1300 results about "Bayesian optimization" patented technology

The invention discloses a predictive maintenance method for an optical storage and charging integrated power station based on deep learning, and the method comprises the steps: constructing an efficient equipment state evaluation and prediction model based on multi-source data fusion, an intelligent prediction algorithm and a closed-loop optimization feedback mechanism, collecting multi-source data, and carrying out the fusion processing, an improved Attention-LSTM model is utilized to evaluate and predict the state of equipment, a transfer learning method is adopted to improve generalization ability, Bayesian optimization and an adaptive sliding window technology are combined at the same time, dynamic threshold adjustment is performed, a deep reinforcement learning algorithm based on a Markov decision process is adopted to optimize a maintenance strategy, and the maintenance efficiency is improved. Weibull distribution is introduced for failure probability modeling, the maintenance cost and the fault risk are balanced, continuous optimization and dynamic adaptive adjustment of a predictive maintenance scheme are realized through a closed-loop feedback mechanism, the prediction accuracy and the intelligent level of maintenance decision are remarkably improved, planned maintenance and sudden fault maintenance are reduced, and the maintenance efficiency is improved. And the reliability of the charging station is improved.

The invention discloses an integrated power distribution cabinet energy efficiency dynamic optimization method based on multi-modal data fusion, and relates to the technical field of intelligent power grids. The problems of failure of an energy efficiency optimization model and poor long-term operation stability caused by data time sequence misalignment and error accumulation of a multi-source sensor in the prior art are solved. According to the scheme, the time offset is dynamically corrected through the adaptive time sequence deviation prediction model; compensating missing data by adopting a non-uniform time step reconstruction algorithm and Kalman filtering; detecting an error drift trend through an exponentially weighted moving average model, updating a feature weight, and inhibiting long-term error accumulation; constructing a self-adaptive time sequence attention fusion network model, and fusing physical constraints and a data driving mechanism to generate an optimization decision; bayesian optimization is utilized to quantify parameter uncertainty, closed-loop feedback execution data is carried out, and model parameters are dynamically updated; according to the invention, the precision, long-term stability and equipment safety of energy efficiency optimization of the power distribution cabinet are remarkably improved, and efficient and reliable operation under multi-physics field coupling constraint is ensured.

The invention relates to the field of welding process control, and discloses a pipeline all-position automatic TIG (Tungsten Inert Gas) welding method which comprises the following steps: collecting pipeline geometric parameters, welding position angles and material attribute data in real time through multi-source data fusion; constructing a Gaussian process regression dynamic response model, coupling a nonlinear mapping relationship among the process parameters, the molten pool morphology and the corrosion tendency index, and dynamically adjusting the weight of the model based on the welding position angle; a hierarchical strategy of Bayesian optimization and model prediction control is adopted to generate a parameter solution set meeting the fusion depth constraint and the corrosion threshold value, and the molten pool oscillation frequency is used as feedback to correct the current in real time; the heat accumulation evolution trend is predicted through a hidden Markov chain, and parameter closed-loop migration and trajectory compensation are achieved in combination with molten pool flow field coupling correction. The problems of uneven forming quality and corrosion risk caused by space displacement, dissimilar metal interface effect and dynamic disturbance in all-position welding are solved.

The invention discloses an online monitoring method and system for the light transmittance of an optical lens, and relates to the technical field of precise optical detection. The objective of the invention is to solve the problem of large light transmittance calculation error caused by halo scattering noise interference, low optical path calibration precision of a complex curved lens, a measurement blind area of a large-aperture lens and environmental disturbance of a high-reflection / high-light-transmittance lens in the prior art. According to the scheme, a three-dimensional curved surface model is constructed based on Gray code structured light projection and ICP registration, a dynamic partition scanning instruction set is generated through an improved genetic algorithm, and multi-wavelength polarized light is driven to scan and collect multi-dimensional data; specular reflection and scattering noise are suppressed by combining an improved Stokes vector algorithm and an attention mechanism U-Net network, and the data precision of the complex curved surface is improved by adopting Bayesian optimization and Zernike polynomial weighted fusion; constructing a double-loop coupling optimization architecture to realize closed-loop adaptive optimization; according to the invention, the anti-interference capability, the complex lens adaptability and the full-aperture detection precision are obviously improved.

