotropic tetrahedrons are adopted to discrete the boundary layer and isotropic tetrahedrons in the outer field. Then, the anisotropic tetrahedrons in the boundary layer are agglomerated to generate prismatic grids. The agglomeration method can improve the grid quality in boundary layer and reduce the grid quantity to enhance the numerical accuracy and efficiency. In order to accelerate the convergence history, a multigrid/parallel algorithm is developed also based on anisotropic agglomeration approach. The numerical results demonstrate the excellent accelerating capability of this multigrid method.展开更多
Analysis, evaluation and interpretation of measured signals become important components in engineering research and practice, especially for material characteristic parameters which can not be obtained directly by exp...Analysis, evaluation and interpretation of measured signals become important components in engineering research and practice, especially for material characteristic parameters which can not be obtained directly by experimental measurements. The present paper proposes a hybrid-inverse analysis method for the identification of the nonlinear material parameters of any individual component from the mechanical responses of a global composite. The method couples experimental approach, numerical simulation with inverse search method. The experimental approach is used to provide basic data. Then parameter identification and numerical simulation are utilized to identify elasto-plastic material properties by the experimental data obtained and inverse searching algorithm. A numerical example of a stainless steel clad copper sheet is consid- ered to verify and show the applicability of the proposed hybrid-inverse method. In this example, a set of material parameters in an elasto-plastic constitutive model have been identified by using the obtained experimental data.展开更多
This paper presents a new hybrid approach that combines Modified Priority List (MPL) with Charged System Search (CSS), termed MPL-CSS, to solve one of the most crucial power system’s operational optimization problems...This paper presents a new hybrid approach that combines Modified Priority List (MPL) with Charged System Search (CSS), termed MPL-CSS, to solve one of the most crucial power system’s operational optimization problems, known as unit commitment (UC) scheduling. The UC scheduling problem is a mixed-integer nonlinear problem, highly-dimensional and extremely constrained. Existing meta-heuristic UC solution methods have the problems of stopping at a local optimum and slow convergence when applied to large-scale, heavily-constrained UC applications. In the first step of the proposed method, initial hourly optimum solutions of UC are obtained by Modified Priority List (MPL);however, the obtained UC solution may still be possible to be further improved. Therefore, in the second step, the CSS is utilized to achieve higher quality solutions. The UC is formulated as mixed integer linear programming to ensure the tractability of the results. The proposed method is successfully applied to a popular test system up to 100 units generators for both 24-hr and 168-hr system. Computational results show that both solution cost and execution time are superior to those of published methods.展开更多
A hybrid intelligent approach is proposed to help the decision maker to select the appropriate third-party reverse logistics provider. The following process is included: firstly,the evaluation team is established to d...A hybrid intelligent approach is proposed to help the decision maker to select the appropriate third-party reverse logistics provider. The following process is included: firstly,the evaluation team is established to determine the selection criteria and evaluate them by triangular fuzzy numbers; secondly,calculate the weight of criteria by the proposed hybrid algorithm integrating particle swarm optimization( PSO) and simulated annealing( SA); then, the performance evaluation for each supplier is predicted by the proposed self-feedback neural network( SFBNN) based on the historical data. A numerical example is also presented to interpret the methodology above.展开更多
Sustainable building in China has gained attention both domestically and abroad. Despite the fast increase in sustainable assessment tools developed locally or adopted from overseas, there are still criticisms about t...Sustainable building in China has gained attention both domestically and abroad. Despite the fast increase in sustainable assessment tools developed locally or adopted from overseas, there are still criticisms about the current situation of weak implementation and lack of comprehensive consideration. The lack of consideration of economic and social aspects or building performance on whole building life cycle all lead to departure from the true meaning of sustainable development. And lack of participation on the part of stakeholders makes it too theoretical to be carried out. This research aims to develop a model to address this problem. This research started with review of current sustainable assessment tools applied in China. As the assessment indicators have clear regional disparities, and almost no current tool considers all three pillars of environmental, economic and social in building life cycle. An industry survey was therefore designed for generation of indicators at different building stages, and personal interviews relevant to different occupation in building industry were conducted to complement the questionnaire survey. After that, the model Building Sustainable Score (BSS) was developed based on the stakeholders’ participation. Finally, the model is verified by a case study.展开更多
