1024 results about "Hybrid model" patented technology

The invention provides a health state monitoring and service life prediction method and system for an energy storage battery pack, relates to the field of energy storage batteries, and solves the problems that prediction models in the prior art mostly adopt a single machine learning algorithm and lack adaptability to a battery degradation mechanism and actual working conditions, and the prediction efficiency is poor. And the battery health state evaluation and residual life prediction precision is low. The method comprises the following steps: preprocessing an original data set, analyzing a multi-dimensional health feature vector, and constructing a health feature matrix; constructing a health state evaluation model based on the improved CNN-LSTM hybrid model and by fusing battery degradation physical mechanism constraints; inputting the health feature matrix into a health state evaluation model, and outputting a current SOH value; and predicting residual life information based on the current SOH value and the load fluctuation correction coefficient. The method is used in the process of health state evaluation and residual life prediction of the energy storage battery pack.

The invention discloses a power transmission line fault diagnosis and operation and maintenance scheduling method and system based on networking learning, and relates to the technical field of power transmission line fault diagnosis operation and maintenance scheduling. Related data is extracted to construct a high-risk equipment area and a visual high-risk area thermodynamic diagram, a visual risk grading diagram is constructed in combination with electrical quantity data, and meanwhile, an intelligent recognition storage network and a fault type classification recognition model are constructed in combination with a convolutional neural network-long and short-term memory network hybrid model; the model is optimized through networking learning and an attention mechanism, maintenance teams and resources are autonomously allocated in combination with an operation and maintenance management system, then autonomous optimization and closed-loop operation are achieved, full-process coverage of fault sensing, intelligent decision making and efficient response is achieved, the response time after a line fault occurs is remarkably shortened, and the maintenance efficiency is improved. And the fault handling and operation maintenance capabilities of the power grid system are comprehensively enhanced.

The invention provides a battery health state dynamic evaluation method based on multi-modal feature fusion, and relates to the technical field of battery health state dynamic evaluation. The method comprises the steps of collecting multi-modal operation data of a battery, constructing a standardized cross-scale data set, performing hierarchical feature extraction, obtaining a multi-dimensional feature vector, generating a dynamic fusion feature matrix, constructing an SOH dynamic prediction model based on the fusion feature matrix, outputting an SOH prediction value, and establishing a dynamic threshold early warning mechanism based on digital twinning. And the attenuation source is backtracked and analyzed. According to the method, full-dimensional monitoring is realized by introducing microscopic data, and the data quality is guaranteed through cross-scale preprocessing; the feature expression and fusion precision is improved by means of a hybrid model and an AMKAF algorithm; data precision and physical rationality are both considered by using a hybrid prediction model; the threshold value is dynamically adjusted and traced through digital twinborn early warning, accurate evaluation of the whole life cycle of the SOH is achieved, safety is guaranteed, the service life is prolonged, and the operation and maintenance cost is reduced.

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 reservoir real-time scheduling simulation system based on a deep learning algorithm, and belongs to the technical field of intelligent water conservancy and artificial intelligence. Aiming at the problems of low prediction precision, poor multi-target coordination capability, weak coping uncertainty and the like of a traditional scheduling system, the system is designed to acquire hydrological, meteorological, water quality and engineering safety data through a multi-source data acquisition unit, and a multi-dimensional feature tensor is generated after preprocessing and fusion; the dispatching center server adopts an STGCN-LSTM mixed model to achieve high-precision prediction and uncertainty quantification of the water inflow process in the future 7-30 days, a reservoir hydrodynamic model and an MO-PPO algorithm are combined to complete multi-scene simulation and multi-target optimization decision, and an AF-DT mechanism dynamically adjusts the dispatching rule priority. According to the system, a sensing-decision-execution-feedback closed loop is constructed, the scheduling adaptive capacity and robustness are improved, the synergistic interaction of flood control, water supply, power generation and ecological protection is realized, and the system is suitable for real-time intelligent scheduling of large and medium reservoirs.

