278 results about "Frequency data" patented technology

A computing device for predicting an expected loss for a set of claim transactions is provided. The computing device predicts, at a first machine learning model, a claim frequency of the set of claim transactions over a given time period and trained using historical frequency data and based on a segment type defining a type of claim, each type of segment having peril types. The computing device also predicts, at a second machine learning model, claim severity of the set of claim transactions during the given time period, the second machine learning model trained using historical severity data and based on the segment type and the corresponding peril types. The computing device then determines the expected loss for the set of claim transactions over the given time period by applying a product of prediction of the first machine learning model and the second machine learning model.

A computing device for predicting an expected loss for a set of claim transactions is provided. The computing device predicts, at a first machine learning model, a claim frequency of the set of claim transactions over a given time period and trained using historical frequency data and based on a segment type defining a type of claim, each type of segment having peril types. The computing device also predicts, at a second machine learning model, claim severity of the set of claim transactions during the given time period, the second machine learning model trained using historical severity data and based on the segment type and the corresponding peril types. The computing device then determines the expected loss for the set of claim transactions over the given time period by applying a product of prediction of the first machine learning model and the second machine learning model.

The invention provides an equipment health examination method and system based on multi-agent collaboration. The method comprises the following steps: a data acquisition step: acquiring target data to generate a multi-dimensional feature vector; the target data comprises frequency data, process data and control data; an equipment monitoring step: monitoring the equipment based on the generated multi-dimensional feature vector, and outputting a monitoring result; and a deployment processing step: deploying and implementing a corresponding processing scheme according to a monitoring result. The invention provides an equipment early warning and diagnosis method and system based on multi-agent cooperation, and the method comprises the steps: combining the advantages of a professional mechanism model, an AI model and a large language model through the multi-agent cooperation of feature extraction, threshold adjustment, fault diagnosis, decision generation, summary review and closed-loop feedback; the problems that a traditional method is single in model, high in false alarm rate, lagged in decision and the like are solved.

The invention discloses a lake ecosystem health evaluation method and system, and particularly relates to the technical field of data management. A monitoring area is divided through a zoning model of a lake area, distribution density coverage rate characteristics and sampling frequency abnormal fluctuation characteristics are extracted based on distribution density and acquisition frequency data of sampling points, data spatial and temporal distribution uniformity indexes of the sampling points are calculated, and the acquired data are classified according to the uniformity indexes. Establishing an evaluation model and generating a health state report by preferentially utilizing the uniformity data, generating a data quality analysis report aiming at the non-uniformity data and feeding back a sampling strategy optimization suggestion, and performing error accumulation prediction and dynamic sampling adjustment on the incomplete uniformity data; by improving comprehensiveness, uniformity and timeliness of data acquisition, scientificity and reliability of health evaluation of the lake ecosystem are improved, and powerful support is provided for ecological management and restoration.

The invention provides a rapid random model correction method for an active learning type ocean platform structure, and the method comprises the steps: firstly carrying out the selection of correction parameters through considering the sensitivity, then carrying out the design of a test scheme, and building an initial Kriging model; a new correction parameter training sample is found, the frequency corresponding to the new sample is calculated, a Kriging model is reconstructed by adopting a new training set, random model correction is performed based on the reconstructed Kriging model, an objective function is constructed by adopting actually measured frequency data and initial finite element model frequency data, and a correction parameter mean value and a standard deviation are taken as solving objectives. And solving by utilizing an optimization algorithm to obtain a mean value and a standard deviation of correction parameters of the finite element model to be corrected, and repeatedly iterating to realize random correction of the ocean platform structure. According to the method, rapid, efficient and accurate model correction under small samples and noise errors is realized, and higher correction accuracy can be obtained by adopting fewer training samples.

The invention discloses a data auditing method based on big data, and relates to the technical field of big data, and the method comprises the steps: obtaining multi-modal data in a big data platform form, extracting features of the multi-modal data to generate a feature set, creating a rule base based on the feature set, and constructing a cross-form dependency graph according to the feature set and the rule base; cascade auditing is executed through a cross-form dependency map, when auditing fails, an affected field is reversely positioned according to the connection direction of the map, and incremental state rollback and re-auditing are executed on the affected field; when it is detected that the high-frequency data is changed, an anti-rollback storm mechanism is started, a cascade load index is obtained, and a rollback instruction set is generated through cascade blocking based on the index; and executing distributed fault-tolerant control, constructing a node collaborative protection system through cascade loads, and outputting a fault-tolerant operation instruction.

