With the development of advanced high strength steel,especially for dual-phase steel,the model algorithm for cooling control after hot rolling has to achieve the targeted coiling temperature control at the location of...With the development of advanced high strength steel,especially for dual-phase steel,the model algorithm for cooling control after hot rolling has to achieve the targeted coiling temperature control at the location of downcoiler whilst maintaining the cooling path control based on strip microstructure along the whole cooling section.A cooling path control algorithm was proposed for the laminar cooling process as a solution to practical difficulties associated with the realization of the thermal cycle during cooling process.The heat conduction equation coupled with the carbon diffusion equation with moving boundary was employed in order to simulate temperature change and phase transformation kinetics,making it possible to observe the temperature field and the phase fraction of the strip in real time.On this basis,an optimization method was utilized for valve settings to ensure the minimum deviations between the predicted and actual cooling path of the strip,taking into account the constraints of the cooling equipment′s specific capacity,cooling line length,etc.Results showed that the model algorithm was able to achieve the online cooling path control for dual-phase steel.展开更多
Tube hydroforming process is a relative new process f or production of structural parts of low weight and high rigidity. The successfu lness of the process depends largely on the a proper selection of loading path w h...Tube hydroforming process is a relative new process f or production of structural parts of low weight and high rigidity. The successfu lness of the process depends largely on the a proper selection of loading path w hich is axial feeding distance as related to the applied internal pressure. Due to the complicated nature of plastic deformation, a optimum loading path which w ill guarantee good hydroformed parts free of winkle and fracture has often to be determined by finite element analysis. In order to save trials and errors, adap tive FEM simulation method has been developed. To effectively apply the adaptive simulation method, we have to know the applicability of the method. In this pap er, a classification of tube hydroforming (THF) processes based on sensitivity to loading parameters has been suggested. Characteristics of the classification have been analyzed in terms of failure mode, dominant loading parameters and th eir working windows. It was discussed that the so called pressure dominant THF p rocess is the most difficult process for both simulation in FEM analysis and pra ctical operation in real manufacturing situation. To effectively find out the op timum loading path for pressure dominant THF process, adaptive FEM simulation st rategies are mostly needed.展开更多
Yanshanian igneous rocks in the East China, on an orogenic belt scale, are characterized by the continental marginal arc in petrology and geochemistry as Andes and West USA, except for the Hercyn type biotite two mi...Yanshanian igneous rocks in the East China, on an orogenic belt scale, are characterized by the continental marginal arc in petrology and geochemistry as Andes and West USA, except for the Hercyn type biotite two mica muscovite granite belt in the Nanling region. Three segments of the Yanshanian igneous rocks along the belt are recognized. In terms of magma tectonic event sequence, the north, middle and south segments have counter clockwise (ccw), clockwise (cw) and ccw+cw pTt paths of the orogenic process, respectively. A genetic model of the lithospheric delamination (loss of the lithospheric root in about 120 km) in combination with the oceanic subduction for the Yanshanian Andes like orogenic belt and both the crust and lithosphere thickening for the Yanshanian Hercyn type Nanling orogenic belt in the East China is suggested.展开更多
The conventional optimization methods were generally based on a deterministic approach, since their purpose is to find out an accurate solution. However, when the solution space is extremely narrowed as a result of se...The conventional optimization methods were generally based on a deterministic approach, since their purpose is to find out an accurate solution. However, when the solution space is extremely narrowed as a result of setting many inequality constraints, an ingenious scheme based on experience may be needed. Similarly, parameters must be adjusted with solution search algorithms when nonlinearity of the problem is strong, because the risk of falling into local solution is high. Thus, we here propose a new method in which the optimization problem is replaced with stochastic process based on path integral techniques used in quantum mechanics and an approximate value of optimal solution is calculated as an expected value instead of accurate value. It was checked through some optimization problems that this method using stochastic process is effective. We call this new optimization method “stochastic process optimization technique (SPOT)”. It is expected that this method will enable efficient optimization by avoiding the above difficulties. In this report, a new optimization method based on a stochastic process is formulated, and several calculation examples are shown to prove its effectiveness as a method to obtain approximate solution for optimization problems.展开更多
The entropy production rate of stationary minimal diffusion processes with smooth coefficients is calculated. As a byproduct, the continuity of paths of the minimal diffusion processes is discussed, and that the point...The entropy production rate of stationary minimal diffusion processes with smooth coefficients is calculated. As a byproduct, the continuity of paths of the minimal diffusion processes is discussed, and that the point at infinity is absorbing is proved.展开更多
