661 results about "Modal decomposition" patented technology

A system and method are disclosed for generating hyperspectral images from multi-modal sensor data including RGB, LiDAR, thermal, and near-infrared inputs. Training data includes hyperspectral images and corresponding multi-modal measurements. Spectral band grouping is performed based on correlation coefficients. A multi-modal decomposition network with cross-modal attention mechanisms generate reconstructed hyperspectral images by fusing complementary sensor information. A fine-tuning network creates reconstructed RGB images. A comprehensive quality assurance system analyzes spectral consistency, cross-modal coherence, and fusion artifacts to generate quality metrics. Missing data compensation strategies handle corrupted sensor inputs using information from other modalities. The system includes temporal integration for video sequences and multi-resolution processing for different sensor resolutions. Quality metrics guide network weight adjustments to improve reconstruction accuracy while maintaining robustness to sensor failures and environmental variations.

The invention discloses a harbor shore power system oscillation damping suppression method based on heuristic probability optimization. According to the method, sliding window preprocessing is carried out on an alternating current bus side current time domain oscillation signal, modal decomposition is carried out based on a Prony algorithm, and modal energy is calculated to judge an oscillation mode; the discriminated oscillation modes are aggregated and mapped into equivalent circuit elements, a corresponding three-order circuit state matrix is constructed, and the damping ratio of each mode is determined according to the characteristic value of the matrix; taking a damping ratio as an evaluation index, introducing an influence factor to construct a multi-objective optimization function, parameterizing the parallel adjustable impedance, and limiting an adjustable range; and searching the control parameters by adopting a heuristic probability optimization strategy to obtain final damping control parameters, and downloading the final damping control parameters to the parallel adjustable impedance device to realize online dynamic adjustment. According to the method, multi-modal identification, physical magnitude mapping and online adaptive optimization can be realized, and the suppression capability and the operation stability of the shore power system on sub / super synchronous oscillation are improved.

The invention relates to the technical field of wind power equipment monitoring, and discloses a wind power gear box intelligent fault early warning method and system based on machine learning. The method comprises the steps that multi-source monitoring data such as vibration signals, temperature data and oil analysis data of the wind power gear box are acquired, and multi-scale operation characteristics are extracted through time-frequency conjoint analysis; key fault sensitive features are determined through an adaptive feature selection algorithm, and a dynamic fault feature weight matrix is constructed in combination with a historical fault case library; multi-modal data fusion is adopted to generate an enhanced fault feature set, and modal decomposition is carried out on the enhanced fault feature set to obtain a trend component and a fluctuation component; a fault evolution feature space is constructed by using a deep neural network based on two components, then a fault development mode is identified by using a time sequence mode matching algorithm, and finally a graded early warning signal is generated according to a matching degree with a preset mode, so that fault features can be comprehensively captured, and safe operation of a wind power gear box is ensured.

The invention provides a joint denoising method and system based on adaptive large neighborhood search and modal decomposition, and belongs to the technical field of signal processing and nondestructive detection.The method comprises the steps that an ultrasonic signal and a vibration signal of a detected insulator are synchronously collected and preprocessed; dynamically estimating the noise level based on the preprocessed ultrasonic signal power spectral density, and optimizing decomposition parameters by adopting an adaptive large neighborhood search algorithm; on the basis of the optimized decomposition parameters, wavelet packet decomposition and ensemble empirical mode decomposition are executed in parallel, and effective intrinsic mode function components are screened through cross-correlation verification; extracting the resonance frequency of the preprocessed vibration signal, performing target frequency band weighted enhancement on the low-frequency sub-band, and dynamically adjusting the threshold parameter of the high-frequency sub-band and the low-frequency sub-band according to the resonance frequency; and generating a preliminary de-noised signal from the fused signal, performing affine projection algorithm filtering and multi-modal cross validation, and outputting the verified ultrasonic signal as a final de-noising result.

The invention belongs to the technical field of radar signal processing and target identification, and particularly relates to a maritime hybrid target identification method and system based on modal decomposition and reconstruction, and the method comprises the steps: carrying out the variational modal decomposition of a radar echo signal of a maritime hybrid target, and decomposing an original signal into a plurality of intrinsic modal signals; estimating a background noise energy reference and removing noise modals based on the decomposed modal signals, clustering the remaining modals according to the center frequency, and combining the modals with the frequency within the center frequency range into an independent single-target signal which is of the same target and is reconstructed into an independent single-target signal; respectively carrying out time-frequency analysis on each reconstructed single target signal to obtain a corresponding time-frequency diagram, and extracting time-frequency domain features from the time-frequency diagram; and inputting the extracted features into a trained support vector machine classifier to realize automatic identification of the ship target and the floating target. A ship target and a floating target can be distinguished more accurately in a mixture scene, and the stability of tracking identification is improved.