The invention relates to a power construction deviation degree diagnosis method based on multi-modal time series data fusion, and the method comprises the steps: collecting voltage, current and frequency data through a multi-channel synchronous sampling technology, filling missing data through cubic spline interpolation, and constructing an initial data matrix; based on a hierarchical feature extraction technology, mapping the voltage frequency domain features and the current time domain statistical features to a unified feature space through canonical correlation analysis, and generating a multi-modal feature vector with a time sequence tag in combination with a sliding window; analyzing the dynamic trend of the electrical variable under multiple time scales by adopting a long short-term memory network, and capturing a key time point through an attention mechanism; a sudden change point and a stationary section are defined, an isolated forest algorithm is combined to detect an abnormal point location deviating from a trajectory, anomaly is classified as transient disturbance or continuous deviation through a multi-layer perceptron, the evolution trend of regional continuous deviation is predicted, and the key problem of the power deviation degree diagnosis capability is improved.

The invention provides a rolling bearing digital twinning dynamic evolution method and system based on continuous learning, and belongs to the technical field of bearing life prediction. The method comprises the following steps: processing a bearing monitoring signal through short-time Fourier transform to generate standardized time-frequency data; constructing health indexes based on the index degeneration function and dividing health levels; training a life prediction model by using the extended LSTM network and taking the time-frequency data as input; real-time data is collected through a fixed time window to predict the life, and when the root-mean-square error of a predicted value and an actual value exceeds the limit, the edge device is triggered to upload new data; evaluating parameter importance in combination with a Fisher information matrix, and dynamically adjusting a regularization intensity updating model; and monitoring the data standard deviation in real time, triggering shutdown when the data standard deviation exceeds the limit, otherwise, predicting the remaining life by updating the model, and stopping when the remaining life reaches the threshold value. According to the method, dynamic evolution of the digital twin model is realized through continuous learning, and the industrial equipment state monitoring and predictive maintenance capability is effectively improved.

The invention belongs to the technical field of machine room power distribution, and provides a machine room power distribution equipment remote monitoring method and system, and the method comprises the steps: collecting operation data in real time through deploying edge equipment, fusing basic operation data, transient feature data and historical abnormal data, and constructing a state scoring model; utilizing a neural network training weight coefficient to realize equipment health degree dynamic evaluation; the sampling frequency is adaptively adjusted based on a scoring result, abnormal data are screened by combining multiple characteristic thresholds such as current sudden change intensity, energy sudden change quantity and temperature gradient, and only high-frequency data fragments in an abnormal time period are reserved; through an edge-cloud collaborative storage mechanism, abnormal data are locally cached after RAID redundancy check, normal data are uploaded to the cloud according to storage duration and access frequency in a grading manner, full-life-cycle traceability of the data is realized through tagging processing, anomaly detection sensitivity is improved, and storage efficiency and fault diagnosis reliability are both considered.

The present invention belongs to the technical field of wind farm active power control and discloses a wind farm frequency modulation power distribution method that takes into account the historical fatigue load of the unit. The method comprises the following steps: collecting the frequency data of the wind farm grid connection point; when the frequency change exceeds the frequency modulation dead zone, calculating the wind farm active power change reference value ΔP farm ; Match the station active power change reference value ΔP in the formed scenario strategy set farm The corresponding optimized active power distribution results of the units. This distribution method is compared with the traditional proportional distribution scheme. While meeting the system frequency response requirements, the present invention improves the problems of sudden increase in fatigue load in wind farms and large differences in fatigue accumulation between units, and verifies the effectiveness of the proposed method.

The invention relates to the technical field of information management, in particular to a safety production informatization data management method and system, and the method comprises the following steps: obtaining a synchronous monitoring record, screening field integrity and numerical value qualified information, marking and classifying abnormal items, filing qualified and abnormal data, constructing a time sequence, additionally recording and correcting abnormal contents, and storing the abnormal contents. Weight hierarchical storage information is extracted, low-frequency data is compressed, a field structure is optimized, and a management scheme is generated. According to the method, the monitoring information is preliminarily screened according to field integrity and numerical standard, the data distribution efficiency is improved, abnormal information is classified and labeled, the structure recognition precision is enhanced, missing supplementary pushing and numerical correction are realized through time sequence comparison, the data continuity is guaranteed, hierarchical storage is performed according to information weight, attributes are clearly reserved, and low-frequency data compression and integration are performed; and the storage burden is relieved, the field structure is automatically expanded and rearranged, the format uniformity and the management specification are improved, and refined processing and efficient circulation of data are realized.

