43 results about "Morlet wavelet" patented technology

The invention discloses a fault diagnosis method and a fault diagnosis system for an electric valve actuating mechanism. The method comprises the following steps: synchronously acquiring signals through an anti-EMI (Electro-Magnetic Interference) multi-source sensor; adopting complex Morlet wavelet packet decomposition to extract a 1.2-2.4 kHz energy entropy minimum frequency band, and calculating a kurtosis index; separating the third harmonic of the current through variational mode decomposition, and calculating the total distortion rate of the third harmonic; a graph attention network with 12-dimensional features is constructed, and weighted fusion is carried out through a multi-head attention mechanism; the lightweight CNN outputs a fault type, and when the confidence coefficient is less than 0.9, a knowledge graph rule engine is triggered; and updating a threshold value based on a historical diagnosis clustering result, and aggregating edge model parameters by federal learning. The system comprises a wafer-level micro-strain sensing layer, an FPGA accelerated edge computing layer, a cloud platform supporting federated learning, and an AR maintenance guidance and block chain evidence storage module. The early fault detection rate is improved, the false alarm rate under strong EMI is reduced, and the average repair time is shortened.

The invention relates to the technical field of education big data analysis, in particular to a student information intelligent management system based on big data, comprising a data convergence module used for converging multi-source heterogeneous behavior data streams of target students in campus Internet of Things and interaction logs of the target students in a digital learning platform in real time to obtain an original time sequence data vector set; and the feature generation module is used for carrying out cross-modal time domain alignment and wavelet coherent transformation on the original time sequence data vector set so as to generate a multi-scale spatial-temporal feature map representing the individual learning and living states of the students. According to the invention, global network time protocol synchronization timestamp synchronization and Kalman filtering interpolation are introduced through the data aggregation module, and the feature generation module adopts remoley wavelet transform and wavelet coherence spectrum analysis, so that the phase locking relationship of online interaction and offline behaviors of students on a time-frequency domain can be quantified; therefore, the learning and living states of the students can be more comprehensively described.

According to the power distribution network fault protection and positioning method and system based on the fast switch, an edge calculation node adopts noise self-adaptive improved Morlet wavelet transform, and a current change rate and a voltage break variable are extracted from a transient signal; constructing a three-dimensional decision model taking the current change rate, the voltage break variable and the line characteristic impedance as variables; based on a three-dimensional decision-making model, when it is judged that an internal fault occurs by using the extracted current change rate and voltage break variable, the distributed detection unit sends the action state quantity of the equipment where the distributed detection unit is located to an edge computing node; after the edge computing node utilizes the action state matrix of the equipment, a state reasoning method based on a fuzzy Petri network is adopted to determine a fault section; verifying the fault section according to the matching degree of the fault current weighting and the characteristic impedance of the equipment in the fault section; after the fault section is verified, fault isolation is executed; and after fault isolation, fault positioning is optimized, and it is ensured that the cooperative breaking time sequence of the multi-stage switch is accurately matched with a fault diffusion path.

The invention discloses a substation intelligent auxiliary control monitoring system based on a gateway machine. The substation intelligent auxiliary control monitoring system comprises a data acquisition module, a protocol adaptive adjustment module, an anomaly detection module, a fault early warning module and an intelligent operation control module. The invention relates to the technical field of transformer substation intelligent management, in particular to a transformer substation intelligent auxiliary control monitoring system based on a gateway machine. According to the scheme, protocol features are automatically extracted and predicted through self-supervised comparative learning and a second-order Markov chain, and label-free rapid switching and high-reliability communication are achieved in combination with confidence and delay decision; fusing a sliding window transfer entropy and a kernel PCA reconstruction residual error, performing unsupervised detection and positioning electrical, network and environment anomalies; by means of multi-scale Morlet wavelet entropy and DBSCAN rare cluster recognition, unknown fault precursor spontaneous early warning is achieved; based on real-time apparent power autoregression prediction and mixed integer convex optimization, peak suppression, load smoothing and temperature constraint are considered, and a scheduling strategy is optimized.

