389 results about "Modal decomposition" patented technology

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 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 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 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 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.

The invention relates to the technical field of forging heat treatment, and discloses a forging quenching and tempering method based on intelligent temperature control. The method comprises the following steps: acquiring a real-time temperature time sequence and a temperature distribution characteristic during heat treatment of a forge piece, and executing multi-scale signal decomposition through an optimal signal decomposition primary function and a decomposition depth hierarchy to obtain a multi-scale temperature signal component; and calculating a complexity metric value of the decomposition coefficient to extract randomness characteristics, and screening out a key temperature region coefficient which is most relevant to the structure evolution of the forge piece. The optimal temperature control frequency parameter is determined by combining the material phase change baseline characteristic, the current heat treatment stage state and the randomness characteristic, a temperature field evolution characteristic sequence is reconstructed and is modally decomposed into a slow change component and an accelerated change component, accordingly, the hardening and tempering state type is recognized, a temperature control strategy library is matched to generate a control instruction, and accurate and efficient forging hardening and tempering treatment is achieved. The method solves the problem of lagging structure performance regulation in traditional heat treatment, and improves the stability and consistency of the comprehensive performance of the forge piece.

The invention discloses an ultrasonic image denoising method based on variational mode decomposition and local space sparse fusion, which comprises the following steps of: firstly, adaptively optimizing key parameters of variational mode decomposition by using a grey wolf optimization algorithm to realize stable and efficient decomposition of an ultrasonic image; then, classifying the modal components according to the structural features of the modal components, and implementing differentiated denoising strategies for different types of modals to separate noise and reserve useful information; after modal reconstruction, a sparse expression method based on local space information is further introduced, according to the method, accurate boundary detection is carried out through gradient vector flow and gray scale proportion analysis, self-adaptive partitioning is carried out on an image according to boundary information, and finally sparse reconstruction is carried out through double dictionaries trained for different areas. According to the method, speckle noise in the ultrasonic image can be effectively suppressed, and meanwhile, the capability of keeping the edge and detail information of a tissue structure is remarkably improved, so that the ultrasonic image with higher quality is obtained.

The invention provides a vibration nonlinear signal energy analysis method and system based on variational mode decomposition, and relates to the technical field of signal processing, and the method comprises the following steps: obtaining a monitoring signal of a vibratory roller, determining a corresponding state based on root-mean-square data of the monitoring signal, and determining the state of the monitoring signal; performing segmentation processing on the monitoring signal based on the state corresponding to the monitoring signal to obtain a signal segmentation result; performing variational mode decomposition processing on the signal segmentation result to obtain at least two second mode components; performing Hilbert transformation processing on the second modal component, and combining the instantaneous frequency and the instantaneous amplitude of each modal component obtained through transformation to obtain frequency spectrum information of the monitoring signal; and performing marginal spectrum calculation and integration on the frequency spectrum information to obtain the total energy of the monitoring signal. According to the method, interference signals can be efficiently identified and eliminated in the vibration signals, so that the precision and robustness of compaction quality evaluation are improved.

The invention discloses an adaptive signal decomposition and denoising method, device and system, and a storage medium. The method comprises the following steps: acquiring an original signal; carrying out global optimization on key parameters of continuous variational mode decomposition (SVMD) by adopting an improved snake optimization algorithm ISO which introduces a dynamic bidirectional population evolution dynamics (DBPED) strategy, and carrying out accurate self-adaptive decomposition on an original signal; and for all the decomposed modal components IMFs, calculating correlation coefficients of all the decomposed modal components IMFs and an original signal, matching different adaptive wavelet denoising strategies for each component according to the magnitude of the correlation coefficients to carry out differencing and refining processing, and finally reconstructing all the processed components to realize deep denoising of the signal. By adopting the technical scheme of the invention, aiming at a time sequence signal under a non-stable and strong noise background, the signal and the noise are accurately separated through a self-adaptive decomposition means, and a high-quality signal with high fidelity and high signal-to-noise ratio is finally reconstructed.

