Irregular Characteristics Research Articles

Local Three-Dimensional Characterization of Nonlinear Grain Boundary Length within Bulk ZnO Using Nanorobot in SEM

Aiming at the problems of lack of data on the nonlinear morphology to divide uneven grain boundary in bulk ceramics, a unique approach of nanorobot-based characterization of three-dimensional nonlinear structure length can be creatively proposed under scanning electron microscope to quantify the actual morphology of local micro-area grain boundary in bulk ZnO. Contour shapes of the targeted grain boundaries in plane X-Y can be imaged using SEM. Z-directional relative height differences at different positions can be sequentially probed by nanorobot. Experiments demonstrate that it is effective to characterize three-dimensional length structures of nonlinear grain boundaries in bulk materials. By quantifying Z-directional relative height differences, it can be verified to show that irregular characteristics exist in three-dimensional grain boundary length, which can extend the depth effect on nonlinear bulk conductance. Furthermore, this method can also obtain nonlinear quantitative topographies to divide grain boundaries to uneven structure in the analysis of bulk polycrystalline materials.

Mahasweta Devi: The Voice of Dalits and Tribal People

Writing is a mirror that reflects social recorded, financial and political occasions refracted through nonexistent or anecdotal domains of public sayings. Strangely, in such accounts, writing additionally mirrors the irregular characteristics or complexities that exist in social as well as individual connections. Like many other European writers, Indians also have launched a war against such political, social and economic exploitations of the oppressors. As people know that women are more kind enough by heart, that’s why they have explored the various social evils and maladies that are continuously ruining the lives of the marginalized people in the form of caste, creed and religion. Apart from writing about feminism and gender discrimination, they have also dealt with the other grave issues that destroy the lives of these marginalized outcastes. Their works reveal the true picture of the contemporary society where innocence is exploited through the corrupted ideas of human beings in this man-made society. The present research paper has tried to explore the plight of Dalits and Tribals in the works of Mahasweta Devi, one of the great marginal voices in Indian English Literature.

Storm-time variability of ionospheric irregularities over South America

The generation and development of ionospheric irregularities is an important topic of study in space weather, mainly because of their adverse effects on navigation and positioning systems, as well as in trans-ionospheric communications. To improve our prediction capabilities, it is necessary to better understand their variabilities during different geomagnetic conditions. The purpose of this research is to analyse the occurrence characteristics of ionospheric irregularities over South America during geomagnetic storms. Using data from six ionosondes and GPS stations in Brazil and Perú, observations from the JULIA radar and Swarm in situ electron density measurements, we examined the presence of irregularities during three intense storms (October 12, 2016, October 7, 2015 and August 25, 2018). Our data show that during the geomagnetic storms that occurred in October 2016 and October 2015, in the Brazilian region, the generation of ionospheric irregularities was usually inhibited during the storm recovery phase. During the main phase, spread-F was generated over the stations located close to the northern crest of the EIA, and it was inhibited over Cachoeira Paulista, a station near the southern crest. During the August 2018 storm, local winter, the geomagnetic activity may have helped generate the irregularities in all the stations analysed regardless of the phase of the storm. We suggest that the generation (inhibition) of irregularities is related to the effect of eastward (westward) storm time electric fields—disturbance dynamo electric fields and prompt penetration electric fields—that created favourable (unfavourable) conditions for the generation of irregularities by uplifting (lowering) the F region.

Characteristics of rail deformation caused by tunnel floor heave and corresponding running risk of high-speed train