The invention discloses a primary equipment state monitoring method and system in a new energy power system, and the method comprises the following steps: deploying a multi-mode sensor array on primary equipment, and synchronously collecting a voltage signal, a current signal, a temperature signal, a vibration signal and an environment parameter; inputting the collected data into an edge computing node for preprocessing to obtain a multi-modal signal sequence; variational mode decomposition is carried out to form a multi-dimensional feature vector; inputting a long-short-term memory neural network model containing an attention mechanism, performing training and reasoning by using an AdamW optimizer and a cosine annealing learning rate strategy, and outputting the health degree of equipment; determining the weight of each monitoring index based on an analytic hierarchy process, and dividing the equipment into a plurality of state grades; the fault probability is obtained through fuzzy Petri net reasoning, and a corresponding early warning mechanism is triggered according to a preset threshold value. According to the invention, through multi-dimensional data fusion and intelligent analysis, the accuracy and real-time performance of state monitoring are significantly improved.

The invention provides a high-voltage circuit breaker voiceprint denoising method based on data enhancement and a storage medium, and the method comprises the steps: processing a collected original voiceprint data sequence, extracting stable and effective Mel-frequency cepstrum coefficient features, and constructing a two-dimensional feature matrix; a parallel mixed data enhancement strategy is adopted to generate a positive sample pair, and an encoder is trained in combination with a contrast learning mechanism, so that the representation robustness of the model under different voiceprint change conditions is improved. The method comprises the following steps: decomposing an original signal containing noise fringes into a plurality of modal components by using variational modal decomposition, extracting low-frequency effective components, introducing Gaussian white noise, constructing a corrosion target signal as a decoder training target, learning through a denoising automatic encoder, and finally outputting a denoised voiceprint feature signal. The method has the advantages of high robustness, high noise suppression capability, excellent feature expression capability and the like, is suitable for the field of online monitoring and intelligent diagnosis of the state of high-voltage circuit breaker equipment, and has good application prospect and engineering value.

The invention belongs to the technical field of radar signal processing, and discloses a sea surface small target detection method based on optimized characteristic mode decomposition, which comprises the following steps: S1, acquiring to-be-detected signal data; s2, decomposing an original signal into a plurality of modal components by using FMD, and selecting an envelope spectrum entropy as a fitness function; s3, performing global optimization on the fitness function in the FMD by using an SOS algorithm; s4, introducing a PSO algorithm to carry out local optimization on key parameters of the FMD; s5, components with low envelope spectrum entropy values and correlation coefficients larger than a threshold value are reserved; s6, extracting an envelope spectrum entropy and frequency band energy ratio feature from the screened modal components, introducing a Gini coefficient as a weighting factor, and constructing a GSEBE joint feature; and S7, inputting the entropy value of the envelope spectrum into a DELM classifier with a controllable false alarm, and realizing target detection based on comparison between a predicted value and a judgment threshold. According to the invention, the capability of distinguishing sea clutters and target echoes is enhanced, and more accurate classification detection is realized.

The invention relates to the technical field of power quality monitoring, and discloses a method for identifying power quality disturbance characteristics of a distributed photovoltaic interference power supply, which comprises the following steps: S1, data acquisition and preprocessing: acquiring a power quality signal of a photovoltaic system and carrying out denoising, normalization and time alignment; and S2, carrying out disturbance signal adaptive decomposition based on improved variational mode decomposition, and automatically selecting a mode number by utilizing information geometric optimization. An improved variational mode decomposition method is adopted, information geometric optimization and Bayesian optimization are combined, self-adaptive mode decomposition of disturbance signals is achieved, the optimal mode number and penalty factors can be automatically determined through improved variational mode decomposition, decomposition errors caused by manual parameter setting in traditional variational mode decomposition are avoided, and the method is suitable for large-scale popularization and application. Compared with a fixed parameter variational mode decomposition method in the prior art, the method has the advantages that the analysis capability of complex disturbance signals is improved, and the disturbance mode in the photovoltaic system is accurately decomposed.

