166 results about "Dynamic time warping" patented technology

Embodiments include systems and methods for adaptive monitoring of operational technology networks. In some embodiments, the method includes collecting multi-modal time series data from a plurality of wireless sensor nodes deployed near at least one operational technology asset, aligning and fusing the time series data using dynamic time warping, extracting at least one feature and at least one dependency from the fused time series data, generating, based on the extracted feature and dependency, a real-time anomaly score using a trained machine learning model, determining, based on the real-time anomaly score, at least one anomaly regarding the operational technology asset, and presenting a visualization of the anomaly at an interactive user interface.

The invention relates to the technical field of forestry intelligent management and control, and discloses a forestry optimization management and control method and system based on artificial intelligence. The method comprises the following steps: collecting multi-source environment monitoring data such as soil humidity, illumination intensity and vegetation growth indexes in a forestry area, aligning a time sequence through a dynamic time warping algorithm, and separating steady-state and transient components; detecting anomalies through an isolated forest algorithm and generating a thermodynamic diagram, and obtaining a potential disease and pest outbreak area through causal reasoning in combination with historical records; constructing a dynamic growth reference curve, and identifying a disturbance sensitive area by using a generative adversarial network and a convolutional neural network; and integrating and generating a management and control priority partition map, optimizing resource allocation through deep reinforcement learning, outputting a task sequence, and driving equipment to execute irrigation, fertilization or pest control operation. According to the method, multiple artificial intelligence algorithms are fused, accurate control over the whole forestry process is achieved, and the method adapts to the dynamically-changing forestry environment.

The invention discloses a tightening process abnormal fluctuation analysis and early warning method and system, and the method comprises the steps: collecting original torque and angle signals of a tightening process in real time, carrying out the time synchronization processing, and carrying out the abnormal value filtering and feature extraction, thereby obtaining a feature data set; then comparing and analyzing the feature data set and a pre-generated standard tightening curve, and performing anomaly judgment through a trained anomaly recognition model based on a comparison result to generate an anomaly recognition result; and finally, determining an early warning level according to an abnormal recognition result and outputting corresponding early warning information. The system correspondingly comprises a data acquisition module, a feature extraction module, an abnormity identification module and an early warning output module. According to the method and system, the dynamic time warping algorithm and the long-short-term memory network model are adopted, early-stage tiny abnormal fluctuation in the tightening process can be effectively recognized, multi-stage early warning and preventive quality control are achieved, and the quality control level and production efficiency of the tightening process are remarkably improved.

The invention discloses an intelligent monitoring and early warning system and method for project progress and cost, and relates to the technical field of constructional engineering management. The streaming data fusion module adopts an Apache Flink engine and applies a dynamic time warping algorithm to carry out time alignment on multi-source asynchronous data to realize semantic unification; the space-time diagram neural network prediction module constructs a space-time association diagram, integrates global features such as weather and supply chain fluctuation, and adaptively learns an influence weight by using a graph attention mechanism; the self-adaptive early warning module adopts a Bayesian online learning framework, an early warning threshold value is dynamically adjusted according to a historical false alarm rate and a missing report rate, the method comprises the steps of data acquisition, fusion, mapping, joint prediction and self-adaptive early warning, the problem of data islands is solved, complex space-time association is accurately captured through a space-time diagram neural network, and real-time early warning is achieved. Joint prediction of progress and cost risk is realized, false report and missing report are reduced, and real-time performance, accuracy and decision-making efficiency of engineering management and control are improved.

The invention belongs to the technical field of power system load prediction, and discloses a load prediction method and system based on similar day screening and time sequence alignment decomposition. The method comprises the following steps: acquiring a date feature vector and a meteorological feature vector of a to-be-predicted day, and a historical comprehensive feature matrix; screening a plurality of historical days with the highest comprehensive similarity from the historical comprehensive feature matrix as similar days; performing time sequence alignment on the load sequences of the screened similar days; extracting a trend component, a periodic component and a residual component of the aligned load sequence; performing trend component prediction, periodic component prediction and residual component prediction; and performing fusion based on the trend component prediction value, the periodic component prediction value and the residual component prediction value to obtain a load prediction result of the to-be-predicted day. According to the method, a high-precision load prediction model is constructed through multi-feature weighted similar day screening, dynamic time warping time sequence alignment and a multi-resolution time sequence decomposition technology, and the load prediction precision in extreme weather is improved.

