Multivariate Time Series Anomaly Detection Based on Spatial-Temporal Network and Transformer in Industrial Internet of Things

In the Industrial Internet of Things(IIoT),sensors generate time series data to reflect the working state.When the systems are attacked,timely identification of outliers in time series is critical to ensure security.Although many anomaly detection methods have been proposed,the temporal correlation of the time series over the same sensor and the state(spatial)correlation between different sensors are rarely considered simultaneously in these methods.Owing to the superior capability of Transformer in learning time series features.This paper proposes a time series anomaly detection method based on a spatial-temporal network and an improved Transformer.Additionally,the methods based on graph neural networks typically include a graph structure learning module and an anomaly detection module,which are interdependent.However,in the initial phase of training,since neither of the modules has reached an optimal state,their performance may influence each other.This scenario makes the end-to-end training approach hard to effectively direct the learning trajectory of each module.This interdependence between the modules,coupled with the initial instability,may cause the model to find it hard to find the optimal solution during the training process,resulting in unsatisfactory results.We introduce an adaptive graph structure learning method to obtain the optimal model parameters and graph structure.Experiments on two publicly available datasets demonstrate that the proposed method attains higher anomaly detection results than other methods.

Effects of Pr on the structure and magnetic properties of FePt alloys

The effects of Pr on the structure and magnetic properties of PrxFe60.5-xPt39.5 alloys （x = 0, 0.5, 1.0, and 1.5） were investigated. X-ray diffraction data indicated that the phase transition temperature of FePt based alloys from disordered face-centered-cubic to ordered face-centered-tetragonal cubic decreases with the increase in Pr concentration. Pr plays the role of a grain refiner and it can enhance the exchange coupling between soft magnetic phase and hard magnetic phase. The results indicate that the replacement of Fe by Pr can significantly improve the remanence and coercivity of the Fe60.5Pt39.5 alloy. These results can be explained on the basis of phase transformation and microstructure. Both the remanence ratio and coercivity of the FePt based alloy as a function of the Pr content are increased by the optimum addition of 0.5 at.% Pr.

Anomaly detection method based on kinematics model and nonholonomic constraint of vehicle

A method used to detect anomaly and estimate the state of vehicle in driving was proposed.The kinematics model of the vehicle was constructed and nonholonomic constraint conditions were added,which refer to that once the vehicle encounters the faults that could not be controlled,the constraint conditions are violated.Estimation equations of the velocity errors of the vehicle were given out to estimate the velocity errors of side and forward.So the stability of the whole vehicle could be judged by the velocity errors of the vehicle.Conclusions were validated through the vehicle experiment.This method is based on GPS/INS integrated navigation system,and can provide foundation for fault detections in unmanned autonomous vehicles.

STUDY ON DYNAMICS, STABILITY AND CONTROL OF MULTI-BODY FLEXIBLE STRUCTURE SYSTEM IN FUNCTIONAL SPACE

The dynamics, stability and control problem of a kind of infinite dimensional system are studied in the functional space with the method of modern Mathematics. First, the dynamical control model of the distributed parameter system with multi-body flexible and multi-topological structure was established which has damping, gyroscopic parts and constrained damping. Secondly, the necessary and sufficient condition of controllability and observability, the stability theory and asymptotic property of the system were obtained. These results expand the theory of the field about the dynamics and control of the system with multi-body flexible structure, and have important engineering significance.

Effect of Ho-doping on microstructure and magnetostriction of TbDyFe alloys

Tb0.3Dy0.7HoxFe1.95（x=0.00, 0.05, 0.10, 0.15, 0.20, 0.35, 0.50, 0.65） quaternary alloys were prepared by arc-melting and followed by annealing.The phases present and structure of the alloys were determined using a D8-Advance X-ray diffractometer.The magnetostriction of the alloys was studied by standard strain gauge technique.The dependence of Ho content on the structure, magnetostriction and density of the alloys was investigated in detail.The research results showed that Ho-doping did not change MgCu2-type cubic Laves structure in Tb0.3Dy0.7Fe1.95.When Ho content x≤0.2, rich rare earth phase presented in the alloys increased and magnetostriction of the alloys reduced evidently with increasing x, but for alloys with x〉0.2, the content of rich rare earth phase started to reduce and the magnetostriction increased quickly, especially at low magnetic field in the alloy with x=0.65 due to separation of rich rare earth phases on the surface of the alloy.