The invention provides a vehicle driving track prediction method, system and device and a medium, and belongs to the technical field of vehicle track prediction.The method comprises the steps that vehicle state information and environment information of each track point of a vehicle are collected to serve as track data, and a deep learning denoising algorithm is used for preprocessing and feature sequence extraction; constructing a trajectory prediction model by using a Transform in combination with a graph neural network, constructing a training set by using the extracted feature sequence to train the trajectory prediction model, and adjusting model parameters by using a multi-task loss function constructed by trajectory prediction precision and uncertainty estimation in the training process; and using the trajectory prediction model to predict the vehicle trajectory, using the Bayesian optimization method to optimize the trajectory parameters with the goal of minimizing the prediction error, and adjusting the optimization parameters with the vehicle dynamics constraint and the road constraint as constraint conditions in the optimization process. According to the invention, through multi-fusion and multi-stage optimization, high-precision prediction of the vehicle track in a complex traffic environment is realized.

The invention relates to the technical field of wind turbine generator control, and discloses a wind turbine generator control optimization method based on dynamic changes of wind speed and wind direction. According to the method, real-time wind speed time sequence data and three-dimensional wind direction vector field data of a target wind field are received, a wind field dynamic analysis model is constructed by using a space-time convolutional neural network, and a wind field energy density distribution matrix and a turbulence intensity probability graph are generated. And constructing a multi-target adaptive optimization model on the basis, generating a unit control parameter instruction set, optimizing a cooperative adjustment coefficient according to a preset unit load-power generation efficiency balance equation, and outputting an optimal control action sequence to a wind turbine generator master control system through Bayesian optimization framework iterative updating. The method can accurately sense the wind field change, effectively balance the unit load and power generation efficiency, realize multi-unit cooperative control, improve the wind energy capture efficiency, and improve the operation stability and economic benefits of the wind turbine generator.

The invention discloses a dynamic leakage prediction method and system for an old oil and gas pipeline, and the method comprises the steps: collecting pressure, flow and temperature parameters in real time through a multi-source sensor, and recognizing abnormal fluctuation through the combination of time sequence analysis and frequency domain feature extraction; calculating a pipeline state evaluation result based on the material degradation model; establishing a leakage prediction model fusing a wall thickness degradation kinetic equation and an LSTM neural network, calculating a leakage probability by adopting a Monte Carlo method, and generating a diffusion velocity and a concentration gradient through CFD numerical simulation; when the diffusion prediction exceeds a safety threshold value, a control strategy is optimized through fuzzy logic and a genetic algorithm; the verification model is fed back after real-time adjustment, and online learning is carried out through Bayesian optimization; and finally, calibrating the model by using experimental data, and deploying and generating risk early warning. The system comprises a multi-source sensor array, a data processing platform and other modules, and full-chain closed-loop control from sensing to early warning is achieved.

The invention discloses a meta-learning Bayesian optimization prediction method for multi-modal displacement of a tank body of a photo-thermal power station, and the method comprises the steps: collecting the data of displacement, temperature, vibration and the like through a multi-modal sensor, separating a displacement sequence into trend, season and residual components through STL decomposition, and carrying out the fusion with the data of the sensor, thereby constructing a 6-dimensional spatial-temporal characteristic matrix; a two-way LSTM-attention mechanism model is adopted, time sequence dependence is captured in a two-way mode, and key cross-modal features are dynamically weighted. And introducing meta-learning-guided working condition adaptive Bayesian optimization: pre-training a meta-model by using a historical working condition to establish a mapping relationship between working condition characteristics and hyper-parameters, dynamically dividing working conditions by real-time data, then activating a corresponding Gaussian sub-model, initializing a search space through meta-learning prior, and optimizing hyper-parameters in combination with an adaptive acquisition function. The test set evaluates the performance of the model through RMSE and MAPE, and finally three-way displacement real-time prediction and safety early warning are achieved. The prediction precision and the dynamic adaptability of the tank body of the photo-thermal power station under the complex working condition are remarkably improved.