The invention belongs to the technical field of tunnel and underground engineering intelligent construction and geotechnical engineering informatization, and discloses a high-energy geological environment surrounding rock classification and decision-making method based on digital twinning and multi-source feedback. The problems caused by difficulty in realizing surrounding rock state dynamic sensing, multi-source data fusion classification and construction decision closed-loop linkage in the prior art in a high-energy geological environment are solved. The method comprises the following steps: firstly, constructing a tunnel three-dimensional geology-structure digital twinborn body based on initial survey data; in the construction process, multi-source data such as geology, construction disturbance and surrounding rock response are collected in real time through the Internet of Things technology and mapped to the digital twinborn body, and virtual-real synchronous updating is achieved. And then, constructing a deep learning-parameter inversion hybrid model on the basis of the multi-source fusion data, outputting a dynamic surrounding rock classification index DRCI and key mechanical parameters, inputting the DRCI and the key mechanical parameters into a multi-objective optimization module, and giving a self-adaptive drilling and blasting scheme. And finally, reversely correcting the model through a construction feedback result to realize closed-loop self-learning.

The invention discloses an abnormal traffic detection method and system based on deep learning and a generative adversarial network, and relates to the technical field of network security and artificial intelligence. In order to solve the core problems of scarcity of annotated data, unbalanced categories, difficulty in feature extraction and the like in abnormal traffic detection, the invention aims to construct a self-supervision-generation-attention three-layer collaborative detection architecture: general features are extracted from unannotated traffic through a self-supervision feature representation learning module, and the problem of annotation dependence is solved; a VAE-GAN generation enhancement module is used for generating high-quality samples for minority class abnormal traffic, and class balance is achieved; packet-level, flow-level and session-level multi-modal features are dynamically fused based on a multi-head attention mechanism, accurate detection is carried out in combination with a Transform-CNN-LSTM hybrid model, and interpretable analysis is provided. The method is characterized in that end-to-end high-precision abnormal flow detection is realized systematically through organic cooperation of data acquisition and preprocessing, self-supervised learning, generation enhancement, attention detection and a result output module.

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 relates to the technical field of text verification, in particular to an intelligent text verification method based on a hybrid model knowledge graph, which comprises the following steps of: analyzing a document, separating a text from a visual object, and generating semantics and visual vectors by using a bidirectional encoder and a hybrid visual model; performing form normalization verification by constructing a self-adaptive template matrix; judging the semantic homology of the image-text content by using a cross-modal gating arbiter; the text is converted into a semantic fact triple mapped to a unified space-time coordinate system, and logic irregularity is detected in a domain knowledge graph based on ontology constraint; and finally, summarizing all results to generate a structured verification report. According to the method, cross-modal semantic understanding and knowledge graph reasoning are effectively fused, full-dimension intelligent verification of content forms, image-text semantics and deep space-time causal logic is achieved, and the depth and accuracy of large-scale digital content verification are remarkably improved.

The invention discloses a deep learning prospecting prediction method and system for multi-modal geological data, and relates to the technical field of mineral resource exploration and prediction. The method comprises the following steps: acquiring multi-modal geological data, and preprocessing the multi-modal geological data to obtain preprocessed geological sensing data; constructing a prospecting prediction model based on a hybrid model architecture; the hybrid model architecture comprises a CNN branch, an RNN branch and a GNN branch, and each branch is connected with the full connection layer through splicing operation; inputting the multi-modal geological data into a trained prospecting prediction model for processing to obtain a mineralization potential prediction result; the mineralization potential prediction result comprises a mineralization type, an ore body scale and an ore body grade; and based on the mineralization potential prediction result, constructing a three-dimensional mineralization potential model of the target area by using a depth generation model for visual display. According to the invention, the precision and generalization ability of prospecting prediction can be improved.

The invention relates to the technical field of robot control, and discloses an industrial robot adaptive control method and system based on multi-modal sensor fusion, and the method comprises the steps: collecting multi-modal original data, and carrying out the time-space alignment; capturing space-time semantic association of visual textures, tactile pressure distribution and force sense fluctuation in the multi-modal data through a multi-head attention mechanism guided by a physical model, and performing space-time registration; a CNN-LSTM hybrid model is adopted to extract visual texture features and time sequence tactile features in the physical information enhanced multi-modal feature matrix; and carrying out dynamic weight distribution on the fusion feature vectors with physical consistency by utilizing a weight distribution model driven by element reinforcement learning to generate dynamic weighted fusion features. According to the method, the spatial positioning precision of the industrial robot in a precise assembly scene is greatly improved, the contact force control stability is greatly improved, and the control robustness in a complex operation scene is remarkably enhanced.