The invention discloses a high-reliability planetary gearbox signal denoising method, system, medium and equipment, and the method comprises the steps: obtaining original vibration signals of a nuclear power circulating pump planetary gearbox in different health states, and carrying out the detrending and demean preprocessing of the signals; performing modal decomposition on the original vibration signal by adopting an empirical mode decomposition (EMD) algorithm, an ensemble empirical mode decomposition (EEMD) algorithm and a variational mode decomposition (VMD) algorithm to obtain a plurality of different modal components; iteratively optimizing a hyper-parameter value in the variational mode decomposition algorithm VMD by adopting a sparrow search algorithm SSA so as to realize the self-adaptive decomposition of the variational mode decomposition algorithm VMD on the signal; and carrying out modal decomposition on the gearbox vibration signal by adopting a variational modal decomposition algorithm VMD after iterative optimization, removing noise components in modal components, and reconstructing the signal to realize gearbox vibration signal denoising.

The invention discloses an ultrasonic guided wave signal noise reduction method based on HHO-SVMD and singular spectrum analysis, and the method comprises the steps: obtaining a to-be-processed ultrasonic guided wave signal, optimizing a penalty factor of variation mode decomposition (SVMD) through employing an improved Harris eagle algorithm, initializing a population through Circle chaotic mapping, introducing chaotic disturbance and weight, and carrying out the noise reduction of the to-be-processed ultrasonic guided wave signal. Determining an optimal alpha value and decomposing the signal into an optimal modal component; calculating a kurtosis value of each modal component, and screening effective components containing damage information according to a threshold value; singular spectrum analysis denoising is carried out on the effective components, and a self-adaptive window mechanism is introduced to dynamically adjust the window length and the truncation strength; reconstructing the de-noised effective component to obtain a de-noised signal; according to the method, the parameter optimization precision and efficiency are improved, damage characteristics and noise are effectively separated, different dominant frequency signals are adapted, the damage characteristics can still be reserved in a low-signal-to-noise-ratio environment, the noise reduction effect of ultrasonic guided wave signals and the damage detection reliability are improved, and the method is suitable for nondestructive detection of components such as ultra-long small-diameter heat absorption pipes.

The invention belongs to the technical field of vibration analysis and testing of bearings, and particularly relates to a cam driven bearing wear degree monitoring method and system, and the method comprises the steps: carrying out the equal-angle resampling processing of a vibration signal through a rotating speed signal, decomposing an obtained angular domain vibration signal into a plurality of mode components through a variational mode decomposition algorithm, and carrying out the measurement of the vibration signal; according to the kurtosis value of each modal component and the correlation coefficient of each modal component and the original vibration signal, evaluating the impact saliency weight of each modal component, and performing weighted summation on the energy of each modal component to obtain comprehensive impact energy; calculating to obtain a speed decoupling wear index without the influence of the rotating speed by utilizing the comprehensive impact energy and the vibration energy calculated by the physical mapping model; and the speed decoupling wear index is compared with a preset self-adaptive alarm threshold value, and the wear state of the cam driven bearing is judged according to a comparison result. According to the invention, the problems of false alarm and missing alarm under the variable-speed working condition are solved.

The invention discloses a distribution network fault positioning method, system and device based on variational mode decomposition and a medium, and relates to the technical field of power system fault positioning, and the method comprises the steps: collecting a traveling wave signal of a power distribution network, and carrying out the preprocessing of the collected traveling wave signal; performing modal decomposition on the preprocessed traveling wave signal, and outputting a plurality of modal components; based on the mode component obtained through decomposition, wave head arrival time is extracted; performing correction compensation based on the wave head arrival time difference, the phase difference and the propagation characteristics, and calculating the relative distance between the fault point and the known node; calculating the position coordinates of the fault point in the distribution network according to the geographic coordinates and the direction vectors of the nodes in combination with the relative distance; and constructing a visual interface, displaying the position of a fault point, and storing the traveling wave signal data and a fault positioning result into a database. According to the method, the adaptive correction function and the time difference compensation model are constructed, so that time difference errors caused by factors such as frequency change and phase nonlinearity can be corrected, and the accuracy of fault positioning is improved.

