28 results about "Deep level" patented technology

The invention belongs to the technical field of semiconductor defect detection, and relates to a deep learning-based deep energy level defect identification method, system and device, and a medium. According to the method, transient curve data of an external capacitor is modulated to obtain a time sequence feature vector containing time, temperature and bias voltage information, then a multi-defect-induced weighted capacitor feature vector is obtained through calculation and modulation of a neural network model, and the time sequence feature vector and the multi-defect-induced weighted capacitor feature vector are trained after being spliced. Until the neural network model converges, the trained neural network model predicts a defect parameter vector, defect weight distribution and transient capacitance response at the (i + 1) th moment at the ith moment; according to the method, DLTS test data is modeled and analyzed in combination with a deep learning algorithm and a semiconductor deep energy level defect kinetic model, precise recognition and quantification of a complex defect system are achieved, the problem that defect recognition precision is insufficient in an existing DLTS test method is solved, and meanwhile the method is low in requirement for test equipment and high in applicability.

The invention discloses a multi-sliding-block die structure for a box shell die casting and a die casting method thereof.The die structure comprises four sliding blocks which are located on the four side faces of the die structure correspondingly and used for achieving four-side touch-through forming; the interior of at least one sliding block is cut to form an inclined small sliding block, and the small sliding block and the sliding block form a nested core-pulling structure which is used for forming a reverse groove or hole rib structure on the side face; the feeding hole is formed in the upper die and is used for injecting molten metal from the upper part; and an inductor is configured and used for controlling the small sliding block to exit before the sliding block in the demolding process, so that graded demolding is realized. The problem that a traditional single sliding block cannot process a groove / hole forming an included angle with the main demolding direction or forming a reverse direction with the main demolding direction is solved, and demolding with deeper features is completed while lateral core pulling is achieved through the nested small sliding block; and the small sliding block is tightly matched with the sliding block, so that the size precision and the surface quality of formed fine structures such as reverse grooves and thin ribs are ensured.

The invention belongs to the technical field of large-scale power grid safety guarantee, and particularly relates to a secondary virtual loop intelligent checking method and system based on a substation configuration file. According to the method, an electrical information fusion graph fusing primary wiring and secondary functions is constructed by analyzing a substation configuration file; secondly, performing reverse tracing to form an independent virtual loop causal chain aiming at an execution outlet node; calculating a full-link time sequence deviation of each virtual loop causal chain; and finally, performing weighted summation on respective time sequence deviations of a plurality of causal chains which are gathered at the same outlet and have mutually exclusive starting end function logics to obtain comprehensive risk weighted time delay, and judging whether virtual loop configuration conflicts exist or not according to a comparison result of an index and a preset threshold value. According to the method, accumulated time delay risks can be found, and hidden deep logic configuration conflicts among different functions can be identified and quantified, so that the substation configuration file checking depth and precision are remarkably improved, and the safety of large-scale power grid operation is ensured.

The invention relates to the technical field of deep learning, and particularly provides a joint classification method for hyperspectral images and laser radar data. The method comprises the following steps: firstly, extracting multi-scale features of multi-modal data through a decoupling three-branch encoder, and then carrying out attention guidance cross-modal fusion on three initial features of the same scale through an autonomously designed feature fusion module to obtain three multi-modal fusion features of different scales; inputting the deepest fusion feature into a weight sharing decoder, and obtaining pseudo data through a reconstruction task; and the real data and the pseudo data are identified by the structure consistency perception discriminator, and the discrimination loss is returned, so that the encoder parameters are updated, and iteration is performed to the optimal. And finally, inputting the three-scale fusion features obtained based on the optimal parameters into a multi-level feature fusion classifier to complete classification, thereby effectively improving the classification precision, and realizing the adaptive fusion and enhancement of the multi-modal features.

A hibernation depth management method and a solid state disk (SSD), the SSD periodically determines a set hibernation depth for itself according to a hibernation depth that an application function in the SSD can enter; wherein the set hibernation depth is a deepest level of hibernation depth that each application function in the SSD can enter. Embodiments of the present disclosure enable the SSD to adaptively adjust the hibernation depth, thereby achieving autonomous optimization of power consumption.