Hybrid simulation has been shown to be a cost-effective approach for assessing the seismic performance of structures. In hybrid simulation,critical parts of a structure are physically tested,while the remaining portio...Hybrid simulation has been shown to be a cost-effective approach for assessing the seismic performance of structures. In hybrid simulation,critical parts of a structure are physically tested,while the remaining portions of the system are concurrently simulated computationally,typically using a finite element model. This combination is realized through a numerical time-integration scheme,which allows for investigation of full system-level responses of a structure in a cost-effective manner. However,conducting hybrid simulation of complex structures within large-scale testing facilities presents significant challenges. For example,the chosen modeling scheme may create numerical inaccuracies or even result in unstable simulations; the displacement and force capacity of the experimental system can be exceeded; and a hybrid test may be terminated due to poor communication between modules(e.g.,loading controllers,data acquisition systems,simulation coordinator). These problems can cause the simulation to stop suddenly,and in some cases can even result in damage to the experimental specimens; the end result can be failure of the entire experiment. This study proposes a phased approach to hybrid simulation that can validate all of the hybrid simulation components and ensure the integrity largescale hybrid simulation. In this approach,a series of hybrid simulations employing numerical components and small-scale experimental components are examined to establish this preparedness for the large-scale experiment. This validation program is incorporated into an existing,mature hybrid simulation framework,which is currently utilized in the Multi-Axial Full-Scale Sub-Structuring Testing and Simulation(MUST-SIM) facility of the George E. Brown Network for Earthquake Engineering Simulation(NEES) equipment site at the University of Illinois at Urbana-Champaign. A hybrid simulation of a four-span curved bridge is presented as an example,in which three piers are experimentally controlled in a total of 18 degrees of freedom(DOFs). This simulation illustrates the effectiveness of the phased approach presented in this paper.展开更多
Under complex working conditions,accurate prediction of the remaining useful life(RUL)of lithium-ion batteries is of great significance to ensure the stable operation of energy storage systems,the safe driving of elec...Under complex working conditions,accurate prediction of the remaining useful life(RUL)of lithium-ion batteries is of great significance to ensure the stable operation of energy storage systems,the safe driving of electric vehicles,and the continuous power supply of electronic devices.This paper systematically describes the RUL prediction methods of lithium-ion batteries and comprehensively summarizes the development status and future trends in this field.First,the battery degradation mechanisms and lightweight data acquisition are analyzed.Secondly,a systematic classification model is constructed for the more widely used lithium battery RUL prediction methods,and the application characteristics and implementation limitations of different methods are analyzed in detail.An innovative classification framework for hybrid methods is proposed based on the depth of physical-data interaction.Then,collaborative modelling of calendar ageing and cyclic ageing is discussed,revealing their coupled effects and corresponding RUL prediction methods.Finally,the technical bottlenecks faced by the current RUL prediction of lithium batteries are identified,potential solutions are proposed,and the future development trends are outlined.展开更多
El Niño-Southern Oscillation(ENSO)can be currently predicted reasonably well six months and longer,but large biases and uncertainties remain in its real-time prediction.Various approaches have been taken to impro...El Niño-Southern Oscillation(ENSO)can be currently predicted reasonably well six months and longer,but large biases and uncertainties remain in its real-time prediction.Various approaches have been taken to improve understanding of ENSO processes,and different models for ENSO predictions have been developed,including linear statistical models based on principal oscillation pattern(POP)analyses,convolutional neural networks(CNNs),and so on.Here,we develop a novel hybrid model,named as POP-Net,by combining the POP analysis procedure with CNN-long short-term memory(LSTM)algorithm to predict the Niño-3.4 sea surface temperature(SST)index.ENSO predictions are compared with each other from the corresponding three models:POP model,CNN-LSTM model,and POP-Net,respectively.The POP-based pre-processing acts to enhance ENSO-related signals of interest while filtering unrelated noise.Consequently,an improved prediction is achieved in the POP-Net relative to others.The POP-Net shows a high-correlation skill for 17-month lead time prediction(correlation coefficients exceeding 0.5)during the 1994-2020 validation period.The POP-Net also alleviates the spring predictability barrier(SPB).It is concluded that value-added artificial neural networks for improved ENSO predictions are possible by including the process-oriented analyses to enhance signal representations.展开更多
