188 results about "Sample entropy" patented technology

The invention belongs to the field of wind power prediction, and provides an ultra-short-term wind power prediction method based on secondary decomposition and TCN-ECA-BiGRU by considering the strong volatility and randomness of wind power. The method comprises the following steps: firstly, constructing a secondary mode decomposition framework based on improved complete set empirical mode decomposition, sample entropy, K-means clustering and variational mode decomposition, adaptively selecting components with relatively high complexity for secondary decomposition, and weakening volatility and randomness of an original sequence; and then, on the basis of the time convolutional network, an efficient channel attention module (ECA) is introduced to mine a coupling relationship among components, weights are given to the components in a self-adaptive manner to highlight important information, and a long-term time sequence dependency relationship of the components is further captured by using a bidirectional gating cycle unit, so that the prediction effect of the ultra-short-term wind power is effectively improved.

The invention relates to the technical field of crane line fault diagnosis, in particular to a crane line fault diagnosis system and method based on multi-source data fusion, which comprises a data acquisition and processing unit, a mechanical and electrical coupling characteristic unit and a characteristic fusion and fault quantification unit, the three-axis vibration acceleration and the three-phase current waveform of the track are obtained through the data collecting and processing unit, the mechanical and electrical coupling characteristic unit conducts three-dimensional vector synthesis and wavelet packet decomposition on vibration data, and a time-space incidence matrix of harmonic distortion and vibration is constructed. And the feature fusion and fault quantification unit outputs coupling factors by using a bidirectional long-short-term memory network and an attention mechanism, and outputs a fault probability value through a dynamic time warping matching algorithm after time-frequency domain analysis and sample entropy judgment, so that time-space correlation modeling and dynamic fault matching of multi-source data are realized. And the fault positioning precision and the diagnosis accuracy are improved.

The invention discloses an office building energy consumption prediction method and system, and relates to the technical field of energy consumption prediction, and the method comprises the steps: collecting the current office building energy consumption data; decomposing the load sequence into a plurality of modal components, calculating the sample entropy of each modal component, and recombining the modal components by using a K-means clustering algorithm according to the calculation result of the sample entropy; taking each mode component after recombination as a node, taking the time sequence similarity between the mode components as an edge between the nodes, and constructing a graph structure; inputting the graph structure into a GCN-Transform model, extracting spatial features of nodes in the graph structure, and introducing a self-attention mechanism to extract time sequence features; inputting the spatial-temporal characteristics into a full-connection layer to obtain an energy consumption predicted value in a future period of time; according to the method, space cooperation and time dependence can be considered at the same time in a complex and changeable energy consumption scene, so that a more accurate prediction result is provided.

The invention discloses an intelligent power prediction method considering dynamic load change, and relates to the technical field of power grid load prediction, and the method comprises the steps: collecting original load data, carrying out the preprocessing, constructing a VMD constraint optimization model, carrying out the four-stage improvement of optimization parameters through employing an improved dung beetle optimization algorithm, so as to generate IMF components, reconstructing the IMF component by calculating a sample entropy to obtain a low-frequency component and a high-frequency component; establishing a Kalman filtering state space model based on the low-frequency component, and decomposing the low-frequency component into a residual component and a pseudo trend component through a Kalman filtering recursive algorithm; external features are obtained, the high-frequency component, the residual component and the pseudo trend component are aligned and spliced with the external features, multi-component collaborative prediction is carried out through a local-global interactive attention mechanism, and a final load prediction result is obtained; and generating a power demand visualization chart based on the final load prediction result. And reliable decision support is provided for power dispatching and energy management.