The invention relates to the technical field of cable line operation and maintenance, in particular to a cable fault diagnosis method and system based on quantum optimization variational mode decomposition and multi-scale evaluation, and the method comprises the steps: employing a quantum genetic algorithm to optimize the modal number and penalty factor of variational mode decomposition through a multi-target fitness function; constructing a multi-scale evaluation system fusing time domain, frequency domain and wavelet domain features, and screening an optimal modal component; and carrying out multi-feature fusion wave head calibration on the optimal modal component to calibrate the arrival time of the wave head, and realizing accurate positioning of a fault point in combination with a double-end traveling wave method. According to the method, the ranging error can be effectively reduced under the conditions of high transition resistance and low signal-to-noise ratio, the robustness and engineering applicability of cable fault diagnosis are improved, and the problems of attenuation distortion of fault traveling wave signals and difficulty in wave head calibration under the conditions of strong noise and high transition resistance are solved.

The embodiment of the invention discloses a malignant load identification method, device and equipment, a medium and a program product, and relates to the technical field of power load monitoring. The method comprises the following steps: performing modal decomposition on an original power utilization sequential sequence to obtain a plurality of intrinsic mode components, and reconstructing intrinsic mode components which do not belong to noise components to obtain a target power utilization sequential sequence; performing feature extraction on the target power consumption time sequence to obtain target power consumption features, and inputting the target power consumption features into a pre-trained malignant load identification model for identification to obtain an identification result; the malignant load identification model is obtained by updating model parameters of a weak learner based on a natural gradient descent method and performing training optimization. The lightweight malignant load learning model obtained through training in the scheme can be deployed and operated on the intelligent electric meter, high-quality input features are obtained through multi-mode decomposition and reconstruction, the accuracy of malignant load recognition is improved, and accurate recognition of the malignant load based on the lightweight model is achieved.

The invention discloses an electric vehicle permanent magnet motor control method and system based on temperature rise prediction, and belongs to the field of motor control. The method comprises the following steps: generating motor temperature rise sample data based on a meshless method; a chaotic mapping-dream optimization algorithm is adopted to optimize multivariate variational mode decomposition parameters, and high-precision temperature rise data are reconstructed; a GNN-BILSTM-Attention prediction model is constructed, and a space-time double Attention mechanism is fused to predict a future temperature rise; and establishing a temperature rise-electromagnetic parameter mapping model, designing a graded early warning control strategy, and forming a prediction-control closed loop. According to the invention, the speed and precision of temperature rise prediction are improved, prediction-control deep coupling is realized, and the operation reliability and control precision of the motor are significantly enhanced.

The invention belongs to the technical field of lithium battery health management, and particularly relates to a lithium battery residual life prediction method based on self-adaptive modal number estimation and multi-scale decomposition, which comprises the following steps of: firstly, acquiring a capacity attenuation sequence of a battery, and then calculating the residual life of the battery through a variational modal decomposition method combining a self-adaptive modal number determination mechanism and Bayesian modal screening. Carrying out adaptive decomposition and denoising on the sequence, and separating a low-frequency trend mode and a medium-high frequency oscillation mode; according to the long-range dependence of the trend mode, a Transform model is adopted for prediction; and for the nonlinear fluctuation characteristics of the oscillation mode, a random forest model is adopted for prediction. And finally, fusing the prediction results of the two groups of components, reconstructing a complete future capacity attenuation curve, and calculating the remaining service life based on a preset failure threshold. According to the method, through adaptive decomposition and grouping modeling, the adaptability, noise immunity and prediction precision of the prediction model to different battery individuals and complex working conditions are effectively improved.

The invention discloses a mixed regular variational mode decomposition method, device and equipment suitable for an unsteady flow field of an aircraft and a storage medium, and relates to the technical field of flow analysis, and the method comprises the steps: determining a bandwidth estimation value and a frequency separation weight coefficient based on the unsteady flow field, an expected mode number, a spatial mode and a time evolution coefficient, constructing a first regular term and a second regular term, weighting to obtain a mixed regular term, introducing a flow field reconstruction term to establish a flow field modal decomposition variational optimization problem, converting the problem into a frequency domain optimization problem through Fourier transform, and simplifying the problem into a sub-convex optimization problem by adopting an alternating direction multiplier method; an analytic solution is obtained through a variational method and iteratively updated to obtain a flow field space mode, a time evolution coefficient frequency domain representation, a center frequency and a Lagrange multiplier, the time evolution coefficient is obtained through inverse Fourier transform, a mode decomposition result is obtained, and therefore high-precision mode separation of the unsteady flow field is achieved. And the calculation efficiency and the iteration convergence speed of the variational optimization problem are improved.

