To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new lig...To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new light attention module,and a residue module—that are specially designed to learn the general dynamic behavior,transient disturbances,and other input factors of chemical processes,respectively.Combined with a hyperparameter optimization framework,Optuna,the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process.The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models,including the feedforward neural network,convolution neural network,long short-term memory(LSTM),and attention-LSTM.Moreover,compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1,the LACG parameters are demonstrated to be interpretable,and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM.This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling,paving a route to intelligent manufacturing.展开更多
A novel fluorene-based conjugated copolymer containing cyclobutenedione unit was synthesized by Suzuki reaction. Its structure and properties were characterized by FTIR, 1HNMR, elemental analysis, PL spectroscopy, DSC...A novel fluorene-based conjugated copolymer containing cyclobutenedione unit was synthesized by Suzuki reaction. Its structure and properties were characterized by FTIR, 1HNMR, elemental analysis, PL spectroscopy, DSC, TGA and cyclic voltammetry. The resulting polymer shows strong yellow PL emission (561 nm) and good solubility in polar aprotic solvents, i.e. THF, DMF, DMAC, DMSO, etc. DSC and TGA studies reveal that the novel polymer possesses excellent thermal stability with high glass transition temperature of 127℃ and onset decomposition temperature of 411℃. Cyclic voltammetry measurement demonstrated that the polymer has both hole and electron-transporting property.展开更多
Large cities suffer from traffic congestion,particularly at intersections,due to a large number of vehicles,which leads to the loss of time by increasing carbon emissions,including fuel consumption.Therefore,the need ...Large cities suffer from traffic congestion,particularly at intersections,due to a large number of vehicles,which leads to the loss of time by increasing carbon emissions,including fuel consumption.Therefore,the need for optimising the flow of vehicles at different intersections and reducing the waiting time is a critical challenge.Conventional traffic lights have been used to control traffic flow at different intersections and have been improved to become more efficient by using different algorithms,sensors and cameras.However,they also face some challenges,such as high-cost installation,operation,and maintenance issues.This paper develops a new system based on the Virtual Traffic Light(VTL)technology to improve traffic flow at different intersections and reduce the encountered loss of time and vehicles’travel time.Additionally,it reduces the costs of installation,maintenance and operation over various conventional traffic light systems.Consequently,the system proposes algorithms for traffic scheduling and lane identification by using vehicle ID,priority and time of arrival.To evaluate the system,four scenarios were presented where each scenario uses a different number of vehicles consisting of three types(emergency vehicles,public buses and private vehicles),each given a different priority.The proposed system is evaluated by integrating two simulators,namely,(OMNeT++)and(SUMO),and two frameworks,namely,(VEINS)and(INET)to prepare an appropriate working environment.the results prove that an improvement in the average travel time for several vehicles reaches 44.43%–49.76%compared with conventional traffic lights.Further,it is proven from the obtained results that the average waiting time for emergency vehicles is enhanced by 96.63%–97.63%,while the average waiting time for public buses is improved by 94.81%–97.23%.On the other hand,the waiting time for private vehicles‘improved by 87.14%to 89.71%’.展开更多
Classical Mechanics using Einstein’s theories of relativity places a limit on speed as the speed of light. Quantum Mechanics has no such limitation. To understand space accelerating faster than the speed of light and...Classical Mechanics using Einstein’s theories of relativity places a limit on speed as the speed of light. Quantum Mechanics has no such limitation. To understand space accelerating faster than the speed of light and information being exchanged instantaneously between two entangled electrons separated by huge distances, one uses Planck’s length, Planck’s time, and Planck’s mass to indicate that space and time are discrete and therefore along with masses smaller than Planck’s mass are Quantum Mechanical in nature. Faster than the speed of light c = 3 × 10<sup>8</sup> m/s is a classical effect only in dimensions of space lower than our 3-D Universe, but it is a Quantum effect in all dimensions of space. Because space can oscillate sending out ripples from the source, it is the medium used for transporting light waves and gravity waves.展开更多
基金support provided by the National Natural Science Foundation of China(22122802,22278044,and 21878028)the Chongqing Science Fund for Distinguished Young Scholars(CSTB2022NSCQ-JQX0021)the Fundamental Research Funds for the Central Universities(2022CDJXY-003).
