Abstract:Proposed is a two-dimensional (2D) spectrum analysis system for acquiring the statistical information of ra-dioactive particles on two dimensions, i.e. energy and time. Based on pulse width modulation readout circuit, such a system with 4-channels is designed, which converts the radiation signal into a rectangular pulse signal with pulse width modulated. The pulse width, occurrence time, and pulse count of the rectangular pulses are measured simultaneously with digital counters, so that the 2D spectra on energy and time of the radioactive particles can be obtained efficiently based on bi-parameter statistical analysis. A prototype of this 2D system is tested with gamma rays from 241Am isotopes, from which both the correlated 2D spectra and the independent spectra on energy and time are obtained. The energy spectra of four channels shows all characteristic peaks of 241Am gamma rays, among which the full-energy peak at 59.5keV exhibits energy resolution of about 5-6%, suggesting a good energy resolution and channel uniformity of the system. The regression of the time spectra of the characteristic peaks can give the time constants of each characteristic peak, revealing the time characteristics of the nuclear reactions in the radiative source.

Abstract:Automatic gauge control (AGC in the article) is the key technology of product thickness accuracy and flatness quality in modern cold rolling mill. Most traditional AGC control algorithms need stable external system con-ditions and hard to stabilize under complex interference that meets coverage requirements. This paper presents a new anti-interference strategy for AGC control of 20-Hi cold reversing mill. The proposed algorithm intro-duces a united dynamic weights algorithm of feed forward-mass flow to avoid the complex interference problem in AGC control, the relevant control strategy is provided to eliminate the adverse effects. At the same time, the D-value between feed forward-mass flow pre-computation and thickness measurement deviation is dynamic compared, the final gap position regulation is calculated by developing a set of united dynamic weights between feed forward control and mass flow control. Finally, the output of controllers is sent to actuator though a constant rate smoothing. The proposed strategy is compared with conventional AGC control on Experimental platform and project application, the results show that the proposed strategy is more stable than comparison method and majority of system uncertainty produced by mentioned interference is significantly eliminated.

Abstract:In order to improve the accuracy and efficiency of the measurement of the Shell Case size, a measurement system based on machine vision is introduced. Through the preprocessing, threshold segmentation algorithm and edge detection of the shell case image. Correlated size measurement of lines and circles in contour using binary search method and Hough transform. The experiment of detecting four sizes of 100 qualified shells shows that the system can realize the rapid and accurate detection of shell casings, and can be used to assess their quality performance. It effectively improves the detection efficiency and further improves the automation level of detection, which has a good application prospect.

Abstract:To address the problems of low detection accuracy and slow speed of traditional vision in the pharmaceutical industry, a YOLOv5s-EBD defect detection algorithm: Based on YOLOv5 network, firstly, the channel attention mechanism is introduced into the network to focus the network on defects similar to the pill background, re-ducing the time-consuming scanning of invalid backgrounds; the PANet module in the network is then replaced with BiFPN for differential fusion of different features; finally, Depth-wise separable convolution is used in-stead of standard convolution to achieve the output Finally, Depth-wise separable convolution is used instead of standard convolution to achieve the output feature map requirements of standard convolution with less number of parameters and computation, and improve detection speed. the improved model is able to detect all types of defects in tablets with an accuracy of over 94% and a detection speed of 123.8 fps, which is 4.27% higher than the unimproved YOLOv5 network model with 5.2 fps.

Abstract:At present, the over-travel measurement of high-voltage circuit breakers is mostly carried out after the circuit breaker is completely dismantled. The disadvantage of the measurement is that it can only be measured when the circuit breaker is dismantled and overhauled. Defects are diagnosed in a timely and effective manner, and capacity causes hidden troubles. This article provides a method for direct measurement of hydraulic circuit breakers without any adjustment or disassembly. The method can be carried out in various situations such as minor repairs, major repairs, and temporary repairs, which not only saves time, but also improves accuracy of the measurement. The comparative test results show that this method can be simple, convenient and effective to measure the overtravel of the high-voltage circuit breaker.

Abstract:Low-order wavefront error account for a large proportion of wave aberrations. A compensation method for low order aberration of projection lithography objective based on Interior Point Method is presented. Compensation model between wavefront error and degree of movable lens freedom is established. Converting over-determined system to underdetermined system, the compensation is solved by Interior Point Method (IPM). The presented method is compared with direct solve the over-determined system. Then, other algorithm GA, EA and PS is compared with IPM. Simulation and experimental results show that the presented compensation method can obtained compensation with less residuals compared with direct solve the over-determined system. Also, the presented compensation method can reduce computation time and obtain results with less residuals compare with AGA, EA and PS. Moreover, after compensation, RMS of wavefront error of the experimental lithography projection objective decrease from 56.05 nm to 17.88 nm.

Abstract:Recently, people have been paying more and more attention to mental health, such as depression, autism, and other common mental diseases. In order to achieve a mental disease diagnosis, intelligent methods have been actively studied. However, the existing models suffer the accuracy degradation caused by the clarity and oc-clusion of human faces in practical applications. This paper, thus, proposes a multi-scale feature fusion network that obtains feature information at three scales by locating the sentiment region in the image, and integrates global feature information and local feature information. In addition, a focal cross-entropy loss function is designed to improve the network's focus on difficult samples during training, enhance the training effect, and increase the model recognition accuracy. Experimental results on the challenging RAF_DB dataset show that the proposed model exhibits better facial expression recognition accuracy than existing techniques.

Abstract:Aluminum production is a high energy consumption process so that maintaining fundamental compositions in balance and optimal conditions are essential. The molten electrolyte and melted aluminum are primary materials and their boundary needs to be monitored from time to time. An automatic measurement technic is presented in the paper to substitute for the traditional manual measurement work that is dull, poor efficiency and dangerous for operators. The boundary forming mechanism is analyzed, the vertical profile of electric potential is simulated, an automatic in-strument is developed to sense the potential distribution, and a strategy is provided to identify the boundary according to the potential curves. Finally, some practical results are compared with manual measurements, which shows good consistency.