For complex systems with high nonlinearity and strong coupling,the decoupling control technology based on proportion integration differentiation(PID)neural network(PIDNN)is used to eliminate the coupling between loops...For complex systems with high nonlinearity and strong coupling,the decoupling control technology based on proportion integration differentiation(PID)neural network(PIDNN)is used to eliminate the coupling between loops.The connection weights of the PIDNN are easy to fall into local optimum due to the use of the gradient descent learning method.In order to solve this problem,a hybrid particle swarm optimization(PSO)and differential evolution(DE)algorithm(PSO-DE)is proposed for optimizing the connection weights of the PIDNN.The DE algorithm is employed as an acceleration operation to help the swarm to get out of local optima traps in case that the optimal result has not been improved after several iterations.Two multivariable controlled plants with strong coupling between input and output pairs are employed to demonstrate the effectiveness of the proposed method.Simulation results show t hat the proposed met hod has better decoupling capabilities and control quality than the previous approaches.展开更多
为有效提升配电网韧性,提出了一种基于数据-模型混合驱动的多类型移动应急资源优化调度方法。首先,考虑到交通道路状态动态变化对移动储能车(mobile energy storage system,MESS)和应急抢修队(repair crew,RC)策略的影响,构建了以电力-...为有效提升配电网韧性,提出了一种基于数据-模型混合驱动的多类型移动应急资源优化调度方法。首先,考虑到交通道路状态动态变化对移动储能车(mobile energy storage system,MESS)和应急抢修队(repair crew,RC)策略的影响,构建了以电力-交通耦合网总损失成本最小为目标的多类型移动应急资源随机优化调度模型。然后,为了实时准确地求解MESS和RC最优路由和调度策略,提出了一种数据-模型混合驱动方法对所构建的复杂非线性随机优化模型进行求解。在数据驱动部分提出一种图注意力网络多智能体强化学习算法,以求解考虑交通网道路修复时间和移动应急资源邻接关系动态变化等不确定因素的MESS和RC最优路由策略。所提算法有效结合多种改进策略和优先经验回放策略以提高算法的采样效率和训练效果。在模型驱动部分采用二阶锥松弛和大M法将多类型移动应急资源优化调度问题构建为混合整数二阶锥规划模型以求解可再生能源出力和配电网负荷变化影响下MESS和RC最优调度策略。最后,在2个不同规模的电力-交通耦合网中验证所提方法的有效性、泛化能力和可拓展能力。展开更多
One of the main problems of machine learning and data mining is to develop a basic model with a few features,to reduce the algorithms involved in classification’s computational complexity.In this paper,the collection...One of the main problems of machine learning and data mining is to develop a basic model with a few features,to reduce the algorithms involved in classification’s computational complexity.In this paper,the collection of features has an essential importance in the classification process to be able minimize computational time,which decreases data size and increases the precision and effectiveness of specific machine learning activities.Due to its superiority to conventional optimization methods,several metaheuristics have been used to resolve FS issues.This is why hybrid metaheuristics help increase the search and convergence rate of the critical algorithms.A modern hybrid selection algorithm combining the two algorithms;the genetic algorithm(GA)and the Particle Swarm Optimization(PSO)to enhance search capabilities is developed in this paper.The efficacy of our proposed method is illustrated in a series of simulation phases,using the UCI learning array as a benchmark dataset.展开更多
文摘As far as the present state is concerned in detecting the behavioral pattern of humans(subject)using morphological image processing,a considerable portion of the study has been conducted utilizing frontal vision data of human faces.The present research work had used a side vision of human-face data to develop a theoretical framework via a hybrid analytical model approach.In this example,hybridization includes an artificial neural network(ANN)with a genetic algorithm(GA).We researched the geometrical properties extracted from side-vision human-face data.An additional study was conducted to determine the ideal number of geometrical characteristics to pick while clustering.The close vicinity ofminimum distance measurements is done for these clusters,mapped for proper classification and decision process of behavioral pattern.To identify the data acquired,support vector machines and artificial neural networks are utilized.A method known as an adaptiveunidirectional associative memory(AUTAM)was used to map one side of a human face to the other side of the same subject.The behavioral pattern has been detected based on two-class problem classification,and the decision process has been done using a genetic algorithm with best-fit measurements.The developed algorithm in the present work has been tested by considering a dataset of 100 subjects and tested using standard databases like FERET,Multi-PIE,Yale Face database,RTR,CASIA,etc.The complexity measures have also been calculated under worst-case and best-case situations.