文摘To equip data-driven dynamic chemical process models with strong interpretability,we develop a light attention–convolution–gate recurrent unit(LACG)architecture with three sub-modules—a basic module,a brand-new light attention module,and a residue module—that are specially designed to learn the general dynamic behavior,transient disturbances,and other input factors of chemical processes,respectively.Combined with a hyperparameter optimization framework,Optuna,the effectiveness of the proposed LACG is tested by distributed control system data-driven modeling experiments on the discharge flowrate of an actual deethanization process.The LACG model provides significant advantages in prediction accuracy and model generalization compared with other models,including the feedforward neural network,convolution neural network,long short-term memory(LSTM),and attention-LSTM.Moreover,compared with the simulation results of a deethanization model built using Aspen Plus Dynamics V12.1,the LACG parameters are demonstrated to be interpretable,and more details on the variable interactions can be observed from the model parameters in comparison with the traditional interpretable model attention-LSTM.This contribution enriches interpretable machine learning knowledge and provides a reliable method with high accuracy for actual chemical process modeling,paving a route to intelligent manufacturing.
文摘A novel fluorene-based conjugated copolymer containing cyclobutenedione unit was synthesized by Suzuki reaction. Its structure and properties were characterized by FTIR, 1HNMR, elemental analysis, PL spectroscopy, DSC, TGA and cyclic voltammetry. The resulting polymer shows strong yellow PL emission (561 nm) and good solubility in polar aprotic solvents, i.e. THF, DMF, DMAC, DMSO, etc. DSC and TGA studies reveal that the novel polymer possesses excellent thermal stability with high glass transition temperature of 127℃ and onset decomposition temperature of 411℃. Cyclic voltammetry measurement demonstrated that the polymer has both hole and electron-transporting property.
文摘Large cities suffer from traffic congestion,particularly at intersections,due to a large number of vehicles,which leads to the loss of time by increasing carbon emissions,including fuel consumption.Therefore,the need for optimising the flow of vehicles at different intersections and reducing the waiting time is a critical challenge.Conventional traffic lights have been used to control traffic flow at different intersections and have been improved to become more efficient by using different algorithms,sensors and cameras.However,they also face some challenges,such as high-cost installation,operation,and maintenance issues.This paper develops a new system based on the Virtual Traffic Light(VTL)technology to improve traffic flow at different intersections and reduce the encountered loss of time and vehicles’travel time.Additionally,it reduces the costs of installation,maintenance and operation over various conventional traffic light systems.Consequently,the system proposes algorithms for traffic scheduling and lane identification by using vehicle ID,priority and time of arrival.To evaluate the system,four scenarios were presented where each scenario uses a different number of vehicles consisting of three types(emergency vehicles,public buses and private vehicles),each given a different priority.The proposed system is evaluated by integrating two simulators,namely,(OMNeT++)and(SUMO),and two frameworks,namely,(VEINS)and(INET)to prepare an appropriate working environment.the results prove that an improvement in the average travel time for several vehicles reaches 44.43%–49.76%compared with conventional traffic lights.Further,it is proven from the obtained results that the average waiting time for emergency vehicles is enhanced by 96.63%–97.63%,while the average waiting time for public buses is improved by 94.81%–97.23%.On the other hand,the waiting time for private vehicles‘improved by 87.14%to 89.71%’.
文摘Classical Mechanics using Einstein’s theories of relativity places a limit on speed as the speed of light. Quantum Mechanics has no such limitation. To understand space accelerating faster than the speed of light and information being exchanged instantaneously between two entangled electrons separated by huge distances, one uses Planck’s length, Planck’s time, and Planck’s mass to indicate that space and time are discrete and therefore along with masses smaller than Planck’s mass are Quantum Mechanical in nature. Faster than the speed of light c = 3 × 10<sup>8</sup> m/s is a classical effect only in dimensions of space lower than our 3-D Universe, but it is a Quantum effect in all dimensions of space. Because space can oscillate sending out ripples from the source, it is the medium used for transporting light waves and gravity waves.
