3707 results about "Hyperparameter" patented technology

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 intelligent building energy-saving control, and discloses a green building equipment intelligent energy-saving control method and system based on artificial intelligence, and the method comprises the steps: collecting building environment data, and carrying out the preprocessing; and simulating the energy consumption of the building equipment by using the digital twin model, and training the baseline neural network model to obtain an initial control strategy. And adopting a genetic algorithm to optimize hyper-parameters of the baseline model, and generating a plurality of candidate energy-saving control strategies. And inputting the optimized strategy into the deep reinforcement learning model, carrying out strategy iteration, calculating the energy-saving efficiency and comfort score after each iteration, screening the optimal strategy through a reward mechanism, and improving the accuracy of energy consumption prediction of the building equipment. The hyper-parameter of the neural network is optimized by using the genetic algorithm, and the intelligent degree of the energy-saving control strategy is improved. On the basis of deep reinforcement learning, the intelligent agent can adaptively adjust an energy-saving strategy under different environmental conditions, and the user comfort is guaranteed while the optimal building energy consumption is ensured.

A system is provided for managing Internet of Things (IoT) networks. The system includes a learning module configured to employ machine learning models with hyperparameters optimized through a hyperparameter optimization process; wherein the process includes evaluating a set of hyperparameters against a performance metric to select optimal hyperparameters that enhance the adaptability and efficiency of dynamic membership functions within an adaptive fuzzy logic engine (AFLE).

A method and a system for reconstructing aerosol chemical components based on CNN-BiLSTM-BO, including collecting multi-source environmental observation data through observation equipment, preprocessing and extracting key characteristic variables. The pre-treated multi-source environmental observation data are input into the CNN-BILSTM model for feature analysis, and the CNN-BiLSTM hyperparameters are adjusted by Bayesian optimization algorithm to generate a reconstructed model of aerosol chemical components. After verifying the performance and stability of the reconstructed model, the predicted results of the chemical components of the aerosol are output. On the basis of not relying on traditional chemical analysis technology, the invention can accurately reconstruct various aerosol chemical components, greatly reduce the cost and time of chemical analysis, effectively solve the problems of variable inconsistency, data missing, and spatio-temporal mismatch in multi-source observation data, and automatically adjust hyperparameters through Bayesian optimization algorithm to ensure that the output prediction results are more accurate.

The invention discloses a production scheduling strategy adjustment system and method, and belongs to the technical field of production management, and the method comprises the steps: constructing a multi-source heterogeneous database, setting a semantic association method, generating a demand knowledge graph, setting a prediction and correction method, constructing an order prediction model, generating order quantity fluctuation matrixes with different confidence degrees, and providing quantitative parameters for risk assessment. Constructing a risk assessment basic data set, setting a risk assessment method, dynamically adjusting a risk threshold value to realize adaptive early warning, constructing a risk probability model, and generating a production decision result based on a formulated production decision judgment rule; calculating a factory quantity deviation rate, setting causal analysis, detecting deviation by using a threshold value, triggering an alarm, integrating production data to construct a causal graph, and generating a causal effect report; and calculating a deviation rate of deviation detection, setting a self-optimization method, obtaining an optimal hyper-parameter combination, and optimizing an input feature vector so as to improve the production scheduling prediction accuracy.

The invention discloses an urban inland inundation situation deduction method based on fusion of mechanism knowledge and deep learning, and the method comprises the steps: collecting data, such as weather, terrain and historical disaster situations, and constructing a standardized database in combination with an inland inundation production and convergence mechanism; constructing an urban inland inundation numerical twinborn model, and optimizing hyper-parameters to improve prediction precision by adopting finite element calculation and a multi-scale coupling method based on hydrological and hydrodynamic models; constructing a causal association network by using the numerical twinborn data, and identifying a core affected area; designing a situation deduction algorithm of a space-time diagram neural network, capturing rainfall waterlogging dynamic characteristics, and realizing advanced early warning and accurate deduction; based on the waterlogging intensity and the exposure and vulnerability of the disaster-bearing body, a risk assessment system is constructed, the disaster diffusion trend and the disaster risk are analyzed, and support is provided for flood prevention decision and emergency management.