The invention provides a comprehensive energy system multi-element load prediction method based on double-layer decomposition and reconstruction and TECNFormer, and the method comprises the steps: obtaining standardized input data, meteorological factors and time characteristics, which are obtained through the preprocessing of a historical multi-energy load sequence of a comprehensive energy system, wherein the historical multi-energy load sequence comprises an electric load sequence, a cold load sequence and a heat load sequence; performing double-layer modal decomposition on the standardized input data, and classifying the standardized input data into different types of dynamic components; respectively inputting the dynamic components into a time sequence enhanced convolution module, and extracting multi-scale local features by combining multiple heterogeneous differential convolution operators with causal convolution; taking a TECNFormer composed of a time sequence enhanced convolution module and an improved long sequence prediction network as a unified shared feature extraction layer, combining the improved long sequence prediction network with a bidirectional long-short-term memory network and a sparse attention mechanism to capture long-range dependence and local details, and obtaining joint modeling features; on the basis of a hard shared network architecture, a multi-task branch is arranged at an output end, and electric, cold and heat load prediction results are synchronously output.

The invention belongs to the technical field of new energy microgrid group prediction and scheduling, and particularly relates to a large-scale distributed photovoltaic cluster-oriented output prediction method and system, and the method comprises the steps: collecting data, constructing a multi-source input data set, and carrying out the preprocessing of the multi-source input data set; applying an improved variational mode decomposition method to the power time sequence data of each photovoltaic power station to obtain a plurality of mode components and residual terms; modal-level feature extraction is carried out on each modal component; constructing a graph structure based on a geographical and meteorological relationship between the photovoltaic power stations, and extracting spatial embedding representation of nodes by using a graph neural network; based on the modal feature vector and the spatial embedding representation, constructing a time sequence prediction model and training to obtain a future prediction result of each modal; and fusing prediction results of all modes, outputting a final output prediction value and an uncertainty interval of the photovoltaic cluster, and meeting the requirements of operation of the micro-grid group and the power distribution network on short-term and medium-term prediction.

The invention discloses a flow field data modal decomposition method, device and equipment suitable for a non-stationary flow field of an aircraft, and a storage medium, and relates to the technical field of hydrodynamics, and the method comprises the steps: obtaining the spatial-temporal data of the non-stationary flow field of the aircraft, determining a physical representation form, and obtaining the spatial-temporal data of the non-stationary flow field of the aircraft; the method comprises the following steps of: decomposing a plurality of low-order dynamic process components consisting of spatial modals and time evolution coefficients by utilizing a frequency modulation technology, constructing a frequency modulation operator, converting the time evolution coefficient of each component into a narrowband frequency modulation component time sequence signal, and optimizing the narrowband signal bandwidth by taking minimization of the narrowband signal bandwidth as an optimization target; and constructing a to-be-solved variational optimization problem by combining the flow field reconstruction constraint and the frequency modulation structure constraint. According to the method, a time evolution coefficient, an instantaneous frequency, an instantaneous amplitude and a spatial mode are obtained through iterative solution by adopting an alternating direction multiplier method, and a modal decomposition result is determined based on a solution result, so that adaptive extraction and dynamic characteristic description of the non-stationary flow field are realized, and the modal separation precision and the extraction efficiency of nonlinear and transient characteristics of the non-stationary flow field are improved.

The invention provides a wind power prediction method and system based on a multivariate combination prediction model and a medium, and relates to the technical field of machine learning, and the method comprises the steps: obtaining a historical wind power data time sequence and a historical numerical weather forecast data time sequence of a wind power plant; analyzing a nonlinear dependency relationship by using correlation, and optimally training a multi-modal parallel time sequence prediction model by using a variational mode decomposition algorithm in combination with a sliding window length; and based on the final sliding window length, constructing an input sample, inputting the input sample into a multi-mode parallel time sequence prediction model, outputting future prediction values of a plurality of intrinsic mode function components, and carrying out summation to obtain a wind power prediction result. According to the method and the device, the technical problem of insufficient wind power prediction precision caused by strong volatility and nonlinearity of a wind power sequence and limited learning ability of a single prediction model in the prior art can be solved, and the wind power prediction precision is improved by combining variational mode decomposition with a machine learning model for prediction.