The invention relates to the technical field of government affair services, in particular to an NLP entity recognition method based on semantic extension, which comprises the following steps: collecting multi-source time sequence data and generating an entrepreneurship ecological data graph through a dynamic time warping algorithm; dynamic evolution of a term library is realized by using a generative adversarial network, and a term semantic association graph is constructed in combination with a graph convolutional network; a double-path attention mechanism is deployed in a Transform encoder, and global semantics and local attention guided by terms are fused through a gating loop unit; modeling fuzzy query analysis into a Markov decision process, and optimizing a semantic extension strategy by adopting a reinforcement learning agent; multi-granularity features are extracted through a feature pyramid network, and model parameters are optimized in combination with a bidirectional long-short-term memory network and an online learning feedback loop; and finally, calculating entity service association strength by using a graph attention network, and generating an interpretable report based on a Shapley value attribution algorithm. A closed-loop learning system is formed, and the business starting policy matching accuracy is improved.

The invention relates to the technical field of touch control of touch all-in-one machines, in particular to a touch control processing system of a centralized control type touch all-in-one machine and a control method, and aims to solve the problems that in the prior art, touch events and track characteristics cannot be accurately fused, gesture types cannot be accurately recognized, and the touch control efficiency is high. Operation modules cannot be accurately divided, behavior dynamics cannot be described, and closed-loop analysis from touch input to behavior intention is difficult to realize; a gesture behavior analysis module fuses a touch event and track features, constructs a multi-dimensional vector, recognizes a gesture category through a regression model, aligns an interaction and physiological sequence, calculates a Pearson's correlation coefficient, combines a filtering threshold value to generate an emotion trend, and utilizes a dynamic time warping matching template and a clustering division operation mode. And calculating an evolution rate to describe behavior dynamics, outputting structured data, and realizing closed-loop analysis from touch input to behavior intention.

The invention relates to the technical field of artificial intelligence and music information processing, in particular to a multi-modal signal fusion music playing accuracy evaluation system. The system comprises a multi-modal signal synchronous acquisition module, a signal preprocessing and feature extraction module, a time domain alignment and event association engine, a hierarchical collaborative evaluation module and a comprehensive evaluation report generation module. Through high-precision synchronous acquisition of an MIDI instruction, an acoustic signal and a structural vibration signal, a nonlinear time domain alignment mechanism taking dynamic time warping as a core is constructed, accurate matching of a symbol event and a physical response is realized, and an alignment multi-modal event frame is formed; and collaborative quantitative evaluation of basic accuracy, technical skill and music expressive force is carried out through the hierarchical model. By adopting the technical scheme, full-link high-fidelity analysis from playing intention to physical presentation can be realized, and the accuracy, robustness and interpretability of evaluation are remarkably improved.

The invention discloses a mine underground space recycling project disaster-causing key factor identification method, and relates to the technical field of underground space energy storage. The method comprises the following steps: firstly, collecting multi-source monitoring data such as displacement, microseism, stress and the like, and carrying out timestamp alignment, denoising and interpolation completion preprocessing through improved bidirectional dynamic time warping, Hampel filtering and GRU-D algorithms; converting the data to generate an initial index set containing the underground space stability state rate and the inter-field coupling strength, and screening out an optimal index subset through 20-50 generations of Bayesian optimization search and 5-fold cross validation; constructing a multi-field coupling dynamic graph based on the subset; and finally, inputting the dynamic graph into a graph neural network, outputting a node importance degree sequence through a GNN Explainer algorithm, and determining disaster-causing key factors. According to the method, multi-source data and a multi-field coupling mechanism are fused, the recognition accuracy and the model interpretability are improved, and technical support is provided for safe operation and disaster prevention and control of mine underground space recycling engineering.

The invention discloses an unbalanced disaster risk prediction method based on a WGAN-CNN, relates to the technical field of disaster risk prediction, and aims to improve the prediction capability by optimizing feature learning of WGAN and CNN models in order to solve the problem of predicting rare disasters by using unbalanced and heterogeneous data. Data sources comprise satellite images, radars, social media and the like, and data consistency is ensured by unifying multi-modal data timestamps and aligning time sequences through dynamic time warping; then, using an improved WGAN to generate a rare disaster sample so as to enhance unbalanced data, and realizing data security sharing through encryption gradient and differential privacy technologies; in addition, based on geological similarity cross-neg region mapping weights, risk levels are evaluated and pushed in real time in combination with a CNN discriminator. According to the method, the data quality is improved through the WGAN, accurate prediction is realized by using the CNN, a real-time risk assessment tool applicable across regions is finally formed, and the rare disaster prediction capability is effectively improved.

