45results about How to "Low robustness" patented technology

The invention provides a sleeve length matching optimization method and system suitable for a mandrel type hanger and a terminal, and the method comprises the steps: converting a length matching problem of a mandrel type hanger sleeve into a combined optimization problem based on a simulated annealing algorithm, carrying out the random search in a solution space, and carrying out the step-by-step optimization to find an optimal length matching closest to a target, thereby achieving the optimization of the length matching of the mandrel type hanger sleeve. Through random jump and local optimization among different solutions, a local optimal solution can be effectively avoided, a global optimal solution is finally converged, the calculation process is simple, the speed is high, the error is small, the stability is good, the cost is low, and on-site popularization and application are facilitated.

The invention relates to the technical field of neural network optimization, and discloses a target identification method and system based on multiple consistency perception, and the method comprises the steps: constructing a training data set, determining a supervision signal, and carrying out the model initialization training through the training data set and the supervision signal; constructing a self-consistency loss function based on the consistency of the prediction label and the given label of the target sample; constructing a context consistency learning loss function based on the prediction label of the target sample and the prediction label of the neighbor sample; constructing an open set identification loss function based on a multi-branch structure based on the prediction labels of the target sample under different perspectives; performing joint optimization through a self-consistency loss function, a context consistency learning loss function and a multi-branch structure-based open set identification loss function to obtain an optimized reference model; target matching identification is carried out by using the optimized reference model; according to the invention, the problems of large data marking demand and serious label noise influence of the existing target identification method are solved.

The invention discloses a preparation method of a large-area decoupling type fiber grating sensor based on an island bridge structure, and the method comprises the steps: firstly carrying out the peripheral pre-stretching of an elastic substrate, and then bonding a plurality of carbon fiber composite sheets which are arranged in a matrix manner on the elastic substrate in a pre-stretching state, a fiber grating and a fiber grating wrapped by glass fiber are respectively bonded and fixed on the two rows of fiber positioning grooves of each row of carbon fiber clad sheets, each fiber grating is provided with a grating point in the groove of each carbon fiber clad sheet, and each groove of each carbon fiber clad sheet is filled and cured; finally, after the elastic substrate is pre-stretched and released, the top surface of the elastic substrate is covered with an elastic top sealing layer, and therefore the large-area decoupling type fiber grating sensor is formed. The large-area decoupling fiber grating sensor prepared by the invention can still obtain a high-precision measurement result when facing high mechanical stress and dynamic deformation.

The invention provides a digital watermark embedding and detecting method, equipment and a medium, and aims to solve the problems of easy perception, opaqueness and low robustness of the existing text digital watermark technology. The method comprises the steps that an Nth target clause is predicted, and at least two (N + 1) th candidate clauses are generated; according to the Nth target clause and a preset first watermark feature coding sequence, a first watermark feature coding value of an (N + 1) th target clause is determined, and the (N + 1) th target clause is the next clause of the Nth target clause; determining the (N + 1) th target clause according to the prediction probability of the at least two (N + 1) th candidate clauses, the first watermark feature coding value and a preset readability threshold; under the condition that the N + 1 target clauses comprise text end characters, a full text embedded with watermarks is determined, the full text embedded with watermarks comprises the N + 1 target clauses, and N is an integer larger than 0. According to the invention, low perception, transparency and robustness of digital watermark embedding can be realized.

The invention discloses a microgrid robust constraint scheduling method and system considering data center demand response, and relates to the technical field of power system optimization control scheduling, and the method comprises the steps: considering the operation characteristics of a micro gas turbine, an energy storage device, a photovoltaic unit and a data center, and carrying out the modeling of the operation stage of a microgrid; establishing a data center microgrid flexibility model, processing the uncertainty of photovoltaic output, conventional load and data center load by using distributed robust opportunity constraint, and constructing an objective function with operation cost minimization; and solving the model by using a CPLEX solver. By optimizing the scheduling strategy, various new energy equipment such as the micro gas turbine, the energy storage equipment and the photovoltaic unit can efficiently and cooperatively work, renewable energy sources are utilized to the maximum extent, and the energy consumption cost of the data center is reduced. A distributed robust opportunity constraint method is adopted to deal with the uncertainty of photovoltaic output, conventional load and data center load, and the operation cost is minimized while the robustness of the system is ensured.