The invention discloses an electric vehicle charging load prediction method and system, and the method comprises the steps: collecting and obtaining the historical charging load time series data of an electric vehicle, and employing an ICEEMDAN model to carry out the decomposition of the charging load time series data, and obtaining a plurality of components; performing sample entropy calculation on the components, and performing signal classification by adopting K-medoids clustering according to a sample entropy result to obtain a high-frequency component F1, an intermediate-frequency component F2 and a low-frequency component F3; carrying out secondary decomposition on the high-frequency component F1 by adopting a characteristic mode decomposition (FMD) model to obtain a plurality of components; the MTS-Mixers model, the Crossform model and the DeepESN model are optimized by using an improved artemisinin AO optimization algorithm, and a high-frequency component F1, an intermediate-frequency component F2 and a low-frequency component F3 are predicted; the prediction results of the AO-MTSMixers model, the AO-Crossform model and the AO-DeepESN model are reconstructed, and the prediction result of the charging load is obtained; compared with a traditional method, the charging load prediction accuracy can be improved, and powerful support is provided for charging use and management of the electric vehicle.

The invention relates to the technical field of machine learning, and discloses a load prediction method based on dual feature processing and error correction. The method comprises the following steps: acquiring multi-source time sequence data; decomposing the historical load data into a plurality of modal components by adopting a variational modal decomposition algorithm; classifying each modal component into different frequency levels according to the size of the sample entropy; performing phase-space reconstruction according to the modal component of each frequency level and the corresponding external influence factor data, and generating a multivariable phase-space data set of each frequency level; respectively inputting the multivariable phase space data set of each frequency level into the corresponding load prediction sub-model, generating prediction output results, and superposing the prediction output results; constructing a residual sequence based on the historical load data and the initial load prediction result; inputting the residual error sequence into a residual error prediction model to obtain a load residual error prediction value; and compensating the initial load prediction result through the load residual prediction value. According to the scheme, the load prediction accuracy can be improved.

The invention discloses a spatio-temporal crime prediction method and system fusing spatio-temporal heterogeneous information. The method comprises the following steps: constructing a spatio-temporal data set; constructing a crime time sequence signal data set; periodically decomposing the time sequence signal into a plurality of intrinsic mode functions (IMF); the sample entropy is used as a fitness function to evaluate the advantages and disadvantages of decomposition results under different parameter combinations so as to determine the optimal input time window length; performing clustering processing on the crime data to identify urban crime hotspot areas, and generating crime spatial distribution data; performing feature analysis in time and space, and further completing contribution evaluation of key features to the crime situation; constructing a space-time prediction model, and segmenting a three-dimensional space-time data set into samples in a sliding window mode according to a time window determined in a self-adaptive mode to serve as input and output of the model; and completing training and tuning of the model. And a more accurate and efficient solution is provided for urban crime situation analysis.

The invention discloses a wind power plant wind speed prediction method, system and device and a storage medium, and the method comprises the steps: optimizing the white noise amplitude weight and noise addition times in adaptive noise ensemble empirical mode decomposition CEEMDAN through employing an improved energy valley optimization algorithm IEVO, and carrying out the CEEMDAN decomposition of the historical data of a wind power plant; the decomposed data is preprocessed by adopting sample entropy SE, so that the calculation complexity of the data is reduced; for the preprocessed data, introducing a random forest algorithm RF feature selection of a heuristic strategy for optimization, and eliminating redundant features; converting the optimized data from one-dimensional time sequence data into a two-dimensional image by using a GASF (Grubby Amplitude Shift Function), and extracting image features; the extracted image features are sent to a time sequence block converter Patch TST model for wind speed prediction, and a training algorithm GPTuner based on a gradient boosting decision tree is introduced into the Patch TST model to adjust model parameters; compared with a traditional method, the accuracy of wind speed prediction can be effectively improved, and stable operation of a wind power plant is guaranteed.