The invention relates to the technical field of battery health management, in particular to a battery fault unsupervised detection method based on diffusion Transform and confidence coefficient calibration, which comprises the following steps: acquiring multi-modal time sequence data in a battery operation process, and performing preprocessing, including data cleaning, normalization processing, alignment and sampling; a diffusion Transform self-supervised learning framework is constructed, and the framework comprises a diffusion process based on a cosine scheduling strategy, multi-scale Transform architecture coding and a cross-modal self-adaptive fusion mechanism. Through the framework, potential space representation is optimized, and the battery state confidence coefficient is calculated; the optimal detection threshold value is dynamically determined by adopting a Bayesian optimization framework, whether the battery state is normal or faulty is judged according to the comparison result of the battery state confidence coefficient and the optimal detection threshold value, dependence on a fault sample label is completely eliminated, and a high-performance fault detection model can be trained only by utilizing normal sample data.

The invention discloses an intelligent early warning method for pipeline blockage of a slurry circulation system of a slurry shield, which relates to the field of intelligent early warning, and comprises the following steps of: performing spatial-temporal feature analysis on a standardized multi-dimensional data stream, constructing a blockage feature knowledge graph based on pipeline position and time sequence correlation analysis, and generating a blockage feature vector through a graph neural network; based on the blockage feature vector, analyzing the dynamic change trend of particle distribution through a long-short-term memory network and predicting the particle blockage risk in combination with an acoustic signal, then performing adaptive judgment by fusing geological conditions and construction stage information to obtain a risk assessment result, and inputting the risk assessment result and the blockage feature vector into digital twinborn simulation to obtain the particle blockage risk. A blockage scene is predicted based on fluid dynamics and a particle sedimentation model, early warning parameters are adjusted through Bayesian optimization, and graded early warning signals are generated; according to the invention, by generating the blockage feature vector, the recognition capability of the early local abnormal propagation trend is enhanced, and a reliable basis is provided for accurately predicting the blockage risk.

The invention relates to the field of civil engineering and artificial intelligence, in particular to a transfer learning optimization system and method for predicting the early-age strength of concrete, and the system comprises a multi-scale data sensing module, a physical information constrained deep neural network module, a formula adaptive transfer learning module, a Bayesian optimization prediction module and a federated learning feedback module. The whole process from data collection to model optimization is achieved, through the system, the concrete strength prediction errors of the extremely early age and the standard age are remarkably reduced to + / -5% and + / -3% respectively, meanwhile, the number of concrete test pieces for testing is reduced by 85%, the material and labor cost is greatly saved, and the method not only improves the prediction precision, but also reduces the construction cost. And through continuous learning and feedback, the prediction model is continuously optimized, and an efficient and economical concrete strength prediction solution is provided for actual engineering.

The invention discloses a deep learning artificial intelligence security vulnerability detection platform, and relates to the technical field of intelligent detection, and the platform comprises an information processing module which collects heterogeneous data in real time, carries out the labeling, format unification and modal aggregation processing of the data, and generates a sample set; the feature learning module is used for performing feature unwrapping on the sample set by using a variational auto-encoder, extracting modal data features and potential space representation learning, and outputting a potential space vector; the response generation module is used for generating a vulnerability response strategy through a modal consistency verification and response template matching mechanism based on the vulnerability risk level vector in combination with a response generation engine; and the repair feedback module is used for executing automatic vulnerability repair operation in combination with federal reinforcement learning and Bayesian optimization, performing feedback optimization according to an execution result, and outputting the vulnerability repair operation and a feedback result. According to the method, the response strategy is combined with intelligent matching of the real-time risk level, so that the accuracy and adaptability of vulnerability repair are improved.

The invention discloses a life prediction method based on health index construction and neural network fusion, and belongs to the technical field of equipment state monitoring and predictive maintenance. According to the method, through multi-source degradation feature extraction, common dynamic principal component analysis (CDPCA) dimensionality reduction, health index construction and normalization, deep learning multi-model modeling, integrated learning fusion and Bayesian optimization hyper-parameter optimization, online health assessment and residual life prediction of the equipment part degradation process are realized. Specifically, the method comprises the following steps: firstly, extracting time domain, frequency domain and time-frequency domain features from a sensor acquisition signal, and performing dimension reduction through CDPCA to obtain effective degradation characterization; then, weighting the main features to construct a health index (HI) curve, optimizing the weight through a genetic algorithm, and then performing normalization; a plurality of neural network models such as CNN, Bi-GRU, Bi-RNN, Bi-LSTM and SRNN are constructed based on the normalized HI sequence, and degradation trend modeling is realized; inputting the output results of the neural networks into an integrated learning module for fusion optimization; and finally, carrying out automatic optimization on the key hyper-parameters of the model by utilizing Bayesian optimization. In the equipment operation process, a normalized HI curve can be calculated in real time and input into the fusion model, and the residual life estimation value of the part is dynamically output. According to the method, high-precision, high-robustness and online life prediction can be provided under complex working conditions, the safety and reliability of equipment operation and maintenance are improved, and the method has wide engineering application value.