The invention discloses a high-accuracy threat intelligence assisted network threat tracing method, which comprises the following steps: S1, collecting and preprocessing multi-source network security data, and constructing a time-marked event sequence set; s2, constructing an optimized Transform network model, and processing an attack event sequence by using position coding and time embedding; s3, a black swan optimization algorithm is initialized, and a Transform structure hyper-parameter is dynamically optimized; s4, outputting an attack event semantic vector, and constructing an attack path semantic map; s5, the intelligence information vector is embedded into a Transform hidden space; s6, calculating semantic similarity and dependency intensity, and generating an attack source candidate set and a traceability path; s7, outputting an attack traceability path, a starting point node and an information label, and generating a structured traceability report; and S8, according to the traceability result feedback, updating the black swan algorithm and the Transform model. The method is used for realizing intelligent modeling of multi-source network attack events and high-accuracy traceability analysis of attack source nodes.

The invention discloses an AI model training parameter dynamic optimization system, and relates to the technical field of artificial intelligence model training optimization. According to the scheme, by monitoring gradient norms in real time and fusing a frequency weighting mechanism, dynamic gradient self-adaptive cutting is achieved, the limitation of a fixed threshold value is broken through, and the model precision is guaranteed while the batch scale is expanded by 30%; a weight matrix is innovatively decomposed into a low-rank factor matrix, the internal storage is compressed to O (n + m), a strategy perception distillation technology is synchronously combined, a reward signal is dynamically generated by utilizing comparative learning to replace manual preference labeling, and collaborative optimization of parameter lightweight and knowledge migration is realized; aiming at a heterogeneous equipment environment, designing a computing power perception parameter group automatic division mechanism, and reducing communication redundancy by 40% by adopting asynchronous weighted aggregation; and constructing a data-parameter joint adjustment and optimization closed loop, and integrating a real-time data cleaning framework and a parameter normalization module to dynamically adjust the hyperparameters of the optimizer. According to the system, an efficient solution is provided for edge calculation and large model training by using a full-link adaptive architecture.

The invention discloses an electrical equipment life prediction system and method based on deep learning, and belongs to the field of electrical equipment life prediction, and the method comprises the steps: constructing a data set, and carrying out the preprocessing; performing convolution operation on the time sequence data in the data set, extracting local features to obtain a convolutional neural network, capturing a long and short term dependency relationship of the time sequence data in the data set by using LSTM to obtain a recurrent neural network, and fusing output features of the convolutional neural network and the recurrent neural network to obtain comprehensive feature representation; constructing a deep learning model based on the fusion of a convolutional neural network and a recurrent neural network, adding an attention mechanism, adopting a mean square error as a loss function, optimizing model parameters, carrying out model training by utilizing a training data set, evaluating model performance by adopting a verification set, and adjusting hyper-parameters; and inputting real-time data into the trained model, predicting the residual life of the electrical equipment, and designing an online learning mechanism. According to the invention, the accuracy and real-time performance of prediction are improved.

The invention discloses a typhoon wave forecasting method based on integrated machine learning. The method comprises the following steps: firstly, integrating historical typhoon wave data, meteorological data and marine environment data; preprocessing the data, including integration, cleaning, vacancy filling and standardization, and performing multi-source data completion by adopting a K-nearest neighbor algorithm and a spline interpolation method; secondly, screening key characteristic parameters through a Pearson's correlation coefficient, and reinforcing nonlinear correlation representation in combination with a mutual information method; then, constructing an integrated prediction model containing an LSTM (Long Short Term Memory), an XGBoost (X Goose Boost) and a Transform; and finally, dividing a training set and a verification set by adopting a dynamic time sequence division strategy, optimizing model hyper-parameters, and completing training and testing of the typhoon wave height prediction model. According to the method, the data sparsity problem is solved through multi-source data fusion and feature selection optimization, the generalization ability is improved through an integrated model architecture, and compared with a traditional single model, the training period is remarkably shortened, and the forecasting precision and timeliness are improved.

