The study of the critical behavior is important for classifying different configuration states.Recently,machine learning is capable of discriminating polymer states in the presence of human supervision.Here,we introdu...The study of the critical behavior is important for classifying different configuration states.Recently,machine learning is capable of discriminating polymer states in the presence of human supervision.Here,we introduce an unsupervised approach based on the self-organizing map(SOM)and the autoencoder network to locate critical phase transitions from raw configuration without the necessity for manual feature engineering.High-dimensional configuration data can be encoded to low-dimensional codes by employing neural network of multilayer restrictive Boltzmann machines and the intermediate code can also be reconstructed to high-dimensional input vector.And then the codes are used to cluster different configuration states for polymers adsorbed on the homogeneous and the stripe-patterned surface by the SOM network and K-Means method.This work presents an unusual tool to identify polymer configuration.展开更多
In this work,Monte Carlo simulations are used to study the critical adsorption behaviors of flexible polymer chains under the action of an external driving force F parallel to an attractive flat surface.The critical a...In this work,Monte Carlo simulations are used to study the critical adsorption behaviors of flexible polymer chains under the action of an external driving force F parallel to an attractive flat surface.The critical adsorption temperature Tc decreases linearly with increasing F,indicating that the driving force suppresses the adsorption of polymer.The conformation of polymer is also affected by the driving force.However,the effect of F is dependent on the competition between the driving force and temperature.Under strong force or at low temperature,the polymer is stretched along the direction of the force,while under weak force or at high temperature,the polymer is not stretched.When the force is comparable to the temperature,the polymer may be stretched perpendicular to the driving force,and below Tc,we observe conformational transitions from parallel to perpendicular and again to parallel by decreasing the temperature.We found that the perpendicular stretched conformation leads the polymer chain to synchronously move along the direction of the driving force.Moreover,the conformational transitions are attributed to the competition and cooperation between the driving force and the temperature.展开更多
基金supported by the Natienal Natural Science Foundation of China(No.11775161).
文摘The study of the critical behavior is important for classifying different configuration states.Recently,machine learning is capable of discriminating polymer states in the presence of human supervision.Here,we introduce an unsupervised approach based on the self-organizing map(SOM)and the autoencoder network to locate critical phase transitions from raw configuration without the necessity for manual feature engineering.High-dimensional configuration data can be encoded to low-dimensional codes by employing neural network of multilayer restrictive Boltzmann machines and the intermediate code can also be reconstructed to high-dimensional input vector.And then the codes are used to cluster different configuration states for polymers adsorbed on the homogeneous and the stripe-patterned surface by the SOM network and K-Means method.This work presents an unusual tool to identify polymer configuration.
基金financially supported by the Research Fund of Zhejiang Provincial Education Department(No.Y201738867)the National Natural Science Foundation of China(Nos.11775161,11875205,and 11974305)。
文摘In this work,Monte Carlo simulations are used to study the critical adsorption behaviors of flexible polymer chains under the action of an external driving force F parallel to an attractive flat surface.The critical adsorption temperature Tc decreases linearly with increasing F,indicating that the driving force suppresses the adsorption of polymer.The conformation of polymer is also affected by the driving force.However,the effect of F is dependent on the competition between the driving force and temperature.Under strong force or at low temperature,the polymer is stretched along the direction of the force,while under weak force or at high temperature,the polymer is not stretched.When the force is comparable to the temperature,the polymer may be stretched perpendicular to the driving force,and below Tc,we observe conformational transitions from parallel to perpendicular and again to parallel by decreasing the temperature.We found that the perpendicular stretched conformation leads the polymer chain to synchronously move along the direction of the driving force.Moreover,the conformational transitions are attributed to the competition and cooperation between the driving force and the temperature.