The invention relates to the crossing field of material design and artificial intelligence, in particular to a solid electrolyte intelligent inverse design method fusing a graph neural network and confidence analysis. According to the method, a prediction framework integrating multiple models is constructed, support vector regression, gradient boosting regression, a deep neural network and a graph neural network are included, component, process and structure parameter characteristics are fully fused, and the nonlinear mapping relation between input variables and performance parameters such as resistivity and conductivity is efficiently learned. In order to improve the credibility, a Bayesian neural network and a Monte Carlo method are further introduced, a confidence interval corresponding to each group of prediction results is output, and quantitative evaluation of the credibility of the prediction value is realized. In the inverse design module, high-dimensional submerged space parameters are generated based on a variational auto-encoder, and intelligent recommendation of parameter combination driven by target performance is realized in combination with strategies such as Bayesian optimization and a genetic algorithm. The design efficiency of the solid electrolyte and the success rate of material discovery can be effectively improved.

The invention discloses a lithium battery charge state estimation method based on a Bayes-TLCO optimization deep neural network, and belongs to the technical field of battery state monitoring. The method comprises the following steps: firstly, preprocessing a lithium battery charging and discharging data set; then, constructing a deep neural network model comprising a convolutional neural network, a long-short-term memory network and a multi-head attention mechanism, dynamically optimizing hyper-parameters of the model by using a Bayesian optimization-assisted termite life cycle optimization algorithm, introducing Bayesian optimization during iteration stagnation in a TLCO algorithm iteration process, and finally obtaining a termite life cycle optimization model; fitting historical data through a Gaussian process to construct a search empirical model, generating high-value sampling points, and accelerating model hyper-parameter convergence to a globally optimal solution; and finally, estimating the state of charge of the lithium battery. The method breaks through the limitation of a single algorithm, achieves the high-precision estimation of the state of charge of the lithium battery under a complex working condition, effectively improves the model training efficiency, is suitable for electric vehicles, energy storage systems and other scenes, and provides a key technical support for the intelligent upgrading of battery management.

The invention relates to the technical field of simulation model optimization, and discloses an aero-engine model Bayesian optimization method for quantizing uncertainty, and the method comprises the steps: building a probability mapping relation from a component index to an output response through constructing a Bayesian neural network agent model based on a probability weight coefficient; and by taking the difference between the output response and the corresponding complete machine test data as a multi-objective loss function and taking the minimization of the multi-objective loss function as an optimization objective, optimizing the component indexes by adopting a Bayesian optimization method based on a Gaussian process to obtain an optimal component index combination. Not only is a nonlinear relationship between high-dimensional parameters and simulation-test deviation accurately modeled through a neural network, but also efficient search of a parameter space is realized through a Gaussian process. The technical problems that when a traditional optimization method is used for processing the high-dimensional, strong-nonlinearity and multi-parameter coupling complex optimization problem of the aero-engine, the calculation efficiency is low, local optimum is prone to occurring, and result uncertainty cannot be quantified are solved.

The invention discloses a stress analysis method for bridge incremental launching construction, and particularly relates to the field of stress analysis. According to the method, a mechanical state matrix is generated by combining wavelet noise reduction and Kalman filtering through distributed optical fibers, a piezoelectric force sensor, a vibrating wire stress meter and other equipment and real-time data; a pushing system-temporary support-beam body coupling dynamic mechanical model is established, and a generalized alpha method is adopted for solving and Bayesian optimization calibration parameters are adopted; key parameters are identified on line through a three-level progressive framework, boundary conditions are dynamically updated in combination with a total station and a laser tracker, and supporting rigidity self-adaptive adjustment is achieved through fuzzy PID control. Model confidence evaluation adopts a residual norm-modal confidence criterion-Bayesian update three-level mechanism, finally, stress distribution, support reaction and displacement deviation are calculated based on a correction model, and a safety index, threshold alarm and risk analysis report is generated through a fuzzy comprehensive evaluation method and fed back to a construction control center in real time.

