31 results about "Rényi entropy" patented technology

The invention discloses an intelligent steel pipe surface defect recognition system based on deep learning, and particularly relates to the technical field of pipe surface defect analysis. An annular polarization light source array and a high-frame-rate CMOS sensor are adopted to synchronously collect visible light and near-infrared multi-polarization images; a surface normal is calculated based on Stokes parameters, mirror surface suppression and diffuse reflection enhancement are realized, a defect candidate area is generated by fusing multi-scale Laplacian pyramid residual error and Renyi entropy segmentation threshold positioning, multi-physical quantity registration is completed through white light interference and infrared thermal imaging, a six-channel feature cube is constructed, and a three-dimensional image is obtained. According to the method, space, spectrum and thermal characteristics are jointly extracted in the multi-head attention convolutional neural network, the confidence coefficient is evaluated in combination with Jensen-Shannon divergence, and the polarization angle and the focal length are dynamically adjusted according to the confidence coefficient, so that closed-loop parameter self-optimization is realized, and the micro-scale pitting corrosion and millimeter-scale crack detection precision is remarkably improved.

The invention discloses a public opinion propagation prediction method based on a dynamic time weighted Renyi entropy and a graph neural network, and the method comprises the steps: constructing a public opinion propagation network based on the hot topic information of a network platform; constructing a public opinion propagation prediction model based on the dynamic time weighted Renyi entropy and the graph neural network; and inputting the public opinion propagation network into the public opinion propagation prediction model to complete public opinion propagation prediction of the hot topic information. According to the method, the machine learning method, the complex network and the graph entropy theory are combined, a new view angle is provided for public opinion propagation prediction, a new thought is provided for application of the time weighted entropy features in complex network analysis, and the method has important theoretical value and practical significance.

The invention discloses a time-frequency attention-based selective state space model alarm detection method, which comprises the following steps of: extracting time-frequency characteristics from a time sequence by using continuous wavelet transform, calculating a time-frequency domain weight based on Renyi entropy, constructing an attention mechanism through a multi-layer perceptron and a convolutional neural network, and weighting the time-frequency characteristics to obtain a time-frequency attention-based selective state space model. Therefore, more representative time domain feature embedding is obtained. According to the method, a selective state space model is utilized to decode hidden space embedding representation, a time-frequency image is reconstructed, and anomaly detection is realized by calculating a reconstruction error. According to the invention, attention on key time-frequency characteristics is enhanced through an attention mechanism, abnormal events in a time sequence can be effectively captured, and high-precision alarm detection is realized. The method is suitable for anomaly detection tasks of periodic complex time series data in the field of industrial monitoring, and can effectively detect various types of anomalies including mutation, drift, periodic change and the like.

The invention provides a malicious encrypted traffic classification method and system based on a session spatio-temporal feature map. The method comprises the following steps: sliding on a cleaned encrypted traffic session by using a sliding window with a predefined duration, and extracting statistical characteristics of the encrypted traffic session, including a packet size characteristic, a packet arrival time characteristic and a packet load alpha-Renyi entropy; taking the packet size feature and the packet arrival time feature of the encrypted traffic session as a Y axis and an X axis respectively, mapping the packet load alpha-Renyi entropy into a gray value, and forming a session spatial-temporal feature map; and inputting the session spatio-temporal feature map into a ResNet-50 model of a CBAM attention mechanism to perform malicious encrypted traffic classification. The scheme provided by the invention can adapt to different malicious encrypted traffic application scenes, so that more efficient and more accurate encrypted traffic classification is realized.