The invention relates to the field of state monitoring and fault diagnosis of power equipment, in particular to a transformer fault diagnosis method based on a chaos evolutionary optimization algorithm, which comprises the following steps of: 1, acquiring a magnetic flux leakage signal during operation of a transformer; 2, optimizing a parameter modal number K and a penalty factor alpha of variational modal decomposition by using a chaos evolutionary optimization algorithm; 3, performing variational mode decomposition on the magnetic flux leakage signal to obtain an intrinsic mode function component; 4, calculating the envelope entropy of the intrinsic mode function component, and obtaining an effective intrinsic mode function component through screening; 5, extracting the energy entropy and the sample entropy of the effective intrinsic mode function component to form a feature vector; and 6, inputting the feature vector into a pre-trained support vector machine classifier, and outputting a fault type diagnosis result of the transformer. According to the method, the CEO algorithm is combined with the ergodicity of chaotic mapping and the global search capability of the evolutionary algorithm, and the problems that VMD parameters K and alpha are sensitive and depend on experience, and a traditional optimization algorithm is prone to local optimum are effectively solved.

The invention provides a satellite network self-similar traffic prediction method based on double decomposition and a neural network, and relates to the technical field of satellite networks. The method comprises the following steps: firstly, performing first modal decomposition on an original self-similar traffic sequence of a satellite network by using a CEEMDAN algorithm, and decomposing the original self-similar traffic data sequence into a plurality of IMF components; dividing the IMF components into high-frequency components, intermediate-frequency components and low-frequency components by calculating the sample entropy of each IMF component after decomposition; performing second modal decomposition on the clustered high-frequency components by using a VMD decomposition model; then constructing a CNN-BiLSTM-based self-similar flow prediction model, and respectively inputting each IMF component subjected to two-time decomposition into the model for prediction; meanwhile, an improved artificial rabbit optimization algorithm is adopted to optimize hyper-parameters of the self-similar flow prediction model, and an optimal self-similar flow prediction model is obtained. The method can effectively improve prediction precision and reduce prediction errors.

The invention relates to the technical field of steel structure wind resistance detection, in particular to a steel structure wind resistance detection method and system. The method comprises the following steps: constructing a steel structure geometric model, calculating a geometric instability angle between steel structure surfaces through a stereographic projection method, and identifying instability areas under different wind load conditions; arranging a sensor in the instability area, and collecting and normalizing dynamic response data to construct combined time sequence data of the instability area; setting a reference entropy value and an instability entropy threshold value, calculating a sample entropy of the instability region combined time sequence data, and determining an instability region; and calculating an instability risk index by using a combined risk assessment formula, and assessing the risk of the instability region based on the instability risk index. According to the method and system for detecting the wind resistance of the steel structure, the stereographic projection method and the entropy theory are combined, the instability risk area is recognized under different wind load conditions, the comprehensive instability risk index is defined and calculated, and multi-dimensional quantification and early warning of the instability risk of the structure are achieved.

The invention discloses a method for predicting the charging load of an electric vehicle, and the method comprises the steps: collecting the historical charging load data of the electric vehicle, and carrying out the one-time decomposition of the time series data of the charging load through employing an ICEEMDAN model, and obtaining 10 components; performing sample entropy calculation on components obtained by primary decomposition, performing signal classification by adopting K-medoids clustering according to a sample entropy result to obtain a high-frequency component, an intermediate-frequency component and a low-frequency component respectively, optimizing parameters in an MTS-Mixers model, a Crossform model and a DeepESN model by using an improved AO optimization algorithm, and performing signal classification by adopting K-medoids clustering to obtain a high-frequency component, an intermediate-frequency component and a low-frequency component; and predicting the high-frequency component, the intermediate-frequency component and the low-frequency component by using an MTS-Mixers model, a Crossform model and a DeepESN model, and finally reconstructing prediction results of the three models to obtain a prediction result of the charging load.