In this paper, we use a modified path simulation method for valuation of Asian American Options. This method is a modification of the path simulation model proposed by Tiley. We assume that the behavior of the log ret...In this paper, we use a modified path simulation method for valuation of Asian American Options. This method is a modification of the path simulation model proposed by Tiley. We assume that the behavior of the log return of the underlying assets follows the Variance Gamma (VG) process, since its distribution is heavy tail and leptokurtic. We provide sensitivity analysis of this method and compare the obtained prices to Asian European option prices.展开更多
Many design engineers in cross-domain industries have attended training classes of TRIZ to improve their innovative abilities in China. Most of them are successful, but others are not. So the latest target of the trai...Many design engineers in cross-domain industries have attended training classes of TRIZ to improve their innovative abilities in China. Most of them are successful, but others are not. So the latest target of the trainers is to improve the training process used now in industry in China and to make the engineers to understand the basic principles of TRIZ better. Based on the mass-engineer-oriented training model(MEOTM) and mechanical engineers’ design cases, a relationship between managing activities about the opportunities for innovation and the training process is set up. It is shown that the inventive problems come first from opportunity searching for engineers. A training and gate system for evaluation is developed to involve the managing activities of the companies in the training process. Then comparison between the general analogous process and the application of TRIZ is made, which shows the advantages and depth principles of TRIZ for the engineers to apply them confidently. Lastly a new process is formed in which opportunity searching, engineers training, inventive problems identifying and solving,and three redesign paths are connected seamlessly. The research proposes an opportunity-driven redesign path that cooperates the training and opportunity searching, which will be applied in future training classes to make more and more engineers to follow.展开更多
In order to overcome some defects of the traditional immune algorithm, the immune algorithm was improved for solving a path optimization problem in deep immune learning of a gene network. Firstly, the diversity of the...In order to overcome some defects of the traditional immune algorithm, the immune algorithm was improved for solving a path optimization problem in deep immune learning of a gene network. Firstly, the diversity of the solution population was enhanced in the evolution process by improving the memory cell processing method. Moreover, effective gene information was dynamically extracted from the genes of the excellent antibodies to make good vaccines in the process of immune evolution. Worse antibodies were optimized by vaccinating these antibodies, and the convergence of the immune algorithm to the optimal solution was improved. Finally, the feasibility of the improved immune algorithm was verified in the experimental simulation for solving the classic NP problem in deep immune learning of the gene network.展开更多
We introduce a super-Lévy process and study maximal speed of all particles in the range and the support of the super-Lévy process. The state of historical super-Lévy process is a measure on the set of p...We introduce a super-Lévy process and study maximal speed of all particles in the range and the support of the super-Lévy process. The state of historical super-Lévy process is a measure on the set of paths. We study the maximal speed of all particles during a given time period, which turns out to be a function of the packing dimension of the time period. We calculate the Hausdorff dimension of the set of a-fast paths in the support and the range of the historical super-Lévy process.展开更多
Sorting and collecting the data by questionnaire survey and literature analysis,the childrenswear brand elemental analysis is completed.The development goal of differentiated positioning of Chinese childrenswear brand...Sorting and collecting the data by questionnaire survey and literature analysis,the childrenswear brand elemental analysis is completed.The development goal of differentiated positioning of Chinese childrenswear brands is decided.Four modules which influence the brand differentiated development were extracted to establish the hierarchical analysis framework for the differentiated positioning development of Chinese childrenswear brand.Judgment matrix diagram is constructed by using the analytic hierarchy process(AHP).According to the data analysis and judgment,the core elements,basic elements and auxiliary elements are identified which support the development of differentiated positioning of Chinese childrenswear brands.The clear development path of differentiated positioning of Chinese childrenswear brands is formed,namely to enhance the core essential factors as the key point,to grasp the elements’spirit exactly in differentiated positioning of brand style,childrenswear color feature,green and security of products quality and retail prices which influence the brand differentiated development.The Chinese existing technical advantages was given full play by providing the basic support for the differentiated development of childrenswear brands.Auxiliary elements were heleped to grow by making auxiliary elements play a greater role.The goal was achieved to improve the market competitiveness by development of differentiated positioning of Chinese childrenswear brands.展开更多