The invention discloses an elastomer layer carbon fiber composite material damage positioning method based on elliptic probability fusion, which comprises the following steps: taking different sensors as excitation sources, and collecting Lamb wave signals of a plurality of sensing paths; performing continuous wavelet transform by using a complex Morlet wavelet, and extracting actually measured flight time; introducing a layered wave velocity correction model to optimize an elliptical orbit method, and calculating theoretical flight time and damage probability; introducing a dynamic short-axis optimization model to optimize a probability weighting method, and calculating a damage probability; generating prior distribution by using results calculated by an elliptical orbit method and a probability weighting method; constructing a likelihood function based on the difference between the actually measured flight time and the theoretical flight time; the posterior distribution of the damage position is obtained through the Bayesian theorem in combination with the prior distribution and the likelihood function; sampling the posterior distribution by using an adaptive MCMC algorithm, and generating a probability cloud picture of the damage position; and outputting a final imaging result of the damage position, and positioning the damage position.

The present invention discloses a method for generating a rotor fault diagnosis model based on multiple transform domains and a diagnosis method. The former includes: collecting vibration signal data of a modular rotor fault of a gas turbine in multiple categories to construct a training and test data set; transforming each data to the short-time Fourier time-frequency domain using the STFT transform domain, transforming it to the Morlet wavelet time-frequency domain using the Morlet wavelet transform domain, and transforming it to the complex network phase space domain using the complex network recurrence plot method; inputting the training data set transformed by the three transform domains into a preset model, and using the CNN network layer for feature extraction; using the LSTM network to perform feature structure learning on the output features, and training to obtain a rotor fault model; using the test data set transformed by the three transform domains to verify and adjust the rotor fault model to obtain a rotor fault diagnosis model for fault detection. The present invention can realize automatic data processing, reduce manual input, and improve the efficiency and accuracy of fault diagnosis.

The invention belongs to the field of building environment control, and provides a thermal comfort dynamic adaptive control method based on multi-modal wave analysis and AI driving. According to the method, environmental parameters, user physiological signals (HRV) and subjective thermal comfort data are synchronously collected in real time, time-frequency characteristics of the physiological signals are extracted through continuous Morlet wavelet transform, high-order dynamic characteristics are constructed, the thermal comfort state is predicted in combination with deep learning, a deep reinforcement learning strategy is optimized through an NSGA-II algorithm, a multi-target optimal strategy set is generated, and the optimal thermal comfort state is obtained. And finally, a multi-arm bandit model with Bayesian inference is utilized to realize strategy online adaptive updating. By applying the method, the thermal comfort prediction precision can be expected to be greater than or equal to 90%, the net energy conservation is greater than or equal to 32%, the limitation of the existing thermal comfort regulation and control method in a dynamic situation is effectively solved, and the dynamic balance of personalized thermal comfort and system energy conservation is realized.

The invention discloses a natural gas pipeline leakage detection method based on novel wavelet basis transformation and singular value decomposition in a two-dimensional convolutional neural network. Firstly, a sound signal collected by a sound wave sensor is converted into a digital signal; secondly, in the data preprocessing stage, singular value decomposition is carried out on the digital signals to effectively eliminate background noise interference, and then batch normalization is carried out on the processed data; then, converting the one-dimensional time sequence signal into a two-dimensional time-frequency image by adopting a self-defined Morlet wavelet basis function; and finally, based on the time-frequency images, constructing and training a 2D-CNN model for fault classification, and presenting a diagnosis result through a confusion matrix and a comparison graph. According to the method, 97.55% of fault recognition accuracy is obtained in a public data set, and compared with other competitive methods, the method shows more excellent noise robustness and classification performance, and has higher accuracy and wide application prospects in pipeline leakage diagnosis in a complex noise environment.

