80 results about "Linear relation" patented technology

The invention discloses a safety monitoring system of a liquid cooling over-charging pile, and relates to the technical field of over-charging pile monitoring, the system comprises a data acquisition module, a data processing and analysis module, a dynamic model construction module, a temperature prediction module and a safety early warning module; according to the method, the dynamic model is constructed through the long short-term memory network LSTM, the complex nonlinear relation and the time sequence dependence of the multi-dimensional data are mined by using the gating mechanism of the dynamic model, the accurate characterization of the operation state of the liquid cooling over-charging pile is realized, the actual operation state of the equipment can be accurately described, the temperature data time sequence modeling is performed through the LSTM, and the accuracy of the temperature data time sequence modeling is improved. Parameters such as multi-source temperature and cooling liquid flow are fused, real-time prediction of the temperature change trend is achieved, the defect that a traditional algorithm is insufficient in temperature time sequence dependence capture is overcome, temperature abnormity can be recognized in advance, a safety threshold value is dynamically adjusted through a fuzzy logic algorithm, and self-adaptive threshold value adjustment is achieved in combination with parameters such as charging power. The problem that a traditional fixed threshold value is poor in adaptability is solved, and the early warning accuracy is improved.

The invention relates to the field of foundation detection and multi-source big data intelligent analysis, and discloses a multi-source big data intelligent analysis fusion processing method based on foundation detection equipment, and the method comprises the following steps: carrying out the standardization processing, sampling frequency unification, missing value filling, and completion time and space alignment of multi-source data collected by the foundation detection equipment; based on the preprocessed multi-source data, constructing a similarity weight matrix between the data points for measuring the correlation between the data points; a manifold learning algorithm is adopted to embed multi-source data into a low-dimensional manifold space, and low-dimensional embedding representation used for describing a data local geometric structure is constructed; the method is based on a high-order Gaussian process model. By introducing the high-order Gaussian process method of multi-modal interaction modeling, the internal correlation of the modals and the complex interaction relationship between the modals can be comprehensively described. The problem that the nonlinear relation of the multi-modal data cannot be captured is solved, and more accurate feature extraction and fusion of the data are realized.

The invention relates to a sea fog quantitative forecasting method based on a period enhanced Transform, and the method comprises the steps: firstly constructing a Transform model as a forecasting model, enabling the Transform model and a self-attention mechanism to better capture the complex nonlinear relation and long-distance time dependence related to the formation of sea fog, and being superior to a conventional statistical method and an early-stage RNN / LSTM model, a data set for model training is constructed based on a time period enhancement technology and visibility standardization mapping, and the explicit time period enhancement technology enables the model to more accurately learn and forecast seasonal and daily change rules of sea fog; and a sample amplification and training set balancing strategy is executed on the data set, so that the problem of sparse fog samples is effectively solved, and the forecasting capability of the model on key low-visibility events is improved. According to the sea fog quantitative forecasting method based on the period enhanced Transform, the precision, timeliness (forecasting per hour) and spatial resolution of sea fog forecasting of a target area can be improved, and sea fog data characteristics can be effectively processed.

The invention provides an abnormal data detection and recovery method and system for reports of a water plant management and control platform, and relates to the technical field of water plant data detection.The abnormal data detection and recovery method comprises the steps that report data of the water plant management and control platform are collected, then the threshold range of the report data is obtained through threshold detection, and the report data exceeding the threshold range are marked as potential abnormal data; performing exception scoring on each potential exception data in the report data by adopting an exception detection model, and then marking the potential exception data with an exceptional exception scoring result as burr data points; and deleting each burr data point in the report data, and then estimating missing data points by utilizing a linear relationship between adjacent data points of the deleted burr data points to carry out linear interpolation so as to carry out data recovery on the report data. The method has the beneficial effects that the accuracy and stability of data analysis of the water plant management and control platform are improved through multi-stage anomaly detection, and efficient detection and recovery of abnormal data are realized through combination of statistical analysis and machine learning technologies.