• A four-year-long observation of uneven rail deformation is performed in two HSR tunnels. • The predominant wavelength and amplitude of rail deformation in tunnel are 3–30 m and 2–10 mm, respectively. • The heave transfer within track structure exhibits more significantly on wavelength than on amplitude. • Speed raising has strong effects on the magnitude and location of wheel-rail contact force. • The risk of derailment and passenger comfort is more sensitive to short- and long-wavelength floor heave, respectively. Floor heave is a huge threat to the safe operation of high-speed trains in tunnels. However, rare research recognizes the characteristics of the rail irregularity caused by tunnel floor heave and the corresponding running risk of high-speed trains. In this paper, uneven rail profiles observed within four years in two HSR tunnels are used to investigate the temporal variation and spatial distribution of tunnel floor heave. The predominant wavelength and amplitude of the heave profile are determined. Hypothetic floor heave profiles with a wide range of wavelength and amplitude are used as the input in the simulation of the dynamic response of a VRT (vehicle-rail-track) system. Based on the simulation, the transfer laws for the wavelength and amplitude of heave within the track structure are revealed. The wheel-rail contact force, the wheel load reduction rate, and the sperling factor under various floor heave profiles are calculated. The floor heave profile that may lead to a high risk of derailment and low passenger comfort is presented for two train speeds. The research reveals that the predominant range of the wavelength for the rail heave in the tunnel is from 3 m to 30 m, and that of the amplitude is 2 mm to 10 mm. The heave transfer law within the track structure is strongly affected by both the wavelength and amplitude of the floor heave profile. The deformation of the rail varies more significantly on wavelength than on amplitude. Speed raising strongly influences the wheel-rail contact force, the wheel load reduction rate, and the sperling factor. The passenger comfort is more sensitive to longer-wavelength floor heave, whereas the risk of the derailment is more sensitive to shorter-wavelength floor heave.

Cloud Detection Method Based on All-Sky Polarization Imaging.

Sky cloud detection has a significant application value in the meteorological field. The existing cloud detection methods mainly rely on the color difference between the sky background and the cloud layer in the sky image and are not reliable due to the variable and irregular characteristics of the cloud layer and different weather conditions. This paper proposes a cloud detection method based on all-sky polarization imaging. The core of the algorithm is the “normalized polarization degree difference index” (NPDDI). Instead of relying on the color difference information, this index identifies the difference between degree of polarization (DoPs) of the cloud sky and the clear sky radiation to achieve cloud recognition. The method is not only fast and straightforward in the algorithm, but also can detect the optical thickness of the cloud layer in a qualitative sense. The experimental results show a good cloud detection performance.

A Novel Hybrid Method to Predict PM2.5 Concentration Based on the SWT-QPSO-LSTM Hybrid Model

PM2.5 concentration is an important indicator to measure air quality. Its value is affected by meteorological factors and air pollutants, so it has the characteristics of nonlinearity, irregularity, and uncertainty. To accurately predict PM2.5 concentration, this paper proposes a hybrid prediction system based on the Synchrosqueezing Wavelet Transform (SWT) method, Quantum Particle Swarm Optimization (QPSO) algorithm, and Long Short-Term Memory (LSTM) model. First, the original data are denoised by the SWT method and taken as the input of the prediction model. Then, the main parameters of the LSTM model are optimized by global search based on the QPSO algorithm, which solves the problems of slow convergence and local extremum of traditional parameter training algorithms. Finally, the PM2.5 daily concentration data of Chengdu, Shijiazhuang, Shenyang, and Wuhan are predicted by the proposed SWT-QPSO-LSTM model, and the prediction results are compared with those of single prediction models and hybrid prediction models. The experimental results show that the proposed model achieves higher prediction precision and lower prediction error than other models.

Spectral properties of sub-kilometer-scale equatorial irregularities as seen by the Swarm satellites

The faceplates on-board the Swarm satellites have provided high-resolution measurements of electron density at a frequency of 16 Hz along the satellite paths. The 16-Hz electron density data from Swarm were analyzed to determine the spectral characteristics of the F-region ionospheric irregularities at Swarm altitudes. The electron density data covered all geographic longitudes with quasi-dipole latitude limited between ±30° and the period considered was from October 2014 to October 2018, when the data was available. The Power Spectral Densities (PSDs) observed follows a power law. The values of spectral indices obtained showed a peak centered at around −2.5, located at the Equatorial Ionization Anomaly (EIA) belts. The spectral indices were found to be sensitive to irregularity amplitude. The local time distribution of the spectral indices also showed a peak within the time sector 20:00 LT - 22:00 LT and then decreased gradually after about 22:00 LT till 06:00 LT. The peak of the spectral index was also observed in the South American-Atlantic-African longitudes and it was generally low in the Asian-Pacific region. The angle between the Swarm satellite orbital path and the magnetic field (∡(B,v)) was also examined and it was observed that the highest percentage of occurrence of ionospheric irregularities and the peak in spectral index was obtained only when the ∡(B,v) was between 20° and 40°. The local turbulence is anisotropic with respect to the background magnetic field as indicated by a more negative spectral index for larger ∡(B,v).

