Non-invasive load decomposition technology can obtain equipmentlevel power consumption information by disassembling household total load which can provide help for residents to improve theway of electricity consumptio...Non-invasive load decomposition technology can obtain equipmentlevel power consumption information by disassembling household total load which can provide help for residents to improve theway of electricity consumption.To solve the problems of single feature extraction scale and low decomposition accuracy of current load decomposition models a sequence-to-sequence model based on Inception-SimAM(simple,parameter-free attention)-BiLSTM(bidirectional long short-term memory network)was proposed.This model includes an improved Inception module which incorporates Batch Normalization to avoid the problem of overfitting the model.At the same time,the SimAM mechanism is used to compute the three-dimensional attention weight of the characteristic sequence(considering the spatial and channel dimensions)to optimize the feature of the load sequence.Finally,the input sequence is decomposed by the BiLSTM.The results based on the REDD dataset indicate the proposed model extracts multi-scale features and feature concerns without SimAM through the improved Inception module,which significantly improves the decomposition accuracy.展开更多
The internal solitary wave(ISW)represents a frequent and severe oceanic dynamic phenomenon observed in the South China Sea,exposing marine structures to sudden loads.This paper examines the prediction model of interac...The internal solitary wave(ISW)represents a frequent and severe oceanic dynamic phenomenon observed in the South China Sea,exposing marine structures to sudden loads.This paper examines the prediction model of interaction loads between ISW and FPSO,accounting for varying attack angles and incorporating ISW theories.The research demonstrates that the horizontal and transverse forces on FPSO under internal solitary waves(ISWs)comprise wave pressure difference force and viscous force,while the vertical force primarily consists of vertical wave pressure difference force.The wave pressure difference force is determined using the Froude-Krylov equation.The viscous force is derived from the tangential particle velocity induced by ISW and the viscous coefficient.The viscous coefficient formula is obtained through regression analysis of experimental data with different ISW attack angles.The research reveals that the horizontal viscous coefficient C_(vx)decreases as Reynolds number(R_(e))increases,while the transverse viscous coefficient C_(vy)initially increases and subsequently decreases with the growth of the Keulegan-Carpenter number(KC).Moreover,changes in wave propagation direction significantly affect the extreme magnitudes of both horizontal and transverse forces,and simultaneously modify the transverse force orientation,while having minimal impact on the vertical force.Additionally,the forces increase with the ISW’s amplitude.For horizontal and transverse forces,a thinner upper fluid layer generates larger forces.Comparative analysis of experimental,numerical,and theoretical results indicates strong agreement between theoretical predictions and experimental and numerical outcomes.展开更多
文摘Non-invasive load decomposition technology can obtain equipmentlevel power consumption information by disassembling household total load which can provide help for residents to improve theway of electricity consumption.To solve the problems of single feature extraction scale and low decomposition accuracy of current load decomposition models a sequence-to-sequence model based on Inception-SimAM(simple,parameter-free attention)-BiLSTM(bidirectional long short-term memory network)was proposed.This model includes an improved Inception module which incorporates Batch Normalization to avoid the problem of overfitting the model.At the same time,the SimAM mechanism is used to compute the three-dimensional attention weight of the characteristic sequence(considering the spatial and channel dimensions)to optimize the feature of the load sequence.Finally,the input sequence is decomposed by the BiLSTM.The results based on the REDD dataset indicate the proposed model extracts multi-scale features and feature concerns without SimAM through the improved Inception module,which significantly improves the decomposition accuracy.
基金supported by JUST Start-up Fund for Science Research,the Jiangsu Natural Science Foundation(Grant No.BK20210885).
文摘The internal solitary wave(ISW)represents a frequent and severe oceanic dynamic phenomenon observed in the South China Sea,exposing marine structures to sudden loads.This paper examines the prediction model of interaction loads between ISW and FPSO,accounting for varying attack angles and incorporating ISW theories.The research demonstrates that the horizontal and transverse forces on FPSO under internal solitary waves(ISWs)comprise wave pressure difference force and viscous force,while the vertical force primarily consists of vertical wave pressure difference force.The wave pressure difference force is determined using the Froude-Krylov equation.The viscous force is derived from the tangential particle velocity induced by ISW and the viscous coefficient.The viscous coefficient formula is obtained through regression analysis of experimental data with different ISW attack angles.The research reveals that the horizontal viscous coefficient C_(vx)decreases as Reynolds number(R_(e))increases,while the transverse viscous coefficient C_(vy)initially increases and subsequently decreases with the growth of the Keulegan-Carpenter number(KC).Moreover,changes in wave propagation direction significantly affect the extreme magnitudes of both horizontal and transverse forces,and simultaneously modify the transverse force orientation,while having minimal impact on the vertical force.Additionally,the forces increase with the ISW’s amplitude.For horizontal and transverse forces,a thinner upper fluid layer generates larger forces.Comparative analysis of experimental,numerical,and theoretical results indicates strong agreement between theoretical predictions and experimental and numerical outcomes.
