System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose sign...System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose significant challenges for efficient decision-making,necessitating a modular multiagent control system.Deep Reinforcement Learning(DRL)and Decision Tree(DT)have been utilized for these complex decision-making tasks,but each has its limitations:DRL is highly adaptive but lacks interpretability,while DT is inherently interpretable but has limited adaptability.To overcome these challenges,we propose the Adaptive Interpretable Decision Tree(AIDT),an evolutionary-based algorithm that is both adaptable to diverse environmental settings and highly interpretable in its decision-making processes.We first construct a Markov decision process(MDP)-based simulation environment using the Cooperative Submarine Search task as a representative scenario for training and testing the proposed method.Specifically,we use the heat map as a state variable to address the issue of multi-agent input state proliferation.Next,we introduce the curiosity-guiding intrinsic reward to encourage comprehensive exploration and enhance algorithm performance.Additionally,we incorporate decision tree size as an influence factor in the adaptation process to balance task completion with computational efficiency.To further improve the generalization capability of the decision tree,we apply a normalization method to ensure consistent processing of input states.Finally,we validate the proposed algorithm in different environmental settings,and the results demonstrate both its adaptability and interpretability.展开更多
A state/event fault tree(SEFT)is a modeling technique for describing the causal chains of events leading to failure in software-controlled complex systems.Such systems are ubiquitous in all areas of everyday life,and ...A state/event fault tree(SEFT)is a modeling technique for describing the causal chains of events leading to failure in software-controlled complex systems.Such systems are ubiquitous in all areas of everyday life,and safety and reliability analyses are increasingly required for these systems.SEFTs combine elements from the traditional fault tree with elements from state-based techniques.In the context of the real-time safety-critical systems,SEFTs do not describe the time properties and important timedependent system behaviors that can lead to system failures.Further,SEFTs lack the precise semantics required for formally modeling time behaviors.In this paper,we present a qualitative analysis method for SEFTs based on transformation from SEFT to timed automata(TA),and use the model checker UPPAAL to verify system requirements’properties.The combination of SEFT and TA is an important step towards an integrated design and verification process for real-time safety-critical systems.Finally,we present a case study of a powerboat autopilot system to confirm our method is viable and valid after achieving the verification goal step by step.展开更多
As far as the weighted digraph is considered, an optimal directed spanning tree algorithm called table based algorithm (TBA) is proposed in the paper based on the table instead of the weighted digraph. The optimality ...As far as the weighted digraph is considered, an optimal directed spanning tree algorithm called table based algorithm (TBA) is proposed in the paper based on the table instead of the weighted digraph. The optimality is proved, and a numerical example is demonstrated.展开更多
The learning Bayesian network （BN） structure from data is an NP-hard problem and still one of the most exciting chal- lenges in the machine learning. In this work, a novel algorithm is presented which combines ideas...The learning Bayesian network （BN） structure from data is an NP-hard problem and still one of the most exciting chal- lenges in the machine learning. In this work, a novel algorithm is presented which combines ideas from local learning, constraint- based, and search-and-score techniques in a principled and ef- fective way. It first reconstructs the junction tree of a BN and then performs a K2-scoring greedy search to orientate the local edges in the cliques of junction tree. Theoretical and experimental results show the proposed algorithm is capable of handling networks with a large number of variables. Its comparison with the well-known K2 algorithm is also presented.展开更多
Six-year old apple trees were selected for field experiment.The objective of this study was to obtain the reasonable arrangement of surge-root irrigation emitters in apple orchards.There were three factors:the buried ...Six-year old apple trees were selected for field experiment.The objective of this study was to obtain the reasonable arrangement of surge-root irrigation emitters in apple orchards.There were three factors:the buried depth H(25,40,55 cm),the horizontal distance L(30,40,60 cm)between the emitters and the trunk of the experimental tree,and the number of the irrigation emitters N(1,2,4).The effect of the arrangement of surge-root irrigation emitters on the growth,yield and irrigation water use efficiency(IWUE)of apple trees were studied in Northern Shaanxi where the irrigation quota takes 60%-75%of the field water capacity.The results showed that the arrangement of emitters for surge-root irrigation had a significant