The invention provides a hybrid parallel and dynamic scheduling method of a hybrid expert model based on 3D near-memory processing. The method comprises the following steps: establishing a joint performance analysis model; performing off-line linear programming optimization expert distribution; performing Bayesian optimization on physical node mapping; performing online reasoning; carrying out online dynamic priority detection; and an expert pre-broadcast and communication-friendly lexical element distribution strategy with optimal efficiency is provided. According to the method, node balancing optimization is realized through offline linear programming, and the problem of load imbalance of 3D NMP calculation is remarkably improved; in combination with a Bayesian optimization mapping strategy of link balance, the communication speed-up ratio is increased, and NoC link congestion is reduced; a dynamic scheduling strategy adapts to dynamic changes of expert activation in real-time reasoning through calculation load prediction and a pre-broadcast mechanism. Through cooperation of the offline automatic hybrid parallel mapping algorithm and the online dynamic scheduling strategy, the calculation load and the communication overhead are effectively balanced, and the reasoning efficiency of the hybrid expert model MoE on the 3D near-memory processing architecture is remarkably improved.

The invention relates to the field of wind speed and wind direction prediction, and discloses a wind speed and wind direction prediction method based on an improved TCN-LSTM, and the method comprises the following steps: collecting real-time monitoring multi-dimensional meteorological data of an offshore wind station, and carrying out the preprocessing; performing feature fusion and feature enhancement processing on the preprocessed data, wherein the feature enhancement processing comprises spatial feature extraction, tensor reconstruction and time sequence modeling; inputting the data after feature fusion and feature enhancement processing into a wind speed and wind direction prediction model based on an improved TCN-LSTM hybrid neural network, and predicting the wind speed and wind direction at a future moment; the wind speed and direction prediction model comprises a time-space separation TCN network, a multi-head self-attention mechanism, an adaptive Dropblock mechanism, an LSTM network and a Bayesian optimization module; according to the method disclosed by the invention, the accuracy, robustness and calculation efficiency of wind power prediction in a complex marine environment can be improved.

The invention relates to the technical field of power system optimization, and discloses a regional building group source network load storage demand response optimization method. Comprising the following steps of multi-source heterogeneous data fusion collection and intelligent preprocessing, power utilization behavior spatial-temporal characteristic deep mining, multi-dimensional response potential dynamic evaluation modeling, multi-target layered optimization decision generation, personalized excitation strategy self-adaptive generation and closed-loop cooperative regulation execution and feedback. According to the method, user strategy updating is simulated through a replication dynamic equation of an evolutionary game, efficient search of excitation parameters is realized by combining a Bayesian optimization Gaussian process and an expectation improvement function, a user group strategy evolution rule can be dynamically captured, parameters such as electricity price discount and subsidy gradient are accurately optimized in a limited sampling range, and the method is suitable for large-scale popularization and application. A'behavior modeling-data optimization 'closed loop is formed, users are stimulated to participate in demand response, optimal configuration of power resources is realized, and the flexibility and economy of the system are improved.

The invention relates to the technical field of electrical variable testing, in particular to a high-precision performance testing processing method and system for a low-impedance voltage transformer. The method comprises the following steps: constructing a controllable test excitation signal, and synchronously collecting a corresponding primary side voltage and a secondary side voltage of a mutual inductor; space electromagnetism elimination is carried out according to the primary side voltage and the secondary side voltage of the mutual inductor, and frequency domain characteristic decomposition and signal instantaneous offset calculation are carried out at the same time, so that a mutual inductor signal characteristic matrix is constructed; acquiring environment parameters corresponding to the low-impedance voltage transformer; constructing a neural network model based on Bayesian optimization, and predicting and outputting a performance parameter set corresponding to frequency response and load characteristics; and comparing the performance parameter set with a preset standard threshold value, feeding back, generating a calibration compensation coefficient, testing and evaluating, and generating a high-precision performance test report corresponding to the low-impedance voltage transformer. According to the invention, high-precision performance testing of the low-impedance voltage transformer can be realized.

