203 results about "Bayesian optimization algorithm" patented technology

The invention discloses a power grid photovoltaic output and load sequence modeling method, system and device and a storage medium, and the method comprises the steps: comprehensively utilizing the multi-scale feature extraction capability of a time-frequency decomposition technology, the time sequence dependence modeling capability of a long and short-term memory network, and the global hyper-parameter optimization capability of a Bayesian optimization algorithm; and carrying out collaborative modeling and prediction on the photovoltaic output and the power load under a unified framework. By introducing a source load time-delay correlation analysis and probability interval construction mechanism, point prediction results and uncertainty intervals of photovoltaic, load and net load can be output at the same time, and a set of source load integrated prediction system with high prediction precision, strong robustness and reliable interval characterization capability is constructed. The method can improve the precision and reliability of photovoltaic power and load prediction, also can reduce the risk in power system scheduling, optimizes the energy storage configuration strategy, and especially has wide popularization potential and application prospects in the scenes of new energy grid-connected operation, intelligent micro-grid and virtual power plant management and the like.

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 power distribution network transient characteristic prediction method based on supervised learning, and relates to the technical field of power distribution network state prediction, and the method comprises the steps: collecting historical operation data through a power distribution network monitoring system, carrying out the data preprocessing, and obtaining standardized multi-dimensional time series data; carrying out transient feature extraction, constructing a high-dimensional feature set, and carrying out feature dimension reduction according to a transient event tag to generate a feature subset; inputting the feature subset into a mixed supervised learning model of a gradient boosting decision tree GBDT and a long short-term memory network LSTM for joint training to obtain a transient feature prediction result; and calculating a root-mean-square error according to the transient characteristic prediction result and the real-time monitoring observation value of the power distribution network, and dynamically adjusting hyper-parameters of the supervised learning model based on a Bayesian optimization algorithm. According to the method, the detection accuracy can be improved, the calculation complexity can be reduced, and the discrimination capability and the time sequence prediction capability of the model are considered.

The invention discloses a river and lake backflow recognition and driving mechanism analysis method based on interpretable machine learning, and relates to the technical field of hydrology and water resource analysis and artificial intelligence application, and the method comprises the steps: collecting long-sequence hydrology data of a river and lake system; taking operation nodes of the large hydro-junction project as boundaries, and dividing the time sequence into different characteristic periods; constructing a multi-dimensional input feature set; a class weight balance strategy and a Bayesian optimization algorithm are adopted to train a backward flow recognition model based on a gradient lifting decision tree; a marginal contribution value of each hydrological driving factor is calculated by using an SHAP interpretability method, a physical threshold for inducing backward flow is identified by combining an SHAP dependency graph with a binary box plot, analysis results in different periods are compared, and an evolution rule of a backward flow driving mechanism is revealed. The method effectively solves the problems that a traditional method is difficult to capture nonlinear hydrological response and the black box model lacks physical mechanism explanation, and can accurately recognize the backward flow event.

The invention discloses a telescope parameter efficient optimization method and system based on a Bayesian algorithm and a fluctuation optical TTL coupling noise calculation model, and aims to solve the problem that a fluctuation optical high-precision calculation module is used for improving TTL coupling noise calculation precision in an existing telescope parameter optimization method. And due to frequent calling of a high-time-consumption module, the optimization time is sharply increased, and the efficient design requirement of a space gravitational wave detection task is difficult to meet. According to the method, on the basis of the principle of a Bayesian optimization algorithm, potential optimal to-be-evaluated telescope parameters are searched through an agent model, a collection function and the optimization function of Zermarkes software; and calculating TTL coupling noise of the telescope to be evaluated by combining a light field propagation calculation method based on a wave optics theory with a light field-phase resolving method, carrying out iterative optimization on telescope parameters, and outputting optimal TTL coupling noise and optimal telescope optical parameters.

