70 results about "Maximal information coefficient" patented technology

The invention relates to the field of new energy, and discloses a wind power generation power prediction method based on space-time diagram convolution and gating attention, and the method comprises the steps: obtaining the geographic position information, meteorological information and historical wind power generation power data of each fan in a wind power plant, and obtaining the normalized data; constructing a dynamic adjacency matrix based on the maximum information coefficient among the historical power data of each fan in the wind power plant, and generating a graph structure; a node set of the graph structure corresponds to each station in the wind power cluster, and an edge set is dynamically determined by a maximum information coefficient of historical power data between the stations; spatial feature extraction is carried out by using a graph convolutional network, and a graph structure learning module is introduced; and inputting the sequence output by the graph structure learning module into a gating circulation unit, introducing an Informer encoder based on a sparse attention mechanism, and generating a wind power prediction result of a future time step. According to the invention, high-precision prediction of the wind power generation power in a multi-fan scene is realized.

The invention discloses an integrated energy load prediction method and system based on modal decomposition and TCN-Transform fusion, and aims to solve the key problems of low prediction precision, insufficient utilization of meteorological factor and load correlation, insufficient optimization of a model structure and the like in integrated energy system load prediction. The method comprises the following steps: comprehensively acquiring electric load, cold load, thermal load and various meteorological data, acquiring different types of data by adopting a special device, and then preprocessing the data; using a maximum information coefficient correlation analysis method to screen remarkably related meteorological features; determining an optimal decomposition parameter in combination with variational mode decomposition and a crown porcupine optimization algorithm; a prediction model fusing TCN and Transform advantages is constructed, and the structure is optimized according to load prediction characteristics; the precision and stability of load prediction of the integrated energy system are remarkably improved, the relation between the integrated energy load and external factors is reflected more comprehensively, and a reliable load prediction basis is provided for optimized operation and management of the integrated energy system.

The invention discloses a wind driven generator temperature monitoring method based on a graph space-time attention network, and the method comprises the following steps: carrying out the preprocessing of collected SCADA data, and obtaining a data set; each sensor is used as a node, the top-k neighbor relation of each node is calculated, edge weights among the nodes are calculated through a Gaussian kernel function, a weighted adjacency matrix is constructed based on the neighbor relation and the edge weights of all the nodes, and therefore a multi-sensor time sequence diagram of the wind driven generator is obtained, time sequence characteristics are given to the nodes by time sequence data collected by different timestamps, and a multi-sensor time sequence diagram of the wind driven generator is obtained. Forming a space-time diagram structure, and outputting time sequence characteristics of each sensor; a graph attention network is introduced into wind driven generator temperature state monitoring, and global and connectivity characteristics of a multi-sensor network are modeled. According to the method, the generator temperature prediction precision is remarkably improved by fusing a graph space-time two-dimensional attention mechanism and key variable screening, redundant variables are eliminated by adopting the maximum information coefficient MIC, and noise interference is reduced.

The invention discloses an SNCR outlet NOx concentration prediction method and system based on a random forest, and the method comprises the steps: S1, obtaining the operation data of an SNCR system, selecting a plurality of input variables affecting the outlet NOx concentration, and carrying out the normalization processing of the input variables; s2, carrying out maximum information coefficient analysis on the normalized data set, determining the delay time of each input variable relative to the NOx concentration of the outlet, and reconstructing the data set according to the delay time; s3, dividing the reconstructed data set into a training set and a test set, constructing a random forest model, and initializing model parameters; s4, optimizing parameters of the random forest model to obtain an optimal parameter combination; and S5, predicting by using the random forest model of the optimal parameter combination to obtain a predicted value of the NOx concentration at the outlet of the SNCR system. The method has the advantages of high prediction precision and the like.