The invention discloses a water turbine governor fault modeling and parameter optimization method based on iterative learning control. The method comprises the following steps: S1, system dynamics modeling; s2, iterative learning parameter updating, wherein a water turbine governor fault diagnosis method based on iterative learning control realizes progressive identification of fault features through periodically correcting model parameters; s3, fault feature extraction: calculating a residual signal of an actual output and a model predicted value, performing time-frequency analysis on the residual signal by adopting improved Morlet wavelet transform, and extracting an energy entropy feature and a time domain statistical feature; s4, fault diagnosis and dynamic optimization: based on the extracted fault features, fault detection and classification are realized through a three-level linkage decision mechanism, a dynamic adjustment strategy is introduced to carry out online optimization on a diagnosis rule base, and fault modeling and parameter optimization closed loop are completed; according to the method, the problem of modeling misalignment of a traditional method under a nonlinear working condition is effectively solved.

The invention relates to a vegetation leaf dry matter content remote sensing high-precision inversion method based on wavelet analysis. The method comprises the following steps that S1, a leaf sample database is constructed; S11, a leaf actual measurement data set is constructed; s12, constructing a blade simulation data set; s13, data set division: dividing an actual measurement data set into an actual measurement training set and an actual measurement verification set according to wavelet features; s2, extracting dry matter feature information through wavelet transform; S2, performing multi-scale decomposition on the leaf spectral signal by using continuous wavelet transform; s22, adopting Morlet wavelet as a generating function to carry out continuous wavelet transform analysis on the original reflection spectrum of the blade; s23, carrying out correlation test on the obtained wavelet coefficient and an LMA value; s24, according to a set threshold value, wavelet coefficient characteristics sensitive to the dry matter content are screened out; and S3, constructing an LMA inversion model based on the wavelet coefficient characteristics and the spectral indexes. The method is high in inversion precision, strong in robustness and good in stability.

The invention relates to the field of smelting magnetic stirring, in particular to an aluminum alloy smelting magnetic stirring system which comprises a magnetic field sensing module, an anomaly detection module, a coupling output module and a database. The anomaly detection module extracts magnetic field signal features through a Morlet wavelet transform 1D-CNN and LSTM hybrid network, and identifies abnormal working conditions; the coupling output module constructs a four-field coupling equation based on FEM and CFD, introduces a modified turbulence model, and optimizes magnetic field parameters by taking flow velocity, temperature and impurity distribution uniformity as targets after discretization solution; accurate regulation and control and anomaly detection of the aluminum alloy smelting process are achieved, and the stirring effect and the process stability are improved.

The invention discloses a carbon trading market analysis method and system based on market data, and relates to the technical field of artificial intelligence, and the method comprises the steps: initializing a solver through a four-order Runge-Kutta method, employing symbolic regression and pi-net forward propagation, generating a predicted carbon price curve, calculating the TBPPT truncation length, and employing EMA for smoothing. A time-space gating mechanism is combined with a smooth length to update a hidden state of a starting point, a triangular membership function parameter is randomly set by initializing a particle swarm, Levy flight is used for position updating, Morlet wavelet mutation is used for position mutation, and adjustment is performed by combining a smell concentration mechanism. The Pi-net network is combined with the PNODE differential equation to improve the precision of carbon price prediction, the dynamic characteristics of the carbon market are adaptively captured through the time-space gating mechanism and ST-ODE modeling, and the efficiency and accuracy of transaction instructions are improved through fuzzy rule generation of the triangular membership function and particle swarm optimization.

The invention provides a flow velocity data multi-scale period rule extraction method and device based on an improved Morlet wavelet and a readable storage medium thereof, and aims to solve the problems of insufficient time domain positioning, unbalanced high and low frequency resolution and noise interference in non-stationary flow velocity data in a traditional method. The method is realized through the following steps: carrying out five-point Gaussian interpolation completion and normalization preprocessing on original flow velocity data; a Morlet wavelet function with the center frequency changing adaptively along with the scale is constructed, and parameters are dynamically optimized based on a period identification contrast index by using an improved whale optimization algorithm; carrying out wavelet transformation on the preprocessed data and calculating a power spectrum; and screening and extracting a key period through an energy spectrum density local maximum value and a threshold value. According to the method, the period recognition precision is remarkably improved, the signal-to-noise ratio is improved, accurate and stable extraction of multi-scale period characteristics is achieved, and the method is suitable for non-stationary signal analysis scenes such as hydrological flow velocity state monitoring.

