25 results about "Approximate entropy" patented technology

The invention belongs to the technical field of equipment state monitoring, and particularly relates to a boiler wall temperature anomaly detection and early warning method based on approximate entropy calculation, which comprises the following steps: dividing a large coal-fired power plant boiler wall temperature time sequence into continuously overlapped sliding windows; calculating three statistical parameters in each sliding window; the three statistical parameters comprise standard deviation, range and approximate entropy; forming a three-dimensional time sequence matrix formed by n groups of parameters based on the three statistical parameters; and performing anomaly detection and early warning on the three-dimensional time sequence matrix by using an isolated forest anomaly detection algorithm. Abnormalities are accurately recognized from different dimensions, and high-dimensional data are efficiently dealt with. The method has the real-time performance and the dynamic performance, online calculation and real-time response can be achieved, the model is flexibly updated along with new data inrush, and the anomaly detection requirement of the dynamic data environment is met.

The invention relates to the technical field of brain fatigue detection, provides a robust feature extraction and brain fatigue detection method and system based on electroencephalogram signals, and aims to solve the problems of difficulty in cross-individual robust feature extraction and lack of quantitative evaluation means in the prior art. The method comprises the following steps: constructing time-frequency-space multi-scale fusion features based on electroencephalogram signals, and performing feature screening of preset times on the fusion features based on contribution values of the fusion features to brain fatigue detection results to obtain a candidate feature group; and determining the target frequency of the single feature based on the selection times and the preset times of the single feature in the candidate feature group, and determining a robust feature set from the candidate feature group based on the target frequency. The robust feature set comprises # imgabs0 # and # imgabs1 # sub-band energy, total band energy, # imgabs2 # band energy ratio, sample entropy and approximate entropy, and left and right brain symmetric distribution exists in the feature set. And the robust feature set is input into the brain fatigue detection model to obtain a detection result, so that the brain fatigue recognition precision is remarkably improved.

The invention relates to a hydroelectric generating set fault early warning method based on SCN and VMD-approximate entropy, and the method comprises the steps: building a time domain health model of a hydroelectric generating set based on a random configuration network, and calculating a relative error between a time domain feature actual value and a health value of the hydroelectric generating set, and taking the relative error as a time domain fault symptom index of the hydroelectric generating set; combining a variational mode decomposition algorithm with an approximate entropy algorithm to construct a frequency domain fault symptom index of the unit; and fusing to obtain a time-frequency domain fault symptom index as a unit vibration degradation index, and realizing unit vibration abnormity real-time early warning according to the unit vibration degradation index. According to the invention, effective combination of model driving and data driving is realized; and through real-time monitoring and early warning, potential faults of the unit can be found and processed in time, and the operation reliability of the unit can be improved.

The invention discloses a water turbine runner fault diagnosis method based on RLMD optimized by an improved masking signal method, and relates to the technical field of water turbine fault diagnosis. An obtained original sound vibration signal is decomposed into a plurality of components by using RLMD, a Spearman correlation coefficient is used to select a component containing effective features, and an approximate entropy is used to remove a component containing a high-frequency interference noise signal. According to the method, the selected components are masked by using the MS method, and the processed PF components are reconstructed to obtain denoised signals, so that the modal aliasing phenomenon is further reduced, the redundant semaphore entering subsequent calculation is greatly reduced, the improved MS-RLMD method is more suitable for water turbine fault diagnosis, the time required for fault detection is shorter, and the recognition precision is higher. The GWO-SVM of the SVM is optimized by using the grey wolf algorithm to recognize the denoised signal, the GWO optimization algorithm is used for parameter optimization, the SVM performance is further improved, and the recognition accuracy of the GWO-SVM is 96.67%.

The invention discloses an industrial sewage water quality soft measurement method. The method comprises the following steps: collecting sewage water quality data of a sewage plant; carrying out feature extraction on the input data by adopting an AHSICLasso method; decomposing the variable signal into a plurality of symplectic geometric components by using symplectic geometric mode decomposition (SGMD), and then performing secondary decomposition on the decomposed high-frequency nonlinear components through singular spectrum analysis (SSA); carrying out complexity quantification on the decomposed multi-mode component by utilizing approximate entropy so as to evaluate the dynamic characteristics of the multi-mode component; according to a quantization result, reconstructing the multi-mode component; using a time step adaptive dynamic selection mechanism and approximate entropy to screen components at past moments, and using CBO to optimize component weights; the AHSICLasso feature extraction data, the screened components at the past moment and the components obtained after secondary decomposition are input into an OfficANet model; the method comprises the following steps: optimizing hyper-parameters of an EfficANet model by using a CBO collider, introducing an adaptive attention weight mechanism into a GTVA module of the EfficANet model for improvement, and learning and predicting a reconstructed multi-modal component to realize soft measurement of total nitrogen in industrial sewage; according to the invention, high-precision and real-time prediction of the total nitrogen concentration of the industrial sewage is realized.