The present application relates to a method, device, equipment and medium for verifying the commissioning status of power equipment, and relates to the technical fields of power engineering auditing and artificial intelligence. It includes: parsing the submitted review materials using a multimodal document parsing model; inputting the dispatching operation power time series into a variational autoencoder model for sequence reconstruction calculation to obtain the reconstruction error and generate a time series anomaly feature component; generating a trajectory space anomaly feature component based on the spatio-temporal data of project personnel clock-in and the benchmark coordinates of the equipment ledger, and at the same time performing error level analysis on the on-site commissioning image data to generate an image anti-counterfeiting anomaly feature component; submitting the above multi-source heterogeneous data to a multimodal large model for cross-comparison and logical reasoning, breaking the limitation of only relying on the submitted review materials by a single party, identifying forgery behaviors from the source. With the equipment identifier as the only primary key, in the face of false commissioning scenarios with strong concealment and across multiple links, a multi-dimensional cross-verification closed loop is formed to identify deep造假行为 is misspelled. It should be "deep造假行为 is misspelled. It should be "deep forgery behaviors" here. So the corrected translation is as follows: The present application relates to a method, device, equipment and medium for verifying the commissioning status of power equipment, and relates to the technical fields of power engineering auditing and artificial intelligence. It includes: parsing the submitted review materials using a multimodal document parsing model; inputting the dispatching operation power time series into a variational autoencoder model for sequence reconstruction calculation to obtain the reconstruction error and generate a time series anomaly feature component; generating a trajectory space anomaly feature component based on the spatio-temporal data of project personnel clock-in and the benchmark coordinates of the equipment ledger, and at the same time performing error level analysis on the on-site commissioning image data to generate an image anti-counterfeiting anomaly feature component; submitting the above multi-source heterogeneous data to a multimodal large model for cross-comparison and logical reasoning, breaking the limitation of only relying on the submitted review materials by a single party, identifying forgery behaviors from the source. With the equipment identifier as the only primary key, in the face of false commissioning scenarios with strong concealment and across multiple links, a multi-dimensional cross-verification closed loop is formed to identify deep forgery behaviors.

The application discloses an ultrasonic signal classification and identification method, medium and equipment, and belongs to the technical field of signal processing and deep learning; the method comprises the following steps: collecting ultrasonic signals of excitation channels and receiving channels under different working conditions in structural ultrasonic detection, reconstructing channel signals into time sequence samples; inputting the time sequence samples into a double-branch deep learning model, and outputting working condition category probability distribution results; the double-branch deep learning model obtains the working condition category probability distribution results through a time domain feature extraction module, a space domain feature extraction module, a feature fusion module and a classification and prediction module; the application fully considers and utilizes the excitation and receiving signal features in ultrasonic detection, adopts a time and space domain feature fusion mode to fully capture multi-scale feature information and perform deep-level fusion, solves the problem that a single network is difficult to represent ultrasonic signal features from a multi-scale level, has strong engineering practicability, and can be widely applied in the fields of structural nondestructive detection, structural health monitoring and the like.

The application provides a lightweight steel surface defect detection method and device and processing equipment, which are based on a YOLOv11 model, deep adaptability optimization is performed, the steel surface defect detection task has better detection precision, the parameter quantity and the calculation quantity can be effectively reduced, the generalization ability is good, when the industrial terminal is deployed, the high performance and the lightweight can be considered, and thus the industrial application prospect is good.

The invention provides a high-electron-mobility silicon MOS (Metal Oxide Semiconductor) quantum device and a preparation method thereof. The method comprises the following steps: growing a dielectric layer on a silicon substrate; etching the dielectric layer and the silicon substrate to form a mesa structure; removing the dielectric layer by wet etching; cleaning the sample from which the dielectric layer is removed; growing a dielectric layer on the cleaned sample; repeatedly executing the step of removing the dielectric layer by wet etching until growing the dielectric layer on the cleaned sample for preset times; and preparing a metal electrode on the sample which is repeated for preset times. According to the preparation method, after RIE etching, silicon dioxide circulation oxidation is adopted for multiple times, an oxide layer is removed in combination with a buffer oxide etching solution, surface roughness scattering of the MOS structure can be greatly reduced, ionized intrinsic deep energy level defects introduced in the dielectric layer due to RIE table top etching can be removed by corroding original silicon dioxide, and the carrier mobility is effectively improved.

