37 results about "Permutation entropy" patented technology

The invention discloses a financial traceability risk measurement and analysis method and system based on dynamic entropy transfer, and the method comprises the steps: constructing a dynamic entropy transfer graph through combining with various types of structure information, such as local guiding entropy, path exploration entropy and behavior collaborative entropy; the method can effectively describe the propagation path and the structure level of the risk factor in the complex financial network while keeping the calculation controllable. According to the method, the edge behavior sequence is constructed through the Gaussian kernel function on the basis of the node behavior time sequence, and the multi-scale permutation entropy is combined to model the inter-edge time sequence collaborative change, so that the expression ability of the system to the microscopic interaction behavior is remarkably improved, and the method has good adaptability and interpretability. The method can achieve the positioning of a potential high-influence risk source and the reconstruction of a propagation chain, is suitable for a plurality of scenes, such as financial supervision, risk early warning and abnormal path tracking, is high in processing efficiency, and is stable and reliable in result.

The invention discloses a short-term power load prediction method, system and device based on multi-intelligent-model fusion and a medium, and belongs to the technical field of short-term power load prediction, and the method comprises the steps: obtaining regional historical load data and meteorological data; performing data cleaning on the obtained load data and meteorological data; measuring linear and nonlinear correlation between the power load and the meteorological factors, and screening meteorological data with high load correlation; decomposing the load data into a time sequence by using an empirical mode decomposition method based on combination of multi-scale permutation entropy to obtain a multi-scale sub-data sequence; respectively predicting the multi-scale sub-data sequences to obtain prediction results; carrying out weighted fusion on the prediction result through a long short-term memory network model to obtain a load prediction result, and optimizing model parameters to obtain a trained multi-model prediction model; and predicting the test set data by using the trained model to obtain a final load prediction result. According to the invention, the precision and adaptability of load prediction are effectively improved.

The invention relates to the field of water environment pollution detection and analysis, in particular to a water environment pollution detection and analysis system and method based on the Internet of Things, and solves the problems of sampling redundancy, missing detection, high-dimensional data over-fitting, difficulty in traceability and early warning lag in traditional detection. The system comprises a monitoring acquisition module, a water quality anomaly detection module, a pollution tracing module, a pollution early warning module and a database. The monitoring acquisition module adopts chaotic adaptive sampling to adjust sensor frequency, and entropy optimization water quality data is obtained by combining permutation entropy and collaborative filtering denoising; the water quality anomaly detection comprises the following steps: standardizing data into high-dimensional point clouds, calculating a Betti number and a non-equilibrium state entropy, and fusing to generate a comprehensive pollution topological entropy index; according to pollution traceability, a dynamic graph and a diffusion kernel matrix are constructed by using GNN, and the optimal source intensity is solved through quantum annealing; the range is predicted through a diffusion equation for early warning, and information is integrated to generate a report to be pushed to users. The method corresponds to a module flow and provides support for pollution prevention and control.

The invention relates to the technical field of intelligent operation and maintenance supervision, and discloses an industry intelligent operation and maintenance supervision method and system based on a large model. The method comprises the steps of collecting multi-source time sequence data of an industry operation and maintenance system; performing time-frequency conversion on the data to obtain time-frequency feature representation, and configuring a decomposition basis function and hierarchical parameters of an adaptive decomposition model according to the time-frequency feature representation; the model is used for carrying out multi-scale analysis on data to obtain a multi-resolution characteristic component, and permutation entropy of the multi-resolution characteristic component is calculated to serve as complexity measurement. And based on the feature component and complexity, selecting a core feature set through importance evaluation, and generating a customized monitoring strategy in combination with a system operation baseline portrait, a real-time working mode and large model reasoning. Constructing an operation and maintenance event feature sequence according to the core features and strategies, and performing variational mode decomposition on the operation and maintenance event feature sequence to extract steady-state and transient components; and a machine learning classifier is adopted to carry out mode recognition on the components, event categories are output, and intelligent operation and maintenance decision and accurate supervision are realized.