The invention discloses an attack detection method and device, equipment and a storage medium, and relates to the technical field of automobiles. The method comprises the steps that first message data received by a CAN in a first time period are acquired, the end time node of the first time period is the current moment, and the start time node is the historical moment spaced from the current moment by a preset duration; determining a message identifier Shannon entropy, a data field relative entropy and a time interval approximate entropy according to the first message data; performing weighted summation on the message identification Shannon entropy, the data field relative entropy and the time interval approximate entropy through an attention mechanism to obtain a composite entropy feature; and through a pre-trained anomaly detection model and the composite entropy features, determining whether the CAN suffers from hostile attacks in the first time period. Through the technical means, the stability of the message data is evaluated from the three dimensions of message identification, byte distribution and message time sequence, so that whether malicious attacks are injected into the message data or not is effectively identified, and accurate detection of the malicious attacks is realized.

The present invention relates to the field of electric power technology and discloses a fault detection method, storage medium and device for distribution overhead lines. The method comprises the following steps: obtaining a target signal set, decomposing the target signal to obtain multiple layers of high-frequency detail coefficients and multiple intrinsic mode functions to determine the weight, skewness, kurtosis and approximate entropy of each data in the high-frequency feature set, and constructing a multidimensional feature vector corresponding to the target signal. Finally, each multidimensional feature vector corresponding to each signal in the target signal set is input into a preset line fault prediction model to obtain a fault classification detection result. That is, by adopting weight, skewness, kurtosis and approximate entropy to construct a multidimensional feature vector corresponding to the target signal, key fault features can be accurately extracted from complex hidden fault signals, the accuracy of model fault detection is effectively improved, and solid and reliable technical support is provided for ensuring the intelligent operation of the power system.

The invention discloses an anesthesia equipment monitoring system and method, and relates to the technical field of anesthesia monitoring, and the method comprises the steps: constructing an anesthesia path and an anesthesia depth table based on a general anesthesia operation flow, and covering the anesthesia depth ranges of different anesthesia types and patient physiological states; acquiring an anesthesia depth construction sequence of a patient, and analyzing and judging whether the anesthesia depth is stable or not by using approximate entropy; if not, the correlation between the curve feature points and the operation state change sequence is analyzed; if yes, the consistency of the current anesthesia depth change curve and the historical anesthesia depth change curve is compared; if the change trends are inconsistent, performing time section division on the anesthesia depth sequence, calculating approximate entropies in the time sections, performing prediction analysis, judging whether the anesthesia depth of the patient in the future time section is stable or not, and if the anesthesia depth is not stable, generating an anesthesia early warning signal; the anesthesia scheme can be optimized, and the safety of a patient is guaranteed.

This invention relates to the field of healthcare informatics technology, specifically to a dynamic prediction system for the risk of delayed chest closure after surgery in children with congenital heart disease. It collects high-frequency vital signs signals during surgery, imaging report text, and clinical structured data; extracts the maximum Lyapunov exponent, correlation dimension, and approximate entropy as chaotic features; quantifies the ambiguous semantics in the imaging report into membership values; uses Dempster-Shafer evidence theory to fuse multimodal features and encode uncertainty; constructs a dynamic ensemble learning model, detects concept drift using ADWIN and updates it online, dynamically weights it based on Shapley values; uses multi-objective reinforcement learning to dynamically optimize the risk threshold; and generates counterfactual explanations to provide individualized intervention suggestions. This invention achieves accurate and dynamic early warning of the need for delayed chest closure.

The invention relates to an improved support vector machine fault diagnosis method based on multi-feature signal fusion. The method specifically comprises the following steps: acquiring an aviation bearing vibration signal; performing fast Fourier transform on the aviation bearing vibration signal to extract a frequency domain characteristic signal; respectively decomposing the aircraft bearing vibration signal by adopting improved completely adaptive noise set empirical mode decomposition and variational mode decomposition; calculating an approximate entropy and a fuzzy entropy of the decomposed aviation bearing vibration signal to obtain two time-frequency characteristic signals, and fusing the time-frequency characteristic signals with a frequency domain characteristic signal to obtain a fused characteristic signal; using a random forest feature screening method to evaluate and select the importance of the fusion feature signal, and then performing further dimension reduction on the feature signal through principal component analysis to obtain a low-dimension fusion feature signal; and inputting the signals into an atomic search algorithm optimized support vector machine improved by Logistic-Tent mapping and Levy flight variation, and respectively carrying out model training and fault diagnosis.

