335 results about "Time series dataset" patented technology

The invention discloses an operation collaborative optimization method for an optical storage direct current flexible interaction system. Comprising the steps of collecting operation data such as photovoltaic output, an energy storage state, household load power and direct current bus transmission power, fusing power market price information, and constructing a multi-dimensional time series data set; then, predicting an adjustable load capacity interval of the system based on a coupled physical constraint neural network model embedded with DC bus power balance, voltage constraint and equipment operation limitation; further constructing a state-action space, solving a Pareto frontier by adopting a multi-objective optimization algorithm, and generating a light storage and home load collaborative scheduling strategy set; then combining the real-time operation state and the prediction deviation information, applying a voltage-power droop control mechanism to carry out strategy decoupling, and generating an energy storage power correction amount and a flexible load priority control instruction; and finally, a control instruction is issued to the optical storage direct flexible system, so that collaborative optimization operation with consideration of economical efficiency, safety and comfort of the system is realized.

The invention relates to the technical field of automobile part manufacturing, and discloses an automobile injection molding part production process control system and method, and the system comprises the following modules: a data collection module which is used for collecting technological parameters, molds, raw materials and equipment operation original data, attaching timestamps, and storing the data in a database; the process parameter prediction module is used for reading original data to construct a time sequence data set, inputting the time sequence data set into a TFT model to obtain a pre-training model, and predicting a short-term process parameter fluctuation range in combination with current production working condition parameters; and the quality risk index acquisition module is used for inputting the process parameter data and the mold data into a quality risk index calculation formula to obtain a quality risk index. Through the system, data-driven comprehensive production optimization is realized, the process control accuracy and adaptability are improved, the quality control scientificity and reliability are enhanced, the intelligent level of the production process is improved, the production efficiency is effectively improved, the defective rate is reduced, and the product quality is stabilized. The problem that process control lacks system intelligence is solved.

The invention discloses a single-person abnormal behavior identification method and system based on multi-modal skeleton feature fusion, and the method comprises the steps: S1, collecting continuous RGB images and infrared thermal imaging images in a monitoring video, carrying out the human body detection and key point estimation of visible light and infrared images through employing a multi-modal fusion model of YOLOv12 in combination with Transform, and constructing a single-person posture time series data set; s2, key point speed vectors are calculated for the continuous skeleton frame sequence of each target person, skeleton key point information and speed information are fused, and an action feature sequence is formed; s3, inputting the motion feature sequence into an MPED-RNN model, decomposing skeleton motion into a global displacement component and a local attitude deformation component, and performing joint coding, decoding and prediction through a dual-channel GRU network; and S4, calculating a prediction error and a reconstruction error according to a reconstruction result and a future skeleton key point prediction result, evaluating whether the current behavior deviates from a normal trajectory, and judging whether the current behavior is in an abnormal state. According to the invention, real-time identification of abnormal behaviors of a single person in a complex scene is realized.

The invention provides an artificial intelligence network model-based early warning and monitoring method for the occurrence amount of agricultural pests, and particularly relates to a time sequence modeling method by combining a variable structure bus module VSB with a bidirectional long short-term memory network BiLSTM, which is used for predicting the occurrence dynamic state of important pests in a field and an orchard with high precision. Comprising the following steps: selecting three monitoring sites in a main crop producing area; and establishing a time sequence data set of the corresponding relationship between the average daily temperature, the rainfall and the effective accumulated temperature and the number of pests in ten days. According to the method, a hybrid neural network prediction model is constructed, the model comprises five function modules, and the model can accurately early warn annual dynamic changes of main crop main pest populations and judge peak values, and helps farmers establish efficient pest prevention and control measures.

The invention discloses an offshore rocket recovery platform attitude stability control method based on particle swarm optimization, and the method comprises the following steps: S1, collecting and preprocessing multi-source attitude data, and generating a time series data set; s2, constructing a fuzzy PID controller, and setting nine three-axis control parameters; s3, performing global optimization by adopting an improved particle swarm algorithm, and outputting an initial parameter solution; s4, introducing a zebra optimization algorithm to carry out local refined optimization; s5, constructing a collaborative optimization architecture, and fusing and outputting optimal control parameters; s6, the optimal parameters are input into a controller, and a servo system is driven to adjust the three-axis attitude; s7, monitoring disturbance amplitude, dynamically triggering a zebra strategy and feeding back the zebra strategy to the particle swarm; and S8, evaluating the control performance, and feeding back iterative optimization if the control performance does not reach the standard. According to the method, the improved particle swarm optimization algorithm and the zebra optimization algorithm are fused, so that self-adaptive optimization and accurate attitude stable control of attitude control parameters of the offshore rocket recovery platform are realized.