The invention provides a method for selecting a high-concentration VOCs adsorbent at different temperatures and application, and belongs to the technical field of waste gas governing. According to the method, through testing pore structure parameters of a model adsorption material with concentrated pore size distribution, a static adsorption isotherm and a dynamic penetration curve for VOCs at different temperatures, a high-concentration VOCs adsorbent is obtained; a linear relation equation of the critical aperture and the critical pressure is established through linear fitting, then a correlation equation of the critical aperture, the temperature and the partial pressure is established, and the appropriate aperture distribution range and the model selection standard of the high-concentration VOCs adsorbent at different temperatures are determined by combining dynamic adsorption results. According to the method, the ternary matching relation equation of the VOCs partial pressure, the temperature and the critical aperture is constructed, accurate type selection of the high-concentration VOCs adsorbent at different temperatures is achieved, the pore volume utilization rate and the adsorption capacity can be improved, meanwhile, desorption energy consumption and the VOCs pyrolysis risk are reduced, and a theoretical basis is provided for adsorbent type selection and technical optimization.

The invention discloses a runoff prediction method based on multi-source data fusion, and relates to the technical field of model prediction, and the method comprises the following steps: S1, data source selection and collection; s2, data preprocessing; s3, designing a data fusion strategy; s4, feature extraction and selection; s5, model selection and construction; s6, model training and verification; s7, optimizing and improving the model; and S8, runoff prediction and result analysis. According to the runoff prediction method based on multi-source data fusion, through fusion of multi-source data and introduction of multiple deep learning models, the capture ability of the model to a complex non-linear relationship is enhanced, and the physical consistency and the coping ability to an extreme event are also ensured; a more comprehensive runoff prediction result is provided, the prediction robustness and the reliability of an analysis result can be improved, and the defects that a traditional model is single in data source, poor in physical consistency, insufficient in prediction uncertainty analysis and the like are overcome.

The invention discloses a bridge longitudinal and transverse displacement reconstruction method and system based on time sequence feature extraction, and relates to the technical field of bridge health monitoring. The method comprises the following steps: acquiring structural state data and environmental data of a continuous beam bridge and a cable-stayed bridge; analyzing a linear relation between the structure state data and the environment data by using a correlation coefficient analysis method; processing the related characteristics by using the bridge displacement reconstruction model to obtain three-dimensional displacement data of bridge reconstruction; and based on the obtained three-dimensional displacement data of the bridge reconstruction, screening key factors in related characteristics through a grid search algorithm, and optimizing the input of a bridge displacement reconstruction model. According to the method, the time sequence characteristics of the data are fully monitored to construct the De-SpcNet-based bridge displacement reconstruction model, so that the reconstruction precision of longitudinal and transverse displacement is improved. And then, model output is optimized through refined model parameter setting and a post-processing technology, so that the accuracy and stability of a reconstruction result are further improved.

The invention belongs to the related technical field of capacitor life prediction, and particularly relates to a metallized film capacitor life prediction method, which comprises the following steps: carrying out an aging simulation test on a sample capacitor, cooling the sample capacitor after each round of test, measuring the capacitance of the sample capacitor, and calculating the capacitance attenuation value under each round; when the capacitance attenuation value and the number of turns reach preset values, fitting to obtain a linear relationship between the number of turns and the capacitance attenuation value, thereby obtaining a corresponding turn when the capacitance is attenuated to a performance deterioration index, and obtaining attenuation duration according to the turn; wherein the preset value corresponding to the capacitance attenuation value is smaller than the performance deterioration index; and according to the attenuation duration and other simulation experiment parameters and actual working condition data required by the capacitor failure life evaluation and prediction theoretical model, calculating the service life of the metallized film capacitor under the actual working condition by adopting the capacitor failure life evaluation and prediction theoretical model. The method can simply and conveniently predict the operation life of the metallized film capacitor.