Preparation and Magnetostriction of Tb_(0.22)Dy_(0.48)Ho_(0.35)Fe_2 Alloys

Tb0.22Dy0.48Ho0.35Fe2 quaternary alloys are prepared by melting-top casting-annealing process. X-ray diffraction reveals that the alloy is single phase polycrystalline alloy with MgCu2 type cubic Laves phase structure, and (511) preferred orientation occurs in its. The magnetostriction measurements are carried out at room temperature using standard strain gauge technique in magnetic fields up to 400 kA·m-1. The results show that when the magnetic field, H, is 90 kA·m-1, the magnetostriction, λ, of Tb0.22Dy0.48Ho0.35Fe2 quaternary alloys is 260×10-6, and when the H is 210 kA·m-1, the λ is 438×10-6. When the H is 400 kA·m-1, the λ is up to the saturation value, 538×10-6. As compared with TbDyFe ternary alloys, the λ of the quaternary alloy is significantly higher when the H is less than or equal to 210 kA·m-1. When the H is 120 kA·m-1, the λ of the alloy is 333×10-6, 70×10-6 more than the ternary alloy. Research results and mechanism are discussed.

Recent Progress on Electrode Characteristics of Mg and Mg-Based Hydrogen Storage Alloys

Recent development of Mg and Mg-based hydrogen storage alloys used in Ni-MH battery was discussed extensively. The results obtained from recent studies prove that these alloys with nanocrystalline/amorphous structure formed by mechanical alloying (MA) or mechanical grinding (MG) have good electrode characteristics. In general, MA or MG, and elemental substitution alloying are regarded as the effective means to seek new system of Mg-based alloys and nano-composite with improved electrode characteristics. However, until now, the currently known improvement in these electrode characteristics is still far from reach to that required for commercial application.

Effects of R-site compositions on the meta-magnetic behavior of Tb_(1-x)Pr_x(Fe_(0.4)Co_(0.6))_(1.88)C_(0.05)(x=0, 0.8, and 1)

We investigate the low-temperature magnetic properties of intermetallic compounds Tb1-xPrx（Fe0.4Co0.6）1.88C0.05（x = 0, 0.8, and 1） by detailed magnetization measurements. Obvious temperature- and field-induced irreversibilities suggest the coexistence of multiple magnetic phases. Sharp magnetization jumps across the antiferromagnetic to ferromagnetic transition are observed only in the Pr-containing samples, indicating that the behavior of the avalanche-like growth of ferromagnetic clusters is mainly related to the light lanthanide Pr ions. In addition, the time relaxation, field sweep rate, and cooling field dependence of magnetization jumps in the sample with x = 1 are consistent with those in the martensitic scenario.

NONLINEAR CHARACTERIZATION OF CONCURRENT DUAL-BAND RF POWER AMPLIFIERS

In this paper, the synchronous concurrent dual-band RF signal is used to drive the RF Power Amplifier (PA). The nonlinear characterization of a concurrent dual-band RF PA is discussed while two band signals in the dual-band are modulated by CDMA2000 and WCDMA signals. When the two band signals in the dual-band of the PA are modulated with the same signals, it is found that the nonlinearity of the PA can be expressed by any of the two corresponding baseband data. On the other hand, when the two band signals in the dual-band of the PA are modulated with two different signals, the PA nonlinearity cannot be characterized by any of the two corresponding baseband data. In this case, its nonlinearity has to be denoted by a composite signals consisting of the two baseband signals. Consequently, the requirements for the speed of the A/D converter can be largely reduced. The experimental results with CDMA2000 and WCDMA signals demonstrate the speed of the A/D converter required is only 30 M Sample Per Second (SaPS), but it will be at least 70 M SaPS for the conventional method.

The Magnetic Anisotropy and Complete Phase Diagram of CuFeO2 Measured in a Pulsed High Magnetic Field up to 75 T

The magnetization behavior of a CuFeO2 single crystal grown by the floating zone technique is investigated with a pulsed high magnetic field. We observe a series of field-induced multi-step-like transitions with hysteresis, of which the critical magnetic fields are temperature-dependent and show anisotropy. By using a pulsed high magnetic field up to 75 T, the magnetization behavior shows that the critical transition magnetic fields of spin- flip/flop shift to lower field regions with an increase in temperature. According to the magnetization curves, a complete magnetic phase diagram is depicted.