The invention discloses a time-frequency analysis method based on local entropy optimization synchronous demodulation reassignment transformation, relates to the technical field of signal processing, and solves the problem that a traditional time-frequency analysis method is not easy to carry out when complex non-stable vibration signals generated by rotating machinery and the like are processed. The problems of difficulty in balancing time and frequency resolution, easiness in energy diffusion, difficulty in multi-component signal separation and the like exist; according to the method, zero padding is carried out on the two ends of a target signal, a discrete Gaussian window is constructed to generate a sliding windowing signal matrix, a projection angle sequence is generated in an angle space, a time axis and a frequency axis are discretized, a demodulation function containing undetermined parameters is constructed to generate a complex number time-frequency representation matrix, the Renyi entropy value of time-frequency sub-blocks is calculated to determine an optimal demodulation parameter, and the optimal demodulation parameter is obtained. And setting a frequency difference threshold to construct a frequency redistribution operator to generate an optimized time-frequency matrix. The method is mainly used for time-frequency analysis of complex non-stationary vibration signals in the fields of rotating machinery and the like, and high-precision frequency modulation feature extraction and enhancement processing are achieved.

The invention relates to a rotary machine composite fault detection method and system under a time-varying working condition, and belongs to the technical field of rotary machine fault diagnosis. The method comprises the steps of collecting a non-stationary vibration signal under a variable speed working condition, fusing a third-order Renyi entropy and kinematics prior to construct an adaptive time-frequency enhancement model, and outputting weighted time-frequency distribution; global optimization is carried out through a priori constraint Viterbi algorithm, and an instantaneous frequency ridge line is extracted under the condition of no rotating speed sensor; performing angular domain resampling by taking the ridge line as a phase reference, and converting a non-stationary signal into an angular domain stationary signal; constructing an extended difference mode decomposition convex optimization model, and iteratively solving an optimal difference spectrum; and determining a frequency spectrum segmentation threshold value based on self-adaptive change point analysis, performing decoupling separation and time domain reconstruction on the optimal difference spectrum, and completing composite fault diagnosis through feature comparison. The method does not need an external tachometer, can adaptively extract and separate the composite fault features under the variable speed working condition, is high in diagnosis accuracy, and is good in engineering application value.

The invention discloses an image segmentation optimization method, system, equipment and medium, and relates to the technical field of computer optimization algorithms, and the method comprises the steps: constructing a two-dimensional histogram for an original gray level image, employing a two-dimensional Renyi entropy as a target function for evaluating the segmentation quality of the two-dimensional histogram, finding a group of optimal threshold combinations, and carrying out the segmentation of the two-dimensional histogram through the optimal threshold combinations; the problem of searching the optimal threshold value combination is converted into an optimization problem to be solved, the found optimal threshold value combination is used for segmenting the original image, and a final segmentation result image is generated; when an optimization problem is solved, operating individuals in the population by adopting a differential variation strategy so as to generate a first group of candidate solutions, and executing a Rime optimization mechanism and a randomized step size covariance matrix adaptive mechanism in parallel on each individual in the population so as to generate a second group of candidate solutions; and updating the population according to a greedy selection mechanism. The algorithm premature convergence can be effectively prevented, and the method can be applied to complex optimization tasks such as image segmentation and engineering design.

The present application relates to transmission link early warning technical field, disclose a real-time analysis and early warning system for rotating machine pump vibration data based on edge side calculation, include: capture the physical layer error code time sequence of transmission link and build the differential error code time sequence vector which removes the influence of absolute time drift;A dynamic rotating virtual electric vector space is constructed in the edge computing node, and the gradient ascent algorithm is used to optimize the target functional which measures the phase clustering strength, and the virtual space rotating frequency is adaptively adjusted to lock the best virtual frequency which makes the error code projection most concentrated;Based on the best frequency, the probability density distribution of error code phase is reconstructed by using kernel density estimation, and the generalized Renyi entropy is calculated as the characteristic of transmission error code phase clustering dispersion degree;By comparing the entropy characteristic with the dynamic threshold based on the environmental noise base, the transmission link abnormality is determined.