基金supported by the Specialized Research Fund for the Doctoral Program of Higher Education(Grant No.20131101120023)the Excellent Young Scholars Research Fund of the Beijing Institute of Technology(Grant No.2012YG0203)
文摘The stochastic paralld gradient descent （SPGD） algorithm is widely used in wavefront sensor-less adaptive optics （WSAO） systems. However, the convergence is relatively slow. Modal-based algorithms usually provide much faster convergence than SPGD; however, the limited actuator stroke of the deformable mirror （DM） often prohibits the sensing of higher-order modes or renders a closed-loop correction inapplicable. Based on a comparative analysis of SPGD and the DM-modal-based algorithm, a hybrid approach involving both algorithms is proposed for extended image-based WSAO, and is demonstrated in this experiment. The hybrid approach can achieve similar correction results to pure SPGD, but with a dramatically decreased iteration number.
基金supported by the National Defense Basic Technology Research Program of China(Grant No.Z312012B001)the National Program on Key Basic Research Project of China("973" Program)(Grant No.2013CB035405)the Combining Production and Research Program of Guangdong Province,China(Grant No.2010A090200009)
文摘The problem of maximizing system reliability through component reliability choices and component redundancy is called tell-ability-redundancy allocation problem （RAP）, and it is a difficult but realistic nonlinear mixed-integer optimization prob- lem. For the RAP. we pay attention to an improved particle swarm optimization （IPSO）, and introduce four hybrid approaches for combining the IPSO with other conventional search techniques, such as harmony search （HS） and LXPM （a real coded GA）. The basic structure of the hybrid approaches includes two phases. After devising an initial solution by the HS or LXPM technique in the first phase, the IPSO performs an optimal search in the next phase. In addition, a new procedure by using golden search, named GS, is developed for further improving the solutions obtained by IPSO. Consequently, four ISPO-based hybrid approaches are proposed including HS-IPSO, LXPM-IPSO, HS-IPSO-GS, and LXPM-IPSO-GS. In order to validate the per-formance of proposed approaches, five nonlinear mixed-integer RAPs are investigated where both the number of re- dundancy components and the corresponding component reliability in each subsystem are to be decided simultaneously. As shown, the proposed approaches are all superior in terms of both optimal solutions and robustness to those by IPSO. Especially the pro-posed LXPM-IPSO-GS has shown more excellent performance than other typical approaches in the literature.
基金supported by Open Foundation of National Engineering Laboratory for High Speed Railway Construction(No.HSR202006)National Natural Science Foundation of China(Grant Nos.52178495,52078498).
文摘Based on the domain reduction idea and artificial boundary substructure method,this paper proposes an FK-FEM hybrid approach by integrating the advantages of FK and FEM(i.e.,FK can efficiently generate high-frequency three translational motion,while FEM has rich elements types and constitutive models).An advantage of this approach is that it realizes the entire process simulation from point dislocation source to underground structure.Compared with the plane wave field input method,the FK-FEM hybrid approach can reflect the spatial variability of seismic motion and the influence of source and propagation path.This approach can provide an effective solution for seismic analysis of underground structures under scenario of earthquake in regions where strong earthquakes may occur but are not recorded,especially when active faults,crustal,and soil parameters are available.Taking Daikai subway station as an example,the seismic response of the underground structure is simulated after verifying the correctness of the approach and the effects of crustal velocity structure and source parameters on the seismic response of Daikai station are discussed.In this example,the influence of velocity structure on the maximum interlayer displacement angle of underground structure is 96.5%and the change of source parameters can lead to the change of structural failure direction.
