4537 results about "Model prediction" patented technology

The invention relates to an intelligent power distribution harmonic monitoring and dynamic compensation system which comprises a monitoring unit, a correction unit and a compensation unit. The monitoring unit continuously collects high-frequency harmonic voltage and current data in a distribution line at a high sampling frequency, extracts transient harmonic components through wavelet packet transformation and empirical mode decomposition, and generates low-dimensional feature vectors based on sparse representation. And the correction unit decodes the low-dimensional feature vector, recovers harmonic time-frequency features, calculates a phase drift rate, predicts a harmonic propagation path and an accumulation node by combining real-time power distribution network topology construction and adopting a nonlinear dynamic prediction model, and generates a correction instruction when abnormality is detected. And the compensation unit adopts pulse sequence density modulation to dynamically adjust a compensation current phase according to the correction instruction, and meanwhile, an inductive coupling device is utilized to transfer harmonic energy to a low-risk node, so that harmonic voltage distortion of a target node is quickly recovered to a stable level in a fundamental wave period after early warning.

The invention discloses a multi-agent-based gas insulated switchgear fault diagnosis method and system, and relates to the technical field of intelligent operation and maintenance of power equipment, and the method comprises the steps: obtaining signal data of target equipment, carrying out the feature extraction of the signal data, and constructing a multi-modal feature matrix; time delay features of acoustic and electromagnetic signals are extracted from the multi-modal feature matrix, a GIS propagation model is established, and the space coordinate position of a liberated power source is solved through a wave field inversion algorithm; combining the space coordinate position and the multi-modal feature matrix into a complete fusion feature vector, inputting the fusion feature vector into a dynamic Bayesian model, and outputting a fault type label and a corresponding confidence coefficient; migrating the dynamic Bayesian model based on a migration learning mechanism, and dynamically updating a classification threshold value; inputting the diagnosis history sequence into a time sequence prediction model, and predicting a future operation state; through multi-modal fusion and intelligent reasoning, GIS fault accurate positioning and prediction are realized, and the problems of low precision and poor adaptability of traditional diagnosis are solved.

The invention provides a dam intelligent early warning method and system based on a depth time sequence attention network, and the method comprises the steps: carrying out the time alignment and sliding window segmentation of environment variables and historical displacement data of dam monitoring, extracting multi-scale statistical features, fusing the multi-scale statistical features with original features, carrying out the unified normalization processing of a spliced high-dimensional vector, and carrying out the calculation of the unified normalization processing; model input is generated; based on the constructed DSA-Net, carrying out local feature extraction, bidirectional time sequence modeling and key moment weighting on an input sequence, and jointly outputting horizontal and vertical displacement predicted values; fusing double deformation prediction results into a unified radial deformation index, and dynamically setting an early warning threshold value band according to a historical residual error to realize self-adaptive deformation early warning; quantitative evaluation is carried out on the model prediction precision, online prediction and threshold determination of real-time observation data are realized by using the qualified model and an adaptive threshold mechanism, abnormal early warning is triggered, and alarm information is recorded. According to the invention, deep coupling of deformation dimensions and dynamic threshold early warning are realized.

The invention belongs to the technical field of power system load prediction, and discloses a cross-dimension multi-scale fusion load prediction method based on multi-user load time-space correlation, which comprises the following steps of: firstly, preprocessing user load statistical data, extracting time sequence dependence and periodic characteristics in a time sequence, and calculating the time sequence dependence and periodic characteristics of the user load statistical data; introducing a channel attention mechanism to adaptively mine key variable information; then, a multi-scale space-time fusion module is combined with frequency domain analysis and a graph convolutional network to realize depth feature interaction under different time scales and space levels; and finally, outputting a load prediction result under a plurality of time granularities in the future through a linear projection structure. Compared with an existing method, the method has the remarkable advantages in the aspects of capturing a complex load mode, improving model prediction precision and enhancing generalization ability, and is suitable for various application scenes such as power consumer energy consumption management and power grid load dispatching.