The present invention discloses a 5G exo-radiation radar signal accumulation method, belonging to the field of exo-radiation radar technology. The method comprises the following steps: S1, signal acquisition and parameter setting; S2, signal segmentation interception; S3, Rényi entropy calculation; S4, signal accumulation interval selection; S5, signal coherent accumulation. To address the problem that the bandwidth of 5G downlink signals strongly depends on the transmission content, a sliding Rényi entropy calculation is performed to select signal intervals in the 5G signal with high transmission content as the coherent accumulation intervals for the exo-radiation radar. This method can effectively improve target resolution and echo signal-to-noise ratio, achieving effective detection of low-lying, slow, and small targets while using less computing resources.

The present invention discloses a seismic data analysis method and system based on cascaded squeeze time-frequency transformation. The optimal large time window is selected according to the minimum Renyi entropy of the short-time Fourier transform under multiple window functions of a single-channel seismic record; according to the selected optimal large time window, the second-order squeeze time-frequency transformation under the optimal large time window is performed; according to the range of the target area of interest, the second-order squeeze time-frequency transformation under the optimal large time window is reconstructed; a series of second-order squeeze time-frequency transformations under smaller time windows are performed according to the reconstructed structure, and the window function corresponding to the minimum reconstruction error is selected as the optimal small time window; the second-order squeeze time-frequency transformation is performed according to the selected optimal small time window, and then the seismic data is analyzed with high precision. The present invention can effectively and accurately extract the time-frequency spectrum of seismic data. By adopting cascaded squeeze time-frequency transformation, it has the characteristics of high resolution, fast speed and accuracy, and can be used for high-precision time-frequency analysis of seismic data.

The application discloses a forward scattering radar echo parameter extraction method based on GNSS, and comprises the following steps: 1, forward scattering signal extraction; 2, using the Rényi entropy of the smooth pseudo-Wigner-Ville distribution to judge whether the forward scattering signal contains a target scattering signal; 3, using a sliding window to analyze the frequency domain characteristics of each signal segment of the target scattering signal, and judging whether a target crossing event occurs; 4, using a smaller sliding window to analyze the signal segment of the crossing event in sections, calculating the time domain statistical characteristic value of the signal segment in the sliding window, and extracting an optimal signal; 5, using the optimal signal to estimate the target crossing Doppler slope; and 6, using the optimal signal to estimate the target crossing time. The application can realize preliminary judgment of the relative position relationship between a target and a baseline, can realize target crossing Doppler slope estimation and target crossing time estimation of a forward scattering radar echo, and can be popularized to a forward scattering radar network of platforms such as the ground, the sea surface and the air.

The invention belongs to the technical field of artificial intelligence and computer vision, relates to an environmental sanitation video garbage detection method based on uncertainty guide hierarchical retrieval, and aims to solve the problem that an existing environmental sanitation video garbage detection method is high in labeling cost and weak in generalization ability or lacks historical context support, so that complex scenes are missed and missed. The method comprises the following steps: firstly, acquiring an environmental sanitation video frame sequence and dividing the sequence into fragments, extracting visual and garbage category language features through a pre-training encoder, and calculating a negative cosine distance to obtain category probability distribution; secondly, estimating the uncertainty of frames and fragments by using normalized Renyi entropy, retrieving high-confidence reference fragments from short-time, scene and global levels of a clean and junk double-memory library when the uncertainty is high, and directly inputting the high-confidence reference fragments into a pre-trained VLM model when the uncertainty is low; and finally, obtaining a final result through evidence perception time sequence attention fusion, and dynamically updating the memory bank. According to the scheme, additional training is not needed, the detection robustness and accuracy in complex scenes such as low illumination and shielding are effectively improved, and reliable technical support is provided for intelligent environmental sanitation operation.

