712 results about "Gaussian process" patented technology

The invention relates to the technical field of high temperature sensing and data fusion, in particular to a method for array thermocouple multi-mode compensation and DIC stress field space-time coupling fusion, which comprises the following steps: step 1, in a thermotechnical signal intelligent processing and compensation unit, completing hardware and algorithm collaborative design of an electronic cold junction compensation module; 2, constructing a multi-algorithm fusion compensation module, integrating nonlinear correction, drift compensation and interference suppression functions, and accurately coping with various interference signals through a dynamic weighting strategy; step 3, adopting a sub-pixel-level matching algorithm and a homography matrix calibration technology to realize high-precision space alignment of the temperature and stress measurement units; and establishing a nonlinear incidence relation between the temperature and the stress based on an improved Gaussian process regression model. According to the invention, based on collaborative design of the thermotechnical signal intelligent processing and compensation unit and the DIC vision and temperature data conjoint analysis module, the core precision problem of temperature and stress detection in a high-temperature environment is solved through hardware optimization and algorithm innovation.

The invention relates to the technical field of computer information processing, and discloses a high-fidelity terrain surface interpolation method and system for large-scale point cloud data, and the method comprises the steps: carrying out the multi-level cleaning of original point cloud data, and generating a cleaned point cloud data set; performing adaptive tile grid division based on the cleaned data to generate a tile set covering the target area; in each tile, taking the to-be-interpolated grid point as a query point, constructing and optimizing a local Gaussian process model, and obtaining a real elevation predicted value of the query point; processing all query points in the tiles in parallel to obtain a tile elevation interpolation result set; performing weighted average on each tile result to generate a global seamless terrain surface; according to the method, the problems of poor expandability and surface discontinuity caused by local interpolation in large-scale point cloud data processing are effectively solved, and high-precision and high-fidelity terrain surface construction is realized.

The invention belongs to the field of material performance optimization, and particularly discloses a carbon ceramic resistor formula optimization method based on a genetic algorithm and Bayesian optimization, and the method comprises the steps: receiving formula parameter combinations and corresponding performance parameters of a plurality of groups of carbon ceramic resistors; a Gaussian process regression model based on a radial basis kernel function is established to construct a mapping relation between formula parameters and performance parameters, and a performance prediction model of the carbon ceramic resistor is obtained through training by maximizing marginal likelihood optimization model hyper-parameters; and based on the performance prediction model, performing joint optimization by using a genetic algorithm and a Bayesian optimization algorithm, and determining an optimal formula combination. According to the method, global exploration and local fine convergence can be considered, the prediction efficiency can be improved, and the accuracy, comprehensiveness and reliability of a prediction result can be improved.

The invention discloses a Bayesian algorithm-based swivel bridge spherical hinge structure optimization design method, which is characterized in that a parameterized model of a swivel bridge spherical hinge structure is constructed, and a finite element simulation technology and a Bayesian optimization algorithm are combined, so that multi-target global optimization design is realized. The method specifically comprises the following steps: establishing a refined finite element model of the swivel bridge spherical hinge; defining input design variables (spherical radius, supporting radius, pin roll radius and the like) and output optimization targets (maximum contact stress, horizontal and vertical friction moment); adopting Latin hypercube sampling (LHS) to generate a plurality of groups of initial parameter combinations; dynamically selecting a high-value parameter combination through a Bayesian optimization framework to carry out finite element simulation; training a Gaussian process agent model and carrying out iterative optimization; and quantizing the parameter sensitivity and outputting a Pareto optimal solution set. According to the method, the simulation frequency can be remarkably reduced, the design efficiency is effectively improved, and the problem that traditional experience design is prone to falling into local optimum is solved.