According to the new energy Internet of Things multi-level analysis sharing platform based on digital twinning, the intelligent perception and edge access module collects data through a multi-mode sensor, and reliable data is provided for subsequent analysis through edge calculation preprocessing and hierarchical transmission. And the digital twinning construction and dynamic updating module constructs equipment-level, station-level and regional-level digital twinning models based on a Bayesian optimization algorithm to realize dynamic calibration of the models. And the multi-level analysis decision module realizes equipment fault diagnosis, generation power prediction, energy storage scheduling and power grid optimization through a four-level architecture. The digital twin mirror image regulation and control module establishes a bidirectional control channel and supports remote configuration of equipment parameters and automatic triggering of fault plans. The cross-domain data security sharing module adopts a three-layer security protection system and a federal learning mechanism to guarantee data security and sharing. According to the platform, full-process intelligent management of the new energy system is realized, and the operation efficiency and safety of the system are improved.

A combined rock mass strength prediction and floor strength mapping method based on a PCA-KAN fusion neural network comprises the following steps: preparing combined rock mass test pieces with different layer sequences, thickness ratios and interface states, and obtaining multi-dimensional mechanical parameters through a compression mechanical test; carrying out dimension reduction processing by adopting a principal component analysis method, constructing a comprehensive strength index according to a principal component load coefficient, and forming a dimension reduction feature vector; constructing an Attn-KAN model, and adjusting hyper-parameters by adopting a Bayesian optimization algorithm; the performance and interpretability of the model are ensured through layered K-fold cross validation and SHAP analysis; the method comprises the following steps: carrying out a compression mechanical test on a field rock core sample to obtain multi-dimensional mechanical parameters, carrying out dimension reduction processing by adopting a principal component analysis method, and predicting by taking a principal component feature vector as input data to obtain a comprehensive strength predicted value; and adopting a Kriging interpolation method to output an intensity distribution and risk grade partition map. According to the method, accurate prediction of the strength of the combined rock mass can be realized, and spatial visual mapping of the strength of the coal seam floor and the risk level can be realized.

The invention discloses a coal seam gas content dynamic prediction method based on Bayesian optimization XGBoost, and belongs to the field of coal mine gas control, and the method comprises the steps: collecting a sample set U composed of influence factors of coal seam gas occurrence, preprocessing the sample set to obtain a sample set, and dividing the sample set in proportion to obtain a training set, a verification set and a test set; dividing the training set into a plurality of sample sets; an XGBoost model is constructed, the nth sample set serves as input, the actual coal seam gas content serves as output, the XGBoost model is trained, and an nth coal seam gas content prediction model is obtained; the influence factors of coal seam gas occurrence are calculated through a three-dimensional geologic model, geologic structure characteristics and coal seam roof and floor lithologic characteristics are comprehensively considered, and a Bayesian optimization algorithm is adopted to carry out adaptive search on hyper-parameters of an XGBoost model. The technical problem that a traditional gas content prediction method mostly depends on static geological parameters and cannot achieve real-time prediction of the gas occurrence state under the complex geological condition is solved.

An adaptive model partitioning method and system applied to distributed training, which method and system belong to the technical field of deep learning, and aim at solving the technical problem of how to implement, in respect of distributed training, distributed model training by means of combining deep reinforcement learning and a Bayesian optimization algorithm. The method comprises the following steps: constructing a Q network on the basis of a deep neural network, and defining state information, actions and a reward function, wherein the state information comprises feature vectors of partitioned models, and training times, resource utilization rates and inter-node communication overheads of when the partitioned models are subjected to distributed training by means of distributed computing nodes, each action is a partitioning strategy used by an agent under the current state information, the reward function R is used for evaluating the effect of the current partitioning strategy, and the Q network uses the state information as input to predict and output a Q value of each action that the agent may take; and performing multiple iterative training on a deep reinforcement adaptive model, so as to obtain a final partitioning strategy and parameters of the Q network.