The invention discloses a molten steel quality real-time prediction method based on sample entropy and fractal feature fusion evolution, and relates to the technical field of converter steelmaking molten steel quality prediction. A molten steel quality multi-index real-time prediction model is constructed and trained, fractal features and sample entropy features are innovatively introduced, converter steelmaking process data are deeply analyzed through a mathematical method, and key features are extracted and serve as model input. In the model construction stage, an LSTM network is selected, and the advantage of processing time sequence data of the LSTM network is utilized, so that the two key indexes of the carbon element content and the temperature of the molten steel are predicted at the same time; and the LSTM network is further optimized by adopting a multi-objective algorithm, the molten steel quality real-time prediction model based on sample entropy and fractal feature fusion evolution is obtained, the model can more quickly and accurately complete the real-time prediction task of the molten steel carbon element content and the temperature, and powerful support is provided for accurate control of the converter steelmaking process.

The invention discloses an orbit fault diagnosis method and system, and the method comprises the steps: calculating a sample entropy, an energy entropy, a power spectrum and a permutation entropy of an optimal solution # imgabs0 #, selecting an optimal entropy from the sample entropy, the energy entropy, the power spectrum and the permutation entropy according to a preset optimal entropy weight selection strategy, and extracting typical features according to the optimal entropy; an improved CNN-BiLSTM-SA neural network is constructed, and sequence space features are extracted according to the improved CNN-BiLSTM-SA neural network; hyper-parameters of the CNN-BiLSTM-SA neural network are optimized and improved according to a Cauchy-Euclidean clustering particle swarm optimization algorithm, and an orbit fault diagnosis model is obtained; the optimal solution # imgabs1 # of the steel rail vibration signals, the typical features and the sequence space features are fused to obtain fused features, the fused features are input into a rail fault diagnosis model, and the rail fault diagnosis model outputs and obtains a rail fault diagnosis result. The accuracy and efficiency of track fault category diagnosis can be improved.

The invention discloses an ultra-short-term wind power prediction method based on scene real-time switching. The method comprises the following steps: firstly, extracting a multi-dimensional feature vector capable of representing a wind speed fluctuation degree from a historical wind speed time sequence; and then clustering the multi-dimensional feature vectors by adopting a K-means clustering algorithm, and dividing the wind power operation state into a plurality of scenes. Then distinguishing a strong fluctuation scene and a weak fluctuation scene according to the sample entropy of each scene, wherein the strong fluctuation scene is predicted by adopting a CNN-BIGRU model; and the weak fluctuation scene adopts a least square support vector machine (LSSVM) model. And finally, according to the real-time wind speed data, identifying fluctuation characteristics of a previous time sequence segment of a to-be-predicted moment, calculating an Euclidean distance with a scene clustering center, judging a scene to which the to-be-predicted moment belongs, selecting a corresponding prediction model, and dynamically generating a wind power prediction result. According to the method, adaptive switching of different scenes can be realized in an environment with frequent and complex wind speed fluctuation, and the accuracy and stability of ultra-short-term wind power prediction are effectively improved.

The invention relates to the technical field of fault diagnosis, and discloses a fault diagnosis method and system applied to an automobile air conditioner compressor. The method comprises the following steps: firstly, introducing auxiliary noise to decompose a vibration signal, calculating a decomposition result by using a sample entropy method to obtain a sample entropy, and identifying and removing noise; secondly, variational mode decomposition is carried out on the vibration signals after noise elimination, an improved crayfish optimization algorithm is used for optimizing a decomposition scale and a penalty factor in the variational mode decomposition process, and a final IMF component signal set is obtained; mapping the final IMF component signal set to polar coordinates through a symmetric polar coordinate transformation method to form a fault diagnosis image set; and finally, training to obtain a convolutional neural network fault diagnosis model, identifying a fault diagnosis image set, and outputting a fault diagnosis result of the automobile air conditioner compressor. The vibration signal of the automobile air conditioner compressor is processed and analyzed, the purpose of fault diagnosis is achieved, and the method is objective and accurate.