基金sponsored by the Ningbo Natural Science Funding Scheme(Project code:2019A610393)The Zhejiang Provincial Department of Science and Technology is acknowledged for this research under its Provincial Key Laboratory Programme(2020E10018).
文摘Building prototyping has regularly been used in building performance analyses with statistically feasible models.The novelty of this research involves a new hybrid approach combining stratified sampling and k-means clustering to establish building geometry prototypes.The research focuses on residential buildings in Ningbo,China.Seventeen small residential districts(SRDs)containing 367 residential buildings were systemically selected for survey and data collection.The stratified sampling used building construction year as the main parameter to generate stratification.Floor numbers,shape coefficients,floor areas,and window-to-wall ratios were used as the four observations for k-means clustering.Based on this new approach,nine building geometry prototypes were identified and modelled.These statistically representative prototypes provide building geometrical information and characteristic-based evaluations for subsequent building performance analysis.
文摘Purpose-Software defect prediction(SDP)is a critical aspect of software quality assurance,aiming to identify and manage potential defects in software systems.In this paper,we have proposed a novel hybrid approach that combines Grey Wolf Optimization with Feature Selection(GWOFS)and multilayer perceptron(MLP)for SDP.The GWOFS-MLP hybrid model is designed to optimize feature selection,ultimately enhancing the accuracy and efficiency of SDP.Grey Wolf Optimization,inspired by the social hierarchy and hunting behavior of grey wolves,is employed to select a subset of relevant features from an extensive pool of potential predictors.This study investigates the key challenges that traditional SDP approaches encounter and proposes promising solutions to overcome time complexity and the curse of the dimensionality reduction problem.Design/methodology/approach-The integration of GWOFS and MLP results in a robust hybrid model that can adapt to diverse software datasets.This feature selection process harnesses the cooperative hunting behavior of wolves,allowing for the exploration of critical feature combinations.The selected features are then fed into an MLP,a powerful artificial neural network(ANN)known for its capability to learn intricate patterns within software metrics.MLP serves as the predictive engine,utilizing the curated feature set to model and classify software defects accurately.Findings-The performance evaluation of the GWOFS-MLP hybrid model on a real-world software defect dataset demonstrates its effectiveness.The model achieves a remarkable training accuracy of 97.69%and a testing accuracy of 97.99%.Additionally,the receiver operating characteristic area under the curve(ROC-AUC)score of 0.89 highlights themodel’s ability to discriminate between defective and defect-free software components.Originality/value-Experimental implementations using machine learning-based techniques with feature reduction are conducted to validate the proposed solutions.The goal is to enhance SDP’s accuracy,relevance and efficiency,ultimately improving software quality assurance processes.The confusion matrix further illustrates the model’s performance,with only a small number of false positives and false negatives.
文摘This letter reports a study of a hybrid burst assembly and a hybrid burst loss recovery scheme （delay-based burst assembly and hybrid loss recovery （DBAHLR）） which selectively employs proactive or reactive loss recovery techniques depending on the classification of traffic into short term and long term, respectively. Traffic prediction and segregation of optical burst switching network flows into the long term and short term are conducted based on predicted link holding times using the hidden Markov model （HMM）. The hybrid burst assembly implemented in DBAHLR uses a consecutive average-based burst assembly to handle jitter reduction necessary in real-time applications, with variations in burst sizes due to the non-monotonic nature of the average delay handled by additional burst length thresholding. This dynamic hybrid approach based on HMM prediction provides overall a lower blocking probability and delay and more throughput when compared with forward segment redundancy mechanism or purely HMM prediction-based adaptive burst sizing and wavelength allocation （HMM-TP）.