The invention provides a prediction method for a sudden change type signal of gas dissolved in oil. The prediction method comprises the following steps: firstly, acquiring a time sequence signal of transformer gas monitoring; processing the time sequence signal according to a variational mode decomposition algorithm to obtain a plurality of mode components; according to the variational mode decomposition algorithm, the sum of confusion entropies of all mode components is used as an objective function of parameter optimization; and finally, according to a pre-established prediction model, performing prediction and superposition reconstruction on each modal component to obtain a prediction result of the abrupt change type signal of the gas dissolved in oil. According to the method, the VMD decomposition architecture optimized by the frost ice algorithm is introduced, the non-stationarity of the signal is quantified and obviously reduced through the chaos entropy index, higher prediction precision and robustness of the gas signal in the mutation type oil are realized, and the method has obvious innovativeness and superiority in the field of transformer fault trend prediction.

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 rainstorm torrential flood disaster-causing element prediction method and system based on modal decomposition and deep learning, and solves the problems that a traditional model is insufficient in non-linear time sequence feature capture, and a physical model depends on complex data and is weak in generalization ability. Comprising the steps of collecting flow, flow velocity and water level data of an upstream site as input, and taking downstream disaster point data as output; preprocessing the data; a frost ice optimization algorithm is adopted to optimize variational mode decomposition parameters; a Fourier transform high and low frequency feature enhanced attention network is constructed, low-frequency and high-frequency components are divided, trend features are extracted through a fluctuation enhancement module, dynamic changes are captured through a multi-path difference calculation unit, self-perception attention is introduced to achieve feature weighted fusion and long-term memory, and a downstream hydrological state prediction result is output. By optimizing a modal decomposition and deep learning cooperation mechanism, the precision, robustness and generalization ability of sudden mountain torrent prediction are significantly improved, and the method is suitable for disaster emergency management in complex scenes of small and medium watersheds.

A lithium battery life prediction method based on modal decomposition and Informer-LSTM belongs to the field of battery life prediction, and adopts a CEEMDAN method to decompose a battery capacity data sequence into a plurality of intrinsic modal components serving as high-frequency components and a residual component serving as a low-frequency component, so as to reduce the influence caused by the irregular recovery phenomenon of the battery capacity; inputting the low-frequency component into the LSTM network model to obtain a low-frequency component prediction result; a high-frequency component is secondarily decomposed into a trend term and a residual term by adopting a Dlinear method, and the fluctuation degree of the high-frequency component is reduced while key information is reserved, so that the prediction stability is improved. Respectively inputting a trend term and a residual term decomposed by each high-frequency component into an Informer network model for prediction, then superposing results, extracting implicit features in the complex fluctuation data, and obtaining a prediction result of the high-frequency component; and carrying out weighted fusion on the low-frequency component prediction result and the prediction results of the plurality of high-frequency components to obtain a final prediction result.

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 photovoltaic inverter operation state diagnosis method, which belongs to the technical field of photovoltaic inverters, and comprises the following steps: collecting multi-source operation signals of a photovoltaic inverter, carrying out wavelet packet decomposition on the signals to construct a time-frequency characteristic dense matrix, generating a fault characteristic super-sparse representation vector through singular value decomposition and sparse processing, and carrying out fault characteristic super-sparse representation on the fault characteristic super-sparse representation vector. Performing envelope demodulation on sensitive mode components obtained by complete set empirical mode decomposition to extract approaching periodic feature vectors, and inputting three types of complementary features into a weak fault recognition model with a circulation attention mechanism to perform fusion diagnosis. And whether preventive maintenance early warning is triggered or not is judged according to the output determinant characteristic value of the convergence state matrix, and an operation strategy is adjusted. The technical problem that early weak fault characteristics of the photovoltaic inverter are difficult to be accurately identified and early warned in time in a strong noise background is solved.

The invention relates to a multi-modal fusion pipeline damage positioning method, which comprises the following steps of: uniformly arranging piezoelectric transducer arrays along the circumferential direction of a pipeline, generating non-frequency dispersion L (0, 2) and T (0, 1) guided waves respectively excited by 70kHz sine pulses as excitation signals, and unidirectionally spreading the excitation signals along the pipeline; the method comprises the following steps: acquiring reflection echoes at a to-be-measured section of a pipeline, and performing matched filtering, omega-k domain filtering and circumferential modal decomposition on the reflection echoes to obtain two modal components in an L (0, 2) mode and a T (0, 1) mode; performing back propagation and focusing imaging on each modal component to obtain imaging results under two modals L (0, 2) and T (0, 1); and fusing the imaging results in the two modals to obtain a multi-modal fusion pipeline damage image. Compared with the prior art, the method has the advantages that the problem that sensitivity of different defect types is difficult to consider due to single-mode optimization and the problems of signal waveform distortion and energy dispersion existing in multi-mode signals are solved.

