53 results about "Time scaling" patented technology

The invention provides a power load prediction method based on multi-time scale fusion, and the method comprises the steps: collecting the historical time series data of a power load, carrying out the decomposition processing of the historical time series data of the power load, obtaining a multi-time scale intrinsic mode component set, and carrying out the prediction of the multi-time scale intrinsic mode component set according to the multi-time scale load prediction demand. Calculating the correlation between the historical time sequence data of the power load and the coupling factors, and determining strong correlation coupling factors; performing preset processing on the multi-time scale intrinsic mode component set and the strong correlation coupling factor to obtain a plurality of processed data sets; inputting the plurality of data sets into a time sequence analysis model to obtain a plurality of time scale prediction results; and evaluating the precision of the plurality of time scale prediction results, and determining a power future day-level load prediction result. According to the method, static trend and dynamic change are both considered, the comprehensiveness, precision and robustness of load prediction are improved, scientific support is provided for scheduling optimization and resource allocation of the smart power grid, and improvement of safety and reliability of operation of the power grid is facilitated.

The invention discloses a low earth orbit satellite edge computing service optimization method and system based on double time scales, and relates to the technical field of satellite networks and edge computing, and the method comprises the steps: obtaining a plurality of time frames and time slots, the plurality of time frames and time slots are divided based on time, and the time scales of the time frames are larger than the time scales of the time slots; dynamically adjusting satellite selection and request scheduling based on the visibility and resource state of the current satellite in each time slot; according to the method, a service deployment and migration strategy is dynamically adjusted based on long-term service requirements and resource states in each time frame, and the dynamic adjustment method is an optimization algorithm based on double time scales, so that the service quality can be improved, and the system cost can be reduced.

The invention discloses an authority management system of interactive equipment, particularly relates to the field of computer authority management, is used for solving the problem that an interface state is disjointed from an authority decision, and is characterized in that a time mark acquisition module is used for acquiring a role context, a process state and an interface operable item on a unified timeline to generate a context snapshot and writing the context snapshot into a time anchor point; the contract construction module establishes interface contracts based on context snapshots to perform homologous binding to form a constraint set, and the mapping evidence solidification module generates permission mapping table expansion constraints in a rendering stage and writes behavior evidence chain solidification presentation basis. The judgment evaluation module calculates a judgment credibility coefficient according to a time anchor point alignment operation event and an approval record to execute local judgment or record through generating a judgment record; and the version revision module executes a minimum change revision mark change on an interface contract according to the judgment record and releases a new permission mapping table to recycle an old version to form a reviewable sequence.

The invention relates to a train delay prediction method based on multiple time scales, and the method comprises the steps: carrying out the multi-source data fusion of train operation data, and obtaining the space-time embedding representation of a data tensor; wherein the space-time embedding representation comprises time embedding representation, space embedding representation and feature embedding representation; identifying periodicity in a time sequence for the space-time embedding representation through fast Fourier transform, and dividing information of a plurality of time scales; capturing space-time correlation for the space-time embedded representation, and generating space-time correlation feature representation; based on the information of multiple time scales, performing multi-time scale decomposition on the space-time correlation feature representation, and performing channel attention learning on the decomposed information to obtain aggregated multi-time scale sequence information; and based on the aggregated multi-time scale sequence information, obtaining a late prediction result. According to the method, accurate delay prediction of the train under the multi-station and complex railway network conditions can be realized.

The invention discloses a ka lman filtering time scale establishment method considering abnormal data, and the method comprises the steps: obtaining a time difference measurement value sequence of an atomic clock group, carrying out the processing of the time difference measurement value sequence, and obtaining the atomic clock state variable calculation information of all epochs in the time difference measurement value sequence, and calibrating any single timekeeping clock by using the atomic clock state variable resolving information to obtain a calibrated time scale. Compared with an existing time scale algorithm, the algorithm can directly eliminate influences of atomic clock time difference observation data interruption and abnormal conditions on the time scale, the generated time scale is continuous, and the stability is not affected.