The invention discloses a power load prediction method and device based on quadratic mode decomposition and double-model parallelism, and a medium, and the method comprises the steps: carrying out the fine decomposition of an original load sequence through a quadratic mode decomposition method, carrying out the denoising and reconstruction through combining with a wavelet threshold method, and finally obtaining a series of stable mode components; in a prediction stage, a parallel prediction architecture of the Informer and the BiLSTM is constructed, all modal components are synchronously input, global long-term dependence is captured by using a multi-head probability sparse self-attention mechanism of the Informer, and local short-term dynamic is captured by using the BiLSTM; and carrying out splicing and nonlinear fusion on the heterogeneous features extracted by the two to obtain a final prediction value. Compared with the prior art, cooperative capture and accurate prediction of the multi-scale features of the non-stationary power load sequence are realized through secondary decomposition from coarse to fine and a targeted double-model parallel architecture.

A generator fault identification method, device, product and medium relate to the technical field of generator fault category identification. The method comprises the following steps: acquiring a vibration signal and a noise signal; performing multi-mode decomposition processing on the vibration signal and the noise signal to obtain a first sub-mode component and a second sub-mode component; determining a vibration signal sequence based on each first sub-mode component and the vibration signal; determining a noise signal sequence based on each second sub-mode component and the noise signal; determining a vibration characteristic matrix based on the vibration signal sequence; determining a noise feature matrix based on the noise signal sequence; determining a first recognition result and a first confidence coefficient based on the vibration feature matrix; determining a second recognition result and a second confidence coefficient based on the noise feature matrix; when the identification results are inconsistent, determining a fault identification result according to the confidence coefficient; and when the identification results are consistent, determining the first identification result as a fault identification result. The method is advantaged in that generator fault identification accuracy is improved.

The invention discloses a wind power plant power prediction method based on a data modal adaptive large language model. The method comprises the following steps: a, data acquisition and preprocessing; b, performing EEVMD decomposition on the preprocessed wind power time sequence data; c, data modal self-adaptive adjustment and time embedding: mapping a continuous power value sequence into a discrete text modal sequence, and embedding a corresponding time information code into a conversion result; d, large language model prediction: inputting the converted discrete text modal sequence into a pre-trained large language model for wind power prediction, and generating a corresponding output text sequence prediction result; and e, mapping and outputting a result. According to the method, the advantages of a large language model in the aspects of text reasoning and knowledge understanding are brought into full play, the robustness and generalization ability of the model are effectively improved while the wind power plant power prediction cost is not increased by introducing a data modal adaptive conversion and energy entropy guided modal decomposition method, and high-precision prediction of the wind power is achieved.

The invention relates to the technical field of wind turbine generator fault early warning, and discloses a wind turbine generator fault early warning method and system based on multi-modal data fusion, and the method comprises the steps: collecting the data of a multi-modal sensor, and carrying out the time-space alignment preprocessing; multi-modal features are extracted through variational mode decomposition, STL decomposition and other methods, and cross-modal fusion is achieved through dimension adaptive projection and a multi-head attention mechanism; calculating a dynamic weight based on three factors of data quality, fault type correlation and information gain, and carrying out weighted fusion; constructing a dynamic unit topological graph, and capturing cross-unit association features by using a space-time diagram convolutional network; long-time early warning with confidence is realized through double-branch gating fusion in combination with a Bayesian neural network; a multi-label classification identification multi-fault mode is adopted, and an operation and maintenance decision is optimized through an adaptive large neighborhood search algorithm. According to the method, the long early warning window of the offshore wind turbine generator can be realized, and uncertainty quantification and intelligent operation and maintenance decision support are provided.

The invention discloses a offset output drift compensation method for a butterfly wing type MEMS resonant structure. The offset output drift compensation method comprises the steps that a compensation model composed of a variational mode decomposition module, a Transform encoder and a time convolution network is constructed; acquiring an original bias output signal, and performing variational mode decomposition, screening and reconstruction to obtain a bias output signal # 1; constructing a multi-dimensional feature sequence by using the observed quantities related to the multiple temperature changes and the calculated derivative features; on the basis of a Transform encoder, modeling is carried out with the multi-dimensional feature sequence as input and the bias output signal # 1 as a learning target, and a bias output signal # 2 is obtained; and based on the time convolutional network, modeling is carried out by taking the multi-dimensional feature sequence after dimension transposition as input and the bias output signal # 2 as a learning target, and a bias output signal # 3 is obtained and is output as a final compensation result. The method is applied to the field of MEMS resonant structures, and can accurately capture bias drift signal components with different characteristics under the temperature change of the butterfly wing type MEMS resonant structure so as to realize high-precision compensation.