effect on apple tree yield and IWUE,especially,the yield and IWUE reached 28388.17 kg/hm2 and 16.83 kg/m3 in treatment T3,respectively.At the same L and N levels(T1,T2,and T3),the yield and IWUE in treatment T3 were the highest,and the yields in treatments T1 and T2 were decreased by 26.22%and 31.48%,while IWUE is reduced by14.02%and 18.12%compared with T3,respectively.At the same H and N levels(T3,T4,and T5),the yield and IWUE of apple trees were decreased with increasing L level.Especially,when L was 30 cm(T3),the yield and IWUE were the highest.The same L and H levels(T3,T6,and T7)could promote the growth of apple trees when N was 2(T3).Compared with treatment T3,it was found that the increment of new shoots was decreased by 8.07%-18.71%,and the fruit diameter was decreased by 5.41%-9.11%.Therefore,two emitters should be arranged symmetrically on both sides of an apple tree,each was buried at a 40 cm depth and 30 cm away from the trunk of the tree to effectively improve the yield and IWUE of the apple tree in mountainous areas in Northern Shaanxi.展开更多
A simple fast method is given for sequentially retrieving all the records in a B tree. A file structure for database is proposed. The records in its primary data file are sorted according to the key order. A B tree ...A simple fast method is given for sequentially retrieving all the records in a B tree. A file structure for database is proposed. The records in its primary data file are sorted according to the key order. A B tree is used as its dense index. It is easy to insert, delete or search a record, and it is also convenient to retrieve records in the sequential order of the keys. The merits and efficiencies of these methods or structures are discussed in detail.展开更多
Suffix trees are the key data structure for text string matching, and are used in wide application areas such as bioinformatics and data compression. Ukkonen algorithm is deeply investigated and a new algorithm, which...Suffix trees are the key data structure for text string matching, and are used in wide application areas such as bioinformatics and data compression. Ukkonen algorithm is deeply investigated and a new algorithm, which decreases the number of memory operations in construction and keeps the result tree sequential, is proposed. The experiment result shows that both the construction and the matching procedure are more efficient than Ukkonen algorithm.展开更多
This research is to control the pests inside fruits and buds by injecting pesticides into the tree with the high-pressure injector. The soluable pesticides injected into the trunk can transported insides to every part...This research is to control the pests inside fruits and buds by injecting pesticides into the tree with the high-pressure injector. The soluable pesticides injected into the trunk can transported insides to every part of the tree to kill pests. The change of pesticides inside the tree was observed. The result showed that injecting pesticides once a year could kill above 80% of the pests which happened once annually. The effect of injection lasts longer than that of applying the pesticide outside. The pesticides injected into the tree are not affected by environment and do not kill natural enemies directly,and the residual amount of pesticides is below the international standard level.展开更多
In many decision making tasks,the features and decision are ordinal.Several ordinal classification learning algorithms have been developed in recent years,it is shown that these algorithms are sensitive to noisy sampl...In many decision making tasks,the features and decision are ordinal.Several ordinal classification learning algorithms have been developed in recent years,it is shown that these algorithms are sensitive to noisy samples and do not work in real-world applications.In this work,we propose a new measure of feature quality, called rank mutual information.Then,we design an ordinal decision tree(REOT) construction technique based on rank mutual information.The theoretic and experimental analysis shows that the proposed algorithm is effective.展开更多
Objective According to the report from American Heart Association(AHA),cardiovascular diseases(CVDs)are the leading causes of death globally,and coronary artery disease(CAD),known as coronary atherosclerotic plaques,a...Objective According to the report from American Heart Association(AHA),cardiovascular diseases(CVDs)are the leading causes of death globally,and coronary artery disease(CAD),known as coronary atherosclerotic plaques,accounts for over 30%of cardiovascular diseases.Therefore,it is of great clinical significance to study the relationship between coronary bifurcations morphometrical feature change and coronary artery disease.Although coronary atherosclerosis has been extensively investigated,there is a lack of in-deep study on the differences in morphometric features between optimal and realistic geometry of coronary arterial trees.The purpose of the present paper is to determine the morphological changes in patients with CAD lesion compared with non-coronary artery disease(non-CAD)subjects.Methods Due to the difficulty of studying the coronary bifurcations in vivo,image-based in vitro anatomical 3D models have been widely used as a noninvasive method for morphometric measurement and clinical diagnosis