The invention discloses an intelligent management system and method applied to a radio frequency energy output device, and belongs to the technical field of intelligent management of the radio frequency energy output device.An integrated sensor array is deployed on a radio frequency host and a hand tool electrode, and load voltage, output current, electrode temperature and tissue impedance are synchronously collected; a dynamic thermal impedance collaborative analysis model is constructed after time synchronization alignment, a three-dimensional thermal field simulation map is generated, and a thermal accumulation trend is predicted; a double-layer control framework is constructed, a first control layer generates a dynamic power adjustment rule base based on a preset treatment target and a safety threshold value and outputs an instruction, a second control layer receives the instruction and adjusts output parameters in real time, and a strategy is adjusted by combining a model prediction result in the execution process; meanwhile, the operation state is continuously monitored, a fault classification model is constructed for anomaly detection, a fault source is positioned, and a visual report is generated; and finally, constructing a mapping relation based on historical data, and generating an energy control scheme adapted to individualized requirements through iterative optimization.

The present invention relates to the technical field of dynamic carbon sink accounting, and specifically relates to a dynamic carbon sink accounting system based on multi-modal AI remote sensing monitoring and blockchain-based evidence storage. The system collects optical remote sensing, radar, photosynthetically active radiation and meteorological data, performs unified spatiotemporal calibration on the data, and then fuses the calibrated data by means of a cross-modal attention mechanism, so as to generate multi-modal feature vectors, and inputs same into a TCN model for carbon stock and trend prediction. A prediction result and metadata are uploaded to a blockchain by means of smart contracts, so as to generate a carbon sink NFT including a geographic fence and a confidence level, thereby realizing trusted evidence storage. A residual mapping function is established in view of on-chain historical data, so as to dynamically optimize the model, and improve the accounting accuracy. The system improves the fusion capability and prediction accuracy, and enhances the credibility and transparency of carbon asset management and transactions.

The invention relates to the technical field of artificial intelligence, can be applied to business scenes such as financial science and technology and medical health, and discloses a processing environment switching and recovery method, device, equipment and medium. The method comprises the steps that multi-source heterogeneous data in a main processing environment and a standby processing environment are acquired, and the system fault probability is obtained through multi-model collaborative prediction; a dynamic threshold value is generated in combination with a historical service period mode and a real-time service load, when the fault probability exceeds the threshold value, a switching strategy is generated based on the fault scene knowledge base and the service priority, and flow scheduling between the main processing environment and the standby processing environment is executed; and monitoring the business index of the standby processing environment during the scheduling period, and triggering the fusing rollback when the business index is lower than the health standard. According to the method, the fault identification precision is improved through multi-source data fusion and multi-model prediction, adaptive scheduling is realized in combination with a dynamic threshold and a switching strategy, and fusing rollback is triggered to guarantee high availability and data consistency, so that the continuity and stability of key services are enhanced.

The invention provides a tunnel excavation ground surface settlement prediction method and system based on a machine learning hybrid model, and relates to the technical field of tunnel engineering and machine learning crossing, and the method comprises the steps: obtaining the multi-source heterogeneous information of a target tunnel, and constructing a ground surface settlement data set; a Transform-BiLSTM hybrid model is constructed, the robustness of the algorithm in a noise environment is enhanced based on a VMD (variational mode decomposition) algorithm, hyper-parameters are adaptively adjusted and optimized by using a PSO (particle swarm optimization) algorithm based on a ground surface settlement data set, the model prediction precision is maximized, and a ground surface settlement prediction model is obtained; and analyzing decision logic of the ground surface settlement prediction model through the SHAP value, and outputting interpretable engineering guidance suggestions. By constructing a machine learning hybrid model, high-precision and real-time prediction of ground surface settlement in the whole process of tunnel excavation is realized. The precision and generalization ability of the model are improved, the characterization ability of complex spatial-temporal characteristics is enhanced, and overfitting is avoided; and the interpretability is optimized, and the influence of key parameters on a prediction result is quantified, so that construction parameter adjustment is guided.