According to the CNN electromagnetic valve fault diagnosis method and device based on time-frequency analysis disclosed by the invention, the fault diagnosis performance under a complex working condition is improved by fusing time-frequency domain feature extraction and a double-attention mechanism. According to the method, current and voltage signals are used as input, a complex value convolution preprocessing layer containing STFT and Morlet wavelet transform is constructed, and corresponding complex value convolution kernel functions are deduced respectively; on the basis, a CBAM module is improved, and a double-time-frequency attention module fusing channel-space attention is constructed. And a dual-time-frequency attention module is combined with a one-dimensional convolutional neural network (CNN) to construct a dual-time-frequency attention network. And finally, carrying out validity verification on the pneumatic electromagnetic valve fault data set by using a double-time-frequency attention network. The method is suitable for a complex electromagnetic valve working environment, and the fault judgment accuracy is improved; according to the method, generalization and robustness are enhanced, and the modeling cost is reduced.

The present invention proposes a method, device, and readable storage medium for extracting multi-scale periodic patterns from flow velocity data based on an improved Morlet wavelet. This method addresses the problems of insufficient time-domain localization, imbalanced high- and low-frequency resolution, and noise interference in non-stationary flow velocity data, as observed in traditional methods. The method is implemented through the following steps: The original flow velocity data is preprocessed using 5-point Gaussian interpolation and normalization; a Morlet wavelet function whose center frequency adaptively changes with scale is constructed, and parameters are dynamically optimized based on a period identification contrast index using an improved whale optimization algorithm; a wavelet transform is performed on the preprocessed data and the power spectrum is calculated; and key periods are extracted through local maxima of the energy spectral density and threshold screening. The present invention significantly improves period identification accuracy, enhances the signal-to-noise ratio, and achieves accurate and stable extraction of multi-scale periodic features. The method is suitable for non-stationary signal analysis scenarios such as hydrological flow velocity status monitoring.

The application discloses a kind of based on gateway machine's intelligent auxiliary control monitoring system of substation, including data acquisition module, protocol self-adapting adjustment module, abnormality detection module, fault early warning module and intelligent operation control module.The application relates to the technical field of intelligent management of substation, specifically refers to a kind of based on gateway machine's intelligent auxiliary control monitoring system of substation, the present scheme utilizes self-supervised contrast learning and second-order Markov chain automatically extracts and predicts protocol features, combines confidence and delay decision, realizes no label fast switching, high reliable communication;Fusion sliding window transfer entropy and kernel PCA reconstruction residual, unsupervised detection and positioning electrical, network and environmental anomaly;With the help of multi-scale Morlet wavelet entropy and DBSCAN rare cluster identification, unknown fault precursor spontaneous early warning is realized;Based on real-time apparent power autoregressive prediction and mixed integer convex optimization, peak suppression, load smoothing and temperature constraint are considered, and scheduling strategy is optimized.

The double-teacher sleep staging feature migration method based on knowledge distillation and domain adaptation belongs to the field of signal processing and pattern recognition. First, the sleep electroencephalogram and electrooculogram signals are preprocessed to obtain a plurality of multi-modal sleep signal data samples. Next, each channel contained in each sample of the source domain and target domain data is sequentially extracted using Morlet wavelet transform of different resolutions to obtain time-frequency features, and then input into the source domain teacher and target domain teacher for pre-training. In the training and optimization of the student, the two teachers with frozen feature extractors are introduced for guidance to constrain the student to learn the source domain and target domain general features and the domain-specific features of the target domain. Experiments prove that the model proposed in the application fully utilizes the features of the data for feature migration, and good results can be obtained when the amount of target domain data is small, which can effectively solve the problem that the existing automatic sleep staging method has a decreased accuracy when facing new data sets.