The invention discloses a 360-degree video edge caching joint bit rate allocation method based on double time scales, and belongs to the technical field of 360-degree video streaming and edge caching. The method comprises the following steps that: in a long-time scale period, an edge server collects and analyzes historical request data of a user, calculates a comprehensive value priority for candidate video slices according to long, medium and short-term popularity of the slices, and further generates an optimal caching strategy which takes effect in a next period. In a short time scale period, according to the caching strategy, the edge server processes the real-time requests of the user and distributes bit rates to all concurrent requests fairly and efficiently. Through a self-adaptive optimization mechanism combining long-term planning and real-time response, the high cache hit rate of high-value slices can be ensured in different storage spaces, the data request quantity to the cloud is reduced, the pressure of a return link is relieved, and the comprehensive experience quality of a user is remarkably improved.

This invention proposes a multi-energy safety assessment method and system considering multiple time scales and coupled faults. The method includes: establishing an intermediate time-scale model and a long-time-scale model of the integrated energy system; conducting a safety assessment for each fault scenario in a fault scenario set; wherein, using the long-time-scale model to perform an N-1 safety scan of the fault scenarios considering coupled faults, calculating system risk assessment indicators; when the system risk assessment indicators reflect that the fault scenario may lead to water hammer consequences, using the intermediate time-scale model to calculate the overpressure value generated during the water hammer process; and generating the final safety assessment result of the integrated energy system based on the safety assessment results of each fault scenario. This invention can capture the water hammer effect of the heating network and the cascading faults caused by the coupling of the logical and geographical layers, which are often overlooked in traditional assessments, achieving a more comprehensive and accurate safety assessment of the integrated energy system and helping to improve the operational safety of the system.

The dual-time-scale state observation method and system for a piezoelectric actuator provided in the present application establish a hysteresis model of the piezoelectric actuator; design a state observer based on the hysteresis model; divide the state observer into time scales; design an adaptive parameter update law for the state observer after the time scale division; connect the input and output ends of the state observer after the adaptive parameter update law to the input and output ends of the piezoelectric actuator to achieve observation of the output state of the piezoelectric actuator. The dual-time-scale state observation method and system for a piezoelectric actuator provided in the present application overcome the problem that traditional models and state observation methods for piezoelectric actuators are mostly performed on one time scale, and there is an avoidable time scale problem in terms of state observation accuracy and acquisition of model parameters, so that the state observer parameters of the piezoelectric actuator are more accurate and the actuator state is accurately applied in the feedback controller.

The invention relates to the technical field of coal mine gas overrun prediction, and provides a self-adaptive gas overrun long-time prediction method and system. The method comprises the following steps: processing acquired coal mine underground multi-source data, and constructing different time scale characteristics of the data; adaptively screening an optimal prediction index combination according to the Pearson correlation coefficients of the target gas concentration for the different time scale characteristics; and determining an optimization parameter combination of the Informer long-time prediction model, optimizing the Informer long-time prediction model based on a grey wolf optimization algorithm to obtain an optimal prediction model so as to carry out over-limit long-time prediction on the gas concentration of the working face, and carrying out comprehensive evaluation on a prediction result based on a predetermined accuracy evaluation index. Therefore, the problems that in the prior art, gas overrun disaster-causing factors in different mining areas, different coal mines and different working faces are large in difference, the generalization ability is weak, and the long-time prediction ability is insufficient are effectively solved.

The invention discloses a dynamic feature space construction method for time dimension coupling multi-modal data, which comprises the following steps: time synchronization modeling is realized through time dynamic correlation calculation and time step relation weight generation; time granularity alignment is realized through dynamic time warping optimization and time scale unification; and dynamic feature space construction is realized through global time feature extraction and local-global feature fusion. The invention discloses a dynamic feature space construction method for time dimension coupling multi-modal data, and the method comprises the steps: capturing a time synchronization relation between modals through dynamic correlation calculation and time step weight generation; unifying a multi-modal time resolution and a time step relationship through time granularity alignment; and finally, through fusion of local and global time features, a dynamic shared feature space is generated, and the multi-modal time dynamic state is comprehensively expressed.

The embodiment of the invention provides a demand prediction method and device based on a time sequence, and the method comprises the steps: decomposing the input equipment spare part time sequence data into a plurality of patches along the time dimension, and introducing a learnable pseudo timestamp for each patch according to the attention score of each patch to serve as a data placer; connecting the output of the patch through a gating rule in loop connection according to the pseudo timestamp, inputting the feature sequence into a multilayer patch attention structure stacked in a triangular manner, and iteratively applying a time sequence processing unit on a plurality of time scales with different time granularities, aggregating the total output of each layer in the multilayer patch attention structure and each scale in the time scale to a full-connection neural network predictor, and iteratively training the full-connection neural network predictor through a mean square error loss function; obtaining a corresponding equipment spare part demand prediction result through the output of the full-connection neural network predictor; according to the invention, the accuracy and efficiency of demand prediction can be effectively improved.

