This paper presents a nonlinear model predictive control(NMPC) approach based on support vector machine(SVM) and genetic algorithm(GA) for multiple-input multiple-output(MIMO) nonlinear systems.Individual SVM is used ...This paper presents a nonlinear model predictive control(NMPC) approach based on support vector machine(SVM) and genetic algorithm(GA) for multiple-input multiple-output(MIMO) nonlinear systems.Individual SVM is used to approximate each output of the controlled plant Then the model is used in MPC control scheme to predict the outputs of the controlled plant.The optimal control sequence is calculated using GA with elite preserve strategy.Simulation results of a typical MIMO nonlinear system show that this method has a good ability of set points tracking and disturbance rejection.展开更多
The objective of the paper is to explore the fields of propulsion for rockets and defence systems tomeet the increasing demands for cost-effectiveness and faster and friendly manufacturing processes to increase the ef...The objective of the paper is to explore the fields of propulsion for rockets and defence systems tomeet the increasing demands for cost-effectiveness and faster and friendly manufacturing processes to increase the efficiency of the burn time/rate of solid rocket motors.This particular research includes the use of powerful machine learning algorithms applied on the burn rate dataset to predict the best burn rate.The main focus of this particular research is based on the burning rate study which has been carried out at ambient and different pressures of 2.068 MPa,4.760 MPa and 6.895 MPa with the use of binder as Hydroxyl-Terminated Polybutadiene,oxidizer as Ammonium Perchlorate and a catalyst as Iron Oxide.Two types of models are designed and created to predict the best burn rate from the experiments conducted namely;Empirical Mathematical Model and Machine Learning Regression.Empirical modelling gave an accuracy of 47%while Machine Learning Regression gave a prediction accuracy of nearly 99%.展开更多
This study examines the electrical resistivity of metals and binary,ternary alloy thin films across a broad range of compositions and microstructures through data-driven approaches.Electrical resistivity values for ov...This study examines the electrical resistivity of metals and binary,ternary alloy thin films across a broad range of compositions and microstructures through data-driven approaches.Electrical resistivity values for over 70,000 alloy compositions were measured through high-throughput experiments on combinatorially synthesized specimens.A machine learning prediction model was developed,and an explainable artificial intelligence(XAI)algorithm was utilized to identify the key features influencing electrical resistivity.The results demonstrate that the average valence electron concentration(VECavg)is the most significant descriptor governing the electrical resistivity of these alloys.Electronegativity difference(ΔEN)and mixing entropy(ΔS)were identified as collaborative features contributing to resistivity.The relationships between these features and resistivity are discussed in the context of traditional theoretical frameworks to provide a comprehensive understanding of the electrical behavior of alloys.展开更多
Changes in personality tend to be intertwined with life events(e.g.,family violence[FV]).This study aimed to examine the personality changes before and after an FV incident using Weibo data.Samples were selected from ...Changes in personality tend to be intertwined with life events(e.g.,family violence[FV]).This study aimed to examine the personality changes before and after an FV incident using Weibo data.Samples were selected from 1.16 million Weibo users in China who had posted their own FV experience as victims.We used Linguistic Inquiry and Word Count(LIWC)to extract the linguistic features of these unstructured texts as the scores of participants’personality.We built prediction models to measure and compare personality differences between the victim group and control group in Sample 1;and personality changes between the victim group and control group before and after an FV incident in Sample 2.Results showed that the victims’neuroticism increased and conscientiousness decreased after experiencing FV.At the same time,their agreeableness and openness levels were lower than those of the control group.Implications and limitations are also discussed.展开更多
基金Supported by the National Natural Science Foundation of China(21076179)the National Basic Research Program of China(2012CB720500)
文摘This paper presents a nonlinear model predictive control(NMPC) approach based on support vector machine(SVM) and genetic algorithm(GA) for multiple-input multiple-output(MIMO) nonlinear systems.Individual SVM is used to approximate each output of the controlled plant Then the model is used in MPC control scheme to predict the outputs of the controlled plant.The optimal control sequence is calculated using GA with elite preserve strategy.Simulation results of a typical MIMO nonlinear system show that this method has a good ability of set points tracking and disturbance rejection.
文摘The objective of the paper is to explore the fields of propulsion for rockets and defence systems tomeet the increasing demands for cost-effectiveness and faster and friendly manufacturing processes to increase the efficiency of the burn time/rate of solid rocket motors.This particular research includes the use of powerful machine learning algorithms applied on the burn rate dataset to predict the best burn rate.The main focus of this particular research is based on the burning rate study which has been carried out at ambient and different pressures of 2.068 MPa,4.760 MPa and 6.895 MPa with the use of binder as Hydroxyl-Terminated Polybutadiene,oxidizer as Ammonium Perchlorate and a catalyst as Iron Oxide.Two types of models are designed and created to predict the best burn rate from the experiments conducted namely;Empirical Mathematical Model and Machine Learning Regression.Empirical modelling gave an accuracy of 47%while Machine Learning Regression gave a prediction accuracy of nearly 99%.
基金supported by the Basic Science Research Program and Creative Materials Discovery Program through the National Research Foundation of Korea(NRF)funded by Ministry of Science and ICT(2020M3D1A1016092)Samsung Research Funding&Incubation Center of Samsung Electronics(SRFC-MA2202-01)+1 种基金Samsung Electronics Co.,Ltd.(IO201211-08077-01)the Institute of Information&Communications Technology Planning&Evaluation(IITP),grant funded by the Korea government(MSIT)under Grant No.RS-2025-02306043.
文摘This study examines the electrical resistivity of metals and binary,ternary alloy thin films across a broad range of compositions and microstructures through data-driven approaches.Electrical resistivity values for over 70,000 alloy compositions were measured through high-throughput experiments on combinatorially synthesized specimens.A machine learning prediction model was developed,and an explainable artificial intelligence(XAI)algorithm was utilized to identify the key features influencing electrical resistivity.The results demonstrate that the average valence electron concentration(VECavg)is the most significant descriptor governing the electrical resistivity of these alloys.Electronegativity difference(ΔEN)and mixing entropy(ΔS)were identified as collaborative features contributing to resistivity.The relationships between these features and resistivity are discussed in the context of traditional theoretical frameworks to provide a comprehensive understanding of the electrical behavior of alloys.
基金support from National Natural Science Foundation of China(Grant 31700984)Youth Innovation Promotion Association CAS.
文摘Changes in personality tend to be intertwined with life events(e.g.,family violence[FV]).This study aimed to examine the personality changes before and after an FV incident using Weibo data.Samples were selected from 1.16 million Weibo users in China who had posted their own FV experience as victims.We used Linguistic Inquiry and Word Count(LIWC)to extract the linguistic features of these unstructured texts as the scores of participants’personality.We built prediction models to measure and compare personality differences between the victim group and control group in Sample 1;and personality changes between the victim group and control group before and after an FV incident in Sample 2.Results showed that the victims’neuroticism increased and conscientiousness decreased after experiencing FV.At the same time,their agreeableness and openness levels were lower than those of the control group.Implications and limitations are also discussed.