The invention relates to the technical field of electronic scale anti-cheating, in particular to a recoverable electronic price computing scale with anti-counterfeiting and anti-cheating functions, and the electronic price computing scale comprises an information obtaining module which is used for obtaining a two-dimensional code image corresponding to transaction information of the electronic price computing scale and steganography information; the information embedding module is used for determining a clustering coefficient matrix of each clustering cluster; determining a steganography position and a steganography window to be selected of each cluster; determining the texture complexity of each cluster; determining the steganography window position of each cluster; determining a steganography coefficient range of the DCT coefficient matrix of each DCT block; a steganographic two-dimensional code image is obtained; and the anti-counterfeiting verification module is used for extracting to-be-verified steganographic information of the steganographic two-dimensional code image and carrying out anti-counterfeiting verification on the steganographic two-dimensional code image. According to the method and the device, the steganography information robustness reduction caused by the regional frequency difference of the two-dimensional code image can be avoided, so that the anti-attack capability of the steganography information is improved.

The invention provides a method and device for identifying cryptocurrency miners and a readable storage medium, and relates to the technical field of mining, and the method comprises the steps: obtaining a DNS traffic log and an RADIUS user access log; the method comprises the following steps: acquiring traffic characteristics of target traffic of a target user from a DNS traffic log and an RADIUS user access log by utilizing a characteristic device, wherein the traffic characteristics comprise a request internet protocol (IP) and a port, the size and the number of data packets, domain name information and an encryption / non-encryption mark; in response to the fact that the target flow is encrypted flow, the flow features are input into a trained mining flow recognition model, and a recognition result about whether the target flow is mine pool flow or not is obtained; and identifying the target user as the cryptocurrency miner in response to the fact that the target flow is the mine pool flow. According to the method, the device and the medium, the problems that the existing method for discovering miners is mainly realized by identifying the flow content, but the efficiency and the accuracy are low when the mining flow is mostly encrypted and the flow content is directly identified can be solved.

The present application discloses an image processing method, an image processing device, an electronic device and a computer-readable storage medium, wherein the image processing method comprises: extracting features of an image to be processed based on a backbone network of a pre-trained image processing model to obtain image features; inputting the image features into at least two processing networks of the image processing model for processing to obtain corresponding processing results; wherein each processing network is constructed based on at least one preset task, and the processing network comprises a neck module and a detection module; the neck module is used to fuse image features to obtain fused features matching the preset task, and the detection module is used to detect the fused features to obtain processing results corresponding to the preset task. This method can avoid "parameter preemption" between different preset tasks, improve the robustness of the image processing model, and thereby improve the accuracy of the processing results of each preset task.

The present invention discloses a method, device, equipment and medium for gesture recognition based on feature fusion. The method includes: obtaining a standardized video corresponding to a target vehicle, and processing the standardized video by regional cropping to generate a target video containing a hand area; extracting spatial features from the target video based on a spatial attention model to generate posture features corresponding to the target video, and extracting temporal features from the target video based on a temporal attention model to generate motion features corresponding to the target video combined with optical flow information; processing posture features and motion features by feature fusion to generate target fusion features corresponding to the target video; determining the gesture category corresponding to the target fusion feature based on a fully connected classification network as target gesture recognition information corresponding to the target video. Through the technical solution of the present invention, dynamic gestures can be accurately and real-time recognized, thereby improving the accuracy and robustness of gesture recognition.

The invention discloses a calibration method and device, equipment, a storage medium and a program product, and the method comprises the steps: determining a data set in a preset register list, wherein the data set comprises a plurality of groups of candidate bias voltages of a to-be-calibrated chip; according to a data set in a preset register list, values of bias voltage of the chip to be calibrated are sequentially adjusted, a radio frequency signal received by the chip to be calibrated is tested, test data of multiple groups of N-order intermodulation points are obtained, and N is a positive integer; determining at least two candidate intermodulation points based on the test data of the plurality of groups of N-order intermodulation points; and retesting the radio frequency signal received by the chip to be calibrated according to the at least two candidate intermodulation points, and determining a target intermodulation point. Therefore, aiming at the intermodulation distortion problem in the radio frequency system, the signal distortion and interference can be more effectively reduced, and the accuracy of test data is ensured; moreover, the calibration efficiency can be improved, the test cost is reduced, and the overall performance of the radio frequency system is improved.

