Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

685results about How to "Strong characteristic" patented technology

State recognition and prediction method for spindle characteristic test bench based on deep learning

The invention relates to a state recognition and prediction method for a spindle characteristic test bench based on deep learning, which comprises the steps of collecting vibration signals in the operating process of the spindle characteristic test bench, performing normalization processing on the vibration signals, performing noise reduction processing on the normalized vibration signals by adopting EEMD (Ensemble Empirical Mode Decomposition) to obtain IMF components, and reconstructing the obtained IMF components to form restored signals; enabling the restored signals to serve as input samples of a CNN, performing feature extraction on the restored signals to obtain feature vectors, carrying out CNN feature learning on the feature vectors to obtain training feature samples; coding timeinformation for the training feature samples through a multi-layer LSTM (Long Short Term Memory), carrying out classification through Softmax logistic regression to obtain prediction feature samples,and realizing prediction for the operating state; and performing Softmax logistic regression through the training feature samples and the prediction feature samples, carrying out classification on a logistic regression layer so as to judge the fault type of a rotor rotation test bench system, and realizing state recognition. The state recognition and prediction method has fast response performanceand tracking performance.
Owner:BEIJING INFORMATION SCI & TECH UNIV

Method for preparing porous membranes based on selective swelling of block copolymers

The invention relates to a method for preparing porous membranes based on selective swelling of block copolymers. The method includes the steps of preparing a block copolymer (a block copolymer is formed by a block A and a block B) solution, preprocessing microfiltration basement membranes, coating the block copolymer solution on the processed microfiltration basement membranes, placing the microfiltration basement membranes coated with the block copolymer solution in a drying cabinet for vacuum heat treatment (a block copolymer layer solvent is volatilized to form membranes in the process), submerging the microfiltration basement membranes coated with the copolymer thin membranes in a solvent which has a selective swelling effect on one block of the block copolymer to be processed for a while, and taking out the microfiltration basement membranes coated with the copolymer thin membranes from the solvent for drying to obtain the compound porous membranes with block copolymer layers as separation layers and microfiltration basement membranes as supporting layers. The method is simple to operate, convenient and controllable. Chemical reaction is not involved, the prepared compound membranes have high mechanical strength, neat surface structure, and apparent potential of hydrogen (pH)-stimulus sensitivity, show good separation performances and have broad application prospects.
Owner:NANJING UNIV OF TECH

Hyperspectral remote sensing image classification method based on dense residual three-dimensional convolutional neural network

The invention discloses a hyperspectral remote sensing image classification method based on a dense residual three-dimensional convolutional neural network. According to the method, original hyperspectral data are used as network input, three-dimensional spatial-spectral features of a hyperspectral remote sensing image are extracted through three-dimensional convolution, the hyperspectral image can be directly processed through three-dimensional convolution, preprocessing operations such as dimension reduction are not needed, and the spatial-spectral features of the hyperspectral image are extracted more sufficiently. The dense residual network is used to deepen the number of network layers and learn deeper spectral and spatial features, the residual network can effectively reduce the problem of gradient disappearance along with the increase of the network depth, and the structure can more effectively utilize the features and enhance the feature transfer between convolutional layers. The training time is shortened through an early stop method, classification prediction is carried out through a Soft-max classifier, and an initial classification result is obtained; and proposing a multi-label conditional random field optimization algorithm, and optimizing a classification result. The method improves the operation efficiency, and improves the classification accuracy of the remotesensing images.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Method for detection of insertion deletion mutation based on second generation sequencing, device and storage medium

The present application discloses a method for detection of insertion deletion mutation based on second generation sequencing, a device and a storage medium. The method comprises the following steps:comparing a sample to be tested with a file of a reference genome to extract a set of candidate mutation sites with mutation allele frequency being greater than or equal to a threshold; filtering to remove sites in a short tandem repeat region; making detail statistics of comparison information of the mutation sites and comparison information surrounding the mutation sites, wherein the comparisoninformation includes InDel site and reference base support number, comparison quality, coverage depth, surrounding non-reference base and other insertion deletion mutations, surrounding read quality;and filtering to remove sites that do not reach the set threshold according to statistical information to obtain mutation results. The method does not require partial assembly, and filters second-generation sequencing data in advance to quickly eliminate most of false positive results caused by the comparison, reduces detection running time and computing resources, improves detection efficiency, has strong sensitivity and specificity, and can quickly and accurately detect InDel mutations.
Owner:深圳裕策生物科技有限公司

Multi-degree of freedom mixed entangled W-state photon producing system and method

The invention discloses a multi-degree of freedom mixed entangled W-state photon producing system and method. The multi-degree of freedom mixed entangled W-state photon producing system comprises a first mixing entanglement unit, a second mixing entanglement unit, a polarization entanglement unit and an entanglement exchange unit, wherein the first mixing entanglement unit is used for producing an orbital angular momentum-polarization entanglement photon pair, the second mixing entanglement unit is used for producing a linear momentum-polarization entanglement photon pair, the polarization entanglement unit is used for producing mutually-perpendicular polarization entanglement photon pairs, and the entanglement exchange unit is used for performing entanglement exchange on the orbital angular momentum-polarization entanglement photon pair, the linear momentum-polarization entanglement photon pair and the mutually-perpendicular polarization entanglement photon pairs and obtaining multi-degree of freedom mixed entangled W-state photons. The W-state photons facilitate improvement of the safety of quantum communication and have a strong entanglement characteristic and bit loss resisting capacity, and the influence of noise, decoherence and other factors is reduced.
Owner:国腾(广州)量子计算科技有限公司