This paper relates to a generator set control method and device based on multi-timescale features. The higher-level scale provides guidance information to the lower-level scale; the weekly plan provides the unit start-up and shutdown status for the day-ahead plan, and the day-ahead plan provides the basic output points of the units for the intraday plan. At the weekly scale, the constraints of unit timing coupling can be ignored, and a dataset is generated by feeding back from the lower-level scale to the higher-level scale. This results in smaller data dimensionality and lower computational cost for data generation. Then, based on a neural network, the start-up and shutdown status of the units is predicted, and reliable start-up and shutdown statuses are selected and passed down, eliminating the need for feasibility remedial measures for start-up and shutdown statuses and reducing computational complexity. At the day-ahead and intraday scales, the start-up and shutdown statuses of the units determined by the higher-level time scale are used to identify more redundant constraints and accelerate the solution speed. This paper utilizes the features of different time scales to solve the unit combination problem, which can accelerate the solution speed while ensuring solution quality, and the solution speed is more stable.

The invention discloses a high-precision wave recording acquisition and time mark synchronization system for power grid fault positioning, and relates to the technical field of power grid wave recording synchronization, and the system comprises the steps: 1, synchronously outputting three-gear sampling under a time axis of the same coordinated world time, and generating a time uncertainty upper bound and a group delay signature for a channel and a fragment; 2, performing quality locking near-lossless on the high-energy fragment, after coding, checking the high-energy fragment to reach a sample position and a peak amplitude through homologous detection, and returning to be lossless if the high-energy fragment is unqualified; 3, writing a fragment index, quality metadata, a fragment verification structure and a whole file signature into the compatible single file expansion container; step 4, carrying out progressive retrieval, breakpoint resume and cross-station de-duplication according to indexes, and implementing cold and hot hierarchical storage; and 5, based on group delay signature compensation and quality weighted loading, solving a reference moment and generating an acceptance check list. According to the scheme, cross-device alignment, reproducible key features, transmission and storage peak clipping, playback and evidence obtaining caliber unification and tool compatibility and auditing are realized.

The invention discloses a physiological state monitoring method, device and equipment based on multi-time scale constraint and a medium, relates to the technical field of medical information processing and data analysis, is applied to a computer device, and comprises the following steps: determining a target physiological baseline value of each mode; obtaining a current physiological signal of each mode in a current monitoring time period, extracting a basic physiological feature under a multi-time scale sliding window from the current signal based on a consistency constraint mechanism, and generating a physiological change feature; analyzing cross-modal joint features according to the basic physiological features and the change features; the method comprises the following steps: establishing a state unit containing each feature, respectively organizing each state unit into a state sequence of a corresponding time scale to obtain a multi-scale physiological state sequence of a current monitoring time period, and adding the sequence to the end of a previous sequence to obtain a latest physiological state monitoring result. The pertinence and accuracy of physiological state evaluation and the collaborative characterization of multi-modal data are realized, and the continuity of full-cycle data is guaranteed.

The application discloses a wind speed prediction model training method and a prediction method based on multi-time scale fusion, relates to the technical field of computers, and the wind speed prediction model training method is characterized in that: initial data in a same time length is divided by different time scales to obtain first training samples and second training samples of different time scales; a first time scale prediction wind speed is obtained by performing feature extraction on the first training samples; average wind speed is obtained by performing data conversion on the first time scale prediction wind speed; a fluctuating wind prediction result is determined based on the first time scale prediction wind speed and the average wind speed; a second time scale prediction wind speed is determined by performing feature extraction on the second training samples; a prediction wind speed is determined based on the fluctuating wind prediction result and the second time scale prediction wind speed; the microfluctuation of wind speed is extracted according to the first training samples of the first time scale; and the macro trend of wind speed is extracted according to the second training samples of the second time scale, so that the accuracy of wind speed prediction can be improved.