The invention discloses an operation safety analysis method and system based on big data, and relates to the technical field of data analysis, and the method comprises the steps: decomposing standardized data, obtaining a signal component, calculating an envelope entropy and a Renyi entropy, obtaining a comprehensive fitness, carrying out the optimization through employing an MIGA algorithm, obtaining an initialized signal component, and constructing a risk level matrix. Respectively optimizing the LSTM parameter combination and the LSSVM parameter combination by using an SSA algorithm to obtain a predicted value and a risk value, and performing anomaly marking; the multi-source heterogeneous data is partitioned, denoised, standardized and dynamically fragmented, the data processing efficiency and accuracy are improved, parameter optimization is performed through the multi-target multi-island genetic algorithm, accurate risk prediction and anomaly detection are performed in combination with the LSTM and LSSVM models, and the real-time performance and accuracy of operation safety analysis are enhanced.

The present invention claims protection for an intrusion detection method based on deep learning in an SDN (Software-Defined Network) environment. For the traffic information flowing through the SDN network, the controller polls the flow table in the switch at a fixed rate to statistically analyze the traffic information. However, if the polling time is too long, it will lead to the inability to obtain network traffic information in a timely manner, thereby affecting the judgment of network intrusion detection. If the time is too short, it will cause an excessive load on the controller. The present invention proposes an adaptive network traffic sampling method based on the change of Renyientropy (Renyi entropy) of the source IP address for collecting traffic data in the SDN network. For intrusion detection, an intrusion detection model combining SAE-GRU (Sparse Autoencoder-Gated Recurrent Unit Neural Network) is proposed to identify abnormal network traffic. When the traffic is determined to be abnormal traffic, the controller issues a flow table to discard the abnormal traffic. The present invention can collect SDN network traffic information more real-time and accurately and identify abnormal traffic in the network.

This invention discloses a method and system for data expansion and reliability analysis of avionics equipment, comprising: collecting reliability growth test data of avionics equipment to obtain a full sample dataset and a candidate subsample set; evaluating the information content of the candidate subsample set by maximizing Rényi entropy; constructing a dual-objective collaborative optimization model of entropy constraint and distribution distance by minimizing the distribution difference between the candidate subsample set and the full sample set by minimizing the Wasserstein distance metric; determining the globally optimal subsample set and sample reuse degree by using a greedy search to traverse the sample reuse degree; establishing an avionics equipment reliability analysis model based on a two-parameter Weibull distribution; adaptively selecting a hyperparameter estimation method according to prior information conditions and model complexity and constructing a posterior distribution based on Bayes' theorem; and using a step-by-step sampling method for avionics equipment reliability analysis and life prediction. This invention achieves both information content and distribution representativeness in data expansion and reliability analysis.

The application discloses a kind of vehicle-mounted SAR imaging self-focusing methods based on Rényi entropy, it is related to vehicle-mounted synthetic aperture radar imaging technical field, vehicle-mounted SAR motion compensation is realized in the case without inertial navigation equipment;The method comprises: obtaining vehicle-mounted SAR original data, and the sub-aperture division is carried out to vehicle-mounted SAR echo data;For each sub-aperture, first, imaging is carried out using Omega-K algorithm, then, the Rényi entropy of SAR image is defined, and a self-focusing method based on Rényi entropy is designed to optimize image quality;SAR subgraph imaging is realized by sub-aperture iteration, and sub-aperture splicing is carried out according to the division principle, to obtain wide vehicle-mounted SAR image with high precision.The present application can be directly applied to existing vehicle-mounted FMCW-SAR system, and the performance of SAR system can be more accurately measured using Rényi entropy, to further optimize the self-focusing algorithm, significantly improve the vehicle-mounted SAR imaging quality and system applicability, and provide technical support for the development of vehicle-mounted SAR technology.

The invention discloses a frequency modulation wavelet transform time-frequency analysis method based on local entropy selection scale extraction, belongs to the technical field of signal processing, and particularly relates to the problem of insufficient time-frequency representation precision of non-stationary signals. According to the method, a sliding Gaussian window function matrix is constructed, a frequency modulation angle is discretized to generate a telescopic primary function, and a multi-angle time-frequency sub-representation matrix is generated in combination with frequency modulation wavelet transform; after Fourier transform, constructing a redistribution operator by using a partial derivative and a Dirichlet function, and extracting time-frequency points with strong energy and stable phases to form a high-resolution time-frequency distribution matrix; and finally, time-frequency blocks are divided, Renyi entropy is calculated, and optimal time-frequency blocks with the minimum entropy value are selected to be spliced into a complete time-frequency representation matrix. The method is mainly used for improving the time-frequency resolution and energy concentration of non-stationary signals (such as mechanical fault diagnosis and biomedical signals).