Preparation method of polyacrylamide nano composite fracturing fluid

The invention adopts polyacrylamide and a nano inorganic phase to prepare a polyacrylamide nano composite material through an in-situ polymerization method and then forms a fracturing fluid thickening agent. The nano inorganic phase is prepared by mixing the products of intercalation reactions between an organic long-chain intercalator and layered silicate with magnesium nitrate and aluminum nitrate. The nano inorganic phase, acrylamide monomer, a coupling agent, a complexing agent, an initiator, an oxidant, a reductant, a cosolvent, an auxiliary agent, and deionized water form a suspension fluid reaction system, and the polyacrylamide nano composite material is formed after the polymerization-intercalation composite reactions. The polyacrylamide nano composite material with a mass percentage of 0.25% is taken as the thickening agent, and then is mixed with a crosslinking agent with a mass percentage of 0.20%, a gel breaker with a mass percentage of 0.20%, and other auxiliary agents to form a fracturing fluid system. The system is sheared for 70 minutes under a shearing speed of 170 s<-1> at a temperature of 150 DEG C so as to form a fracturing fluid with a viscosity larger than 50 mPa.s, and the fracturing fluid has the characteristics of high temperature resistance, shearing resistance, low frictional resistance, complete glue breaking effect, and good compatibility with the formation fluid.
Owner:CHINA UNIV OF PETROLEUM (BEIJING)

Method for controlling quality of radix scutellariae medicinal materials

The invention relates to a method for controlling the quality of radix scutellariae medicinal materials, comprising the following steps: taking standard radix scutellariae medical materials, obtaining a nuclear magnetic resonance spectroscopy thereof, and using characteristic ingredients of the radix scutellariae to identify the characteristic peak of medicinal effective ingredients as the characteristic peak of the radix scutellariae; taking a radix scutellariae sample to be tested, adopting the same method as a preparation method, a test condition and a test method of the standard radix scutellariae medical materials to test, obtaining a fingerprint electropherogram, and comparing the nuclear magnetic resonance spectroscopy of the radix scutellariae medicinal materials to be tested with the fingerprint electropherogram of the standard radix scutellariae medical materials. According to the differences of characteristic resonance peaks of the fingerprint electropherogram between the radix scutellariae medicinal materials to be tested and the standard radix scutellariae medical materials and number of common characteristic resonance peaks, the radix scutellariae medicinal materials can be classified as the following grades: high-class products: N is greater than 20, first-class products: N is greater than and equal to 18 and is less than or equal to 20, second-class products: N is greater than or equal to 16 and is less than 18, qualified products: N is greater than or equal to 14 and is less than 16, and unqualified products: N is less than 14.
Owner:SHANDONG ANALYSIS & TEST CENT

Seasoning placement control method and placement device

The invention discloses a seasoning placement control method and placement device. The seasoning placement control method comprises setting the flavor type through flavor type numerical strings; combining with heavy flavor coefficients to control the placement quantity; performing sorting flavor selection, flavor type figure flavor selection, divided feeding and the like. The seasoning placement device comprises CPU (Central Processing Unit) control units, a power supply, an input device and at least two feeding units and the structure is simple. Running program codes and at least dozens of flavor type numerical strings are stored in a storage of every CPU control unit, wherein sections of flavor quantity values of one certain flavor type numerical string are converted into corresponding seasoning feeding quantities respectively; the heavy flavor coefficients, food material weight parameters and the flavor type numerical strings can be input through the input device, wherein the flavor type numerical strings can be input, modified, stored and called; the flavor type numerical strings or flavor type composition figures can be displayed through a display and flavors can be distinguished and selected through figure viewing; a plurality of fan-shaped cabins are combined into a compact feeding unit layer and the lightning parallel feeding can be performed through the plurality of CPU control units. The seasoning placement control method and placement device is the optimum selection of kitchens, restaurant delicacy concoction and delicacy enjoyment supply.
Owner:宋大勇

Rolling bearing fault diagnosis method based on 1-DCNN (1-Dimensional Convolutional Neutral Network) and LSTM (Long Short-Term Memory) fusion

The invention discloses a rolling bearing fault diagnosis method based on 1-DCNN (1-Dimensional Convolutional Neutral Network) and LSTM (Long Short-Term Memory) fusion. The method comprises the following steps that a, data processing and expansion are carried out on original one-dimensional vibration signals through utilization of a sliding window overlapped sampling method, thereby obtaining expanded signals; b, the expanded signals are input into two channels of the 1-DCNN and the LSTM for training and analysis, and feature information is extracted, extraction is carried out in the 1-DCNN channel to obtain space feature information, and the extraction is carried out in the LSTM channel to obtain time feature information; c, the space feature information and the time feature information are concatenated through utilization of a concatenate layer, thereby obtaining concatenated features; and d, the concatenated features are connected with a full concatenate layer, and fault types are classified through utilization of a Softmax classifier. The method is relatively high in accuracy rate, relatively rapid in convergence rate and relatively low in loss and has high generalization and robustness.
Owner:GUIZHOU UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products