The application discloses a kind of multi-agent preset time formation control methods based on backstepping method under distance rigidity matrix, comprising: 1) based on the double integrator dynamics model of multi-agent system is established based on rigidity graph theory, define the minimum and infinitesimal rigidity frame corresponding to the expected formation;2) introduce backstepping design framework, define virtual speed error variable;3) introduce time-varying scaling function to construct time scale transformation;4) design distributed preset time controller;5) through numerical simulation and physical platform are verified, verify the effectiveness of distance error in user preset time under different initial conditions converges to the vicinity of zero.The application is fused by backstepping and preset time scaling function, for the first time in only local relative measurement distance rigidity formation Convergence time user self-defined preset is realized, and convergence time upper bound is independent of initial condition and controller parameter, provides reliable, engineering implementation solution for time-critical multi-agent cooperative task.

This application relates to a Temporal Information Aggregation (TIA) neural network block to extract latent multi-scale temporal information. By applying TIA, information at different time scales can be efficiently extracted. The TIA block can be implemented as a single block and can therefore be plugged into any architecture. The extracted multi-scale temporal information contributes to the final output as a residual.

The present invention relates to a multi-time-scale train delay prediction method, comprising: fusing train operation data from multiple sources to obtain a spatiotemporal embedding representation of the data tensor; wherein the spatiotemporal embedding representation includes a time embedding representation, a spatial embedding representation, and a feature embedding representation; using the spatiotemporal embedding representation to identify periodicity in the time series through fast Fourier transform and divide information at multiple time scales; capturing spatiotemporal correlations in the spatiotemporal embedding representation to generate a spatiotemporal correlation feature representation; decomposing the spatiotemporal correlation feature representation at multiple time scales based on the information at multiple time scales, and performing channel attention learning on the decomposed information to obtain aggregated multi-time-scale sequence information; and obtaining a delay prediction result based on the aggregated multi-time-scale sequence information. The present invention can achieve accurate train delay prediction under multi-station and complex railway network conditions.

The invention discloses a time sequence diagram time scale generation method and device, equipment and a medium. The method comprises the steps that to-be-generated data, the maximum number of preset scales and to-be-selected primary and secondary time scale unit arrays are acquired; determining primary and secondary time scale units of the time sequence diagram in combination with the timestamp of the to-be-generated data and the primary and secondary time scale unit array; determining a candidate step length list according to the time stamp extreme value and the primary and secondary time scale units of the to-be-generated data; and according to the candidate step length list and the first main time scale value, determining a pre-selected time scale of the time sequence diagram. The maximum number of the time scales is limited through the maximum number of the preset scales, the number of the time scales of the pre-selected time sequence diagram is screened, and then the optimal step length and the final time scale are determined. It is ensured that the key time scale, namely the integer number of main time units in the time range, is certainly selected, then it is ensured that the scales are uniform, and display of the time sequence diagram is optimized.

The invention discloses a multi-time scale energy scheduling method and system based on electricity price prediction. The method comprises the steps of obtaining electricity price prediction values on multiple time scales in the future; generating an energy scheduling strategy on multiple time scales; executing an energy scheduling strategy on multiple time scales, monitoring an actual electricity price in real time, and comparing the actual electricity price with a corresponding electricity price prediction value to determine a prediction error; judging whether the prediction error is greater than an error threshold; in response to the fact that the prediction error is larger than an error threshold value, updating parameters of the electricity price prediction model according to the prediction error, and returning to the step of obtaining electricity price prediction values on multiple time scales in the future; and taking the current energy scheduling strategy on the multi-time scale as a final energy scheduling strategy on the multi-time scale in response to the fact that the prediction error is not greater than the error threshold value. By using the scheme of the invention, the electricity price trend in the short period, the middle period and even the long period in the future can be pre-judged, and a solid foundation is provided for formulating a comprehensive and fine energy scheduling strategy.

The invention relates to an atomic clock group change-oriented elastic time scale generation method, system and device. The method comprises the following steps: constructing an elastic factor graph model generated by time scales, generating a main time scale and a standby time scale which are consistent, carrying out time difference change accumulation of the main time scale and the standby time scale by utilizing atomic clock group change, compensating time difference and frequency deviation jump values of the time scales under the clock group change, generating an elastic time scale, and calculating the elastic time scale according to the elastic factor graph model. The continuity and stability of the time scale are ensured, and the monitoring performance of the atomic clock is improved. Meanwhile, by utilizing a plug-and-play architecture of the factor graph, factor nodes can be dynamically added or removed to update the model when the clock group changes, and the whole elastic factor graph model does not need to be reconstructed, so that the generation of the elastic time scale has the advantages of flexibility and expandability.