The invention discloses a linear guide rail optimization design method and device, a medium and a program product, and the method comprises the steps: (1) constructing a simulation model and a MaOP design model which can optimize the rigidity, modal and weight at the same time based on the linear guide rail structure and static load analysis; (2) generating an elite population based on a Latin hypercube and diversity criterion, obtaining target values of the elite population, establishing a database, and constructing a Gaussian process function model; (3) designing mixed mutation operation based on OCC to generate a filial generation guide rail set; (4) designing a DEP-driven DPM evolutionary strategy to generate a candidate guide rail set, and selecting an optimal candidate guide rail; and (5) obtaining each target value of the optimal candidate guide rail, updating the database and the Gaussian process function model, returning to the step (3) until all optimization targets meet requirements, and outputting an optimal parameter value. According to the method, the MaOP process aiming at the rigidity, the modal and the weight of the linear guide rail can be effectively balanced, and higher precision and better comprehensive performance are achieved.

The invention discloses a learning-based composite layered anti-interference control system and method suitable for a large-windward-area unmanned aerial vehicle, is used for realizing robust wind resistance control of the large-windward-area unmanned aerial vehicle, and aims at the flight characteristics of large windward area and sensitivity to external wind field change in a vertical take-off and landing stage. A wind speed estimation method without an additional sensor is provided, modeling of external disturbing force is realized in combination with a Gaussian process regression algorithm, and compensation of the disturbing force is realized by using quaternion-based model prediction control, so that the influence of an external change wind field on the dynamics of the large-windward-area unmanned aerial vehicle is reduced, and the trajectory tracking precision is remarkably improved. A backstepping controller based on SO (3) is designed in an attitude control loop, a nonlinear disturbance observer is integrated, and active compensation of external disturbance torque and robust tracking control of attitude are realized. Based on the technical characteristics, a complete dynamic control link capable of estimating and feeding back compensation disturbance in real time is further constructed.

The invention relates to the technical field of digital twinning, physical modeling and multi-source data fusion, and provides a digital twinning dynamic construction method based on multi-source data fusion and physical simulation. The method comprises the following steps: acquiring a multi-source heterogeneous data stream from a preset sensor array, a numerical simulation result and a historical database, identifying a key feature mode of a dominant physical process in the multi-source heterogeneous data stream, acquiring a key feature mode time-varying physical field evolution rule corresponding to the key feature mode by using a time sliding window and a forgetting mechanism, extracting a low-dimensional sparse characteristic parameter set reflecting dynamic behaviors from a high-dimensional observation space, and constructing a reduced-order proxy model by adopting Gaussian process regression, a neural network proxy model or an intrinsic orthogonal decomposition combined interpolation technology; and receiving a corresponding real-time observation data stream to establish a full-closed-loop feedback link from model prediction, high-fidelity solution verification to observation data correction in combination with the reduced-order proxy model so as to complete the construction of the digital twin.

The invention relates to the technical field of ship energy consumption prediction, and discloses a ship energy consumption interval prediction method and system based on a Gaussian quantile regression model.The method comprises the steps that firstly, a ship navigation historical data set is preprocessed, a model input feature set is screened, a Gaussian process quantile regression model with a radial basis function as a kernel is constructed, and hyper-parameters are optimized; and after the prediction performance of the subset evaluation point is verified through the model, an upper quantile prediction model and a lower quantile prediction model are respectively established according to a target confidence level, and finally a prediction interval is synchronously output and an evaluation report is generated. According to the method, through combination of Gaussian process processing nonlinear relation and quantile regression estimation condition distribution, high-precision point prediction is provided, meanwhile, prediction uncertainty can be quantized, an energy consumption prediction interval corresponding to a target confidence level is output, and more comprehensive and reliable information support is provided for ship energy efficiency management and operation decision making.

The invention provides a virtual sample generation method and system based on a non-stationary neural network Gaussian process, and the method comprises the steps: obtaining original data, judging the non-stationarity, and judging whether a statistical characteristic changes with an input position or not; if not, a hidden variable model fusing the neural network and the Gaussian process is constructed, and a hidden variable space representing non-stationary distribution is obtained through training; sampling based on hidden variable space probability distribution; using the model to generate = (, Z) (Z, Z)-1X through non-stationary high-dimensional mapping, which is a non-stationary kernel function, Z is a low-dimensional hidden variable, and X is an input variable; checking the consistency of the high-dimensional virtual samples and the original data, and screening a virtual sample set meeting statistical consistency; according to the method, high-quality and high-diversity virtual samples can be generated in small sample and non-stationary scenes.

