Presented is a multiple model soft sensing method based on Affinity Propagation （AP）, Gaussian process （GP） and Bayesian committee machine （BCM）. AP clustering arithmetic is used to cluster training samples acco...Presented is a multiple model soft sensing method based on Affinity Propagation （AP）, Gaussian process （GP） and Bayesian committee machine （BCM）. AP clustering arithmetic is used to cluster training samples according to their operating points. Then, the sub-models are estimated by Gaussian Process Regression （GPR）. Finally, in order to get a global probabilistic prediction, Bayesian committee mactnne is used to combine the outputs of the sub-estimators. The proposed method has been applied to predict the light naphtha end point in hydrocracker fractionators. Practical applications indicate that it is useful for the online prediction of quality monitoring in chemical processes.展开更多
Thanks to advances in tunnel boring machine(TBM)and monitoring,significant progress has been achieved in the application of soft computing techniques for the optimization of TBM tunneling and the reduction of disturba...Thanks to advances in tunnel boring machine(TBM)and monitoring,significant progress has been achieved in the application of soft computing techniques for the optimization of TBM tunneling and the reduction of disturbance related to tunneling in urban areas.Because experimental,analytical,and numerical methods have limitations in solving problems related to TBM tunneling,engineers can use soft computing techniques in analyzing the relationship between the target tunneling responses and influential design inputs parameters,including the geometrical,geological,and TBM operational factors.These techniques are useful in achieving robust and low-cost solutions.However,engineers face difficulties in making an optimal choice of the soft computing technique to solve the complex problems related to TBM tunneling.To help with this choice,this study presents state of the art about the use of soft computing techniques in TBM tunneling through practical applications.The study proposes recommendations for the optimal use of these techniques,in particular(i)the importance of preliminary analyses for the selection and reduction of input parameters,(ii)the necessity to complete insufficient data using laboratory tests and numerical modeling,(iii)the selection of reduced number of hidden layers and nodes to avoid overfitting,(iv)the use of recurrent neural networks to deal with time-series data,and(v)the association of soft computing methods with hybrid optimization techniques to reduce the risk of convergence to local minima.展开更多
Soft machine refers to a kind of mechanical system made of soft materials to complete sophisticated missions, such as handling a fragile object and crawling along a narrow tunnel corner, under low cost control and act...Soft machine refers to a kind of mechanical system made of soft materials to complete sophisticated missions, such as handling a fragile object and crawling along a narrow tunnel corner, under low cost control and actuation. Hence, soft machines have raised great challenges to computational dynamics. In this review article, recent studies of the authors on the dynamic modeling, numerical simulation, and experimental validation of soft machines are summarized in the framework of multibody system dynamics. The dynamic modeling approaches are presented first for the geometric nonlinearities of coupled overall motions and large deformations of a soft component, the physical nonlinearities of a soft component made of hyperelastic or elastoplastic materials, and the frictional contacts/impacts of soft components, respectively. Then the computation approach is outlined for the dynamic simulation of soft machines governed by a set of differential-algebraic equations of very high dimensions, with an emphasis on the efficient computations of the nonlinear elastic force vector of finite elements. The validations of the proposed approaches are given via three case studies, including the locomotion of a soft quadrupedal robot, the spinning deployment of a solar sail of a spacecraft, and the deployment of a mesh reflector of a satellite antenna, as well as the corresponding experimental studies. Finally, some remarks are made for future studies.展开更多