The invention provides an intelligent recommendation method, system and device for MySQL dynamic parameters and a medium, and belongs to the technical field of databases. The method comprises the following steps: collecting structured performance indexes in real time, extracting unstructured text knowledge, and storing the unstructured text knowledge into a data lake; performing cleaning, fusion and feature extraction processing on the acquired data, constructing a time sequence data set, and generating a multi-modal feature vector; constructing a parameter optimization model fusing the text encoder, the parameter dependency graph encoder and the reinforcement learning decision maker, and training the parameter optimization model; according to the real-time system state vector and the user optimization target, using the parameter optimization model to output parameter adjustment suggestions, generating a parameter adjustment suggestion list, and predicting potential risks; according to the parameter adjustment suggestion, a progressive adjustment strategy is adopted to execute parameter adjustment operation, and the adjusted performance index is monitored in real time; and feeding back a parameter adjustment implementation result to a parameter optimization model training process, updating a model weight, generating a parameter adjustment case and storing the parameter adjustment case in a knowledge base.

The invention discloses a cascade system online monitoring and prediction method based on a sparse self-attention mechanism, and the method comprises the steps: S1, obtaining and preprocessing multi-working-condition data of a cascade system, and constructing a time series data set; s2, performing embedded conversion and position coding on the data, and capturing sequence position information; s3, pre-fusion of adjacent time step information is realized through one-dimensional convolution; s4, a multi-head sparse attention mechanism is introduced, and a ReLU2 activation function is adopted to replace softmax so as to reduce calculation overhead; s5, completing information fusion through one-dimensional convolution, ELU activation and maximum pooling; s6, constructing an encoder containing a multi-head sparse attention mechanism; s7, designing an autoregressive decoder, and combining self-attention with cross attention; s8, adopting a HuberLoss loss function to train the model; and S9, carrying out reverse normalization on the model output to obtain a final prediction value. According to the invention, by optimizing the Transform architecture, 60 s effective prediction of the key parameters of the cascade system is realized, the prediction error is significantly reduced, and the intelligent early warning capability and the operation stability of the system are improved.

The invention provides a water chiller predictive maintenance method and system based on digital twinning, and the method comprises the steps: obtaining the evaporation pressure, suction temperature, refrigerant flow and outlet water temperature parameters during the operation of a main module of a water chiller, and carrying out the synchronous collection through multiple sensors, thereby forming a time series data set; according to the time sequence data set, a sliding window method is adopted to extract the mean shift amount, variance volatility and cross correlation coefficient of evaporation pressure and suction temperature, and a collaborative drift mode reflecting micro leakage is obtained; according to the corrected drift rate and cross correlation coefficient, generating a feature vector of a collaborative change direction among the evaporation pressure, the suction temperature and the refrigerant flow; and by calculating the Euclidean distance between the feature vector of the cooperative change direction and the health baseline, whether the micro leakage reaches the early warning triggering degree is judged, and the strength of an early warning signal is obtained.

The invention relates to the technical field of psychosomatic health management, in particular to a psychological immune system evaluation system and intervention method for cancer patients. And the data acquisition module is used for acquiring and fusing the immune biochemical indexes of the patient, the continuous physiological time sequence signals generated by the wearable device, the digital psychological assessment data and the clinical treatment stage marks, and outputting a structured multi-dimensional time sequence data set through time alignment and feature extraction operation. Through multi-modal data fusion and integrated machine learning analysis, the psychosomatic health risk of the patient can be predicted based on the continuous physiological and psychological data change trend of the patient, and corresponding intervention measures can be triggered before the patient has obvious clinical symptoms by outputting the quantized risk coefficient and the multi-stage early warning signal, so that the accuracy of the patient is improved. Therefore, an intervention mode is promoted to be converted from traditional intervention after evaluation to predictive and preventive intervention.

The invention specifically discloses a long-time-sequence high-frequency ecological environment quality space-time differentiation and driving analysis method, and relates to the technical field of remote sensing and ecological environment. The method comprises the following steps: determining an evaluation area, and constructing a macroscopic ecological safety risk evaluation framework; ecological indexes of greenness, humidity, temperature and dryness are calculated, and a time sequence data set is constructed; reconstructing a time sequence data set and constructing a remote sensing ecological index model based on the reconstructed time sequence data set; verifying the precision of the model, and evaluating the reconstruction precision by taking the screened high-quality pixels as true values; analyzing the spatial and temporal change trend and significance output by the model by using slope estimation and trend test, outputting future change continuity by using a Hurst index analysis model, and measuring spatial autocorrelation output by the model by using a Moran index; remote sensing ecological index evolution factors are researched by means of an optimal parameter geographic detector. According to the invention, the precision and timeliness of ecological assessment are improved, and decision support is provided for ecological management.

