Shield tunnel lining is prone to water leakage,which may further bring about corrosion and structural damage to the walls,potentially leading to dangerous accidents.To avoid tedious and inefficient manual inspection,m...Shield tunnel lining is prone to water leakage,which may further bring about corrosion and structural damage to the walls,potentially leading to dangerous accidents.To avoid tedious and inefficient manual inspection,many projects use artificial intelligence(Al)to detect cracks and water leakage.A novel method for water leakage inspection in shield tunnel lining that utilizes deep learning is introduced in this paper.Our proposal includes a ConvNeXt-S backbone,deconvolutional-feature pyramid network(D-FPN),spatial attention module(SPAM).and a detection head.It can extract representative features of leaking areas to aid inspection processes.To further improve the model's robustness,we innovatively use an inversed low-light enhancement method to convert normally illuminated images to low light ones and introduce them into the training samples.Validation experiments are performed,achieving the average precision(AP)score of 56.8%,which outperforms previous work by a margin of 5.7%.Visualization illustrations also support our method's practical effectiveness.展开更多
Background HIRFL is a heavy ion accelerator built by the Institute of Modern Physics,Chinese Academy of Sciences,which constitutes a total length of over 900 m by the SFC,SSC,CSRm,CSRe and so on.It bears a lot of rese...Background HIRFL is a heavy ion accelerator built by the Institute of Modern Physics,Chinese Academy of Sciences,which constitutes a total length of over 900 m by the SFC,SSC,CSRm,CSRe and so on.It bears a lot of research task of the country,so to ensure its safe operation is very important.Purpose Cool-water system is a key part in HIRFL,and the parameters of the cool-water system need to be monitored before an accident occurs.Methods This article describes three aspects of the system,from the water leakage detection,pressure monitoring,to the water-level monitoring.A complete monitor system was designed and constructed,including the hardware structure;the data transfer mode,as well as specific control program.C++,FLASH and SCADA are used in the monitoring system.Results Fault alarm was performed timely and accurately by the monitoring system,and many accidents were avoided.Conclusion Water system monitoring is an important part of the accelerator control system.It will also play a major role in the construction of large-scale scientific device named HIAF in the further.展开更多
基金This work is funded by the National Natural Science Foundation of China(Grant Nos.62171114 and 52222810)the Fundamental Research Funds for the Central Universities(No.DUT22RC(3)099).
文摘Shield tunnel lining is prone to water leakage,which may further bring about corrosion and structural damage to the walls,potentially leading to dangerous accidents.To avoid tedious and inefficient manual inspection,many projects use artificial intelligence(Al)to detect cracks and water leakage.A novel method for water leakage inspection in shield tunnel lining that utilizes deep learning is introduced in this paper.Our proposal includes a ConvNeXt-S backbone,deconvolutional-feature pyramid network(D-FPN),spatial attention module(SPAM).and a detection head.It can extract representative features of leaking areas to aid inspection processes.To further improve the model's robustness,we innovatively use an inversed low-light enhancement method to convert normally illuminated images to low light ones and introduce them into the training samples.Validation experiments are performed,achieving the average precision(AP)score of 56.8%,which outperforms previous work by a margin of 5.7%.Visualization illustrations also support our method's practical effectiveness.
文摘Background HIRFL is a heavy ion accelerator built by the Institute of Modern Physics,Chinese Academy of Sciences,which constitutes a total length of over 900 m by the SFC,SSC,CSRm,CSRe and so on.It bears a lot of research task of the country,so to ensure its safe operation is very important.Purpose Cool-water system is a key part in HIRFL,and the parameters of the cool-water system need to be monitored before an accident occurs.Methods This article describes three aspects of the system,from the water leakage detection,pressure monitoring,to the water-level monitoring.A complete monitor system was designed and constructed,including the hardware structure;the data transfer mode,as well as specific control program.C++,FLASH and SCADA are used in the monitoring system.Results Fault alarm was performed timely and accurately by the monitoring system,and many accidents were avoided.Conclusion Water system monitoring is an important part of the accelerator control system.It will also play a major role in the construction of large-scale scientific device named HIAF in the further.
