Recently,a novel type of neural networks,known as liquid neural networks(LNNs),has been designed from first principles to address robustness and interpretability challenges facing artificial intelligence(AI)solutions....Recently,a novel type of neural networks,known as liquid neural networks(LNNs),has been designed from first principles to address robustness and interpretability challenges facing artificial intelligence(AI)solutions.The potential of LNNs in telecommunications is explored in this paper.First,we illustrate the mechanisms of LNNs and highlight their unique advantages over traditional networks.Then we explore the opportunities that LNNs bring to future wireless networks.Furthermore,we discuss the challenges and design directions for the implementation of LNNs.Finally,we summarize the performance of LNNs in two case studies.展开更多
Accurate forecasting of buildings'energy demand is essential for building operators to manage loads and resources efficiently,and for grid operators to balance local production with demand.However,nowadays models ...Accurate forecasting of buildings'energy demand is essential for building operators to manage loads and resources efficiently,and for grid operators to balance local production with demand.However,nowadays models still struggle to capture nonlinear relationships influenced by external factors like weather and consumer behavior,assume constant variance in energy data over time,and often fail to model sequential data.To address these limitations,we propose a hybrid Transformer-based model with Liquid Neural Networks and learnable encodings for building energy forecasting.The model leverages Dense Layers to learn non-linear mappings to create embeddings that capture underlying patterns in time series energy data.Additionally,a Convolutional Neural Network encoder is integrated to enhance the model's ability to understand temporal dynamics through spatial mappings.To address the limitations of classic attention mechanisms,we implement a reservoir processing module using Liquid Neural Networks which introduces a controlled non-linearity through dynamic reservoir computing,enabling the model to capture complex patterns in the data.For model evaluation,we utilized both pilot data and state-of-the-art datasets to determine the model's performance across various building contexts,including large apartment and commercial buildings and small households,with and without on-site energy production.The proposed transformer model demonstrates good predictive accuracy and training time efficiency across various types of buildings and testing configurations.Specifically,SMAPE scores indicate a reduction in prediction error,with improvements ranging from 1.5%to 50%over basic transformer,LSTM and ANN models while the higher R²values further confirm the model's reliability in capturing energy time series variance.The 8%improvement in training time over the basic transformer model,highlights the hybrid model computational efficiency without compromising accuracy.展开更多
A soft-measuring approach is presented to measure the flux of liquid zinc with high temperature andcausticity. By constructing mathematical model based on neural networks, weighing the mass of liquid zinc, the fluxof ...A soft-measuring approach is presented to measure the flux of liquid zinc with high temperature andcausticity. By constructing mathematical model based on neural networks, weighing the mass of liquid zinc, the fluxof liquid zinc is acquired indirectly, the measuring on line and flux control are realized. Simulation results and indus-trial practice demonstrate that the relative error between the estimated flux value and practical measured flux value islower than 1.5%, meeting the need of industrial process.展开更多
The control of suitable and stable height of liquid column is the crucial point to operate the electromagnetic casting(EMC) process and to obtain ingots with desirable shape and dimensional accuracy. But due to the co...The control of suitable and stable height of liquid column is the crucial point to operate the electromagnetic casting(EMC) process and to obtain ingots with desirable shape and dimensional accuracy. But due to the complicated interact parameters and special circumstances, the measure and control of liquid column are quite difficult. A fuzzy neural network was used to help control the liquid column by predicting its height on line. The results show that the stabilization of the height of liquid column and surface quality of the ingot are remarkably improved by using the neural network based control system.展开更多