The invention discloses a landslide displacement double-layer fusion prediction method and model, and the method comprises the steps: carrying out the decomposition of an original displacement time sequence through employing an ICEEMDAN algorithm, and obtaining a plurality of IMF components; performing feature engineering on each IMF component, representing a displacement trend by adopting a trend slope and a window mean value, representing mutation early warning by adopting kurtosis and a frequency spectrum entropy, representing a period rule by adopting a main frequency and a zero-crossing rate, representing system stability by adopting a sample entropy and a standard deviation, and constructing a three-dimensional feature space fusing a time domain and a frequency domain; data standardization is carried out on the extracted features, the interference effect of dimensions on the model is eliminated, and it is ensured that all feature dimensions are within a unified calculation scale range; a CNN-BiLSTM model is constructed for each IMF component; a CPO algorithm is used to optimize the CNN-BiLSTM model; according to the method, the data acquisition difficulty during model training and use can be reduced, and the usability of the model in actual deployment is enhanced; and the prediction precision and the accuracy of landslide displacement prediction are improved.

The invention discloses a wind power plant power prediction method and system in extreme weather and a medium, and belongs to the technical field of renewable energy power generation prediction. Comprising the following steps: acquiring historical weather characteristic data and corresponding wind power plant power data, and screening out weather characteristics with high correlation with the wind power plant power data through a maximum mutual information coefficient; processing the power data of the wind power plant by adopting a CEEMDAN method and a VDM method in combination with a sample entropy analysis and wavelet packet threshold denoising method to obtain a noise-suppressed and feature-enhanced wind power plant power sequence; based on weather features and a wind power plant power sequence with noise suppression and feature enhancement, a wind power plant power prediction model is constructed according to the BiLSTM network after hyper-parameter combination optimization to predict the power of the wind power plant in extreme weather; performing interval shrinkage reconstruction on the wind power plant power in the future extreme weather through time sequence similarity to obtain a final prediction result of the future wind power plant power; according to the invention, the wind power plant power prediction precision in extreme weather is improved.

The invention provides a rotating machine fault diagnosis method based on OCSSA-VMD-CNN-BILSTM. The rotating machine fault diagnosis method comprises the following steps: inputting a rotating machine vibration signal; obtaining a range of a vmd decomposition layer number K value through a center frequency method, and setting a range of a penalty factor alpha; and taking the minimum sample entropy as a fitness function, and performing parameter optimization on the VMD by using an improved sparrow optimization algorithm OCSSA to obtain a [K, alpha] optimal combination. According to the method, the bearing fault diagnosis model is built based on the CNN-BILSTM model, the multi-strategy fusion improved sparrow search algorithm (OCSSA) is utilized to optimize the VMD parameters, and when the model is subjected to hyper-parameter optimization, the OCSSA has extremely high convergence speed and extremely high test precision. According to the method, the optimal parameters of the vmd can be obtained without priori knowledge, the algorithm efficiency is improved, manual parameter screening is avoided, higher diagnosis precision and stability are achieved, and the generalization and intelligent level of a diagnosis model are greatly enhanced.

The invention relates to the technical field of load prediction, and provides a power load prediction method and system based on time sequence decomposition and an attention mechanism, and the method comprises the steps: carrying out the adaptive time sequence decomposition of an obtained original load sequence, calculating the sample entropy of each decomposed component, and carrying out the clustering; constructing a group of encoder and decoder networks for each piece of clustered data, performing parallel encoding to extract features, performing serial decoding reconstruction on the features from low frequency to high frequency, and outputting prediction data from low frequency to high frequency step by step; the weight is initialized based on the sample entropy, the trained weight is obtained through optimization in the encoder and decoder network training process, and the predicted value of the power load is obtained through weighted fusion. According to the method, adaptive time sequence decomposition, a weight mechanism guided by sample entropy and an attention-enhanced encoder-decoder structure are introduced, so that multi-component collaborative modeling and cross-scale dynamic prediction are realized, and the prediction accuracy and stability in complex load data and small sample scenes are effectively improved.