The invention discloses a full-link collaborative optimization method for flexible supply chain toughness evaluation, and relates to the technical field of supply chain intelligent management, and the method comprises the steps: obtaining supply chain multi-source data, and carrying out the preprocessing of the data, and obtaining a structured time series data set; constructing a supply chain heterogeneous graph and fusing the supply chain heterogeneous graph with the domain knowledge graph to obtain a supply chain semantic graph structure; generating a toughness index set and identifying supply chain weak links in a mode of combining rule calculation and large language model reasoning; inputting the order data into the time sequence prediction model to obtain a future demand prediction value, and calculating a supply chain risk prediction result; generating a candidate scheme set, inputting the toughness index set and the candidate scheme set into a multi-objective optimization model for solving, and generating a collaborative instruction set; executing the collaborative instruction set, collecting feedback data, and updating model parameters according to the feedback data. According to the method, intelligent evaluation of the supply chain toughness and accurate early warning of the risk are realized, and the anti-risk capability and the response efficiency of the supply chain are remarkably improved through collaborative optimization.

The invention discloses an aero-engine performance degradation prediction method driven based on a limited airborne sensor and a GA-LSTM combined architecture, a medium and a computer program. The method comprises the following steps: acquiring engine operation state data by using a standard airborne sensor with limited configuration; constructing a time series data set with state parameters as input and performance parameters as output, then constructing an engine performance prediction model based on a long short-term memory (LSTM) network, and optimizing structure parameters and training hyper-parameters of the LSTM network by using a genetic algorithm (GA); and finally, performing performance prediction and degradation trend evaluation based on the optimized LSTM model. According to the invention, through a GA-LSTM combined architecture, a complex nonlinear relationship in an engine performance degradation process can be effectively modeled, and prediction precision and generalization ability are improved. The method has good engineering adaptability and deployment feasibility, and has a wide application prospect in the field of aero-engine health monitoring and fault diagnosis.

The invention relates to an anatomy intelligent tutoring system and method based on term alignment and multi-modal verification. The method comprises the following steps: acquiring multi-modal data of a learner and implementing time axis alignment and term alignment to generate a standardized time sequence data set for feature extraction; inputting the feature vector into a long short-term memory network model, and analyzing the time sequence relevance to generate a cognitive state vector; when the conceptual error probability in the cognitive state vector exceeds a threshold value, extracting a term set to be verified based on a three-dimensional anatomical model interaction log; the term pair with the highest confusion degree is accurately positioned as an error attribution result by performing knowledge graph topological correlation analysis on the term set and calculating the confusion degree between the terms; and finally, in combination with the historical ability portrait of the learner, performing dynamic matching from the multi-modal strategy library to generate personalized tutoring content, and embedding the personalized tutoring content into a three-dimensional model interface to execute intervention, so that the effects of automatically identifying anatomical concepts from the multi-modal behavior data to understand error roots and generating targeted tutoring strategies are realized.

The invention relates to the technical field of gateway electric energy meter verification, and discloses a gateway electric energy meter metering verification method and system. The method comprises the following steps: monitoring a metering value of real-time operation of a gateway electric energy meter and a current environment condition, and synchronously querying an associated previous verification record; environmental condition data in previous records are classified and sorted to form a plurality of environmental category groups, historical deviation data and a verification moment set are extracted from each group, and a historical evaluation index set is obtained through operation; compressing each evaluation index set to obtain an evaluation index sequence, organizing the evaluation index sequence into a time sequence data set according to time, and analyzing and deriving an error increase and decrease trend; matching the current environment condition with each environment category group, determining an optimal matching group, adjusting the error trend according to the environment difference and outputting the error trend; and selecting a verification strategy according to the adjusted trend, generating a verification guidance scheme and executing a prompt action.