基金supported partially by National Basic Research Program of China (Grant No. 2009CB723800)National Natural Science Foundation of China (Grant Nos: 91016001 and 10872023)
文摘A hybrid grid generation technique and a multigrid/parallel algorithm are presented in this paper for turbulence flow simulations over three-dimensional （3D） complex geometries. The hybrid grid generation technique is based on an agglomeration method of anisotropic tetrahedrons. Firstly, the complex computational domain is covered by pure tetrahedral grids, in which anisotropic tetrahedrons are adopted to discrete the boundary layer and isotropic tetrahedrons in the outer field. Then, the anisotropic tetrahedrons in the boundary layer are agglomerated to generate prismatic grids. The agglomeration method can improve the grid quality in boundary layer and reduce the grid quantity to enhance the numerical accuracy and efficiency. In order to accelerate the convergence history, a multigrid/parallel algorithm is developed also based on anisotropic agglomeration approach. The numerical results demonstrate the excellent accelerating capability of this multigrid method.
基金supported by the National Natural Science Foundation of China (Nos.10732080 and 10572102)National Basic Research Program of China (No.2007CB714000)
文摘Analysis, evaluation and interpretation of measured signals become important components in engineering research and practice, especially for material characteristic parameters which can not be obtained directly by experimental measurements. The present paper proposes a hybrid-inverse analysis method for the identification of the nonlinear material parameters of any individual component from the mechanical responses of a global composite. The method couples experimental approach, numerical simulation with inverse search method. The experimental approach is used to provide basic data. Then parameter identification and numerical simulation are utilized to identify elasto-plastic material properties by the experimental data obtained and inverse searching algorithm. A numerical example of a stainless steel clad copper sheet is consid- ered to verify and show the applicability of the proposed hybrid-inverse method. In this example, a set of material parameters in an elasto-plastic constitutive model have been identified by using the obtained experimental data.
文摘This paper presents a new hybrid approach that combines Modified Priority List (MPL) with Charged System Search (CSS), termed MPL-CSS, to solve one of the most crucial power system’s operational optimization problems, known as unit commitment (UC) scheduling. The UC scheduling problem is a mixed-integer nonlinear problem, highly-dimensional and extremely constrained. Existing meta-heuristic UC solution methods have the problems of stopping at a local optimum and slow convergence when applied to large-scale, heavily-constrained UC applications. In the first step of the proposed method, initial hourly optimum solutions of UC are obtained by Modified Priority List (MPL);however, the obtained UC solution may still be possible to be further improved. Therefore, in the second step, the CSS is utilized to achieve higher quality solutions. The UC is formulated as mixed integer linear programming to ensure the tractability of the results. The proposed method is successfully applied to a popular test system up to 100 units generators for both 24-hr and 168-hr system. Computational results show that both solution cost and execution time are superior to those of published methods.
基金Project of the Shanghai Committee of Science and Technology,China(No.12DZ1510000)
文摘A hybrid intelligent approach is proposed to help the decision maker to select the appropriate third-party reverse logistics provider. The following process is included: firstly,the evaluation team is established to determine the selection criteria and evaluate them by triangular fuzzy numbers; secondly,calculate the weight of criteria by the proposed hybrid algorithm integrating particle swarm optimization( PSO) and simulated annealing( SA); then, the performance evaluation for each supplier is predicted by the proposed self-feedback neural network( SFBNN) based on the historical data. A numerical example is also presented to interpret the methodology above.
文摘Sustainable building in China has gained attention both domestically and abroad. Despite the fast increase in sustainable assessment tools developed locally or adopted from overseas, there are still criticisms about the current situation of weak implementation and lack of comprehensive consideration. The lack of consideration of economic and social aspects or building performance on whole building life cycle all lead to departure from the true meaning of sustainable development. And lack of participation on the part of stakeholders makes it too theoretical to be carried out. This research aims to develop a model to address this problem. This research started with review of current sustainable assessment tools applied in China. As the assessment indicators have clear regional disparities, and almost no current tool considers all three pillars of environmental, economic and social in building life cycle. An industry survey was therefore designed for generation of indicators at different building stages, and personal interviews relevant to different occupation in building industry were conducted to complement the questionnaire survey. After that, the model Building Sustainable Score (BSS) was developed based on the stakeholders’ participation. Finally, the model is verified by a case study.