This invention discloses a method and apparatus for real-time damage detection of plate structures based on a physical information spatiotemporal graph neural network in the field of structural health monitoring technology. The method includes: constructing a three-dimensional physical mesh model of the plate structure based on the acquired dimensional information and material properties of the plate structure to be monitored; generating a sensor and excitation source layout in the physical mesh model based on a pre-determined sensor placement range; arranging corresponding sensors and excitation sources on the plate structure to be monitored based on the sensor and excitation source layout; acquiring feedback signals received by the sensors after pulse signals are emitted to the plate structure by the excitation sources; and sending the feedback signals to a pre-trained physical information spatiotemporal graph neural network model to generate the location, area, major axis length, minor axis length, orientation angle, and severity index of each damage. This invention achieves low-cost and highly robust structural health monitoring.

The invention discloses an imaging method for passing through a random scattering medium in visible light based on a diffractive optical neural network, and the method comprises the following steps: 1, carrying out the optical coding of an input image through a coherent or low-coherent monochromatic plane wave, and enabling a coded light field to pass through a random phase diffuser for scattering; and step 2, continuous wavefront modulation of the scattered light field is obtained through a coherent or incoherent diffractive optical neural network, and finally, high-fidelity original image reconstruction is generated on an output plane. The invention finds that the coherent diffraction neural network obtains dynamic phase modulation by introducing a randomly generated diffuser in the training process, enhances the adaptive capacity of the network to the spatial coherence change of the light source, realizes the high-quality reconstruction of the scattering image under the visible light, has the robustness to the low-coherence light source, and is suitable for large-scale popularization and application. The method can be applied to low-power-consumption and real-time imaging of the dynamic scattering medium under natural light.

According to the full duplex wireless simultaneous information and energy transfer system and the implantable medical device, an upper computer part comprises a level switching module which is responsible for controlling level switching according to a baseband signal; the class-D power amplifier converts a direct-current power supply into an alternating-current square wave signal; the radio frequency receiver receives an uplink radio frequency signal of the lower computer. The upper computer adds downlink data to an energy link in an ASK envelope mode through cooperative work of the level switching module and the class D power amplifier, and transmits the downlink data to the lower computer in a near field coupling mode. The lower computer part comprises an ASK (Amplitude Shift Keying) demodulation circuit for demodulating data from a downlink; the rectifying circuit converts the received alternating current signal into a direct current signal to supply power; and the radio frequency transmitter modulates the uplink data to a radio frequency signal and sends the radio frequency signal to the radio frequency receiver of the upper computer. According to the system design, the separation of data and energy links is optimized, the transmission efficiency is improved, the complexity, the power consumption and the cost are reduced, full-duplex communication is supported, the performance of the implantable medical device is improved, and the application range of the implantable medical device is widened.

A mobile object includes: a first braking / driving torque application unit (30R) that applies first braking / driving torque to a right driving wheel (22R); a second braking / driving torque application unit (30L) that applies second braking / driving torque to a left driving wheel (22L); a right driven wheel (21R) and a left driven wheel (21L) each of which is constituted of a caster wheel; and a control unit (40) that controls the first braking / driving torque application unit and the second braking / driving torque application unit. Moreover, the control unit is configured to perform turning, advancing / reversing and braking of the mobile object by controlling the first braking / driving torque and the second braking / driving torque or by controlling rotational speed of the right driving wheel and rotational speed of the left driving wheel.

The invention discloses a rehabilitation training human body posture estimation method and system based on a conditional space-time diagram diffusion model, and belongs to the field of artificial intelligence rehabilitation medicine. The system comprises a multi-view image acquisition module, a two-dimensional attitude detection module, a rough three-dimensional reconstruction module, a standard action library module, a condition space-time diagram diffusion optimization module and an output module. The method comprises the following steps: acquiring a video through a low-cost multi-view camera, and obtaining a rough attitude sequence through two-dimensional detection and three-dimensional reconstruction; then, semantic features are matched and extracted on the basis of a standard action library and serve as conditions to guide a condition space-time diagram diffusion model to conduct space-time joint optimization on the rough sequence, and a high-quality and smooth three-dimensional posture sequence conforming to clinical semantics is generated. According to the method, a collaborative architecture of a lightweight front end and an intelligent rear end is constructed, the precision and smoothness of human body posture estimation in a rehabilitation scene are remarkably improved on the premise that the hardware cost is controllable, and a practical and reliable intelligent rehabilitation evaluation tool is provided for medical staff.