The invention discloses a material stress-strain constitutive relation modeling method and device, a program product and a medium, and relates to the technical field of metal material constitutive models. Uniaxial tensile experiment data of a metal material under the conditions of different temperatures and different strain rates is obtained and preprocessed, and a training data set reflecting mechanical behaviors of the material under the wide-range working condition can be constructed; constructing an initial neural network model comprising a main body network structure layer, a neuron unit, a connection parameter and a training mechanism based on the training data set, and performing iterative optimization on a hyper-parameter by adopting a Bayesian optimization algorithm to obtain a target neural network model; the nonlinear stress-strain relationship of the material under the conditions of different temperatures and strain rates can be accurately captured; the target neural network model is further converted into a user-defined material subprogram of the finite element analysis platform, and the subprogram can output a predicted material stress value according to the input strain, strain rate and temperature, so that seamless joint with a universal finite element analysis platform is realized, and the prediction precision of simulation is improved.

The invention discloses an electric power system relay protection fault identification method, system and device based on Bayesian optimization and a storage medium, and relates to the field of electric power system fault identification and relay protection, and the method comprises the steps: collecting original electric quantity data from a power grid fault recording system, and converting the original electric quantity data into a two-dimensional image with a label; based on the two-dimensional image with the label, constructing a hybrid deep learning model skeleton for cooperatively extracting local features and associating with a time sequence; based on the two-dimensional image with the label, a Bayesian optimization algorithm is adopted to carry out automatic hyper-parameter tuning and training on the constructed hybrid deep learning model skeleton, and a CBAM-CNN-LSTM model capable of being used for actual fault identification is obtained; the CBAM-CNN-LSTM model is used to carry out online fault identification on the electrical quantity data acquired in real time; according to the method, the weak fault and the high-resistance fault of the new energy power grid are accurately and rapidly identified, the accuracy rate exceeds 99.7%, the response time of the whole process is less than 10 milliseconds, and the safety of the power grid is remarkably improved.

The invention relates to a GEO spacecraft maneuver detection method considering sample imbalance. The method comprises the following steps: forming time sequence data according to an SGP4 model; on the basis of a maneuvering control equation of the GEO satellite, screening feature vectors from the time sequence data; pCA dimension reduction processing is carried out on the feature vectors, then clustering is carried out on data after dimension reduction, sampling and copying are carried out according to a clustering result and a preset rule, and a balanced sample training set is generated; constructing a CCBGA deep learning framework, performing adaptive optimization on network parameters of the CCBGA deep learning framework by adopting a Bayesian optimization algorithm, and training the optimized CCBGA framework by using a balanced sample training set; and inputting orbit parameter time sequence data of the GEO spacecraft to be detected into the trained CCBGA frame, and outputting a maneuvering detection result. By adopting the method, the maneuvering detection precision and stability of the GEO spacecraft can be improved.

The invention discloses a metallocene polypropylene synthesis catalytic performance prediction method, which comprises the following steps: data collection: collecting experimental data of metallocene catalyst synthesis polypropylene, and establishing a data set containing input variables and output variables; data preprocessing: cleaning, standardizing and coding experimental data; feature engineering: carrying out feature correlation analysis on the preprocessed data; model construction: constructing independent prediction models for predicting catalyst activity, number-average molecular weight and molecular weight distribution by using a plurality of machine learning algorithms respectively; performing hyper-parameter optimization: performing hyper-parameter optimization on the prediction model by adopting a Bayesian optimization algorithm to obtain an optimal model parameter; model evaluation: evaluating the performance of the prediction model by adopting a cross validation method; and predicting: inputting process parameters and catalyst ligand parameters input by a user into the optimized and evaluated optimal prediction model, and outputting predicted values of catalyst activity, number-average molecular weight and molecular weight distribution.