The invention belongs to the technical field of intelligent safety guardrails, and particularly relates to a multifunctional sensing and local control intelligent safety guardrail system, which comprises a data acquisition module, a wavelet transformation module and an early warning module, and is used for performing Morlet continuous wavelet transformation on a vertical real-time depth map and a vertical reference depth map output by the data acquisition module to obtain a vertical real-time depth map and a vertical reference depth map; respectively generating a plurality of phase spectrums of the vertical real-time depth map and the vertical reference depth map; obtaining a continuous phase difference distribution map for the phase difference between the two complex phase spectrums; the linear relation between the phase difference and the displacement is used for calculating the horizontal displacement, the Morlet wavelet transform is used for directly calculating the point cloud displacement through the frequency domain phase difference, the process that an ICP algorithm is needed for multiple iterations in traditional electric cloud calculation is avoided, the geometrical characteristics of the infrastructure are converted into the physical scale of wavelet analysis, time domain localization analysis is achieved, and the calculation efficiency is improved. Displacement detection is converted into a phase matching problem of a signal and a wavelet, and the precision is improved while the speed is increased.

The present invention proposes a method and system for evaluating the state of oil-paper insulation based on harmonic-discharge coupling analysis, which relates to the technical field of transformer oil-paper insulation. The method comprises the following steps: configuring harmonic parameters, extracting the time-frequency energy distribution of each harmonic using a Morlet wavelet convolution kernel to construct a harmonic fingerprint matrix, collecting oil-paper insulation data to construct nonlinear cross features to generate an enhanced feature vector, calculating the dynamic attention weight of each harmonic component on the insulation state, and performing dual-channel degradation evaluation through the equivalent circuit equation of the physical channel and the attention LSTM network of the data channel to obtain the harmonic impact factor and state evaluation matrix. Finally, the HIF index is calculated by weighted fusion of the harmonic frequency offset and the amplitude exceeding the standard, and the evaluation result is output according to the HIF index. The present invention solves the problems of insufficient accuracy and poor interpretability of traditional methods in complex harmonic coupling scenarios, and significantly improves the accuracy and engineering applicability of oil-paper insulation state evaluation.

The present invention discloses a method for extracting micro-motion features of low-altitude, slow and small targets based on a GST-WT combination, which relates to the field of micro-motion feature extraction of low-altitude, slow and small targets. The method comprises the following steps: acquiring a multi-band radar echo signal, preprocessing the multi-band radar echo signal, and adopting a GST-WT combination model to perform time-frequency analysis on the preprocessed signal to obtain time-frequency features of an improved generalized S transform and a Morlet wavelet transform; performing linear interpolation on the time-frequency features of the improved generalized S transform; adopting a linear weighting strategy to fuse the time-frequency features to obtain fused time-frequency features; and quantitatively evaluating the feature extraction effect by combining energy entropy and energy concentration indicators. By giving full play to the advantages of GST global time-frequency analysis and WT local adaptation, the micro-motion features of the target are effectively separated and accurately extracted, and the time-frequency resolution, noise resistance and feature stability are improved, thereby providing technical support for the detection of low-altitude, slow and small targets in scenarios such as low-altitude security and unmanned aerial vehicle monitoring.

The present invention discloses a channel state information (CSI) indoor positioning method based on a graph isomorphic network (GIN). First, a local outlier factor (LOF) is detected for each subcarrier in the CSI amplitude measurement to remove abnormal points in the CSI amplitude measurement value. Then, a time-frequency diagram of the CSI measurement value is obtained using the Morlet wavelet function, and a CSI image is constructed using color mapping. Then, a corresponding graph topology structure is constructed based on the CSI image, and the CSI image is superpixel segmented using the SLIC algorithm to achieve node selection and neighboring edge relationship construction. The position features and color features of the nodes are integrated to form a feature matrix. Finally, GIN is used for classification learning to train the final position estimation model. The method achieves the advantages of high efficiency, reliability, and feasibility.

