2013 results about "Hyperparameter" patented technology

The invention discloses a multi-target intelligent optimization method and system for blasting parameters of a strip mine in a high-altitude cold region. The method comprises the following steps: carrying out data acquisition to obtain a parameter data set; performing data preprocessing on the parameter data set to obtain a feature sample set; constructing an initial blasting parameter model based on a machine learning algorithm, and performing hyper-parameter optimization on the model to obtain a blasting parameter model; a multi-objective optimization function is constructed: based on the multi-objective optimization function and the blasting parameter model, solving is carried out in combination with environmental condition constraints, and a pareto optimal solution set is obtained; according to the pareto optimal solution set, a representative solution is selected, a visual scheme is generated, and blasting parameter optimization of the strip mine in the high-altitude cold region is completed. According to the method, temperature, oxygen and frozen soil constraint conditions of the high-cold and high-altitude environment are introduced, blasting safety, lumpiness uniformity and the explosive utilization rate are considered at the same time through multi-target collaborative optimization, the method can adapt to the extreme environment, meanwhile, the one-sidedness of single-target optimization is avoided, and the intelligent level of blasting design and implementation is greatly improved.

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.

A method, computer program product, and computing system for processing a query provided to a generative AI model. A content portion retrieved by a Retrieval Augmented Generation system for the query is processed. User context information associated with a user providing the query is determined. Hyperparameters are generated for processing the prompt with the generative AI model by processing the query, the content portion, and the user context information using run-time surrogate model inversion optimization.

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 discloses a machine learning assisted polyethylene reaction performance prediction model training method, prediction method and device. The method comprises the following steps: acquiring a training set; screening feature items used for model training; obtaining a gradient boosting regression model for catalytic activity, a gradient boosting regression model for molecular weight and a gradient boosting regression model for molecular weight distribution; extracting feature items for model training from the data of the training set so as to obtain feature vectors; and respectively inputting the feature vectors into each model so as to train each model, thereby respectively obtaining hyper-parameters of the trained gradient-boosted regression model for catalytic activity, hyper-parameters of the trained gradient-boosted regression model for molecular weight and hyper-parameters of the trained gradient-boosted regression model for molecular weight distribution. According to the method, a model relationship between input characteristics and polymerization results (including catalytic activity, molecular weight, molecular weight distribution and the like) is established through training set learning.

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 provides an urban solid waste incineration NOx emission prediction method based on MSGSE-NSCF, and the method comprises the steps: obtaining a key variable and nonlinear dependence of NOx emission, and constructing a non-stationary cross converter; constructing a non-stationary gated spectrum enhancement sub-module and a gated convolution attention fusion sub-module, extracting space-time enhancement representation, and realizing time-frequency domain feature fusion modeling; performing hyper-parameter verification to obtain reasonable parameters of the model; according to the NOx emission prediction method based on the non-stationary cross converter and the multi-scale time-frequency feature enhancement, the non-linear dependence, the original structure and the dynamic change of data can be reserved, the non-stationary time sequence is modeled, the output scale is kept, and the NOx emission concentration is obtained. In addition, time domain-frequency domain and global-local cooperative enhancement can be achieved, selective modeling of periodicity and key frequency components is enhanced, and an accurate NOx emission prediction result is obtained.

The invention discloses a TR assembly gold wire bonding process parameter prediction method based on a multilayer perceptron neural network, and belongs to the technical field of microwave device intelligent manufacturing. According to the method, an intelligent mapping model of gold wire bonding geometric parameters and radio frequency performance is constructed by fusing a multi-layer perceptron neural network and parameterized electromagnetic simulation. The method specifically comprises the following steps: generating 45 groups of samples in a process parameter space by adopting Latin hypercube sampling; obtaining an S parameter data set through batch processing electromagnetic simulation; box-Cox conversion and normalization preprocessing are carried out on the data; the method comprises the following steps: constructing an MLP neural network model of a 3-32-16-2 structure, and determining hyper-parameters by using Bayesian optimization; and after training is completed, rapid reverse mapping from target performance to process parameters is realized. According to the method, the number of traditional tests is reduced from more than 200 to 45, the predicted root-mean-square error of S21 is smaller than or equal to 0.12 dB, the determination coefficient is larger than or equal to 0.96, and the parameter backstepping time lt is obtained; according to the method, full-process automation from simulation, training, optimization to production and issuing is realized, and the development efficiency of the TR component is remarkably improved.