The invention discloses a power system data access management and control system based on risk dynamic assessment, and particularly relates to the technical field of power system information security and access control. Comprising an access request interception module, a multi-dimensional risk data acquisition module, a dynamic risk assessment engine module, a self-adaptive access control decision module and a security audit and learning module. Multi-dimensional dynamic context information such as an access subject, an object, an environment and a behavior sequence is collected in real time, a rule engine and machine learning hybrid model is combined to carry out real-time risk calculation, a quantitative comprehensive risk value is output, and an access control decision is dynamically generated according to a risk level threshold. The system has self-learning and self-adaptive optimization capabilities, continuously optimizes the model through an audit log, improves the security and flexibility of data access of the power system, and balances service availability and security protection requirements.

The invention discloses a command and control system resource trend prediction method based on fusion of long and short time sequence characteristics. The method comprises the following steps: acquiring a public power load or similar time sequence monitoring data set, and preprocessing the data in the data set; a deep learning network model based on a TCN-Transformer hybrid model is constructed, a TCN model and a Transformer model are adopted for parallel computing to achieve feature extraction, the TCN model extracts short-term information, the Transformer model extracts long-term features, then fusion features are obtained through a cross attention mechanism and multi-layer perceptron (MLP) weighting, and finally prediction output is generated through full connection layer mapping. Taking data in the training set as input, training the constructed TCN-Transform hybrid model, and continuously optimizing the model until convergence meets a set requirement; and performing prediction by using the trained network model. According to the method, the TCN-Transform hybrid model is constructed, so that local fine-grained features are reserved, the global time trend is effectively captured, and the accuracy of command decision making is improved.

The invention discloses a self-adaptive dynamic control method and system for the machining process of a numerical control machine tool, and relates to the field of intelligent control, and the method comprises the steps: collecting machining data in real time through physical and virtual sensors, and constructing a standardized data set after layering preprocessing; a CNN-LSTM hybrid model is utilized to extract spatial-temporal characteristics to realize working condition classification, and an NSGA-II algorithm is combined to solve a multi-objective optimization problem to generate an optimal control parameter solution set; parameters are dynamically adjusted through fuzzy PID, and a GRU model is adopted to predict machining errors for feed-forward compensation, so that closed-loop control of perception-decision-execution-feedback is formed. The system continuously monitors the actual machining deviation, parameters are optimized again when the actual machining deviation exceeds a threshold value, and cooperative improvement of machining precision and efficiency is achieved. The method has the advantages that NSGA-II multi-target optimization, fuzzy PID correction and GRU error prediction compensation are recognized through CNN-LSTM working conditions, closed-loop feedback iteration is combined, the machining precision and efficiency are improved in a balanced mode, the service life of a tool is prolonged, and the method is suitable for complex working conditions.

The invention relates to the technical field of meteorological disaster early warning and emergency management, and discloses a meteorological disaster risk assessment and prevention method based on artificial intelligence, and the method comprises the steps: obtaining multi-source heterogeneous data, carrying out the cleaning, alignment and standardization processing of the multi-source heterogeneous data, and constructing a multi-dimensional feature data set; based on the multi-dimensional feature data set, outputting predicted meteorological elements of the target area in a future preset time period through a meteorological prediction model, extracting interaction features of the predicted meteorological elements and non-meteorological factors from the multi-dimensional feature data set, and inputting the predicted meteorological elements and the interaction features into a long and short term memory-convolutional neural network hybrid model to obtain a long and short term memory-convolutional neural network hybrid model; outputting the meteorological disaster risk probability and risk level of each grid unit in the target area; based on the meteorological disaster risk probability and the risk level, differential prevention instructions for different risk level areas are generated, and the technical problems that in an existing meteorological disaster risk assessment and prevention method, multi-source data integration is difficult, and meteorological prediction precision is insufficient are solved.

The invention relates to the technical field of computers, discloses a product full-process quality monitoring method and system based on big data, and aims to solve the problem of insufficient quality management refinement caused by data islands, monitoring lag, tracing difficulty and single analysis dimension in the prior art. The method comprises the following steps: constructing a full-process data acquisition system covering design, materials, production, logistics and after-sale, integrating multi-source heterogeneous data, and performing cleaning and time alignment; using an LSTM and GRU mixed model to extract time sequence features of the process parameters, and generating a high-dimensional process feature vector; and constructing a material-process-quality association knowledge graph in combination with the graph attention network, and representing the internal association of the quality influence factors of each link. According to the scheme, full-process data fusion, active quality prediction, accurate traceability and intelligent optimization are realized, and the real-time performance, the accuracy and the self-adaptive capability of quality control are remarkably improved.