Surface tension plays a core role in dominating various surface and interface phenomena. For liquid metals with high melting temperature, a profound understanding of the behaviors of surface tension is crucial in indu...Surface tension plays a core role in dominating various surface and interface phenomena. For liquid metals with high melting temperature, a profound understanding of the behaviors of surface tension is crucial in industrial processes such as casting, welding, and solidification, etc. Recently, the room temperature liquid metal （RTLM） mainly composed of gallium-based alloys has caused widespread concerns due to its increasingly realized unique virtues. The surface properties of such materials are rather vital in nearly all applications involved from chip cooling, thermal energy harvesting, hydrogen generation, shape changeable soft machines, printed electronics to 3D fabrication, etc. owing to its pretty large surface tension of approximately 700 mN/m. In order to promote the research of surface tension of RTLM, this paper is dedicated to present an overview on the roles and mechanisms of surface tension of liquid metal and summarize the latest progresses on the understanding of the basic knowledge, theories, influencing factors and experimental measure- ment methods clarified so far. As a practical technique to regulate the surface tension of RTLM, the fimdamental principles and applications of electrowetting are also interpreted. Moreover, the unique phenomena of RTLM surface tension issues such as surface tension driven self- actuation, modified wettability on various substrates and the functions of oxides are discussed to give an insight into the acting mechanism of surface tension. Furthermore, future directions worthy of pursuing are pointed out.展开更多
Severe gas disasters in deep mining areas are increasing,and traditional protective coal seam mining is facing significant challenges.This paper proposes an innovative technology using soft rock as the protective seam...Severe gas disasters in deep mining areas are increasing,and traditional protective coal seam mining is facing significant challenges.This paper proposes an innovative technology using soft rock as the protective seam in the absence of an appropriate coal seam.Based on the geological engineering conditions of the new horizontal first mining area of Luling Coal Mine in Huaibei,China,the impacts of different mining parameters of the soft-rock protective seam on the pressure-relief effect of the protected coal seam were analyzed through numerical simulation.The unit stress of the protected coal seam,which was less than half of the primary rock stress,was used as the mining stress pressure-relief index.The optimized interlayer space was found to be 59 m for the first soft-rock working face,with a 2 m mining thickness and 105 m face length.The physicochemical characteristics of the orebody were analyzed,and a device selection framework for the soft-rock protective seam was developed.Optimal equipment for the working face was selected,including the fully-mechanized hydraulic support and coal cutter.A production technology that combined fully-mechanized and blasting-assisted soft-rock mining was developed.Engineering practices demonstrated that normal circulation operation can be achieved on the working face of the soft-rock protective seam,with an average advancement rate of 1.64 m/d.The maximum residual gas pressure and content,which were measured at the cut hole position of the protected coal seams(Nos.8 and 9),decreased to 0.35 MPa and 4.87 m^3/t,respectively.The results suggested that soft-rock protective seam mining can produce a significant gas-control effect.展开更多
Due to the development of the novel materials,the past two decades have witnessed the rapid advances of soft electronics.The soft electronics have huge potential in the physical sign monitoring and health care.One of ...Due to the development of the novel materials,the past two decades have witnessed the rapid advances of soft electronics.The soft electronics have huge potential in the physical sign monitoring and health care.One of the important advantages of soft electronics is forming good interface with skin,which can increase the user scale and improve the signal quality.Therefore,it is easy to build the specific dataset,which is important to improve the performance of machine learning algorithm.At the same time,with the assistance of machine learning algorithm,the soft electronics have become more and more intelligent to realize real-time analysis and diagnosis.The soft electronics and machining learning algorithms complement each other very well.It is indubitable that the soft electronics will bring us to a healthier and more intelligent world in the near future.Therefore,in this review,we will give a careful introduction about the new soft material,physiological signal detected by soft devices,and the soft devices assisted by machine learning algorithm.Some soft materials will be discussed such as two-dimensional material,carbon nanotube,nanowire,nanomesh,and hydrogel.Then,soft sensors will be discussed according to the physiological signal types(pulse,respiration,human motion,intraocular pressure,phonation,etc.).After that,the soft electronics assisted by various algorithms will be reviewed,including some classical algorithms and powerful neural network algorithms.Especially,the soft device assisted by neural network will be introduced carefully.Finally,the outlook,challenge,and conclusion of soft system powered by machine learning algorithm will be discussed.展开更多