基金a NEESR-SG project(Seismic Simulation and Design of Bridge Columns under Combined Actions and Implications on System Response)funded by the National Science Foundation under Award No.CMMI-0530737NSC in Taiwan under Grant No.NSC-095-SAF-I-564-036-TMS
文摘Hybrid simulation has been shown to be a cost-effective approach for assessing the seismic performance of structures. In hybrid simulation,critical parts of a structure are physically tested,while the remaining portions of the system are concurrently simulated computationally,typically using a finite element model. This combination is realized through a numerical time-integration scheme,which allows for investigation of full system-level responses of a structure in a cost-effective manner. However,conducting hybrid simulation of complex structures within large-scale testing facilities presents significant challenges. For example,the chosen modeling scheme may create numerical inaccuracies or even result in unstable simulations; the displacement and force capacity of the experimental system can be exceeded; and a hybrid test may be terminated due to poor communication between modules(e.g.,loading controllers,data acquisition systems,simulation coordinator). These problems can cause the simulation to stop suddenly,and in some cases can even result in damage to the experimental specimens; the end result can be failure of the entire experiment. This study proposes a phased approach to hybrid simulation that can validate all of the hybrid simulation components and ensure the integrity largescale hybrid simulation. In this approach,a series of hybrid simulations employing numerical components and small-scale experimental components are examined to establish this preparedness for the large-scale experiment. This validation program is incorporated into an existing,mature hybrid simulation framework,which is currently utilized in the Multi-Axial Full-Scale Sub-Structuring Testing and Simulation(MUST-SIM) facility of the George E. Brown Network for Earthquake Engineering Simulation(NEES) equipment site at the University of Illinois at Urbana-Champaign. A hybrid simulation of a four-span curved bridge is presented as an example,in which three piers are experimentally controlled in a total of 18 degrees of freedom(DOFs). This simulation illustrates the effectiveness of the phased approach presented in this paper.
基金supported by the National Natural Science Foundation of China(No.U23A20651)the Central Government Guides Local Science and Technology Development Foundation(No.2023ZYDF022)+1 种基金the Sichuan Science and Technology Program(2024ZDZX0031)the Open Fund Project of State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines(No.SKLMRDPC23KF19).
文摘Under complex working conditions,accurate prediction of the remaining useful life(RUL)of lithium-ion batteries is of great significance to ensure the stable operation of energy storage systems,the safe driving of electric vehicles,and the continuous power supply of electronic devices.This paper systematically describes the RUL prediction methods of lithium-ion batteries and comprehensively summarizes the development status and future trends in this field.First,the battery degradation mechanisms and lightweight data acquisition are analyzed.Secondly,a systematic classification model is constructed for the more widely used lithium battery RUL prediction methods,and the application characteristics and implementation limitations of different methods are analyzed in detail.An innovative classification framework for hybrid methods is proposed based on the depth of physical-data interaction.Then,collaborative modelling of calendar ageing and cyclic ageing is discussed,revealing their coupled effects and corresponding RUL prediction methods.Finally,the technical bottlenecks faced by the current RUL prediction of lithium batteries are identified,potential solutions are proposed,and the future development trends are outlined.
基金supported by the Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA19060102)the National Natural Science Foundation of China[NSFCGrant Nos.41690122(41690120),and 42030410].