The present invention relates to an unsupervised pedestrian re-identification method based on feature consistency. The method comprises the following steps: 1: designing a robust feature extraction model based on random feature masks, and then calculating a time average model based on the feature extraction model; 2: feeding the pedestrian image to the feature extraction model and the time average model twice respectively, obtaining four features, and making the four features close to each other through consistency loss; 3: clustering the features extracted by the feature extraction model, and then adjusting the clustering results according to independence and compactness, and finally fine-tuning the model based on the clustering results. The method based on feature consistency designed by the present invention aims to make the feature extraction model pay more attention to the high-level semantic information of the image by randomly masking part of the information of the image, thereby improving the robustness of the feature extraction model.

The application discloses a semi-supervised HRRP noise label filtering method based on early learning guidance, comprising the following steps: constructing an HRRP training data set and a deep neural network model; pre-training the deep neural network model; predicting the HRRP training data set by using the pre-trained network model and dividing the HRRP training data set into two data sets according to the confidence; constructing a known label data set and an unknown label data set to form a semi-supervised training data set and performing data enhancement; semi-supervised training the network model by using the enhanced data; generating the label of the unknown label data set by using the semi-supervised trained network model and fully supervised training the network model; and target recognition of the HRRP data by using the fully supervised trained network model. The application uses a generalized cross-entropy loss function in the early learning training stage of the model, proposes a data enhancement scheme suitable for HRRP, can better reduce the influence of noise labels on the model, and has better stability and implementability.

The present application relates to the field of electronic scale anti-cheating technology, and specifically to a recyclable electronic price-calculating scale with anti-counterfeiting and anti-cheating functions, the electronic price-calculating scale comprising: an information acquisition module, used to obtain a two-dimensional code image corresponding to the transaction information of the electronic price-calculating scale, and steganographic information; an information embedding module, including: determining the clustering coefficient matrix of each cluster cluster; determining the steganographic position and the selected steganographic window of each cluster cluster; determining the texture complexity of each cluster cluster; determining the steganographic window position of each cluster cluster; determining the steganographic coefficient range of the DCT coefficient matrix of each DCT block; obtaining the two-dimensional code image after steganography; an anti-counterfeiting verification module, used to extract the steganographic information to be verified of the two-dimensional code image after steganography, and perform anti-counterfeiting verification on the two-dimensional code image after steganography. The present application can avoid the reduction of the robustness of the steganographic information caused by the regional frequency difference of the two-dimensional code image, thereby improving the anti-attack ability of the steganographic information.

The present application relates to the technical field of intelligent transportation and video image processing, and particularly relates to a highway tunnel litter detection method and system for multi-path video stream. The method comprises the following steps: S1: data acquisition and preprocessing, constructing a litter dataset, and dividing the dataset into a training set, a validation set and a test set; S2: model construction, constructing an efficient feature enhancement network, wherein the efficient feature enhancement network comprises a double-path re-parameterization attention module, a multi-scale dynamic large kernel feature extraction module and a Swin Transformer feature fusion module; S3: model training and performance testing, training and optimizing the litter detection model using the training set and the validation set, and evaluating the model using the test set after the training is completed; and S4: algorithm deployment, buffering multi-path video streams to a Redis database frame by frame, and reading video frames from the Redis database by a computing node and performing detection.

The invention discloses a control method of a two-phase cold plate type liquid cooling system. The control method comprises the following steps: acquiring a working medium phase change temperature type of cooling liquid in the two-phase cold plate type liquid cooling system; when the working medium phase change temperature type is a fixed value, the working medium phase change rate of each branch is controlled to be a preset value by controlling the system flow; and when the working medium phase change temperature type is a range value, the working medium phase change rate of each branch is controlled to be a preset value by controlling the phase change rate of each branch. By applying the two-phase cold plate type liquid cooling system control method provided by the invention, the robustness of the control system is improved, the system performance is improved, and manpower is saved. The invention also discloses a two-phase cold plate type liquid cooling system control device, equipment and a storage medium, which have corresponding technical effects.