Artificial neural networks (ANN), being a sophisticated type of information processing system by imitating the neural system of human brain, can be used to investigate the effects of concentration of flux solution, te...Artificial neural networks (ANN), being a sophisticated type of information processing system by imitating the neural system of human brain, can be used to investigate the effects of concentration of flux solution, temperature of liquid aluminium, temperture of tools and pressure on thickness of the intermetallic layer at the interface between steel and aluminium under solid-liquid pressure bonding of steel and aluminium perfectly. The optimum thickness has been determined according to the value of the optimum shearing strength.展开更多
In this paper, the control method for fixed offshore platforms using semi-active tuned liquid column damper (TLCD) is presented. The equation of motion for the platform-TLCD control system is given and the semi-active...In this paper, the control method for fixed offshore platforms using semi-active tuned liquid column damper (TLCD) is presented. The equation of motion for the platform-TLCD control system is given and the semi-active control strategy is established. A back propagation artificial neural network (ANN) is used to adjust the orifice opening of TLCD because of the nonlinear motion of liquid in TLCD. The effectiveness of the control method is verified by numerical examples.展开更多
In order to use effectively renewable energy sources, we propose a new system, called Advanced Superconducting Power Conditioning System (ASPCS) that is composed of Superconducting Magnetic Energy Storage (SMES), Fuel...In order to use effectively renewable energy sources, we propose a new system, called Advanced Superconducting Power Conditioning System (ASPCS) that is composed of Superconducting Magnetic Energy Storage (SMES), Fuel Cell-Electrolyzer (FC-EL), hydrogen storage and DC/DC and DC/AC converters in connection with a liquid hydrogen station for fuel cell vehicles. The ASPCS compensates the fluctuating electric power of renewable energy sources such as wind and photovoltaic power generations by means of the SMES having characteristics of quick response and large Input-Output power, and hydrogen energy with FC-EL having characteristics of moderate response and large storage capacity. The moderate fluctuated power of the renewable energy is compensated by a trend forecasting method with the Artificial Neural Network. In case of excess of the power generation by the renewable energy to demand it is converted to hydrogen with EL. In contrast, shortage of the electric power is made up with FC. The faster fluctuation power that cannot be compensated by the forecasting method is effectively compensated by SMES. In the ASPCS, the SMES coil with an MgB2 conductor is operated at 20 K by using liquid hydrogen supplied from a liquid hydrogen tank of the fuel cell vehicle station. The necessary storage capacity of SMES is estimated as 50 MJ to 100 MJ depending on the forecasting time for compensating fluctuation power of the rated wind power generation of 5.0 MW. As a safety case, a thermosiphon cooling system is used to cool indirectly the MgB2 SMES coil by thermal conduction. In this paper, a trend forecasting result of output power of a wind power generation and the estimated storage capacity of SMES are reported.展开更多
In this paper, the volumetric properties of pure and mixture of ionic liquids are predicted using the developed statistical mechanical equation of state in different temperatures, pressures and mole fractions. The tem...In this paper, the volumetric properties of pure and mixture of ionic liquids are predicted using the developed statistical mechanical equation of state in different temperatures, pressures and mole fractions. The temperature dependent parameters of the equation of state have been calculated using corresponding state correlation based on only the density at 298.15 K as scaling constants. The obtained mean of deviations of modified equation of state for density of all pure ionic liquids for 1662 data points was 0.25%. In addition, the performance of the artificial neural network(ANN) with principle component analysis(PCA) based on back propagation training with28 neurons in hidden layer for predicting of behavior of binary mixtures of ionic liquids was investigated. The AADs of a collection of 568 data points for all binary systems using the EOS and the ANN at various temperatures and mole fractions are 1.03% and 0.68%, respectively. Moreover, the excess molar volume of all binary mixtures is predicted using obtained densities of EOS and ANN, and the results show that these properties have good agreement with literature.展开更多