The invention provides a system and method for managing the lifecycle of machine learning models, from development to deployment and ongoing operation, across various environments including on-premises, cloud, and hybrid infrastructures. The system features a model build platform for data processing, feature generation, model development, training, and hyperparameter tuning. A model analytics engine extracts metadata, performs complexity analysis, and generates configuration files specifying environment settings and resource needs. A secure model repository enables version-controlled storage, while a deployment platform retrieves, validates, and deploys models in containerized environments like OpenShift or Kubernetes. The platform dynamically allocates resources, supports real-time and batch scoring, and monitors model performance with guardrails. Customizable agents provide real-time feedback and automated optimization, and the system can securely decommission models while maintaining detailed lifecycle records. The invention enhances the efficiency, security, and scalability of machine learning operations with continuous performance improvement and compliance automation.

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 provides a lithium ion battery health state lightweight detection method based on a physical information neural network, and the method comprises the steps: collecting the time, voltage, current, temperature and state-of-charge data of a battery in a takeoff and landing stage discharge process, processing the data into takeoff and landing stage discharge time sequence data, and carrying out the detection of the lithium ion battery health state based on the takeoff and landing stage discharge time sequence data. The method comprises the following steps: designing characteristic factors related to battery aging, screening the characteristic factors by utilizing a Pearson's correlation coefficient and a grey relational degree algorithm to obtain optimal characteristic sequence data, inputting the optimal characteristic sequence data into a physical information neural network model constructed by two serially connected neural networks for training, and in the training process, obtaining the optimal characteristic sequence data. And performing hyper-parameter tuning on the two neural networks by adopting a Bayesian optimization algorithm, then performing fine tuning on the second neural network by adopting a hierarchical transfer learning strategy, and finally applying the trained physical information neural network model to battery health state detection. The method improves the quality of feature data, reduces the calculation complexity of features and models, and achieves the accuracy and reliability of the detection of the health state of the battery under the airborne condition.

The invention discloses a tunnel or mine water gushing space-time prediction method and system coupled with a hydrodynamic numerical model, and the method comprises the steps: outputting multi-source data based on an identified and verified underground water numerical model, complementing the missing of measured data, quantifying the difference between the permeability characteristics of a fault and a normal stratum, and coupling the difference to a data system, and tunnel or mine excavation space data are merged. And constructing an LSTM-isolated forest-K neighbor regression coupling model, and configuring a multifunctional module to realize multi-scene data co-training. The preprocessed multivariate time series data is divided into a training set and a test set, hidden features are extracted through a coupling model, anomaly detection results are fused, a residual error correction model is synchronously trained, and hyper-parameters and weights are adaptively optimized according to multi-engineering prediction error feedback. And based on the trained coupling model, carrying out synchronous water gushing space-time prediction by adopting a window rolling strategy, and outputting prediction data meeting engineering precision in combination with residual correction. And reliable technical support is provided for safety prevention and control of engineering construction.

The invention relates to the field of gas concentration detection, and particularly discloses a real-time feedback and adaptive learning method for natural gas infrared spectrum measurement, which comprises the following steps: S1, acquiring infrared spectrum information of a natural gas body by using an infrared spectrometer, and constructing a historical sample set; s2, preprocessing the spectral data of the historical sample set; s3, selecting an optimal algorithm and a hyper-parameter by adopting XGBoost and Bayesian optimization; s4, constructing a qualitative model to identify gas types and match data; s5, calculating the similarity between a field sample and a historical sample through a Siamese network, and setting a threshold value to screen local data; s6, improving the KNN to construct a local dynamic quantitative model to predict the concentration; s7, processing low-similarity abnormal data by the global dynamic model, and improving the reliability by combining moving average and abnormal calibration; and S8, introducing reinforcement learning and online gradient descent to adjust parameters in real time to optimize the precision. According to the technical scheme, high-accuracy natural gas detection can be carried out in a complex environment.