The invention belongs to the technical field of power equipment signal processing, and particularly relates to a multi-channel signal reverberation suppression method based on phase weighted cross-correlation optimization, which comprises the following steps: S1, acquiring an original multi-channel time domain signal matrix; s2, estimating propagation time delay of each channel relative to the reference channel; s3, enabling all channels to realize time domain alignment in a direct sound main energy section; s4, processing to obtain a multi-channel time-frequency domain signal; s5, performing reverberation suppression by adopting a WPE algorithm to obtain a multi-channel time-frequency domain signal after reverberation removal; before the WPE algorithm is executed, through a Bayesian optimization method based on a Gaussian process, a prediction order and prediction delay parameter combination enabling the SI-SNR of the multi-channel dereverberation signal to be maximum is searched, and the prediction order and prediction delay parameter combination is applied to the WPE algorithm; s6, reconstructing the multi-channel time-frequency domain signal after reverberation removal into a time domain signal; and S7, calculating a normalization coefficient, and performing amplitude scaling. According to the method, the dereverberation ultrasonic signal with high fidelity, high consistency and high robustness can be obtained in a complex reverberation environment.

The invention discloses a real-time emergency prevention and control system and method for an electrochemical energy storage system based on digital twinning, and belongs to the field of energy storage safety. The system comprises a multi-source sensing unit, a digital twin deduction unit and a visual emergency decision unit. The sensing unit collects multi-source data to form a state vector; the deduction unit outputs a future thermal runaway evolution path containing a temperature field, a gas concentration field and a fire blast risk probability and uncertainty measurement thereof in real time through a pre-trained Gaussian process regression agent model; and the decision-making unit performs three-dimensional visual rendering, jointly determines a high-confidence risk area based on the risk level and the uncertainty level, and generates an emergency prevention and control instruction with accurate spatial positioning. The problems that in the prior art, disaster evolution paths cannot be predicted in real time, and prevention and control measures are extensive are solved, millisecond-level online deduction and accurate active prevention and control of the thermal runaway process are achieved, and the safety of an energy storage system is remarkably improved.

The invention relates to the technical field of wind field construction, and provides a low-altitude three-dimensional real-time wind field construction method and system based on unmanned aerial vehicle data inversion, and the method comprises the steps: collecting the multi-dimensional data of a flight attitude, a power system, navigation positioning and the like in real time through an unmanned aerial vehicle group in the process of executing a distribution task; and extracting key indexes such as attitude change features, control response deviation features, energy consumption features and the like from the data, inputting the features into a deep neural network with a physical model as a constraint to carry out wind field inversion training, and finally carrying out multi-scale spatio-temporal interpolation on discrete observation points through a Gaussian process regression algorithm fused with the physical constraint. And generating continuous three-dimensional wind field distribution meeting the law of conservation of mass. Dynamic wind field monitoring under urban complex terrains is realized by utilizing the characteristics of high-frequency and wide-coverage operation of the unmanned aerial vehicle, and the problem of insufficient observation data of a traditional weather station in a building dense area is effectively solved.

The invention belongs to the technical field of crossing of high polymer materials and artificial intelligence, and discloses a method for optimizing the proportion of a nano-composite flame-retardant master batch in engineering plastic based on machine learning. The method is used for solving the problems that a traditional experience trial and error method is low in efficiency in multi-target performance collaborative optimization, high-dimensional nonlinear parameter space search is difficult, and microscopic coupling effect modeling is missing. According to the method, a multi-dimensional input feature set containing material composition and process parameters is constructed, six key performance indexes are combined to form training data, a mixed model formed by cascading a multi-layer perceptron and Gaussian process regression is trained, an improved non-dominated sorting genetic algorithm (NSGA-II) is adopted for multi-target global optimization, and an optimal ratio meeting preset constraints is obtained. The method is an industrial internet technology system service, and solves the technical problem that multi-target performance is difficult to collaboratively optimize due to the fact that a traditional experience trial-and-error method cannot perform modeling and searching on a high-dimensional nonlinear parameter space of a nano-composite flame-retardant system.