Response of lightly overconsolidated clay under irregular cyclic loading and comparison with predictions from the strain accumulation procedure

Offshore wind turbine foundations are designed to withstand environmental loads from the wind and waves, both of which are cyclic in nature. The current design methods consider site-specific cyclic load histories and typically require these to be translated from a time–load history with irregular characteristics to an idealised history of parcels of cycles with uniform amplitude and constant average load. The Rainflow counting method is typically used for this translation. The idealised history is then applied in a design method, for example the strain accumulation method. These methods assume that the idealised load history will give approximately the same effect on the soil as the irregular time history. This paper investigates this assumption by a laboratory test programme where the soil response under realistic irregular loading is compared with the response under idealised loading. The laboratory programme consists of cyclic direct simple shear tests on lightly overconsolidated North Sea clay. For most problems, the test results suggest that the assumption is reasonable and represents a convenient simplification for practical design. However, for load histories with large average load, prediction of permanent strain based on idealised histories may underestimate the strain observed in tests with irregular time histories.

Evolutionary power spectrum density of earthquake-induced rail geometric irregularities

China’s high-speed railway (HSR) construction has gradually extended to earthquake-vulnerable areas in recent years. However, there is currently a lack of studies on the characteristics of earthquake-induced rail irregularities, making it impossible to ascertain the threshold of post-earthquake train running speed. Taking the multi-span HSR simply supported girder bridge of a CRTS II-type track system as the research focus, the distribution models for residual rail irregularity under random seismic actions have been analyzed in this study. The statistical distribution of the evolutionary power spectrum density (EPSD) of the residual rail irregularity set is also explored. Based on the obtained results, the EPSD of earthquake-induced rail geometric irregularity was calculated, and a time-domain sample for earthquake-induced rail geometric irregularity was developed. Finally, the equating method of earthquake-induced rail geometric irregularity under different span numbers was discussed, and a method for fitting earthquake-induced rail geometric irregularity was proposed.

A Deep Convolutional Autoencoder for Automatic Motion Artifact Removal in Electrodermal Activity Signals: A Preliminary Study.

Automatic motion artifact (MA) removal in electrodermal activity (EDA) signals is a major challenge because of the aperiodic and irregular characteristics of EDA. Given the lack of a suitable MA removal algorithm, a substantial amount of EDA data is typically discarded, especially during ambulatory monitoring. Current methods for MA removal in EDA are feasible when data are corrupted with low magnitude artifacts. In this study, we propose a more data-driven deep convolutional autoencoder (DCAE) for automated motion artifact removal in EDA signals. The DCAE was trained using several publicly available datasets. We used both Gaussian white noise (GWN) and real-life induced MA data records collected in a laboratory setting to corrupt the clean EDA signals. We compared the performance of our DCAE network with three state-of-the-art methods using the performance metrics the signal-to-noise ratio (SNR) improvement (SNRimp), and the mean squared error (MSE). The proposed DCAE provided significantly higher SNRimpand lower MSE compared to three other methods for both synthetically and real-life induced MA. While the work is preliminary, this work illustrates a promising approach which can potentially be used to remove many different types of MA.

Regularized Convolutional Neural Network for Highly Effective Parallel Processing

Convolutional neural network (CNN) has been adopted in various areas. Using graphics processing unit (GPU), speed improvement can be achieved on CNN, and many studies have proposed such acceleration methods. However, parallelizing the CNN on GPU is not straightforward because there are irregular characteristics in generating output feature maps in typical CNN models. In this paper, we propose a method that maximizes the utilization of GPU by modifying convolution combinations of a well-known CNN network, LeNet-5. Our regularized implementation on a heterogeneous system has achieved an improvement of up to 37.26 times in convolution and sub-sampling layers. Further, an energy consumption reduction of up to 26.40 times is achieved.

An introduction to technological tools and process of Heritage Building Information Modeling (HBIM)

Heritage Building Information Modelling (or HBIM) is a multi-disciplinary process and a promising tool for the management and documentation of heritage structures. HBIM can record the significant historic events that have taken place in the built environment and is used to track the aging process of the built asset. However, the digital re-construction procedures for HBIM development associated with historic buildings are very challenging: the objects of the historic models consist of components whose heterogeneous, complex, and irregular characteristics and morphologies are not represented in the existing BIM software libraries. Unlike conventional BIM workflows for new constructions, the tried and tested tools and methods must be adapted, and even reinvented, for HBIM applications. This article introduces the basic concept of HBIM, a set of technological tools of data capture for HBIM model development, and a feasible HBIM workflow.