The invention relates to the technical field of deep learning hyper-parameter optimization, in particular to a multi-target hyper-parameter joint optimization method and system for a deep learning model. The specific implementation process comprises the steps of obtaining a current hyper-parameter of a deep learning model, generating a learning track vector, and performing utility prediction to generate a learning utility projection; on the basis of the dominating relationship between the learning utility projection and the current Pareto optimal leading edge, pruning the disadvantage training task, updating the Pareto optimal leading edge by using non-dominating sorting, and constructing a Pareto strategy network; and carrying out topology congestion degree analysis on the updated Pareto optimal leading edge, generating a leading edge exploration bias vector, inputting the leading edge exploration bias vector into the Pareto strategy network to update hyper-parameter codes, and entering the next round of iteration. According to the method, through the multi-objective optimization algorithm and in combination with the dynamically updated Pareto strategy network, the problems that the hyper-parameter optimization process is long in time consumption, low in efficiency and prone to falling into local optimum are effectively solved, and the optimization efficiency and the solving quality are improved.

The invention belongs to the technical field of underground engineering intelligent construction, and particularly discloses a shield tunneling performance prediction method and system based on an interpretable BO-LGBM model, and the method comprises the steps: receiving detection data in a shield tunneling process, and determining tunneling parameters, geological parameters and karst parameters based on the detection data, so as to construct an input feature set; constructing an LGBM model, performing multi-stage screening on the input feature set to obtain a comprehensive feature importance sequence, and determining key target features corresponding to model prediction influence according to the comprehensive feature importance sequence; on the basis of key target features, a Bayesian optimization algorithm is used to optimize hyper-parameters of the LGBM model, and a trained BO-LGBM prediction model is obtained; the BO-LGBM prediction model is used for predicting ground surface settlement, tunneling efficiency, specific energy and overexcavation rate of the detection data; and obtaining a performance index based on the trained prediction model so as to evaluate model performance and prediction precision. According to the invention, the model prediction accuracy of the shield performance can be improved.

The invention provides a low-voltage power distribution network load change trend intelligent prediction and management method, belongs to the field of low-voltage power distribution network load prediction, and is used for solving the problems of large load fluctuation, insufficient prediction precision and high cloud deployment delay of a hybrid industry transformer area in related technologies. The method is deployed at an edge node of a transformer area, high-quality data is output through multi-modal data anomaly detection and scene completion, a four-dimensional dynamic load portrait is constructed based on the high-quality data, model super-parameter self-adaptive parameter adjustment is realized by combining transfer learning and Bayesian optimization, and accurate load data is output through three-dimensional linkage resource scheduling and dynamic fusion residual error correction. The method improves the load prediction precision and efficiency, reduces the response delay, and can effectively support the real-time scheduling of the power distribution network.

The invention discloses a photovoltaic power interval prediction method based on a GRU-LSTM combined neural network, and belongs to the technical field of photovoltaic power interval prediction. The method comprises the following steps: S1, taking historical power generation data as original wind-solar power generation power prediction data, processing the data, and screening related meteorological characteristics by adopting a Pearson correlation coefficient; s2, a GRU-LSTM combination model is constructed, and related hyper-parameters are set; s3, taking the screened related meteorological features as input for training, calculating a photovoltaic point prediction result according to a weight coefficient, and performing related error evaluation; and S4, based on the photovoltaic power point prediction result, calculating a photovoltaic power interval prediction result by using a quantile regression technology, and detecting performance evaluation through a test set. According to the method, the minimum prediction error correlation index is taken as the target, the influence of different weathers on photovoltaic power processing is considered, the Pearson's correlation coefficient analysis is utilized to select more representative meteorological characteristics, and the combined model and the quantile regression technology are utilized to finally obtain the photovoltaic power interval prediction result.