A computer-implemented method is provided for monitoring and / or controlling a chemical and / or biological process. The method comprises: obtaining (S10) a time series dataset comprising observations, each one of the observations being collected with respect to the chemical and / or biological process at a particular time point, wherein each one of the observations includes values of observed parameters obtained with a spectroscopic method at the particular time point and a value of an analyte parameter obtained with a reference measurement method at the particular time point; obtaining (S20) a prediction model for estimating a predicted value of the analyte parameter in the chemical and / or biological process, the prediction model being trained using at least part of the time series dataset; validating (S30) the prediction model by assessing an ability of the prediction model to predict a difference between an actual value of the analyte parameter which would be obtained with the reference measurement method at a given time point and an expected value of the analyte parameter at the given time point, using a set of observations that is not included in the at least part of the time series dataset used for training the prediction model; determining (S40) whether the prediction model is valid or invalid based on a result of the validating; and monitoring and / or controlling (S50) the chemical and / or biological process when the prediction model is determined to be valid.

The invention discloses a vertical bamboo flute teaching optimization system based on multi-dimensional fusion big data analysis, and belongs to the field of intelligent teaching, and the system comprises a multi-source sensing module which is used for obtaining an original multi-source data record and processing the original multi-source data record to obtain a unified time sequence data set; the data fusion module is used for performing space-time alignment on the unified time sequence data set by adopting a multi-modal feature fusion algorithm to construct a multi-modal database; the intelligent analysis module is used for constructing a multi-task deep learning model based on the multi-modal database and performing intelligent analysis based on the multi-task deep learning model to obtain a deviation classification result; and the interaction feedback module is used for guiding updating of the Chinese vertical bamboo flute teaching content based on the deviation classification result.

The invention discloses a building air conditioner energy consumption-electric charge-comfort level intelligent control method based on MMOE and ParetoMTL, and the method comprises the following steps: (1) collecting the cooling load data of a large commercial building air conditioner, carrying out the abnormal value detection, and completing the normalization preprocessing; (2) constructing an environment-price-behavior multi-source time sequence data set and performing grading standardization; (3) dividing a training set, a verification set and a test set according to building grouping; (4) completing feature fusion and realizing task decoupling under cooperative constraint by using an MMOE mechanism; (5) jointly training a three-branch expert network, an MLP gating network and a PCGrad shared parameter optimization model; (6) generating a multi-task prediction and Pareto solution set on the test set; and (7) evaluating prediction performance and trade-off efficiency by using a plurality of indexes. According to the method, multi-target conflict, physical consistency and Pareto solution set missing difficulty can be effectively solved, and a new scheme is provided for demand response HVAC intelligent control.

The invention provides a power transmission line operation risk prediction method based on big data mining, and the method comprises the steps: collecting the high-frequency vibration data and environment parameters of a bolt connection part of a power transmission line tower in real time, and generating a time sequence data set containing the vibration frequency, the amplitude and the temperature; a Fourier transform algorithm is adopted for the time sequence data set, a dominant frequency component of the vibration frequency is extracted, linear correction is conducted on the vibration frequency according to the thermal expansion coefficient and the temperature of the bolt material, and a frequency feature set is generated; constructing a bolt state evaluation model according to the preliminary feature set and the stress distribution feature set, evaluating the bolt state, and outputting the bolt pre-tightening force attenuation degree; and according to the state score of each bolt output by the optimized state evaluation model, calculating the overall load sharing and vibration frequency drift degree of the bolt joint, and generating a load sharing feature set.

According to the SARIMA prediction-based inland river navigation draught optimization management and control method for the ship with the overrun draught, a multi-source time sequence data set is obtained and preprocessed to obtain an input time sequence set, and the input time sequence set is processed through a constructed SARIMA model to obtain a water level prediction sequence; a ship dynamic draught prediction sequence is obtained through the constructed ship dynamic draught model based on water level prediction sequence processing, a draught safety margin judgment operator is constructed to carry out draught safety margin evaluation and risk grading, and finally a draught optimization management strategy is solved through the draught optimization management model and issued. A ship draught control closed-loop chain of prediction-calculation-evaluation-optimization-feedback is formed, through deep coupling of SARIMA time sequence prediction, ship dynamic draught calculation and draught optimization management, prospective recognition and dynamic regulation and control of draught safety margin of a draught overrun ship are achieved, and under the premise of guaranteeing navigation safety, the ship draught safety margin is effectively controlled. And the water depth utilization efficiency of the inland waterway and the ship loading efficiency are greatly improved.