The invention discloses a microfluidic nitration reaction platform based on in-situ Raman and a reaction optimization method. The platform integrates a microreactor, an in-situ Raman detection module, a spectrogram processing and quantifying module, an experimental optimization module and a central control module, and is suitable for monitoring and optimizing complex reactions under a non-mutual solution phase plunger flow system. According to the method, an indirect hard modeling (IHM) method is used for processing an overlapped Raman spectrogram, a standard curve is combined for establishing a multi-component concentration prediction model, and high-precision quantification of reactants and products is realized. According to the platform, a Gaussian process model is combined with dynamics prior, a multi-target Bayesian optimization process based on expected hypervolume improvement (EHVI) is driven, and Pareto optimal conditions in a temperature and residence time space are effectively explored. The system has the functions of automatic focusing sampling, spectrogram real-time decoupling, concentration inversion and experimental condition decision making, and is suitable for intelligent reaction development and optimization in the fields of fine chemical engineering, high-throughput reaction screening and the like.

The invention relates to an active optimization design method of an axial flow fan blade, which comprises the following steps of: defining a blade profile construction line by adopting seven parameters such as a leading edge radius, and parameterizing and representing two-dimensional blade profile geometric characteristics based on NURBS curve control points; a two-dimensional blade profile and three-dimensional fan coordinate system is constructed, and control point coordinate mapping is achieved through matrix transformation; the method comprises the following steps: acquiring an initial sample based on Latin hypercube sampling, and establishing a Gaussian process proxy model by combining two-dimensional CFD calculation data; a K-RVEA algorithm is applied, maximization of a worst attack angle lift-drag ratio and minimization of a resistance coefficient are taken as double targets, Pareto optimization is carried out in combination with geometry and performance constraints, and iteration is terminated through a hyper-volume convergence criterion; and the optimized two-dimensional blade profile parameters are converted into NURBS description, and stacking is carried out in the spanwise direction to generate a three-dimensional blade entity. The grid sensitive effect in three-dimensional optimization is overcome, the flow field analysis precision is improved, invalid calculation is reduced, the blade profile curvature continuity and the process feasibility are guaranteed, and the design period of the axial flow fan is shortened.

The invention provides a magnetic positioning error compensation method and system based on Gaussian process regression, and a medium. The method comprises the following steps: extracting a feature vector reflecting magnetic field environment distortion in real time; inputting the feature vector into a pre-trained Gaussian process regression model to obtain a predicted mean value and a predicted variance of the positioning error; dynamically adjusting a measurement noise covariance matrix in the Kalman filter based on the prediction variance so as to adaptively change a filtering weight; and executing state updating by using the adjusted covariance matrix, and performing deviation compensation on the output pose in combination with the predicted mean value. According to the method, the observation uncertainty is quantified through Gaussian process regression, the filter parameters are adaptively adjusted according to the observation uncertainty, and in a complex metal interference environment, the positioning precision and dynamic response can be intelligently balanced, the trajectory jump can be effectively inhibited, and the robustness and reliability of a magnetic positioning system can be remarkably improved.

The invention relates to the field of mechanical engineering, in particular to a hydraulic-structure collaborative optimization design method for a shield pump, and aims to solve the problems of load distortion and structure matching imbalance caused by traditional staged optimization. The method comprises the following steps: constructing a fluid-solid bidirectional coupling simulation model, and extracting transient hydraulic loads under multiple working conditions; establishing a structure dynamic response agent model based on modal superposition and Gaussian process regression; key coupling parameters such as the impeller outlet width and the volute base circle diameter are recognized through a Sobol method; and the efficiency, the lift fluctuation rate, the stress and the vibration are taken as multiple targets, and a Pareto optimal solution is searched through an improved genetic algorithm. Manufacturing constraints are embedded in the optimization process, the single period is shorter than 48 hours, and fatigue life evaluation and knowledge base intelligent recommendation are supported. According to the method, closed-loop cooperation of hydraulic excitation and structural response is achieved, the vibration prediction error is lower than 10%, the optimization dimension is compressed to be within 5 dimensions, the efficiency is improved by 20 times or above, and the performance reliability and the design intelligence level of the shield pump are remarkably improved.