of the coronary bifurcations.With the development of coronary computed tomography angiography(CTA)hardware and software technologies,the CTA imaging technique has been shown a promising application in the characterization,visualization,and identification of coronary artery disease in recent decades.The CTA images used to reconstruct three-dimensional(3D)coronary arterial trees are from Asia populations(Southern Chinese populations),including five cadavers without CAD lesion and 102 patients with CAD lesion.The best fit artery diameter was calculated as twice the average radius between the points in the centerlines and the points on the coronary arterial inner wall.The bifurcation angles between larger daughter artery and smaller daughter artery were determined by the intersection angle of their centerlines.Murray’s law was introduced to assess the deviation of the realistic vascular networks from its optimal state.Results Based on the morphometric analysis of coronary artery bifurcations in non-CAD subjects and patients with CAD lesion subjects,the most important finding is that morphological feature parameters of non-CAD subjects are closer to the optimal values than those of patients with CAD lesion.Moreover,by comparing the morphometric data between the left and right coronary arteries,the right coronary artery exhibits a structure closer to the optimal one in morphological feature than the left coronary artery.In addition,coronary arterial trees with CAD lesion have higher asymmetry and larger area expansion ratio(AER)than those of the coronary arterial trees without CAD lesion.Conclusions We morphologically found that the coronary arterial trees with CAD lesion and left are more likely to deviate from the optimal structure predicted by Murray’s law than those without CAD lesion and right.The degree to which coronary arterial system deviating from their optimal state may directly affect the incidence of coronary artery disease.This computer morpho-logical analysis strategy is illustrated to be effective in the distinguishing of the geometric differences between the healthy and diseased coronary arteries,and the analysis method may have a large potential in cardiovascular disease earlier diagnosis.展开更多
Finding sustainable energy resources is essential to face the increasing energy demand.Trees are an important part of ancient architecture but are becoming rare in urban areas.Trees can control and tune the pedestrian...Finding sustainable energy resources is essential to face the increasing energy demand.Trees are an important part of ancient architecture but are becoming rare in urban areas.Trees can control and tune the pedestrian-level wind velocity and thermal condition.In this study,a numerical investigation is employed to assess the role of trees planted in the windward direction of the building complex on the thermal and pedestrian wind velocity conditions around/inside a pre-education building located in the center of the complex.Compared to the previous studies(which considered only outside buildings),this work considers the effects of trees on microclimate change both inside/outside buildings.Effects of different parameters including the leaf area density and number of trees,number of rows,far-field velocity magnitude,and thermal condition around the main building are assessed.The results show that the flow velocity in the spacing between the first-row buildings is reduced by 30%-40% when the one-row trees with 2 m height are planted 15 m farther than the buildings.Furthermore,two rows of trees are more effective in higher velocities and reduce the maximum velocity by about 50%.The investigation shows that trees also could reduce the temperature by about 1℃around the building.展开更多
The electrical tree discharge channel will be formed at concentrate spot of electric field in solid insulation dielectric,in order to study the difference of electrical tree under different electrical field,the short-...The electrical tree discharge channel will be formed at concentrate spot of electric field in solid insulation dielectric,in order to study the difference of electrical tree under different electrical field,the short-cable electrode system with actual XLPE cable was designed,experiments were performed under 12 kV,15 kV,18 kV,21 kV compare to the needle-plate electrode system.Experiment results show that the electrical tree of short-cable electrode system have the same growth trend with the needle-plate electrode system in the growing characteristic,the dense of electrical tree increase with the increase of voltage level,electrical tree of short-cable electrode system growth is slower than the needle-plate electrode system at the same voltage;To get the same shape of electrical tree,the voltage of short-cable electrode system must be higher than needle-plate electrode system,the results show that the semiconductor layer and the copper shield layer outside of XLPE cable have very important affection on the electrical trees degradation.展开更多