This invention discloses a method for extracting moiré fringe phase information based on Morlet wavelet transform, comprising: converting a target moiré fringe image into a grayscale image; filtering the grayscale image to obtain a filtered binarized image; performing mathematical morphological denoising on the binarized image to obtain a processed image, wherein the mathematical morphological denoising includes erosion and dilation; convolving each column of the processed image using modulated Morlet wavelets and calculating the amplitude and phase of the wavelet coefficients; determining wavelet ridges based on the amplitude of the wavelet coefficients and extracting the phase of the scale coefficients and time coefficients corresponding to the wavelet ridge positions; and obtaining complete moiré fringe phase information based on the phases of all extracted columns. This method is highly accurate and easy to implement, making it suitable for further refractive index reconstruction and key parameter measurement of the measured flow field.

The application relates to the technical field of structural damage positioning, and discloses a damage positioning method based on an acoustic emission array, which comprises the following steps: firstly, the acoustic emission signal is subjected to adaptive inverse filtering and delay compensation through a virtual time reversal mirror technology; secondly, a narrowband single-frequency signal is extracted based on Morlet wavelet transformation to inhibit frequency dispersion and multi-modal interference; and finally, a long-short-time kurtosis ratio enhancement operator is adopted to realize high-precision adaptive pickup of the arrival time in a strong noise environment. Through multi-stage cooperative processing, the application can effectively overcome multi-modal effects, frequency dispersion and noise interference, realize high-precision, high-robustness and high-real-time acoustic source positioning in a complex industrial scene with sparse sensor arrangement, non-uniform medium and variable noise, and significantly improve the detection capability for hidden defects and the system adaptability.

This invention discloses a brain-computer interface (BCI) teaching demonstration system and control method, belonging to the field of BCI and artificial intelligence education technology. The system includes: a multi-channel EEG headband for synchronously acquiring EEG signals and head posture data; an edge AI hub with a built-in NPU accelerator for dynamically gating and adaptively filtering EEG signals based on head posture data, generating a two-dimensional time-frequency graph through complex Morlet wavelet transform, and using a lightweight RepEEG-Net neural network with structural reparameterization and quantization processing to analyze user intentions in real time, while simultaneously generating visualized teaching data; and a microcontroller execution chassis equipped with a real-time operating system (RTOS) for controlling the actions of the execution mechanism through multi-priority task scheduling. This invention achieves low-latency, highly interference-resistant brain-controlled demonstrations by deploying lightweight intelligent algorithms at the edge, and visualizes the algorithm processing process, significantly improving the real-time performance, robustness, and intuitiveness of the teaching demonstration.

This application provides a method and system for early screening of Alzheimer's disease based on electroencephalogram (EEG) signals, comprising: acquiring the resting-state EEG signals of the subject as raw EEG signals, and performing data preprocessing on the raw EEG signals; extracting the average power value of the preprocessed signals based on the multi-band Morlet wavelet transform algorithm, constructing a functional connectivity matrix based on the extracted average power value and performing multi-dimensional feature fusion, and using the resulting multi-dimensional functional connectivity tensor as the core feature; inputting the multi-dimensional functional connectivity tensor into a pre-constructed deep separable residual convolutional network to perform end-to-end feature learning and decision classification on the core features, and using the network output as the early screening result for Alzheimer's disease. This application covers three core links: automatic preprocessing, data analysis, and classification detection, which work together to achieve efficient and convenient early screening for Alzheimer's disease.