The invention discloses a heterogeneous time series data-oriented multi-modal fusion fault prediction system and method. The system comprises a heterogeneous time series data access and alignment module; a multi-scale frequency domain decomposition module; a cross-modal attention fusion module; a time sequence dependence enhancement module; a fault feature reconstruction and prediction module; and the self-adaptive threshold decision module is connected to the fault feature reconstruction and prediction module and is used for modeling the real-time fault probability sequence based on a peak threshold exceeding method, dynamically calculating a self-adaptive early warning threshold and outputting a fault early warning signal and a health state evaluation report according to the threshold. According to the method, a dynamic time warping algorithm and a self-adaptive resampling strategy are adopted, the problem of time sequence dislocation caused by inconsistent sampling rates, transmission delay and the like of a multi-source sensor is effectively solved, a unified and high-quality three-dimensional time sequence tensor is constructed, and an accurate time reference is provided for subsequent feature fusion and modeling.

The invention discloses a visual anti-occlusion tracking method based on AIS and video fusion. The method comprises the following steps: synchronously obtaining AIS data and corresponding video data; preprocessing the AIS data, predicting latitude and longitude coordinates of the AIS data, projecting the latitude and longitude coordinates to a video pixel plane, and generating a ship AIS track; meanwhile, identifying a ship bounding box in a video frame by using a video detection algorithm, and tracking by using a three-stage association anti-occlusion tracking algorithm; the similarity between the AIS trajectory and the video trajectory is calculated through a dynamic time warping algorithm, and the correlation matching of the AIS trajectory and the video trajectory is realized by using a Hungary matching algorithm, so that a stable and anti-shielding ship tracking trajectory fusing AIS and video information is obtained. According to the invention, the problem that pure visual tracking is easy to fail under the shielding condition is effectively solved.

The invention relates to the technical field of power grid data processing, and provides a power network malicious traffic multi-dimensional feature fusion analysis system, which comprises a data acquisition module for acquiring original traffic data from power network monitoring equipment; the time sequence alignment module performs nonlinear time alignment on the network flow sequence and the service flow sequence by adopting a dynamic time warping technology; a feature extraction module extracts a protocol feature vector and a service feature vector from the aligned data through a double-flow space-time diagram convolutional network; the feature fusion module performs weighted fusion on the multi-dimensional feature vectors by using a cross-modal attention mechanism; the time sequence modeling module processes the fusion feature vector through a pre-training time sequence large model to extract high-dimensional time sequence representation; the anomaly detection module judges malicious traffic events based on the anomaly score and generates a report; the defense response module executes an active defense action according to the report. According to the invention, through multi-dimensional feature fusion and a closed-loop processing mechanism, the accuracy of malicious traffic detection of the power network is effectively improved.

The application discloses a kind of virtual image model construction method and system based on image clone, it is related to computer graphics field, including: from real-time audio and video stream of real person, the multimodal data of fusion vision, voice and action are obtained;Respectively extract facial expression, voice and action emotional data;Adopt dynamic time warping algorithm to calculate the similarity between each modal emotional data, generate the modal correlation mapping matrix of quantitative modal synchronization relationship;Adopt machine learning model to construct emotional label to limb posture expression action mapping model;According to the deviation of expression and action, the feature is adjusted back;Finally, based on the feature after adjustment, mapping matrix and mapping model, generate the virtual image that expression, voice and action are accurately aligned on time axis.The application establishes the quantitative correlation and feedback adjustment mechanism between modal, significantly improves the real sense and coordination of virtual image when cloning real person in multidimensional emotional expression.

The application discloses a kind of internal resistance big data driven safe operation method and system, method includes: the historical and real-time internal resistance data of target equipment is collected, and the internal resistance time series data set after normalization is generated by dynamic time normalization algorithm;The internal resistance time series data set is carried out multi-scale feature extraction and high-dimensional space mapping, and the internal resistance abnormal mode cluster implied in data distribution is identified using adaptive density clustering algorithm;Based on internal resistance abnormal mode cluster, multi-modal fault correlation analysis is carried out, and a fault prediction atlas is generated;According to the fault prediction atlas, a set of differentiated operation and maintenance strategies is generated, and the operation and maintenance management platform is driven to execute corresponding operation and maintenance instructions. Using the embodiment of the application, the timeliness and accuracy of fault early warning can be improved, the operation and maintenance cost is reduced, and the safe and stable operation of equipment is guaranteed.