The invention relates to a metal additive manufacturing three-dimensional temperature field Gaussian process prediction method, belongs to the technical field of material science, and particularly relates to a metal additive manufacturing three-dimensional temperature field prediction method. Logarithmic transformation is adopted to preprocess a temperature field, and prediction difficulty caused by extreme gradient near a molten pool is avoided; dividing the overall computational domain into a plurality of sub-domains by adopting a domain decomposition strategy to reduce the problem dimension; for each sub-domain, further combining singular value decomposition to extract a temperature field reduced-order base; establishing a local Gaussian process regression model based on a Maren kernel function and carrying out parallel training so as to establish rapid mapping from process parameters to reduced-order output; during online prediction, efficient and accurate prediction of a complete temperature field is realized through parallel calculation and full-field assembly of each local model.

The invention discloses a ship port entering-berthing autonomous navigation control method based on LBMPC, and the method comprises the steps: building a port environment model, and selecting an optimal berth from a candidate berth set according to the port information and the ship navigation state; dividing the whole ship entering-berthing process into a ship entering stage, a berthing area stage and a low-speed berthing stage, and calculating track nodes of all stages based on a port environment model; an improved fast exploration random tree star algorithm is adopted to plan a path of a port entering stage, a Durbin curve is adopted to plan a path of a berthing area stage, and a nonlinear attenuation model is combined to carry out speed distribution to obtain a global trajectory; in the actual sailing process, learning type model predictive control based on Gaussian process regression compensation is adopted for local dynamic pose planning and trajectory tracking control, and in the low-speed berthing stage, motion constraint is tightened, so that the berthing task of the ship is completed. According to the method, the control precision and safety of navigation of the ship in the whole process of entering the port can be improved.

The invention provides a rheumatoid arthritis patient low muscle quality risk prediction method based on an uncertainty perception stacked meta-learning structure, and belongs to the technical field of machine learning. The method comprises the following steps: acquiring a rheumatoid arthritis data set; constructing a base learner set comprising a table Transform class network and a gradient boosting tree class model; splicing the out-of-fold prediction probabilities of all the base learners and the statistics thereof to form a meta-feature matrix; taking the meta feature matrix as input, and constructing and training a meta learner comprising a spectrum normalization multilayer perceptron and a random feature Gaussian process output layer; collecting to-be-detected data, inputting the to-be-detected data into the trained base learner set and the trained meta learner in sequence, and performing temperature scaling and beta-calibration on a prediction result; and taking the calibrated prediction probability as a final prediction result. Through multi-source data fusion, the defects of an existing model in the aspects of practicability, probability reliability and the like are overcome.

The invention discloses an urban atmospheric pollution real-time monitoring and tracing method based on reinforcement learning, and relates to the technical field of atmospheric environment monitoring, and the method comprises the following steps: S1, collecting a pollution source data set; s2, constructing a Gaussian plume fidelity simulation model; s3, constructing a CFD fidelity simulation model; s4, constructing a multi-fidelity simulation model based on a Gaussian process proxy model; s5, constructing a DPPO reinforcement learning model; s6, using an improved multi-fidelity Bayesian optimization algorithm to continuously train and iterate the DPPO reinforcement learning model; and S7, generating a standardized pollution source real-time traceability analysis report. According to the method, the limitations of much manual intervention, low efficiency and poor real-time performance in a traditional urban pollution monitoring and tracing method are overcome, and an efficient and accurate solution is provided for intelligent real-time monitoring of urban environmental pollution and accurate and rapid tracing of pollution sources.