The invention provides an energy efficiency evaluation and intelligent diagnosis method for a process industrial production system, and the method comprises the steps: determining an energy efficiency evaluation index, building an energy balance equation, and calculating the heat efficiency, efficiency and energy consumption of each equipment, production process and system according to the equipment characteristics, process matching and overall production process in industrial production; an industrial production process database is constructed, and data preprocessing is carried out; based on the industrial production process database, quantitatively evaluating the influence of each parameter on heat efficiency, efficiency and energy consumption by adopting a grey relational analysis method, and taking the parameter with relatively high influence as a key parameter; linear relations between the key parameters and the heat efficiency, efficiency and energy consumption are analyzed by constructing a multiple regression model; carrying out hierarchical division on key parameters, screening a reference working condition based on similarity analysis K-Means clustering, determining and comparing an optimal working condition with an actual working condition, implementing intelligent diagnosis, taking energy consumption as a core evaluation target, determining an optimal production mode, and carrying out auxiliary decision making.

The invention discloses a seismic oscillation parameter selection and high arch dam response prediction method based on random forest-recursive feature elimination. The method comprises the following steps: (1) constructing a high arch dam finite element model; (2) seismic oscillation input of a finite element is obtained, and nonlinear seismic response of the arch dam under the seismic oscillation input is obtained through nonlinear dynamic time-history analysis; (3) taking the output parameters as a data set to obtain an optimal feature set of the high arch dam; and (4) on the basis of the obtained optimal IM feature set of the high arch dam and the corresponding random forest model, in combination with seismic oscillation input data, predicting a response result of the high arch dam through sampling. According to the seismic oscillation parameter selection and high arch dam response prediction method based on random forest-recursive feature elimination, the complex nonlinear relation between the features can be fully captured, the interaction between the features can be better considered, the complexity of the model can be better controlled, too many or too few features are prevented from being selected, the over-fitting risk is reduced, and the method is suitable for large-scale popularization and application. The performance and the effect of feature selection are improved.

The invention discloses a carbon market price prediction method considering multi-dimensional influence factors, and relates to the technical field of carbon market price prediction, comprising the following steps: obtaining carbon market price influence data including energy factor influence data and index influence data; obtaining text data of carbon market internal cause information, processing the text data of the carbon market internal cause information based on a natural language to obtain a plurality of keyword vectors, and obtaining a comprehensive feature vector of the carbon market internal cause information based on cross fusion of the plurality of keyword vectors; obtaining a carbon market price prediction model based on the comprehensive feature vectors of the carbon market price influence data and the carbon market internal cause information on the basis of SVR (Support Vector Regression); and generating short-term and long-term carbon market price curve graphs according to the carbon market price prediction model, and judging the carbon market price prediction trend according to the short-term and long-term carbon market price curve graphs. Through the SVR technology, the problem that the accuracy of a prediction model is reduced due to the fact that data collection and considered factors are often not perfect enough is solved. And some models may have limitations when processing a nonlinear relationship and multivariable interaction, resulting in insufficient predictive ability.

The invention relates to a UHPC-NC interface mechanical property prediction method and system considering a size effect, and the method comprises the steps: preparing a target test piece, collecting original data through a direct shear test and a pull-out test, and obtaining a shear stress-displacement curve and a tensile stress-displacement curve according to the original data; extracting shear performance parameters and a linear relation according to the curve, carrying out fitting analysis on the shear performance parameters to obtain a shear size effect law, further defining a shear macroscopic constitutive model, and carrying out fracture mechanical quantitative evaluation on the shear performance parameters to obtain a shear macroscopic constitutive model. Deriving and constructing a prediction expression of shear resistance and a shear-displacement constitutive model according to a quantitative evaluation result; extracting tensile property parameters according to the curve, performing series analysis on the tensile property parameters to obtain an interface tensile relationship, performing probability distribution analysis on the tensile property parameters to obtain a tensile size effect law, and performing derivation according to the interface tensile relationship and the tensile size effect law to obtain a tensile property prediction expression and a tensile-fracture constitutive model.