The application relates to the field of semiconductor technology and discloses a gallium oxide single crystal substrate defect map construction method and equipment, which comprises the following steps: preparing an ohmic contact on the back surface of a gallium oxide single crystal substrate to form a capacitor structure for deep level transient spectrum measurement; setting a high-density two-dimensional measurement grid point on the surface to be measured; controlling an automatic translation platform to make the gallium oxide single crystal substrate move in sequence, automatically collecting deep level transient spectrum signals on each two-dimensional measurement grid point through a programmable fast DLTS measurement system to obtain DLTS spectra of each two-dimensional measurement grid point; automatically analyzing the DLTS spectra of each two-dimensional measurement grid point, identifying deep level defects of different categories, and calculating the concentration of each category of deep level defects in each two-dimensional measurement grid point; and based on the identified defect categories and the concentration data of each two-dimensional measurement grid point, constructing a full-field defect map for representing the spatial distribution information of deep level defects on the gallium oxide single crystal substrate.

The application discloses a kind of hypersonic gas-solid interface atomic collision event statistics method.The method comprises: simulating the high-speed flight of object in gas environment in NAMD software, output the position and speed information of all atoms in system at different time;Using VMD software, all gas atoms that can interact with the front surface in a certain period after system steady state are counted, and the coordinates, speed and potential energy of these gas atoms are output;Define the time when the gas atom turns in the gas-solid atomic repulsive force layer as the collision point, the incident point of the gas atom into the attractive force layer is obtained by pre-searching from the collision point, and the reflection point when the gas atom leaves is obtained by post-searching, which is recorded as a collision event, and the collision event information of different atoms and surface is obtained by circulation.The application proposes a kind of gas-solid interface atomic collision event statistics method under hypersonic strong shock wave condition, which can study the energy transfer mechanism of gas-solid interface from a deeper level and reveal the nature of aerodynamic heating.

This application relates to an acoustic lens, an ultrasonic probe, and an ultrasonic imaging device. The acoustic lens has a front surface, and the curvature of the front surface includes a central region and side regions located on both sides of the central region. The focal length of the central region is greater than that of the side regions. This acoustic lens adjusts the focal length in sections to achieve multi-dimensional, multi-point focusing. Ultrasonic waves passing through the central region are focused at a deeper level of the target, while those passing through the side regions are focused at a shallower level. Furthermore, the beam narrowing is significant, enabling the acquisition of clear images from shallow to deep within complex structures, thus improving the quality of ultrasonic images.

The application provides a defect detection method and system for an EUV photomask body, which can scan at least one to-be-detected position point of the EUV photomask body (including an EUV mask blank or an EUV photomask plate with a corresponding pattern) by using extreme ultraviolet laser with different incident intensities without damaging the EUV photomask body, obtain corresponding reflectivity, and obtain defect information of the corresponding to-be-detected position point by analyzing the reflectivity, including a distribution range in a transverse direction and deep information.

A temperature noise correction method for CMOS space cameras based on attention mechanisms and LSTM is presented. This method relates to the field of optical remote sensing technology, specifically to the field of temperature noise correction for CMOS space cameras. The core of the method is the use of a multi-level Long Short-Term Memory (LSTM) network with an attention mechanism to explore how temperature changes affect the noise performance of CMOS space cameras under two different operating conditions: dark and bright fields. This deep learning model possesses powerful autonomous learning capabilities, capable of mining and understanding complex noise patterns hidden within massive amounts of data, thereby improving the accuracy of noise identification and calibration. Its key advantage lies in its end-to-end learning approach, automatically learning and establishing a deep, nonlinear relationship between temperature and noise directly from the raw data, without requiring manual intervention for feature extraction or designing complex correction algorithms. This significantly enhances the model's generalization ability and adaptability to unseen data scenarios.