Soft robot is a kind of machine form with flexible deformation capability. Making flexible actuators has recently become a hot research topic in the field. In this study, we demonstrated the facile fabrication of a so...Soft robot is a kind of machine form with flexible deformation capability. Making flexible actuators has recently become a hot research topic in the field. In this study, we demonstrated the facile fabrication of a soft electromagnetic actuator using liquid metal coil of Ga-In alloys, and designed several illustrative mechanical devices, such as jellyfish like robot, soft fishtail and flexible manipulator. Measurements of the liquid metal coil's electrical properties confirmed that the liquid metal coil was mechanically stable under 48% uniaxial strains. Furthermore, the resistance of the liquid metal coil is stable under 60° bending deformation. Tests on the liquid metal coil's driving properties confirmed that the liquid metal coil(55 mm×55 mm×1 mm) could reach the maximum displacement amplitude of 21.5 mm with the current of 0.48 A. It was shown that the electromagnetic interaction between the magnet and the liquid metal coil enables the coil as a highly efficient actuator. The mechanisms lying behind were interpreted and future applications of such system were discussed.展开更多
Fe-based metallic glasses(MGs)have shown great commercial values due to their excellent soft magnetic properties.Magnetism prediction with consideration of glass forming ability(GFA)is of great signifi-cance for devel...Fe-based metallic glasses(MGs)have shown great commercial values due to their excellent soft magnetic properties.Magnetism prediction with consideration of glass forming ability(GFA)is of great signifi-cance for developing novel functional Fe-based MGs.However,theories or models established based on condensed matter physics exhibit limited accuracy and some exceptions.In this work,based on 618 Fe-based MGs samples collected from published works,machine learning(ML)models were well trained to predict saturated magnetization(B_(s))of Fe-based MGs.GFA was treated as a feature using the experimental data of the supercooled liquid region(△T_(x)).Three ML algorithms,namely eXtreme gradient boosting(XGBoost),artificial neural networks(ANN)and random forest(RF),were studied.Through feature selection and hyperparameter tuning,XGBoost showed the best predictive performance on the randomly split test dataset with determination coefficient(R^(2))of 0.942,mean absolute percent error(MAPE)of 5.563%,and root mean squared error(RMSE)of 0.078 T.A variety of feature importance rankings derived by XGBoost models showed that T_(x) played an important role in the predictive performance of the models.This work showed the proposed ML method can simultaneously aggregate GFA and other features in ther-modynamics,kinetics and structures to predict the magnetic properties of Fe-based MGs with excellent accuracy.展开更多
基金Supported by the National High Technology Research and Development Program of China (2006AA040309)National BasicResearch Program of China (2007CB714000)
文摘Presented is a multiple model soft sensing method based on Affinity Propagation （AP）, Gaussian process （GP） and Bayesian committee machine （BCM）. AP clustering arithmetic is used to cluster training samples according to their operating points. Then, the sub-models are estimated by Gaussian Process Regression （GPR）. Finally, in order to get a global probabilistic prediction, Bayesian committee mactnne is used to combine the outputs of the sub-estimators. The proposed method has been applied to predict the light naphtha end point in hydrocracker fractionators. Practical applications indicate that it is useful for the online prediction of quality monitoring in chemical processes.
文摘Thanks to advances in tunnel boring machine(TBM)and monitoring,significant progress has been achieved in the application of soft computing techniques for the optimization of TBM tunneling and the reduction of disturbance related to tunneling in urban areas.Because experimental,analytical,and numerical methods have limitations in solving problems related to TBM tunneling,engineers can use soft computing techniques in analyzing the relationship between the target tunneling responses and influential design inputs parameters,including the geometrical,geological,and TBM operational factors.These techniques are useful in achieving robust and low-cost solutions.However,engineers face difficulties in making an optimal choice of the soft computing technique to solve the complex problems related to TBM tunneling.To help with this choice,this study presents state of the art about the use of soft computing techniques in TBM tunneling through practical applications.The study proposes recommendations for the optimal use of these techniques,in particular(i)the importance of preliminary analyses for the selection and reduction of input parameters,(ii)the necessity to complete insufficient data using laboratory tests and numerical modeling,(iii)the selection of reduced number of hidden layers and nodes to avoid overfitting,(iv)the use of recurrent neural networks to deal with time-series data,and(v)the association of soft computing methods with hybrid optimization techniques to reduce the risk of convergence to local minima.
