A lifespan prediction model was developed based on a few samples to provide decision-making information for operation and maintenance,as well as improve the economy and safety of nuclear power plant(NPP)operations.Thi...A lifespan prediction model was developed based on a few samples to provide decision-making information for operation and maintenance,as well as improve the economy and safety of nuclear power plant(NPP)operations.This paper applies a Weibull model to forecast the lifespan of electronic cards with a few samples in NPPs.Relationship between the lifespan prediction of electronic cards and the ambient temperature is revealed using the Arrhenius equation.Censored samples are used to compensate for the lack of fault electronic card data.Scale parameter and shape parameter of the Weibull model are optimized by adjusting the weight ratio between the censored data and the fault data.Characteristic life is then obtained using the rank regression fitting equation.Parameters of the Arrhenius equation can be calculated by dividing the samples into groups according to the ambient temperature.A case study of the intermediate range high-voltage electric card of ex-core neutron detectors demonstrates that the lifespan prediction of electronic cards in NPPs can be successfully predicted with a few samples by combining the Weibull model and the Arrhenius model.This can help provide preventive maintenance recommendations for electronic cards.Finally,operation suggestions for the electronic card’s ambient temperature can be made by utilizing the temperature-life model.展开更多
How to use a few defect samples to complete the defect classification is a key challenge in the production of mobile phone screens.An attention-relation network for the mobile phone screen defect classification is pro...How to use a few defect samples to complete the defect classification is a key challenge in the production of mobile phone screens.An attention-relation network for the mobile phone screen defect classification is proposed in this paper.The architecture of the attention-relation network contains two modules:a feature extract module and a feature metric module.Different from other few-shot models,an attention mechanism is applied to metric learning in our model to measure the distance between features,so as to pay attention to the correlation between features and suppress unwanted information.Besides,we combine dilated convolution and skip connection to extract more feature information for follow-up processing.We validate attention-relation network on the mobile phone screen defect dataset.The experimental results show that the classification accuracy of the attentionrelation network is 0.9486 under the 5-way 1-shot training strategy and 0.9039 under the 5-way 5-shot setting.It achieves the excellent effect of classification for mobile phone screen defects and outperforms with dominant advantages.展开更多
基金the Major Scientific Instrument Research of National Natural Science Foundation of China(No.61627810)the National Science and Technology Major Program of China(No.2018YFB1305003)。
文摘A lifespan prediction model was developed based on a few samples to provide decision-making information for operation and maintenance,as well as improve the economy and safety of nuclear power plant(NPP)operations.This paper applies a Weibull model to forecast the lifespan of electronic cards with a few samples in NPPs.Relationship between the lifespan prediction of electronic cards and the ambient temperature is revealed using the Arrhenius equation.Censored samples are used to compensate for the lack of fault electronic card data.Scale parameter and shape parameter of the Weibull model are optimized by adjusting the weight ratio between the censored data and the fault data.Characteristic life is then obtained using the rank regression fitting equation.Parameters of the Arrhenius equation can be calculated by dividing the samples into groups according to the ambient temperature.A case study of the intermediate range high-voltage electric card of ex-core neutron detectors demonstrates that the lifespan prediction of electronic cards in NPPs can be successfully predicted with a few samples by combining the Weibull model and the Arrhenius model.This can help provide preventive maintenance recommendations for electronic cards.Finally,operation suggestions for the electronic card’s ambient temperature can be made by utilizing the temperature-life model.
文摘How to use a few defect samples to complete the defect classification is a key challenge in the production of mobile phone screens.An attention-relation network for the mobile phone screen defect classification is proposed in this paper.The architecture of the attention-relation network contains two modules:a feature extract module and a feature metric module.Different from other few-shot models,an attention mechanism is applied to metric learning in our model to measure the distance between features,so as to pay attention to the correlation between features and suppress unwanted information.Besides,we combine dilated convolution and skip connection to extract more feature information for follow-up processing.We validate attention-relation network on the mobile phone screen defect dataset.The experimental results show that the classification accuracy of the attentionrelation network is 0.9486 under the 5-way 1-shot training strategy and 0.9039 under the 5-way 5-shot setting.It achieves the excellent effect of classification for mobile phone screen defects and outperforms with dominant advantages.