A transformer short-circuit impedance three-phase synchronous testing method and system, comprising: synchronously collecting different signals on the high-voltage side of the transformer; dynamically adjusting the center frequency and bandwidth parameters of the Morlet wavelet base function based on the real-time frequency; respectively performing wavelet decomposition on the different signals based on the adjusted Morlet wavelet base function to obtain the complex wavelet coefficient matrix corresponding to the different signals; purifying the complex wavelet coefficient matrix of each signal; selecting an effective calculation interval based on the maximum ridge line area of the modulus matrix of the purified different signals, and solving the optimal estimation value of the short-circuit impedance through the least square method according to the elements of the purified complex wavelet coefficient matrix of the different signals in the effective calculation interval; and correcting the calculated short-circuit impedance value through temperature and frequency. The present application ensures the strict alignment of three-phase data and effectively supports the fault diagnosis based on three-phase unbalance degree.

The invention discloses a transformer iron core damping measurement method and system, and the method comprises the steps: placing a transformer iron core on a smooth plane, and enabling the environment noise to be smaller than a preset value; an acceleration sensor is adsorbed on the surface of the transformer iron core; an iron core is tested through excitation of a vibration exciter, vibration signals of the acceleration sensor are collected, and the modal inherent frequency corresponding to the damping ratio is determined; the method comprises the following steps: calculating a Moley wavelet based on a modal inherent frequency, introducing a wavelet time broadening coefficient and a length coefficient to control the length of the Moley wavelet, converting a vibration signal by using the Moley wavelet, calculating an amplitude ratio, and finally solving a damping coefficient by using a relational expression between the amplitude ratio and the damping coefficient; the method has the advantage that the damping coefficient of the transformer iron core is accurately obtained.

The invention provides a data transmission analysis method, device and equipment based on multi-scale condition mutual information, and relates to the technical field of data mining. The method comprises the following steps: performing Morlet wavelet decomposition on an original sequence to obtain wavelet coefficients under a plurality of time scales, and constructing a candidate lag variable set corresponding to the time scale based on each wavelet coefficient under each time scale; screening a key lag component in each candidate lag variable set by adopting a conditional mutual information progressive strategy to obtain an optimal embedding vector corresponding to each time scale; and for each time scale, estimating conditional probability density and marginal probability density based on the corresponding optimal embedding vector, calculating conditional mutual information, and substituting the conditional mutual information into a corresponding variable embedding data transmission intensity calculation formula to obtain data transmission intensity and direction between the first original sequence and the second original sequence. According to the method, multi-scale, self-adaptive and high-precision depiction of the dynamic influence relationship among the cross-stage engineering data can be realized.

This invention discloses a method and device for early warning of energy consumption in air conditioning refrigeration systems based on genetic algorithms. It aims to solve the problems of traditional energy consumption prediction models, such as single feature set, weak nonlinear modeling ability, reliance on experience for parameter tuning, and susceptibility to local optima. The method first integrates operating parameters such as indoor and outdoor temperature difference, humidity, compressor performance, and refrigerant charge to construct input features that comprehensively reflect the system state. Second, it designs a wavelet neural network with Morlet wavelet function as the activation function and introduces a genetic algorithm to globally optimize network weights, scaling factors, and translation factors, automatically searching for the optimal parameter combination to improve model convergence speed and prediction accuracy. Third, it dynamically sets energy consumption thresholds based on historical data, compares the prediction results in real time, and triggers an early warning when the threshold is exceeded. This method ensures high accuracy while possessing good generalization ability and engineering applicability, providing effective support for intelligent operation and maintenance and energy-saving management.

The invention discloses an LPG sales volume prediction method and device based on multi-source features and an adaptive network, and aims to solve the problems that the LPG terminal sales volume is affected by multi-source data, the time sequence features are complex and the general model adaptability is poor. Basic sales volume, user behaviors, external influences and operation response levels are covered; time sequence data time-frequency domain enhancement is realized through Morlet wavelet transform, and capture of an LPG service period is enhanced in combination with a service awareness position coding enhancement model; secondly, designing a multi-channel convolution-attention-cycle hybrid network MCA-RNet, and processing local fluctuations, periodic trends and external factors in parallel; and finally, outputting a prediction result through business rule verification and a dynamic optimization mechanism. According to the method, high-precision prediction of the LPG sales volume is realized, and reliable support is provided for filling operation plans, inventory optimization and dynamic pricing.