The invention discloses an underwater wireless power transmission system parameter identification method based on machine learning, which comprises the following steps: constructing a data set through finite element simulation, and obtaining original input parameters including geometry, electromagnetism and position offset and corresponding key output parameters; feature engineering is executed, and derived features with physical significance are extracted; performing standardized preprocessing on the data; for each key output parameter, independently training an XGBoost regression model; carrying out five-fold cross validation on the training set by adopting a Bayesian optimization algorithm, and carrying out independent hyper-parameter optimization on each XGBoost model; and carrying out interpretability analysis on the trained agent model by utilizing SHAP analysis, quantifying the contribution degree of each input feature to a prediction result, and providing physical insight. According to the method, high-precision prediction of the electromagnetic parameters under the complex working condition is achieved, complex electromagnetic field calculation is avoided, the system design efficiency is remarkably improved, and the efficiency and interpretability of intelligent optimization design of the UWPT system are remarkably improved.

The invention discloses a weld defect intelligent identification and path adaptive planning system based on deep learning, and relates to the technical field of ultrasonic nondestructive testing, and the system comprises an ultrasonic data acquisition module, a defect identification module, a path planning module, a parameter adaptive regulation and control module and a result output module. The defect identification module adopts a multi-scale feature extraction network to be combined with an atlas convolution processing unit to extract deep semantic information and a global topological relation of ultrasonic features, high-precision defect identification is realized through an attention enhancement classification network, and the path planning module is used for planning a path based on a defect distribution probability graph. The self-adaptive scanning path is dynamically generated by adopting the Bayesian optimization algorithm, the detection efficiency is remarkably improved on the premise that the detection quality is guaranteed, the problems that a traditional method is insufficient in recognition accuracy and fixed and inflexible in detection path are solved, the recognition accuracy reaches 93%-96%, and the detection time is shortened by about 35%-40%.

The invention discloses an MDCK cell low-serum culture medium construction method based on KAN modeling and Bayesian optimization and application thereof.The MDCK cell low-serum culture medium construction method comprises the steps that firstly, key influence factors are screened out from numerous nutrient components through multi-factor experimental design, and then a high-precision nonlinear prediction model between the key factors and cell performance is established through KAN; based on the model, a Bayesian optimization algorithm is adopted for rapid optimization, and the optimal concentration of each component is determined. The cell line culture medium has universality and can be migrated and applied to culture medium development of other cell lines. According to the MDCK cell low-serum culture medium constructed through the method, the adding amount of fetal calf serum (FBS) is only 2%-4% (v / v), the formula is systematically optimized, efficient growth of cells can be directly supported, and pre-domestication is not needed. The culture medium has obvious effects on promoting MDCK cell proliferation, improving virus (such as influenza virus) titer and reducing production cost, and is suitable for large-scale production of vaccines.

The invention discloses a traffic-electric power fusion network bearing capacity analysis method based on a double-layer model and multi-software joint simulation, and relates to the technical field of traffic engineering and electric power engineering crossing. According to the technical scheme, an upper-layer system optimization-lower-layer operation simulation double-layer model normal form is introduced, the upper layer aims at maximizing the total bearing capacity of the traffic-electric power fusion network, the lower layer constructs a real-time interaction channel through a TraCI interface of SUMO and a TCP / IP tool box of Matlab, and dynamic coupling simulation of the two networks is achieved; and solving the model by adopting a Bayesian optimization algorithm, and verifying the precision of the model through actual scene data in combination with a three-level evaluation index system covering traffic, electric power and fusion collaborative dimensions. The problems that a traditional method is insufficient in evaluation precision and poor in collaboration are solved, precise evaluation of the bearing capacity of the fusion network is achieved, technical support can be directly provided for charging facility layout and two-network collaborative scheduling in highways and other scenes, and the engineering application value is remarkable.

The invention provides a shield excavation face stratum recognition method and system based on optimization classification feature selection, and relates to the technical field of shield tunnel construction. Shield construction data are collected and preprocessed, and an excavation face stratum recognition database is established; for class imbalance, performing feature importance sorting by using a weight-corrected maximum correlation minimum redundancy algorithm mRMR, selecting first m features corresponding to feature importance curve inflection points to form a roughing data set, and dividing core features, important features and edge features; establishing a multi-target feature selection framework through an NSGA-II-LightGBM algorithm based on a rough selection database with the minimum number of features, the maximum weighted F1 value and the maximum minority class recall rate as targets, outputting a Pareto leading solution, screening the most suitable individual in the Pareto leading solution based on a constraint screening-priority ranking-stability verification strategy, and establishing a fine selection data set; a Bayesian optimization algorithm is adopted to optimize the LightGBM classification model, and rapid and accurate prediction of the excavation face stratum in the shield construction process is achieved.