The invention provides a wind power prediction method and system based on time sequence decomposition and multi-model fusion, and the method comprises the steps: collecting the historical power generation power and meteorological data of a target wind power plant; decomposing the historical power generation power and the meteorological data to obtain a trend component, a seasonal component and a residual component; fusing with meteorological data to construct a trend feature matrix, a periodic feature matrix and a residual feature matrix; different modeling schemes are adopted to construct corresponding single models; dividing into a training set, a verification set and a test set according to a time sequence; performing training optimization on the single model by using the training set, the verification set and the test set, and constructing a wind power short-term power prediction model; and inputting the real-time meteorological data and the generated power to the wind power short-term power prediction model, and outputting the generated power prediction value of the target wind power plant, thereby effectively improving the comprehensiveness, accuracy and stability of model prediction.

The invention relates to a model predictive control charging optimization method based on a dynamic power state, which initiates a'dynamic power state collaborative optimization 'mechanism, takes a real-time power upper limit as an active optimization target instead of a fixed constraint condition, and breaks through the technical bottleneck of power limitation passive response in a traditional charging strategy. The method specifically comprises the following steps: constructing an electric-thermal-aging multi-physics field coupling model of the lithium ion battery, updating electric-thermal characteristic parameters in real time through an online parameter identification algorithm, and synchronously estimating a core temperature and an aging state in combination with a double-Kalman filtering state observer; innovatively establishing a four-dimensional objective function optimization model containing a dynamic power state, and performing multi-objective collaborative optimization on a power upper limit, a charging speed, a capacity fading rate and a current fluctuation rate; and designing a dynamic rolling optimization algorithm based on a model prediction control framework, and solving the optimal charging current meeting the dynamic power distribution requirement of the power grid in real time under the hard constraint of ensuring the maximum core temperature and terminal voltage.

The invention discloses a geotechnical engineering intelligent investigation system and method based on big data. The system comprises a field sensing module, a multi-source fusion module, an intelligent analysis module, a modeling early warning module and a report generation module. The field sensing module collects drilling parameters, in-situ test data and geological images in real time; the multi-source fusion module receives an original investigation signal and accesses a historical engineering investigation database and a regional geology database; the intelligent analysis module receives the fused data signal, constructs a knowledge graph containing a rock-soil entity relationship, predicts rock-soil parameters and stratum distribution of an unexplored area based on a machine learning model, and generates a parameter prediction signal; the modeling early warning module receives the parameter prediction signal; and the report generation module receives the parameter prediction signal and the risk early warning signal. The geotechnical engineering intelligent investigation system and method based on big data can solve the problems of discrete investigation data, strong experience dependence and low intelligent degree.

The invention discloses a water quality time sequence prediction method of an SSA-VMD-LSTM-XGBoost hybrid model, and belongs to the technical field of water quality monitoring and prediction. Comprising the following steps: (1) data preparation and preprocessing; (2) optimizing the water quality time sequence decomposition of the VMD based on SSA: optimizing a penalty factor and a modal number of the VMD by adopting a sparrow search algorithm (SSA), and decomposing the water quality time sequence into a plurality of sub-components with high stability and low complexity by utilizing the optimized VMD; (3) construction and training of an LSTM-XGBoost hybrid prediction model: constructing a hybrid prediction model fusing long-short term memory (LSTM) and extreme gradient boost (XGBoost), inputting a high-frequency component into the LSTM model, inputting a low-frequency component into the XGBoost model, and finally performing superposition and integration on prediction results of the models; and (4) multi-component prediction result integration and performance verification. According to the method, adaptive optimization of VMD parameters is realized through SSA, the feature extraction and time sequence modeling capability is improved by combining the advantages of LSTM and XGBoost, and the prediction precision and stability of the water quality time sequence are effectively improved.