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

The invention discloses a multi-modal traffic flow prediction method based on a dynamic space-time hypergraph and a large language model, and relates to the field of computer machine learning, and the method comprises the steps: obtaining a traffic data set, aligning the timestamps of text description and sensor data, and dividing a training set, a verification set and a test set; constructing a dynamic space-time hypergraph, and retaining a key space-time dependency relationship; and constructing a traffic flow prediction model, training the model by using the training set, monitoring the training process and adjusting hyper-parameters by using the verification set, and finally evaluating the prediction performance of the model by using the test set. The method is superior to an existing method, and the effectiveness of the method in a complex dynamic traffic environment is proved.

The invention discloses a power plant equipment fault prediction method based on a time sequence large model, and the method comprises the following steps: S1, collecting and preprocessing the time sequence data of a multi-source sensor of a power plant, and generating a standardized time sequence data set; s2, constructing a time sequence large model, inputting standardized data, and outputting a future operation state predicted value; s3, comparing the running state prediction value with an actual measurement value to generate a prediction residual sequence; s4, constructing a Bayesian neural network model, inputting a prediction residual sequence, and outputting error probability distribution; s5, optimizing a Bayesian neural network structure and hyper-parameters by adopting an ant colony optimization algorithm; s6, confidence interval estimation is executed, and whether the state is a high-risk state or not is judged; and S7, outputting a running state label, and dynamically acquiring a data closed-loop updating model. According to the invention, high-precision prediction and uncertainty evaluation of the operation state of the power plant equipment are realized, so that the accuracy and response time efficiency of fault early warning are improved.

The invention discloses a gait sub-phase prediction method and device based on deep learning model fusion. The method comprises the following steps: synchronously collecting multi-source gait data of a wearer walking at various speeds; preprocessing the collected multi-source gait data, dividing a time window by adopting a sliding overlapping window technology, and constructing a supervised learning training data set based on double tags; hierarchically fusing CNN, Bi-LSTM and MHA, and constructing a gait sub-phase prediction model; automatically searching an optimal hyper-parameter combination by using a Bayesian optimization algorithm; a stable prediction time (Pstable) index is defined, and model performance is comprehensively evaluated through one-by-one subject rejection cross validation and a speed migration robustness experiment in combination with a classical index; a modular gait sub-phase prediction system architecture is constructed based on a Simulink platform, and a multi-thread buffer mechanism is integrated to process data streams in real time; and solidifying model parameters to an online reasoning module, and dynamically outputting a prediction result.

The invention discloses a coal rock fracture intelligent extraction method based on improved U-Net. The method comprises the following steps: S1, constructing a coal rock fracture CT image data set; s2, constructing an improved U-Net segmentation model, specifically comprising the following steps: S2.1, taking VGG16 as a backbone network, and introducing a depth separable convolution module; s2.2, a PPA attention module is added after each layer of depth separable convolution of the decoder, the PPA attention module is introduced after each up-sampling stage of the decoder, and the output of the PPA attention module is subjected to batch normalization and Dropout layer processing; s2.3, defining a composite loss function; s3, training and optimizing a segmentation model, wherein the specific steps comprise: S3.1, setting hyper-parameters; and S3.2, training the model by using the training set, adjusting hyper-parameters by using the verification set, and evaluating the performance by using the test set, wherein the evaluation indexes comprise MIoU, MAcc and FWIoU. According to the method, the problems of difficult identification of small fractures, large model calculation amount, poor multi-scale information fusion and class imbalance in the coal rock fracture image can be solved, and the robustness, segmentation precision and practicability of the model are improved.

The invention relates to the field of construction engineering, in particular to a roadbed construction slope displacement monitoring system based on cloud computing. A sensor network is used for collecting roadbed construction data in a roadbed, wavelet transform is used for denoising the data, a dynamic time warping algorithm in a cloud computing unit is used for aligning time sequence data in the initial roadbed construction data, and the weight of each sensor data is dynamically distributed based on an entropy weight method. A hybrid prediction model is established based on an LSTM long short-term memory network and FEA finite element analysis, a slope stress field result simulated by FEA is used as a physical constraint layer of the LSTM, an attention layer is embedded in the physical constraint layer, hyper-parameters of the initial hybrid prediction model are optimized by using a Cs-Ant improved cuckoo-ant colony combinatorial algorithm, and a slope stress field is obtained. And inputting the feature roadbed construction data into the target Cs-FEA-LSTM hybrid prediction model for prediction. The manual analysis cost is effectively reduced, and the level of roadbed engineering full-period monitoring is improved.