The invention provides a data-driven saline screw compressor unit dynamic modeling method, and belongs to the technical field of industrial intelligence and predictive maintenance. According to the method, adaptive deep denoising of original data is realized through a composite signal processing flow of fusing variational mode decomposition, permutation entropy criterion and wavelet packet transformation optimal threshold denoising; meanwhile, a sectional sampling strategy is introduced to enhance the diversity of training data. Then, a wavelet multi-scale energy entropy extraction layer is used for constructing a high-information-density feature vector; furthermore, a prediction model formed by multiple layers of stacked long and short-term memory network units is adopted, and the complex time sequence dependency relationship of the system is deeply captured. According to the method, pure and stable system dynamic representation can be extracted from high-noise industrial data, the dynamic characteristics of the system in the full working condition range are accurately described, and it is ensured that the prediction result is self-consistent physically and reliable in engineering, so that the prediction precision and generalization performance of the model are remarkably improved.

The method comprises the following steps: obtaining a power quality signal containing noise; selecting permutation entropy as an adaptive function of genetic algorithm, calling variational mode decomposition through genetic algorithm, and iteratively optimizing a penalty factor α and a decomposition mode number k of the variational mode decomposition to determine optimal parameters; decomposing signal data into k mode components through the variational mode decomposition, and determining effective mode components and noise mode components through a correlation coefficient; for improved wavelet threshold, a parameter-adjustable threshold function is proposed, and the concept of wavelet energy entropy is introduced into the threshold function; the noise mode components are denoised through the improved wavelet threshold, and the effective mode components and the denoised noise mode components are reconstructed to obtain a denoised power quality disturbance signal. The method can effectively remove noise interference while retaining singular information of mutation points of the collected signal, and provides help for subsequent analysis and treatment of the power quality disturbance signal.

The invention relates to a daily runoff prediction method based on adaptive signal decomposition and deep learning fusion. The method comprises the following steps: acquiring daily runoff sequence data of a historical time period; adopting an ICEEMDAN algorithm to decompose the standardized runoff sequence into a plurality of intrinsic mode function components and one residual component; calculating the permutation entropy of each IMF component and screening noise dominant components; carrying out wavelet hard threshold noise reduction processing on the screened noise dominant component; carrying out superposition reconstruction on the noise dominant component after noise reduction, the effective characteristic component and the residual component; an ICEEMDAN-CNN-LSTM hybrid prediction model is constructed, and an ICEEMDAN- Constructing a sample set; training a hybrid prediction model; and performing prediction based on the daily runoff prediction model. According to the method, the prediction precision of the non-stationary runoff sequence is remarkably improved, the dependence on hydrological observation conditions is reduced, the model adaptability is high, the application threshold is low, and the method can be widely popularized to flood control and disaster reduction, water resource optimal configuration and other scenes.

The invention relates to the technical field of fluid mechanical fault diagnosis, and discloses an emulsion pump fault intelligent diagnosis method and system based on multi-dimensional entropy feature fusion, and the method comprises the steps: constructing a multi-dimensional physical field state monitoring space, and synchronously collecting vibration acceleration, outlet pressure and flow time sequence signals; the method comprises the following steps: performing adaptive variational mode decomposition and effective sensitive component screening reconstruction on a vibration signal, calculating a normalized vibration quantile permutation entropy through phase-space reconstruction and quantile mapping, extracting a pressure fluctuation entropy and a flow pulsation variance, fusing the pressure fluctuation entropy and the flow pulsation variance into a multidimensional fault feature vector, inputting the multidimensional fault feature vector into a multi-classification support vector machine, and outputting an operation state label; executing hierarchical closed-loop control; according to the method, through quantile mapping and multi-physics field fusion, the problems of entropy value feature distortion and liquid-machine coupling weak fault feature masking caused by non-Gaussian impact noise are effectively solved, and the fault diagnosis robustness and accuracy of the emulsion pump under complex working conditions are improved.