The application relates to a sea surface target recognition method using a time domain approximate entropy feature, and belongs to the technical field of radar signal processing and feature recognition. The method comprises the following steps: 1, target echo data buffering; 2, target time domain approximate entropy feature extraction echo data time domain analysis; 3, time domain approximate entropy feature optimization; and 4, target recognition using the time domain approximate entropy feature. The application aims to recognize sea surface targets under the condition that traditional target features cannot effectively recognize targets.

The application discloses a kind of drop lightning arrester multi-source signal discrimination and alarm method, it is related to the on-line monitoring and fault early warning technical field of power system equipment, the application can effectively separate high-frequency sub-band signal by wavelet packet decomposition technology, adapt to non-stationary vibration environment, ensure the robustness of feature extraction;The introduction of approximate entropy and peak factor and other characteristics, quantifies the randomness and impact of signal, can sensitively capture the subtle changes in the fatigue accumulation process of lead wire;Single-class classification model trained only by healthy sample is used, such as support vector data description, decision boundary is constructed, so that the model has high sensitivity to abnormal state, and can early warning before lead wire fracture occurs;This kind of evaluation mode based on healthy baseline avoids the false alarm problem of traditional threshold method in complex environment.

A kind of permanent magnet synchronous motor bearing fault diagnosis method based on motor current analysis method, first acquisition permanent magnet synchronous motor stator U, V phase current signal, calculate W phase current;Three-phase current is obtained by space vector dimension reduction two-phase current under rectangular coordinate system, and two-phase current is carried out vector normalization processing;Based on the mechanism of action of bearing fault to current signal and the characteristics of current signal, the signal after space vector dimension reduction is carried out variation modal decomposition, the approximate entropy of modal component is calculated and the feature matrix is formed;The improved standard artificial bee colony algorithm makes the bee colony type mutually transform according to the optimal solution, and changes the bee colony initialization population generation rule, the optimal classification model is obtained by using the optimized adaptive variable type algorithm to optimize machine learning model parameter;Using optimal model, the test set in sample set is classified according to fault type, and compared with label to obtain test set accuracy rate;The present application has the advantages of high accuracy, high diagnostic efficiency and the like.

The invention discloses a real-time intelligent prediction method and system for cobalt ion concentration in a zinc hydrometallurgy purification process, and the method comprises the steps: S1, collecting a cobalt ion concentration data set generated in the zinc hydrometallurgy purification process in a preset time period, and carrying out the preprocessing of the cobalt ion concentration data set, and obtaining an updated cobalt ion concentration data set; s2, decomposing the updated cobalt ion concentration data set by using an ITD decomposition algorithm, wherein a decomposed cobalt ion concentration sub-sequence comprises an inherent rotation component and a residual component; s3, performing complexity analysis on the decomposed cobalt ion concentration subsequences by adopting approximate entropy, and classifying the decomposed cobalt ion concentration subsequences based on an entropy calculation result; s4, predicting the classification results by using a machine learning algorithm to obtain prediction results; and S5, reconstructing the prediction result to obtain a cobalt ion concentration prediction result, and displaying the cobalt ion concentration prediction result.

The present invention discloses a method for solving structural parameters based on complete modal decomposition and random forest response surface fitting. First, obtain the estimated values of the structural natural vibration frequencies and the number of dominant frequencies. Secondly, obtain the minimum frequency difference, design a frequency overlap criterion and combine it with VMD to determine the number of decomposition components K, and perform noise reduction processing on the K + 1 components including the obtained K IMF components and the residual term respectively. Then, use the variable-speed GWO algorithm combined with the FIR band-pass filter to perform complete division on the noise-reduced and reconstructed signal, set the objective function by comprehensively considering the correlation coefficient, mutual approximate entropy and envelope spectrum entropy, determine the weights of different factors and obtain the optimal segmentation frequency, and solve the damping ratio based on the single-mode attenuation signals of each order. Finally, use the random forest to fit the response surface and combine the modal frequencies to solve the structural elastic modulus and Poisson's ratio. The present invention can accurately identify the modal structure parameters in an environment with strong noise and dense modes, and improve the accuracy, robustness, reliability and practicability of the algorithm.