Training a mixed language speech recognition model, and speech recognition performed by the model, can be enhanced. Model manager can control training and / or operation of the model. Mixed language data generation manager can generate an enhanced mixed language dataset that can enhance training of the model. Fine tuner can facilitate configuring hyperparameters of the model. Audio-based information and transcript that are representative of the dataset can be applied to the model to facilitate model training. FAL evaluator can determine fidelity, accuracy, and latency of performance of speech recognition on the audio-based information and transcript by the model. Based on such determination, mixed language data generation process and / or hyperparameters can be updated to enhance further training of the model to enhance fidelity, accuracy, and / or latency regarding performance of speech recognition by the model. Model manager can control one or more iterations of model training.

The invention discloses a ship abnormal track identification method based on AIS data, which belongs to the technical field of AIS data mining processing, is used for identifying an abnormal ship track, and comprises the following steps: collecting and sorting AIS historical abnormal track data and marking, and constructing a graph structure of the track data; dividing the abnormal trajectory data into a training set and a test set, training a graph convolutional neural network model by the training set, evaluating model performance by the test set, and adjusting hyper-parameters of the model; performing matching according to mmsi to obtain complete AIS data, and establishing a graph structure of trajectory data; classifying ship trajectories to be classified by using the model, and finding out individual abnormal trajectories; and processing the ship trajectory points based on a neighbor mapping Haversine grid algorithm, and finding out a group abnormal trajectory. Compared with the prior art, the method has stronger automatic feature learning ability, can effectively capture the space-time relationship and the complex trajectory mode, and improves the recognition performance and adaptability.

The invention discloses a federated learning model training method and system based on differential privacy image noise addition. The method comprises the following steps: S1, initializing an evaluation network, a target network and hyper-parameters; s2, initializing a global model and parameters; s3, acquiring a selected client and a privacy budget; s4, the selected client performs local training and uploads the disturbance gradient to the central server; s5, the central server aggregates the disturbance gradient of the client to obtain an updated global model and a reward corresponding to the current state; s6, the next state of federated learning is obtained, and the evaluation network and the target network are updated; s7, repeatedly executing the steps S3 to S6 until the set number of global iterations is reached; and S8, updating the exploration rate and repeatedly executing the steps S2 to S7 until the set federal learning times are reached. The invention provides a dynamic differential privacy method in combination with a federal learning framework, which can improve the image recognition rate while ensuring the privacy of the user.

The invention discloses a transformer fault diagnosis method based on multi-sensor multi-domain feature fusion, and the method comprises the following steps: 1, obtaining a vibration signal data set of a transformer box, and carrying out the decentralization of a collected signal; 2, decomposing the decentralized transformer vibration signal by adopting a dung beetle optimized ICEEMD method, calculating a Pearson correlation coefficient between an IMF component and an original signal, and selecting a strongly correlated component to reconstruct the transformer vibration signal, so as to filter and denoise the transformer vibration signal; step 3, extracting time domain, frequency domain and space domain features in the transformer vibration signals by adopting an MVAR model, VMD-BIS decomposition and Riemannian manifold, and constructing a joint feature vector; 4, performing fusion dimension reduction by adopting a kernel principal component analysis algorithm to obtain a fusion dimension reduction feature vector; and a fifth step of constructing a kernel extreme learning machine model, training parameters of the kernel extreme learning machine model in combination with the time-frequency-space fusion features, and optimizing hyper-parameters of the kernel extreme learning machine model in combination with a Harris eagle optimization algorithm so as to obtain an optimal kernel extreme learning machine classification model. According to the method, the problems of misjudgment, missed judgment and low diagnosis rate caused by unbalanced distribution due to nonlinear characteristics of vibration signals in transformer fault diagnosis are effectively solved.