The invention discloses a world model driven decision model training method, system, device and product, and relates to the technical field of artificial intelligence. According to the scheme, the initial world model is generated through the target video data and the diffusion generation model, and the initial world model is finely adjusted by using three different loss functions, namely the diffusion loss function, the dynamic loss function and the structure maintenance loss function based on the third-order motion prior; physical consistency and high-frequency detail fidelity of short-term and long-range prediction are realized; furthermore, a reward function is automatically generated by using the uncertainty of world model prediction, so that the training efficiency is improved; according to target video data and a world model closed-loop training decision model, collaborative optimization of environment cognition and strategy evolution is realized; and finally, the trained world model and the decision model can be integrated to the target server, closed-loop control of perception-decision-motion execution is realized, the method has low delay, high robustness and expansibility, and the safety of the automatic driving system is improved.

The embodiment of the invention provides an energy-saving optimization system for heating, ventilating and air conditioning of an indoor ski field. The energy-saving optimization system comprises a multi-source sensing layer, an edge computing layer, a cloud decision-making layer and an equipment execution layer. The multi-source sensing layer is used for collecting multi-source data such as weather, passenger flow, temperature and humidity and equipment state; the edge calculation layer carries out fusion processing on the data and generates a load prediction result through a load prediction mechanism; the cloud decision-making layer generates an optimization control instruction based on a multi-agent deep reinforcement learning and model prediction control optimization strategy; and the equipment execution layer receives and executes the instruction and feeds back the equipment state. Through a multi-layer collaborative optimization architecture, accurate load prediction and equipment intelligent collaborative control are realized, five-stage stepped optimization and a dynamic priority mechanism are adopted, the energy efficiency of the system is remarkably improved, the energy consumption is reduced while the environmental comfort is ensured, and the economical efficiency and the stability of system operation are effectively improved.

The invention provides a gas ultrasonic transducer fast matching method, device and equipment and a storage medium, original measurement data such as flight time are obtained by deploying an ultrasonic transducer in a gas ultrasonic flowmeter in a gas conveying pipeline, and multi-dimensional data acquisition is carried out in combination with other sensor parameters. Wavelet noise reduction and dynamic time warping processing are carried out on collected signals, signal quality and time sequence consistency are improved, time domain, frequency domain, environment and statistical features are extracted, and multi-dimensional feature vectors are formed. Modeling is carried out through a time sequence feature branch and an environment feature branch, weighted fusion is carried out by adopting an attention mechanism, and the recognition capability of the model on key features is enhanced. A machine learning model is trained based on fusion features, a multi-objective loss function and a data enhancement strategy are adopted, the prediction precision and generalization ability of the model are improved, and a compensation value is output to calibrate the original traffic in real time. According to the method, the accuracy and stability of gas flow measurement in a complex environment are effectively improved, and the method has a good engineering application prospect.

The invention discloses an intelligent thickness control system for calendering a high-brightness edge sealing sheet, and relates to the technical field of intelligent manufacturing and industrial process control. The method sequentially comprises six steps of multi-modal online acquisition, multi-source fusion drift compensation, digital twinning real-time synchronization, model prediction closed-loop control, high-speed execution fault self-diagnosis and reinforcement learning adaptive optimization. Thickness data are synchronously obtained through laser, terahertz, ultrasound and environment quantity, trusted thickness flow is output through a drift model and a confidence matrix, future thickness is predicted through digital twinning rolling to give uncertainty, first-step control quantity is generated through quadratic programming, millisecond-level execution is conducted through a distributed clock, and self-healing is conducted under shadow driving hot standby and cloud diagnosis. And reinforcement learning agent online iteration improves the energy-saving and stable performance, and full-life-cycle closed-loop control with accurate thickness, low energy consumption and long service life of equipment under complex working conditions is realized.