The invention discloses a time-frequency double-domain isolation time sequence anomaly detection method based on Mamba-self-attention, which can be applied to the fields of industrial manufacturing, medical equipment and the like and can detect anomaly by quantifying time-frequency difference. The method comprises the steps of extracting a multivariable time sequence sample from business data, and obtaining multivariable data through reversible instance normalization; the input time domain representation module is used for independently inputting a Mama network according to a natural time sequence and an inversion time sequence, capturing forward and reverse time features and fusing the forward and reverse time features into time features; a frequency domain representation module is input, seasonal variables are extracted, frequency features are extracted in combination with discrete cosine transform and an attention mechanism, and the frequency features are reconstructed to a time domain through inverse discrete cosine; the time and frequency characteristics are input into a time-frequency difference module, and the inconsistency is quantified through Kullback-Leible (KL) divergence so as to compare and learn a similarity loss function training model; and generating an anomaly score and setting a hyper-parameter to judge anomaly. The method is based on a bidirectional Mama and self-attention time-frequency double-domain isolation architecture, mode specificity discrimination features masked by traditional fusion are reserved, the consistency of normal mode domains is high, the correlation of abnormal performance is collapsed, and the detection accuracy and reliability are improved.

A composite AI system and method for advanced reasoning and automation that integrates symbolic knowledge graphs and algorithms with non-symbolic, or connectionist, models such as neural embeddings. A hierarchical architecture enables dynamically distributed, cooperative reasoning through layperson and expert-led challenge-based verification, model blending, model fitness and retraining and selection, comprehensive feedback loops at individual model or model blend or process flow with or without supervision, and specialized routing of processing to account for various operational risk, regulatory, legal, privacy, or economic considerations. Models, datasets, knowledge bases, simulations and simulation components, and embeddings are iteratively refined using knowledge graph elements and model, process, simulation or flow / process optimal hyperparameters which are recorded and tracked. Extraction of symbolic representations from connectionist models links them to curated ontologies of facts and principles.

The invention relates to the technical field of numerically-controlled machine tool diagnosis, and discloses a numerically-controlled machine tool fault diagnosis system based on machine learning. The system comprises a multi-source sensing data acquisition module for acquiring multi-dimensional sensing data such as vibration spectrum, spindle current waveform, temperature distribution, servo motor encoder feedback and the like; the operation feature coding module receives the multi-dimensional sensing data, extracts time domain statistical features and frequency domain energy distribution features, and generates a multi-source feature coding result; the incremental learning analysis module dynamically updates the feature weight through an incremental learning algorithm, and constructs an incremental training data set; the genetic optimization module optimizes the network structure and hyper-parameter configuration of the fault diagnosis model according to the incremental training data set, and generates optimized network structure parameters; and the integrated diagnosis decision module receives the current operation state data and the optimized network structure parameters, fuses diagnosis results of a plurality of base classifiers through an integrated learning algorithm, and outputs fault type classification signals.

The invention discloses an evidence deep learning method for double-layer dynamic uncertainty calibration based on a meta-strategy. A double-layer optimization architecture is adopted. An inner layer optimizes an evidence deep learning model to execute a pixel-level segmentation task and estimate uncertainty; and the outer layer optimizes a state-aware meta-policy network. The meta-policy network receives state information reflecting training dynamics in real time and generates key hyper-parameters used for configuring an inner-layer model loss function according to the dynamic state; and a multi-target reward signal is formed through performance in multiple aspects of prediction accuracy, calibration error, misclassification uncertainty and the like of a periodic evaluation model on a verification set. According to the method, hyperparameter dynamic adaptive adjustment is carried out by introducing a state-aware meta-strategy, the limitation that a traditional method depends on static setting is overcome, prediction precision and uncertainty calibration can be better balanced, and the reliability and generalization ability of a deep learning model in high-risk application scenes (such as medical image analysis) are remarkably improved.