This invention belongs to the field of data processing technology, specifically relating to a method and system for generating maintenance strategies for bridge collision avoidance facilities based on knowledge graphs. The method includes: constructing a physical topology map of the collision avoidance facilities, obtaining the stiffness weights of connecting edges and initializing node parameters; collecting strain and stress data sequences of the collision avoidance units, and calculating the rheological damage index of the collision avoidance units using a dynamic time warping algorithm; constructing a force transmission probability matrix, and obtaining the comprehensive structural risk value of the collision avoidance units through iterative calculation; and calculating the maintenance urgency index by combining the position weight coefficients and service duration of the collision avoidance units to generate a dynamic maintenance strategy. This invention, by constructing a physical topology map reflecting the physical connection relationships between collision avoidance units, and combining the calculation of hysteresis energy consumption and stress transmission deduction of viscoelastic materials, can accurately identify latent transmitted damage and assess the degree of material rheological aging, thus achieving intelligent maintenance of bridge collision avoidance facilities.

This invention discloses a method and apparatus for drill bit wear detection and remaining life prediction. The method includes: acquiring multimodal data of the drill bit; performing time-series alignment of the multimodal data using a dynamic time warping algorithm; inputting the time-series aligned multimodal data of the drill bit into an intelligent analysis center and outputting the remaining life prediction result of the target drill bit; using a visual prediction model to segment the wear region of the target drill bit; using a dynamic rating algorithm to classify the wear region; and using a digital twin simulation model, which is a multi-scale simulation system driven by digital twin simulation technology based on wear region segmentation results, classification results, real-time point cloud data of the target drill bit, and real-time sensor data, which can improve the detection accuracy, real-time performance, model generalization, and life prediction capability of drill bit wear.

This application provides a method and apparatus for detecting covert communication behavior, relating to the field of network security technology. On one hand, the method uses a dynamic time warping algorithm to determine the minimum cumulative distance between the packet length-timestamp sequence and the standard response traffic template sequence in the packet length dimension. This quantifies temporal misalignment differences, thus solving the problem of missed detection caused by the lack of temporal analysis capabilities in traditional methods. On the other hand, based on the arrival timestamp of the packet length-timestamp sequence, the method determines the differential entropy and the maximum time span of sudden events. The differential entropy can amplify the minute temporal fluctuations caused by the mechanical packet sending of tunnel traffic, while the maximum time span can identify deliberately lengthened idle periods in tunnel traffic. Combining these two methods can accurately capture gradual covert communication such as slow tunnels. Therefore, this method can improve the accuracy of detecting covert communication behavior.

The invention provides a method and system for collecting working state data of a manufacturing execution system, and the method comprises the steps: obtaining an equipment working data set, a personnel working video set and a workpiece information set, and respectively extracting a corresponding equipment working feature sequence set and a corresponding workpiece feature sequence set, performing illumination compensation, foreground segmentation and time window splitting on the personnel operation video set, and performing multi-dimensional attitude decoupling, action semantic recognition and production rhythm modeling on the personnel operation video set after the time window splitting to obtain a personnel action feature sequence set; performing dynamic time warping, beat alignment and feature binding based on the production task order to obtain a multi-modal production feature sequence set, and performing collaborative feature enhancement and dimension reduction compression to obtain a multi-modal working time sequence feature sequence set; and by taking the production task order as an edge index, constructing a dynamic hypergraph model of the multi-modal working time sequence feature sequence set, and carrying out man-machine collaborative analysis on the dynamic hypergraph model to obtain a working state data sequence.

The invention provides a non-contact double-recording signature method and device based on end intelligence, and the method comprises the steps: loading a face recognition model and a gesture recognition model preset in end side equipment, and initializing a real-time video stream of a camera; face detection, living body judgment and facial feature comparison are carried out based on the real-time video stream, and an identity verification result is generated; synchronously recognizing a gesture of a user or an object moving track, matching a standard signature template through dynamic time warping, and generating a track consistency verification result; the identity verification result, the track consistency verification result and the signature track data are locally encrypted and stored, and are asynchronously uploaded to a server when the network is recovered; and through a timestamp alignment mechanism, audio and video streams in a signature process, an identity verification result and track data are synchronously recorded, encrypted and stored. According to the invention, the authenticity and security of signature are effectively improved, the risk of data leakage is reduced, and the system stability is enhanced.