The embodiment of the invention provides a risk zoning method and device for helicopter flight, equipment and a storage medium. The method is applied to the technical field of data processing, and comprises the following steps: carrying out classification and threshold division on meteorological elements according to a fusion data set and different flight scenes to obtain a meteorological element threshold breakpoint set; based on the meteorological element threshold breakpoint set, performing frequency statistics and data synthesis on the fused data set to obtain a multi-layer meteorological element frequency data set; obtaining an initial clustering result of each meteorological element through clustering analysis according to the meteorological element frequency data set; according to the initial clustering result, carrying out risk grade division on each meteorological element to obtain a standardized single-element risk zoning result; and based on a single-element risk zoning result, adopting a multi-element fusion method to obtain a comprehensive risk zoning map. In this way, the technical problem that in the prior art, due to the fact that multiple elements jointly participate in clustering, the risk level is difficult to judge can be solved.

The invention discloses an asynchronous motor fault diagnosis device based on model residual error and machine learning integration, and relates to the technical field of industrial equipment state monitoring. According to the scheme of the invention, based on a motor state space model, a current estimation value is generated according to an input voltage signal, state space model parameters are updated by using a subspace identification algorithm, a difference value between an actually measured current and an estimated current is converted into a three-phase residual signal for fast Fourier transform, and the three-phase residual signal is converted into a frequency domain signal. According to a fault characteristic frequency theory of the asynchronous motor, extracting a characteristic frequency amplitude in the residual frequency spectrum, calculating a statistical threshold value of each characteristic frequency, when the obtained characteristic frequency amplitude exceeds the statistical threshold value, outputting a fault identification signal, constructing a fault characteristic frequency database by utilizing fault characteristic frequency data, and taking the residual characteristic as an input to determine the fault characteristic frequency of the asynchronous motor. And constructing a neural network model for fault classification by taking the corresponding fault type label as output, and outputting the fault type of the fault identification signal.

The invention provides a personalized content generation method and system for a content sharing platform, and belongs to the technical field of data processing, and the method specifically comprises the steps: carrying out the correlation sorting of recall results of different recall links, obtaining N recall results with the highest correlation degree, and inputting the N recall results to an instance of a multi-modal fusion model, the method comprises the following steps: performing feature extraction and analysis based on input data of a user within a specified time range, generating intention keywords, generating a quantitative result of short-term interest by utilizing evaluation of priorities of the intention keywords, integrating the short-term interest and the long-term interest through a weighting model, and performing low-frequency data supplement and high-frequency data depolarization optimization to obtain an interesting result of the short-term interest. According to the method, the stable long-term preference distribution is generated, and the generation processing of the demand content of the user is performed by using the instance and the long-term preference distribution, so that the personalization and accuracy of the content generation processing are improved.

The invention is suitable for the technical field of oil-gas exploration, and provides a seismic data convolution cross-correlation intelligent FWI method, which integrates a proposed seismic data convolution cross-correlation FWI target equation into a deep learning framework, and combines an automatic encoder technology to significantly reduce the nonlinearity of the traditional FWI, effectively avoid the cycle jump problem, and improve the accuracy of the FWI. Therefore, the speed model inversion precision of the FWI is improved. Finally, the FWI technology which can still carry out stable and accurate high-resolution speed modeling under the conditions that seismic source wavelets are unknown, the initial speed is unknown and low-frequency data are missing is realized, and the method has important significance on seismic exploration.