The invention discloses a power system probability load prediction method, system and device, and a storage medium, relates to the technical field of hydrogen energy ship power system load prediction, and aims to solve the technical problems that multi-source data and physical information rules are not integrated and multi-scale chaos in an HPV complex operation environment is not considered in the prior art. The method specifically comprises the steps of collecting and preprocessing multi-source data; screening strong correlation data by using the maximum information coefficient, and reconstructing multi-source data into a unified spatial-temporal characteristic matrix; constructing an electrical and environmental parameter chaos model based on a Lorentz dynamic equation as a physical constraint term of a loss function; a BERT-PINN framework with an attention mechanism is established, and multi-step probability prediction is realized through two-stage training. According to the method, the data driving model and the physical information rule of the multi-source data are effectively integrated, the feature fusion problem of the multi-scale chaotic features is solved, and the model prediction performance is improved.

A photovoltaic power generation associated physical quantity mining method based on historical time series data analysis, and a related apparatus. The method comprises: acquiring historical time series data of multiple dimensions during photovoltaic power generation; calculating degrees of mutual information between the historical time series data of the multiple dimensions of photovoltaic power and the photovoltaic power; selecting the historical time series data of which the degree of mutual information satisfies a set requirement to serve as data related to photovoltaic data; and using a linear discriminant analysis (LDA) method to perform feature dimension reduction on the selected historical time series data to obtain data having undergone dimension reduction processing. In the present invention, by using a maximal information coefficient (MIC) feature selection method, data most related to photovoltaic power generation is selected from original feature variables, and then by using an LDA-based feature dimension reduction method, high-dimensional data is mapped to a lower-dimensional space. By means of the MIC feature selection method and the LDA-based feature dimension reduction method, the accuracy of photovoltaic power generation prediction is effectively improved.

The invention discloses an air conditioning system-oriented multi-control object modeling method, which comprises the following steps of: acquiring multi-source operation data acquired by an air conditioning system sensor, performing principal component analysis and time shift correlation analysis on the multi-source operation data, and screening out a core input variable corresponding to a target control object; the target control object comprises virtual indoor temperature, air source heat pump unit energy consumption, water pump energy consumption and fan energy consumption; according to the time-shifting correlation analysis, the lag step length of each variable is determined through the maximum information coefficient, and key time sequence features are screened; and on the basis of the screened core input variables, data driving models of all the control objects are constructed, and the combined type multi-control-object simulation framework is used for predicting the energy consumption and the environment state of the air conditioning system. According to the invention, the dependence of a test method on an actual system and hardware is overcome, and the test cost and risk are reduced. The source code can be tested before system and hardware configuration, and the problem of frequent equipment control caused by testing in an actual system is avoided.

The invention provides a converter station power supply side wind power and photovoltaic novel power supply output prediction model and method, and belongs to the field of electric power prediction. Data are processed and analyzed through various technologies such as an isolation forest algorithm, autocorrelation, partial autocorrelation analysis, Pearson correlation coefficients and maximum information coefficients. And then, constructing a power generation output prediction model of wind, light and water renewable resources by adopting a bidirectional long-short-term memory network based on an Attention mechanism, and realizing accurate prediction of future new energy power generation output. According to the method, various data processing and prediction technologies are integrated, various factors influencing new energy power generation output are comprehensively analyzed, the prediction accuracy and reliability are improved, and the method plays an important role in promoting optimal scheduling and operation safety of a power grid.

The invention discloses a multivariable cross-correlation spatial-temporal feature fusion dissolved oxygen content prediction method and system. The method comprises the following steps: acquiring a water quality sample data set; aiming at the water quality sample data set, screening an influence factor sequence of which the correlation with dissolved oxygen is greater than a preset value by adopting a maximum information coefficient, and screening a dissolved oxygen sequence; standardizing the screened influence factor sequence and the dissolved oxygen sequence to obtain standardized data; the standardized data are adopted to train a dissolved oxygen content prediction model, a trained dissolved oxygen content prediction model is obtained, and the dissolved oxygen content prediction model comprises a spatial feature extraction network, a local feature extraction network, a multi-channel attention network and an encoder-decoder long-short-term memory network combined with an attention mechanism; inputting to-be-detected water quality data into the trained dissolved oxygen content prediction model for prediction, and outputting a dissolved oxygen content prediction result at the next moment. The method can effectively improve the prediction precision of the dissolved oxygen content.