This invention provides a method for evaluating the consistency between virtual and real data in electromechanical systems. The method includes: determining the phase error based on the correlation coefficient between the simulation data sequence of the electromechanical system simulation model and the corresponding measured data sequence of the actual electromechanical system at different time-shift steps; obtaining a first simulation data sequence and a first measured data sequence based on the phase error; identifying local phase error regions in the first simulation data sequence and the first measured data sequence; performing dynamic time warping on the first simulation data sequence and the first measured data sequence within each local phase error region to calculate the amplitude error; performing dynamic time warping on the simulation slope data sequence of the first simulation data sequence and the measured slope data sequence of the first measured data sequence to calculate the shape error; and obtaining the consistency evaluation result between the electromechanical system simulation model and the actual electromechanical system based on the phase error, amplitude error, and shape error. This invention can improve the computational efficiency of the consistency evaluation result.

The invention discloses an intelligent skill action evaluation method and system fusing a fine-tuning visual language model and improved dynamic time warping. Comprising the following steps: constructing a professional data set of skill actions, performing field fine tuning on a MediaPipe attitude estimation model, and improving the detection accuracy of key points under unconventional attitudes such as rolling and handstand; and performing instruction fine tuning on the visual language model to enable the visual language model to output the structured professional evaluation conforming to the teaching habits of the coach. An improved dynamic time warping algorithm is adopted, a speed adaptive weight is introduced, and three-level deviation quantitative analysis of a frame level, a joint point level and an action stage level is realized. A double-track parallel and dynamic bottom-taking mixed evaluation framework is innovatively provided, dynamic time regular quantized data is taken as a physical reference, a bottom-taking mechanism is triggered through double judgment of deviation part overlap ratio and score deviation, and large model illusion is effectively inhibited. According to the invention, the problems of lack of professional standards, difficulty in time sequence alignment, large model illusion and the like in skill action evaluation are solved, and accurate, professional and interpretable intelligent evaluation and teaching guidance are realized.

This invention belongs to the field of meteorological driving element screening technology, and discloses a method, system, equipment, and medium for meteorological element screening based on data-driven grid aggregation and causal sparse screening, to solve the problems of high-dimensional grid redundancy, spurious correlation interference, difficulty in identifying nonlinear time delays, cross-seasonal instability, and difficulty in verifying the necessity of elements. The method of this invention includes: acquiring and preprocessing target variable, grid meteorological, and calendar data to construct a standardized dataset; performing data-driven aggregation on the grid meteorological data to obtain regional-level sequences, and generating a candidate set based on correlation, partial correlation, and mutual information; performing time-delay causal discrimination and sparse screening on the candidate set, identifying time delays by combining cross-correlation and dynamic time warping, and estimating uncertainty through Bootstrap; performing split-Blu-ray and seasonal stability screening on key elements, quantifying contribution through counterfactual testing, and generating a callable meteorological element library.

The application belongs to the technical field of computer vision, and discloses a motion action correction method, system, storage medium, computer device and terminal, the method comprising: collection of human motion posture recognition data; design of a motion action classification neural network model and training of the model; comparison of single-frame image postures and DTW (Dynamic Time Warping) distance comparison of action time sequences.The application uses a common USB camera to acquire human motion images, uses a notebook computer to perform inference on the structure of a human posture recognition neural network model, extracts a skeleton and classifies postures, and completes error action comparison and correction, and has high universality, small calculation amount, high accuracy, and well meets daily life requirements.The application uses a double comparison strategy of key frame action and time sequence comparison, first, key actions are used to correct actions of parts, and second, a complete action segment is compared.The correction strategy is more accurate and reasonable than general systems.

The application provides a kind of industrial vertical field corpus construction data cleaning method, belong to industrial big data technical field, the application is through collecting multi-modal industrial data and recording original time stamp, unified time reference is generated using dynamic time warping algorithm for time alignment, cross-modal fusion feature vector is generated by multi-modal attention mechanism learning feature interaction weight, key data section is identified based on event-driven trigger rule and is associated as event data package, quality evaluation and abnormal calibration are carried out through step response consistency detection, multi-modal knowledge graph is constructed and cross-modal alignment model based on dual optimization constraint satisfaction framework is used for feature completion, finally, data quality is ensured through adaptive verification process, solve the technical problems that multi-modal industrial data is difficult to ensure alignment accuracy and original information integrity in time dimension alignment and semantic level fusion process.

