Magnetic rings are widely used in automotive, home appliances, and consumer electronics. Due to the materials used, processing techniques, and other factors, there will be top cracks, internal cracks, adhesion, and other defects on individual magnetic rings during the manufacturing process. To find such defects, the most sophisticated YOLOv5 target identification algorithm is frequently utilized. However, it has problems such as high computation, sluggish detection, and a large model size. This work suggests an enhanced lightweight YOLOv5 (MR-YOLO) approach for the identification of magnetic ring surface defects to address these issues. To decrease the floating-point operation (FLOP) in the feature channel fusion process and enhance the performance of feature expression, the YOLOv5 neck network was added to the Mobilenetv3 module. To improve the robustness of the algorithm, a Mosaic data enhancement technique was applied. Moreover, in order to increase the network’s interest in minor defects, the SE attention module is inserted into the backbone network to replace the SPPF module with substantially more calculations. Finally, to further increase the new network’s accuracy and training speed, we substituted the original CIoU-Ioss for SIoU-Loss. According to the test, the FLOP and Params of the modified network model decreased by 59.4% and 47.9%, respectively; the reasoning speed increased by 16.6%, the model’s size decreased by 48.1%, and the mAP only lost by 0.3%. The effectiveness and superiority of this method are proved by an analysis and comparison of examples.
28 April 2022 in Measurement Science and Technology
The existing methods of contact respiration rate (RR) measurement can bring discomfort to the person being measured. However, RR is a human index that has to be monitored in clinical medicine. To overcome the limitations of contact measurement methods, a non-contact RR measurement method based on an infrared thermal camera is proposed. This is based on the phenomenon that human breathing causes periodic temperature changes around the nostrils. First, an infrared thermal camera is used to collect image sequences of the human face. And then, to track a region-of-interest (ROI) in moving image sequences, the You Only Look Once V3 deep learning method is used to track the nostril ROI from the recorded facial image sequences. The performance of the deep learning model is analyzed through experiments. The average temperature of the nostril ROI of the tracked image is calculated, and the temperature change value of the continuous image series can be obtained. The temperature change curve reflects the respiratory process. A Butterworth low-pass filter is used to filter the continuous temperature value to obtain robust respiratory signals, to improve the signal-noise ratio. Last, the respiratory rate is calculated by time-domain and frequency-domain methods. RR is calculated in different conditions, such as normal respiration, fast respiration, and slow respiration. Through the training, the training accuracy of the model reaches 97.9%. Experimental results show that the method can achieve high precision, and the maximum error is not more than 2%. Those indicate the proposed method can effectively measure the RR. Therefore, the proposed non-contact RR measurement method can be a useful reference for clinical RR measurement and other applications.
19 April 2017 in Measurement Science and Technology
In order to achieve high accuracy and good stability of temperature measurement results, an online vision-based temperature field measurement system for continuous casting billets is developed instead of the conventional single-point radiation pyrometer in this paper. This system is a hybrid temperature measurement system which consists of a monochrome array CCD camera with high resolution and a single spot colorimetric thermometer simultaneously. In this system, a narrow-band spectrum radiation temperature measurement model is established for the optical CCD-based pyrometer system, and the non-uniformity of the temperature field measurement due to the inter-element sensitivity deviations of the CCD-array detector and photometric distortion caused by the vignetting in the optical system is analyzed in detail and compensated. Furthermore, in order to eliminate the temperature fluctuation caused by the stripped iron oxide scale on billets, a temperature field reconstruction approach, which took full advantage of the high resolution characteristic of CCD and the distribution character of the surface temperature field of billets, is introduced in this system. Meanwhile, based on the narrow band spectral thermometry theory, the spot temperature measured by the colorimetric thermometer is used to correct the temperature field measured by the CCD camera on-line so as to reduce the temperature measurement error caused by the inconclusive absolute emissivity of different grades of steel and the interference of industrial dust. Currently, the system has been successfully applied and verified in some continuous casting production lines. Industrial trials indicate that the system could effectively eliminate false temperature variation caused by striped iron oxide scale and provide information about changes of processing parameters in the continuous casting production line in real time.
1 December 2007 in Journal of Systems Science and Complexity
In order to eliminate the influences of surface stripped iron oxide scale, dust and emissivity on temperature measurement for casting billets, a novel surface temperature measurement system based on multisensory information fusion technology is described in this paper. The system consists of a visible imaging charge coupled device (CCD) camera with high resolution, a colorimetric thermometer, an optical filter and associated software processing units. It makes use of the high resolution characteristic of CCD and the distribution character of surface temperature field of casting billets to reduce the temperature fluctuation aroused by the surface stripped iron oxide scale, and the spot temperature measured by the colorimetric thermometer is fused into the temperature field measured by the CCD camera to overcome shortcomings of merely using the CCD camera in temperature measurement, such as being susceptible to dust at wide field, and not capable of obtaining true temperature because of inconclusive emissivity for different grades of steel. In order to validate the effectiveness of the method proposed in this paper, temperatures of different grades of steel are measured by this system, and temperature is also measured by this system during the changes of the casting speed and the volume of the cooling water. All these measurement results show the maximum fluctuation of the temperature measured by this system was ±5 K and the surface temperature of casting billets measured by this system can reflect changes of processing parameters in the continuous casting production line in real time. Thus, the temperature measured by this system can be used as a feedback control parameter to improve the control for dynamically adjusting water distribution and casting speed in practical application.