The invention discloses a grassland degradation monitoring method based on remote sensing monitoring. Acquiring multi-source remote sensing data; preprocessing the multi-source remote sensing data to obtain preprocessed remote sensing data; extracting multi-dimensional feature parameters based on the preprocessed remote sensing data to obtain a multi-dimensional feature parameter set; performing time sequence analysis on the dynamic vegetation features, the dynamic soil features and the man-made interference features through the multi-dimensional feature parameter set in combination with multi-temporal observation data, and constructing a dynamic feature time sequence data set; according to the dynamic feature time sequence data set, utilizing a convolutional neural network model to carry out deep fusion on spatial features and time sequence changes in a time sequence, and generating a space-time fusion feature set; according to the space-time fusion feature set, obtaining a degradation grade division result graph; and integrating multi-source remote sensing data based on the degradation grade division result graph, obtaining a refined grassland degradation evaluation result, and monitoring grassland degradation according to the evaluation result.

The invention provides a wind turbine power prediction method based on multi-modal feature fusion, and relates to the technical field of wind turbine power prediction.The method comprises the steps that multiple types of sensors are used for obtaining multi-source sensor data, and a standardized time sequence data set is generated; establishing a first observation matrix based on the standardized time sequence data set, and constructing a weight sensing fractional order adaptive genetic algorithm to optimize the first observation matrix to obtain a second observation matrix; performing feature fusion and noise reduction on the second observation matrix by applying extended Kalman filtering and combining the working state and physical modeling of the wind turbine; constructing a bidirectional long-short-term memory network, and performing power time sequence modeling based on the multi-dimensional noise reduction feature vector to obtain an output power predicted value; and feeding back an error between an output power prediction value and a true value to a weight sensing fractional order adaptive genetic algorithm to carry out parameter iterative optimization to obtain a third observation matrix, and obtaining a power prediction value of the wind turbine based on the third observation matrix.

The invention discloses an open-web gravity dam deformation prediction and mechanism interpretation method, system, equipment and medium, and belongs to the technical field of dam and hydraulic structure health monitoring and state evaluation. Constructing the preprocessed monitoring data into corresponding feature vectors, dividing a time sequence data set, and performing XGBoost model training and hyper-parameter optimization to obtain a prediction model; calculating a corresponding SHAP value, and screening a key factor as an independent variable for model analysis; and selecting a control index to evaluate the performance of the model, and deploying the model to a dam safety monitoring system after verification so as to carry out real-time prediction and early warning. According to the method, while high-precision deformation prediction of the open-web gravity dam is realized, quantifiable mechanism explanation of the prediction result is provided, so that transparent and reliable decision support is provided for safety monitoring and early warning of the dam.

The invention discloses a water plant inlet water quality change identification method and system, and the method comprises the steps: collecting water plant inlet water turbidity, pH value, dissolved oxygen content, COD concentration, ammonia nitrogen concentration, total phosphorus concentration and other parameters, removing abnormal values, and constructing a water quality parameter time sequence data set; causal association among parameters is mined through a causal inference-based hybrid model, a weight matrix is generated, after the matrix and time sequence data are fused, bidirectional time features are extracted through a bidirectional long-short-term memory network in combination with an attention mechanism, attention weights are given, and then a gradient elevator integrated model is input; a plurality of base learners are used for parallel learning and dynamic weighted fusion of local results to obtain a preliminary recognition result, and finally the preliminary recognition result is mapped to a water quality change type space to determine a change type. The system comprises six units, a complete and efficient treatment flow is formed from water quality parameter collection to final recognition result output, and the actual requirements of a water plant for high-precision and high-reliability recognition of inflow water quality changes are practically met.

The invention provides a fault diagnosis method and device for a water electrolysis hydrogen production system. The method comprises the following steps: acquiring operation parameter data of a multi-source sensor in the water electrolysis hydrogen production system; preprocessing the operation parameter data, constructing a time sequence data set, and dividing the time sequence data set into data representation with a time topological structure by adopting a sliding window; constructing a graph structure based on the time sequence data set, and dynamically generating an adaptive adjacency matrix by calculating the characteristic difference between nodes in the graph structure so as to capture the dynamic coupling relationship between sensors in the water electrolysis hydrogen production system; importance weights of different sensor features are dynamically adjusted based on a node attention mechanism, and a sensor feature weight matrix is obtained; and inputting the data representation, the adaptive adjacency matrix and the sensor feature weight matrix into a pre-trained fault diagnosis model, and outputting a fault diagnosis result by the fault diagnosis model. According to the invention, the accuracy of fault diagnosis of the water electrolysis hydrogen production system can be improved.

