Since in practical industrial applications, soft sensors based on static models often lead to low accuracy and poor robustness, a multiple neural network (MNN) model is presented to develop dynamic soft sensors. The a...Since in practical industrial applications, soft sensors based on static models often lead to low accuracy and poor robustness, a multiple neural network (MNN) model is presented to develop dynamic soft sensors. The approach is applied to building a dynamic soft sensor estimating the production component in a simulated binary distillation unit and good results are obtained.展开更多
现有的基于特高频（UHF）信号的局部放电时延定位方法研究重点多集中于提高时差的计算精度,而对系统定位误差的校正鲜有涉及。为此,论文直接从系统定位误差入手,提出了一种基于多神经网络的定位误差修正算法。在极径r∈[2 m, 6 m]、r∈[...现有的基于特高频（UHF）信号的局部放电时延定位方法研究重点多集中于提高时差的计算精度,而对系统定位误差的校正鲜有涉及。为此,论文直接从系统定位误差入手,提出了一种基于多神经网络的定位误差修正算法。在极径r∈[2 m, 6 m]、r∈[6 m, 12 m]及r∈[12 m, 18 m]这3个区间分段内建立了相应的误差补偿网络,利用有限个标定点的时延误差来训练径向基（RBF）神经网络,以模拟系统定位误差的分布特性,并对实际定位结果进行修正。仿真及实验结果表明,通过误差补偿网络的修正,提高了定位精确度、降低了定位结果的离散程度,最终可将定位距离误差控制在0.5 m以内,方向角误差控制在6°以内。研究结果验证了所提算法的误差修正能力。展开更多
Gear assembly errors can lead to the increase of vibration and noise of the system,which affect the stability of system.The influence can be compensated by tooth modification.Firstly,an improved three-dimensional load...Gear assembly errors can lead to the increase of vibration and noise of the system,which affect the stability of system.The influence can be compensated by tooth modification.Firstly,an improved three-dimensional loaded tooth contact analysis(3D-LTCA)method which can consider tooth modification and coupling assembly errors is proposed,and mesh stiffness calculated by proposed method is verified by MASTA software.Secondly,based on neural network,the surrogate model(SM)that maps the relationship between modification parameters and mesh mechanical parameters is established,and its accuracy is verified.Finally,SM is introduced to establish an optimization model with the target of minimizing mesh stiffness variations and obtaining more even load distribution on mesh surface.The results show that even considering training time,the efficiency of gear pair optimization by surrogate model is still much higher than that by LTCA method.After optimization,the mesh stiffness fluctuation of gear pair with coupling assembly error is reduced by 34.10%,and difference in average contact stresses between left and right regions of the mesh surface is reduced by 62.84%.展开更多
[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-base...[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.展开更多
文摘Since in practical industrial applications, soft sensors based on static models often lead to low accuracy and poor robustness, a multiple neural network (MNN) model is presented to develop dynamic soft sensors. The approach is applied to building a dynamic soft sensor estimating the production component in a simulated binary distillation unit and good results are obtained.
文摘现有的基于特高频（UHF）信号的局部放电时延定位方法研究重点多集中于提高时差的计算精度,而对系统定位误差的校正鲜有涉及。为此,论文直接从系统定位误差入手,提出了一种基于多神经网络的定位误差修正算法。在极径r∈[2 m, 6 m]、r∈[6 m, 12 m]及r∈[12 m, 18 m]这3个区间分段内建立了相应的误差补偿网络,利用有限个标定点的时延误差来训练径向基（RBF）神经网络,以模拟系统定位误差的分布特性,并对实际定位结果进行修正。仿真及实验结果表明,通过误差补偿网络的修正,提高了定位精确度、降低了定位结果的离散程度,最终可将定位距离误差控制在0.5 m以内,方向角误差控制在6°以内。研究结果验证了所提算法的误差修正能力。
基金Project(11972112)supported by the National Natural Science Foundation of ChinaProject(N2103024)supported by the Fundamental Research Funds for the Central Universities,ChinaProject(J2019-IV-0018-0086)supported by the National Science and Technology Major Project,China。
文摘Gear assembly errors can lead to the increase of vibration and noise of the system,which affect the stability of system.The influence can be compensated by tooth modification.Firstly,an improved three-dimensional loaded tooth contact analysis(3D-LTCA)method which can consider tooth modification and coupling assembly errors is proposed,and mesh stiffness calculated by proposed method is verified by MASTA software.Secondly,based on neural network,the surrogate model(SM)that maps the relationship between modification parameters and mesh mechanical parameters is established,and its accuracy is verified.Finally,SM is introduced to establish an optimization model with the target of minimizing mesh stiffness variations and obtaining more even load distribution on mesh surface.The results show that even considering training time,the efficiency of gear pair optimization by surrogate model is still much higher than that by LTCA method.After optimization,the mesh stiffness fluctuation of gear pair with coupling assembly error is reduced by 34.10%,and difference in average contact stresses between left and right regions of the mesh surface is reduced by 62.84%.
文摘[Objective]Accurate prediction of tomato growth height is crucial for optimizing production environments in smart farming.However,current prediction methods predominantly rely on empirical,mechanistic,or learning-based models that utilize either images data or environmental data.These methods fail to fully leverage multi-modal data to capture the diverse aspects of plant growth comprehensively.[Methods]To address this limitation,a two-stage phenotypic feature extraction(PFE)model based on deep learning algorithm of recurrent neural network(RNN)and long short-term memory(LSTM)was developed.The model integrated environment and plant information to provide a holistic understanding of the growth process,emploied phenotypic and temporal feature extractors to comprehensively capture both types of features,enabled a deeper understanding of the interaction between tomato plants and their environment,ultimately leading to highly accurate predictions of growth height.[Results and Discussions]The experimental results showed the model's ef‐fectiveness:When predicting the next two days based on the past five days,the PFE-based RNN and LSTM models achieved mean absolute percentage error(MAPE)of 0.81%and 0.40%,respectively,which were significantly lower than the 8.00%MAPE of the large language model(LLM)and 6.72%MAPE of the Transformer-based model.In longer-term predictions,the 10-day prediction for 4 days ahead and the 30-day prediction for 12 days ahead,the PFE-RNN model continued to outperform the other two baseline models,with MAPE of 2.66%and 14.05%,respectively.[Conclusions]The proposed method,which leverages phenotypic-temporal collaboration,shows great potential for intelligent,data-driven management of tomato cultivation,making it a promising approach for enhancing the efficiency and precision of smart tomato planting management.