The invention relates to the technical field of transmission link early warning, and discloses a rotating machine pump vibration data real-time analysis early warning system based on edge side calculation, which comprises the following steps: capturing a physical layer error code time sequence of a transmission link and constructing a differential error code time sequence vector for removing absolute time drift influence; constructing a dynamically rotating virtual electric vector space at an edge computing node, optimizing a target functional for measuring the phase clustering intensity by using a gradient rising algorithm, and adaptively adjusting the rotation frequency of the virtual space to lock the optimal virtual frequency which enables the error code projection to be most concentrated; based on the optimal frequency, probability density distribution of error code phases is reconstructed through kernel density estimation, and generalized Reniy entropy is calculated to serve as a characteristic for representing transmission error code phase clustering dispersion; and the entropy feature is compared with a dynamic threshold value based on an environment noise base, so that transmission link abnormity judgment is realized.

The application is specifically a network security identification method and system based on multi-modal fusion features, relates to the technical field of network security, and comprises: a flow reorganization and sequence extraction module, a multi-dimensional entropy feature calculation module, a phase space reconstruction and trajectory analysis module, and a topological geometry judgment module.In the application, the adjustable parameter Renyi entropy can accurately capture the content confusion degree difference of different types of encrypted traffic, the box dimension fractal dimension quantifies the self-similarity of the traffic, and the maximum Lyapunov index is combined to realize accurate mining of time sequence chaotic characteristics; and the flow reorganization and sequence extraction module supports multiple network access modes, adapts to different bandwidth scenes, and rearranges out-of-order packets to guarantee data authenticity.

The invention discloses an intracranial hemorrhage CT image segmentation method and device, a medium and equipment, and relates to the technical field of image segmentation. In a segmentation threshold optimization process, a Bareones mechanism and an orthogonal learning mechanism are integrated into an African vulture optimization algorithm, a search space is expanded in a search population corresponding to a segmentation threshold through Gaussian mutation, and the ability of the threshold optimization algorithm to get rid of local optimum is enhanced; and an orthogonal learning mechanism promotes resource sharing among search population individuals corresponding to the segmentation threshold, and improves the search diversity of the segmentation threshold. And obtaining an optimal individual with the maximum Renyi entropy after the two-dimensional histogram is divided based on the threshold value through multi-round iterative optimization, and taking the optimal individual as an optimal segmentation threshold value of the intracranial hemorrhage CT image. According to the method, the population diversity and convergence speed in segmentation threshold optimization of the intracranial hemorrhage CT image are improved, and the image segmentation effect of the intracranial hemorrhage CT image is improved.

The invention provides an inter-view offset calculation method and device when a DICOM image is generated by a fluorescence scanning slide and a readable storage medium, and the method comprises the steps: obtaining a to-be-matched image ROI and a template region of an adjacent view overlapping region, calculating a matching result based on a square difference matching algorithm in combination with a GPU acceleration, and obtaining the offset of the to-be-matched image. The calculation efficiency is improved by converting the image into a frequency domain to carry out cross-correlation convolution operation and optimizing a video memory access rule; introducing a credibility judgment mechanism, and counting the proportion of matching results lower than a preset threshold value to eliminate uncredible results; the non-zero pixel ratio of a template area is calculated through an Otsu threshold method in combination with false peak construction, Gamma correction and Renyi entropy binarization, and abnormal results caused by too few samples or uneven illumination are screened. According to the method, through a multi-dimensional evaluation mechanism and a GPU acceleration strategy, the reliability and efficiency of offset calculation are remarkably improved.

