Prediction of rock mass classification in tunnel boring machine tunneling using the principal component analysis (PCA)-gated recurrent unit (GRU) neural network

Due to the complexity of underground engineering geology,the tunnel boring machine(TBM)usually shows poor adaptability to the surrounding rock mass,leading to machine jamming and geological hazards.For the TBM project of Lanzhou Water Source Construction,this study proposed a neural network called PCA-GRU,which combines principal component analysis(PCA)with gated recurrent unit(GRU)to improve the accuracy of predicting rock mass classification in TBM tunneling.The input variables from the PCA dimension reduction of nine parameters in the sample data set were utilized for establishing the PCA-GRU model.Subsequently,in order to speed up the response time of surrounding rock mass classification predictions,the PCA-GRU model was optimized.Finally,the prediction results obtained by the PCA-GRU model were compared with those of four other models and further examined using random sampling analysis.As indicated by the results,the PCA-GRU model can predict the rock mass classification in TBM tunneling rapidly,requiring about 20 s to run.It performs better than the previous four models in predicting the rock mass classification,with accuracy A,macro precision MP,and macro recall MR being 0.9667,0.963,and 0.9763,respectively.In Class II,III,and IV rock mass prediction,the PCA-GRU model demonstrates better precision P and recall R owing to the dimension reduction technique.The random sampling analysis indicates that the PCA-GRU model shows stronger generalization,making it more appropriate in situations where the distribution of various rock mass classes and lithologies change in percentage.

Structural mass prediction in conceptual design of blended-wing-body aircraft

The Blended-Wing-Body(BWB) is an unconventional configuration of aircraft and considered as a potential configuration for future commercial aircraft. One of the difficulties in conceptual design of a BWB aircraft is structural mass prediction due to its unique structural feature. This paper presents a structural mass prediction method for conceptual design of BWB aircraft using a structure analysis and optimization method combined with empirical calibrations. The total BWB structural mass is divided into the ideal load-carrying structural mass, non-ideal mass, and secondary structural mass. Structural finite element analysis and optimization are used to predict the ideal primary structural mass, while the non-ideal mass and secondary structural mass are estimated by empirical methods. A BWB commercial aircraft is used to demonstrate the procedure of the BWB structural mass prediction method. The predicted mass of structural components of the BWB aircraft is presented, and the ratios of the structural component mass to the Maximum TakeOff Mass(MTOM) are discussed. It is found that the ratio of the fuselage mass to the MTOM for the BWB aircraft is much higher than that for a conventional commercial aircraft, and the ratio of the wing mass to the MTOM for the BWB aircraft is slightly lower than that for a conventional aircraft.

Neutrinos Described as Vacuum Energy Excitations Predict Observed Neutrino Mass Sum

Reliable observations find only three neutrino mass eigenstates, oscillating between each other as neutrinos travel through space, and limit the sum of the three neutrino masses. At a minimum, any reliable description of neutrinos must allow only three neutrino mass eigenstates and predict a neutrino mass sum consistent with observations. This paper describes neutrinos as spheres, with radius one quarter of their Compton wavelength and thickness of the Planck length, surrounding a central core along their rotation axis, with diameter of the Planck length. This description of neutrinos as excitations of the vacuum energy allows only three neutrino mass eigenstates and predicts a neutrino mass sum consistent with observations.

Quantum Mechanics and General Relativity Identify Standard Model Particles as Black Holes

The Standard Model of particle physics does not account for charged fermion mass values and neutrino mass, or explain why only three particles are in each charge state 0, -e/3, 2e/3, and -e. These issues are addressed by treating Standard Model particles with mass m as spheres with diameter equal to their Compton wavelength l =ħ/mc, where ħis Planck’s constant and c the speed of light, and any charge in diametrically opposed pairs ±ne/6 with n = 1, 2, or 3 at the axis of rotation on the sphere surface. Particles are ground state solutions of quantized Friedmann equations from general relativity, with differing internal gravitational constants. Energy distribution within particles identifies Standard Model particles with spheres containing central black holes with mass m, and particle spin resulting from black hole angular momentum. In each charge state, energy distribution within particles satisfies a cubic equation in l, allowing only three particles in the charge state and requiring neutrino mass. Cosmic vacuum energy density is a lower limit on energy density of systems in the universe, and setting electron neutrino average energy density equal to cosmic vacuum energy density predicts neutrino masses consistent with experiment. Relations between charged fermion wavelength solutions to cubic equations in different charge states determine charged fermion masses relative to electron mass as a consequence of charge neutrality of the universe. An appendix shows assigning charge ±e/6 to bits of information on the event horizon available for holographic description of physics in the observable universe accounts for dominance of matter over anti-matter. The analysis explains why only three Standard Models are in each charge state and predicts neutrino masses based on cosmic vacuum energy density as a lower bound on neutrino energy density.

Mono-isotope Prediction for Mass Spectra Using Bayes Network

Mass spectrometry is one of the widely utilized important methods to study protein functions and components. The challenge of mono-isotope pattern recognition from large scale protein mass spectral data needs computational algorithms and tools to speed up the analysis and improve the analytic results. We utilized na¨？ve Bayes network as the classifier with the assumption that the selected features are independent to predict monoisotope pattern from mass spectrometry. Mono-isotopes detected from validated theoretical spectra were used as prior information in the Bayes method. Three main features extracted from the dataset were employed as independent variables in our model. The application of the proposed algorithm to public Mo dataset demonstrates that our na¨？ve Bayes classifier is advantageous over existing methods in both accuracy and sensitivity.

Optimal channels of the Garvey-Kelson mass relations in extrapolation

Garvey-Kelson mass relations connect nuclear masses of neighboring nuclei within high accuracy, and provide us with convenient tools in predicting unknown masses by extrapolations from existent experimental data. In this paper we investigate optimal"channels" of the Garvey-Kelson relations in extrapolation to the unknown regions, and tabulate our predicted masses by using these optimized channels of the Garvey-Kelson relations.