The invention discloses a short temporary wind speed extrapolation method based on a decomposition algorithm and sample entropy, and the method comprises the steps: obtaining minute-level wind speed data of a construction point at different construction heights; according to the method, multi-layer minute-level wind speed historical observation data of a vertical gradient observation tower or minute-level wind speed historical observation data of an automatic meteorological station close to a construction point location are utilized, noise reduction is carried out on original wind speed data through an ICEEDMAN decomposition algorithm, high-frequency noise components are removed, and a wind speed sequence after noise reduction is generated; a wavelet packet decomposition algorithm is applied to the de-noised wind speed sequence for multiple times of decomposition, the complexity of each wind speed component is judged through sample entropy calculation to determine the number of decomposition layers, and a suitable wind speed component and a model are selected for modeling, so that a short temporary wind speed extrapolation model construction module is constructed; and generating a minute-level wind speed short-critical extrapolation result of the construction height in the future one hour. The method can effectively improve the extrapolation precision of the short temporary wind speed.

The invention relates to an ultra-short-term photovoltaic power generation power prediction method based on secondary decomposition and BiGRU, and the method comprises the following steps: S1, carrying out the primary decomposition of an original signal based on CEEMDAN, and obtaining a plurality of components with different complexities; s2, calculating an entropy value of each component by using a sample entropy, and reconstructing a signal by using a K-means clustering algorithm; s3, carrying out secondary decomposition on the complex signal by adopting VMD, and taking the decomposed signal as input; s4, carrying out normalization processing on each component, respectively carrying out modeling prediction, and carrying out linear summation to form a prediction result of Clu-IMF0; s5, evaluating a prediction result of the model; according to the method, in the process of processing time series data by the multi-layer stacked BiGRU neural network, rules and features in the data can be well mined; the complexity of original data is greatly reduced through data processing; the method improves the prediction precision of the photovoltaic power, and has a good application prospect in solving the problem of power prediction of a photovoltaic power station with less data.

The invention provides a monitoring method and system based on intrinsic multi-scale sample entropy. The monitoring method comprises the following steps: acquiring original data; preprocessing the data to obtain a data time sequence to be analyzed; a step of applying the EEMD to the data time sequence and decomposing the data time sequence into E-IMFs; and an iMSE calculation step, wherein a plurality of iMSEs are obtained. At least a portion of the plurality of iMSEs is used as an output of the monitoring method.

The invention discloses a distribution hidden danger assessment and prediction method based on a natural time domain and a fuzzy rough set, and belongs to the technical field of operation and maintenance of power grid equipment. According to the method, based on collected multi-source monitoring signals of leakage current, induction current, temperature and the like, adaptive signal preprocessing is carried out by adopting a method of combining empirical mode decomposition (EMD) and sample entropy, effective mode components are effectively extracted, and noise interference is suppressed; natural time domain analysis is introduced on the basis of a traditional time domain, an event sequence is constructed, dynamic features are extracted, and a hidden danger feature data set with time sequence evolution information is formed; further performing unsupervised attribute reduction on the high-dimensional features by using a fuzzy rough set theory, removing redundant information, and retaining key discrimination features; and finally, identification and trend prediction of wiring hidden danger types are realized through a support vector machine (SVM) classifier. According to the method, the accuracy and robustness of hidden danger identification are improved, and effective technical support is provided for intelligent operation and maintenance of power distribution.

The invention provides a sea wave height prediction method and system based on hybrid quadratic decomposition, and relates to the technical field of sea wave height prediction, and the method comprises the steps: obtaining to-be-predicted original wave height data; performing primary decomposition on the original wave height data to obtain an intrinsic mode function and a residual term; calculating a sample entropy of the intrinsic mode function; according to the size of the sample entropy, classifying the intrinsic mode function to obtain a reconstructed mode component; performing secondary decomposition on the high-frequency components through a VMD algorithm to generate sub-sequence components; establishing a periodic sensing time deep learning model; and inputting the subsequence component, the intermediate-frequency component and the low-frequency component into a periodic sensing time deep learning model, and outputting a sea wave height prediction result.