The invention belongs to the technical field of gas pipelines, and particularly relates to a gas engineering construction quality evaluation system based on big data, which comprises the following steps of: firstly, constructing a defect feature tensor, introducing a space-time grid analysis technology to analyze defect disposal aging interval data and location defect reproduction frequency data, and constructing a defect feature tensor on the basis of a preset quality-efficiency reliability quantification rule; defect features are converted into quantifiable quality-effect scores, then deep fusion of multi-source heterogeneous data is achieved by establishing a space-time incidence matrix of welding defects, welding process parameters and environment monitoring parameters, and on this basis, a fuzzy correlation analysis technology and a preset process compliance quantification rule are adopted to achieve quality-effect evaluation of the welding defects. Complex process parameters and environmental conditions are converted into quantifiable process scores, the process scores and quality-effect scores are integrated to generate a gas pipeline welding quality comprehensive evaluation value of a target contractor, and a quantifiable intelligent decision support system is provided for gas pipeline construction quality management and control of the contractor.

The invention discloses an evaporator energy storage process control method and system based on fractional order MIMO nonlinearity. Historical operation data of the evaporator are obtained, and corresponding fractional order MIMO nonlinear system models are constructed according to different dryness intervals; operating data containing dryness is collected in real time, the fractional order MIMO model of the current dryness is input, and a prediction result is generated; comparing the prediction result with the real-time data, and if the deviation exceeds a threshold value, adjusting the parameters and re-executing; otherwise, calculating a dynamic weight to optimize the model in the next stage; real-time data are analyzed through fractional order MIMO models under different dryness degrees, abnormal stages are identified, and early warning is carried out; and comparing real-time analysis results of different dryness interval models, identifying dryness fluctuation amplitude and pressure oscillation frequency data, and then judging an anomaly type. According to the method, reliable control over the energy storage process of the evaporator is achieved.

The invention relates to the field of sensor data processing, and discloses an MEMS drift correction method based on data dynamic sampling and multi-source fusion, and the method comprises the following steps: S1, collecting MEMS three-axis acceleration original data at a first sampling frequency, and synchronously collecting environment temperature, humidity and air pressure data at a second sampling frequency, the first sampling frequency is higher than the second sampling frequency, the basic drift correction model is established by using the low-frequency data to capture the macroscopic and slow-varying relationship between the environmental factors and the drift, then the residual refinement model is established for the high-frequency data, and the high-frequency residual is specially processed; high-frequency drift components related to the environmental change rate are captured, through the two-stage fusion strategy, the accuracy of the model in the macroscopic trend is guaranteed, high-frequency data are fully utilized to improve the instantaneous correction precision, information loss caused by simple downsampling in a traditional method is avoided, and false signals introduced by rough interpolation are also avoided.

The invention provides a query optimization method and system for a distributed database. The method comprises the following steps: determining a high-frequency data unit set in a distributed database, and generating a sub-query task division scheme for each data unit in the high-frequency data unit set; according to the dependency relationship between the sub-query tasks represented by the sub-query task division scheme, determining the interaction frequency between the data units, and determining a data distribution scheme according to the interaction frequency; according to a storage relationship indicated by the data distribution scheme, determining an index set of each node for querying the stored data unit; for each index set, respectively calculating execution costs of different sub-query tasks according to an access mode supported by a query data unit supported by the index set, and generating a sub-query task parallel scheme according to the execution costs; and generating a node scheduling scheme meeting the execution sub-query task parallel scheme. The query speed of the distributed database and the overall performance of the system can be improved.

The invention provides a manipulator false impact control method and system based on a vibration sensor, and relates to the technical field of intelligent control, and the method comprises the following steps: extracting real-time amplitude and frequency data corresponding to a manipulator according to a current state; calculating relative deviation between the real-time amplitude and frequency data and a preset reference value, wherein the relative deviation comprises amplitude relative deviation and frequency relative deviation; according to the relative deviation and a preset deviation threshold value, whether abnormal collision exists in the state of the mechanical arm or not is judged, and a judgment result is obtained; and according to the judgment result, a corresponding control instruction is sent to the manipulator, so that the manipulator moves according to the corresponding control instruction. By monitoring the amplitude and frequency data of the manipulator in real time, whether abnormal collision exists or not is accurately judged, the corresponding control instruction is sent to the manipulator according to the abnormal collision, and the operation safety and the intelligent level of the manipulator are effectively improved.