The invention discloses a bearing electrostatic signal noise reduction method based on VMD-OMP. In order to solve the problem that early fault features are difficult to extract due to the fact that bearing electrostatic signals are easily affected by power frequency interference and environmental noise, a noise reduction technology based on combination of VMD (variational mode decomposition) and OMP (orthogonal matching pursuit) is provided. The method comprises the following steps of: firstly, performing automatic optimization on a modal number and a secondary penalty factor of VMD decomposition by taking an envelope entropy as a fitness function through a grey wolf optimization algorithm to realize adaptive decomposition; and then, screening effective modal components according to the cross correlation coefficient and the kurtosis, determining the optimal sparseness by adopting a saturation value method, respectively reconstructing the components through an OMP algorithm, and finally, directly adding reconstructed signals to obtain a noise reduction result. According to the method, power frequency noise and broadband interference in the bearing electrostatic signal can be effectively suppressed, and the feature definition and the fault recognition capability of the electrostatic signal are improved.

The invention discloses a fault detection method and system for a virtual power plant micro-grid. The method comprises the following steps: step 1, acquiring three-phase voltage and current historical data of a power grid bus as an input signal; 2, decomposing the input signal into a plurality of modes by adopting a variational mode decomposition method; step 3, calculating energy of each mode and a correlation coefficient between each mode and the input signal, establishing a phase asymmetry index and a disturbance frequency index, and calculating a weighted sum of the energy of each mode and the correlation coefficient, a weighted sum of the phase asymmetry index and the correlation coefficient, and a weighted sum of the disturbance frequency index and the correlation coefficient; forming a training feature vector; 4, training a fault detection model by using the training feature vector; according to the real-time data of the three-phase voltage and the three-phase current of the power grid bus, feature vectors are obtained according to the steps 1-3; outputting a fault probability according to the feature vector and the fault detection model, and if the fault probability is greater than a set threshold, determining that a fault exists; the method has the advantages of fault sensitivity, high robustness and the like.

The invention discloses an electric power system multi-source forced oscillation positioning method based on a graph attention network and variational mode decomposition. The method comprises the following steps: acquiring power grid topology data of a target electric power system and attribute data of each node; inputting the power grid topology data and the attribute data of each node into a pre-trained target network model, wherein the topology perception space decoupling network processes the power grid topology data and the attribute data of each node and outputs the energy contribution degree of each node; the frequency domain time decoupling network processes the attribute data of each node and the corresponding energy contribution degree and outputs a synchronous machine component and a fan component; and the physical constraint oscillation classification network processes the synchronous machine component and the fan component and outputs a multi-source forced oscillation positioning result. According to the invention, the modeling of the electrical connection relation between the power grid nodes is realized through the topology perception space decoupling network, and the decoupling of the synchronous machine and the fan component is realized through the frequency domain time decoupling network, so that the precision of oscillation source space positioning is improved.

The invention relates to the technical field of renewable energy power generation, and provides a photovoltaic power prediction method, device and equipment, and the method comprises the steps: obtaining historical power data and meteorological factor data of a target photovoltaic power station, and carrying out the preprocessing; dividing the historical days into different meteorological categories by adopting a clustering algorithm, and constructing a training set corresponding to the meteorological categories; performing correlation analysis on each training set to obtain core meteorological features and form a core feature sequence, and performing parallel decomposition on the core feature sequence by adopting three modal decomposition algorithms to form an enhanced feature set; constructing a double-flow neural network model, and taking the enhanced feature set as the input of the double-flow neural network model to obtain an optimized feature vector; and inputting the optimized feature vector into at least one full connection layer to obtain a final short-term photovoltaic power prediction value. According to the method, the prediction task is simplified, and the prediction accuracy and stability of the short-term photovoltaic power are remarkably improved in combination with the double-current neural network model.

The embodiment of the invention provides a fault identification method of a shield tunneling machine, electronic equipment, a storage medium and a program product. The method comprises the steps that a vibration signal of a bearing of the shield tunneling machine is obtained, iterative calculation is conducted on the vibration signal through a preset mantis shrimp algorithm, a signal decomposition parameter corresponding to the vibration signal is obtained, and the preset mantis shrimp algorithm at least comprises the parameter range of the preset signal decomposition parameter; decomposing the vibration signal according to a modal decomposition number and a filter length carried in the signal decomposition parameter to obtain a target modal component containing fault information; and determining an envelope spectrum corresponding to the target component, and determining the fault type of the shield tunneling machine according to the fault frequency in the envelope spectrum. The method is used for achieving the effect of determining the fault type of the shield tunneling machine.

