11 results about "Fuzzy entropy" patented technology

The present application provides a kind of vital signs detection signal denoising method and device, it is related to physiological perception and signal processing technical field, including: based on millimeter wave radar's Doppler technique, obtains the original phase signal containing physiological signal;Original phase signal is carried out variational mode decomposition based on the search algorithm of variational mode decomposition super parameter optimization algorithm optimized by particle swarm optimization algorithm, obtain the vibration modal function information corresponding to the original phase signal;Wherein, the particle swarm optimization algorithm uses permutation entropy and fuzzy entropy as fitness function;After denoising processing is carried out to the vibration modal function, the vibration modal function after denoising processing is recombined, and high-precision denoising processing is obtained after physiological signal;From the high-precision denoising processing physiological signal, extract respiratory and heartbeat physiological signal.

This invention discloses a lithology identification method based on hybrid mode decomposition and fuzzy entropy-PSO optimization of drilling signals, belonging to the field of integrated deep earth space exploration and drilling geophysical exploration technology. The method first acquires real-time seismic monitoring signals during drilling; then, it uses an empirical and variational hybrid mode decomposition (EVMD) method to decompose the original signal, removing strong noise disturbances; finally, it employs a particle swarm optimization (PSO) algorithm combined with adaptive optimization using fuzzy entropy as the objective function to obtain the optimal parameter combination [K, α] of EVMD, and decomposes it to obtain the optimal modal data and construct a multi-dimensional feature vector, completing the real-time identification and judgment of strata lithology and rock mass structural characteristics. This invention effectively solves the technical problems of traditional methods, such as difficulty in separating strong noise, fixed parameters that cannot be adaptively adapted, mode aliasing, and poor real-time performance. It achieves extremely high lithology identification accuracy and is suitable for deep earth space development, deep resource exploration, and intelligent construction of underground engineering projects.

This invention discloses a method for monitoring the state trends of hydropower units based on two-stage signal decomposition and the IBiLSTM model. The method involves collecting vibration signals from the hydropower units for preprocessing; constructing the ITGCOA optimization algorithm and designing a fitness function; using the ITGCOA optimization algorithm to adaptively optimize the SVMD and BAACMD models, achieving initial decomposition of the preprocessed signal and secondary decomposition of the sub-mode component with the highest center frequency obtained from the initial decomposition; calculating the fuzzy entropy values ​​of the remaining sub-mode components for reconstruction; and fusing the high-frequency feature sub-sequences obtained from the secondary decomposition with the reconstructed feature sub-sequences to construct the input sequence of the prediction model. This input sequence is then used to construct the IBiLSTM prediction model for monitoring the state trends of hydropower units, achieving high-precision prediction. Compared with existing technologies, this invention improves the efficiency and accuracy of hydropower unit state trend prediction, accurately warns of abnormal unit operating conditions, ensures the safe and stable operation of the units, and improves the overall efficiency of the power plant.

This invention relates to the field of computer technology and provides an algorithm for analyzing the complexity of EEG signals based on multi-domain fusion. The method includes: data preprocessing to acquire multi-band, multi-channel EEG signals; single-scale single-channel analysis at the single-scale level, performing single-scale single-channel analysis on the multi-band, multi-channel EEG signals and outputting multi-band fuzzy entropy; multi-scale single-channel analysis at the multi-scale level, performing multi-scale single-channel analysis on the multi-band, multi-channel EEG signals and outputting a multi-scale fuzzy entropy vector; and multi-scale multi-channel analysis at the multi-scale level, performing multi-scale multi-channel analysis on the multi-band, multi-channel EEG signals and outputting multi-channel multi-scale fuzzy entropy. This invention, through multi-band decomposition combined with multi-scale multi-channel analysis, can comprehensively capture the dynamic variation characteristics of EEG signals across different frequency bands, scales, and channels, effectively solving the problem of incomplete information extraction in traditional methods and improving the ability to characterize the dynamic characteristics and complexity of EEG signals.

This invention discloses a multi-energy power prediction method integrating signal processing and machine learning, belonging to the field of new energy power system prediction and dispatch technology. For wind and solar power prediction, historical power time-series data from wind farms and photovoltaic power plants are collected. The wind and solar power sequences are decomposed using IMF, and the fuzzy entropy of each component is calculated and grouped according to the center frequency. Based on thresholds, LSTM and GRU models combined with SSA are used to predict wind and solar power respectively. For hydropower, based on historical meteorological data from reservoirs, recurrent neural networks and NGboost-TPE models are used to obtain daily and monthly inflow point predictions and probability predictions, which are then converted into predicted hydropower output. This invention achieves a deep integration of signal processing in feature extraction and complexity quantification with machine learning in time-series modeling and uncertainty quantification.