The invention discloses a day-ahead electricity price prediction method and system based on similar day adaptive screening and SHAP compensation. The method mainly comprises the following steps: preprocessing historical electricity price, load, new energy output and meteorological data; calculating the maximum information coefficient of the features and the electricity price based on a sliding window, and carrying out the self-adaptive screening of similar days through combining the clustering and grey correlation degree after dynamic weighting; the method comprises the following steps: constructing a prediction model by fusing a conditional variation auto-encoder with a multi-head attention mechanism, capturing historical sequence multi-scale time sequence characteristics and future condition information through a double-path encoder, and generating a day-ahead electricity price point prediction result; and performing feature contribution decomposition on the prediction error by using an SHAP tool, and training an error compensation model to correct an initial prediction value. The method can dynamically adapt to market changes, the prediction precision and interpretability are improved, closed-loop self-optimization is achieved, and reliable decision support is provided for electricity market transactions.

The invention belongs to the field of geological disaster prediction, and particularly provides a reservoir landslide displacement prediction method based on dynamic lag recognition and fuzzy entropy optimization, which comprises the following steps: acquiring and preprocessing landslide time sequence monitoring data; combining the distributed lag nonlinear model with the maximum information coefficient, dynamically analyzing the lag relationship between the displacement and the rainfall and reservoir water level through a sliding window, outputting a self-adaptive lag stage and constructing a lag feature set; adaptively decomposing the displacement sequence by using variation mode decomposition of fuzzy entropy optimization, determining the optimal mode number according to the minimum fuzzy entropy, and reconstructing the intrinsic mode function into trend, period and random items; the method comprises the following steps: extracting local features of a multi-lag feature space through CNN, inputting reconstructed displacement components into GRU to capture time dependence, introducing an attention mechanism to weight a key time step, and outputting a predicted value and a confidence interval through quantile regression; according to the method, dynamic lag capture, adaptive decomposition and CNN-GRU-Attention are fused, and high-precision and high-robustness prediction is realized.

The invention discloses an electricity price prediction method based on dynamic mode decomposition fusion LSTM + CKDE. The method comprises the following steps of: 1, collecting data, including historical electricity prices containing time sequence characteristics and price fluctuation indexes, power generation parameters, power market supply and demand data and external environment factor parameters; 2, performing data preprocessing, abnormal value processing and missing value interpolation on the collected data; 3, performing feature input variable screening on the data processed in the step 2 by adopting a maximum information coefficient method or a Pearson correlation coefficient analysis method; 4, performing dynamic modal decomposition on the screened feature input variables to obtain dynamic feature vectors; step 5, constructing an electricity price prediction model by using an LSTM algorithm, and inputting a dynamic feature vector; and 6, evaluating the electricity price prediction model by adopting a CKDE method. According to the invention, the accuracy of electricity price prediction is improved.

The invention provides a bidirectional LSTM photovoltaic power generation prediction method based on wavelet decomposition and double attention, and belongs to the technical field of power generation prediction. Selecting an optimal wavelet basis function by using a particle swarm optimization algorithm to carry out adaptive noise complete set empirical mode decomposition on the power sequence to obtain a multi-layer intrinsic mode function component, and carrying out adaptive denoising and power signal reconstruction according to a multi-scale permutation entropy and a Bayesian risk minimization criterion in combination with meteorological conditions; key feature variables are extracted through a maximum information coefficient, a bidirectional long-short-term memory network prediction framework is established, a feature attention mechanism and a double-path time attention structure are introduced, and when power mutation or irradiance mutation is detected, a sparse attention weight rapid reconstruction mechanism is triggered to complete prediction. The technical problem that the prediction precision is reduced when the photovoltaic power generation power changes suddenly under the cloudy weather condition is solved.