The invention discloses a laser gyroscope design life optimization and prediction method and a laser gyroscope. The laser gyroscope design life optimization and prediction method comprises the following steps: respectively obtaining a standard curve between the power and offensive gas content of a getter of a laser gyroscope in a non-activated state and the percentage of the amount of a getter barium film edge of the getter of the laser gyroscope in an activated state in an integral getter barium film; the method comprises the following steps: optimizing a deep impurity gas removal treatment process of a laser gyroscope by combining a standard curve in a state that a getter is not activated, vacuumizing, filling working gas, standing for a period of time, automatically removing gas by the getter, activating the laser gyroscope, standing for a period of time again, and observing the disappearance of the edge of a barium film of the getter. And calculating the complete disappearance time of the getter barium film to obtain the service life of the laser gyroscope. The service life of the laser gyroscope is prolonged by optimizing a deep miscellaneous gas removal treatment process, and the service life of the laser gyroscope is predicted.

The embodiment of the application provides a kind of based on ROP chain and the method and device of obfuscation and anti-reverse protection of opaque predicate, this scheme proposes a kind of three-order obfuscation protection framework of combining ROP instruction dynamic reconstruction, opaque predicate protection, instruction semantic hiding, after the ordinary C / C++ source code is compiled into LLVM intermediate representation IR, dynamic extraction Gadget and opaque predicate combination based on user input state are used, the deep level semantic disturbance of key logic block, jump structure, constant field of program is realized. To completely break the control flow restoration chain, it is difficult for reverse personnel to analyze the obfuscation result, realize the controllable, verifiable, high-stability obfuscation protection of program, while maximizing resistance to symbolic execution and static analysis and other advanced analysis techniques.

Embodiments of the present disclosure provide a storage management method, an electronic device and a computer program product. In the storage management method, a computing device can determine, based on description information of a failure of a storage system, that the failure belongs to one failure category of a plurality of predefined failure categories. Then, the computing device can determine, in a first level of a hierarchical structure of predefined failure causes, at least one failure cause associated with the failure category. Next, the computing device can determine, among the at least one failure cause, a first failure cause that causes the failure. Then, the computing device can determine, based on the first failure cause, a target failure cause of a deepest level that causes the failure. Through the embodiments of the present disclosure, the root cause of the storage system failure can be accurately and efficiently determined, thereby providing the possibility of fundamentally eliminating the failure.

The invention provides a gallium oxide device ultra-deep energy level defect characterization method and system and electronic equipment, and relates to the technical field of semiconductor materials.The gallium oxide device ultra-deep energy level defect characterization method comprises the steps that isothermal DLTS testing is carried out on a gallium oxide device, an isothermal capacitance-testing period curve is obtained, and according to the isothermal capacitance-testing period curve, a gallium oxide device ultra-deep energy level defect characterization result is obtained; determining a value range of a test period; based on preset initial experiment parameters, performing a first DLTS test on the gallium oxide device to obtain an initial DLTS atlas; according to the initial DLTS atlas, prolonging the test period in the value range, and repeatedly carrying out DLTS test on the gallium oxide device to obtain a final DLTS atlas; all defect peaks in the final DLTS atlas are fitted, and the defect energy level and the capture cross section of each defect peak in the final DLTS atlas are determined. According to the invention, through progressive testing and accurate fitting, the detection and characterization precision of the gallium oxide device defect is improved.

The invention discloses a multi-stage data synthesis and progressive fine tuning method and system for digital copies, and the method comprises the steps: carrying out the structural processing of user notes, and constructing a triple knowledge base and a global user portrait; on the basis, training data is synthesized in three stages, wherein the high-order data adopts a structured format containing a specific label to explicit the reasoning chain; carrying out two-stage supervision fine adjustment and portrait-based preference optimization on the model by adopting a progressive strategy; during model reasoning, the generated content is verified and corrected by retrieving the original note vector library in real time. The system comprises corresponding modules. According to the method, the problems of infirm memory, disordered time sequence, superficial personality and illusion in the construction of the digital clones are solved, and the personalized digital clones with high credibility, deep level and traceability can be generated.