Multi-objective evolutionary algorithm based on decomposition with an external archive and local-neighborhood based adaptation of weights

Multi-objective evolutionary algorithms (MOEAs) present an interesting approach to solve multi-objective problems (MOPs). Moreover, studies on MOEAs with decomposition approaches have been rapidly growing and many have demonstrated that the distribution of weight vectors plays a key role in obtaining a uniform set of solutions. However, a uniform distribution of weight vectors at the beginning of the evolution may not always result in a uniform set of solutions in the objective space, as the results are highly dependent on the Pareto front shape. Pareto fronts with irregular shape (disconnected, inverted, etc.), are usually not present in all parts of the initial set of weight vectors and one approach to overcome this issue is to adapt the weight vectors to the shape of the Pareto front. To remedy this problem and contribute with the field of study, it is proposed an algorithm based on decomposition that adapts progressively its weight vectors during the evolution process. The algorithm is called Multi-objective Evolutionary Algorithm based on Decomposition with Local-Neighborhood Adaptation (MOEA/D-LNA). To better evaluate the adaptation of weight vectors, a set of benchmark functions with irregular characteristics is proposed through the Generalized Position-Distance (GPD) benchmark generator. Thereafter, the proposed algorithm is compared against other algorithms in the literature on three additional sets of benchmark functions and with two different procedures for the initialization of weight vectors. The experiments have shown promising results on irregular Pareto fronts, specially for disconnected and inverted ones.

Solar Cycle and Seasonal Variability of Martian Ionospheric Irregularities from Mars Atmosphere and Volatile Evolution Observations

Spacecraft observations around Mars show that ionospheric irregularities occur frequently in the Martian ionosphere. In this study, Mars Atmosphere and Volatile Evolution data (the region is below ∼200 km) during 2015 January to 2021 March were used to revisit the statistical characteristics of ionospheric irregularities and the comparison of irregularities in Martian years with higher or lower solar activity phase of solar cycle. Results show that the characteristics of the irregularities with a larger length scale associated with the magnetic field and solar zenith angle are similar to the previous studies. Moreover, our results show that the occurrence rate of irregularities exhibits dawn and dusk asymmetry, and the occurrence rate at dusk is higher than that at dawn. In addition, results demonstrate that the occurrence rate of irregularities is higher in Martian years with higher solar activity than Martian years with lower solar activity, which means that the solar cycle might play an important role in the formation of irregularity events. Further studies show that the solar zenith angle (SZA) and altitude at the maximum occurrence rate depend on the level of solar activity. The SZA and altitude of the maximum occurrence rate are smaller in the Martian year with higher solar activity than the lower. We also found that the rate of events is lower during the day than the terminator in the ionospheric dynamo region. By contrast, in the regions where both electrons and ions are magnetized, events have a higher rate during the day than the terminator. Furthermore, the seasonal variation of the irregularity events was also presented in this study. Results show that the occurrence rate in the dynamo region with 80° < SZA < 150° in MY34 and MY35 show an incremental trend from spring to winter, but this trend is not obvious in MY33.

Analytical representations of inherent structural irregularities in turnout crossing with moveable point

The inherent structural irregularities in turnouts are an impact source during train passing. The position of the wheel–rail contact point on the rails and the wheel trajectory can help reveal the characteristics of such structural irregularities. In this work, for a given nominal turnout, several parameterised single harmonic-shaped functions are selected as analytical representations to describe the inherent structural irregularities in a crossing with moveable point using multiobjective optimisation. The objective of the optimisation is achieved by ensuring that the responses of the analytical representation applied to a plain track are close to those of the turnout model under the constraint of maximum and minimum wheel–rail contact forces as well as a correlation coefficient. Thus, a plain track with irregularity functions can be considered an equivalent model to enable a fast modelling procedure and efficient assessment of vehicles. For a robust design in different traffic situations, two stochastic variables, namely the rail pad stiffness and axle load, are selected and are found to be significant. The influence of the random distributions of the input parameters on the statistical outputs of the wheel–rail contact forces is assessed using a descriptive sampling technique for several stochastic realizations.