The invention discloses a KCBMA algorithm-based windmill bridge system safety assessment method, which relates to the technical field of windmill bridge coupling systems, combines a Kepler optimization algorithm (KOA) with a convolutional neural network-bidirectional long-short-term memory network (CNN-Bi-LSTM-MA) under a multi-head attention mechanism, adaptively searches an optimal hyper-parameter combination of the CNN-Bi-LSTM-MA network through the KOA, and provides a safety assessment method for a windmill bridge system. Constructing a neural network prediction model with dynamic adaptive capacity; the Bi-LSTM unit performs modeling by fusing the randomness characteristics of wind load excitation and system parameters, so that a numerical model can effectively represent the randomness of a wind-vehicle-bridge system and predict the random response of the wind-vehicle-bridge system. According to the method, the dynamic interaction among the wind-vehicle-bridge structures is integrated into the neural network model, the modeling time is remarkably shortened by using the KOA, the modeling accuracy is improved, the calculation cost is reduced, and the system response is more accurately predicted.

The invention discloses a soil salinity inversion method, system and device based on multi-mode remote sensing data fusion and a storage medium, and is applied to the technical field of soil quality monitoring, and the method comprises the steps: obtaining radar and optical remote sensing data of a to-be-inverted region of soil salinity, and carrying out the conductivity measurement, and taking the obtained data as an inversion index of the soil salinity; obtaining multi-modal remote sensing features based on radar and optical remote sensing data fusion, optimizing a remote sensing feature combination by combining the radar and optical remote sensing data and based on a random forest algorithm and utilizing a recursive feature elimination method, and performing model performance evaluation on the remote sensing feature combination by adopting cross validation to obtain an optimal remote sensing feature combination; and based on the optimal remote sensing feature combination, constructing and training a soil conductivity prediction model based on a random forest algorithm, and inputting to-be-measured data to the conductivity prediction model after hyper-parameter adjustment to complete soil salinity inversion. According to the method, more accurate inversion of the soil salinity under the interaction influence of a complex environment and human factors is realized.

A method, program and system for training a neural network to perform a machine learning task is provided. The method comprises receiving input data for the neural network. The method further comprises determining values for a plurality of hyperparameters of the neural network. The method further comprises building the neural network according to the hyper parameter values, wherein the neural network comprises a plurality of neurons. Each neuron includes a probability distribution for a plurality of logic operators, such that the neuron includes a corresponding probability for each of the logic operators. The method further comprises training the neural network according to the hyper parameter values and the input data by learning the probability distribution of each neuron. The method further comprises determining a logic operator of the plurality of logic operators for each neuron by selecting a value in the probability distribution.

The present disclosure describes computer-implemented methods and systems for automating application processing with dynamic data collection and augmentation related to applicants' behavior. The method includes receiving a plurality of applications with corresponding information, then aggregating, storing, and preprocessing data related to the applicants' behavior. The method also includes a machine learning model including a training dataset, a feature selection module, a hyperparameter tuning module, and a prediction model. The method includes predicting the application outcome based on the application information and behavior data and generating an underwriting decision based on the prediction. The method further includes providing underwritten applications for display and receiving a selection of a subset of the underwritten applications.

The invention discloses a topological structure information guided power distribution network measurement data complementation method and system and a medium, and belongs to the technical field of power distribution networks, and the method comprises the steps: obtaining incomplete historical measurement data under different topological structure sets, and building a measurement data set; building a plurality of conditional auto-encoder models respectively used for missing complementation of different measurement data based on a full-connection neural network; designing a loss function of each conditional auto-encoder model, performing joint training on the plurality of conditional auto-encoder models through the measurement data set, and adjusting hyper-parameters for multiple times to obtain a power distribution network measurement data completion model guided by topological structure information; and inputting incomplete measurement data and a corresponding topological structure into the topological structure information guided power distribution network measurement data completion model, and outputting complete measurement data by the topological structure information guided power distribution network measurement data completion model. According to the invention, the complemented measurement data is controlled to be more authentic and higher in precision by sensing the change of the topological structure.

