86 results about "Linear prediction" patented technology

The invention relates to the field of biological medicine, and discloses a method and system for analyzing cough sound by using disease characteristics to diagnose respiratory diseases, and the method comprises the steps: deploying a six-microphone annular array to achieve the precise positioning and triggering of a sound source; self-adaptive spectral subtraction and Wiener filtering cascade are adopted to enhance the audio; segmenting a cough segment based on energy envelope; fusing the Mel-cepstrum, the linear prediction residual error, the harmonic energy ratio and the transient zero-crossing rate to construct a pathological feature matrix; extracting local, medium-range and global time sequence features through a three-branch parallel convolutional network; inputting a disease specific classifier to discriminate asthma, pneumonia and laryngitis respectively, and applying a feature decoupling regular term to improve interpretability. The system correspondingly realizes the modularized processing flow. According to the method, the cough sound collection quality and the disease subtype recognition accuracy in a complex environment are improved, meanwhile, the thermodynamic diagram is output to assist clinical decision making, and the diagnosis credibility and practicability are enhanced.

An image blur correction device acquires a blur detection signal, and separates it into a high frequency band signal component and a low frequency band signal component using an HPF and an LPF. A high frequency side prediction processing unit acquires an output of the HPF, and a low frequency side prediction processing unit acquires an output of the LPF via a down-sampler. A prediction processing unit updates a filter coefficient of a prediction filter using an adaptive algorithm, and performs linear prediction on the blur detection signal. An adder adds an output of the high frequency side prediction processing unit to an output of the low frequency side prediction processing unit via a up-sampler, and outputs a superimposed output signal. Image blur correction control is performed on the basis of a superimposed output signal.

The invention provides a cloud sensing shared information fusion method for a vehicle and road cloud cooperative system. The method comprises the steps that the vehicle and road cloud cooperative system comprises a cloud, a vehicle end and a road end; the cloud end obtains environment sensing information from other terminals through network communication; a space-time two-dimensional calibration system is constructed, and the space-time two-dimensional calibration system is adopted to calibrate the environmental perception information; dividing a unified global ID for each target by adopting a global target feature matching method, and performing redundancy removal processing on the calibrated environmental perception information by adopting a confidence evaluation comprehensive redundancy removal mechanism; performing pre-estimation compensation on the environment perception information after redundancy removal by adopting a model based on state estimation and kinematics; transmitting the compensated information to a corresponding terminal by adopting a sensing information routing sharing strategy based on the global ID to complete information sharing; according to the method, a resampling optimization strategy and a collaborative prediction correction algorithm are adopted, compared with a traditional linear prediction compensation method, situation information real-time performance and prediction accuracy are remarkably improved, and timeliness and reliability of follow-up decisions are effectively guaranteed.

The present application relates to a kind of place recommendation method based on hypergraph neural network and diffusion model, interest point recommendation model is constructed, interest point recommendation model successively includes local trajectory flow hypergraph module, space-time feature coding, multi-dimensional feature fusion network, global hypergraph representation learning module, feature optimization module, aggregation layer, frequency domain learning layer and linear prediction layer.Analysis of the long trajectory of user, and it is divided into space-time region, constructs three global hypergraphs, aims at comprehensively capturing the overall behavior pattern of user.In order to better optimize trajectory intention representation, propose feature optimization module based on improved diffusion model.Introduce multi-dimensional global representation to ensure a more stable and controllable reverse process, and use feature normalization and improved Transform network, enhanced diffusion model is more suitable for recommendation system.Loss function is designed to train interest point recommendation model, and the interest point recommendation model trained is used to recommend next interest point for new user.

This application relates to a real-time power supply and demand forecasting method and system based on a cloud-native architecture. The method includes: deploying a data access service in a cloud-native cluster using containerized microservices to receive real-time supply and demand data streams and historical time-series data from a power trading system; writing the data streams to distributed storage and pushing them to the forecasting pipeline via a message queue; performing timestamp alignment, missing data handling, normalization, and smoothing / denoising on the supply and demand data by a preprocessing service to obtain a low-noise supply and demand sequence; updating model parameters in a rolling window by an ARIMA forecasting service and outputting linear forecast values ​​as the first forecast result; calculating the forecast residuals based on the first forecast result and the actual observations, constructing residual time-series samples, and outputting residual forecast values ​​by an LSTM forecasting service; and superimposing the first forecast result and the residual forecast values ​​by a fusion service to obtain the real-time supply and demand forecast result and publishing it to the real-time trading business interface.