The application discloses a kind of electric vehicle direct current charging fault diagnosis model training method, diagnosis method, it is related to electric vehicle charging facility test and diagnosis technical field.The electric vehicle direct current charging fault diagnosis model training method, diagnosis method injects 1kHz-100kHz wide frequency test signal, synchronously collects direct current voltage V (t) and current I (t) signal, calculates impedance amplitude spectrum |Z (f)|, forms three-way analysis signal;To each signal parallel extraction wavelet energy entropy, wavelet singular spectrum entropy, approximate entropy, power spectrum entropy four kinds of time-frequency domain entropy features, constructs 12-dimensional fusion feature vector, innovatively introduces four-dimensional confidence evaluation system (maximum probability confidence, probability distribution entropy confidence, classification interval confidence, feature space distance confidence), according to fault type characteristics Dynamic allocation weight, realize comprehensive confidence fusion;Finally, based on confidence threshold, three-level decision output is carried out.

The invention relates to the technical field of electric power, and discloses a power distribution overhead line fault detection method, a storage medium and equipment, and the method comprises the steps: obtaining a target signal set, carrying out the decomposition of a target signal, obtaining a multi-layer high-frequency detail coefficient and a plurality of intrinsic mode functions, determining the weight, skewness, kurtosis and approximate entropy of each piece of data in a high-frequency feature set, and carrying out the calculation of the weight, skewness, kurtosis and approximate entropy; and finally, inputting each multi-dimensional feature vector corresponding to each signal in the target signal set into a preset line fault prediction model to obtain a fault classification detection result. The multi-dimensional feature vector corresponding to the target signal is constructed by adopting the weight, the skewness, the kurtosis and the approximate entropy, so that the key fault features can be accurately extracted from the complex hidden fault signal, the accuracy of model fault detection is effectively improved, and a firm and reliable technical support is provided for guaranteeing the intelligent operation of a power system.

This application belongs to the field of battery thermal runaway prediction technology, and discloses a method, apparatus, device, and medium for battery thermal runaway prediction based on segmented features. The method includes: acquiring the voltage and specified data of each cell in the battery; slicing the specified data according to a preset dimension segmentation rule to obtain slice datasets for each dimension; sorting the cell voltages of each frame of data in each slice dataset, and calculating the mode of the sorted values ​​of each cell per preset time unit under each slice dimension; extracting time-series features, including complexity features, approximate entropy features, average absolute change values, and coefficient of variation, based on the time-series data of the mode of the sorted values ​​of each cell; and predicting the probability of battery thermal runaway based on the time-series features. This application improves the accuracy of battery thermal runaway prediction through multi-dimensional slicing, mode statistics of sorted values, and extraction of time-series features, providing strong support for battery safety management.

The present invention discloses a denoising method for a TDLAS gas monitoring system. The method first obtains a noisy second harmonic signal collected by the TDLAS gas monitoring system, then removes the distorted signal based on the symmetry of the second harmonic signal, performs baseline calibration on the signal, performs ICEEMDAN decomposition using characteristic selection parameters of the second harmonic signal, calculates the approximate entropy of all IMF components and the second harmonic signal, classifies the IMF components according to defined threshold values, denoises the noisy IMF components using multi-layer wavelet decomposition and a wavelet soft threshold function, and then reconstructs the denoised second harmonic signal to complete the denoising process. The present invention can effectively suppress background noise and improve the signal-to-noise ratio, thereby reducing the minimum detection limit of the gas monitoring system and improving system performance. The method is mainly used in the field of environmental monitoring.

The application provides a method for determining the first stage of compressor surge based on variational mode decomposition and approximate entropy, and belongs to the technical field of aero-engines, comprising: arranging dynamic pressure sensors on each pressurization stage of the compressor part of an aero-engine to obtain original signals of each pressurization stage; performing variational mode decomposition on the original signals mixed with the surge signals and modal waves to obtain a plurality of intrinsic modal components containing the surge signals; calculating the approximate entropy of the plurality of intrinsic modal components, determining the decomposition layer number of the variational mode decomposition based on the approximate entropy; reconstructing the original signals under different values of a penalty factor, and determining the penalty factor according to the signal-to-noise ratio of the reconstructed original signals; performing variational mode decomposition on the original signals mixed with the surge signals and modal waves based on the decomposition layer number and the penalty factor to obtain the final intrinsic modal component signals containing the surge signals, and comparing the final intrinsic modal component signals containing the surge signals with the original signals of each pressurization stage to determine the first stage of surge.