The application discloses a kind of parameter self-adapting material reflectivity curve generation method and system, comprising: S1, constructing discrete sample set;S2, form conditional sample set;S3, cost coupling parallel point selection is executed using improved parallel bayesian optimization algorithm;S4, input improved DeepONet model, introduce conditional kernel generation mechanism in integral kernel operator layer, output predicted reflectivity curve;S5, training operator parameters are generated using Kramers-Kronig algorithm to execute Hilbert transform;S6, improved parallel bayesian optimization algorithm is used to generate update operator parameters;S7, physical boundary constraint is executed, and material reflectivity curve is output.The present application realizes the high-precision prediction and self-adaptive update of material reflectivity curve, improves the efficiency and amplitude and phase consistency of measurement point selection, enhances the stability and physical rationality of reflectivity curve generation under different working conditions.

The application relates to a machine learning assisted optimization multifunctional composite hydrogel wound dressing and a preparation and optimization method thereof, and belongs to the hydrogel field. The hydrogel is constructed by ion crosslinking of sodium alginate and calcium ions and chitosan quaternary ammonium salt, and a chemical crosslinking network formed by polyacrylamide is interpenetrated with the network. The hydrogel has high water absorption, strong antibacterial property, reliable adhesion, sensitive strain sensing property and excellent mechanical property, and provides ideal healing for wounds. The method innovatively integrates machine learning intelligent optimization: by establishing a formula-process-performance database, training a Gaussian process regression prediction model, and adopting a Bayesian optimization algorithm for global optimization, optimal preparation parameters for specific performance requirements are efficiently and accurately determined. The method breaks through the traditional trial-and-error development mode depending on experience, realizes high performance, customization and rapid development of the hydrogel dressing, and provides a new paradigm for design and preparation of a new generation of wound care products.

The invention discloses an environment-friendly dyeing process method for paper products, and aims to solve the problems that a traditional environment-friendly dyeing process is large in chromatic aberration fluctuation, unstable in fastness and poor in adaptability of difficult-to-dye paper types. The method comprises the following steps: establishing a paper physical property database based on near infrared spectrum imaging and liquid absorption rate test; calculating an optimal dye liquor concentration gradient, dipping time and temperature through a dye penetration kinetic model and a Bayesian optimization algorithm; gradient permeation dyeing is carried out in the continuous dye vat array by adopting natural vegetable dye; a tannic acid-chitosan composite cross-linking agent is introduced for bio-based color fixation; and closed-loop self-adaptive adjustment is realized by combining hyperspectral imaging online detection and feedback regulation and control. According to the technical scheme, the dye uptake is remarkably increased to 91% or above, the rubbing fastness reaches 4.5 level, the color uniformity and batch consistency are ensured in high-speed continuous production, no heavy metal mordant exists in the whole process, the biodegradability of wastewater is high, and the clean production requirement is met.

The invention discloses an underwater binocular camera calibration method based on laser assistance, and the method comprises the steps: firstly constructing an underwater stereoscopic vision binocular refraction-removing imaging model according to the Snell's law, and correcting an underwater imaging error; secondly, acquiring a camera internal reference matrix by using a Zhang Zhengyou calibration method; then, a laser range finder is used for projecting laser to the calibration plate to form a light spot, the center pixel coordinate of the light spot is extracted through a gray gravity center method, the three-dimensional coordinate of the light spot is calculated in combination with laser ranging data, and the initial value of an external parameter matrix of the binocular camera is solved; and finally, introducing a Bayesian optimization algorithm, and optimizing the constraint equation by taking minimization of a three-dimensional coordinate calculation error as a target so as to obtain an exact solution of an external parameter matrix of the camera. Through organic combination of a deep learning technology and binocular stereo vision, the parameter calibration precision of the underwater binocular stereo vision camera is improved, a reliable technical guarantee is provided for subsequent underwater concrete structure defect quantification, and the fine monitoring requirement in a complex water environment is met.