The invention discloses an air valve on-line self-adaptive adjusting method and system fusing digital twinning, and belongs to the field of air valve intelligent adjusting.The adjusting method comprises the following specific steps that firstly, edge devices collect and preprocess multi-source data of a corresponding air valve system, and based on the preprocessed multi-source data, the multi-source data of the corresponding air valve system are obtained; constructing a virtual simulation environment corresponding to the current air valve system; iI, in a virtual simulation environment, pre-training an air valve control model, identifying a causal relationship between each sensing parameter and an air valve adjustment result, and dynamically optimizing each control variable; according to the method, model prediction precision and simulation credibility are remarkably improved, dependence on a large amount of new data is reduced, cross-system rapid adaptive adjustment is realized, misjudgment and interference of confounding factors can be avoided during strategy optimization, interpretability and credibility of model decision are enhanced, data privacy is protected, convergence of a global strategy is accelerated, and the method is suitable for large-scale popularization and application. The overall intelligent level of the system is improved.

The invention discloses a digital twin-driven bridge full life cycle damage prediction and evaluation method and system, and belongs to the field of bridge structure health monitoring, and the method comprises the steps: obtaining a monitoring data set of a bridge structure; an initial digital twinborn model embedded with a micro physical layer is constructed and trained, the micro physical layer constructs a damage evolution model applied with monotonic physical constraint based on multi-source monitoring data, and a damage evolution trajectory of the bridge in a future time period is predicted through the damage evolution model based on the physical parameter vector; in combination with an uncertainty quantification method, generating a time-varying reliability index of the bridge in a future time period; and based on the time-varying reliability index, constructing and solving a maintenance decision optimization model to generate a maintenance decision of the bridge. According to the invention, the physical authenticity and reliability of the long-term prediction result are ensured.

The invention provides a greenhouse environment adaptive regulation and control method and system, and relates to the technical field of environment control, and the method comprises the steps: collecting multi-dimensional environment parameters in a greenhouse; based on the environmental parameters, a preset crop growth period database and weather prediction data, taking minimization of a preset cost function as a target, and adopting a model prediction control algorithm to generate an equipment linkage instruction set in a future preset time period, the preset cost function fusing environmental regulation and control deviation and operation cost; issuing the equipment linkage instruction set to each execution equipment, and executing linkage regulation and control; wherein when the equipment linkage instruction set is generated, a conflict resolution mechanism based on a dynamic priority is adopted to determine an execution sequence of a plurality of equipment instructions; the adaptive regulation and control method integrating multi-source data verification, multi-scale prediction, dynamic priority conflict resolution and multi-target cost optimization improves the accuracy, economy and crop suitability of greenhouse environment regulation and control.

The invention relates to the technical field of electric power intelligent management, and discloses a cooperative scheduling method and system for a virtual power plant, and the method comprises the following steps: S1, collecting the real-time data of each distributed power supply, each load and an energy storage system in the virtual power plant, and carrying out the ultra-short-term prediction, and obtaining a prediction parameter; s2, dynamically calculating the dynamic operation boundary of the energy storage system based on the real-time state of the energy storage system; s3, on the day before the current operation day, generating a pre-scheduling plan through collaborative decision making of a multi-target fuzzy satisfaction function; s4, in the current running day, taking the pre-scheduling plan as a reference, updating boundaries and prediction parameters in a rolling manner, and generating a real-time scheduling instruction through model prediction; and S5, monitoring the deviation between the actual output of each resource and the real-time scheduling instruction in real time, and when the deviation exceeds a threshold value, starting a collaborative deviation compensation mechanism to carry out power balance. According to the invention, fine cooperative scheduling of different types of distributed resources can be realized in a complex environment with high uncertainty.