The application discloses a bone conduction speech conversion method based on spectral envelope mapping, comprising the following steps: pre-processing and linear prediction analysis of the bone conduction speech signal, and calculating the LP filter coefficient; mapping the LSF coefficient of the air conduction speech signal corresponding to the bone conduction speech signal by using the trained neural network; controlling the minimum error of the original bone conduction speech signal and the synthesized air conduction speech signal according to the timbre weighting characteristic of the bone conduction speech characteristic; estimating the integer pitch of the bone conduction speech signal through the timbre weighting filter, obtaining the reference signal by passing the linear prediction residual signal through the timbre weighting filter, estimating the fractional pitch to obtain the adaptive codebook vector; obtaining the new reference signal by subtracting the adaptive codebook vector from the reference signal, searching for the optimal excitation in the fixed codebook; synthesizing the air conduction speech signal by combining the optimal excitation and the LP filter of the air conduction speech signal, and correcting the air conduction speech signal.

The application provides an artificial intelligence-based carbon analysis and diagnosis method and system, which comprises the following steps: identifying and reconstructing abnormal data from original energy consumption time series data; dividing the standardized energy consumption data set into time blocks in time sequence, mapping the potential representation of the time block into a discrete token sequence through a time convolution network encoder; inputting the discrete token sequence into a preset BERT model for self-supervised pre-training; fine-tuning the linear prediction layer using labeled historical energy consumption data, outputting energy consumption or carbon emission prediction values, and performing energy efficiency analysis and diagnosis based on the energy consumption or carbon emission prediction values. The application can effectively process multi-source heterogeneous device energy consumption data, improve the prediction accuracy and generalization ability in cross-device type scenarios, and provide reliable diagnosis basis for device-level carbon management.

The application discloses a voltage stability margin calculation method considering a control mode of a photovoltaic power station, and adds modeling consideration of a reactive power-voltage control mode of the photovoltaic power station in voltage stability margin calculation. In a continuous power flow calculation process, parameterized power flow equations are obtained by extending node voltage with the fastest voltage drop. Meanwhile, in a prediction link in the continuous power flow calculation process, a hybrid prediction method is adopted. In the case that voltage margin is large, nonlinear prediction is adopted to accelerate the calculation speed. In the case that voltage stability limit is approached, linear prediction is adopted. The voltage stability margin calculation method fully considers the influence of the control mode of the large-scale photovoltaic power station on voltage stability, and improves the calculation efficiency and the calculation precision.

The invention discloses a speckle noise detection and removal method based on sound wave-laser cross-medium communication, and the method comprises the steps: analyzing and recognizing a noise position through a sliding window based on a double-feature joint detection mechanism of a kurtosis ratio and a Teager energy operator; adaptive boundary expansion is carried out on each detected noise position, and adjacent noise positions are combined to form continuous noise segments; processing the noise segments in parallel by adopting two methods of bidirectional linear prediction and empirical mode decomposition, and respectively generating prediction signals of the noise segments; according to the local signal-to-noise ratio and boundary continuity of the prediction signals, fusion weights of the two prediction signals are calculated in a self-adaptive mode, the two prediction signals are subjected to weighted fusion, and a fusion signal is obtained; endpoint continuity matching is carried out on the fusion signal through linear transformation, smooth connection of the repair section and the original signal is ensured, and speckle noise removal is completed. According to the method, speckle noise caused by dynamic water surface disturbance can be detected and effectively suppressed, and the integrity and definition of signal transmission are remarkably improved.

A hybrid learning method for intracranial electroencephalogram (EEG) signal processing based on contrastive learning and mask reconstruction is proposed. After acquiring EEG signals offline and constructing a training set, an IntraBraM network is built, comprising a convolutional network block encoder, a Transformer encoder, a decoder, and a linear prediction layer. Following contrastive and mask reconstruction training, the trained IntraBraM is used for real-time EEG signal classification online. This invention addresses both the pre-training paradigm and model structure design, creating a pre-training paradigm and model structure adapted to the intracranial EEG modality. This enhances the model's performance on downstream tasks within the intracranial EEG modality, provides robustness to the spatial coordinates of adversarial electrodes, and improves generalization ability across subject settings.

