1. College of Metrology and Measurement Engineering,China Jiang University,Hangzhou,Zhejiang 310018,China
2. Goldcard Smart Group Co. Ltd,Hangzhou,Zhejiang 310018,China
3. Zhejiang Testing & Inspection Institute for Mechanical and Electrical Products Quality Co. Ltd,Hangzhou,Zhejiang 310051, China
Abstract：Aiming at the problems of large influence of manual reading and low verification efficiency of wall oxygen inhaler, a verification method of wall oxygen inhaler based on deep learning is proposed. Images of the wall oxygen inhaler are taken by an industrial camera and fed into the improved residual block ResNet-18 network for automatic readings of the float flow meter. Residual block structure improvement strategies include: add a dropout network layer in the direct connection path; remove the 1×1 convolutional layer in the residual block; use the LeakyReLU activation function instead of the ReLU activation function. The dataset is divided into training set and test set according to the ratio of 51, and after 100 batches of training, the accuracy of the network model on the test set is 98.37%. The wall oxygen inhaler with qualified verification results of National Institute of Metrology is connected to the verification device for verification,and the maximum indication error of the float flowmeter is calculated to be±0.2L/min, the error is within the allowable range, and the verification results are the same. The results show that this method can replace manual reading and effectively improve the verification efficiency.
MAO M, LU J X, HONG C X, et al. Research on automatic oxygen inhaler detector based on machine vision［J］. Wireless Internet Technology, 2020, 17(11): 122-123.
ZHOU L, HE J, YU D D. Development of automatic verification system for buoy-type oxygen inhaler［J］. Metrology & Measurement Technique, 2021, 48(12): 76-79.
KANG T T, ZHANG L, WANG Y T, et al. Development of handheld digital multimeter automatic calibration device ［J］. Acta Metrologica Sinica, 2019, 40(S1): 107-110.
WEN K, HAN X, LI C, et al. Intelligent control system for verification process of natural gas flow meter based on neural network［J］. Natural Gas Industry, 2021, 41(7): 124-133.
［11］
SHI X. Person Re-identification Based on Improved Residual Neural Networks［C］//5th International Conference on Communication and Information Systems (ICCIS). Chongqing, China, 2021.
HUANG Y L, AI X. Classification of improved residual network in maize leaf disease images［J］. Computer Engineering and Applications, 2021, 57(23): 178-184.
ZHANG X, ZOU Y, SHI W. Dilated convolution neural network with LeakyReLU for environmental sound classification ［C］//22nd international conference on digital signal processing (DSP). London, UK, 2017.
［17］
LI X, RAI L. Apple leaf disease identification and classification using resnet models［C］//3rd International Conference on Electronic Information and Communication Technology (ICEICT). Shenzhen, China, 2020.
ZHANG J Y, SUN B, XIE X D, et al. Volume measurement method of trace liquid based on laser and machine vision［J］. Acta Metrologica Sinica, 2018, 39(4): 504-509.
Lü H H, WANG Z L, ZHANG H. Hyperspectral Image Classification Combining Edge Protection Filter and Deep Residual Network ［J］. Laser & Optoelectronics Progress, 2022, 59(16): 262-273.
［21］
JERMAK C J, JAKUBOWICZ M, DEREZYNSKI J, et al. Uncertainty of the air gauge test rig［J］. International Journal of Precision Engineering and Manufacturing, 2017, 18(4): 479-485.
［3］
LIU W, WU G, REN F, et al. DFF-ResNet: An insect pest recognition model based on residual networks［J］. Big Data Mining and Analytics, 2020, 3(4): 300-310.
LIN K N, ZHUANG Y, HUANG Y M. Research on small flow verification method of water meter based on machine vision［J］. Acta Metrologica Sinica, 2021, 42(9): 1167-1171.
SUN L, SUN B, ZHAO Y X. Development of automatic calibration system for dual-channel medical infusion pumps［J］. Acta Metrologica Sinica, 2019, 40(6): 1064-1070.
ZHANG S H, YAN X R, SANG Y. Single-image rain removal method based on residual and channel attention mechanism［J］. Acta Metrologica Sinica, 2021, 42(1): 20-28.
［15］
NAYEF B H, ABDULLAH S N H S, SULAIMAN R, et al. Optimized leaky ReLU for handwritten Arabic character recognition using convolution neural networks［J］. Multimedia Tools and Applications, 2022, 81(2): 2065-2094.
ZHU L, SONG X Q, XING X, et al. Research on tree species identification based on improved ResNet34 network［J］. Foreign Electronic Measurement Technology, 2022, 41(07): 119-125.
2024, Vol. 45 