Mesoscopic particulate system assembled from three-dimensional irregular particles

Particles around us are generally in the form of irregular characteristics in shape and size. Establishing rational mesoscale models that are suitable for different types of particles is of great significance to comprehensively evaluate the mechanical properties of particulate systems assembled from irregular particles. The preponderances of previous works are mainly focused on particle simulations using regular-shaped geometries or simple polyhedrons, and little is known about quantitative characterization for the particles with complex shape characteristics. In this paper, a series of novel and efficient algorithms are presented to generate three-dimensional particulate systems assembled from particles with irregular characteristics in shape and size. According to the developed particle generation algorithm and vector-growth algorithm, the convex- and concave particles with different shape- and size configurations are obtained. Parametric analysis of corresponding algorithm parameters on the shape- and size configurations of particles are quantitatively investigated in terms of different indexes, such as sphericity, angularity and size, which provides an important guidance for the shape- and size control of irregular particles. Based on the generated irregular particles, a series of algorithms are proposed to generate the particulate systems with random spatial characteristics as well. Employing the developed compaction algorithm, mesoscopic particulate systems with different particle gradations and compactness are generated precisely. To sum up, the present particle model provides insights into capturing and studying the meso-structure characteristics and macroscopic mechanical properties of particulate systems.

Abstract WMP116: Age-related Dysfunction In Leptomeningeal Collateral Remodeling After Ischemic Stroke

Introduction: The leptomeningeal collaterals (LMCs) are specialized brain surface arterioles that interconnect the major cerebral artery territories. Good outcome following ischemic stroke is highly correlated with high collateral number and function. Unfortunately, with aging and disease, the LMCs demonstrate impaired dilatory capacity, reduced vessel diameter, and even complete vessel loss (rarefaction). The present study examined the chronic remodeling capacity of LMCs following permanent stroke in young and aged mice. Methods: Young and aged C57BL6 mice (5 and 20 months) were subjected to permanent distal middle cerebral artery occlusion (pdMCAO). At 2 weeks or 3 months, LMCs were evaluated for inner diameter and VWF expression (% LMC coverage). We compared the LMCs feeding the occluded MCA territory (LMC ipsi) to the contralateral equivalent vessels (LMC contra). Diameter change is reported as fold change relative to the distal-most arteriole (DMA) associated with each LMC. Results: Young male mice demonstrated increased diameter of LMC ipsi relative to DMA at both 2 weeks (1.36 ± 0.075; n=24 vessels/4 mice, P&lt;0.01) and 3 months after stroke (1.27 ± 0.073, n=19 vessels/2 mice, P&lt;0.01). LMC contra were 0.901 ± 0.064 and 1.01 ± 0.053 for the same time points (n=19 and 10 vessels, P=NS). VWF expression was significantly increased in LMC ipsi at 2 weeks (ipsi 10.9 ± 2.87 vs. contra 2.91 ± 0.82, P&lt;0.05) and neared significance at 3 months (ipsi 6.45 ± 1.54 vs. contra 2.06 ± 0.264, P=0.051). Aged mice demonstrated increased diameter of LMC ipsi relative to DMA at 2 weeks (1.24 ± 0.052, n=25 vessels from 3 mice, P&lt;0.01), but not at 3 months (1.08 ± 0.044, n=14 from 2 mice, P=NS). Notably, the 3 month LMC ipsi vessels demonstrated irregular diameter and characteristics of rarefaction. LMC contra were 0.897 ± 0.032 and 0.967 ± 0.092 for the same time points (n=17 and 8 vessels, P=NS). VWF expression was significantly elevated in LMC ipsi vs. LMC contra at 2 weeks (6.74 ± 1.33 vs. 1.87 ± 0.361, P&lt;0.01), but not at 3 months (2.27 ± 0.387 vs. 1.81 ± 0.398, P=NS). Conclusions: Our data show lasting LMC remodeling in young stroke brain, consisting of increased LMC diameter and expression of VWF. With aging, LMC remodeling is transient and evidence of LMC rarefaction is apparent by 3 months.

