Search

BackgroundTraditional X-ray fluorescence spectrum analysis has the limitations of poor accuracy of the characteristic peak counting rate and shadow peak.PurposeThis study aims to propose a long and short term memory (LSTM) neural network model based on deep learning for the loss correction of the characteristic peak count rate and shadow peak.MethodsFirstly, a LSTM neural network model based on deep learning was proposed to estimate accurately the amplitudes of nuclear pulse signals by learning samples. Then, a convolutional neural network (CNN) with unique convolutional kernel structure was introduced to deal with the challenges of large sample size of the nuclear pulse signal and the low training efficiency of the model by extracting the sample features layer by layer, thereby effectively reducing the number of samples and the complexity of model training. Finally, a series of offline nuclear pulse sequences of powdered iron ore samples were used to generate the dataset required for model training. Among the 64 000 entries in this dataset, 44 800 were used as training sets, 12 800 were used as validation sets, and the remaining 6 400 were used as testing sets.ResultsThe trained CNN-LSTM model saves considerable training time, overcomes the defects of local convergence of traditional methods, and accurately estimates the parameters of input pulse under different degrees of distortion. Results show that the accuracy rate of the training and verification sets is greater than 99%. An analysis of the count repair results reveals that the average value of the correction ratio of the three shadow peaks, that is, the correction ratio of the depth learning model trained in this study to the count loss derived from the distorted pulses, is 91.52%.ConclusionsThe CNN-LSTM model can effectively correct the shadow peaks derived from the amplitude loss of distorted pulses and improve the accuracy of the characteristic peak count rate in X-ray fluorescence spectra. The model is shown to have high application value for the field of X-ray fluorescence spectroscopy.

Correctly and quickly measuring the attitude of aircraft is an important prerequisite for achieving precise docking missions for manned spacecraft. Traditional attitude measurement requires splicing three attitude parameters. This paper proposes an improved optimization algorithm that is applied to attitude measurement with electromagnetic wave structure vectors as reference, achieving synchronous, overall, and rapid measurement of attitude parameters. Firstly, a guidance vector in established based on the changing relationship between multiple electromagnetic vector sensors and received signals, the attitude rotation m the form of an exponential function in the guidance vector in expanded by Taylor approximation. Then an equal-step traversal algorithm combined with Newton method in used to quickly search the spectral peak of the space spectral function of multiple navigation signals, and the attitude measurement of the aircraft in completed. Simulation results show that the attitude measurement accuracy of this method is high and the error can be controlled at about 0. 01°, which improves the efficiency of attitude measurement. This method also has good anti-interference ability and has good application value. [ABSTRACT FROM AUTHOR]

Currently, a set of scientific, systematical quality competitiveness evaluation system are lacked in our country, which is applied to aviation equipment, including aircraft, engines and missiles repair factory.The system engineering theory and process analysis method are used to build the quality competitiveness evaluation index system in the aspects of quality system ability, quality support ability, quality operation ability and quality performance ability, which covers the quality competitiveness evaluation index system with 19 second-level and 60 third-level indexes.At the same time, an evaluation method based on the G1 expert combination of multiple relevant weights is proposed to comprehensively integrate the intention of decision makers or experts to form a set of standardized weight coefficients.According to the evaluation criteria, the quality competitiveness of aeronautic equipment repair factory is evaluated by experts using the scoring and fuzzy evaluation, and is further analyzed.The results show that the index system is rational, the evaluation method is feasible, and the system is of a certain guiding and referential significance for the aeronautic equipment repair factory to improve its quality competitiveness.

Cloud operation is a new operational mode brought by cloud computing technology in the military field. In the future aviation and space information confrontation, cloud operation will have the invisible power application and the combination of virtual and real combat operations. In this paper the construction requirements of aviation and space information equipment system are analyzed. Based on the concept of cloud operation, aviation and space information equipment system is constructed. The enlightenment of the cloud operation concept to the construction of aviation and space information equipment system is discussed. The winning mechanism of cloud operation, equipment integration capability, reliability and safety, and overall coordination etc., are studied. The research deepens the understanding of the requirements and implementation methods of the aviation and space information equipment system construction, and is of certain reference significance for the construction and application of the aerospace battlefield information equipment system.