The present application relates to the field of optical communication and network security technology, and specifically relates to a spectrum fingerprint identification method based on multi-domain joint features, comprising: signal preprocessing, extracting statistical features of mixed signals, extracting distribution features of mixed signals, and classifying mixed signals; the present application extracts time domain and frequency domain features of optical signals transmitted by users through wavelet transform and Fourier transform, constructs a spectrum fingerprint database; extracts physical layer fingerprint features, namely fuzzy entropy features and empirical mode decomposition features of chaotic time series, constructs a physical fingerprint database, realizes the differentiation of legal users and illegal users by using convolutional neural network and support vector machine, and realizes high-precision and real-time user identity recognition through joint identification of spectrum fingerprint and physical fingerprint, improves the anti-interference ability and security of optical networks, and is suitable for the security access scene of future dynamic optical networks.

The application discloses a kind of based on multi-source data fusion and deep optimization network's fault diagnosis method, belong to wind turbine bearing fault diagnosis technical field, including: obtaining the multi-source sensor data of wind turbine under different working conditions, and the multi-source sensor data collected is preprocessed;Design multi-source data feature fusion algorithm based on correlation variance contribution, the multi-source sensor data after pre-processing is fused, and the fuzzy entropy value of the multi-source sensor data after fusion is extracted as the feature vector of input intelligent fault diagnosis model;Intelligent fault diagnosis model DBE based on optimized deep belief network is constructed, and the method and hippocampus optimization algorithm of greedy learning are used to train DBE;Based on the trained DBE, fault diagnosis is carried out.The method solves the problems of signal abnormal value and data missing under the influence of wind turbine variable working condition and external noise interference and fault diagnosis reliability, improves the accuracy of wind turbine fault diagnosis.

The application discloses a rotating machinery fault diagnosis method based on dynamic adaptive continuous wavelet fuzzy entropy, and relates to the technical field of mechanical fault diagnosis. The method first collects a rotating machinery vibration signal and pre-processes, carries out second-order dynamic change enhancement processing on the signal, highlights fault impact features and suppresses low-frequency interference; then adaptively determines a continuous wavelet transform decomposition scale number according to a spectrum entropy of the enhanced signal, and completes multi-scale time-frequency decomposition; subsequently, calculates fuzzy entropy of each scale wavelet component, and splices to form a feature vector; finally, inputs the feature vector into a random forest classification model to complete fault recognition. The application combines dynamic change enhancement with adaptive scale decomposition, improves fault feature extraction precision of non-stationary and noisy vibration signals, gets rid of the limitation of artificial parameter setting, improves stability and generalization ability of the diagnosis method, and is suitable for efficient and accurate diagnosis of multiple types of rotating machinery faults.

The application discloses a kind of lithium battery surface temperature soft monitoring method and system, the method includes: step 1, obtains lithium battery surface temperature signal and the operating state variable related to lithium battery thermal behavior;Step 2, the multiple variables of step 1 obtained are decomposed component and are normalized;Step 3, obtain trend mode prediction result, periodic mode prediction result and noise mode prediction result;Step 4, the optimal parameter combination of each model is output, and the optimal prediction result is obtained;Step 5, using fuzzy entropy determines the weight coefficient of model corresponding prediction result, and each model output result is weighted fusion, obtains lithium battery surface temperature final prediction value.The application can improve the accuracy and stability of lithium battery surface temperature soft monitoring under complex working conditions.

The application provides a multi-target micro-grid power load prediction method, comprising the following steps: step 1, collecting power load data of a micro-grid; step 2, decomposing the power load data by using a method combining time-varying filter characteristic modal decomposition and fuzzy entropy aggregation; step 3, sending the decomposed power load data into an improved Scaleformer model with a multi-target attention mechanism to perform prediction, and obtaining a final charging load prediction result; step 4, using a multi-target marine predator algorithm to optimize parameters in a TVF-FMD method with local fuzzy entropy and minimum error after decomposition as objective functions; and step 5, using a spatiotemporal correlation weighted fluctuation high-order moment error and a multi-scale peak weighted nonlinear error as objective functions to optimize parameters in the improved Scaleformer model. The application greatly improves the accuracy and efficiency of charging load prediction, and is beneficial to meet the prediction requirements in some complex environments.

The application discloses a real-time positioning method for rotor sites of atrial fibrillation. The method performs three-dimensional modeling on an atrium in operation, derives bipolar endocardial electrical signals and electrode positions collected by a multi-pole mapping catheter PENTARAY electrode pair from a CARTO3 system, then calculates average fuzzy entropy of the bipolar endocardial electrical signals, selects electrodes according to the calculated average fuzzy entropy of each electrode, draws a vector through entropy difference between the selected electrode pairs, finds a direction where the rotor is located by using a vector method and an expression, and finally determines a specific position of the rotor through the expression and a relationship between distance and energy. The application adopts endocardial bipolar electrical signals, can well remove ventricular noise, better guides a doctor to find a rotor direction of the atrial fibrillation in operation, accurately positions a specific position of the rotor site, greatly reduces an ablation area, increases a success rate and a recurrence rate of radiofrequency ablation operation, and can have a lower sequelae after operation.