The invention relates to a method and a model for predicting the lifetime of a non-tumor peaceful patient based on clinical data. The method comprises the following steps of: collecting and sorting previous hospitalization clinical data of a non-tumor peaceful treatment death patient, and carrying out standardized pretreatment; carrying out attribute selection and reduction on the high-dimensional data from two perspectives of correlation and redundancy by using a maximum information coefficient (MIC); the method comprises the following steps: respectively carrying out attribute weighting by applying a Pearson correlation coefficient and a Spearman rank correlation coefficient; a weighted naive Bayes classification model is used for modeling; according to the method, clinical factors related to the lifetime of the non-tumor Anning treatment patient can be objectively analyzed and predicted, and guidance is provided for Anning clinical admission standard formulation and early and later treatment plans. The model can be realized in the form of a doctor workstation and the like, and the medical work efficiency and accuracy can be greatly improved.

The invention provides an evolution mode recognition method and system based on time sequence tensor segmentation, and the method comprises the steps: collecting three-order time sequence tensor data, and taking the three-order time sequence tensor data as input data; dividing the third-order time sequence tensor into a plurality of tensor segments through a sliding window; extracting a core tensor of the tensor segment based on Tuck decomposition, and performing clustering based on a time sequence weighted clustering method to obtain a coarse-grained segmentation result; optimizing the coarse granularity segmentation result based on information gain to obtain a fine granularity segmentation result; extracting correlation characteristics of each fragment based on the maximum information coefficient; and introducing a neighbor rule, and identifying an evolution mode corresponding to each fragment by adopting an unsupervised three-way clustering algorithm. The invention further constructs an evolution mode recognition system based on time sequence tensor segmentation, a data acquisition part, a time sequence tensor segmentation and evolution mode mining part and a monitoring APP part are connected with one another to form a complete system, and effective recognition of segmentation of the time sequence tensor and the evolution mode is achieved.

The present invention discloses a multi-control object modeling method for an air-conditioning system, comprising: obtaining multi-source operating data collected by air-conditioning system sensors, performing principal component analysis and time-shift correlation analysis on the multi-source operating data, and screening out core input variables corresponding to target control objects; target control objects include virtual indoor temperature, energy consumption of air-source heat pump units, water pump energy consumption, and fan energy consumption; time-shift correlation analysis determines the lag step length of each variable through the maximum information coefficient, and screens out key time series features; based on the screened core input variables, respectively constructs a data-driven model for each control object, and a combined multi-control object simulation framework is used to predict the energy consumption and environmental status of the air-conditioning system. The present invention overcomes the dependence of the test method on the actual system and hardware, and reduces the test cost and risk. The source code can be tested before the system and hardware are configured, avoiding the frequent equipment control problem caused by testing in the actual system.

The invention relates to the technical field of load prediction, in particular to a load prediction method and system combining a maximum information coefficient method and deep learning. The method comprises the following steps: screening main factors influencing the load of the hydraulic turbine set to obtain the maximum information coefficient of each influence factor; taking the preprocessed data as input data of a first model, and determining basic hyper-parameters of the first model according to the input data; optimizing the first model by using an intelligent optimization algorithm to perform feature extraction so as to improve the feature capturing capability; and predicting the load of the hydraulic turbine set, and outputting a load prediction result.

The embodiment of the invention discloses a data processing method and device, a medium and a product, and the method comprises the steps: obtaining a first data set and a second data set, the first data set comprises a plurality of pieces of bad loan data, and the second data set comprises a plurality of preset bad loan index items used for representing bad loans; calculating a maximum information coefficient between each preset bad loan index item and each loan data item, and determining a plurality of first data items in the loan data items according to the maximum information coefficients; constructing a first matrix based on the plurality of first data items, and calculating a feature vector of the first matrix; and calculating a vector distance between a vector corresponding to each first data item in the first matrix and the feature vector of the first matrix, and determining a second data item associated with the preset bad loan index item in the loan data items according to the vector distance. According to the technical scheme provided by the embodiment of the invention, the data items associated with the bad loan indexes can be accurately reserved, and the analysis efficiency and accuracy are improved.