The present application relates to the field of ocean engineering and simulation modeling technology, especially to a kind of underwater vehicle digital twin synchronization method and system based on predictive compensation, the method comprises the original attitude data of underwater vehicle is acquired, dead zone threshold is dynamically adjusted based on the motion energy of vehicle, and the original attitude data is preprocessed according to dead zone threshold, the received data packet is mapped to the original position by time and space sliding window cache pool according to generation time stamp, and standard state frame is generated after missing data is filled;Standard state frame is pushed to digital twin visualization terminal;Visual terminal carries out predictive compensation rendering, completes digital twin synchronization, including combining hydrodynamic damping model and weighted fusion algorithm, drive virtual model smooth motion, linear prediction interpolation driving algorithm is used in digital twin visualization terminal in the present application, ensure the continuous motion trajectory of underwater vehicle virtual model, significantly improve the reality and operability of shore-based monitoring.

The invention relates to the technical field of manhole cover monitoring, in particular to a manhole cover comprehensive environment monitoring system based on the Internet of Things, which is characterized in that a manhole cover displacement value is calculated point by point in a time window and is subjected to weighted stacking with a preorder trend curve to form a fusion sequence, and then the fusion sequence is input into a long short-term memory network to complete nonlinear prediction; an output result is compared with a threshold value interval section by section, it is ensured that abnormity judgment is achieved in a continuous fragment, through combination of time sequence prediction and nonlinear learning, unified modeling is achieved on displacement trend change and environment trend, the continuity and accuracy of abnormity judgment are improved, the displacement and the inclination angle of the well lid are synchronously judged in a trend set, and the safety of the well lid is improved. According to the method, the initial signal is triggered, the signal and the gas sudden change difference value are accumulated, features are extracted through the convolutional neural network, matching is completed, and the high-risk signal is output, so that sensitive capture of sudden abnormity is enhanced, the probability of missing report is reduced, and the response timeliness under the sudden situation is improved.

This invention belongs to the field of deep learning and time series analysis technology, specifically relating to a multivariate time series prediction method and apparatus based on spatiotemporal feature fusion. The method includes: acquiring multivariate traffic time series data; processing the traffic time series data; dividing the processed traffic time series data into overlapping patches, and generating patch embedding sequences through linear mapping; applying bimodal temporal attention to the patch embedding sequences to obtain fused attention features; generating a time-varying adjacency matrix based on a learnable node embedding matrix through dynamic graph construction, performing graph convolution to obtain a time-domain graph propagation result, and performing a fast Fourier transform, multiplying by a learnable scaling factor, and then performing an inverse transform to obtain an inverse transform time-frequency result; adding the time-domain graph propagation result and the inverse transform time-frequency result to obtain the final spatiotemporal features; flattening the final spatiotemporal features, and generating predicted values ​​for each variable within a future prediction window using a linear prediction head.

The application discloses a kind of FSI dynamic ranging methods based on high-order linear prediction-minimum mean square error, mainly solve the problem of slow speed of existing FSI ranging system to the distance to be measured solution, insufficient dynamic measurement capability.Solution includes: 1) construct to generate the optical frequency scanning interference ranging system required for distance solution interference signal;2) set the sweep rate of laser, so that it carries out optical frequency continuous tuning output, after interference, generates the sinusoidal interference signal that changes continuously on time domain after detection;3) the data acquisition device in FSI system carries out real-time acquisition to sinusoidal interference signal, and sample point is transmitted to measurement module;4) measurement module utilizes high-order linear prediction-minimum mean square error cascade algorithm to carry out real-time prediction to sampling data, and utilizes the interference signal frequency obtained to complete the real-time solution of distance.The application can make the distance solution speed of FSI system significantly improve, effectively improve the ranging rate.

Methods and apparatus prepare medical or therapy data, such as respiratory therapy data for electronic communication to a server system, such as a monitoring system (100). The data may be accessed. Low-pass data may be generated by applying an anti-aliasing filter to the data. Low-rate data may be generated by applying a down-sampling filter to the low-pass data. Encoded data may be generated by performing one or more of intermediate floating-point interpolation, simple linear predictive delta encoding, and / or Rice-Golomb encoding on the low-rate data. The encoded data may be packaged as compressed data with a compression header.