Conical picks are important tools for rock mechanical excavation.Mean cutting force(MCF)of conical pick determines the suitability of the target rock for mechanical excavation.Accurate evaluation of MCF is important f...Conical picks are important tools for rock mechanical excavation.Mean cutting force(MCF)of conical pick determines the suitability of the target rock for mechanical excavation.Accurate evaluation of MCF is important for pick design and rock cutting.This study proposed hybrid methods composed of boosting trees and Bayesian optimization(BO)for accurate evaluation of MCF.220 datasets including uniaxial compression strength,tensile strength,tip angle(θ),attack angle,and cutting depth,were collected.Four boosting trees were developed based on the database to predict MCF.BO optimized the hyper-parameters of these boosting trees.Model evaluation suggested that the proposed hybrid models outperformed many commonly utilized machine learning models.The hybrid model composed of BO and categorical boosting(BO-CatBoost)was the best.Its outstanding performance was attributed to its advantages in dealing with categorical features(θincluded 6 types of angles and could be considered as categorical features).A graphical user interface was developed to facilitate the application of BO-CatBoost for the estimation of MCF.Moreover,the influences of the input parameters on the model and their relationship with MCF were analyzed.Whenθincreased from 80°to 90°,it had a significant contribution to the increase of MCF.展开更多
文摘System upgrades in unmanned systems have made Unmanned Aerial Vehicle(UAV)-based patrolling and monitoring a preferred solution for ocean surveillance.However,dynamic environments and large-scale deployments pose significant challenges for efficient decision-making,necessitating a modular multiagent control system.Deep Reinforcement Learning(DRL)and Decision Tree(DT)have been utilized for these complex decision-making tasks,but each has its limitations:DRL is highly adaptive but lacks interpretability,while DT is inherently interpretable but has limited adaptability.To overcome these challenges,we propose the Adaptive Interpretable Decision Tree(AIDT),an evolutionary-based algorithm that is both adaptable to diverse environmental settings and highly interpretable in its decision-making processes.We first construct a Markov decision process(MDP)-based simulation environment using the Cooperative Submarine Search task as a representative scenario for training and testing the proposed method.Specifically,we use the heat map as a state variable to address the issue of multi-agent input state proliferation.Next,we introduce the curiosity-guiding intrinsic reward to encourage comprehensive exploration and enhance algorithm performance.Additionally,we incorporate decision tree size as an influence factor in the adaptation process to balance task completion with computational efficiency.To further improve the generalization capability of the decision tree,we apply a normalization method to ensure consistent processing of input states.Finally,we validate the proposed algorithm in different environmental settings,and the results demonstrate both its adaptability and interpretability.
基金supported by the National Natural Science Foundation of China(11832012)
文摘A state/event fault tree(SEFT)is a modeling technique for describing the causal chains of events leading to failure in software-controlled complex systems.Such systems are ubiquitous in all areas of everyday life,and safety and reliability analyses are increasingly required for these systems.SEFTs combine elements from the traditional fault tree with elements from state-based techniques.In the context of the real-time safety-critical systems,SEFTs do not describe the time properties and important timedependent system behaviors that can lead to system failures.Further,SEFTs lack the precise semantics required for formally modeling time behaviors.In this paper,we present a qualitative analysis method for SEFTs based on transformation from SEFT to timed automata(TA),and use the model checker UPPAAL to verify system requirements’properties.The combination of SEFT and TA is an important step towards an integrated design and verification process for real-time safety-critical systems.Finally,we present a case study of a powerboat autopilot system to confirm our method is viable and valid after achieving the verification goal step by step.
基金the National Natural Science Foundation of China (No. 79870030).
文摘As far as the weighted digraph is considered, an optimal directed spanning tree algorithm called table based algorithm (TBA) is proposed in the paper based on the table instead of the weighted digraph. The optimality is proved, and a numerical example is demonstrated.
基金supported by the National Natural Science Fundation of China (6097408261075055)the Fundamental Research Funds for the Central Universities (K50510700004)
文摘The learning Bayesian network （BN） structure from data is an NP-hard problem and still one of the most exciting chal- lenges in the machine learning. In this work, a novel algorithm is presented which combines ideas from local learning, constraint- based, and search-and-score techniques in a principled and ef- fective way. It first reconstructs the junction tree of a BN and then performs a K2-scoring greedy search to orientate the local edges in the cliques of junction tree. Theoretical and experimental results show the proposed algorithm is capable of handling networks with a large number of variables. Its comparison with the well-known K2 algorithm is also presented.