The invention discloses a photovoltaic module performance degradation reason determination method and device, relates to the technical field of new energy, and mainly aims to improve the accuracy of a photovoltaic module performance degradation reason determination result. According to the main technical scheme, the method comprises the steps of obtaining power operation data and infrared imaging data of a photovoltaic module; extracting a first feature vector and a second feature vector from the power operation data and the infrared imaging data respectively; on the basis of a maximum information coefficient algorithm, calculating nonlinear correlation intensity between each electric infrared feature pair in the first feature vector and the second feature vector, and constructing an electric heating correlation matrix according to the nonlinear correlation intensity; based on an interpretable machine learning model, quantifying marginal contribution of each power infrared feature pair in the electrothermal incidence matrix during prediction of performance degradation of the photovoltaic module to obtain contribution values of each feature pair; and according to the contribution value and in combination with a preset attenuation mechanism verification rule, determining a reason for performance attenuation of the photovoltaic module.

The invention discloses a gas insulation cabinet partial discharge monitoring method and device based on edge calculation, and relates to the technical field of gas insulation cabinets. The method comprises the following steps: collecting environmental data and background electromagnetic noise signals of the gas insulation cabinet, calculating an environmental noise correlation coefficient by using a maximum information coefficient method, combining an environmental deviation value to obtain a comprehensive environmental disturbance index, and correcting a preset background noise threshold value to obtain a corrected noise threshold value; if the real-time electric signal amplitude exceeds the corrected noise threshold, marking the data as partial discharge signal data; denoising the partial discharge signal data by adopting an improved ensemble empirical mode decomposition adaptive noise method, and extracting a discharge feature vector; calculating the mahalanobis distance of each feature vector in the discharge feature vector sequence, obtaining the discharge similarity, obtaining a homologous discharge link, extracting the feature data of the homologous link, inputting the feature data into a BP neural network model based on a dung beetle optimization algorithm, outputting the type of partial discharge, and carrying out the early warning, thereby achieving the monitoring of the partial discharge of the gas insulation cabinet.

The embodiment of the invention provides a meteorological data processing method and device and electronic equipment. The method comprises the following steps: acquiring generated power and at least one meteorological factor of N new energy power generation equipment at a historical moment; determining the correlation between each meteorological factor and the generated power according to the symmetry uncertainty; according to the sequence of the correlation from high to low, carrying out descending sorting on the meteorological factors for the first time; sequentially determining a maximum information coefficient value between each meteorological factor after one descending sorting and the generated power, and taking the maximum information coefficient value as a correlation score of the meteorological factors; and according to the correlation score of each meteorological factor and a Markov blanket method, redundant meteorological factors in the meteorological factors are screened out to obtain residual meteorological factors, and the residual meteorological factors are used for predicting the generated power of the new energy power generation equipment. According to the method, the meteorological data is screened, and the screened meteorological data is utilized, so that the prediction accuracy of the new energy power generation power can be improved.

This invention discloses a random flood forecasting method based on machine learning and cloud models. The steps are as follows: using typical historical floods as basic data for model calibration and testing, selecting classification indicators that meet the conditions, and classifying historical floods based on a self-organizing map neural network (SOM); using the maximum information coefficient method (MIC) to screen the impact factors of classified floods, and establishing a random flood forecasting model based on different machine learning methods; for different types of floods, solving the fusion weights of different forecasting models based on the cloud model, and weighting the simulation results of each model to obtain the model integrated forecast result; analyzing and calculating the relative forecast error, and establishing the joint distribution function of the relative forecast errors at adjacent moments based on the Copula method; finally, obtaining real-time online flood information to achieve random flood forecasting. This invention can improve the accuracy of flood forecasting and provide a new approach to hydrological prediction and forecasting.