The invention discloses a battery life prediction method based on Bayesian optimization and a physical information neural network, and belongs to the field of battery health monitoring. The method comprises the following steps: collecting and preprocessing lithium battery charging and discharging data, and then dividing the data into a training set and a test set; then, extracting a dQ / dV curve and other related features, constructing a physical information neural network integrated with physical constraints, and optimizing hyper-parameters of the physical information neural network by using a Bayesian optimization algorithm; and training the model by using a training set, updating parameters through back propagation in the process, evaluating precision by using a test set, and adjusting a strategy. And finally, inputting the characteristics of the lithium battery to be predicted into the trained model, outputting a residual service life prediction value, and comparing with actual data evaluation. According to the invention, reliable lithium battery life prediction can be provided for the photovoltaic energy storage system, and the system operation and maintenance efficiency can be significantly improved, the maintenance cost can be reduced, and the safe and stable operation of the energy storage system can be ensured by early warning the health state of the battery in advance.

The invention discloses a stainless steel thin-wall pipe bending forming production line control method and system. The method comprises the steps that state feature vectors are generated through data collection; establishing a hybrid network model, and optimizing hyper-parameters of the hybrid network model by using an OOA eagle optimization algorithm to obtain an improved hybrid network model; inputting the state feature vector into an improved hybrid network model, and outputting predicted values of the springback value, the wrinkling probability and the ovality which are about to occur in the current bending section; inputting the predicted value into a multi-objective optimization algorithm, and performing back calculation in real time to obtain an optimal compensation parameter set by taking minimization of springback, wrinkling risk and ovality as optimization objectives; and the compensation parameter set is transmitted to a physical execution unit for production line control including bending control, core rod control, clamping control and feeding control. And the first-pass yield of bending forming and the production control efficiency are improved.

The invention relates to the technical field of shield tunnel construction intelligent control, in particular to a shield tunneling machine tunneling speed intelligent prediction method based on multi-algorithm collaborative optimization. The method comprises the following steps: firstly, acquiring operation parameters and geological and environmental parameters of the shield tunneling machine in real time through a multi-source sensor and an industrial bus; carrying out localized cleaning, normalization and feature extraction on the data by utilizing an edge computing device; further, integrating particle swarm optimization, a genetic algorithm, a sparrow search algorithm and a starvation game search algorithm, and realizing global automatic optimization of the hyper-parameters of the bidirectional long-short-term memory network through a parallel independent optimization and result aggregation strategy; and finally, predicting the tunneling speed in real time by using the optimized model. According to the method, the problems of low prediction precision, weak model generalization capability, dependence on manpower on hyper-parameter optimization and the like caused by insufficient multi-source heterogeneous data processing capability are effectively solved, the prediction accuracy, the adaptability and the engineering practical value are improved, and reliable support is provided for safe and efficient propulsion of shield construction.

The invention provides an LSTM underwater robot modeling method based on TPE hyper-parameter optimization, and relates to the technical field of underwater robot modeling, and the method comprises the steps: carrying out the time sequence feature extraction through a memory unit comprising a forgetting gate, an input gate and an output gate, and predicting the state change amount delta Yt'at a t + 1 moment through an output layer; performing iterative optimization on the number of layers and the number of units of the LSTM network and training the model to obtain an optimized LSTM model; evaluating the optimized LSTM model through a multi-step cumulative prediction error, inputting an initial real state into the model to carry out T-step recursive prediction, updating a current state by utilizing a prediction state increment in each step, and finally calculating an average position error and an attitude error in a T-step window on a verification set; and selecting the hyper-parameter combination with the minimum comprehensive error of the verification set as a final model parameter, and completing the dynamic modeling of the underwater robot. According to the method, the problem that the model is inaccurate due to excessive parameterization in a nonlinear dynamic model can be solved.