The invention discloses a fatigue electroencephalogram feature extraction method based on a wavelet packet and sample entropy. The fatigue electroencephalogram feature extraction method comprises the following steps: firstly, carrying out wavelet packet transformation on a preprocessed electroencephalogram signal; signals of different frequency bands are obtained, and local time-frequency characteristics are obtained; frequency band energy of the four basic rhythms after wavelet packet decomposition is calculated, and relative energy values and energy ratio characteristics of the frequency band energy are determined; the sample entropy of the electroencephalogram signals is calculated, and the complexity of the electroencephalogram signals is quantified; combining the rhythm relative energy value, the energy ratio feature and the sample entropy into a comprehensive feature vector, and verifying the generalization ability of the model by using methods such as cross validation; and inputting the constructed feature vectors into a support vector machine for classification, and verifying the feature extraction performance and the fatigue state recognition accuracy of the cross fusion algorithm. According to the method, the precision and the resolution of signal analysis are improved, and the distinguishing capability and the classification performance of the features are enhanced, so that remarkable advantages are brought to electroencephalogram signal classification and fatigue detection application.

The invention discloses a public opinion popularity anomaly detection method and system based on information denoising and clustering, and the method comprises the steps: obtaining a to-be-detected public opinion data set, and obtaining a target data set after denoising; the average power, the sample entropy and the standard deviation of the target data set are calculated to serve as feature information, clustering is conducted on elements in the target data set according to the feature information, and the class with the small number of elements serves as a first abnormal data set; according to a preset time window length and a time window moving step length, sequentially intercepting and sorting data from the initial position of the target data set to obtain a process data set, inputting the process data set into the auto-encoder, and extracting elements with deviation of an input signal and an output signal exceeding a limit to construct a second abnormal data set; and inputting the first abnormal data set and the second abnormal data set into a public opinion popularity anomaly detection model to obtain an anomaly classification result of the to-be-detected public opinion data. The method can adapt to complex scenes and has efficient processing capacity, and the performance of public opinion popularity anomaly detection is remarkably improved.

The invention discloses an intelligent bearing health monitoring method based on MSE-SPP-KAResnet, and relates to the technical field of bearing health monitoring. Through a spatial pyramid pooling layer, a KA optimization strategy and a multi-scale sample entropy module, the precision problem of a traditional fault diagnosis method under a multi-channel and unbalanced data set is effectively solved; compared with the prior art, the method has the advantages that pooling processing and feature fusion are carried out on multi-channel features under three spatial scales of global, medium scale and local through the spatial pyramid pooling layer, and the feature extraction capability of multi-channel heterogeneous data is improved; a KA optimization residual module is utilized to enhance the gradient flow and nonlinear mapping capability, and the recognition precision of minority class samples is effectively improved; the introduced multi-scale sample entropy module improves the robustness of signal complexity and uncertainty, and finally ensures the high efficiency and accuracy of bearing fault diagnosis in an unbalanced data environment.

The invention provides a method for predicting the concentration of gas dissolved in transformer oil based on mixed decomposition and Bi TCN-Bi GRU, and is applied to the field of prediction of the concentration of gas dissolved in oil. The method comprises the following steps: firstly, carrying out preliminary decomposition on a gas concentration sequence by utilizing improved self-adaptive noise complete set empirical mode decomposition; secondly, reconstructing a sub-sequence in combination with a sample entropy, and performing secondary decomposition on a high-entropy sub-sequence by using variational mode decomposition; and finally, constructing a Bi TCN-B GRU prediction model, simultaneously capturing forward and reverse features of time series data by using bidirectional convolution and a bidirectional gating mechanism, predicting subsequences of primary decomposition and secondary decomposition, and reconstructing a gas concentration sequence. Compared with the prior art, the method is higher in prediction precision and better in robustness and generalization.

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.