The present invention provides a method for predicting the remaining life of a mechanical structure based on a Wiener process and P‑EMD, and belongs to the technical field of the remaining life estimation of mechanical products. The method comprises: using P‑EMD to decompose the collected vibration signal of the mechanical structure to obtain a plurality of IMFs, wherein P‑EMD represents the empirical mode decomposition based on particle swarm optimization and based on Hermite interpolation polynomials, and IMF represents the intrinsic mode function; calculating the approximate entropy of the decomposed IMF signal, and discriminating the degradation trend of the approximate entropy; based on the change trajectory of the approximate entropy, using the remaining life estimation model based on the Wiener process to predict the remaining life of the mechanical structure. The present invention can improve the prediction accuracy of the remaining life of the mechanical structure.

The invention discloses a dangerous rock mass damage early recognition method and system based on a three-dimensional approximate entropy index, and relates to the technical field of slope collapse geological disaster monitoring and early warning, and the method comprises the steps: synthesizing XYZ three-direction vibration data of a target dangerous rock mass into a three-dimensional time sequence, and obtaining a dangerous rock mass space position sequence; based on the first preset time sequence window and the second preset time sequence window, a plurality of first subsequences and a plurality of second subsequences of the dangerous rock mass space position sequence are extracted respectively; calculating a three-dimensional approximate entropy index of the target dangerous rock mass based on the plurality of first subsequences and the plurality of second subsequences; and performing damage identification on the target dangerous rock mass based on the change trend of the three-dimensional approximate entropy index. The technical problem that the multi-direction damage of the dangerous rock body is difficult to accurately reflect in the prior art is solved.

The invention relates to an underwater acoustic signal denoising method and system based on SVMD optimization and wavelet threshold improvement, and the method comprises the steps: employing a state optimization algorithm to optimize an SVMD model, enabling an underwater acoustic signal to be decomposed into a plurality of IMF components, and employing the ratio of an approximate entropy to a cross correlation coefficient as a classification parameter, dividing the signal into a pure signal component, a noisy signal component and a noise dominant component; carrying out wavelet decomposition on the noisy signal component, extracting a low-frequency approximation coefficient and high-frequency detail coefficients of each layer, and carrying out threshold denoising on the high-frequency detail coefficients layer by layer by adopting an improved cosine semi-soft threshold function with smoothness control parameter constraint and combining a wavelet threshold adaptively obtained based on a generalized cross validation criterion; and performing wavelet reconstruction on the denoised high-frequency detail coefficient and low-frequency approximation coefficient of each layer, and performing linear superposition on an obtained denoised signal component and a pure signal component to obtain a denoised underwater acoustic signal. According to the method, the dependency of underwater sound denoising on parameters is reduced, and meanwhile, the denoising effect is improved.

The invention belongs to a feature selection method based on fuzzy approximate composite entropy and applies the feature selection method to the technical field of fault diagnosis, and particularly relates to a fault diagnosis method based on feature selection of fuzzy approximate composite entropy, which comprises the following steps of: proposing a fuzzy decision; providing fuzzy lower approximation and fuzzy upper approximation under the fuzzy decision; proposing a lower fuzzy dependency degree based on fuzzy lower approximation and an upper fuzzy dependency degree based on fuzzy upper approximation; combining the lower fuzzy dependency degree, the upper fuzzy dependency degree and a fuzzy entropy theory, and respectively constructing a fuzzy lower approximate composite entropy and a fuzzy upper approximate composite entropy; internal and external attribute importance functions are constructed by using the fuzzy joint approximate composite entropy, and a feature selection algorithm based on the fuzzy joint approximate entropy is provided; and finally completing the fault diagnosis of the rolling bearing based on a fault diagnosis method of feature selection and a classifier. According to the method, the classification precision and the fault diagnosis accuracy can be remarkably improved while redundant features are effectively eliminated.

The invention belongs to the technical field of battery thermal runaway prediction, and discloses a battery thermal runaway prediction method and device based on segmentation characteristics, equipment and a medium. The method comprises the following steps: acquiring voltage and specified data of each monomer in a battery; performing slicing processing on the specified data according to a segmentation rule of a preset dimension to obtain a slice data set of each dimension; sorting the monomer voltage of each frame of data in each slice data set, and counting the sorting value mode of each monomer in each preset time unit under each slice dimension; extracting time sequence features including complexity features, approximate entropy features, average values of absolute change values, variation coefficients and the like based on the order value mode time sequence data of each monomer; and predicting the probability of thermal runaway of the battery based on the time sequence characteristics. Through multi-dimensional slicing, sorting value mode statistics and time sequence feature extraction, the accuracy of battery thermal runaway prediction is improved, and powerful support is provided for battery safety management.