The invention relates to the technical field of hydroelectric generating set parameter optimization, in particular to an intelligent hydroelectric generating set parameter optimization method and system based on multi-modal data fusion, and the method integrates multi-modal data, a graph neural network and Bayesian optimization to realize efficient and intelligent hydroelectric generating set parameter optimization. Time domain, frequency domain, acoustics, temperature and hydraulic multi-modal data are integrated, and feature vectors are generated through intra-modal feature extraction and hierarchical attention mechanism fusion; thirdly, constructing a unit knowledge graph, and extracting priori knowledge by using a graph attention network to realize cross-domain knowledge migration; and finally, on the basis of a multi-objective constrained Bayesian optimization algorithm, in combination with a Gaussian process agent model, determining optimal PID parameter configuration, and performing incremental optimization through closed-loop verification. According to the method, the optimization time is shortened from several days to 15 minutes or less, the efficiency is improved by 95% or above, and the parameter optimization efficiency and precision of the hydroelectric generating set are remarkably improved.

The invention discloses a regional power grid wind power generation power prediction optimization method and system, and particularly relates to the technical field of power grid wind power generation. Multi-source environment data is collected, wind speed change characteristics are extracted, a time series data set is constructed, a hybrid prediction model is constructed in combination with a long-short term memory network and a gradient boosting decision tree, a time series trend and a nonlinear wind speed-power mapping relation are captured respectively, and prediction weights of the time series trend and the nonlinear wind speed-power mapping relation are adaptively adjusted through an attention mechanism. According to the method, the model hyper-parameters are adaptively adjusted by further combining Bayesian optimization, short-term prediction errors are corrected by using Kalman filtering, the real-time adaptability and stability of prediction are enhanced, the problems of prediction misalignment and the like caused by high nonlinearity and data scarcity of a wind speed mode in a complex terrain environment are effectively solved, and the prediction accuracy is improved. The wind power prediction precision is improved, a more stable and reliable scheduling reference is provided for a regional power grid, and the standby capacity demand and the operation cost are reduced.

The invention discloses a viscous coarse-grained soil permeability coefficient prediction method based on a physical constraint neural network, and the method comprises the following steps: carrying out an indoor viscous coarse-grained soil seepage test, and establishing a viscous coarse-grained soil permeability coefficient formula considering porosity and grain composition characteristics, further constructing a mixed model containing a physical driving item and a neural network data driving item, forming a complete data set through a numerical simulation technology and literature investigation on the basis of a seepage test, complementarily collecting porosity, grain composition characteristics and corresponding permeability coefficient data of the viscous coarse-grained soil sample, and dividing the complete data set into a training set and a test set; according to the method, optimal hyper-parameters are dynamically searched in combination with Bayesian optimization for model training, a loss function curve and permeability coefficients of the viscous coarse-grained soil under different porosity and grading characteristics are obtained, tests show that high-precision prediction of the permeability coefficients of the viscous coarse-grained soil is achieved, and the problems that a traditional method is insufficient in physical constraint and low in prediction precision are solved.

The invention provides an underground water pollutant concentration prediction method and system based on machine learning, and relates to the technical field of underground water pollutant concentration prediction.The method comprises the steps that historical data, hydrogeological parameters, meteorological data, human activity data and geochemical parameters of underground water pollutant concentration of a target area are preprocessed; dividing a training set, a verification set and a test set; constructing a preset resolution feature set based on a geochemical mechanism; selecting an adaptive machine learning model according to data characteristics and coupling a physical mechanism; performing hyper-parameter tuning by adopting Bayesian optimization, and supplementing small sample data in combination with transfer learning to complete model training; predicting the underground water pollutant concentration of the target area by using the trained model, and outputting a pollutant concentration prediction result with an uncertainty interval; the invention provides a technical scheme for predicting the concentration of underground water pollutants, which is efficient, accurate and high in adaptability.

The invention discloses an axial flux motor temperature prediction method based on equivalent thermal circuit method calculation, and the method comprises the following steps: 1, motor thermal circuit unit division: decomposing a motor into a stator unit, a rotor unit, an air gap unit and a housing unit, and constructing an equivalent thermal network through a node-branch method; 2, calculating a multi-physics coupling heat source; 3, thermal resistance parameter dynamic calculation and CFD coupling optimization: calculating conduction thermal resistance, convection thermal resistance and contact thermal resistance; and 4, parameter self-calibration based on machine learning: constructing a PINN model according to a physical law and known physical parameters, introducing a Bayesian optimization algorithm on the basis of the PINN model, adjusting and optimizing the parameters of the PINN model by using Bayesian optimization, designing a reinforcement learning algorithm, and carrying out self-calibration on the parameters of the PINN model. Enabling the reinforcement learning algorithm to dynamically adjust parameters according to the real-time operation data of the system and the prediction result of the PINN model; 5, constructing and solving a heat balance equation; and step 6, visualizing and verifying the temperature field.