The invention provides a power cabinet working condition evolution prediction method based on a physical time sequence orthogonal decoupling architecture, and the method comprises the steps: firstly constructing a multi-dimensional non-stationary signal system based on arc disturbance and load impact characteristics, and collecting the working voltage, temperature rise upper limit, rated and withstand current and other operation parameter data of a power cabinet; in the modal decomposition and screening process, a noise suppression mechanism and a singular information retention technology are utilized, and weakening of non-Gaussian arc interference and retention of working condition abrupt change characteristics are achieved while physically independent orthogonal modal components are separated out. And finally, constructing a double-flow decoupling prediction network based on a deterministic mechanism and data-driven cooperative work. Further, static safety hyperplane constraint is introduced in a parameter updating stage, and a feasible region self-adaptive adjustment mechanism is supplemented, so that the model parameters are subjected to limited optimization on a constraint manifold defined by an electrical safety boundary; by establishing a multi-target topological potential energy function, balance between prediction precision and physical consistency is dynamically coordinated.

The invention relates to the technical field of data processing, in particular to a DD motor residual life prediction method based on multi-source data fusion, and the method comprises the steps: obtaining a vibration signal, a q-axis torque current and a rotating speed signal of a current time window of a DD motor; constructing frequency spectrum complexity based on the vibration frequency domain distribution characteristics and the q-axis current load fluctuation characteristics; constructing a non-stability constraint coefficient based on the rotating speed transient characteristic and the electromechanical coupling power characteristic; calculating an optimal modal decomposition layer number and an optimal secondary penalty factor of variational modal decomposition through nonlinear mapping; decomposing the vibration signal, taking a kurtosis maximum intrinsic mode function component as a main fault component, and extracting a health factor; and predicting the remaining life based on the health factor change trend. The DD motor residual life prediction precision and reliability are improved, fault features are accurately extracted, under-decomposition or over-decomposition is avoided, and a scientific basis is provided for preventive maintenance.

The invention discloses an underground water level change prediction method and system based on machine learning, and relates to the technical field of hydrogeology, and the method comprises the steps: carrying out the standardization processing of multi-source time series data, obtaining a standardized multivariable time series data matrix, and constructing a supervised learning sample set; inputting the underground water level sequence in the supervised learning sample set into a physical information guided variational mode decomposition network; decomposing the underground water level sequence into K intrinsic mode component sequences and residual term sequences through a loss function of physical driving consistency constraint; and for each of the K intrinsic mode component sequences, dynamically assembling a differentiable simulator from the differentiable simplified physical simulator basic library, and carrying out cooperative training by taking approximation to each intrinsic mode component sequence and overall reconstruction of the original water level sequence as targets to obtain K completely trained assembled differentiable simulators. According to the method, a reliable visual prediction result is generated through multi-simulator collaborative deduction and uncertainty quantization.

The invention discloses a multi-mode composite fault diagnosis method and system for a variable-frequency asynchronous motor. The method comprises the following steps: synchronously acquiring a vibration acceleration signal X, a rotating speed signal R and a current signal D of the variable-frequency asynchronous motor; performing adaptive noise reduction on the vibration acceleration signal X by using a rotating speed driven harmonic wavelet packet-variational mode decomposition method to obtain a reconstructed signal Y; filtering the current signal D through dual-mode collaborative filtering and soft reference noise, and outputting a noise reduction signal S through dual-channel fusion processing; extracting a pass frequency speed effective value and an acceleration kurtosis from the reconstructed signal Y, and extracting a current effective value, a peak coefficient, a degradation coefficient and a harmonic distortion sequence from the noise reduction signal S; vibration, rotating speed and current characteristics are fused to set expert mechanism model rules, and fault types are output according to the rules. The early weak fault sensitivity can be improved, and accurate, real-time and automatic early warning of composite faults such as bearing damage, rotor bar breakage and air gap eccentricity under complex working conditions can be realized without manual intervention.