The invention discloses an automatic classification prediction method for researching natural gas exploration workload, and the method comprises the steps: building an automatic classification model based on multiple regression: supposing that all sample data are x1n, x2n... xpn, the number of influence indexes is p, the number of all sample data is n, and the exploration workload is y, classifying according to different linear relationships between all exploration workloads and all sample data; and constructing prediction sample data, and calculating the exploration workload of the prediction sample data by the automatic classification model. The problem that an existing prediction method is based on experience or simple statistical analysis and lacks systematicness and accuracy is solved. The method is simple in principle, easy to implement and short in calculation time consumption, adopts automatic classification, automatic optimization and automatic prediction, and has very wide application prospects.

The invention discloses an object tiny deformation measurement method and system based on interference fringe analysis, and belongs to the technical field of optical measurement. The method comprises the following steps: acquiring an interference fringe image and probe position and direction data; carrying out phase demodulation and sensitivity vector calculation on the surface of a measured object; obtaining the local phase number of each probe according to the interference image; calculating sensitivity vector data through a geometrical relationship; obtaining global phase and sensitivity data, obtaining initial full-field phase data through a weighted fusion method based on a geometrical relationship between a sensitivity vector and a deformation direction, calculating a consistency error, judging whether the consistency error exceeds a threshold value or not, if so, updating a deformation direction estimation value, and executing fusion processing again; and solving and obtaining three-dimensional deformation field data through a linear relation until the error meets the requirement or reaches the maximum number of iterations. According to the invention, the reliability and early warning capability of structural safety assessment in long-term monitoring can be improved.

The invention provides a double-layer safe trainable quantum machine learning method based on polynomial dynamics Lie algebra, and the method comprises the following steps: 1, constructing core variation simulation meeting the constraint of the polynomial dynamics Lie algebra, and guaranteeing the trainability of a model; 2, performing truncated Chebyshev graph coding at an input end, and constructing a rugged loss function landscape by using graph state entanglement and a Chebyshev tower strategy to prevent a snapshot inversion attack; 3, executing dynamic local scrambling at an output end, applying time-varying random local unitary transformation before measurement, and confusing a linear relation between gradient and a snapshot to prevent recovery attack of the snapshot; and 4, measuring and calculating a loss function, and updating parameters. According to the method, an orthogonal decoupling strategy is adopted, a privacy protection mechanism is externally arranged on an input / output interface, and trainability is anchored to core configuration, so that the capability of resisting algebraic attacks is remarkably improved while model convergence is ensured.

The invention belongs to the field of oil exploration, and relates to a TOC prediction method and device for a shale reservoir, electronic equipment and a computer readable storage medium. Comprising the following steps: 1, collecting logging data, and constructing a rock physical model; 2, carrying out intersection analysis on different elastic parameters and TOC, and screening out the elastic parameter with the best linear relation with the TOC as a sensitive elastic parameter; 3, decomposing the cross plot of the sensitive elastic parameters and the TOC, dividing the range of the characteristic logging data, obtaining the cross plot of the sensitive elastic parameters and the TOC in the range of the specific characteristic logging data, and establishing a linear relation; step 4, based on the pre-stack seismic data, performing inversion on the pre-stack three parameters to obtain an elastic parameter body; and step 5, calculating a TOC value based on the linear relation and the elastic parameter body. According to the method, the problem that the linear relation between the elastic parameters and TOC intersection analysis is not obvious can be effectively solved, and a calculation model better conforming to the actual situation is constructed.

The invention discloses a combined system error correction and target state estimation method based on multi-angle measurement, which is applied to a three-dimensional passive multi-sensor multi-target tracking system. Comprising the following steps: constructing an augmented state vector based on a target state vector, an angle measurement deviation vector, a time deviation vector and a sensor position vector, and constructing an augmented state transition equation; performing modeling by taking azimuth angle measurement, pitch angle measurement and sensor position measurement as functions of an augmented state vector, constructing an augmented measurement vector and an augmented measurement equation, and determining a nonlinear relationship between the constructed augmented measurement vector and augmented state vector; azimuth angle measurement, pitch angle measurement and sensor position measurement are obtained through actual measurement, and an augmented state vector is estimated through linearization of a non-linear relation between a constructed augmented measurement vector and an augmented state vector and sequential filtering. The method can be applied to multi-source information fusion under a passive multi-sensor system, and the tracking and positioning precision of the target is improved.