A modified Miedema model using four atomic parameters and pattern recognition or artificial neural network has been used to study the factors that affect the entropy of mixing of liquid binary alloy systems. It has be...A modified Miedema model using four atomic parameters and pattern recognition or artificial neural network has been used to study the factors that affect the entropy of mixing of liquid binary alloy systems. It has been found that the systems with larger electronegativity difference (△Φ) usuallg have negative △Sxs of mixing, while the systems with larger valence electron density difference(denoted by △n) and small △Φ usually have positive △Sxs of mixing. The artificial neural network-atomic parameter method can be used to predict the △Sxs of binary alloy systems consisting of non-transition elements.展开更多
The surface tensions of pure liquid metals were estimated by using the artificial neural network method. Based on Butler's equation the surface tensions of some liquid Sn-, Ag-, Cu-based binary alloys were calcula...The surface tensions of pure liquid metals were estimated by using the artificial neural network method. Based on Butler's equation the surface tensions of some liquid Sn-, Ag-, Cu-based binary alloys were calculated from surface tensions of pure components and thermodynamic parameters of liquid alloys using a well designed computer program with C++ language, named STCBE. The agreement between calculated values and experimental data was excellent. The surface tensions of binary liquid Cu-RE(RE: Ce, Pr, Nd) alloys at 1400 K were predicted therewith.展开更多
The bonding of solid steel plate to liquid al uminum was studied using rapid solidification. The relationship models of interf acial shear strength and thickness of interfacial layer of bonding plate vs bond ing para...The bonding of solid steel plate to liquid al uminum was studied using rapid solidification. The relationship models of interf acial shear strength and thickness of interfacial layer of bonding plate vs bond ing parameters (such as preheat temperature of steel plate, temperature of alumi num liquid and bonding time) were respectively established by artificial neural networks perfectly.The bonding parameters for the largest interfacial shear stre ngth were optimized with genetic algorithm successfully. They are 226℃ for preh eating temperature of steel plate, 723℃ for temperature of aluminum liquid and 15.8s for bonding time, and the largest interfacial shear strength of bonding pl ate is 71.6 MPa . Under these conditions, the corresponding reasonable thickne ss of interfacial layer (10.8μm) is gotten using the relationship model establi shed by artificial neural networks.展开更多
The bonding of solid steel plate to liquid aluminum was studied by using rapid solidification. The relationship between the bonding parameters such as preheat temperature of steel plate, temperature of aluminum liquid...The bonding of solid steel plate to liquid aluminum was studied by using rapid solidification. The relationship between the bonding parameters such as preheat temperature of steel plate, temperature of aluminum liquid and bonding time, and the interfacial shear strength of bonding plate was established by artificial neural networks perfectly. This relationship was optimized with a genetic algorithm. The optimum bonding parameters are: 226 ℃ for preheat temperature of steel plate, 723 ℃ for temperature of aluminum liquid and 15.8 s for bonding time, and the largest interfacial shear strength of bonding plate is 71.6 MPa.展开更多
基金supported by the China National Key R&D Program under Grant Nos.2021YFA1000500 and 2023YFB2904804National Natural Science Foundation of China under Grant Nos.62331023,62101492,62394292 and U20A20158+1 种基金Zhejiang Provincial Natural Science Foundation of China under Grant No.LR22F010002Zhejiang Provincial Science and Technology Plan Project under Grant No.2024C01033。
文摘Recently,a novel type of neural networks,known as liquid neural networks(LNNs),has been designed from first principles to address robustness and interpretability challenges facing artificial intelligence(AI)solutions.The potential of LNNs in telecommunications is explored in this paper.First,we illustrate the mechanisms of LNNs and highlight their unique advantages over traditional networks.Then we explore the opportunities that LNNs bring to future wireless networks.Furthermore,we discuss the challenges and design directions for the implementation of LNNs.Finally,we summarize the performance of LNNs in two case studies.
基金the DEDALUS project grant number 101103998 funded by the European Commission as part of the Horizon Europe Framework Programme and within Ministry of Research,Innovation and Digitization,CNCS/CCCDI-UEFISCDI,project number PN-IV-P8-8.1-PRE-HE-ORG-2023-0111,within PNCDI IV.