The invention discloses an ultra-short-term wind power prediction method and system for a long-short-term memory network of permutation entropy, and the method comprises the steps: collecting historical wind power data, and repairing the missing data and abnormal values in the historical wind power data; performing normalization processing on the preprocessed historical wind power data; inputting the normalized data, optimizing and solving the number K of decomposition modes and a penalty factor alpha by using a multi-target grey wolf algorithm, ensuring that fitness functions RMSE and PE are globally minimum, obtaining solved parameters, and further performing decomposition to obtain decomposed subsequences; the decomposed subsequences are used as input, and then prediction model training of the subsequences is carried out; and carrying out rolling decomposition, inputting a prediction model of the subsequences, superposing predicted values of the subsequences, and carrying out reverse normalization to obtain a prediction result, thereby realizing rolling prediction. According to the method, the problem that the prediction precision of data with strong volatility is not high in the existing prediction technology is solved, and the problem that the wind power plant faces assessment due to inaccurate prediction is reduced.

The embodiment of the invention provides a multi-mode collaborative gas pipe network hidden danger identification method and system, and relates to the technical field of gas pipe networks. The identification method comprises the following steps: acquiring data of a pressure sensor, a temperature sensor and a gas concentration sensor at key nodes of the gas pipe network; performing wavelet packet decomposition on the data to obtain sub-band signals of the signals; performing feature extraction on the sub-band signals to obtain an energy entropy, a sample entropy and a permutation entropy; normalizing the energy entropy, the sample entropy and the permutation entropy to obtain a corresponding normalized entropy value; inputting the corresponding normalized entropy value into the intelligent prediction model, and outputting a probability distribution diagram of the pipe network hidden danger position; and leakage point positioning and corrosion degree grading identification are carried out according to the probability distribution diagram. According to the method, data of pressure, temperature and gas concentration sensors in the gas pipe network are effectively integrated, through wavelet packet decomposition and deep feature learning, pipe network leakage, corrosion and other hidden dangers are accurately recognized, and stable operation of a gas supply system is ensured.

The invention belongs to the technical field of power system operation and planning, and discloses a power grid net load fluctuation scene generation method, system and device based on an ARIMA and Copula combined model and a medium, so as to solve the problem of poor scene generation accuracy. The method comprises the following steps: decomposing and reconstructing an original time sequence of the net load of the power grid by using discrete wavelet transform; taking permutation entropy minimization as an optimization target, adopting a variable chromosome length hybridization genetic algorithm to divide time segments for the low-frequency linear subsequences, and respectively establishing ARIMA models to generate linear trend scenes; establishing a joint probability distribution model of the high-frequency fluctuation subsequences at adjacent moments based on a Copula function, and deducing conditional probability distribution in combination with a Bayesian formula to generate a fluctuation scene; and the linear trend scene and the fluctuation scene are superposed to form an initial net load scene set, and a k-means clustering algorithm is adopted to reduce the initial net load scene set to obtain a representative scene set.

The invention discloses a high-reliability planetary gearbox fault diagnosis method, system, medium and equipment, and the method comprises the steps: carrying out the feature extraction and feature selection based on a random forest algorithm, and carrying out the nonlinear feature extraction based on multi-scale permutation entropy, performing multi-scale coarse graining processing on each vibration signal, calculating permutation entropy values of coarse graining sequences under different scales, forming a multi-dimensional phase space, and obtaining a feature matrix of permutation entropy; performing feature dimension reduction and feature embedding based on kernel principal component analysis; according to the fault diagnosis based on the bidirectional long-short term memory neural network, a classifier of the bidirectional long-short term memory neural network is used, a feature set is divided into a training set and a test set to serve as input layers, and then a classification result is output through two LSTM units of a hidden layer, a full connection layer and Softmax function mapping. And high-reliability planetary gearbox fault diagnosis is realized.