The invention provides a clinical image-based cancellous bone mechanical property prediction method and system, and the method comprises the steps: carrying out the medical CT scanning of a plurality of prepared cancellous bone cubic samples, and obtaining the medical CT image data; carrying out segmentation processing on the medical CT image data, extracting a sample area and calculating an average HU value of a sample CT image; performing a uniaxial compression experiment on the sample, accurately measuring strain by using a digital image correlation method, and further obtaining a stress-strain curve to calculate an elastic modulus and compression strength; according to the average HU value and the corresponding mechanical index data, a linear relation model of the average HU value of the cancellous bone CT image and the elastic modulus and the compression strength of the cancellous bone is established, and then a personalized treatment scheme is formulated according to the characteristics of the cancellous bone of the patient. The method has high universality and accuracy, and the elastic modulus and the compression strength of the cancellous bone sample can be accurately measured.

Systems and methods for quantum linear prediction include autocorrelations formed with QFTs, and a modified quantum HHL circuit that includes appropriate normalization and encoding steps for solving a linear system of equations, including normalization of the quantum autocorrelation sequence using a norm factor; measuring a probabilistic distribution associated with values of a quantum state solution vector representing a set of quantum autoregressive parameters that correlate with a linear relationship between the quantum autocorrelation matrix and the quantum autocorrelation sequence; and generating a set of quantum linear prediction coefficients by re-normalization of the quantum state solution vector using the norm factor associated with the quantum autocorrelation sequence of the preprocessed input.

The embodiment of the invention provides a bar tolerance measurement method and device based on flying shear length measurement, and the method comprises the steps: determining a current weight ratio parameter according to historical data in a preset time period, the historical data comprises a multi-length shear length measurement data sequence, a flying shear length measurement data sequence, a corresponding finished product bundle weighing data sequence and a finished product bundle theoretical weight, and the current weight ratio parameter is used for representing a linear relation between flying shear length measurement and bar tolerance; according to the current weight ratio parameter, a preset linear model of flying shear length measurement and bar tolerance is updated, and an updated linear model is obtained; inputting the current flying shear length measurement data and the current double-length shear length measurement data into the updated linear model to obtain a current bar tolerance measurement value; according to the method, the bar tolerance measurement model can be designed based on the flying shear length measurement data with higher data precision and higher data stability to calculate the bar tolerance in real time, and the bar tolerance measurement precision is effectively improved.

A method for calculating coordinates of a multi-station fixture of a vertical machining center comprises the following steps: determining a reference point of the fixture and a plurality of stations on the fixture, and measuring the distance between the plurality of stations and the reference point of the fixture to obtain a linear relation between origin coordinates of the plurality of stations and reference coordinates; according to the linear relation between the reference point of the clamp and the zero point of each station, the station zero point coordinate is determined; the linear relation serves as a reference, conversion of a plurality of station coordinate systems is carried out when a machining program is compiled, and the machining zero point of the workpiece to be machined is determined; the clamp is installed on the vertical machining center, and mechanical coordinates of the clamp datum point on the vertical machining center are collected; and inputting the collected mechanical coordinate value of the reference point of the clamp into a vertical machining center system. By means of the method, conversion between the reference coordinate system and the station coordinate system is achieved, on the basis, only coordinate data of the reference original point need to be collected and input into the vertical machining center system when the clamp is replaced every time, and the method is simple in operation step, rapid and high in accuracy.