文摘Accurate forecasting of buildings'energy demand is essential for building operators to manage loads and resources efficiently,and for grid operators to balance local production with demand.However,nowadays models still struggle to capture nonlinear relationships influenced by external factors like weather and consumer behavior,assume constant variance in energy data over time,and often fail to model sequential data.To address these limitations,we propose a hybrid Transformer-based model with Liquid Neural Networks and learnable encodings for building energy forecasting.The model leverages Dense Layers to learn non-linear mappings to create embeddings that capture underlying patterns in time series energy data.Additionally,a Convolutional Neural Network encoder is integrated to enhance the model's ability to understand temporal dynamics through spatial mappings.To address the limitations of classic attention mechanisms,we implement a reservoir processing module using Liquid Neural Networks which introduces a controlled non-linearity through dynamic reservoir computing,enabling the model to capture complex patterns in the data.For model evaluation,we utilized both pilot data and state-of-the-art datasets to determine the model's performance across various building contexts,including large apartment and commercial buildings and small households,with and without on-site energy production.The proposed transformer model demonstrates good predictive accuracy and training time efficiency across various types of buildings and testing configurations.Specifically,SMAPE scores indicate a reduction in prediction error,with improvements ranging from 1.5%to 50%over basic transformer,LSTM and ANN models while the higher R²values further confirm the model's reliability in capturing energy time series variance.The 8%improvement in training time over the basic transformer model,highlights the hybrid model computational efficiency without compromising accuracy.
基金Project (201AA411040) supported by National Plan and Development Committee.
文摘A soft-measuring approach is presented to measure the flux of liquid zinc with high temperature andcausticity. By constructing mathematical model based on neural networks, weighing the mass of liquid zinc, the fluxof liquid zinc is acquired indirectly, the measuring on line and flux control are realized. Simulation results and indus-trial practice demonstrate that the relative error between the estimated flux value and practical measured flux value islower than 1.5%, meeting the need of industrial process.
文摘The control of suitable and stable height of liquid column is the crucial point to operate the electromagnetic casting(EMC) process and to obtain ingots with desirable shape and dimensional accuracy. But due to the complicated interact parameters and special circumstances, the measure and control of liquid column are quite difficult. A fuzzy neural network was used to help control the liquid column by predicting its height on line. The results show that the stabilization of the height of liquid column and surface quality of the ingot are remarkably improved by using the neural network based control system.
文摘Artificial neural networks (ANN), being a sophisticated type of information processing system by imitating the neural system of human brain, can be used to investigate the effects of concentration of flux solution, temperature of liquid aluminium, temperture of tools and pressure on thickness of the intermetallic layer at the interface between steel and aluminium under solid-liquid pressure bonding of steel and aluminium perfectly. The optimum thickness has been determined according to the value of the optimum shearing strength.
文摘In this paper, the control method for fixed offshore platforms using semi-active tuned liquid column damper (TLCD) is presented. The equation of motion for the platform-TLCD control system is given and the semi-active control strategy is established. A back propagation artificial neural network (ANN) is used to adjust the orifice opening of TLCD because of the nonlinear motion of liquid in TLCD. The effectiveness of the control method is verified by numerical examples.
文摘In order to use effectively renewable energy sources, we propose a new system, called Advanced Superconducting Power Conditioning System (ASPCS) that is composed of Superconducting Magnetic Energy Storage (SMES), Fuel Cell-Electrolyzer (FC-EL), hydrogen storage and DC/DC and DC/AC converters in connection with a liquid hydrogen station for fuel cell vehicles. The ASPCS compensates the fluctuating electric power of renewable energy sources such as wind and photovoltaic power generations by means of the SMES having characteristics of quick response and large Input-Output power, and hydrogen energy with FC-EL having characteristics of moderate response and large storage capacity. The moderate fluctuated power of the renewable energy is compensated by a trend forecasting method with the Artificial Neural Network. In case of excess of the power generation by the renewable energy to demand it is converted to hydrogen with EL. In contrast, shortage of the electric power is made up with FC. The faster fluctuation power that cannot be compensated by the forecasting method is effectively compensated by SMES. In the ASPCS, the SMES coil with an MgB2 conductor is operated at 20 K by using liquid hydrogen supplied from a liquid hydrogen tank of the fuel cell vehicle station. The necessary storage capacity of SMES is estimated as 50 MJ to 100 MJ depending on the forecasting time for compensating fluctuation power of the rated wind power generation of 5.0 MW. As a safety case, a thermosiphon cooling system is used to cool indirectly the MgB2 SMES coil by thermal conduction. In this paper, a trend forecasting result of output power of a wind power generation and the estimated storage capacity of SMES are reported.