Signatures of Equatorial Plasma Bubbles and Ionospheric Scintillations from Magnetometer and GNSS Observations in the Indian Longitudes during the Space Weather Events of Early September 2017

Scintillation due to ionospheric plasma irregularities remains a challenging task for the space science community as it can severely threaten the dynamic systems relying on space-based navigation services. In the present paper, we probe the ionospheric current and plasma irregularity characteristics from a latitudinal arrangement of magnetometers and Global Navigation Satellite System (GNSS) stations from the equator to the far low latitude location over the Indian longitudes, during the severe space weather events of 6–10 September 2017 that are associated with the strongest and consecutive solar flares in the 24th solar cycle. The night-time influence of partial ring current signatures in ASYH and the daytime influence of the disturbances in the ionospheric E region electric currents (Diono) are highlighted during the event. The total electron content (TEC) from the latitudinal GNSS observables indicate a perturbed equatorial ionization anomaly (EIA) condition on 7 September, due to a sequence of M-class solar flares and associated prompt penetration electric fields (PPEFs), whereas the suppressed EIA on 8 September with an inverted equatorial electrojet (EEJ) suggests the driving disturbance dynamo electric current (Ddyn) corresponding to disturbance dynamo electric fields (DDEFs) penetration in the E region and additional contributions from the plausible storm-time compositional changes (O/N2) in the F-region. The concurrent analysis of the Diono and EEJ strengths help in identifying the pre-reversal effect (PRE) condition to seed the development of equatorial plasma bubbles (EPBs) during the local evening sector on the storm day. The severity of ionospheric irregularities at different latitudes is revealed from the occurrence rate of the rate of change of TEC index (ROTI) variations. Further, the investigations of the hourly maximum absolute error (MAE) and root mean square error (RMSE) of ROTI from the reference quiet days’ levels and the timestamps of ROTI peak magnitudes substantiate the severity, latitudinal time lag in the peak of irregularity, and poleward expansion of EPBs and associated scintillations. The key findings from this study strengthen the understanding of evolution and the drifting characteristics of plasma irregularities over the Indian low latitudes.

Influence of Cooling Scenarios on the Evolution of Microstructures in Nickel-Based Single Crystal Superalloys

The reprecipitation and evolution of γ’ precipitates during various cooling approaches from supersolvus temperature are studied experimentally and via phase field simulation in nickel-based single crystal superalloys. The focus of this paper is to explore the influence of cooling methods on the evolution of the morphology and the distribution of γ’ precipitates. It is demonstrated that small and uniform spherical shape γ’ particles formed with air cooling method. When the average cooling rate decreases, the particle number decreases while the average matrix and precipitate channel widths increase. The shape of γ’ precipitates which changed from spherical to cubic and irregular characteristics due to the elastic interaction and elements diffusion are observed with the decrease of the average cooling rate. The phase field simulation results are in good agreement with the experimental results in this paper. The research is a benefit for the study of the rejuvenation heat treatment in re-service nickel-based superalloys.

Life Prediction Method of Remanufactured Machinery Equipment Based on Vibration Signal Feature Extraction

Mechanical equipment is a key component of mechanical equipment, and its working condition is directly related to the overall performance of mechanical equipment. Accurate evaluation and prediction of the performance degradation trend of mechanical equipment is of great significance to ensure the reliability and safety of the mechanical equipment system. Based on the data of typical faulty equipment, this paper analyzes the energy characteristic parameters of mechanical equipment under different types and degrees of failure in the time domain. Using amplitude spectrum analysis, Hilbert envelope demodulation and wavelet packet decomposition method, and other vibration signal processing methods, preliminary extraction of multiple statistical feature parameters are given. Secondly, in view of the irrelevant and redundant components of multiple statistical parameters, a new method for extracting fault features of mechanical equipment based on variance value and principal component analysis is proposed. This method can effectively classify the fault status of mechanical equipment. The effectiveness of the method is verified by actual equipment signals. After that, the value extracted from the vibration signal of the double-row roller equipment is used as the degradation feature. In order to reduce the influence of irregular characteristics in the vibration signal and simplify the complexity of the vibration signal, the wavelet transform and the support vector machine model are combined, according to the degradation after decomposition. The 95% confidence interval of the predicted value is also given. The SVM model is established based on data characteristics, and single-step and multistep prediction of equipment degradation trends are carried out. The prediction result shows that, according to the mapping position formula, the distribution of equipment degradation prediction points is obtained, and a 95% confidence interval based on the distribution of the prediction points is given. Finally, on the basis of completing feature extraction, this paper applies an unsupervised feature selection method. The sensitive characteristics of life prediction and the prediction results of a single SVM model and a neural network model are compared and analyzed at the same time.