The invention discloses an unmanned aerial vehicle countering autonomous tracking system based on visual detection, relates to the technical field of unmanned aerial vehicle countering, and constructs a unique rotor visual fingerprint of each unmanned aerial vehicle by capturing rotor micro-motion visual features such as rotation frequency, blade swing amplitude, rotor blade reflective features and blade edge micro-deformation of the rotor of the unmanned aerial vehicle. The feature processing module performs normalization and dimensionality reduction processing on extracted features, effectively unifies different feature dimensions and eliminates redundant information, and the autonomous tracking module uses rotor visual fingerprints as core matching features and adopts a cosine similarity algorithm and a linear pre-judgment formula to realize accurate target identification. Precise identification and continuous and stable tracking of an unmanned aerial vehicle target are realized, the dual verification module combines basic features of an unmanned aerial vehicle body, and the reliability of a tracking result is further enhanced by presetting a matching threshold value and calculating a comprehensive matching degree through weighting.

The invention discloses a chemical data missing process fault detection method and system, and the method comprises the steps: converting two-dimensional data into a three-dimensional tensor through employing MDT, and carrying out the linear prediction and nonlinear prediction of an incomplete value through employing linear smooth CP and CP-SAE, and carrying out the reconstruction of normal data. And extracting a residual error and a feature space of the data in the data missing process through CP-SAE. And combining features extracted by smooth CP-decomposition and CP-SAE, and establishing three statistical magnitudes to realize fault detection. According to the method, the MDT and smooth CP decomposition method is used for solving the problems of data missing and time delay of data sample sampling, and the timeliness is high. The CP-SAE feature extraction robustness is high, and compared with a conventional linear method, the precision is high, and the response speed is high. The method is simple to operate, does not need repeated operation, and can extract the key features of the data while reconstructing the complete data set only by operating on the incomplete data set. The missing data can be effectively supplemented, the process monitoring requirement can be met, and the precision is high.

The application relates to the field of ethylene industry diagnosis, in particular to an ethylene furnace tube coking thickness prediction method and system.The method comprises the following steps: collecting ethylene furnace tube parameter time sequence data, extracting time sequence convolution features, obtaining bidirectional time sequence features through bidirectional time sequence dependence processing, and obtaining time sequence pooling features through attention pooling; linearly mapping the features to obtain a furnace tube coking thickness linear prediction value, combining a learnable nonlinear transformation with the linear prediction value to obtain a furnace tube coking thickness nonlinear prediction value; finally, fusing historical furnace tube coking thickness prediction error features, the furnace tube coking thickness linear prediction value and the furnace tube coking thickness nonlinear prediction value to calculate the furnace tube coking thickness prediction value of the ethylene furnace tube.Compared with the prior art, the linear behavior and the nonlinear behavior are combined, and the fusion strategy is adaptively adjusted based on the historical prediction error, so that the ethylene furnace tube coking thickness can be effectively predicted.

This invention relates to the field of artificial intelligence-based educational assessment, and discloses a cognitive diagnostic model and method based on knowledge text. The model includes a text feature extraction module for extracting and generating knowledge point association vectors representing the degree of association between questions and preset knowledge points; a knowledge proficiency embedding module for mapping knowledge proficiency vectors; a question attribute embedding module for mapping question knowledge difficulty vectors and question discrimination scalars; a knowledge association attention module for adjusting attention weights and generating weighted knowledge representations; and an adaptive nonlinear prediction module containing a multi-layer KANLinear structure composed of B-spline basis functions and outputting the prediction probability of correct student answers. This invention solves the problem of fragmented internal module functions in existing models and features high interpretability and independence from manual annotation.

The application discloses a kind of semi-supervised segmentation methods of dual segmentation head frequency decoupling learning and entropy change pseudo label screening combination, it is applied to image processing field, for the problem that the quality of pseudo label generation is difficult to guarantee in existing semi-supervised semantic segmentation method, and model is single for enhanced disturbance response, it is difficult to distinguish global structure change and local detail change, leading to pseudo label error is high, unstable training;Student model of the present application adopts dual segmentation head structure, respectively by prototype prediction head and linear prediction head is formed, and realizes function division by frequency domain decomposition mechanism: prototype head receives the low-frequency component feature of encoder, linear head receives the high-frequency component feature of encoder, for unlabeled sample, after applying random enhancement, the class distribution of sample before and after enhancement is predicted by two segmentation heads of teacher model respectively, and the change ratio of average prediction entropy is calculated.Based on the ratio of entropy change before and after enhancement, the reaction of prototype head and linear head is integrated, and the prediction stability after enhancement is jointly evaluated.