The invention relates to the technical field of power system monitoring, in particular to an electricity stealing identification method and system based on multi-source data, electronic equipment and a medium. The method comprises the following steps: acquiring a running data stream and a local timestamp to obtain a plurality of groups of time sequence data sets; extracting an electrical quantity sudden change event or a non-commanding switch action event in each group of time sequence data set; constructing a multi-constraint model based on the topological connection relationship of the power line, the Kirchhoff's law and the energy conservation law; iteratively calculating the clock offset of each monitoring device relative to the system logic time; and inversely solving node current unbalance and loop power unbalance so as to output a judgment result of an electricity stealing event. Through the mode, the technical problem of cyclic dependence between event causal inference and timestamp calibration under the condition of multi-source asynchronous monitoring data in the prior art is solved, and the reliability, the accuracy and the automation level of electricity stealing behavior analysis are improved.

A method of database operations includes receiving a user query, generating a query vector embedding representative of the user query, querying a vector database using the query vector embedding, retrieving a first database vector of the plurality of database vectors based on the query and representative of a first data file corresponding to a first time and belonging to a first time-series data set, receiving a first plurality of delta encodings describing differences between vector representations of temporally-adjacent data files of the first time-series data set, identifying a second data file of the first time-series data set having a second vector representation that differs from the first database vector and corresponds to a second time, and retrieving the second data file from a database.

The invention discloses a multi-modal feature tracking method based on a traffic scene, and relates to the technical field of traffic scene feature tracking, and the method comprises the steps: collecting traffic scene RGB image data and event camera data, and constructing a multi-modal time series data set; constructing a multi-modal feature tracking model; extracting a time sequence motion feature of the event camera data, and generating a displacement prediction vector; state prediction updating is carried out, and a tracking prediction result is generated; and continuously tracking the traffic target to generate motion tracking trajectory data. According to the invention, the technical problems of poor image quality, low tracking accuracy, weak single-mode tracking anti-interference capability and difficulty in adapting to high-frequency tracking requirements caused by the influence of factors such as illumination, weather, exposure and the like during traffic scene feature tracking in the prior art are solved; the technical effects of realizing collaborative feature tracking of the RGB image and the event camera multi-modal data in the traffic scene and improving the frequency, accuracy and anti-interference capability of feature tracking are achieved.

The invention discloses a mouse embryo quality and development stage combined prediction system and method based on deep learning, and the system comprises a data preprocessing module which is used for obtaining a time sequence data set, and a feature extraction module which is used for processing the time sequence data set through a pre-trained OfficientNet model, and obtaining the feature vector of an embryo image corresponding to each time point; the time sequence feature fusion module is used for processing the image feature vectors of all embryos arranged according to the time sequence by using a bidirectional long-short-term memory network to obtain hidden state vectors of all embryo image fusion time sequence information; and the multi-task prediction module is used for inputting the hidden state vector into the embryo quality prediction and development stage classification prediction model after joint optimization to obtain a splicing result of embryo quality prediction and development stage classification prediction. According to the method, two prediction tasks of embryo quality and development stage classification can be processed at the same time by utilizing the combination of the OfficientNet model and the bidirectional long-short-term memory network, so that the model processing efficiency is improved.

Embodiments are directed to facilitating identifying seasonal frequencies. In particular, a set of candidate seasonal frequencies associated with a time series data set are determined based on ACF peaks identified in association with a representation of the time series data set. Thereafter, the filters are applied to analyze the candidate seasonal frequencies and update the candidate seasonal frequencies by removing any candidate seasonal frequencies that fail a filter. An example filter can include comparing ACF peaks with peaks associated with SDF peaks. Thereafter, a candidate seasonal frequency of the updated candidate seasonal frequencies can be identified as a seasonal frequency for the time series data set, and such a seasonal frequency can be provided (e.g., to a user or another process) for use in performing data analysis.

The invention relates to the technical field of industrial predictive control, in particular to an industrial predictive control adaptive filtering method and device based on time sequence decomposition. The method comprises the following steps: collecting historical data of a controlled variable in a preset time period in an industrial process to obtain a time sequence data set; decomposing the time sequence data set through a time sequence decomposition algorithm to obtain three types of independent components; and respectively performing feature extraction on the three types of independent components, matching a filtering algorithm based on a feature extraction result, and determining a target filtering parameter of the filtering algorithm. Compared with the prior art, the method has the advantages that the time sequence data set is decomposed into three types of mutually independent components through the time sequence decomposition algorithm, the complex features of the industrial process data are analyzed from three dimensions of the change trend, the fluctuation condition in the period and the specific residual data, and the problem that traditional filtering depends on experience is solved.