The application relates to the technical field of intelligent monitoring and protection of power systems, and discloses a grounding fault diagnosis method based on intelligent time sequence feature extraction. In the feature extraction stage, a multi-scale convolutional neural network is adopted, combined with multi-scale permutation entropy, to perform coarse-grained processing on an original signal, calculate permutation entropy values under different scales, quantify the spatial distribution characteristics of signal complexity, and inhibit noise interference. After feature extraction, the features extracted by the multi-scale convolutional neural network and the multi-scale permutation entropy two channels are spliced through a feature fusion layer, and the fused features are input into a BiGRU module. In view of the problems that the traditional fault diagnosis method has insufficient multi-scale feature extraction, weak anti-noise ability and low time sequence modeling precision under complex working conditions, the application fuses multi-scale feature extraction and dynamic time sequence features, realizes high-precision diagnosis of grounding faults, and significantly improves the precision and robustness of grounding fault diagnosis.

The invention discloses a window optimization-based intra-day prospective dispatching method and device for a power grid, and relates to the technical field of power dispatching, and the method comprises the steps: obtaining a power grid data feature prediction model through employing historical power grid data features and an adaptive differential evolution algorithm; obtaining predicted values of intra-day power grid data features based on a power grid data feature prediction model, thereby generating a plurality of operation scenes; calculating corresponding net load power based on each operation scene, determining permutation entropy, sample entropy and fuzzy entropy based on all the net load power, and establishing a combined entropy calculation formula by using a multi-target equalization method; constructing a look-ahead window optimization model based on a combined entropy calculation formula, and solving the look-ahead window optimization model by adopting a carbon black stingless bee optimization algorithm to obtain a window optimization result; based on a window optimization result, establishing an intra-day look-ahead optimization scheduling model; and solving the intra-day look-ahead optimization scheduling model by adopting a state optimization algorithm to obtain a power grid intra-day look-ahead scheduling plan. The flexibility of the power grid dispatching plan is improved.

The application discloses a modeling method and device for a vehicle-network interaction system and a nonvolatile storage medium. The method comprises the following steps: acquiring time series signals in the vehicle-network interaction system; performing modal decomposition on the time series signals to obtain first-layer intrinsic modal components; calculating target permutation entropy of the first-layer intrinsic modal components; in the case that the target permutation entropy of the first-layer intrinsic modal components is greater than a preset entropy threshold value, determining that the first-layer intrinsic modal components are abnormal modal components; repeating the above steps to obtain an abnormal component set and normal modal components; performing denoising processing on the abnormal component set, and performing weighted aggregation on the processed abnormal component set and the normal modal components to obtain a reconstructed signal; and performing federated learning on multiple subjects based on the reconstructed signal to obtain a target global model. The application solves the technical problem that the current modal decomposition technology is prone to modal aliasing and affects the charging and discharging rule analysis in the vehicle-network interaction.

The invention provides an equipment life prediction method and device, electronic equipment and a storage medium, and relates to the technical field of neural networks. Comprising the steps that a feature sequence of to-be-predicted equipment is collected based on an electrical life test result, and the feature sequence comprises feature parameter sets under continuous time steps; decomposing and reconstructing the feature sequence according to the feature sequence of the to-be-predicted equipment and a plurality of preset scale factors to obtain at least one feature subsequence of the to-be-predicted equipment under each preset scale factor; determining the permutation entropy of the to-be-predicted equipment under each preset scale factor according to the sequence permutation mode of each feature subsequence of the to-be-predicted equipment under each preset scale factor, and determining a multi-scale feature matrix corresponding to the to-be-predicted equipment according to the permutation entropy under each preset scale factor; and according to the multi-scale feature matrix corresponding to the to-be-predicted device, using a pre-trained life prediction model to predict life information of the to-be-predicted device. The method improves the accuracy of the life prediction result.