The Qinling orogenic belt is a collision zone between the North China and Yangtze cratons. The Qinling Complex is a Precambrian metamorphic complex, developed in the inner zone of the orogenic belt , which records the...The Qinling orogenic belt is a collision zone between the North China and Yangtze cratons. The Qinling Complex is a Precambrian metamorphic complex, developed in the inner zone of the orogenic belt , which records the metamorphic and deformational history and PTt path of the regional meta-morphism of the collision zone . The present paper studies the metamorphic and deformational history and the PTt path of various tectono-metamorphic cycles in order to describe the geodynamic processes prevailing in that part of the Qinling orogenic belt since Proterozoic.The tectonometamorphic history and evolution of the Qinling Complex is divided into two stages: the stage of formation and the stage of modification During the stage of formation dated as Proterozoic,three deformational sequences are recognized. The amphibolite facies regional metamorphism is earlier than or synchronous with the first or second phase of folding. Three metamorphic zones, i.e. And-Ms ,Sil- Ms, Sil Kfs are delimited. During the stage of modification , the emplacement of Caledonian granite , superimposed thermal aureole (garnet K feldspar zone )and the development of ductile shear zones are major events.Metamorphic reactions are reconstructed in terms of analysis of re-equilibrium textures. Geothermobarometric calculations are conducted to calibrate the PT conditions of metamorphism .The metamorphic PTt paths have been estabh'shed. The PTt path of the Proterozoic tectonometamorphic cycle shows a clockwise pattern and is characterized by prominent decompression. The PTt path of the Caledonian tectonometamorphic cycle is characterized first by PT rising ,then isothermal decompression (rapid uplift), and finally by isobaric cooling The PTt path of the two tectonometamorphic cycles evidence the geodynamic processes: two major stages of collision and uplift in the Proterozoic and Caledonian Hercynian periods, respectively, during the evolution of Qinling orogenic belt.展开更多
In this paper we present the main phases of the BP-M* methodology and its application to a care pathway for patients in the Oncology Division of a large hospital, to evaluate pros and cons of different drug administra...In this paper we present the main phases of the BP-M* methodology and its application to a care pathway for patients in the Oncology Division of a large hospital, to evaluate pros and cons of different drug administration modalities and the impact of these modalities to the organizational process. BP-M* has been developed for the manufacturing sector but the relevance of business modeling, analysis and reorganization is not restricted to a specific sector. The aim of this work is to show its application to a real life study of a complex process in the health sector.展开更多
The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q le...The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q learning algorithrn for dual-aircraft flight path planning is proposed. The passive detection task model of the dual-aircraft is set up based on the partition of the target active radar＇s radiation area. The problem is formulated as a Markov decision process （MDP） by using the fuzzy theory to make a generalization of the state space and defining the transition functions, action space and reward function properly. Details of the path planning algorithm are presented. Simulation results indicate that the algorithm can provide adaptive strategies for dual-aircraft to control their flight paths to detect a non-maneuvering or maneu- vering target.展开更多
In order to enhance the capability of tracking targets autonomously of unmanned aerial vehicle (UAV), the partially observable Markov decision process (POMDP) model for UAV path planning is established based on the PO...In order to enhance the capability of tracking targets autonomously of unmanned aerial vehicle (UAV), the partially observable Markov decision process (POMDP) model for UAV path planning is established based on the POMDP framework. The elements of the POMDP model are analyzed and described. The state transfer law in the model can be described by the method of interactive multiple model (IMM) due to the diversity of the target motion law, which is used to switch the motion model to accommodate target maneuvers, and hence improving the tracking accuracy. The simulation results show that the model can achieve efficient planning for the UAV route, and effective tracking for the target. Furthermore, the path planned by this model is more reasonable and efficient than that by using the single state transition law.展开更多
Suitable rescue path selection is very important to rescue lives and reduce the loss of disasters, and has been a key issue in the field of disaster response management. In this paper, we present a path selection algo...Suitable rescue path selection is very important to rescue lives and reduce the loss of disasters, and has been a key issue in the field of disaster response management. In this paper, we present a path selection algorithm based on Q-learning for disaster response applications. We assume that a rescue team is an agent, which is operating in a dynamic and dangerous environment and needs to find a safe and short path in the least time. We first propose a path selection model for disaster response management, and deduce that path selection based on our model is a Markov decision process. Then, we introduce Q-learning and design strategies for action selection and to avoid cyclic path. Finally, experimental results show that our algorithm can find a safe and short path in the dynamic and dangerous environment, which can provide a specific and significant reference for practical management in disaster response applications.展开更多
基金Acknowledgements： This work was partially supported by China National Social Science Foundation （No. 08BYY046）, Social Science Foundation of Chinese Ministry of Education （No. 06JJD740007） and Project of Shandong Social Science Fund （No. 07CWXJ03）.