Switchable Ferroelectric Diode Effect and Piezoelectric Properties of Bi_(0.9)La_(0.1)FeO_(3) Ceramics

Multiferroic ceramics Bi0.9La0.1FeO3 are synthesized by solid-state reactions and sintered at various temperatures.The rhombohedral structure with the space group R3c is confirmed by means of x-ray diffraction,and their multiferroic properties are investigated.Bi_(0.9)La_(0.1)FeO_(3) ceramics sintered at 880℃ are found to have the lowest leakage current density and the largest saturated polarization among all the samples.A diode-like currentvoltage hysteresis that could be switched by an external voltage is observed in the Bi_(0.9)La_(0.1)FeO_(3) ceramics.A typical “butterfly” shaped strain-versus-voltage curve is shown with a maximum strain of 0.09%o at 7kV.Roomtemperature magnetization exhibits a hysteresis loop,indicating that the modulation of the spin structure of BiFeOa has been suppressed.

Hadoop + Spark Platform Based on Big Data System Design of Agricultural Product Price Analysis and Prediction by HoltWinters

In the market of agricultural products, the price of agricultural products is affected by production cost, market supply and other factors. In order to obtain the market information of agricultural products, the price fluctuation can be analyzed and predicted. A distributed big data software platform based on Hadoop, Hive and Spark is proposed to analyze and forecast agricultural price data. Firstly, Hadoop, Hive and Spark big data frameworks were built to store the data information of agricultural products crawled into MYSQL. Secondly, the information of agricultural products crawled from MYSQL was exported to a text file, uploaded to HDFS, and mapped to spark SQL database. The data was cleaned and improved by Holt-Winters (three times exponential smoothing method) model to predict the price of agricultural products in the future. The data cleaned by spark SQL was imported and predicted by improved Holt-Winters into MYSQL database. The technologies of pringMVC, Ajax and Echarts were used to visualize the data.

Research on Detection Technology of Micro-Components on Circuit Board Based on Digital Image Processing

Aiming at the stability of the circuit board image in the acquisition process,this paper realizes the accurate registration of the image to be registered and the standard image based on the SIFT feature operator and RANSAC algorithm.The device detection model and data set are established based on Faster RCNN.Finally,the number of training was continuously optimized,and when the loss function of Faster RCNN converged,the identification result of the device was obtained.

Boundary Slip and Surface Interaction： A Lattice Boltzmann Simulation

The factors affecting slip length in Couette geometry flows are analysed by means of a two-phase mesoscopic lattice Boltzmann model including non-ideal fluid-fluid and fluid-wall interactions. The main factors influencing the boundary slip are the strength of interactions between fluid-fluid and fluid-wall particles. Other factors, such as fluid viscosity, bulk pressure may also change the slip length. We find that boundary slip only occurs under a certain density （bulk pressure）. If the density is large enough, the slip length will tend to zero. In our simulations, a low density layer near the wall does not need to be postulated a priori but emerges naturally from the underlying non-ideal mesoscopic dynamics. It is the low density layer that induces the boundary slip. The results may be helpful to understand recent experimental observations on the slippage of micro flows.

Reconstructing bubble profiles from gas-liquid two-phase flow data using agglomerative hierarchical clustering method

The knowledge of bubble profiles in gas-liquid two-phase flows is crucial for analyzing the kinetic processes such as heat and mass transfer, and this knowledge is contained in field data obtained by surface-resolved computational fluid dynamics (CFD) simulations. To obtain this information, an efficient bubble profile reconstruction method based on an improved agglomerative hierarchical clustering (AHC) algorithm is proposed in this paper. The reconstruction method is featured by the implementations of a binary space division preprocessing, which aims to reduce the computational complexity, an adaptive linkage criterion, which guarantees the applicability of the AHC algorithm when dealing with datasets involving either non-uniform or distorted grids, and a stepwise execution strategy, which enables the separation of attached bubbles. To illustrate and verify this method, it was applied to dealing with 3 datasets, 2 of them with pre-specified spherical bubbles and the other obtained by a surface-resolved CFD simulation. Application results indicate that the proposed method is effective even when the data include some non-uniform and distortion.