The invention discloses a carbon emission intensity prediction simulation and land utilization management and control method and system, and belongs to the technical field of carbon emission calculation prediction.The method comprises the steps that firstly, multi-source space and statistical data are integrated to establish a basic database, and the carbon emission intensity of all kinds of space is calculated according to land space classification; then, constructing an extended STIRPAT model to screen a core driving factor, and constructing a feature project containing residual, lag and trend features based on the output of the extended STIRPAT model; training an XGBoost machine learning model by adopting a Bayesian optimization algorithm so as to capture a complex nonlinear relationship between the carbon emission intensity and the influence factors; and finally, inputting future scene feature data, generating a territorial space carbon emission intensity distribution map in combination with a PLUS model, and identifying a high-emission hot spot region. According to the method, the problem that the technical progress influence is difficult to quantify and the spatial explicit prediction is difficult to carry out in the prior art is solved, the prediction precision is remarkably improved, and a scientific basis and decision support are provided for regional territorial space planning and low-carbon management and control.

The invention discloses a method and a system for calculating the mixing proportion of multi-end-member water mass mixed particles. The method comprises the following steps: calculating the contribution proportion of each water mass end member of a mixing area by adopting an isotope mixing model; generating initialization information of a multi-end-member water mass mixed particle model by using the delta < 18 > O and salinity of each end member and derivative information; based on the contribution proportion and the initialization information, constructing a multi-end-member water mass mixed particle model; simulating a simulated delta < 18 > O-salinity linear relation of a mixing area under all iterative mixing proportion combinations based on a multi-end-member water mass mixed particle model; and calculating the mixing ratio of each end member by comparing the simulated delta 18O-salinity linear relationship with the actual delta 18O-salinity linear relationship. According to the method, the multi-end-member water mass mixed particle model is constructed, and iterative calculation and fluctuation simulation are combined, so that accurate quantification of a water mass mixing ratio and quantitative analysis of mixing sufficiency are realized.

The invention provides an air source heat pump frosting rate prediction method and system, and belongs to the technical field of air source heat pump defrosting control. The method comprises the steps that initial parameters needed by prediction are obtained, wherein the initial parameters comprise the outdoor air temperature and relative humidity, the outdoor heat exchanger coil pipe surface temperature and relative humidity and the outdoor heat exchanger air inlet speed; determining air state parameters at the outlet of the outdoor heat exchanger through iterative calculation on the basis of the initial parameters in combination with a linear relation of humid air state change in the enthalpy-humidity diagram; and finally, the real-time frosting rate is calculated according to the air moisture content difference, the air mass flow and the heat exchange area of the inlet and the outlet of the outdoor heat exchanger. The system comprises a corresponding parameter acquisition and calculation module. According to the method and system for predicting the frosting rate of the air source heat pump, accurate dynamic prediction of the frosting rate is achieved through theoretical modeling and iterative optimization, a reliable basis can be provided for intelligent defrosting control, and therefore the defrosting accuracy rate and the overall energy efficiency of the system are improved.

The application provides a significant wave height extraction method based on a synthetic aperture radar image, step 1: data acquisition, matching the altimeter significant wave height with the synthetic aperture radar interferometric imaging mode data to obtain a sample data set. Step 2: the data amount of the altimeter significant wave height in different incidence angle ranges is counted to obtain the numerical distribution of the altimeter significant wave height in the global near-shore range. Step 3: the normalized variance of the backscattering coefficient of the synthetic aperture radar and the altimeter significant wave height are subjected to quality control to obtain the significant wave height and normalized variance data. Step 4: a linear relationship between the significant wave height and the normalized variance is established. Step 5: the estimated value of the synthetic aperture radar significant wave height is evaluated and verified, and the significant wave height can be obtained by inputting only a single image parameter, the normalized variance. The application not only considers the synthetic aperture radar open ocean wave mode, but also relates to the near-shore research, and provides technical support for the development of related topics in the coastal area.