The invention relates to the technical field of data processing, in particular to a large model reasoning optimization method based on context incremental updating, which comprises the following steps: processing a multi-modal data stream through timestamp alignment and a filtering algorithm, extracting features by adopting a shared encoder and a private encoder, and realizing feature decoupling through a depth information bottleneck principle. A dynamic emotion map is constructed by using Gaussian process regression and a random process algorithm, and self-adaptive updating control is realized by combining meta-learning and Bayesian optimization. Incremental state management is realized by adopting a neural Turing machine, reasoning consistency is guaranteed through a generative adversarial network, model parameters are optimized in combination with a digital twin system and reinforcement learning, and a mental health service response is finally generated through a conditional generation model and hierarchical reinforcement learning. According to the method, the problem of asynchronism of multi-modal emotion feature dynamic evolution and context increment updating is effectively solved, accumulated drift of emotion state tracking is eliminated, and the continuity of reasoning logic is guaranteed.

The invention relates to a solar term temperature-based power load prediction method, which comprises the following steps of: obtaining 24 solar term reference temperatures and long-term trends of solar term temperatures, and correcting the long-term trends of the solar term temperatures; generating a continuous basic seasonal temperature curve; generating a high-resolution final simulation temperature sequence; and inputting the high-resolution final simulation temperature sequence into a power load prediction model, and performing power load prediction. Through throttle window smoothing, Gaussian process regression kernel function physical constraint and physical amplitude limiting random noise design, high-frequency random noise and chaos disturbance in original observation temperature are effectively stripped, the sensitivity of a power load prediction model to local atypical weather fluctuation is remarkably reduced, overfitting is relieved fundamentally, and the power load prediction method has the advantages of being high in robustness and high in reliability. The generalization capability and the prediction stability of the power load prediction model are greatly improved; and main physical driving factors of temperature change are subjected to decoupling and explicit modeling, so that the interpretability of the model is enhanced.

The invention discloses a heavy metal ion spectrum recognition method based on deep learning. The heavy metal ion spectrum recognition method comprises the following steps: collecting a one-dimensional spectrum and an ion label, smoothing, correcting a baseline, and standardizing; generating and storing a wavelength prior mask according to the element spectral line; constructing an SNGP trunk, applying spectrum normalization and a hierarchical Lipschitz upper bound, and outputting distance sensing features; configuring a Gaussian process classification head, modulating a kernel amplitude and a length scale as a non-stationary kernel according to a priori mask, and outputting a posteriori mean value and a variance; carrying out joint optimization by using samples with labels, updating an upper bound according to a posterior variance, and executing spectral norm projection; determining and solidifying an identification threshold value and an uncertainty threshold value in the verification set; and deploying a calculation posteriori, outputting an ion category and uncertainty according to a threshold value, and marking a key wavelength. According to the method, distance perception and uncertainty quantification are considered, and the cross-instrument stability and the key wavelength traceability are improved.

The invention relates to a slope instability probability evaluation method based on burial depth constraint space random field simulation, and belongs to the technical field of slope engineering. The method comprises the following steps: acquiring shear strength parameters c and phi at different buried depths of a slope soil body in a research area; the obtained shear strength parameters are expanded according to Gaussian process regression in combination with a radial basis function, the reliability of the expanded parameters is determined through K-S inspection, and cross correlation between c and phi is obtained; determining statistical characteristics of the c and phi expansion data; under the burial depth constraint condition, slope model determinacy research is carried out, a safety coefficient is calculated, the model is compared with a traditional model, and the difference between the potential slip plane of the slope under the burial depth constraint and the potential slip plane of the traditional slope is obtained; the traditional Monte Carlo simulation MCS is optimized; according to deterministic analysis and a random field theory, carrying out uncertainty research on the side slope under the burial depth constraint, and calculating the instability probability of the depth evolution random field side slope model.