The invention relates to the technical field of smart power grids, and discloses a flexible straight valve capacitor fault diagnosis method and system, and the method comprises the steps: obtaining an original signal data set; wavelet packet decomposition is combined with the Leimeh-Tiangers complexity, empirical mode decomposition is integrated with permutation entropy, feature extraction, fusion and dimensionality quantitative optimization are performed on the original signal data set, and the optimal fault feature dimensionality is obtained; a deep belief network model with the visible layer node number equal to the optimal fault feature dimension is constructed, and a target fault diagnosis model is obtained after optimization; in the diagnosis process, the target fault diagnosis model outputs each fault probability, the D-S evidence theory is adopted to fuse the basic probability distribution values obtained by weighting and adjusting the fault probabilities according to the global credibility and the local credibility, and the fused basic probability distribution value is obtained and used for fault diagnosis. The method provided by the invention improves the precision of fault diagnosis, does not need complex diagnosis equipment, and has higher adaptability.

The present application relates to a kind of electromagnetic reversing valve life prediction method based on flow signal, belong to hydraulic component life prediction field.The present application utilizes improved lumped average modal empirical decomposition method, by adding positive and negative pairs of noise to reduce the degree of modal aliasing in modal decomposition, using permutation entropy to detect abnormal component, realize the accurate adaptive modal decomposition of nonlinear measured signal;Application kernel principal component method, introduce nonlinear function as kernel function, based on the principle of mapping, convert original space into high-dimensional space, form new data set, using principal component analysis for data dimension reduction in high-dimensional data space, form feature vector, get performance degradation fusion index;Through cubic exponential smoothing processing;Finally based on the trained adaptive neural network model, establish the life prediction model of electromagnetic reversing valve, calculate the life of electromagnetic reversing valve.This method can effectively predict the pressure drop trend and life of electromagnetic reversing valve.

The invention discloses an electric energy quality signal noise reduction and optimization detection method and system and application thereof, and the method specifically comprises the following steps: S1, dynamically optimizing a penalty factor delta and a mode number beta of variational mode decomposition (VMD) through a particle swarm optimization (PSO) algorithm, constructing a fitness function with a composite index (permutation entropy and mutual information) as a core, and carrying out the dynamic optimization of the penalty factor delta and the mode number beta of the variational mode decomposition (VMD) through the particle swarm optimization (PSO) algorithm; and screening an optimal decomposition parameter. S2, performing VMD decomposition on the power quality signal according to the optimized decomposition parameters delta and beta to obtain a plurality of intrinsic mode function components, namely IMF components; s3, screening an optimal signal component from the IMF components based on the composite index to realize signal noise reduction; according to the method, the parameters of VMD decomposition can be optimized for the electric energy quality signal, so that noise interference in the signal is overcome, the problem of low signal-to-noise ratio of the signal is solved, finally, the detection precision of the electric energy quality is effectively improved, and the measurement error is below 2%.

This invention discloses a multi-objective prediction method for power system sources and loads based on Laguerre polynomial theory, relating to the field of power system prediction and intelligent dispatching technology. The method includes the following steps: using Spearman Rank Correlation Coefficient (SRCC) to analyze the correlation of characteristic influencing factors of wind power, photovoltaic power, and power load; and using Robust Local Mean Decomposition (RLMD) to decompose the time series of wind power, photovoltaic power, and power load into high-frequency and low-frequency components to reduce their fluctuations; using Weighted Permutation Entropy (WPE) to analyze the complexity of the subsequences after RLMD decomposition, merging subsequences with similar complexity to reduce the model's prediction complexity; and constructing a hybrid Laguerre neural network prediction model using Laguerre polynomials. This invention is the first to simultaneously consider both accuracy and stability objectives in source and load prediction, selecting a compromise solution in the Pareto front using the MORUN algorithm, making the prediction results more applicable to power system dispatching scenarios with high robustness requirements.

The application discloses a sleep timing data brain-computer interface adjustment method based on artificial intelligence, and comprises the following steps: collecting and preprocessing multidimensional physiological signals to generate a standardized data set; performing permutation entropy calculation on the standardized data set to obtain a permutation entropy characteristic sequence and construct a timing alignment matrix; performing weighted average on the permutation entropy characteristic sequence according to the timing alignment matrix to obtain alignment characteristics; arranging the alignment characteristics in time sequence to obtain a characteristic matrix, inputting the characteristic matrix into a fusion analysis model to output a final sleep state label and an adjustment demand signal, combining a preset adjustment rule library and individual adaptation characteristics of a subject to generate an adjustment instruction adapted to the current sleep state. Compared with the prior art, the application extracts features through permutation entropy and timing alignment cooperation, provides feature input containing signal complexity information and timing correlation information for sleep state analysis, realizes sleep state recognition and adjustment demand judgment in combination with a fusion analysis model, and generates an adjustment instruction.