A guided search system for suggesting and arranging filter criteria within a user interface for presentation to a user to help guide the user's search for listings is disclosed. The system builds one or more filter criteria frequency data structures indicative of the number of times each filter criterion has been used to filter search results and how often different filter criteria are used together. The system uses the frequency data structures to predict which filter criteria a user will likely employ to narrow their search given the filter criteria the user has already used. The system provides techniques for arranging or rearranging filter criteria within a user interface, by moving, placing, or ordering suggested filter criteria within the user interface, where a user is likely to be able to recognize and interact with the placed filter criteria, based on the determined amounts of use.

The invention provides an oil well load indicator diagram prediction method and system, and the method comprises the steps: synchronously collecting an initial electrical parameter data set, a load data set, an accelerometer data set and a barometer data set of an oil well, the initial electrical parameter data set comprising an active power data unit, and then obtaining an active power data segment and a load data segment; obtaining a time lag based on the two, and further obtaining a final electrical parameter data segment; acquiring a reference displacement sequence through the accelerometer data set and the barometer data set; obtaining a dynamic stroke length based on the reference displacement sequence and the load data segment, and further obtaining a final displacement sequence; and constructing a prediction neural network, and obtaining an oil well load indicator diagram based on the prediction neural network and the real-time electrical parameter data segment. According to the technical scheme, the indicator diagram is obtained through continuous and high-frequency real-time electric parameter data segments, motion period information loss caused by low-frequency data collection is avoided, accumulative errors are avoided, and the accuracy of the indicator diagram is ensured.

The invention provides a speed regulator control method and system for coping with ultralow frequency oscillation, and the method comprises the steps: obtaining the frequency data of a hydropower system in real time, and carrying out the filtering processing based on the original frequency data, thereby obtaining the filtering frequency data; constructing a first discrimination vector based on the filtering frequency data, determining a current oscillation occurrence probability based on the first discrimination vector, and determining whether to start an additional damping controller of the speed regulator based on the current oscillation occurrence probability; predicting frequency data of a plurality of time points in the future based on the current original frequency data, constructing filtering frequency data corresponding to each time point based on the predicted frequency data of the plurality of time points in the future, and constructing a second discrimination vector corresponding to each time point based on the filtering frequency data of each time point; and determining oscillation occurrence probabilities at multiple time points based on the multiple second discrimination vectors, and determining whether to start an additional damping controller of the speed regulator based on the oscillation occurrence probabilities at the multiple time points.

The invention discloses a knowledge graph embedding method based on negative sampling and weighting. The method comprises the following steps: acquiring a medicine data set; based on an embedded vector obtained by pre-training and a designed high-quality candidate negative sample set construction strategy, sampling a high-quality candidate negative sample set for all positive triads; according to the knowledge graph embedding model based on translation, calculating scoring function values of the triad and the negative triad corresponding to the triad; carrying out statistics on related frequency data in the data set, and calculating a frequency-based weight of each triple; according to the scoring function value and the weight, calculating the loss L of the triple set to obtain a final loss function of the training framework; optimizing a loss function of the training model by adopting a stochastic gradient descent method; and outputting a potential association relationship between the medicine and the disease and the symptom. According to the method, the negative sampling quality of the model is improved, the adverse effects of long-tail entities and relationships on model training are relieved by weighting the loss function, and the model training performance is improved.

The invention provides a cooling tower system optimal operation parameter self-adaptive regulation and control method, which comprises the steps of collecting multi-source high-frequency data in a system operation process, and obtaining a standardized variable sequence through normalization, abnormal value processing and time sequence consistency verification. A sliding window mechanism and a lightweight causal discovery algorithm are combined, a causal atlas is dynamically constructed and fused, parameters are corrected in real time through an incremental Bayesian network, a dominant causal path is extracted, lightweight CMA-ES rolling optimization is executed in an equivalent control subspace after dimension reduction, optimal control parameters are solved, system closed-loop adjustment is driven, and the optimal control parameters are obtained. Meanwhile, a map confidence degree evaluation and depth reconstruction mechanism is set, dynamic self-adaption of a causal structure and parameters is ensured, the response capacity of a cooling tower system to working condition changes can be improved, and energy efficiency and operation stability are optimized.