The invention relates to a bridge structure modal parameter identification method, which is based on a bridge structure tiny vibration video acquired by a camera. VMD (variational mode decomposition), PBVM (phase-based video motion amplification), Gabor filtering-based phase extraction method GBP (Gabor filtering), an improved clustering algorithm ICA (independent clustering algorithm) and an integrated covariance-driven random subspace recognition (SSI-Cov) and FDD (frequency domain decomposition) algorithm are fused to construct a set of complete non-contact structural modal parameter recognition system. According to the method, effective decoupling of multiple vibration modes of a bridge structure, frequency domain feature extraction of small-amplitude vibration and intelligent and automatic modal parameter extraction are achieved under the conditions that the target frequency bandwidth does not need to be known in advance, environmental noise interference exists and no obvious feature target exists, and the method belongs to the technical field of bridge structure health monitoring.

The invention relates to the technical field of energy management and prediction, discloses a new energy base power supply capacity calculation method based on high-frequency weather forecast, and aims to solve the problem of insufficient prediction precision and robustness when an existing new energy power generation power prediction model processes high-frequency nonlinear meteorological data. The calculation method comprises the following steps: constructing a meteorological physical causal knowledge graph; carrying out physical constraint guided multi-scale modal decomposition based on the atlas; building a hierarchical predictor network to predict photovoltaic power; and establishing a closed-loop feedback loop of prediction error attribution and model self-calibration. By adopting the above technical scheme, the method can solve the defects of traditional decomposition, improve the effectiveness, prediction accuracy and interpretability of feature engineering, achieve the adaptive optimization of the model, and maintain the high-precision and high-robustness power supply capability calculation performance.

The invention provides a power load prediction method and system based on adaptive modal decomposition, and the method comprises the steps: obtaining an original load sequence and a multi-modal data set based on time sequence distribution, and the multi-modal data set comprises meteorological data, equipment state data, and economic and social activity data; copying the original load sequence into a plurality of copies, and adding adaptive white noise to each original load sequence to obtain a plurality of noise-added sequences; performing modal decomposition, component screening and modal reconstruction on each noise adding sequence, and performing superposition to obtain a de-noising load sequence; performing feature screening based on causal driving on the de-noising load sequence and the multi-modal data set to obtain a feature vector; and inputting the feature vector into a preset load prediction model, so that the load prediction model outputs a corresponding load prediction result based on an attention mechanism and a preset physical rule constraint, and the accuracy of power load prediction in a complex scene is improved.

The invention discloses a giant magnetostrictive bar health state evaluation method considering subharmonic content, which comprises the following steps of: firstly, obtaining output displacement data of a giant magnetostrictive bar through a built giant magnetostrictive bar test platform; in order to select the filter length and the mode decomposition number of the characteristic mode decomposition method, combining with the Shannon entropy coefficient, taking the square envelope spectrum kurtosis as a weight, constructing a weighted square envelope spectrum kurtosis Shannon entropy coefficient objective function, and performing parameter optimization by using a Harris eagle optimization algorithm; according to the method, the principle of maximum square envelope spectrum kurtosis is taken as a principle to select a main mode component, finally, envelope spectrum analysis is carried out, the health state of the giant magnetostrictive bar is evaluated by counting the sub-harmonic content in the envelope spectrum, and the method plays a guiding role in development and application of a giant magnetostrictive transducer. And the service life of the subsequent transducer can be detected and evaluated.

The invention relates to a bearing fault diagnosis method based on variational mode decomposition and time sequence partitioning cross attention fusion, which comprises the following steps: acquiring an original vibration acceleration signal of a rolling bearing, and constructing a standardized original data set; segmenting the standardized original data into a plurality of data blocks, and generating a time domain embedding feature; based on the time domain embedded features, extracting high-order global time domain features by using a multi-head self-attention mechanism, residual connection and a feedforward neural network; decomposing the standardized original data into a plurality of intrinsic mode functions, and extracting frequency domain distribution features through a convolutional neural network; taking the frequency domain distribution characteristics as query vectors, retrieving and matching related fault context information in the global time sequence characteristics, realizing weighted fusion of time-frequency modes, inputting fused fault representation vectors into a classifier, and calculating a result of a bearing health state; and constructing a loss function containing label smoothing and a dynamic learning rate scheduling strategy, and carrying out iterative optimization on model parameters until the model converges.