文摘With the development of advanced high strength steel,especially for dual-phase steel,the model algorithm for cooling control after hot rolling has to achieve the targeted coiling temperature control at the location of downcoiler whilst maintaining the cooling path control based on strip microstructure along the whole cooling section.A cooling path control algorithm was proposed for the laminar cooling process as a solution to practical difficulties associated with the realization of the thermal cycle during cooling process.The heat conduction equation coupled with the carbon diffusion equation with moving boundary was employed in order to simulate temperature change and phase transformation kinetics,making it possible to observe the temperature field and the phase fraction of the strip in real time.On this basis,an optimization method was utilized for valve settings to ensure the minimum deviations between the predicted and actual cooling path of the strip,taking into account the constraints of the cooling equipment′s specific capacity,cooling line length,etc.Results showed that the model algorithm was able to achieve the online cooling path control for dual-phase steel.
文摘Tube hydroforming process is a relative new process f or production of structural parts of low weight and high rigidity. The successfu lness of the process depends largely on the a proper selection of loading path w hich is axial feeding distance as related to the applied internal pressure. Due to the complicated nature of plastic deformation, a optimum loading path which w ill guarantee good hydroformed parts free of winkle and fracture has often to be determined by finite element analysis. In order to save trials and errors, adap tive FEM simulation method has been developed. To effectively apply the adaptive simulation method, we have to know the applicability of the method. In this pap er, a classification of tube hydroforming (THF) processes based on sensitivity to loading parameters has been suggested. Characteristics of the classification have been analyzed in terms of failure mode, dominant loading parameters and th eir working windows. It was discussed that the so called pressure dominant THF p rocess is the most difficult process for both simulation in FEM analysis and pra ctical operation in real manufacturing situation. To effectively find out the op timum loading path for pressure dominant THF process, adaptive FEM simulation st rategies are mostly needed.
文摘Yanshanian igneous rocks in the East China, on an orogenic belt scale, are characterized by the continental marginal arc in petrology and geochemistry as Andes and West USA, except for the Hercyn type biotite two mica muscovite granite belt in the Nanling region. Three segments of the Yanshanian igneous rocks along the belt are recognized. In terms of magma tectonic event sequence, the north, middle and south segments have counter clockwise (ccw), clockwise (cw) and ccw+cw pTt paths of the orogenic process, respectively. A genetic model of the lithospheric delamination (loss of the lithospheric root in about 120 km) in combination with the oceanic subduction for the Yanshanian Andes like orogenic belt and both the crust and lithosphere thickening for the Yanshanian Hercyn type Nanling orogenic belt in the East China is suggested.
文摘The conventional optimization methods were generally based on a deterministic approach, since their purpose is to find out an accurate solution. However, when the solution space is extremely narrowed as a result of setting many inequality constraints, an ingenious scheme based on experience may be needed. Similarly, parameters must be adjusted with solution search algorithms when nonlinearity of the problem is strong, because the risk of falling into local solution is high. Thus, we here propose a new method in which the optimization problem is replaced with stochastic process based on path integral techniques used in quantum mechanics and an approximate value of optimal solution is calculated as an expected value instead of accurate value. It was checked through some optimization problems that this method using stochastic process is effective. We call this new optimization method “stochastic process optimization technique (SPOT)”. It is expected that this method will enable efficient optimization by avoiding the above difficulties. In this report, a new optimization method based on a stochastic process is formulated, and several calculation examples are shown to prove its effectiveness as a method to obtain approximate solution for optimization problems.
基金This work is supported by NSFC (10271008 and 10531070)
文摘The entropy production rate of stationary minimal diffusion processes with smooth coefficients is calculated. As a byproduct, the continuity of paths of the minimal diffusion processes is discussed, and that the point at infinity is absorbing is proved.