The invention discloses a multi-parameter fusion disaster reduction platform system based on earthquake and strong vibration monitoring, and the system comprises a data collection module which collects multi-source earthquake monitoring data; the data preprocessing module is used for denoising, standardizing and synchronizing the seismic waveform data; the time synchronization and space standardization module is used for ensuring time synchronization and coordinate standardization of the seismic waveform data; the local time window division module divides the waveform data into a fragment set; the dynamic time warping algorithm module is used for executing data alignment and ensuring accurate alignment of waveform fragments; the waveform feature extraction module is used for extracting waveform features; the abnormity detection module is used for identifying and marking an abnormal fluctuation mode; and the propagation path speculation module speculates the epicentral position and the propagation path according to the mark set. According to the method, accurate synchronization and alignment of multi-source earthquake monitoring data are realized, the epicenter position speculation accuracy is improved, and the method is widely applied to earthquake disaster early warning and decision support.

The invention belongs to the technical field of cloud computing networks, and discloses a computing power network workload spatio-temporal dynamic prediction method and device, equipment and a medium, and the method comprises the steps: determining a fuzzy set for identifying a workload mode through employing a clustering algorithm based on dynamic time warping according to a performance index during operation; determining a state transition conditional probability matrix of the computing power node, the heterogeneous hypergraph and the working load mode; adopting hypergraph convolution kernel learning to obtain a heterogeneous feature fusion model of workload and computing power nodes; processing the fuzzy set by adopting a fuzzy membership covariance, and further training by adopting a time convolution network of a dynamic receptive field to obtain a time sequence feature of a workload; and according to the heterogeneous feature fusion model and the time sequence features of the workload, carrying out space-time fusion training of cross entropy measurement probability and fuzzy uncertainty by adopting a probability intuitionistic fuzzy relation matrix to obtain a workload space-time dynamic prediction model. The method has the beneficial effect that the error rate of resource scheduling decision is reduced.

The invention discloses a data collection method and device supporting multiple industrial protocols and a medium, and relates to the technical field of industrial data collection, and the method comprises the steps: obtaining protocol type information, loading protocol element description corresponding to the protocol type information, and generating protocol description data; a dynamic time warping algorithm is adopted, protocol device data are analyzed from the protocol description data, timestamps and sampling periods of different protocol device data are converted into a unified time format, and synchronous time data are generated; carrying out data merging on the standard format data, and carrying out priority ranking according to the real-time performance and importance of the protocol equipment data to generate priority scoring data; and performing data transmission monitoring and data integrity verification on the priority scoring data to obtain a data integrity report, and performing data loss analysis to generate a data acquisition state report. According to the overall scheme, the automation level of data acquisition and processing is improved, and the stability and reliability of the system in a multi-protocol environment are enhanced.

The present application relates to a kind of regional carbon peak prediction method and system, storage medium, as follows: the energy historical consumption of collecting regional years is collected;The historical carbon emissions are calculated by the method of IPCC coefficient conversion;The main influencing factors of regional carbon emissions are filtered by dynamic time warping algorithm;According to the main influencing factors of regional historical carbon emissions and carbon emissions, the principal component analysis method and STIRPAT model are comprehensively used, and the regression prediction model of regional carbon emissions is constructed;Select the main influence of carbon emissions as the core element to be quantified and generate multiple scenario modes;The corresponding influence factor under scenario mode is input into carbon emission regression prediction model, and the future carbon emissions of the region to be measured, regional carbon peak peak value and occurrence time are calculated.The present application effectively solves the problem that the identification result has great deviation caused by the inconsistency of element time series and the obvious fluctuation of element in the process of carbon peak prediction, provides theoretical basis and technical support for government carbon reduction policy making.

The invention relates to the technical field of Internet of Things equipment detection, in particular to an industrial Internet of Things equipment operation state anomaly detection system and method oriented to dynamic time sequence data. Comprising a data acquisition unit; a time series data preprocessing unit; an intelligent anomaly detection unit; and an abnormal result output and feedback unit. Synchronous time sequence stamps of the same reference clock source are added to multi-dimensional dynamic time sequence operation data and equipment key component images, and it is guaranteed that initial association of the two types of data is consistent; an optimal time corresponding relation is constructed through a dynamic time warping algorithm, nonlinear time correction and frequency adaptation are completed, and the problem of time asynchronization is solved; through a multi-modal feature drift correction module, a working condition adaptive drift correction factor is generated based on scale invariant feature transformation feature point matching, feature offset and time series data non-fault fluctuation are corrected, feature stability is improved, and the same operation node state of equipment is truly reflected.