The invention discloses a far-field speech enhancement video call system, and relates to the technical field of speech enhancement. Comprising a millimeter wave radar module, a microphone array module, a track processing and feature extraction module, a sound source position prediction and positioning parameter conversion module, and a correlation model and dynamic compensation module. A millimeter-wave radar tracks a user movement track in real time, a user position is associated as a sound source position, and initial positioning accuracy is ensured in combination with a Doppler effect. The sound source position at the next moment is calculated in advance by a linear prediction algorithm based on a historical track, and is converted into a look-ahead positioning parameter, so that the positioning delay is reduced. A correlation model is constructed by extracting track displacement and speed characteristics and voice amplitude and frequency proportion characteristics, dynamic compensation is started when the moving speed of a user exceeds a preset threshold value or a risk index exceeds a threshold value, beam forming weight is optimized, and response time is controlled within a certain period of time. The anti-interference capability is improved through multi-modal data fusion, and the method is adaptive to mobile and strong-noise scenes.

The invention relates to the technical field of ocean engineering and simulation modeling, in particular to an underwater vehicle digital twinning synchronization method and system based on predictive compensation, and the method comprises the steps: obtaining the original attitude data of an underwater vehicle, dynamically adjusting a dead zone threshold value based on the motion energy of the underwater vehicle, and carrying out the digital twinning synchronization of the underwater vehicle. Preprocessing the original attitude data according to a dead zone threshold value, performing mapping homing on a received data packet according to a generated timestamp through a space-time sliding window cache pool, and generating a standard state frame after filling missing data; pushing the standard state frame to a digital twin visualization terminal; the visual terminal carries out prediction compensation rendering to complete digital twinning synchronization, including driving the virtual model to move smoothly in combination with a hydrodynamic damping model and a weighted fusion algorithm, and the digital twinning visualization terminal adopts a linear prediction interpolation driving algorithm to ensure that the motion trail of the virtual model of the underwater vehicle is continuous, so that the dynamic performance of the underwater vehicle is improved. And the reality sense and operability of shore-based monitoring are obviously improved.

The invention discloses a concealed conduit salt elimination project multi-objective optimization and cost prediction method and system, and the method comprises the steps: determining a soil hydraulic parameter, a water and salt migration parameter and a first prediction total cost, and carrying out the calculation of the first prediction total cost according to the soil hydraulic parameter, the water and salt migration parameter and the linear prediction cost; constructing a spatial topological feature, a water-salt dynamic feature and an economic cross feature; and inputting the spatial topological characteristics, the water-salt dynamic characteristics and the economic cross characteristics into a prediction model to obtain the underground pipe spacing, the pipeline diameter, the irrigation water amount and the prediction cost. The method solves the problems that an existing empirical model is difficult to accurately describe the nonlinear relation between parameters, actually measured data is scarce, area coverage is insufficient, and the generalization ability of the model is limited, the prediction precision is remarkably improved, multi-target collaborative optimization of the concealed conduit salt elimination project is achieved, and the design iteration period is shortened.

The invention discloses a Bluetooth sound equipment intelligent sound effect adjusting system based on adaptive noise reduction, and relates to the technical field of audio processing, and the system obtains an environment noise signal and an original audio signal, calculates an initial anti-phase sound wave signal based on the environment noise signal, and obtains an initial anti-phase sound wave signal based on a parameterized large-signal nonlinear model; the bottom layer electrical feedback parameter is converted into the transient physical displacement state of the current loudspeaker diaphragm, and the parameterized large signal nonlinear model takes the force factor, the mechanical stiffness coefficient and the voice coil inductance of the loudspeaker changing along with the displacement as physical constraints to generate a theoretical composite excitation signal; inputting the theoretical composite excitation signal and the transient physical displacement state into a loudspeaker nonlinear prediction network to obtain a pre-judgment result, when the pre-judgment result is that a physical limit threshold value is broken through, constructing a reverse distortion compensation waveform, and superposing the reverse distortion compensation waveform into a mixed signal of an attenuated initial reverse sound wave signal and an original audio signal to obtain the loudspeaker nonlinear prediction network. And outputting the final audio signal.