基金supported in part by the National Natural Science Foundation of China (Grants 11290150 and 11290151)
文摘Soft machine refers to a kind of mechanical system made of soft materials to complete sophisticated missions, such as handling a fragile object and crawling along a narrow tunnel corner, under low cost control and actuation. Hence, soft machines have raised great challenges to computational dynamics. In this review article, recent studies of the authors on the dynamic modeling, numerical simulation, and experimental validation of soft machines are summarized in the framework of multibody system dynamics. The dynamic modeling approaches are presented first for the geometric nonlinearities of coupled overall motions and large deformations of a soft component, the physical nonlinearities of a soft component made of hyperelastic or elastoplastic materials, and the frictional contacts/impacts of soft components, respectively. Then the computation approach is outlined for the dynamic simulation of soft machines governed by a set of differential-algebraic equations of very high dimensions, with an emphasis on the efficient computations of the nonlinear elastic force vector of finite elements. The validations of the proposed approaches are given via three case studies, including the locomotion of a soft quadrupedal robot, the spinning deployment of a solar sail of a spacecraft, and the deployment of a mesh reflector of a satellite antenna, as well as the corresponding experimental studies. Finally, some remarks are made for future studies.
文摘Surface tension plays a core role in dominating various surface and interface phenomena. For liquid metals with high melting temperature, a profound understanding of the behaviors of surface tension is crucial in industrial processes such as casting, welding, and solidification, etc. Recently, the room temperature liquid metal （RTLM） mainly composed of gallium-based alloys has caused widespread concerns due to its increasingly realized unique virtues. The surface properties of such materials are rather vital in nearly all applications involved from chip cooling, thermal energy harvesting, hydrogen generation, shape changeable soft machines, printed electronics to 3D fabrication, etc. owing to its pretty large surface tension of approximately 700 mN/m. In order to promote the research of surface tension of RTLM, this paper is dedicated to present an overview on the roles and mechanisms of surface tension of liquid metal and summarize the latest progresses on the understanding of the basic knowledge, theories, influencing factors and experimental measure- ment methods clarified so far. As a practical technique to regulate the surface tension of RTLM, the fimdamental principles and applications of electrowetting are also interpreted. Moreover, the unique phenomena of RTLM surface tension issues such as surface tension driven self- actuation, modified wettability on various substrates and the functions of oxides are discussed to give an insight into the acting mechanism of surface tension. Furthermore, future directions worthy of pursuing are pointed out.
文摘Severe gas disasters in deep mining areas are increasing,and traditional protective coal seam mining is facing significant challenges.This paper proposes an innovative technology using soft rock as the protective seam in the absence of an appropriate coal seam.Based on the geological engineering conditions of the new horizontal first mining area of Luling Coal Mine in Huaibei,China,the impacts of different mining parameters of the soft-rock protective seam on the pressure-relief effect of the protected coal seam were analyzed through numerical simulation.The unit stress of the protected coal seam,which was less than half of the primary rock stress,was used as the mining stress pressure-relief index.The optimized interlayer space was found to be 59 m for the first soft-rock working face,with a 2 m mining thickness and 105 m face length.The physicochemical characteristics of the orebody were analyzed,and a device selection framework for the soft-rock protective seam was developed.Optimal equipment for the working face was selected,including the fully-mechanized hydraulic support and coal cutter.A production technology that combined fully-mechanized and blasting-assisted soft-rock mining was developed.Engineering practices demonstrated that normal circulation operation can be achieved on the working face of the soft-rock protective seam,with an average advancement rate of 1.64 m/d.The maximum residual gas pressure and content,which were measured at the cut hole position of the protected coal seams(Nos.8 and 9),decreased to 0.35 MPa and 4.87 m^3/t,respectively.The results suggested that soft-rock protective seam mining can produce a significant gas-control effect.