The application discloses a semiconductor laser, comprising: a substrate, a lower limiting layer, a lower waveguide layer, an active layer, an upper waveguide layer, an electron blocking layer and an upper limiting layer arranged in sequence from bottom to top; the active layer comprises a well layer and a barrier layer; the lattice constant of the well layer is greater than or equal to the lattice constant of the barrier layer; the thermal expansion coefficient of the well layer is less than or equal to the thermal expansion coefficient of the barrier layer; and the elastic coefficient of the well layer is less than or equal to the elastic coefficient of the barrier layer. By designing the lattice constant of the well layer to be greater than or equal to the lattice constant of the barrier layer, the thermal expansion coefficient of the well layer to be less than or equal to the thermal expansion coefficient of the barrier layer and the elastic coefficient of the well layer to be less than or equal to the elastic coefficient of the barrier layer, the carrier capture effect, the deep level defect and the insulating interface of the depletion region of the active layer of the semiconductor laser can be effectively controlled, the symmetry breaking of the laser principle equilibrium state phase transition can be inhibited, and thus the sudden change phenomenon of the laser at the threshold can be effectively solved, and problems such as the conductance up-jump, the capacitance down-dip and the junction voltage up-jump can be eliminated.

The invention belongs to the field of hydrogen absorption and desorption performance testing, relates to a data analysis technology, and aims to solve the problem that errors of test results cannot be verified in the prior art, in particular to an integrated test system for hydrogen absorption and desorption performance of a hydride hydrogen storage material. The integrated test platform is in communication connection with a test execution module, a performance analysis module, a test verification module and a database; according to the invention, the hydride hydrogen storage material sample marked as the abnormal object can be diagnosed in a deeper level; by introducing the distribution coefficient and the distribution threshold value, the system can accurately judge whether the abnormal samples have the step-by-step reaction or not, so that blind treatment on all the abnormal samples is avoided; therefore, the subsequent test or calibration work is more targeted; through a hierarchical verification mechanism, equipment calibration is firstly carried out, and then verification is carried out by using a standard sample; according to the method, the possibility of faults of the testing mechanism is effectively eliminated.

This invention discloses a method, system, medium, and equipment for real-time defect detection in laser powder bed fusion additive manufacturing, belonging to the field of additive manufacturing quality monitoring and image processing. The method includes: acquiring image data and constructing a dataset; replacing the standard convolutional modules in the backbone and neck networks of the YOLOv11 network with frequency-domain dynamic convolutional modules; embedding the detection head of this network into a parallelized patch-aware attention module; training the improved network; performing real-time defect detection and outputting the results. This method forms a "detailed supply-semantic filtering" mechanism through the synergistic effect of the frequency-domain dynamic convolutional module and the parallelized patch-aware attention module. It enriches detailed features at a shallow level and performs intelligent filtering and fusion at a deep level, effectively improving the model's detection accuracy, enhancing its adaptability to varying process environments, and significantly improving recall and localization accuracy. This provides an effective solution for real-time industrial quality control in laser powder bed fusion additive manufacturing processes.

The high-purity germanium single crystal quality detection method comprises the following steps: S1, sampling the tail parts of qualified sections of shallow-energy-level impurities, deep-energy-level impurities and crystal defects of high-purity germanium single crystals; s2, sequentially performing grinding, polishing, annealing and liquid nitrogen soaking on the sample wafer; s3, after liquid nitrogen soaking is finished, performing XRT test on the (400) crystal face on the central position and the edge position of the sample wafer to obtain X-ray diffraction patterns of the (400) crystal face at the central position and the edge position of the sample wafer; and S4, based on the X-ray diffraction pattern of each (400) crystal face, determining whether the diffraction peak of the (400) crystal face is a plurality of diffraction peaks or a single diffraction peak, if the diffraction peak is a plurality of diffraction peaks, determining that the quality of the germanium single crystal is poor, and if the diffraction peak is a single diffraction peak, calculating the half-peak width. According to the quality detection method for the high-purity germanium single crystal, the quality of the high-purity germanium single crystal can be detected and evaluated, and then a performance analysis basis is provided for a high-purity germanium detector prepared from the high-purity germanium single crystal.

The invention relates to the technical field of semiconductors, discloses a silicon carbide base material surface defect repairing and passivating process based on plasma activation, and aims to solve the problems that an existing SiC base material defect repairing and passivating process is complex, the repairing effect is poor, and the performance is affected. The method comprises the following steps: pretreating a SiC substrate, and vacuumizing and heating in a plasma chamber; introducing activation gas to form a plasma activated substrate surface; introducing a repairing precursor, filling defects under the assistance of plasma, and promoting lattice reconstruction; and then a passivation precursor is introduced, and a compact passivation layer is formed under the assistance of plasma. The system comprises a pretreatment unit, a plasma reaction chamber, a gas precursor supply unit, a plasma source, a vacuum pump set, a heating device and a process control system. By adopting the scheme, deep and comprehensive defect repair and passivation of the SiC substrate can be realized, the process is simplified, the electrical property, dielectric strength and environmental stability are improved, and the process accuracy and stability are improved through in-situ monitoring and feedback control.