The invention relates to the technical field of settlement monitoring, and discloses a building accurate settlement monitoring and early warning system, which is characterized in that a measuring point module is provided with a near-side representative pile, a far-side representative pile, a pressure measuring pipe and a displacement acquisition device to respectively acquire axial force, underground water level and base displacement data; a parameter calculation module calculates a bearing share asymmetry index, an underground water level equivalent drawdown and an effective stress substitution amount, and eliminates a time trend term to obtain a base displacement residual error; the period and path analysis module divides closed periods according to the periodical characteristics of the equivalent depth reduction of the underground water level, forms parameter paths in all the periods, calculates directed areas and determines net drift amount; the mapping and prediction module establishes a linear relation between a directed area and a net drift amount based on the multi-cycle data to obtain an area drift mapping amount; the judgment module checks whether the area drift mapping amount is zero or not under a predetermined significance level, if yes, output is abnormal, and if not, output is normal.

The invention discloses a model quantification method, a model operation method, equipment, a medium and a program product. The quantification method comprises the following steps: grouping model parameters of each network layer in a to-be-quantified model; determining a quantization parameter group of any group according to a target integer digit required by the network layer to which any group belongs, and quantizing the model parameter of any group according to the quantization parameter group; and replacing the corresponding model parameters in the to-be-quantized model with the quantized model parameters of each group to obtain a quantized model. Model parameters are grouped to be quantized, so that the influence of outliers existing in the model parameters on quantization errors is reduced. When quantization is carried out according to the groups, due to the fact that the quantization parameters in the quantization parameter groups are in a non-linear relation, quantization can be completed on the model parameters in the groups in a non-linear mapping mode according to the quantization parameter groups, and the result generation capacity during model operation is ensured.

The invention discloses a dam deformation space-time prediction method and device based on Kriging interpolation, and relates to the technical field of dam safety monitoring, and the method comprises the steps: carrying out the cleaning and unified processing of dam multi-source heterogeneous deformation monitoring data, including unifying a coordinate reference and carrying out the data fusion through a linear relation, forming a data set of a unified time vector; then, fitting data of each monitoring point and predicting future moments by using regression models such as Fourier series and the like; and after the consistency of the prediction result is checked, the kriging interpolation algorithm is adopted to carry out spatial interpolation on the predicted data passing the check, the space-time continuous deformation field of the dam is finally generated, and when newly added data exist, the process is repeated to update the model, the problems of space-time discretization and difficult fusion of the deformation data in the prior art are effectively solved, and the prediction accuracy of the dam is improved. High-precision and time-space continuous dam deformation prediction can be realized, and a reliable basis is provided for dam safety analysis.

The invention relates to a mathematical modeling method for FPC contact deformation based on segment analysis and solution of nonlinear equation groups, which is used for analyzing the deformation of a flexible printed circuit (FPC) when it contacts with other components. The core steps include: dividing the FPC into different segments based on contact points; linearizing the relationship between the curvature of the FPC and the length of a path along the surface of the FPC in different FPC segments, and obtaining a series of unknowns, such as the slope and intercept in the linear relationship; in addition, the specific coordinates of the contact points and the length of each FPC in different segments are also used as unknown parameters to be solved; the known relationships include the coordinate difference and angle difference at the two ends of different segments, and the curvature at the connecting points of the head and the tail of different segments must be equal; and at the same time, using the Jacobian matrix iteration method and the size iteration method to solve all unknowns, and finally obtaining the deformation curves of the FPC under different contact conditions with other components that need to be solved.

The application discloses a bridge abnormal point identification method and device based on a multi-granularity time window, and the method comprises the following steps: acquiring a plurality of sample data of a bridge by using a real-time monitoring system; constructing a sample initial feature vector representation of a sliding time window, and fusing the sample initial feature vector representation to construct a sample initial feature matrix representation; fitting a linear relationship and a nonlinear relationship of sample neighborhood features of the sliding time window; based on the linear relationship and the nonlinear relationship, fusing linear residual and nonlinear residual block features to identify an abnormal probability value of a sample, and calculating the abnormal probability value of the sample to label an abnormal sample; and identifying abnormal values in the plurality of sample data by using the labeled abnormal sample to identify a bridge abnormal point. The application predicts an abnormal probability of a sample from potential neighborhood features of the sample in a multi-granularity sliding time window, realizes identification of abnormal data points, and provides great support in bridge structure health monitoring data anomaly diagnosis.