文摘In this paper, we use a modified path simulation method for valuation of Asian American Options. This method is a modification of the path simulation model proposed by Tiley. We assume that the behavior of the log return of the underlying assets follows the Variance Gamma (VG) process, since its distribution is heavy tail and leptokurtic. We provide sensitivity analysis of this method and compare the obtained prices to Asian European option prices.
基金Supported by National Natural Science Foundation of China(Grant Nos.51675159,51305123)
文摘Many design engineers in cross-domain industries have attended training classes of TRIZ to improve their innovative abilities in China. Most of them are successful, but others are not. So the latest target of the trainers is to improve the training process used now in industry in China and to make the engineers to understand the basic principles of TRIZ better. Based on the mass-engineer-oriented training model(MEOTM) and mechanical engineers’ design cases, a relationship between managing activities about the opportunities for innovation and the training process is set up. It is shown that the inventive problems come first from opportunity searching for engineers. A training and gate system for evaluation is developed to involve the managing activities of the companies in the training process. Then comparison between the general analogous process and the application of TRIZ is made, which shows the advantages and depth principles of TRIZ for the engineers to apply them confidently. Lastly a new process is formed in which opportunity searching, engineers training, inventive problems identifying and solving,and three redesign paths are connected seamlessly. The research proposes an opportunity-driven redesign path that cooperates the training and opportunity searching, which will be applied in future training classes to make more and more engineers to follow.
文摘In order to overcome some defects of the traditional immune algorithm, the immune algorithm was improved for solving a path optimization problem in deep immune learning of a gene network. Firstly, the diversity of the solution population was enhanced in the evolution process by improving the memory cell processing method. Moreover, effective gene information was dynamically extracted from the genes of the excellent antibodies to make good vaccines in the process of immune evolution. Worse antibodies were optimized by vaccinating these antibodies, and the convergence of the immune algorithm to the optimal solution was improved. Finally, the feasibility of the improved immune algorithm was verified in the experimental simulation for solving the classic NP problem in deep immune learning of the gene network.
基金Project supported by the National Natural Science Foundation of China(No.10571159)the Ph.D.Programs Foundation of Ministry of Education of China(No.20060335032)and the Foundation of Hangzhou Dianzi University(No.KYS091506042)
文摘We introduce a super-Lévy process and study maximal speed of all particles in the range and the support of the super-Lévy process. The state of historical super-Lévy process is a measure on the set of paths. We study the maximal speed of all particles during a given time period, which turns out to be a function of the packing dimension of the time period. We calculate the Hausdorff dimension of the set of a-fast paths in the support and the range of the historical super-Lévy process.
基金High-End Foreign Expert Program Foundation from Chinese Foreign Experts Affairs,China(No.GDW20183300402)Characteristic College Foundation from Ningbo Education Bureau,China(No.TSXY-RCPY04-03)
文摘Sorting and collecting the data by questionnaire survey and literature analysis,the childrenswear brand elemental analysis is completed.The development goal of differentiated positioning of Chinese childrenswear brands is decided.Four modules which influence the brand differentiated development were extracted to establish the hierarchical analysis framework for the differentiated positioning development of Chinese childrenswear brand.Judgment matrix diagram is constructed by using the analytic hierarchy process(AHP).According to the data analysis and judgment,the core elements,basic elements and auxiliary elements are identified which support the development of differentiated positioning of Chinese childrenswear brands.The clear development path of differentiated positioning of Chinese childrenswear brands is formed,namely to enhance the core essential factors as the key point,to grasp the elements’spirit exactly in differentiated positioning of brand style,childrenswear color feature,green and security of products quality and retail prices which influence the brand differentiated development.The Chinese existing technical advantages was given full play by providing the basic support for the differentiated development of childrenswear brands.Auxiliary elements were heleped to grow by making auxiliary elements play a greater role.The goal was achieved to improve the market competitiveness by development of differentiated positioning of Chinese childrenswear brands.