The application discloses a kind of wind-driven generator temperature monitoring methods based on graph space-time attention network, comprising the following steps: the SCADA data collected are preprocessed, obtain dataset;With each sensor as node, the top-k neighborhood relationship of each node is calculated, the edge weight between nodes is calculated by Gaussian kernel function, the weighted adjacency matrix is constructed based on the neighborhood relationship and edge weight of all nodes, so that the wind-driven generator multi-sensor time series graph is obtained, the time series data collected at different time stamps is assigned to node time series feature, form space-time graph structure, and output each sensor time series feature;Graph attention network is introduced into wind-driven generator temperature state monitoring, modeling the globality and connectivity features of multi-sensor network.The application significantly improves the generator temperature prediction accuracy by fusing graph space-time dual-dimensional attention mechanism and key variable screening: redundant variables are removed by using the maximum information coefficient MIC, and noise interference is reduced.

The invention relates to the technical field of thermal power generation, and discloses a coal-fired power plant final-stage superheater wall temperature prediction method and system based on an improved wavelet time convolution network, and the method comprises the steps: obtaining the historical operation data of a plant-level monitoring information system, calculating the maximum information coefficient between each variable and the wall temperature, and obtaining the maximum information coefficient; selecting a variable with the maximum information coefficient greater than a preset threshold value as a key feature; constructing the key features and the wall temperature data at the current moment and the plurality of historical moments into model input features, and taking the wall temperatures at the plurality of future moments as model output features; constructing a wavelet time convolutional network model, wherein the wavelet time convolutional network model comprises an input layer, a wavelet decomposition layer, at least one hybrid expansion convolutional layer and an output layer which are connected in sequence; and training the wavelet time convolutional network model by using the model input features and the model output features to obtain a wall temperature prediction model. According to the method, the wall temperature of the final-stage superheater is predicted, an operator can take control measures in advance, and the overtemperature phenomenon is reduced.

The invention discloses a multi-source data fusion wind-solar-storage combined power generation prediction method. The method comprises the following steps: S1, collecting historical power generation data, real-time meteorological data, energy storage system state data and power grid load data of a wind-solar power station; s2, performing standardization processing on the data, screening key features through a maximum information coefficient, and constructing a feature matrix; s3, fusing multi-source data by adopting a dynamic weight mechanism, and iteratively optimizing the fusion weight of each data source based on a gradient descent method; s4, outputting a wind and light output predicted value by using a multi-modal deep neural network comprising a meteorological feature extraction layer, a time sequence feature extraction layer and a global feature interaction layer; and S5, constructing an optimal scheduling model, and generating a charging and discharging strategy in combination with constraint conditions of the energy storage system. The invention relates to the field of new energy power systems, in particular to a multi-source data fusion wind-solar-storage combined power generation prediction method, which has the following advantages: 1, high-precision prediction; 2, intelligent scheduling; and 3, the adaptability is high.

The application discloses a data-driven traditional Chinese medicine manufacturing process parameter optimization method, which comprises the following steps: calculating the maximum mutual information coefficient (MIC) between the historical process parameters and product quality of a traditional Chinese medicine product production process, constructing a quality prediction model (PM-AdaBoost), calculating an adaptive function according to the maximum mutual information coefficient and the mean square error of the quality prediction model, initializing a particle swarm, calculating the adaptive function, and updating the speed and position of the particle in the process parameter search space through multiple iterations to obtain the key process parameters in the traditional Chinese medicine product production process and the optimized quality prediction model, and further taking the mean square error of the optimized quality prediction model as the adaptive function and utilizing a particle swarm optimization algorithm to obtain the optimized key process parameters. The application measures the linear and nonlinear relationship between variables through the maximum information coefficient, selects the maximum information coefficient and the quality prediction mean square error as the standard for screening the key process parameters and constructing the quality prediction model, and has an absolute advantage in accuracy. Based on the quality prediction model, the key is optimized through the particle swarm algorithm, and the particle swarm has an absolute advantage in convergence speed as the process parameter optimization algorithm.