The invention belongs to the technical field of environmental engineering, and particularly relates to a rapid prediction method for trichloroacetic acid generation potential in a water disinfection process. The rapid prediction method for the trichloroacetic acid generation potential in the water disinfection process comprises the following steps: constructing a training set and a test set which respectively and independently comprise a plurality of organic compounds and trichloroacetic acid generation potential values and key molecular characteristic parameters corresponding to each organic compound; an extreme gradient lifting machine learning algorithm is adopted to construct a trichloroacetic acid generation potential prediction model, and model precision verification is carried out; optimizing by adopting a Bayesian optimization algorithm to obtain a trichloroacetic acid generation potential optimal prediction model; and inputting the key molecular characteristic parameters of the target compound into the optimal prediction model to obtain the trichloroacetic acid generation potential value of the target compound. The rapid prediction method provided by the invention realizes rapid prediction of the TCAAFP value of the organic compound in the chlorine disinfection reaction, and has the advantages of convenient operation, low cost, strong stability and wide application range.

The invention belongs to the technical field of fault diagnosis, and particularly relates to a gearbox fault twinborn diagnosis method based on a virtual-real coding mapping optimization model, and the method comprises the steps: obtaining envelope spectrums of actual measurement and simulation signals of a gearbox under two different working conditions, and constructing a source domain actual measurement and virtual sample set and a target domain test and virtual sample set; building a virtual-real coding mapping network, and obtaining a virtual-real coding mapping optimization model by adopting a Bayesian optimization algorithm; training the optimization model by utilizing the source domain actual measurement and the virtual sample set until convergence; inputting target domain virtual and actual measurement samples into the trained optimization model, extracting corresponding coding features of the target domain virtual and actual measurement samples, training a k-nearest neighbor (KNN) classifier by adopting the coding features of the target domain virtual samples, inputting test sample features into the trained KNN, and outputting a diagnosis result; according to the method, high accuracy can be achieved in small-sample cross-working-condition gearbox fault diagnosis, and the method has good application prospects in the field of twin data driven gearbox fault diagnosis.

The application relates to a river closure date prediction method based on historical similar year performance driving, which comprises the following steps: using a plurality of feature selection algorithms and leave-one-out cross-validation to screen target predictor sets respectively matched with selected machine learning models and statistical models; based on parameter sensitivity analysis and a Bayesian optimization algorithm, sensitive hyperparameters of the machine learning models are optimized to obtain optimized machine learning models; the statistical models and the optimized machine learning models are configured as candidate river closure date prediction models; a K-neighbor algorithm is used to search a set of similar historical years in a historical observation data set according to current observation data, and a target river closure date prediction model is dynamically optimized according to the comprehensive prediction error of the candidate river closure date prediction models on the set of similar historical years, and a prediction result is output, so that the advantages of multiple models are effectively fused, the generalization limitation of a single model in a complex non-stationary environment is avoided, and the accuracy and robustness of the prediction result are significantly improved.

The invention relates to a safety assessment method for pressure-bearing special equipment with crack defects based on health monitoring and digital twinning. Various sensors are installed at key parts of the equipment to collect running state data in real time, a parameterized digital reconstruction technology is adopted to establish high-precision twin bodies of the equipment, and stress distribution and crack propagation trend of the structure are automatically simulated and analyzed by means of cloud computing. A two-stage Bayesian optimization algorithm is innovatively used to realize self-correction of simulation result errors, and adaptive accurate mapping of a digital model to physical equipment is realized. And in a crack defect-containing area, an instability critical dimension prediction model is constructed based on an extended finite element method and a failure evaluation diagram technology, and the crack instability critical dimension is dynamically calculated. According to the invention, real-time, efficient and automatic safety assessment and early warning can be carried out on pressure-bearing special equipment, and scientific data support and decision basis are provided for safe operation and maintenance of the equipment.