基金supported by National Natural Science Foundation of China(No.62201624,32000939,21775168,22174167,51861145202,U20A20168)the Guangdong Basic and Applied Basic Research Foundation(2019A1515111183)+3 种基金Shenzhen Research Funding Program(JCYJ20190807160401657,JCYJ201908073000608,JCYJ20150831192224146)the National Key R&D Program(2018YFC2001202)the support of the Research Fund from Tsinghua University Initiative Scientific Research Programthe support from Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province(No.2020B1212060077)。
文摘Due to the development of the novel materials,the past two decades have witnessed the rapid advances of soft electronics.The soft electronics have huge potential in the physical sign monitoring and health care.One of the important advantages of soft electronics is forming good interface with skin,which can increase the user scale and improve the signal quality.Therefore,it is easy to build the specific dataset,which is important to improve the performance of machine learning algorithm.At the same time,with the assistance of machine learning algorithm,the soft electronics have become more and more intelligent to realize real-time analysis and diagnosis.The soft electronics and machining learning algorithms complement each other very well.It is indubitable that the soft electronics will bring us to a healthier and more intelligent world in the near future.Therefore,in this review,we will give a careful introduction about the new soft material,physiological signal detected by soft devices,and the soft devices assisted by machine learning algorithm.Some soft materials will be discussed such as two-dimensional material,carbon nanotube,nanowire,nanomesh,and hydrogel.Then,soft sensors will be discussed according to the physiological signal types(pulse,respiration,human motion,intraocular pressure,phonation,etc.).After that,the soft electronics assisted by various algorithms will be reviewed,including some classical algorithms and powerful neural network algorithms.Especially,the soft device assisted by neural network will be introduced carefully.Finally,the outlook,challenge,and conclusion of soft system powered by machine learning algorithm will be discussed.
基金supported by Tsinghua University and the Beijing Municipal Science and Technology Funding(Grant No.Z151100003715002)
文摘Soft robot is a kind of machine form with flexible deformation capability. Making flexible actuators has recently become a hot research topic in the field. In this study, we demonstrated the facile fabrication of a soft electromagnetic actuator using liquid metal coil of Ga-In alloys, and designed several illustrative mechanical devices, such as jellyfish like robot, soft fishtail and flexible manipulator. Measurements of the liquid metal coil's electrical properties confirmed that the liquid metal coil was mechanically stable under 48% uniaxial strains. Furthermore, the resistance of the liquid metal coil is stable under 60° bending deformation. Tests on the liquid metal coil's driving properties confirmed that the liquid metal coil(55 mm×55 mm×1 mm) could reach the maximum displacement amplitude of 21.5 mm with the current of 0.48 A. It was shown that the electromagnetic interaction between the magnet and the liquid metal coil enables the coil as a highly efficient actuator. The mechanisms lying behind were interpreted and future applications of such system were discussed.
基金financially supported by National Natural Science Foundation of China(No.21771017)the Fundamental Research Funds for the Central Universities。
文摘Fe-based metallic glasses(MGs)have shown great commercial values due to their excellent soft magnetic properties.Magnetism prediction with consideration of glass forming ability(GFA)is of great signifi-cance for developing novel functional Fe-based MGs.However,theories or models established based on condensed matter physics exhibit limited accuracy and some exceptions.In this work,based on 618 Fe-based MGs samples collected from published works,machine learning(ML)models were well trained to predict saturated magnetization(B_(s))of Fe-based MGs.GFA was treated as a feature using the experimental data of the supercooled liquid region(△T_(x)).Three ML algorithms,namely eXtreme gradient boosting(XGBoost),artificial neural networks(ANN)and random forest(RF),were studied.Through feature selection and hyperparameter tuning,XGBoost showed the best predictive performance on the randomly split test dataset with determination coefficient(R^(2))of 0.942,mean absolute percent error(MAPE)of 5.563%,and root mean squared error(RMSE)of 0.078 T.A variety of feature importance rankings derived by XGBoost models showed that T_(x) played an important role in the predictive performance of the models.This work showed the proposed ML method can simultaneously aggregate GFA and other features in ther-modynamics,kinetics and structures to predict the magnetic properties of Fe-based MGs with excellent accuracy.