The invention discloses a production line data integration method based on a digital twin model, and belongs to the technical field of electronic data processing. The production line data integration method comprises the following steps: step S0, pre-preparation and standard definition; the method comprises the following steps: S1, data acquisition and preprocessing; step S2, data cleaning and integration; s3, data analysis and mining; 4, constructing a digital twinborn model; and 5, managing system-level data. The method has the following advantages: data islands are cracked, data quality and processing efficiency are improved, internal business logic of data is mined, high-precision feature extraction and pattern recognition are realized, and the method is suitable for popularization and application by means of unifying data standards and cleaning rules, optimizing a merge sorting strategy, building a double-layer association analysis model, adopting a CNN-LSTM hybrid model, perfecting data security and authority management and the like. The method supports the cross-line collaborative decision and precise production optimization, finally solves the problem that the prior art cannot support the system-level digital twinning application, and improves the application efficiency and effect of the digital twinning system.

The invention belongs to the technical field of network security, and provides a network threat real-time detection and defense method and system based on artificial intelligence. The method comprises the steps of multi-modal data acquisition and preprocessing, dynamic graph feature engineering and knowledge graph collaborative fusion, dual-adaptive model training and optimization, streaming real-time detection and anomaly scoring, DRL-driven hierarchical defense response and automatic disposal, and feedback-driven model adaptive updating and block chain auditing. According to the method, a mixed model of OS-ELM + dual-adaptive ridge regression + federated learning is designed, the training speed is higher than that of CNN, and over-fitting / under-fitting is avoided by dynamically adjusting a regularization coefficient; the federal learning realizes data local training and parameter uploading, and solves the problem of privacy disclosure; knowledge distillation enables the model volume to be reduced, edge equipment deployment is adapted while the accuracy is maintained, and the generalization ability is obviously superior to that of a traditional static model.

The invention provides an intelligent gas meter remote meter reading method and system based on the Internet of Things, and relates to the technical field of intelligent gas meters. The method comprises the following steps: collecting local metering data and Internet of Things transmission data; constructing a dual-source data multi-dimensional conflict identification system, and screening conflict data groups; performing accuracy verification on the conflict data group; an encrypted transmission channel is established, and the traceability of the data transmission process is realized; triggering a grading early warning mechanism for the abnormal usage data deviating from the baseline; and carrying out iterative updating on the meter reading data knowledge base, and carrying out remote calibration. According to the method, double-source data conflicts are identified through multiple dimensions, conflict data are corrected in combination with a hybrid model, metering accuracy is guaranteed, and disputes are reduced; through constructing a baseline model and a grading early warning mechanism, abnormal usage is accurately identified and disposed, hidden dangers are timely prevented, and service is excellent. Through dynamic on-demand remote calibration of equipment, the metering precision is guaranteed, the operation and maintenance cost is reduced, the user data transparency is improved, and intelligent gas management is assisted.

The invention belongs to the technical field of carbonate rock oil-gas exploration, and particularly discloses a complex carbonate rock logging lithology identification method based on a diffusion model, and the method comprises the following steps: determining the lithology types of a plurality of observation wells based on the on-site rock core observation and slice analysis, and synchronously obtaining the logging data of the corresponding observation wells, constructing a lithology training data set in combination with a depth corresponding relationship between the lithology category and the logging data; a diffusion model is adopted to generate and supplement lithology categories with insufficient samples; logging data is adopted as an input feature, the lithology category is adopted as an output label, and a convolutional neural network fused with a Bayesian optimization algorithm and a Transformer hybrid model are utilized to train a lithology identification model; and inputting to-be-identified logging data into the trained lithology identification model, and outputting a lithology identification result. According to the method, high-precision lithology identification can be realized under the conditions of deep layers and complex stratums.

The invention relates to the technical field of lithium battery state monitoring, and discloses a lithium battery health state prediction method based on multi-feature fusion. Comprising the following steps: S1, a data acquisition and preprocessing step, S2, a multi-dimensional health feature extraction step, S3, a multi-feature fusion and optimization step, S4, a health state prediction model construction and training step, S5, a health state prediction step, and S6, a residual life prediction step. A health factor system for comprehensively describing a battery multi-mode recession mechanism is constructed by fusing a time domain, a transform domain and health association features, the inherent defect that single feature representation is not comprehensive is overcome through the multi-source information complementation mechanism, tiny attenuation of battery performance can be more accurately captured, and the accuracy of the battery performance is improved. And a reliable data basis is provided for realizing accurate management of the battery by combining the strong modeling capability of the TCN-Reformer hybrid model on the local and global dependency relationship of the time sequence data.