The invention provides a method for measuring a deep-energy-level recombination center in silicon, and the method comprises the steps: providing a substrate which comprises doped ions and the deep-energy-level recombination center; an epitaxial layer is formed and located on the substrate, the doping type of the epitaxial layer is the same as that of the substrate, the doping concentration of the epitaxial layer is smaller than that of the substrate, and the deep energy level recombination center in the substrate is completely diffused into the epitaxial layer; preparing a Schottky junction; the deep level transient spectrum of the Schottky junction is measured to simultaneously obtain the level, concentration and capture cross-section of the deep level recombination center in the substrate. According to the method, the limitation that a DLTS technology cannot directly measure a heavily-doped substrate material is broken through, the lightly-doped epitaxial layer is designed and grown, and the deep-energy-level recombination center in the heavily-doped substrate is fully introduced into the lightly-doped epitaxial layer, so that high-sensitivity, accurate and quantitative electrical characterization of the trace deep-energy-level recombination center in the heavily-doped substrate is realized.

The invention provides a semiconductor device and a preparation method thereof. The semiconductor device comprises a substrate and an epitaxial layer, each source region structure comprises a first doped region, a second doped region and a third doped region, and the second doped region comprises deep-energy-level impurities used for forming a recombination center; the JFET region is located in the epitaxial layer and located between any two adjacent source region structures, the second doped region is located on the side, away from the JFET region, of the third doped region, and part of the first doped region is arranged between the third doped region and the JFET region; the gate structure is located at one side, deviating from the substrate, of the JFET region and part of the source region structure; the source electrode is located on the surface of the side, away from the substrate, of the source region structure; the drain electrode is located on the side, away from the epitaxial layer, of the substrate, and the problem that the turn-off loss of a body diode in a semiconductor device is large is solved.

A kind of detector grade high purity germanium monocrystal deep energy level defect detection method includes the following steps: detector grade high purity germanium monocrystal is p-type germanium monocrystal, Hall sample and dislocation sample are taken in the head of p-type germanium monocrystal respectively to carry out carrier concentration and dislocation density detection, DLTS sample is taken in the head of the remaining crystal of p-type germanium monocrystal;Processing;Sputtering dot tin film as Schottky electrode on the front of DLTS sample, the back of DLTS sample is connected with copper sheet using tin foil, the surface contour of copper sheet is greater than DLTS sample, the part of tin foil covering and contacting the back of DLTS sample is used as ohmic electrode, the area of the part is more than ten times the area of dot tin film, so as to form detection sample;Detection: contact detection, if the contact of Schottky electrode and ohmic electrode is not a problem, then carry out normal temperature IV curve detection, if detection sample forms Schottky contact, then carry out DLTS spectrum signal detection, if DLTS spectrum signal is good, then start to carry out complete low temperature DLTS detection to obtain DLTS spectrum.

The invention relates to a uranium mine gamma-ray energy spectrum unfolding method of ResNet based on PSO optimization, and belongs to the technical field of uranium mine gamma-ray energy spectrum unfolding. The ResNet1D model avoids gradient disappearance through residual connection, so that the network can extract fine features of the gamma-ray energy spectrum in a deeper level, and the resolution capability of spectral line overlapping is improved. The ResNet1D model disclosed by the invention is high in robustness and excellent in anti-noise capability through actual tests, can extract a stable characteristic mode in a noise environment, and is more adaptive to field logging noise and instrument drift. Moreover, the method utilizes PSO to optimize hyper-parameters, improves the performance of the model, and avoids the blindness and low efficiency of manual parameter adjustment. Compared with a traditional method, the method has better performance on indexes such as mean square error (MSE), decision coefficient (R) and residual prediction deviation (RPD), and is particularly suitable for uranium mine logging application scenes with high noise and complex spectral lines.