The invention discloses a maritime accident prediction method and device based on interpretable integrated machine learning, and relates to the technical field of maritime affair safety risk analysis, and the method comprises the steps: obtaining accident investigation data, carrying out the preprocessing, balancing the data through a ten-fold layered oversampling method, and carrying out the cross verification training, and determining a performance optimal model by using the test set and carrying out interpretable analysis to explain the influence of the characteristics on the accident prediction result. By constructing a closed-loop'data processing-model optimization-explanation output 'process and adopting SMOTE oversampling and ten-fold layered cross validation training and a heterogeneous base model ensemble learning strategy, the processing capacity of the data imbalance problem of accident categories is improved, the data leakage problem of oversampling is avoided, and the possible bias of a single model is overcome. The interpretability analysis of the model prediction result can quantitatively display the contribution degree of each feature to prediction globally and locally, reveal the nonlinear relationship and interaction effect between the features, and provide transparent interpretation of model decision.

The invention relates to the technical field of battery management, and discloses a forklift battery charging method and device, and the method comprises the steps: collecting the real-time multi-dimensional physical state data, including vibration data, of a forklift battery; dynamically reconstructing a multi-physical field coupling model matched with the current working condition in a preset model library according to the data; performing predictive multi-target optimization based on the model to determine an optimal charging equalization strategy considering charging time, energy loss, health attenuation and thermal risk; charging is executed according to the strategy, the deviation between physical response and model prediction is compared in real time, and online self-correction is conducted on model parameters. The system comprises a state acquisition module, a model reconstruction module, a strategy optimization module and a charging control and correction module. According to the method, the digital twin model capable of self-evolution is constructed and closed-loop feedback correction is carried out, so that the charging strategy can actively adapt to working condition changes caused by factors such as vibration and temperature, and safer and more efficient charging management of the forklift battery is realized.

The invention discloses a video monitoring abnormal behavior identification method and system based on edge AI, and relates to the technical field of intelligent video analysis, and the method comprises the steps: carrying out the frame segmentation processing of a video monitoring data stream, obtaining a video frame sequence, building a target trajectory prediction model, predicting the position region of a current frame, and generating target position prediction data; performing multi-scale feature extraction on the video frame sequence, performing fusion matching on a target feature vector and target position prediction data, and constructing an enhanced feature matrix; carrying out weight distribution on the key behavior characteristics by adopting an attention mechanism, setting a dynamic threshold adjustment mechanism, and dynamically adjusting an abnormal behavior judgment threshold according to the personnel density; and inputting the adjusted feature data into an abnormal behavior classifier for identification and judgment, outputting an abnormal behavior identification result, and generating an abnormal event report. According to the method, the abnormal behavior detection accuracy in a complex monitoring scene is improved, the false report and missing report rate is reduced, and the millisecond-level real-time response capability is realized.

The invention relates to the technical field of building informatization and intelligent construction, and discloses a building engineering digital twinning progress management and control method and system.The building engineering digital twinning progress management and control method comprises the steps that multi-source heterogeneous data in the building engineering construction process is collected; carrying out fusion processing on the original data set by adopting a space-time alignment network; updating the digital twin body by adopting an incremental state estimation method; predicting a future progress by adopting a model fusing a graph neural network and a time sequence attention mechanism; a multi-level detection mechanism is adopted to identify progress deviation and analyze a root cause; generating an optimized resource scheduling scheme by adopting a reinforcement learning method; an intelligent decision support system is constructed, and visual display and interaction functions are provided; according to the method, the graph neural network and the time sequence attention mechanism are fused, the progress prediction model capable of capturing the task topology dependency relationship and the time sequence evolution characteristics at the same time is constructed, and the accuracy of progress prediction is improved.

The invention provides a water quality index fusion data anomaly detection method, system and device and a medium, and relates to the technical field of water quality detection.Physical, chemical and biological parameters are obtained from a water source station in real time, then on the basis that original data are reserved, cross-parameter correlation features are constructed through multi-modal feature reconstruction, and the water quality index fusion data anomaly detection accuracy is improved. An adaptive sensitivity factor is synchronously calculated, the factor fuses the degree of deviation of parameters from a dynamic baseline and the mutation degree of a multi-parameter coupling relation, then original parameters and associated features are input into a multi-task time sequence prediction model, and the adaptive sensitivity factor guides an attention mechanism to focus abnormal signals preferentially; and synchronously predicting the future evolution trend of the indexes and the relationship change trend among the parameters, and finally realizing anomaly diagnosis through triple criteria: detecting whether original parameters exceed a safety threshold, analyzing model prediction deviation, evaluating the fracture degree of coupling characteristics, dividing pollution levels according to the results, and positioning core anomaly parameters based on attention weights.