The invention provides a sewage treatment aeration control method and system based on a deviation compensation hybrid model, and relates to the technical field of intelligent optimization control of a sewage treatment process, a mechanism model driving layer in the hybrid model outputs a benchmark predicted value of effluent quality, and a process deviation compensation layer performs uncertain quantitative estimation on the benchmark predicted value, so that an aeration control result is obtained. Performing process deviation compensation on the reference predicted value; establishing an aeration optimization objective function by taking the minimum aeration rate as an optimization objective, solving to obtain the optimal aeration rate, outputting a control signal to an air blower according to the optimal aeration rate so as to adjust the rotating speed of the air blower or the opening degree of a valve, change the air supply rate to a reaction tank, and simultaneously, collecting inlet water quality data and operation parameters of an aeration system in real time; and updating the optimal aeration rate, and updating the control signal to form a feedback closed loop. Highly intelligent, stable, reliable, energy-saving and efficient aeration control can be realized, and the sewage treatment plant is ensured to stably realize that the effluent quality reaches the standard and the energy consumption is reduced to the greatest extent under complex working conditions.

The invention provides a hybrid model fault early warning method and system based on time sequence prediction and fuzzy logic, and the method comprises the steps: collecting operation and maintenance data of equipment in a continuous operation period, constructing an equipment state feature set, carrying out the feature correlation analysis of the equipment state feature set, generating an equipment state potential vector which reflects a dynamic coupling relation between parameters, and carrying out the fault early warning of a hybrid model. Calling a pre-trained fuzzy logic reasoning model to carry out fuzzy rule matching, and generating a fuzzy state set containing a multi-dimensional fuzzy subset; performing space-time correlation processing on the fuzzy state set to generate a multi-dimensional decision cloud picture, and performing spatial reconstruction on the multi-dimensional decision cloud picture through a quantization weight distribution mechanism to obtain an optimized decision matrix; and generating a fault early warning signal containing a fault early warning level and fault position positioning information based on the confidence distribution characteristics corresponding to the fault types. According to the invention, the accuracy and timeliness of fault early warning can be improved, and reliable decision support is provided for equipment operation and maintenance management.

The invention discloses a bridge safety early warning method and system, and the method comprises the steps: collecting bridge structure response and environment parameter data, and carrying out the preprocessing of the data, and obtaining a distributed multi-source sensing information matrix; constructing a distributed neuron cell automaton network, interacting state information through unit local communication, operating a lightweight feature extraction algorithm, and generating a multi-dimensional feature vector; carrying out distributed modeling by utilizing a pre-trained distributed LSTM-Transform hybrid model, and carrying out parallel calculation on a local prediction result by each unit to obtain a global health state evaluation result; a local gradient change anomaly detection mechanism is established, data anomaly is identified by comparing prediction results of adjacent units, and a potential risk area is positioned by combining a related algorithm; and constructing a hierarchical early warning threshold system, activating a corresponding early warning response by means of local decision logic, executing an alarm operation, generating recovery guidance information and monitoring uploaded data. According to the invention, two types of network models are combined, so that the system reliability and early warning accuracy can be remarkably improved.

The invention provides a rice irrigation online learning forecasting method and system, the method is realized according to a pre-constructed physical mechanism-neural network hybrid model based on physical mechanism model prediction and neural network error correction fusion, and the method comprises the following steps: S1, obtaining real-time environment data of a current decision period of a target rice field; s2, on the basis of the real-time environment data of the current decision period, forecasting a paddy field water layer depth predicted value of the next decision period through a physical mechanism-neural network hybrid model, and generating an irrigation drainage forecast in combination with a crop irrigation drainage mode; s3, real-time environment data of the target rice field in the next decision period after irrigation drainage forecast is executed are obtained, training samples are constructed and put into an experience playback pool, and the physical mechanism-neural network hybrid model executes online learning based on the experience playback pool; and S4, when the next decision cycle starts, returning to S2 until a preset stop condition is met.