The application discloses a signal first arrival time picking method and system, electronic equipment and a storage medium. The method comprises the following steps: obtaining a target signal by collecting and preprocessing to-be-processed data; performing amplitude-aware permutation entropy calculation on the target signal to determine a target interval containing a first arrival time; picking an improved Akaike information criterion minimum value point in the target interval as the first arrival time; and completing a geophysical data processing process according to the first arrival time. The embodiment of the application can improve the picking efficiency and the signal picking accuracy under the condition of low signal-to-noise ratio, and can be widely applied to the near-surface engineering geophysical technology field.

This invention discloses a method and system for monitoring encrypted protocols, belonging to the field of cyberspace security technology. The method includes: parsing encrypted session data and simultaneously extracting protocol semantic feature vectors and randomness original data sequences; determining variational mode decomposition parameters through fast Fourier transform, adaptively decomposing the random sequence to obtain multiple intrinsic mode function components, and calculating the permutation entropy of each component to construct a multi-scale entropy spectrum; fusing the protocol semantic feature vector and the entropy spectrum and inputting them into a pre-trained correlation model to output a multi-dimensional risk feature vector; matching a dynamic evaluation strategy according to the protocol type, calculating a comprehensive risk score by combining a risk threshold vector and a weight vector, and outputting a graded compliance conclusion and key risk description based on the score. This invention achieves deep correlation analysis of the randomness and semantics of encrypted protocols from multiple scales and dimensions, overcoming the limitations of traditional methods' single-scale detection and static judgment.

The invention discloses a traveling wave model setting system and method based on waveform transient characteristics, and relates to the technical field of power system relay protection and fault localization. Secondary signals output by a traveling wave sensor are decomposed into a plurality of intrinsic mode components; screening effective intrinsic mode components; fitting the waveform of the effective intrinsic mode component, and obtaining a waveform distortion rate and a frequency abrupt change range in real time; adjusting the sampling frequency according to the waveform distortion rate and the frequency abrupt change range; and adopting a deep forest model to output the fault type and position. According to the method, the end effect and mode aliasing of empirical mode decomposition are effectively inhibited through complementary set empirical mode decomposition, the components containing effective traveling wave features can be adaptively reserved in combination with dynamic screening of the multi-sequence permutation entropy on the intrinsic mode components, the signal-to-noise ratio is remarkably improved, the end effect error is reduced, and the method has the advantages of being high in robustness and the like. The defect that effective components cannot be dynamically screened in the prior art is overcome.

The application discloses a kind of based on machine learning's rolling bearing fault diagnosis method, belong to mechanical equipment fault diagnosis technical field, comprising the following steps: step S1: VMD parameter optimization;Step S2: effective IMF component screening;Step S3: feature extraction and dimension reduction;Step S4: fault diagnosis.The application utilizes variational mode decomposition to reduce the noise in vibration signal, for the problem of variational mode decomposition parameter selection, adaptive grey wolf algorithm is used to optimize;The data after noise reduction is extracted using permutation entropy, and the dimension of fault feature is reduced using nonlinear principal component analysis algorithm, effectively reducing the influence of noise in vibration signal on fault diagnosis accuracy, which can significantly improve the accuracy of rolling bearing fault diagnosis.