This invention discloses a carbon emission prediction system and method for papermaking processes based on BO-GBDT. The system collects process parameters and energy consumption data during papermaking production, preprocesses the input data, constructs a feature set containing key influencing factors, and obtains a carbon emission dataset for model training. A Bayesian optimization algorithm is introduced to intelligently search for the optimal hyperparameters of four gradient boosting models, constructing a hyperparameter optimization space and setting an optimization objective function. Model performance is evaluated through cross-validation, and the optimal model is updated and selected. BO-GBDT is selected as the final prediction model. The trained model is then used to accurately predict carbon emissions from the papermaking process. By automatically optimizing the hyperparameters of the gradient boosting decision tree model using Bayesian optimization and combining it with multi-source data feature engineering, high-precision and high-efficiency prediction of carbon emissions from the papermaking process is achieved, providing an effective tool for carbon management in the production process.

This invention discloses a high-precision ship energy consumption prediction system based on multi-model fusion. It includes a data collection and analysis module for collecting and processing ship energy efficiency data and meteorological data, and performing feature selection on the data using a feature selection method; a single-model algorithm ship energy consumption prediction module for constructing and testing different types of ship energy consumption prediction models, and selecting high-performing models based on the test results to form a ship energy consumption prediction model set; a multi-model fusion ship energy consumption prediction module for fusing the basic models in the ship energy consumption prediction model set using a stacking model fusion method, and optimizing the fused model using Bayesian optimization and adaptive algorithms, and predicting ship energy consumption based on the optimized fused model; and a human-computer interaction module for displaying the analysis, processing, operation process, and analysis results of other modules. This invention constructs a stacking-based ship energy consumption prediction fusion model, improving the prediction accuracy of the ship energy consumption prediction fusion model.

The present application belongs to the technical field of flexible robots, and relates to a structure optimization method of a fin ray effect gripper, comprising the following steps: step 1: a co-rotation modeling method is used to construct a force-deformation relationship model of the fin ray effect gripper as a fast evaluation model of the performance of the gripper; step 2: structure optimization design parameters and multi-objective performance evaluation indexes of the fin ray effect gripper are determined; step 3: based on a Bayesian optimization algorithm, the fast evaluation model is combined to construct a multi-objective structure optimization framework, global optimal sample search is performed on the design parameters, and a Pareto front is solved; and step 4: experimental verification is performed on typical optimal parameter combinations in the Pareto front, and optimal structure parameters of the gripper suitable for different gripping scenes are output. The present application can be applied to the design and optimization of flexible, rigid and rigid-flexible hybrid robot compliant mechanisms, and can be widely applied to the high-performance design and parameter tuning of gripper structures in industrial gripping, service robots, precision operation and the like.

The invention relates to the technical field of hyperspectral remote sensing spectral analysis, in particular to a full-spectrum splicing high-resolution imaging system and method for a hyperspectral analyzer, and the method comprises the steps: determining a slit switching sequence through an acquisition module; the dynamic collimation module feeds back an aberration result; the adaptive dispersion module carries out wavelength calibration; the high-precision imaging module predicts imaging mirror parameters; the real-time compensation module adopts a Kalman filtering algorithm to predict the defocus compensation amount and executes nanoscale displacement compensation through a piezoelectric ceramic driver; the intelligent splicing module adopts an SIFT feature matching algorithm, a generative adversarial network and a reinforcement learning algorithm to realize image registration and fusion; the cooperative control module generates control signals through Monte Carlo simulation and a Bayesian optimization algorithm to coordinate all the modules. According to the invention, the problems of insufficient spectral resolution, difficulty in data splicing and low real-time measurement efficiency caused by fixed hardware parameters in a wide-spectrum spectral imaging system are solved, and full-spectrum high-resolution imaging is realized.