The present application relates to a kind of ITR-DTV radar forward-looking super-resolution imaging methods based on Renyi entropy, imaging method includes: based on the motion geometry model of radar forward-looking imaging, echo signal is expressed as the form of antenna directional diagram convolution target scattering coefficient in azimuth direction, radar observation model is constructed;Target scattering coefficient is constructed target function;Combined with radar observation model, direction total variation operator is used as the regularization term of target function, while adding positive definite weighting matrix in the loss function of target function, and Renyi entropy is selected as another regularization term of target function, and target optimization model is obtained;ADMM method is used to iteratively solve target optimization model, and model function is obtained, and the relaxation variable in model function, target phase and target amplitude are updated;Target scattering coefficient is calculated using target phase and target amplitude, and the super-resolution imaging of target is realized.The imaging method has strong target image direction texture detail recovery ability, strong scene adaptability and small error.

The application claims a brain and muscle electrical signal decoding method based on time-frequency fusion and double-branch network, comprising the following steps: designing a brain and muscle electrical synchronous experiment paradigm; carrying out denoising and normalization processing on the collected brain and muscle electrical signals; using wavelet coherence analysis to screen the electroencephalogram channel and using short-time Fourier transform to obtain time-frequency characteristics; fusing in the following two ways: one is to stack by channel to obtain global characteristics, and the other is to use the Renyi entropy to obtain the significant feature band of each channel and splice into a new time-frequency graph; designing a double-branch network to extract features, using a time-domain residual module and a channel attention module to extract the features of the spliced time-frequency graph, using a 3D residual module and a ConvLSTM module to capture the dynamic changes and space-time characteristics of the stacked time-frequency graph; finally, splicing and fusing the features extracted by the two branches, using a classification module to calculate errors and classify decoding, effectively improving the accuracy and stability of the brain and muscle electrical fusion decoding.

The invention discloses a vehicle-mounted SAR (Synthetic Aperture Radar) imaging self-focusing method based on Renyi entropy, relates to the technical field of vehicle-mounted SAR imaging, and realizes vehicle-mounted SAR motion compensation without inertial navigation equipment. The method comprises the following steps: acquiring vehicle-mounted SAR original data, and performing sub-aperture division on vehicle-mounted SAR echo data; for each sub-aperture, imaging is carried out by using an Omega-K algorithm, then the Renyi entropy of the SAR image is defined, a self-focusing method based on the Renyi entropy is designed, and the image quality is optimized; sAR subgraph imaging is achieved through subaperture-by-subaperture iteration, subaperture splicing is carried out according to the division principle, and a large-width and high-precision vehicle-mounted SAR image is obtained. The method can be directly applied to an existing vehicle-mounted FMCW-SAR system, the performance of the SAR system can be measured more accurately through the Renyi entropy, the self-focusing algorithm is further optimized, the vehicle-mounted SAR imaging quality and system applicability are remarkably improved, and technical support is provided for development of the vehicle-mounted SAR technology.

The present invention proposes a method, device and readable storage medium for calculating the offset between fields of view when generating DICOM images from fluorescence scanning glass slides, including obtaining the ROI to be matched and the template area of the overlapping area of adjacent fields of view, calculating the matching result based on the sum of squared differences matching algorithm combined with GPU acceleration, improving the calculation efficiency by performing cross-correlation convolution operation on the image converted to the frequency domain and optimizing the video memory access rule; introducing a credibility judgment mechanism, counting the proportion of the matching results below the preset threshold to exclude untrustworthy results; calculating the proportion of non-zero pixels in the template area through Otsu threshold method combined with false peak construction, Gamma correction and Renyi entropy binarization, and screening abnormal results caused by too few samples or uneven illumination. The present invention significantly improves the reliability and efficiency of offset calculation through a multi-dimensional evaluation mechanism and GPU acceleration strategy.