The invention discloses a model training method and device and a chart recognition method, and relates to the technical field of model training, and the method comprises the steps: carrying out the feature extraction of each training image in a pre-obtained training set, and obtaining an initial feature vector corresponding to each training image; obtaining a first classification feature vector of each initial feature vector; performing disturbance operation on each initial feature vector to obtain a disturbed vector corresponding to each initial feature vector; obtaining a second classification feature vector of each disturbed vector; and training the initial model based on a first difference between the first classification feature vector and the corresponding standard chart type and a second difference between the second classification feature vector and the standard chart type corresponding to the first classification feature vector corresponding to the second classification feature vector. The model is trained through the first difference and the second difference, so that the robustness of the trained model and the accuracy of chart type identification are improved.

The present application relates to the field of surface detection technology, and discloses a surface detection method and system for precision fasteners, the method comprising: performing multi-angle image acquisition and image preprocessing on precision fasteners to obtain an initial feature image set; performing three-domain feature extraction, and obtaining a surface feature fingerprint vector by calculating the texture feature domain, shape feature domain, and material feature domain; constructing a deep separable convolution structure and a feature pyramid structure to obtain a deep surface detection network; using a pre-trained target detection model as a teacher network and a deep surface detection network as a student network, and obtaining a target surface detection model by calculating a feature distillation loss function and a response distillation loss function; inputting the image of the precision fastener to be detected into the target surface detection model, and obtaining the category information and location information of the surface defects by two-stage metric recognition calculation. The present invention improves the calculation efficiency while ensuring the detection accuracy of precision fasteners.

The present invention discloses a method for calculating flight trajectory similarity based on representation learning, comprising the following steps: S1. constructing an FT2Vec model, wherein the FT2Vec model comprises a trajectory enhancement module, a feature extraction module and a trajectory encoding module; S2. inputting the original trajectory, creating different variants of the original trajectory with the trajectory enhancement module, and enhancing the trajectory; S3. receiving different enhanced variants of the original trajectory generated by the trajectory enhancement module through the feature extraction module, and extracting fine-grained features of the trajectory position; S4. aggregating the output of the feature extraction module through the twin attention mechanism of the trajectory encoding module, and then generating the final spatiotemporal trajectory representation through LSTM; S5. training and optimizing the FT2Vec model. The FT2Vec proposed by the present invention is the first representation learning model designed specifically for flight trajectory similarity calculation, with low computational cost and high efficiency.

This invention provides an abnormal application data detection method, apparatus, electronic device, and storage medium. The method includes: acquiring application data matching a target user; classifying the acquired application data matching the target user to determine the data type; triggering a first abnormal application data detection process when the data type is tabular; triggering a second abnormal application data detection process when the data type is time-series; and processing the time-series application data through the second abnormal application data detection process to determine abnormal application data in the target user's application data. This enhances the generalization and data processing capabilities of the abnormal application data detection process, adapts to different usage environments, reduces the robustness of the abnormal application data detection process, and improves detection accuracy.

The application discloses a park enterprise inter-coordinated carbon reduction method, a storage medium and a computer program product, relates to the technical field of carbon management, and the method comprises the following steps: acquiring supply-side data and demand-side data reported by park enterprises, and matching a priority weight for each supply-side data; constructing a space-time coupling factor of potential supply pairs existing in the supply-side data and the demand-side data, and calculating an actual schedulable coordination amount of the potential supply pairs according to the space-time coupling factor; calculating an expected carbon emission reduction amount according to the actual schedulable coordination amount and the priority weight, and generating a candidate coordinated carbon reduction scheme based on the expected carbon emission reduction amount; inputting the candidate coordinated carbon reduction scheme into a pre-constructed digital twin simulation unit for verification to obtain a coordinated carbon reduction scheme, so as to improve the coordinated carbon reduction effect and the scheme execution success rate among park enterprises.