基金Supporting founds:National Key R&D Program(2016YFC0400204)Natural Science Foundation of China(51479161,51279157,51779205)。
文摘Six-year old apple trees were selected for field experiment.The objective of this study was to obtain the reasonable arrangement of surge-root irrigation emitters in apple orchards.There were three factors:the buried depth H(25,40,55 cm),the horizontal distance L(30,40,60 cm)between the emitters and the trunk of the experimental tree,and the number of the irrigation emitters N(1,2,4).The effect of the arrangement of surge-root irrigation emitters on the growth,yield and irrigation water use efficiency(IWUE)of apple trees were studied in Northern Shaanxi where the irrigation quota takes 60%-75%of the field water capacity.The results showed that the arrangement of emitters for surge-root irrigation had a significant effect on apple tree yield and IWUE,especially,the yield and IWUE reached 28388.17 kg/hm2 and 16.83 kg/m3 in treatment T3,respectively.At the same L and N levels(T1,T2,and T3),the yield and IWUE in treatment T3 were the highest,and the yields in treatments T1 and T2 were decreased by 26.22%and 31.48%,while IWUE is reduced by14.02%and 18.12%compared with T3,respectively.At the same H and N levels(T3,T4,and T5),the yield and IWUE of apple trees were decreased with increasing L level.Especially,when L was 30 cm(T3),the yield and IWUE were the highest.The same L and H levels(T3,T6,and T7)could promote the growth of apple trees when N was 2(T3).Compared with treatment T3,it was found that the increment of new shoots was decreased by 8.07%-18.71%,and the fruit diameter was decreased by 5.41%-9.11%.Therefore,two emitters should be arranged symmetrically on both sides of an apple tree,each was buried at a 40 cm depth and 30 cm away from the trunk of the tree to effectively improve the yield and IWUE of the apple tree in mountainous areas in Northern Shaanxi.
文摘A simple fast method is given for sequentially retrieving all the records in a B tree. A file structure for database is proposed. The records in its primary data file are sorted according to the key order. A B tree is used as its dense index. It is easy to insert, delete or search a record, and it is also convenient to retrieve records in the sequential order of the keys. The merits and efficiencies of these methods or structures are discussed in detail.
基金supported by the National Natural Science Foundation of China(6050203260672068).
文摘Suffix trees are the key data structure for text string matching, and are used in wide application areas such as bioinformatics and data compression. Ukkonen algorithm is deeply investigated and a new algorithm, which decreases the number of memory operations in construction and keeps the result tree sequential, is proposed. The experiment result shows that both the construction and the matching procedure are more efficient than Ukkonen algorithm.
文摘This research is to control the pests inside fruits and buds by injecting pesticides into the tree with the high-pressure injector. The soluable pesticides injected into the trunk can transported insides to every part of the tree to kill pests. The change of pesticides inside the tree was observed. The result showed that injecting pesticides once a year could kill above 80% of the pests which happened once annually. The effect of injection lasts longer than that of applying the pesticide outside. The pesticides injected into the tree are not affected by environment and do not kill natural enemies directly,and the residual amount of pesticides is below the international standard level.
基金supported by National Natural Science Foundation of China under Grant 60703013 and 10978011Key Program of National Natural Science Foundation of China under Grant 60932008+1 种基金National Science Fund for Distinguished Young Scholars under Grant 50925625China Postdoctoral Science Foundation.
文摘In many decision making tasks,the features and decision are ordinal.Several ordinal classification learning algorithms have been developed in recent years,it is shown that these algorithms are sensitive to noisy samples and do not work in real-world applications.In this work,we propose a new measure of feature quality, called rank mutual information.Then,we design an ordinal decision tree(REOT) construction technique based on rank mutual information.The theoretic and experimental analysis shows that the proposed algorithm is effective.
基金sponsored by the National Natural Science Foundation of China ( 11432006 ( J. Wu) , 11672109 ( Y. Fang) and 31500759 ( J. Lin) )the Fundamental Research Funds for the Central Universities
文摘Objective According to the report from American Heart Association(AHA),cardiovascular diseases(CVDs)are the leading causes of death globally,and coronary artery disease(CAD),known as coronary atherosclerotic plaques,accounts for over 30%of cardiovascular diseases.Therefore,it is of great clinical significance to study the relationship between coronary bifurcations morphometrical feature change and coronary artery disease.Although coronary atherosclerosis has been extensively investigated,there is a lack of in-deep study on the differences in morphometric features between optimal and realistic geometry of coronary arterial trees.The purpose of the present paper is to determine the morphological changes in patients with CAD lesion compared with non-coronary artery disease(non-CAD)subjects.Methods Due to the difficulty of studying the coronary bifurcations in vivo,image-based in vitro anatomical 3D models have been widely used as a noninvasive method for morphometric measurement and clinical diagnosis of the coronary bifurcations.With the development of coronary computed tomography angiography(CTA)hardware and software technologies,the CTA imaging technique has been shown a promising application in the characterization,visualization,and identification of coronary artery disease in recent decades.The CTA images used to reconstruct three-dimensional(3D)coronary arterial trees are from Asia populations(Southern Chinese populations),including five cadavers without CAD lesion and 102 patients with CAD lesion.The best fit artery diameter was calculated as twice the average radius between the points in the centerlines and the points on the coronary arterial inner wall.The bifurcation angles between larger daughter artery and smaller daughter artery were determined by the intersection angle of their centerlines.Murray’s law was introduced to assess the deviation of the realistic vascular networks from its optimal state.Results Based on the morphometric analysis of coronary artery bifurcations in non-CAD subjects and patients with CAD lesion subjects,the most important finding is that morphological feature parameters of non-CAD subjects are closer to the optimal values than those of patients with CAD lesion.Moreover,by comparing the morphometric data between the left and right coronary arteries,the right coronary artery exhibits a structure closer to the optimal one in morphological feature than the left coronary artery.In addition,coronary arterial trees with CAD lesion have higher asymmetry and larger area expansion ratio(AER)than those of the coronary arterial trees without CAD lesion.Conclusions We morphologically found that the coronary arterial trees with CAD lesion and left are more likely to deviate from the optimal structure predicted by Murray’s law than those without CAD lesion and right.The degree to which coronary arterial system deviating from their optimal state may directly affect the incidence of coronary artery disease.This computer morpho-logical analysis strategy is illustrated to be effective in the distinguishing of the geometric differences between the healthy and diseased coronary arteries,and the analysis method may have a large potential in cardiovascular disease earlier diagnosis.