文摘In this paper, the volumetric properties of pure and mixture of ionic liquids are predicted using the developed statistical mechanical equation of state in different temperatures, pressures and mole fractions. The temperature dependent parameters of the equation of state have been calculated using corresponding state correlation based on only the density at 298.15 K as scaling constants. The obtained mean of deviations of modified equation of state for density of all pure ionic liquids for 1662 data points was 0.25%. In addition, the performance of the artificial neural network(ANN) with principle component analysis(PCA) based on back propagation training with28 neurons in hidden layer for predicting of behavior of binary mixtures of ionic liquids was investigated. The AADs of a collection of 568 data points for all binary systems using the EOS and the ANN at various temperatures and mole fractions are 1.03% and 0.68%, respectively. Moreover, the excess molar volume of all binary mixtures is predicted using obtained densities of EOS and ANN, and the results show that these properties have good agreement with literature.
文摘A modified Miedema model using four atomic parameters and pattern recognition or artificial neural network has been used to study the factors that affect the entropy of mixing of liquid binary alloy systems. It has been found that the systems with larger electronegativity difference (△Φ) usuallg have negative △Sxs of mixing, while the systems with larger valence electron density difference(denoted by △n) and small △Φ usually have positive △Sxs of mixing. The artificial neural network-atomic parameter method can be used to predict the △Sxs of binary alloy systems consisting of non-transition elements.
文摘The surface tensions of pure liquid metals were estimated by using the artificial neural network method. Based on Butler's equation the surface tensions of some liquid Sn-, Ag-, Cu-based binary alloys were calculated from surface tensions of pure components and thermodynamic parameters of liquid alloys using a well designed computer program with C++ language, named STCBE. The agreement between calculated values and experimental data was excellent. The surface tensions of binary liquid Cu-RE(RE: Ce, Pr, Nd) alloys at 1400 K were predicted therewith.
基金Funded by the National Natural Science Foundation of China(No.50274047 and 50304001)the Foundation of Ministry of Edu cation of Chinaand the Foundation of Bejing Jiaotong University
文摘The bonding of solid steel plate to liquid al uminum was studied using rapid solidification. The relationship models of interf acial shear strength and thickness of interfacial layer of bonding plate vs bond ing parameters (such as preheat temperature of steel plate, temperature of alumi num liquid and bonding time) were respectively established by artificial neural networks perfectly.The bonding parameters for the largest interfacial shear stre ngth were optimized with genetic algorithm successfully. They are 226℃ for preh eating temperature of steel plate, 723℃ for temperature of aluminum liquid and 15.8s for bonding time, and the largest interfacial shear strength of bonding pl ate is 71.6 MPa . Under these conditions, the corresponding reasonable thickne ss of interfacial layer (10.8μm) is gotten using the relationship model establi shed by artificial neural networks.
文摘The bonding of solid steel plate to liquid aluminum was studied by using rapid solidification. The relationship between the bonding parameters such as preheat temperature of steel plate, temperature of aluminum liquid and bonding time, and the interfacial shear strength of bonding plate was established by artificial neural networks perfectly. This relationship was optimized with a genetic algorithm. The optimum bonding parameters are: 226 ℃ for preheat temperature of steel plate, 723 ℃ for temperature of aluminum liquid and 15.8 s for bonding time, and the largest interfacial shear strength of bonding plate is 71.6 MPa.