The invention relates to an industrial vision adaptive illumination compensation system and method based on Bayesian optimization, and the system comprises an environment perception module which is used for collecting the multi-dimensional environment state data of an industrial site in real time, and collecting an original image; the intelligent preprocessing module is used for enhancing the original image according to the parameter combination output by the Bayesian optimization module to generate an enhanced image; the model reasoning module is used for identifying and detecting the enhanced image through a bimodal algorithm to generate a detection result; the Bayesian optimization module is used for performing objective function calculation to generate an optimization objective score, performing iterative optimization according to the optimization objective score and a historical observation data set, generating a candidate parameter combination, and generating a global optimal parameter and a configuration template based on the candidate parameter combination and a current environment feature; and the industrial interface module is used for transmitting the global optimal parameter, the detection result and the multi-dimensional environment state data to an industrial control system. According to the invention, the efficiency and adaptability of illumination compensation are improved, and the data calculation amount is reduced.

The invention provides a method for predicting the quality of a sparse small sample industrial process based on a stacked network model. The method comprises the following steps: collecting end point quality report data of an industrial production process; performing hierarchical processing on the acquired data according to the missing rate, and removing abnormal data in combination with a quartile method and production experience; generating a synthetic data expansion small sample data set by adopting a conditional generative adversarial network; obtaining a first-layer basic model based on an accumulated contribution rate screening method of an SHAP value; constructing a first layer of a stacked integrated learning model and adjusting hyper-parameters by using Bayesian optimization; constructing a Ridge meta learning device to integrate the output of the basic model and constructing a second-layer network; a six-fold cross validation training model is adopted; predicting performance through a multi-index quantitative model based on the test set; and verifying the prediction precision of the end-point phosphorus content and the temperature by using real converter production data. The method can realize high-precision prediction of the end point quality index of the complex industrial generation process, and is beneficial to ensuring the product quality and improving the production efficiency.

The invention relates to the crossing field of hydraulic engineering hydrological monitoring technology and machine learning prediction technology, discloses a sediment concentration prediction method based on deep learning, and aims to solve the problems that in existing sediment concentration prediction, hyper-parameter manual tuning is low in efficiency, key feature attention is insufficient, local and time sequence information is difficult to consider by a single model and the like. Accurate prediction is realized through five core modules: a data preprocessing module performs missing value filling, abnormal value processing and derivative feature generation on hydrological data; the feature selection module screens key features based on mutual information; the time sequence construction module generates time sequence data through a sliding window; the hyper-parameter automatic optimization module adopts Bayesian optimization iteration to obtain an optimal hyper-parameter; the CNN-LSTM-attention prediction module fuses CNN local feature extraction, bidirectional LSTM time sequence dependence capture and multi-head self-attention mechanism key feature focusing capability, is suitable for scenes such as river channels and channels, and provides efficient decision support for hydrological regulation and control.

The invention relates to a Bayesian optimization-based ruthenium, tin and indium doped lithium-rich manganese-based electrocatalyst screening method, electronic equipment and a storage medium, and the method comprises the following steps: generating a uniform ruthenium, tin and indium doped lithium-rich manganese-based material data set based on Dirac distribution, and generating a doped structure through element replacement; calculating hydroxyl adsorption energy and extracting descriptors to construct a data set to train a machine learning model; performing cell expansion operation on the initial electrocatalyst structure, predicting hydroxyl adsorption energy of each adsorption site, and mapping adsorption energy deviation into current density characterization component activity in combination with Boltzmann distribution; selecting an initial component based on the obtained component activity information, and constructing an agent model by utilizing Bayesian optimization; and determining a to-be-sampled component through an expectation improvement strategy, sampling and updating the agent model, and outputting an optimal doping proportion. Compared with the prior art, the method has the advantages that the ruthenium, tin and indium doped lithium-rich manganese-based electrocatalyst with excellent catalytic performance can be efficiently screened out, and the experiment cost is reduced.