This invention discloses a method for characterizing multi-stage carbonate reservoirs based on time-varying Gaussian window transient extraction transform, used for characterizing multi-stage carbonate reservoirs. The method includes: inputting the seismic signal to be analyzed, where is time; constructing a short-time Fourier transform containing the time-varying window width parameter to be optimized, where represents frequency; determining the optimal window width parameter at each time step based on the local Rényi entropy minimization criterion; substituting and calculating its time partial derivative; constructing a transient extraction operator based on the time partial derivative results, including a local maximum criterion, an energy derivative zero-point criterion, and a group delay migration criterion; and proposing a time-varying Gaussian window transient extraction transform under the action of this operator for characterizing multi-stage carbonate reservoirs.

The invention discloses a ZGV feature extraction method based on a local entropy reconstruction optimization multiple synchronous compression algorithm, and belongs to the technical field of signal feature extraction. The method specifically comprises the following steps: step 1, carrying out preliminary extraction on a signal with a time-varying feature by adopting short-time Fourier transform; 2, estimating an instantaneous frequency corresponding to a short-time Fourier transform result; step 3, synchronous compression transformation; step 4, carrying out iteration on a synchronous compression transformation result; 5, performing Renyi entropy calculation and reconstruction precision calculation on the transformation result, and evaluating the transformation result; step 6, constructing a Bayesian cost function, and performing Bayesian optimization on the cost function to obtain a globally optimized window function length; and 7, taking the obtained length of the globally optimized window function as the window length of a Gaussian window function to obtain a new window function, and then carrying out new operation of short-time Fourier transform to obtain a high-precision time-frequency graph. According to the method, more accurate and reliable feature extraction of the ZGV signal can be realized.

The invention relates to a Renyi entropy theory-based source load balance degree quantitative evaluation method and device, and a medium, and the method comprises the following steps: obtaining a daily load curve and a distributed power supply power output curve of a power distribution network, and carrying out the preprocessing, and obtaining a net load time series data set; dividing the net load time sequence data set into a plurality of net load subsequences according to positive and negative conditions of net load values at all moments; calculating the Renyi entropy of each net load sub-sequence by adopting a Renyi entropy theory; and calculating a source load balance degree based on the Renyi entropy of each net load sub-sequence, and completing a quantitative evaluation process of the source load balance degree. Compared with the prior art, the method has the advantages of accurately quantifying the source load balance degree and the like.

The application discloses a rail surface damage identification method and system based on improved discrete entropy, and equipment. The method comprises the following steps: adopting a normal cumulative distribution function to perform standardization processing on an original rail profile data sequence; generating a vector group based on the standardized sequence; corresponding each vector in the vector group with each discrete mode, and calculating the weighted probability distribution of each discrete mode according to the complexity of each vector; calculating the improved discrete entropy entropy value by adopting Rényi entropy according to the weighted probability distribution; obtaining the entropy value distribution range of each type of damage; and identifying the rail surface damage based on the improved discrete entropy entropy value and the entropy value distribution range. The application can automatically and high-precisely realize the extraction of various damage characteristics, mine valuable information in the damage data, and provide decision-making help and information support for railway staff.

The invention discloses a bearing health state diagnosis method based on category perception multi-view sparse feature learning, which mainly constructs a category perception multi-view sparse feature learning model so as to solve the problem that noise and redundant information in original multi-view health state monitoring data can weaken the health state feature discriminability. And the accuracy of health state diagnosis is effectively improved. The method comprises the following specific implementation processes: (1) designing geometric structure measurement of category perception based on q-Renyi entropy so as to grasp internal structure information of multi-view health state monitoring data; (2) constructing a category perception multi-view sparse feature learning model in combination with a correlation analysis theory and a sparse constraint strategy; (3) solving the model to obtain a feature value and a feature vector of the multi-view health state monitoring data so as to obtain a bearing health state feature with strong discriminability; and (4) identifying the health state characteristics of the bearing by using an SVM classifier to obtain a final diagnosis result. Compared with the prior art, the method has better effectiveness and robustness.