The invention discloses a method and device for determining the water content and connectivity of a crack based on a well-ground electromagnetic detection system, a medium and a product, and relates to the technical field of geophysical exploration, and the method comprises the steps: obtaining a plurality of groups of historical data; based on each group of historical data, determining layout parameters of the well-ground electromagnetic detection system; arranging a well-ground electromagnetic detection system based on the arrangement parameters, and collecting original field time sequence data; determining frequency data based on the original field time sequence data; carrying out current normalization processing based on the frequency data to obtain amplitude and phases under different harmonic waves; determining a three-dimensional data volume of the excitation section based on the amplitude and the phase under each harmonic wave; the three-dimensional data volume comprises a three-dimensional space differential phase data volume, a three-dimensional resistivity inversion data volume and a three-dimensional space differential resistivity data volume; and based on the three-dimensional data volume, determining the water-containing property and the fracture communication condition of the excitation section. According to the invention, the capability of distinguishing the artificial crack is improved.

The invention relates to an intelligent data classified storage method and system based on deep learning, and the method comprises the steps: obtaining an original data set, and obtaining a multi-dimensional data set after preprocessing; acquiring a frequency statistical set of the data, and fitting the frequency statistical set by adopting a least square method to obtain an access frequency predicted value of each type of data; generating a high-frequency or low-frequency data identifier for the corresponding data according to the comparison condition of the access frequency predicted value and a preset frequency threshold value; constructing a high-frequency data list and a low-frequency data list; obtaining a storage cost weight and an access delay index of the storage node according to the storage position index; calculating a storage efficiency score of each storage node; the distribution proportion of each storage node is calculated, adjustment is carried out through storage efficiency scores, and a multi-level storage distribution scheme is generated; after a corresponding migration instruction is generated according to the multi-level storage allocation scheme, data migration is carried out, and hierarchical classified storage of the data is achieved. The system storage resource utilization rate can be improved.

The invention discloses an equivalent inertia online measurement method, system and device, and a storage medium. The method comprises the following steps: obtaining frequency data and active power data of a grid-connected point in a specific time period before and after disturbance power injection; carrying out smoothing processing on the obtained frequency data and the active power data; determining a frequency steady-state value and an active power steady-state value before and after disturbance; calculating a steady-state power difference value between the active power steady-state values before and after the disturbance and a steady-state frequency difference value between the frequency steady-state values before and after the disturbance; determining an equivalent damping parameter of the to-be-tested unit or the to-be-tested station; calculating the damping power at each moment in the disturbance generation process; calculating inertia power at each moment in the disturbance generation process; calculating the frequency change rate of each moment in the disturbance generation process; and in a selected specific time period, determining the equivalent inertia of the to-be-tested unit or the to-be-tested station.

The invention relates to the technical field of power system frequency stability control, in particular to a power system inertia online evaluation method and device, equipment and a medium, and the method comprises the steps: obtaining frequency deviation data and active power data of each node, carrying out the low-pass filtering of the frequency data, and calculating the amount of active unbalance; an inertia response model is constructed based on the rotor motion equation of the synchronous generator, and inertia and damping coefficients are estimated by using a least square method; constructing a transfer function and judging the stability of the transfer function, if the transfer function is stable, inputting an active unbalance amount to obtain a frequency deviation predicted value, and calculating a Pearson correlation coefficient with an actual frequency; different time periods are selected through a sliding window to repeat the process, finally, the inertia corresponding to the maximum Pearson's correlation coefficient is selected as a system inertia evaluation result, the inertia level of the system can be accurately evaluated on line through the method, and therefore data support is provided for frequency control, and the frequency stability and safety of the system are guaranteed.

The invention provides a CFRP plate elastic constant inversion method based on zero group velocity point wave number-frequency, and belongs to the technical field of nondestructive testing of carbon fiber composite plates. In order to solve the problems that in the nondestructive testing process of the CFRP plate, a complete elastic constant matrix of the composite material cannot be obtained and the obtained elastic constant has obvious errors, the method comprises the following steps: calculating frequency dispersion curves in different directions according to the elastic constant of the carbon fiber composite material plate; obtaining theoretical wave number-frequency data based on the wave number-frequency data; carrying out full wave field scanning on the surface of the carbon fiber composite material plate, carrying out three-dimensional Fourier transform on time domain data obtained by the full wave field scanning, and extracting to obtain actually measured wave number-frequency data; and constructing an objective function of an error between the wave number-frequency data corresponding to the theoretical data and the actually measured data ZGV frequency point, and performing multi-parameter optimization on the objective function by using a particle swarm algorithm to obtain an inversion result of the elastic constant of the carbon fiber composite material plate.