This invention discloses a method and system for analyzing load shedding data of pumped storage power stations based on signal decomposition and reconstruction. First, a one-dimensional numerical simulation method is used to simulate the unit's load shedding transient process, which has boundary conditions essentially consistent with the measured signal. The permutation entropy value of the simulated signal is calculated. Next, variational mode decomposition is performed on the measured signal, and component reconstruction is performed using mutual information as a criterion to reduce the permutation entropy value. Then, the reconstructed signal undergoes fully adaptive noise-complete ensemble empirical mode decomposition processing, and the components are superimposed to obtain experimental data consistent with the permutation entropy of the simulated signal. The system includes a data acquisition module, a data processing module, and a data output module. This invention can filter out noise from complex measured data and extract accurate water hammer pressure and pressure pulsation, which is fundamental for analyzing the actual characteristics of the power station's transient process and improving the accuracy of transient process inversion and prediction.

The invention discloses an intelligent identification method for a failure mode of a spiral anchor foundation under a horizontal load, and relates to the technical field of geotechnical engineering and intelligent monitoring. The method comprises the following steps: acquiring load and displacement data, and calculating an arrangement entropy value of a stiffness time sequence window; based on the entropy value, utilizing a confidence coefficient accumulation mechanism to identify a steep drop type or slow deformation failure mode; and determining the ultimate bearing capacity by adaptively selecting a judgment criterion according to an identification result. The method is used for solving the problem that the bearing capacity is inaccurately judged due to the fact that brittleness sudden change and ductility progressive failure are difficult to distinguish by an existing single standard.

The invention discloses a heat pump intelligent control system based on edge calculation, and the system comprises a working condition collection and preprocessing module which is used for collecting operation working condition data, and carrying out the preprocessing to generate a preprocessing time sequence; the entropy feature extraction module is used for generating an entropy feature vector based on a multi-scale permutation entropy algorithm; the network prediction module is used for inputting the improved Times Net network to obtain a prediction result; the trigger optimization module is used for calculating the total energy efficiency cost of each candidate defrosting moment and selecting an optimal defrosting trigger moment; the mode selection module is used for selecting a target defrosting mode; and the execution control module is used for executing defrosting according to the target defrosting mode and controlling the unit to recover normal operation. By introducing the multi-scale permutation entropy algorithm and improving the Times Net network, intelligent optimization of the defrosting opportunity and the defrosting mode of the heat pump is achieved.

The invention discloses a GNSS deformation monitoring denoising method based on improved CEEMDAN and fuzzy permutation entropy, and relates to the technical field of mode decomposition denoising. Comprising the following steps: data acquisition: acquiring original GNSS deformation monitoring data which comprises position quantities in N, E and U directions, comes from a plurality of GNSS observation stations and comprises a plurality of interference noises; and CEEMDAN decomposition: performing complete ensemble empirical mode decomposition on the original GNSS deformation monitoring data to obtain a plurality of intrinsic mode function IMF components. According to the method, the CEEMDAN is improved to optimize the noise intensity coefficient and the number of decomposition times, so that the modal aliasing phenomenon of a traditional CEEMDAN method is effectively reduced, and IMF component redundancy is reduced; the complexity and the noise ratio of each IMF component are quantified by combining fuzzy permutation entropy, high and low frequency modality accurate classification is realized by matching with a dynamic threshold mechanism, and the problems that a traditional method lacks an effective noise recognition mechanism and depends on experience to set a classification standard are solved.

The application discloses a track fault diagnosis method and system, the method comprises the following steps: calculating the sample entropy, energy entropy, power spectrum and permutation entropy of the optimal solution, selecting the optimal entropy from the sample entropy, energy entropy, power spectrum and permutation entropy according to the preset optimal entropy weight selection strategy, and extracting typical features according to the optimal entropy; constructing an improved CNN-BiLSTM-SA neural network, and extracting sequence space features according to the improved CNN-BiLSTM-SA neural network; optimizing the hyperparameters of the improved CNN-BiLSTM-SA neural network according to the Cauchy-Euclidean clustering particle swarm optimization algorithm, and obtaining a track fault diagnosis model; fusing the optimal solution, typical features and sequence space features of the rail vibration signal to obtain fusion features, and inputting the fusion features into the track fault diagnosis model, so that the track fault diagnosis model outputs a track fault diagnosis result. The accuracy and efficiency of track fault category diagnosis can be improved.