The invention relates to an extra-high voltage converter transformer OLTC fault diagnosis method fusing multi-feature information and RIME-CNN-BiLSTM-SAM, and belongs to the technical field of intelligent monitoring of power systems. The method comprises the following steps: firstly, constructing a vibration signal fault data set based on an OLTC mechanical fault simulation experiment; secondly, decomposing an OLTC vibration signal into a plurality of intrinsic mode components by adopting REMD, and preferably selecting components containing rich fault feature information based on a correlation coefficient; then, the multi-scale permutation entropy of IMFs is calculated, time / frequency statistical analysis and the multi-scale permutation entropy are combined, OLTC multi-dimensional vibration characteristic parameters are integrally and locally concerned, and principal component analysis is introduced to carry out characteristic fusion and dimension reduction of OLTC vibration information; and finally, optimizing the hyper-parameters of the CNN-BiLSTM-SAM fault diagnosis model by using the RIME, and realizing the construction of the converter transformer OLTC intelligent fault diagnosis model. The method has a remarkable effect in the aspect of extracting OLTC fault feature information, the fault type recognition rate is superior to that of an existing method, and the effectiveness of the method in converter transformer OLTC fault diagnosis is verified.

The invention is suitable for the technical field of short-term power load prediction and intelligent scheduling, and provides a short-term power load prediction method based on improved sparrow search algorithm (ISSA) optimization. The method comprises the following steps: constructing a multi-scene prediction task according to the time resolution and regional seasonal characteristics of a load; local features are extracted in combination with a convolutional neural network (CNN), time sequence dependence is modeled by a long short-term memory (LSTM) network, and an attention mechanism is introduced to strengthen key features; meanwhile, an ISSA is adopted to optimize a model network structure and hyper-parameters, the number of layers, the learning rate and the batch size of the CNN and the LSTM are adjusted in a self-adaptive mode, and the search efficiency and convergence performance of the ISSA are improved through Latin hypercube sampling, cosine annealing, dynamic spiral search and a Levy flight strategy. Simulation results show that the method can maintain high prediction precision under different time resolutions and regional and seasonal conditions, the generalization ability and cross-scene adaptability of the model are enhanced, and a stable and efficient load prediction scheme is provided for power grid dispatching optimization.

Techniques for increasing the quality of output from large language models using reinforcement learning to select inference-time hyperparameters are disclosed. The large language model is configured with a set of values corresponding to a set of inference-time hyperparameters that are used to influence the output of the machine learning model after the model has been frozen. After obtaining a set of performance metrics that indicate the quality of the output, a reinforcement learning agent computes an adjustment for one or more of the hyperparameters, resulting in a modification of the hyperparameter values. Applying the new hyperparameter values, the large language model is then applied to a new set of input to generate a second output. The process iterates until the performance metrics associated with the output are satisfactory.

The invention provides an urban groundwater inrush risk assessment method based on a three-dimensional grid model and an XGBoost algorithm, and belongs to the technical field of geological disaster early warning. The method comprises the following steps: acquiring geological, environmental and historical disaster data in real time through a multi-source heterogeneous data interface; constructing a heterogeneous grid unit based on three-dimensional geological modeling, and dynamically binding parameters such as underground water level, fault activity and lithologic permeability coefficient; an XGBoost algorithm is combined with second-order Taylor expansion to optimize gradient calculation, and a nonlinear risk assessment model is constructed through Bayesian hyper-parameter tuning and SHAP value feature interpretive analysis; identifying contiguous dangerous areas based on spatial autocorrelation analysis and an adaptive threshold segmentation algorithm; and a risk thermodynamic diagram, geological section superposition and real-time early warning are realized through a 3D GIS platform. According to the method, the problems that a traditional method depends on a linear model, data is single and local risk description is insufficient are solved, and the accuracy, efficiency and engineering practicability of risk assessment are remarkably improved.

The invention relates to the technical field of electric power system disturbance identification, in particular to an electric power system disturbance identification method based on a fusion neural network of parameter optimization, which comprises the following steps: acquiring eight types of disturbance frequency data of an electric power system, and optimizing penalty factors and modal feature vector quantity based on variational modal method decomposition by adopting an improved sparrow search algorithm to obtain eight types of disturbance frequency data of the electric power system; obtaining a target parameter group, obtaining modal feature components selected based on a fitness function, optimizing hyper-parameters of a fusion neural network by adopting a Lundao search algorithm, and distributing feature weights of a second time domain index in combination with a multi-head attention mechanism to obtain a time sequence feature signal; and S400, performing disturbance identification on the time sequence characteristic signal in the step S400 by adopting a convolutional neural network-bidirectional gating cycle unit classifier to obtain a disturbance identification result, and remarkably improving the accuracy of disturbance identification through the method.