Deformation of Two-Dimensional Nonuniform-Membrane Red Blood Cells Simulated by a Lattice Boltzmann Model

To study two-dimensional red blood cells deforming in a shear flow with the membrane nonuniform on the rigidity and mass, the membrane is discretized into equilength segments. The fluid inside and outside the red blood cell is simulated by the D2Q9 lattice Boltzmann model and the hydrodynamic forces exerted on the membrane from the inner and outer of the red blood cell are calculated by a from the curvature of uniform-membrane, we find that stress-integration method. Through the global deviation when the membrane is nonuniform on the rigidity, the deviation first decreases with the time increases and implies that the terminal profile of the red blood cell is static. To a red blood cell with the mass nonuniform on the membrane, the deviation becomes more large, and the mass distribution affects the profile of the two sides of the flattened red blood cell in a shear flow.

Review of Alloy Membranes/Films for Hydrogen Separation or Purification

Hydrogen separation and purification are two important chemical processes in the extensive application of hydrogen energy. Membrane technology has opened up a potential solution to the problems of separation and purification in an energy effective way. Membranes of adequate hydrogen permeability, good thermal and mechanical stability are the key to successful application of membrane technology in hydrogen separation and purification. In this paper, the relative parameters concerning hydrogen permeability, the development of different types of membranes namely: palladium composite membranes; V-based alloy membranes, specific functionality embraced alloy membranes, metal hydride (MH) thin films and fabrications, were reviewed and discussed. Pd-free membranes are found to be the ideal alternatives. Suitable MH thin films with mono- or multi-layer microstructures produced by novel fabrication techniques, is likely to be the promising candidates due to possessing properties distinct from those of bulk materials in membrane form.

Multimodal interaction design and application in augmented reality for chemical experiment

Background Augmented reality classrooms have become an interesting research topic in the field of education,but there are some limitations.Firstly,most researchers use cards to operate experiments,and a large number of cards cause difficulty and inconvenience for users.Secondly,most users conduct experiments only in the visual modal,and such single-modal interaction greatly reduces the users'real sense of interaction.In order to solve these problems,we propose the Multimodal Interaction Algorithm based on Augmented Reality(ARGEV),which is based on visual and tactile feedback in Augmented Reality.In addition,we design a Virtual and Real Fusion Interactive Tool Suite(VRFITS)with gesture recognition and intelligent equipment.Methods The ARGVE method fuses gesture,intelligent equipment,and virtual models.We use a gesture recognition model trained by a convolutional neural network to recognize the gestures in AR,and to trigger a vibration feedback after a recognizing a five finger grasp gesture.We establish a coordinate mapping relationship between real hands and the virtual model to achieve the fusion of gestures and the virtual model.Results The average accuracy rate of gesture recognition was 99.04%.We verify and apply VRFITS in the Augmented Reality Chemistry Lab(ARCL),and the overall operation load of ARCL is thus reduced by 29.42%,in comparison to traditional simulation virtual experiments.Conclusions We achieve real-time fusion of the gesture,virtual model,and intelligent equipment in ARCL.Compared with the NOBOOK virtual simulation experiment,ARCL improves the users'real sense of operation and interaction efficiency.

Lattice Boltzmann Simulations of Particle-Particle Interaction in Steady Poiseuille Flow

The moving behaviour of two- and three-particles in a pressure-driven flow is studied by the lattice Boltzmann simulation in two dimensions. The time-dependent values, including particles＇ radial positions, translational velocities, angular velocities, and the x-directional distance between the particles are analysed extensively. The effect of flow Reynolds number on particle motion is also investigated numerically. The simulation results show that the leading particle equilibrium position is closer to the channel centre while the trailing particle equilibrium position is closer to the channel wall. If Reynolds number Re is less than 85.30, the larger flow Reynolds number results in the smaller x-directional equilibrium distance, otherwise the x-directional distance increases almost linearly with the increase of time and the particles separate finally. The simulation results are helpful to understand the particle-particle interaction in suspensions with swarms of particles.

Interaction Study of Guest with Host in Clathrate Hydrate

Lattice dynamical simulations of noble gas hydrate structures I and II have been performed. Potential energies were investigated to study the influence of guest species on the stability of the hydrate structure. Results show that when the diameter of inclusion molecules is between 3 A and 4.2 A, such as Ar and Kr, the critical role of the 512 cage in the stabilization of hydrates becomes effective. For Xe hydrates SI and SII, with the help of lattice dynamical calculations, the modes attributions are identified directly. We proposed the resonant effect of the fingerprint frequency at about 7 meV and 10 meV which arise from the coupling of Xe molecules in the 512 cage with the host lattice.