The invention relates to the technical field of CNC machining, and discloses a CNC machining path optimization method for a plastic mold, and the method comprises the steps: dividing a mold high / low / transition curvature region through high-precision point cloud scanning, and generating a region machining strategy table; multiple sensors are deployed on the CNC machine tool, and unified machining state evaluation indexes are generated through data fusion; bayesian optimization is initialized by taking a Gaussian process as an agent model, and an optimal path parameter is selected based on monitoring data; a threshold value is set to automatically trigger electric spark finishing, and equipment collaboration is achieved through OPC UA data transmission; and detecting the comparison standard after processing, if the comparison standard is not reached, adjusting the algorithm weight for re-optimization, and storing parameters in a database to form a closed loop. According to the method, the fine trimming quality can be improved in CNC machining of the plastic mold.

The invention discloses an intelligent unmanned aerial vehicle flight state monitoring method and system. The method comprises the steps of data perception, data preprocessing, feature fusion and intelligent monitoring. The invention relates to the technical field of unmanned aerial vehicle safety management, in particular to an intelligent unmanned aerial vehicle flight state monitoring method and system.According to the scheme, a unified time grid with the sampling frequency in the flight stage as the reference is constructed, data alignment and complementation are achieved through time weighted interpolation, and the flight state of an unmanned aerial vehicle is monitored. Abnormities are removed in combination with median absolute deviation and a packet loss probability threshold value, and data consistency and noise immunity are ensured based on short-time energy self-adaptive window resampling; carrying out multi-modal feature extraction, introducing an uncertainty driven attention fusion mechanism, carrying out adaptive weighting, and reserving second-order statistical information; the uncertainty is used for correcting the mahalanobis distance, the health index and Gaussian process life prediction, and a multi-task classification network is combined to realize intelligent and interpretable monitoring and early warning of the flight state of the unmanned aerial vehicle.

The invention discloses a photovoltaic energy storage regulation and control method based on multi-scale power prediction, and the method comprises the following steps: collecting and preprocessing multi-source time sequence data, and generating a multi-scale input sequence; constructing a closed continuous time network, completing continuous time modeling, and generating a power prediction result sequence; a Gaussian process state space model is constructed, a kernel function dynamic adjustment mechanism is introduced, and a prediction distribution set and an uncertainty parameter set are generated; performing correction and confidence weighting on the power prediction result sequence to generate a corrected power prediction result set; constructing an energy storage regulation and control constraint set based on the corrected power prediction result set and the multi-source time sequence data; and generating a photovoltaic energy storage regulation result set based on the energy storage regulation constraint set and the corrected power prediction result set. The photovoltaic prediction precision is improved, and the energy storage regulation and control reliability is enhanced.

The invention discloses an equipment health monitoring method based on multi-modal data fusion, and the method comprises the following steps: carrying out the preprocessing and feature extraction of collected multi-modal monitoring data, and constructing a cross-modal pairing feature sample; a deep canonical correlation analysis model is adopted to model correlativity among different monitoring data, and multi-modal features are mapped to a unified potential health representation space; and further combining with a hidden variable Gaussian process model, carrying out probability modeling and posterior inference on the potential health representation to obtain a continuous estimation result of the equipment health state changing along with time, and generating a health degradation track. The method is suitable for various equipment operation scenes with noise, missing or asynchronization of monitoring data.

The invention relates to the technical field of mechanical arm control, in particular to a mechanical arm predictive control method which comprises the following steps: defining the state of a mechanical arm and modeling; collecting data to construct a Koopman linear lifting determinacy prediction model; carrying out probability representation on the error by utilizing Gaussian process regression; constructing a random prediction model by combining a deterministic model and an error model, and deducing a state distribution evolution equation; and converting the joint constraint into probability opportunity constraint, carrying out deterministic equivalent conversion, and solving a rolling optimization problem. According to the method, dependence on a precise dynamic model can be abandoned, precise approximation of nonlinear dynamics is achieved through data driving, high-precision trajectory tracking of the tail end of the mechanical arm is achieved on the premise that it is guaranteed that high probability meets safety constraints, and control conservative property is reduced.