The invention discloses a wind power short-term prediction method based on feature selection and improved HO optimization. The method comprises the following steps: S1, collecting wind turbine generator data and local meteorological data of a wind power plant; s2, performing normalization preprocessing on the data, and dividing the data into a training set and a test set according to a ratio of 9: 1; s3, screening characteristics with high correlation with the wind power by adopting a maximum information coefficient (MIC); s4, optimizing a hyper-parameter of the Transform-BiLSTM model by using an improved Heima algorithm (IHO); and S5, verifying the optimized model on a test set, and outputting a prediction result by adopting a sliding time window strategy. The method aims at solving the problem that in existing wind power prediction, a traditional optimization algorithm is insufficient in combination model hyper-parameter optimization capacity.

The invention discloses an electrical circuit fire early warning method and system, and belongs to the technical field of circuit fire early warning, and the method comprises the steps: obtaining pyrolysis particles, characteristic gas concentration, temperature and air pressure data of an electrical connection point; carrying out data preprocessing on the collected multi-source data; preprocessing the multi-source data, denoising, unifying timestamps, and forming feature-enhanced data; on the basis of the data after feature enhancement, the nonlinear correlation degree of each parameter is calculated through the maximum information coefficient, an adjacent matrix is generated, and finally a dynamic graph structure reflecting multi-parameter space-time correlation is constructed; carrying out multi-modal feature fusion and early warning; inputting the dynamic graph structure into a space-time graph convolutional network, calculating an abnormal score of a finally output space-time feature vector through an isolation forest algorithm, and generating a fault early warning signal; compared with an existing electrical circuit light-emitting connection fault monitoring means, the electrical circuit light-emitting connection fault monitoring device has the capability of monitoring at the initial stage of a fire disaster, and extremely early warning of the electrical fire disaster is effectively achieved.

The application belongs to the technical field of sub-industry load forecasting, and provides a sub-industry load forecasting method and system based on type analysis and feature reconstruction, which obtains power load data and meteorological feature data of each industry, and carries out pretreatment; classifies power load of different industries; calculates the maximum information coefficient between each meteorological feature variable and power load of different categories, selects features according to the value of the maximum information coefficient, and reconstructs a meteorological feature matrix; takes historical load data in a set time period of a day to be predicted as model input features, and combines them into the feature matrix; takes the combined feature matrix as input and load value as output, trains a deep learning model; selects a corresponding feature matrix according to the power type of a prediction target, and uses the trained deep learning model to perform day-ahead load forecasting. The application can realize day-ahead load forecasting of different industries.

The invention provides a two-stage fan equipment quality abnormity tracing method based on hierarchical information characterization, and relates to the technical field of fan operation and maintenance quality management and control, and the method comprises the steps: obtaining SCADA monitoring data, operation logs and operation and maintenance records of fan equipment, carrying out data preprocessing through overlapping sampling, and constructing a time sequence database; calculating the maximum information coefficient, related to the fault, of each feature in the time sequence database, and screening key features to form a feature subset; constructing a double-end Transform model, taking the feature subset as the input of the model, introducing a classification mark, and outputting a feature prediction value and fault category probability distribution; the difference between the fault sample and the normal sample is calculated based on the mahalanobis distance, the tracing key features are screened according to the contribution degree of the difference, and multi-dimensional time domain statistical indexes are extracted from the tracing key features to construct a high-dimensional feature matrix; and inputting the high-dimensional feature matrix into a tracing model represented by hierarchical information, judging an abnormal reason through a feature matrix threshold value, and outputting a tracing result.