文摘Finding sustainable energy resources is essential to face the increasing energy demand.Trees are an important part of ancient architecture but are becoming rare in urban areas.Trees can control and tune the pedestrian-level wind velocity and thermal condition.In this study,a numerical investigation is employed to assess the role of trees planted in the windward direction of the building complex on the thermal and pedestrian wind velocity conditions around/inside a pre-education building located in the center of the complex.Compared to the previous studies(which considered only outside buildings),this work considers the effects of trees on microclimate change both inside/outside buildings.Effects of different parameters including the leaf area density and number of trees,number of rows,far-field velocity magnitude,and thermal condition around the main building are assessed.The results show that the flow velocity in the spacing between the first-row buildings is reduced by 30%-40% when the one-row trees with 2 m height are planted 15 m farther than the buildings.Furthermore,two rows of trees are more effective in higher velocities and reduce the maximum velocity by about 50%.The investigation shows that trees also could reduce the temperature by about 1℃around the building.
基金Project Supported by Scientific Foundation for Outstanding Young Scientist of China(50425722)Natural Scientific Foundation of Chongqing(11699)
文摘The electrical tree discharge channel will be formed at concentrate spot of electric field in solid insulation dielectric,in order to study the difference of electrical tree under different electrical field,the short-cable electrode system with actual XLPE cable was designed,experiments were performed under 12 kV,15 kV,18 kV,21 kV compare to the needle-plate electrode system.Experiment results show that the electrical tree of short-cable electrode system have the same growth trend with the needle-plate electrode system in the growing characteristic,the dense of electrical tree increase with the increase of voltage level,electrical tree of short-cable electrode system growth is slower than the needle-plate electrode system at the same voltage;To get the same shape of electrical tree,the voltage of short-cable electrode system must be higher than needle-plate electrode system,the results show that the semiconductor layer and the copper shield layer outside of XLPE cable have very important affection on the electrical trees degradation.
基金Project(52374153)supported by the National Natural Science Foundation of ChinaProject(2023zzts0726)supported by the Fundamental Research Funds for the Central Universities of Central South University,China。
文摘Conical picks are important tools for rock mechanical excavation.Mean cutting force(MCF)of conical pick determines the suitability of the target rock for mechanical excavation.Accurate evaluation of MCF is important for pick design and rock cutting.This study proposed hybrid methods composed of boosting trees and Bayesian optimization(BO)for accurate evaluation of MCF.220 datasets including uniaxial compression strength,tensile strength,tip angle(θ),attack angle,and cutting depth,were collected.Four boosting trees were developed based on the database to predict MCF.BO optimized the hyper-parameters of these boosting trees.Model evaluation suggested that the proposed hybrid models outperformed many commonly utilized machine learning models.The hybrid model composed of BO and categorical boosting(BO-CatBoost)was the best.Its outstanding performance was attributed to its advantages in dealing with categorical features(θincluded 6 types of angles and could be considered as categorical features).A graphical user interface was developed to facilitate the application of BO-CatBoost for the estimation of MCF.Moreover,the influences of the input parameters on the model and their relationship with MCF were analyzed.Whenθincreased from 80°to 90°,it had a significant contribution to the increase of MCF.