The invention discloses an insulation fault edge self-healing method and device for a power conversion system, and belongs to the technical field of fault diagnosis and automatic maintenance of power electronic equipment, and the method comprises the steps: obtaining multi-modal sensing data, synchronously collected by a multi-modal sensor array, of the power conversion system; a preset lightweight CNN-Transform hybrid model is used to process the multi-modal sensing data, and a feature vector of each modal is obtained; fusing each modal feature vector by adopting a dynamic weight attention mechanism to obtain a fused fault feature vector; classifying the fused fault feature vectors based on a fault classifier, and determining a fault level; and according to the determined fault level, sending a corresponding control instruction to an execution mechanism, and triggering a hierarchical self-healing action. According to the invention, fault identification and self-healing decision can be rapidly completed, and the accuracy of fault detection is effectively improved.

The invention discloses an NAND block health degree prediction method and system based on read interference perception. The method comprises the steps that read interference event counts of an NAND flash memory block are collected in real time; dynamically triggering multi-dimensional parameter acquisition to generate multi-dimensional parameter data with timestamps; extracting a dynamic change rate, a distribution entropy value and a growth slope feature based on the multi-dimensional parameters, and generating a compression feature matrix; inputting the compressed feature matrix into a pre-trained graph neural network-Hamiltonian Monte Carlo hybrid model, outputting a health degree score and recording a low-confidence sample; based on the health degree score and the historical health degree attenuation trajectory, generating an early warning level signal through a dynamic threshold engine; executing a corresponding block maintenance strategy according to the early warning level, and recording strategy execution effect data; and model parameters are updated through knowledge distillation by utilizing a low-confidence sample and strategy execution effect data, so that level-by-level and cross-level health risks of the NAND flash memory based on read interference perception are truly and accurately reflected.

The invention provides a battery power state prediction method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the data preprocessing of the working condition data of a battery, and determining the processed working condition data; constructing a battery model based on the microscopic electrochemical process, the mesoscopic equivalent circuit characteristic, the macroscopic thermal behavior and the processed working condition data; key parameters of the battery model are identified and updated based on a hierarchical online updating mechanism, so that the battery model determines internal state parameters of the battery; determining a dynamic security boundary in real time based on the internal state parameters; and by taking the dynamic safety boundary as a constraint condition, optimizing and solving the real-time available charging and discharging power of the battery through a predictive control algorithm. By constructing a multi-scale hybrid model, the precision and robustness of battery power state prediction are improved; and a hierarchical online parameter identification mechanism is adopted, so that the dynamic adaptive capacity of the model to battery aging and environment change is enhanced, and the prediction performance is ensured not to be degraded along with the use time.

The invention relates to the cross technical field of AI multi-modal analysis and dialect processing, in particular to a dialect content crawling and auditing system and method based on AI analysis, a simulation terminal generates a real person behavior entropy interval event stream through a Markov chain and reinforcement learning hybrid model, a dialect exclusive operation library and a differentiated interest strategy are integrated, and a real person behavior entropy interval event stream is generated through a real person behavior entropy interval event stream; anti-crawling is avoided in combination with a proxy IP pool and a Bezier curve trajectory, a search unit realizes directional crawling of dialect keywords through a hot updateable script, a blind patrol mode locates high-risk content depending on a triple knowledge graph and risk prediction, whole-course block chain evidence storage is performed, and a collaborative analysis unit analyzes dialect audio and video features in a layered architecture. The multi-modal large model is combined with the professional small model, the audio spectrum, the text translation and the video picture are fused to realize cross-modal violation detection, the application service unit alarms violation content in real time, a supervision report containing a violation distribution thermodynamic diagram is generated, and the accuracy and traceability of dialect violation content crawling and auditing are improved.

The invention discloses a fault prediction method and system for a transformer, and belongs to the technical field of transformer state monitoring and fault prediction. The technical problems that an existing transformer fault prediction method is low in accuracy due to single data modality, insufficient in model generalization ability due to scarcity of real fault data, lack of an adaptive mechanism and the like are solved. According to the technical principle, gas concentration, vibration spectrum, temperature, sound and thermal imaging data are collected through a multi-mode sensor array deployed on a transformer site; a multi-head attention mechanism is adopted in the edge calculation unit to realize multi-source data fusion, and fault prediction is carried out through an LSTM-Attention hybrid model; multi-node model parameters are aggregated through federal learning at the cloud, and model adaptive optimization is realized in combination with reinforcement learning. According to the system, the prediction accuracy is improved, the delay is reduced, training data is expanded by five times through the generative adversarial network, distributed deployment and privacy protection are supported, and an efficient transformer state early warning solution is provided for an intelligent power grid.