文摘El Niño-Southern Oscillation(ENSO)can be currently predicted reasonably well six months and longer,but large biases and uncertainties remain in its real-time prediction.Various approaches have been taken to improve understanding of ENSO processes,and different models for ENSO predictions have been developed,including linear statistical models based on principal oscillation pattern(POP)analyses,convolutional neural networks(CNNs),and so on.Here,we develop a novel hybrid model,named as POP-Net,by combining the POP analysis procedure with CNN-long short-term memory(LSTM)algorithm to predict the Niño-3.4 sea surface temperature(SST)index.ENSO predictions are compared with each other from the corresponding three models:POP model,CNN-LSTM model,and POP-Net,respectively.The POP-based pre-processing acts to enhance ENSO-related signals of interest while filtering unrelated noise.Consequently,an improved prediction is achieved in the POP-Net relative to others.The POP-Net shows a high-correlation skill for 17-month lead time prediction(correlation coefficients exceeding 0.5)during the 1994-2020 validation period.The POP-Net also alleviates the spring predictability barrier(SPB).It is concluded that value-added artificial neural networks for improved ENSO predictions are possible by including the process-oriented analyses to enhance signal representations.
基金This work was supported by the Key Project of Chinese Ministry of Education(No.212135)the Guangxi Natural Science Foundation(No.2012GXNSFBA053165)+1 种基金the Projec t of Education Department of Guangxi(No.201203YB131)the Project of Guangxi Key Laboratory(No.14-045-44)。
文摘For complex systems with high nonlinearity and strong coupling,the decoupling control technology based on proportion integration differentiation(PID)neural network(PIDNN)is used to eliminate the coupling between loops.The connection weights of the PIDNN are easy to fall into local optimum due to the use of the gradient descent learning method.In order to solve this problem,a hybrid particle swarm optimization(PSO)and differential evolution(DE)algorithm(PSO-DE)is proposed for optimizing the connection weights of the PIDNN.The DE algorithm is employed as an acceleration operation to help the swarm to get out of local optima traps in case that the optimal result has not been improved after several iterations.Two multivariable controlled plants with strong coupling between input and output pairs are employed to demonstrate the effectiveness of the proposed method.Simulation results show t hat the proposed met hod has better decoupling capabilities and control quality than the previous approaches.
文摘为有效提升配电网韧性,提出了一种基于数据-模型混合驱动的多类型移动应急资源优化调度方法。首先,考虑到交通道路状态动态变化对移动储能车(mobile energy storage system,MESS)和应急抢修队(repair crew,RC)策略的影响,构建了以电力-交通耦合网总损失成本最小为目标的多类型移动应急资源随机优化调度模型。然后,为了实时准确地求解MESS和RC最优路由和调度策略,提出了一种数据-模型混合驱动方法对所构建的复杂非线性随机优化模型进行求解。在数据驱动部分提出一种图注意力网络多智能体强化学习算法,以求解考虑交通网道路修复时间和移动应急资源邻接关系动态变化等不确定因素的MESS和RC最优路由策略。所提算法有效结合多种改进策略和优先经验回放策略以提高算法的采样效率和训练效果。在模型驱动部分采用二阶锥松弛和大M法将多类型移动应急资源优化调度问题构建为混合整数二阶锥规划模型以求解可再生能源出力和配电网负荷变化影响下MESS和RC最优调度策略。最后,在2个不同规模的电力-交通耦合网中验证所提方法的有效性、泛化能力和可拓展能力。
基金This work was partially supported by the National Natural Science Foundation of China(61876089,61876185,61902281,61375121)the Opening Project of Jiangsu Key Laboratory of Data Science and Smart Software(No.2019DS301)+1 种基金the Engineering Research Center of Digital Forensics,Ministry of Education,the Key Research and Development Program of Jiangsu Province(BE2020633)the Priority Academic Program Development of Jiangsu Higher Education Institutions。
文摘One of the main problems of machine learning and data mining is to develop a basic model with a few features,to reduce the algorithms involved in classification’s computational complexity.In this paper,the collection of features has an essential importance in the classification process to be able minimize computational time,which decreases data size and increases the precision and effectiveness of specific machine learning activities.Due to its superiority to conventional optimization methods,several metaheuristics have been used to resolve FS issues.This is why hybrid metaheuristics help increase the search and convergence rate of the critical algorithms.A modern hybrid selection algorithm combining the two algorithms;the genetic algorithm(GA)and the Particle Swarm Optimization(PSO)to enhance search capabilities is developed in this paper.The efficacy of our proposed method is illustrated in a series of simulation phases,using the UCI learning array as a benchmark dataset.