文摘The Qinling orogenic belt is a collision zone between the North China and Yangtze cratons. The Qinling Complex is a Precambrian metamorphic complex, developed in the inner zone of the orogenic belt , which records the metamorphic and deformational history and PTt path of the regional meta-morphism of the collision zone . The present paper studies the metamorphic and deformational history and the PTt path of various tectono-metamorphic cycles in order to describe the geodynamic processes prevailing in that part of the Qinling orogenic belt since Proterozoic.The tectonometamorphic history and evolution of the Qinling Complex is divided into two stages: the stage of formation and the stage of modification During the stage of formation dated as Proterozoic,three deformational sequences are recognized. The amphibolite facies regional metamorphism is earlier than or synchronous with the first or second phase of folding. Three metamorphic zones, i.e. And-Ms ,Sil- Ms, Sil Kfs are delimited. During the stage of modification , the emplacement of Caledonian granite , superimposed thermal aureole (garnet K feldspar zone )and the development of ductile shear zones are major events.Metamorphic reactions are reconstructed in terms of analysis of re-equilibrium textures. Geothermobarometric calculations are conducted to calibrate the PT conditions of metamorphism .The metamorphic PTt paths have been estabh'shed. The PTt path of the Proterozoic tectonometamorphic cycle shows a clockwise pattern and is characterized by prominent decompression. The PTt path of the Caledonian tectonometamorphic cycle is characterized first by PT rising ,then isothermal decompression (rapid uplift), and finally by isobaric cooling The PTt path of the two tectonometamorphic cycles evidence the geodynamic processes: two major stages of collision and uplift in the Proterozoic and Caledonian Hercynian periods, respectively, during the evolution of Qinling orogenic belt.
文摘In this paper we present the main phases of the BP-M* methodology and its application to a care pathway for patients in the Oncology Division of a large hospital, to evaluate pros and cons of different drug administration modalities and the impact of these modalities to the organizational process. BP-M* has been developed for the manufacturing sector but the relevance of business modeling, analysis and reorganization is not restricted to a specific sector. The aim of this work is to show its application to a real life study of a complex process in the health sector.
基金supported by the National Natural Science Foundation of China(60874040)
文摘The problem of passive detection discussed in this paper involves searching and locating an aerial emitter by dualaircraft using passive radars. In order to improve the detection probability and accuracy, a fuzzy Q learning algorithrn for dual-aircraft flight path planning is proposed. The passive detection task model of the dual-aircraft is set up based on the partition of the target active radar＇s radiation area. The problem is formulated as a Markov decision process （MDP） by using the fuzzy theory to make a generalization of the state space and defining the transition functions, action space and reward function properly. Details of the path planning algorithm are presented. Simulation results indicate that the algorithm can provide adaptive strategies for dual-aircraft to control their flight paths to detect a non-maneuvering or maneu- vering target.
基金supported by the Aeronautical Science Foundation of China(20135153031 20135553035 2017ZC53033)
文摘In order to enhance the capability of tracking targets autonomously of unmanned aerial vehicle (UAV), the partially observable Markov decision process (POMDP) model for UAV path planning is established based on the POMDP framework. The elements of the POMDP model are analyzed and described. The state transfer law in the model can be described by the method of interactive multiple model (IMM) due to the diversity of the target motion law, which is used to switch the motion model to accommodate target maneuvers, and hence improving the tracking accuracy. The simulation results show that the model can achieve efficient planning for the UAV route, and effective tracking for the target. Furthermore, the path planned by this model is more reasonable and efficient than that by using the single state transition law.
基金supported by National Basic Research Program of China (973 Program) (No. 2009CB326203)National Natural Science Foundation of China (No. 61004103)+5 种基金the National Research Foundation for the Doctoral Program of Higher Education of China (No. 20100111110005)China Postdoctoral Science Foundation (No. 20090460742)National Engineering Research Center of Special Display Technology (No. 2008HGXJ0350)Natural Science Foundation of Anhui Province (No. 090412058, No. 070412035)Natural Science Foundation of Anhui Province of China (No. 11040606Q44, No. 090412058)Specialized Research Fund for Doctoral Scholars of Hefei University of Technology (No. GDBJ2009-003, No. GDBJ2009-067)
文摘Suitable rescue path selection is very important to rescue lives and reduce the loss of disasters, and has been a key issue in the field of disaster response management. In this paper, we present a path selection algorithm based on Q-learning for disaster response applications. We assume that a rescue team is an agent, which is operating in a dynamic and dangerous environment and needs to find a safe and short path in the least time. We first propose a path selection model for disaster response management, and deduce that path selection based on our model is a Markov decision process. Then, we introduce Q-learning and design strategies for action selection and to avoid cyclic path. Finally, experimental results show that our algorithm can find a safe and short path in the dynamic and dangerous environment, which can provide a specific and significant reference for practical management in disaster response applications.