The invention belongs to the technical field of computing resource scheduling, and particularly relates to an intelligent scheduling method and system for Huaan Atlas heterogeneous computing resources based on dynamic load awareness. The method comprises the steps that the real-time state of multi-dimensional hardware data is collected, and a basic data source is provided for subsequent steps; dynamically adapting tasks and hardware characteristics through a matching degree matrix, modeling aiming at various basic data, and constructing a state vector required by reinforcement learning; predicting a fault risk score through a lightweight prediction model deployed at each computing node; and a deep Q network is adopted as a model architecture, a state vector and a fault risk score are input, reinforcement learning training is performed through a reward function in a multi-target vector form, a final scheduling model is obtained, and a task allocation decision is output. The problems that in the prior art, the hardware state cannot be sensed in real time, hardware characteristic matching is ignored, consequently, the computing resource utilization rate is insufficient, and fault recovery is passive are solved.

The invention belongs to the technical field of rainfall prediction, and discloses a short and temporary rainfall prediction method based on multi-model random scheduling integration, which develops a robust training and pushing framework based on a continuous rolling prediction strategy, and decomposes long-sequence prediction into manageable stages. According to the method, training is carried out through teacher forcing and planned sampling, error propagation is relieved, and the training process is stabilized. The invention further designs asymmetric encoder-decoders (DSE and AFD) that achieve lower FLOPs than competitive baselines under standardized assessment, where DSE selectively compresses significant features and AFD stepwise reconstructs details to mitigate excessive smoothing problems. Finally, an intensity weighted Gaussian KL divergence loss function is designed, and the key problem of data balance is solved by modeling and predicting on a distribution level and endowing a large weight to a meteorological important heavy rainfall event.

The invention discloses a knowledge cross validation question-answering method and system for reducing hallusion of a large language model, and belongs to the technical field of artificial intelligence, and the method is implemented by the following steps: generating results through multiple times of sampling: when a user puts forward a question, controlling the large model to perform multiple times of sampling, and generating a specified number of results; calculating hidden state related indexes: extracting the hidden state of the last token of the middle layer of the large model corresponding to the result, and calculating covariance matrixes and answer discrete feature values of the hidden states; mLP model prediction: inputting the discrete feature value of the answer and the length of the answer into a multilayer perceptron MLP, and outputting a hallucination-free probability; querying and summarizing a knowledge graph; and calculating a final illusion-free score and outputting a result. According to the method, the answer quality and credibility of a large language model can be remarkably improved, and the method is particularly suitable for application scenes with extremely high requirements on the accuracy of single-mode text generation contents.

The invention discloses a high-precision linear vibration feedback motor system, and relates to the technical field of precise electromagnetic driving, and the system comprises a core driving module which is a moving magnet type linear motor of a Halbach array magnetic circuit structure, and is integrated with a multi-physics field sensing unit; the dynamic parameter tracking module is used for acquiring a reed rigidity coefficient, a damping coefficient and a magnetic constant in real time when the motor runs, and establishing a dynamic displacement model based on a recursive least square method; a double-closed-loop control framework is adopted, an inner loop adopts field-oriented control, and an outer loop is based on model prediction control; the aging prediction unit activates a temperature rise compensation algorithm when the accumulated number of vibration times is greater than a set threshold value; the self-adaptive calibration engine is used for injecting a sweep frequency excitation signal when the system is started, and automatically compensating individual difference parameters according to the harmonic peak offset; and the digital twin mapping unit is used for establishing a real-time mapping relationship between the physical parameters of the motor and the virtual model, and dynamically correcting the model parameters by comparing the actual displacement with the model displacement.

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.