The invention belongs to the technical field of intelligent navigation, and particularly relates to a low-cost collaborative mapping method based on mutual observation of multiple robots. The method is applied to multi-robot formation, each robot in the formation carries a low-cost single-line laser radar, a camera, an I MU or a wheel speedometer and other sensors, and the multiple robots communicate through a Wi-Fi local area network. Each robot in the robot formation is combined with point cloud data of the single-line laser radar, I MU attitude angle data and acceleration data to realize pose estimation and local map construction of the robot; then taking the self key frame pose of each robot as a vertex and the self poses of mutual observation between the robots and estimation of other robots as measurement edges, respectively constructing pose graph optimization models, then performing closed-loop detection by using graph optimization results, and further optimizing the pose of the single robot; on this basis, each robot performs pose transformation on point clouds shared by other observed robots, and then performs map merging incrementally, so that map information sharing among multiple robots is realized, and all robots can independently construct an accurate global multi-harness point cloud map.

The application discloses a beam angle prediction method based on neural network and Kalman filtering fusion, and belongs to the technical field of millimeter wave communication.The method adopts a single-layer neural network without an activation function to learn the behavior of LSTM, extracts a weight matrix of the single-layer neural network as a state transition matrix of a Kalman filtering algorithm, and performs beam tracking by executing the Kalman filtering algorithm.The application fuses the strong robustness of the Kalman filtering algorithm on the basis of accurate prediction of the beam tracking angle; and since the LSTM has strong learning ability, dense observation of a communication target is not needed, the observation interval can be artificially set according to cost, the prediction cost is greatly reduced, and the performance of the beam tracking system is improved.

The invention discloses a hidden attack method based on a depth metric learning model, which comprises the following steps: acquiring different types of pictures and labels, and carrying out data preprocessing to obtain a clean training data set and a clean test data set; designing a depth measurement learning model and designing picture noise; picture noise is injected into the data to obtain a pollution training data set and a pollution test data set; defining a clean objective function and a pollution objective function, and respectively training on the clean training data set and the pollution training data set to obtain a clean model and a pollution model; the clean data and the pollution data are evaluated through the clean model and the pollution model respectively, if the hidden attack requirement is met, training of the pollution model is ended, and the weight of the pollution model is stored; otherwise, continuing to train the pollution model. According to the method, the hidden attack is introduced to emphasize security vulnerabilities in the deep metric learning model, so that the effectiveness of the hidden attack is enhanced, and the robustness of the deep metric learning model is weakened while high hidden performance is ensured.

The embodiment of the invention provides a multi-node UWB relative positioning method and system based on a liquid neural network. The method comprises the steps that observation data between known node pairs are collected in real time through UWB; obtaining a multi-frame time sequence feature sequence corresponding to a moment based on observation data between known node pairs acquired in real time; inputting the multi-frame time sequence feature sequence into a liquid neural network model based on an ordinary differential equation, and outputting a prediction distance result between known node pairs; based on the real distance result and the predicted distance result, optimizing the liquid neural network model by using a loss function to obtain a trained liquid neural network model; using the trained liquid neural network model to obtain a prediction distance result between the unknown node pairs; and obtaining the relative position of the unknown node at the current moment based on the predicted distance result between the unknown node pairs and the relative position of the unknown node at the previous moment. The method can give consideration to the real-time performance and robustness of positioning.

The invention provides an over-break and under-break monitoring method, device and equipment for a tunnel, a medium and a product, and relates to the field of tunnel construction. Comprising the following steps: acquiring real-time point cloud data of a to-be-monitored tunnel by adopting a first preset acquisition unit; a second preset acquisition unit is adopted to acquire contour data of the tunnel to be monitored; performing data fusion processing according to the real-time point cloud data and the contour data to obtain a real-time tunnel three-dimensional model of the tunnel to be monitored; obtaining a design three-dimensional model of the tunnel to be monitored; according to the real-time tunnel three-dimensional model and the design three-dimensional model, determining over-break and under-break information of the to-be-monitored tunnel; and displaying the over-break and under-break information on a preset display interface. The technical problem that in the prior art, due to the fact that the modern sensing technology is poor in environmental adaptability, accurate and real-time monitoring of back break is difficult to achieve, and consequently the back break monitoring efficiency of a tunnel is low is solved.