The invention relates to the technical field of renewable energy source prediction, and provides a method and system for driving a CNN-LSTM neural network to predict photovoltaic power generation based on an eagle optimization algorithm, and the method comprises the steps: collecting historical meteorological factor data and photovoltaic power generation power data, and screening out meteorological factors having a significant influence on the photovoltaic power generation power; building a CNN (convolutional neural network)-RCBAM-LSTM (radio channel Performing global exploration and local mining through an eagle optimization algorithm, and dynamically optimizing hyper-parameters of the CNN-RCBAM-LSTM model; the meteorological factor data are input into the CNN-RCBAM-LSTM model; sequentially carrying out one-dimensional convolution preliminary feature extraction, feature re-calibration based on an RCBAM attention mechanism, and carrying out multiple stacking to obtain a preprocessed feature matrix; in the feature re-calibration process, related coefficients are obtained through an eagle optimization algorithm; outputting a preliminary photovoltaic power generation prediction result; iteratively updating the position of the eagle to obtain a final optimization result; and inputting real-time meteorological factor data into the trained CNN-RCBAM-LSTM model to obtain a final photovoltaic power generation prediction result, so as to solve the problem of insufficient estimation precision of photovoltaic power generation.

The invention discloses a reinforcement learning unmanned ship path control method based on double-track regulation and control random network distillation. The method comprises the operation steps that an unmanned ship builds a path tracking simulation environment and a kinetic model; the unmanned ship builds a core algorithm flexible action evaluation algorithm framework; the unmanned ship deploys a priority experience playback pool based on quality and success guidance; an uncertainty perception and risk perception mechanism is introduced into the unmanned ship; the unmanned ship builds a success rate-based reward attenuation and cold start module, and the unmanned ship calculates a total reward and designs a reward softening mechanism to smooth the total reward; the unmanned ship imports hyper-parameters of all the modules, starts training circulation in a simulation environment, and dynamically adjusts exploration intensity and the like; according to the method, uncertainty and risk indexes are introduced, the exploration intensity of the intelligent agent is controlled, the intelligent agent is prevented from making dangerous actions, and the robustness is improved; a priority experience playback pool based on quality and success guidance is introduced, high-quality samples are better played back, and strategy convergence is accelerated.

Described are a system, method, and computer program product for distributed execution of a machine-learning model on a server cluster. The method includes initiating retrieval of a machine-learning model from a data repository and converting the machine-learning model to an executable format. The method includes transmitting the converted machine-learning model to each node of the server cluster and executing the converted machine-learning model on each node. The method includes generating an initial performance metric based on execution of the converted machine-learning model on each node. The method includes transmitting the plurality of initial performance metrics from each node to an external processor and combining the plurality of initial performance metrics to produce a combined performance metric. The method includes modifying a model hyperparameter of the machine-learning model based on the combined performance metric and executing the modified machine-learning model in a computer system to evaluate real-time event data.

The invention discloses a biomass gasification experimental design and performance prediction method based on support vector and transfer learning, which comprises the following steps: establishing an Aspen plus simulation model, adjusting the gasification temperature to air equivalence ratio in the Aspen plus model, and obtaining a biomass gasification simulation data set covering wide boundary operation conditions; taking the simulation data set as a training sample, constructing a simulation agent model, and searching an optimal hyper-parameter; extracting a support vector sample through a support vector regression method, designing experimental working condition points, and collecting experimental data to obtain an experimental data set; taking the experimental data set as a model input sample, and outputting a predicted value by the model; performing linear migration on a model prediction result; and performing secondary correction on the difference between the migrated result and the experimental data to obtain a high-precision calibration model fusing linear migration and residual correction. According to the method, the problems of high acquisition cost of biomass gasification experiment data, limited simulation data precision and the like are effectively solved, a model with better generalization ability and higher interpretability is constructed under limited experiment samples, and accurate prediction of product distribution is realized.