Techniques are provided for transformation of time-based event data structures to a logarithmic time scale. One method comprises obtaining time-based event data structures associated with respective events, where a given time-based event data structure, associated with a given event, comprises multiple data elements comprising an event base date and an event identifier; converting the time-based event data structures into a tabular format, where each record corresponds to a different event and each data element is assigned to a corresponding field in the corresponding record of the tabular format; determining an overall time duration associated with the events in the tabular format; determining a portion of the overall time duration allocated to each designated time unit in a logarithmic time scale; transforming the tabular format using the determined portions; and initiating an automated action using the transformed tabular format.

The application discloses a quad-rotor unmanned aerial vehicle attitude tracking double-time scale model predictive control method, relates to the quad-rotor unmanned aerial vehicle control technical field, and aims at the double-time scale characteristics and input constraint problems existing in the quad-rotor unmanned aerial vehicle attitude system. First, the singular perturbation theory is used to decompose the attitude system into two slow and fast reduced-order subsystems. Then, a model predictive controller matched with the time scale of each subsystem is designed for each subsystem, and a contraction constraint based on the auxiliary control law design is introduced in the optimization problem to ensure the recursive feasibility and closed-loop stability of the controller. Finally, the control amount of the two subsystems is combined to construct the composite control input of the attitude system. The application reduces the complexity of the quad-rotor unmanned aerial vehicle attitude system controller design through the decomposition-combination design strategy, and can explicitly process the input constraint while improving the attitude tracking performance and robustness through online optimization.

According to the precipitation grading method for obtaining any time scale, only 12-hour and 24-hour grading standards are given by the precipitation grading national standard (GB / T 28592-2012), and precipitation grading standards of other time scales are not given. However, many industries (such as traffic, hydrological monitoring and the like) possibly have requirements for precipitation division standards of other time scales (such as 10 minutes, 1 hour and the like), and in order to meet the requirements, an equal ranking rate method is provided, and the method can obtain precipitation division standards of any time scale not larger than the time resolution of precipitation data. Taking ERA5 hourly rainfall data and time scale 24-hour rainfall division standards (GB / T28592-2012) of Nanjing region (111 DEG E, 32 DEG N) as examples, the rainfall division standards of time scales of 1 hour, 3 hours, 6 hours and 12 hours are obtained by using the method, and the rainfall division standards of time scales of 12 hours obtained by using the method are close to the national standard. Therefore, if minute-level automatic station rainfall data is taken as a research object, the method can obtain a rainfall division standard of any time scale.

The invention relates to a prediction method and device for the starting number of virtual machines, equipment and a storage medium. The method comprises the following steps: preprocessing historical resource data of a virtual machine acquired by adopting a plurality of time scales to obtain original resource data of the plurality of time scales; according to the original resource data of each time scale, distributing a weight to each time scale; according to the weight of each time scale, weighting the original resource data of each time scale to obtain target data of each time scale; and performing prediction analysis on the target data of the plurality of time scales, and predicting the starting number of the virtual machines. By adopting the method, the accuracy of predicting the starting number of the virtual machines can be improved.

The application belongs to the technical field of intelligent education, and discloses a knowledge tracking method and system based on a cascaded time sequence feature processing architecture, which comprises the following steps: mapping historical answering interaction sequence data of students into a high-dimensional feature vector; performing deep processing on the high-dimensional feature vector to capture data features of different time scales; and predicting the performance of students based on the data features of different time scales. Through the collaborative design of the heterogeneous cascaded architecture and the selective state space model, the application improves the training stability and prediction accuracy of the knowledge tracking model, and realizes efficient use of linear time complexity and computing resources.

The application discloses a Kalman filter time scale establishment method considering abnormal data, and comprises the following steps: acquiring a time difference measurement value sequence of an atomic clock group, processing the time difference measurement value sequence to obtain atomic clock state variable solution information of all epochs in the time difference measurement value sequence, and calibrating an arbitrary single time-keeping clock by using the atomic clock state variable solution information to obtain a calibrated time scale. Compared with an existing time scale algorithm, the algorithm can directly eliminate the influence of atomic clock time difference observation data interruption and abnormal conditions on the time scale, and the generated time scale is continuous and stable.