The invention discloses an MEMS gyroscope reliability evaluation method based on rigidity and damping competitive degradation, which comprises the following steps: decomposing a failure mode into a rigidity degradation sub-process and a damping degradation sub-process according to an MEMS gyroscope kinetic equation; wiener degradation models are established for the two degradation sub-processes respectively, a generalized linear predictor is introduced, and the coupling relation of the two degradation processes is quantified through a specific coefficient; joint estimation of a drift coefficient and a diffusion coefficient is realized by using a moment estimation method and a maximum likelihood estimation method, and a parameter estimation result is substituted into a competitive degradation reliability function, so that reliability evaluation of the high-performance MEMS gyroscope is realized.

A radar apparatus comprising one or more processors configured to: receive radar data comprising a plurality of samples representing the reflections of transmitted radar signals from one or more targets having been received by one or more antennas, the transmitted radar signals comprising a series of frequency stepped chirps; calculate a Doppler FFT based on the radar data by determining a Fourier transform of respective first-groups of the samples of the plurality of samples, wherein each first-group comprises a sample from each of the chirps of the series of chirps from a corresponding time-point during the respective chirp, to generate Doppler-FFT data; perform autoregressive linear prediction, wherein said autoregressive linear prediction is respectively applied to the samples of each chirp as represented in the Doppler-FFT data to generate extrapolated Doppler-FFT data; perform further processing to determine range and / or velocity of the targets based on the extrapolated Doppler-FFT data.

The invention belongs to the technical field of combined control of hybrid drive vehicles, and particularly relates to an intelligent energy management method and system for an emergency security vehicle, and the method comprises the steps: carrying out the collection and preprocessing of historical load power, and training an ARIMA model, and obtaining a basic average load power prediction value; based on the preset weight of the task mode and the battery temperature deviation degree, a task and energy uncertainty index is constructed and calculated to be used for correcting the linear prediction limitation of the model; in combination with the basic predicted value and the uncertainty index, calculating burst risk margin power, and superposing the burst risk margin power with the basic predicted value to obtain a corrected load predicted value; and finally, on the basis of the corrected load prediction value, multi-source energy collaborative scheduling is executed, and absolute continuity of a power supply system is ensured. The defect that a traditional prediction model lacks sudden risk assessment can be overcome, and the reliability of emergency power supply and the adaptability of the system to complex working conditions are improved.

The invention belongs to the technical field of urban environment perception and smart city management, and particularly relates to an urban green land recovery benefit evaluation method and system based on a scene-sensitive audio-visual fusion model. The method comprises the following steps: synchronously acquiring video and audio data of the urban green land, extracting a visual element proportion and three types of sound scene proportions, and constructing an audio-visual comprehensive characteristic index; linear prediction sub-models are established for different space types such as parks, residential areas and streets, and a scene sensitivity coefficient matrix is formed; during evaluation, corresponding parameters are automatically called according to scene labels to complete differentiation prediction; and finally generating a recovery benefit distribution thermodynamic diagram and a diagnosis report in combination with the geographic position. According to the method, the limitation that a traditional model cannot distinguish scene differences is overcome, and scene-divided and high-precision intelligent evaluation of urban green land recovery benefits is realized.

The invention discloses an intelligent coffee machine operation state monitoring method and system based on reinforcement learning, and the method comprises the following steps: S1, collecting and preprocessing data, and forming an operation parameter sequence; s2, carrying out dimension reduction processing on the operation parameters, and constructing an operation state sequence; s3, performing multi-step prediction on the running state sequence through a DLinear model, and generating a state prediction sequence by adopting a linear predictor; s4, calculating an instant reward value of each regulation and control behavior according to the running state sequence and the state prediction sequence; s5, an A3C algorithm is adopted, and a regulation and control instruction is generated and executed according to the instant reward value; s6, establishing a state transition group and writing the state transition group into an empirical data set; and S7, updating the DLinear model and A3C algorithm parameters according to the empirical data set. According to the method, the Markov model, the principal component analysis, the DLinear model and the A3C algorithm are fused, and the method has the advantages of being high in adaptability, high in prediction precision and good in stability.

The invention provides a smart community load prediction method and system based on ARIMA-BPNN, and the method comprises the steps: obtaining historical load time series data of a smart community, and carrying out the preprocessing of the historical load time series data; performing preliminary prediction on the preprocessed historical load time sequence data according to a pre-trained ARIMA model to obtain a linear prediction component and a residual sequence; constructing a BPNN neural network model, and predicting the residual error sequence according to the BPNN neural network model to obtain a nonlinear prediction component; and fusing the linear prediction component and the nonlinear prediction component to obtain a final prediction value. According to the method, the prediction accuracy of the community load can be remarkably improved.