3569 results about "Feature selection" patented technology

The invention discloses an industrial robot health state monitoring method and system based on digital twinning, and relates to the technical field of equipment monitoring, and the method comprises the steps: collecting the real-time state data of an industrial robot through a plurality of sensors, and enabling the real-time state data to be matched and aligned with a three-dimensional simulation model, and constructing a digital twinning model; obtaining twinborn data through the digital twinborn model after the adaptive model parameter update, and fusing the twinborn data with the real-time state data to generate a multi-source heterogeneous data set; feature data representing the health state of the industrial robot is obtained through feature selection to construct health indexes; and constructing a health state evaluation model based on the deep belief network, and taking the current health index parameters as model input to obtain an industrial robot health state evaluation result. Multi-source heterogeneous data such as vibration data and electrical data are fused, the health state of the industrial robot is monitored and evaluated in combination with digital twinning, and a reliable reference basis is provided for state monitoring and maintenance of the industrial robot.

The invention discloses a multi-working-condition-oriented equipment fault diagnosis method based on unbalanced learning, and the method comprises the following steps: collecting the operation data of equipment under different working conditions through a plurality of sensors, carrying out the preprocessing, feature extraction and feature selection of the collected original operation data, and obtaining a feature set; processing the feature set by adopting an unbalanced learning technology and a cost-sensitive learning algorithm to obtain a balanced data set; constructing a multi-working-condition fault diagnosis model based on learning, and optimizing model parameters by adopting a method of combining cross validation and grid search according to a balanced data set in a model training process; deploying a multi-working-condition fault diagnosis model obtained through training, carrying out the online diagnosis of equipment faults, and continuously updating and optimizing the model through a continuous learning mechanism. According to the method, the unbalanced learning technology is applied to multi-working-condition fault diagnosis, the accuracy and robustness of diagnosis can be remarkably improved, and real-time monitoring and predictive maintenance of the equipment health state are achieved.

A method for structuring the latent space of an autoencoder is provided. The method includes analyzing natural language descriptions related to input data; creating language-guided libraries that categorize and abstract data features based on the analyzed descriptions; mapping input data into the categorized and abstracted features within the latent space of the autoencoder; and training the autoencoder to minimize reconstruction loss while adhering to the structure imposed by the language-guided libraries.

The invention discloses a high-resolution radar echo extrapolation prediction method fused with satellite data, and the method specifically comprises the following steps: firstly, inputting historical radar echo sequence preprocessing at a previous T moment, including denoising, normalization processing and data set segmentation, and obtaining cleaned data; then, through a deterministic modeling method (SimVP), a fuzzy prediction sequence of a future T duration is obtained, then a variational auto-encoder (VAE) maps an original radar echo image and the fuzzy prediction sequence to a low-dimensional potential space, and two-stage diffusion modeling is carried out on the basis; in the first stage, a space-time converter (ST-Translator) is used to extract space-time evolution characteristics of radar echoes; in the second stage, satellite data at the corresponding time of the previous T moment is input, preprocessing including normalization processing, feature selection and data set segmentation is carried out, cleaned data is obtained, and the influence of the satellite data is dynamically adjusted in the diffusion process by adopting a multi-source fusion denoising network Fsrform so as to make full use of satellite information; and finally, inversely transforming output results of the two stages into a pixel space to obtain a high-resolution radar echo extrapolation prediction result of the future T duration. According to the invention, computing resource consumption can be effectively reduced, and the precision and detail fidelity of short temporary rainfall prediction are improved.

The invention discloses a karst collapse risk analysis method and system based on geological big data mining, and the method comprises the steps: collecting multi-source heterogeneous geological data, and carrying out the data fusion through employing a Tucker decomposition-based tensor decomposition algorithm; cleaning, complementing and standardizing the fused data; feature selection and construction: selecting features related to the karst collapse risk; carrying out feature extraction on the preprocessed data; based on the features extracted by the feature engineering, constructing a risk assessment model by using a graph convolutional neural network, and optimizing model performance through an ensemble learning method; carrying out risk assessment and prediction by utilizing the trained model, and carrying out visualization through a geographic information system; and real-time risk assessment is realized based on an edge computing technology, and the model is continuously optimized. According to the method and the system, complex heterogeneous data can be processed, the time change trend of geological parameters can be accurately captured, the prediction accuracy under complex geological conditions is high, and the timeliness of early warning is greatly improved.

The invention discloses a multi-field part size and appearance defect intelligent detection system, and relates to the field of image analysis. The system comprises an image acquisition module, an image preprocessing module, a feature extraction module, a defect identification and size measurement module, a data processing and analysis module, an automatic control module and a man-machine interaction module. According to the method, CNN and LBP, Hough transform and SIFT algorithms are fused, high-level semantics and bottom-level texture / geometric features are considered, 2304-dimensional fusion feature vectors are formed through feature splicing, the feature extraction integrity of parts in multiple fields is improved, texture detail features can be accurately extracted, geometric shape features can be accurately obtained, and the method is suitable for large-scale popularization and application. Meanwhile, the adaptive feature selection mechanism dynamically optimizes the feature combination according to the detection result, the problem of calculation redundancy is reduced, and the detection precision is ensured while the detection efficiency is improved.

The invention discloses an infrared ship detection method based on an improved RT-DETR algorithm, and aims to improve the detection precision and efficiency of a ship target in an infrared image. By introducing a multi-layer dynamic feature conversion module (MDST), the diversity of feature extraction is enhanced; effective fusion of multi-scale features is realized by using a high-level screening feature fusion pyramid network (HS-FPN); an original RT-DETR backbone network is replaced by a PPA and C2f structure, so that the problem of information loss in a down-sampling process is solved; and the CA module is used for enhancing the feature selection and fusion effect. Experimental results show that the provided method significantly improves the detection performance on an infrared marine ship data set, is suitable for resource-constrained equipment such as unmanned aerial vehicles and smart phones, and has a wide application prospect.

The invention relates to the technical field of health state analysis, in particular to an intelligent health state analysis system and method based on artificial intelligence, and the method comprises the following steps: S1, collecting multi-modal health data; s2, data preprocessing and anomaly detection: preprocessing the collected multi-modal data; s3, multi-modal data fusion and feature selection: carrying out feature fusion on data of different modals through a deep learning model, and carrying out feature extraction on time sequence data by adopting a convolutional neural network (CNN); s4, health state prediction and trend analysis: performing prediction analysis on the health state of the user based on a long and short term memory network (LSTM), and generating a health state trend chart of the user in combination with historical health data and real-time data; and S5, personalized health intervention suggestions are generated: personalized health management suggestions are automatically generated, a more comprehensive health assessment result is provided, the user can better know the own health condition, and personalized management is carried out.

The invention discloses a network security analysis early warning system based on artificial intelligence, and the system comprises a data collection layer which captures full flow based on DPI, aggregates firewall logs, terminal behaviors and threat intelligence, and constructs a structured data pool; through TLS fingerprint identification of AI driving, the encrypted traffic is penetrated, and a sampling strategy is dynamically adjusted in combination with reinforcement learning. The intelligent analysis layer is used for carrying out cross validation on known threats and abnormal behaviors; the time sequence CNN extracts encrypted traffic features, and a novel threat detector is rapidly generated by using historical attack fragments in combination with a meta-learning framework; sHAP value driving dynamic feature selection and optimization feature vector input; the decision-making early warning layer is used for fusing multi-source features through a Bayesian network and generating 0-100 score risk scores; a self-adaptive threshold module is combined to adjust a score threshold in real time, and a high-risk event is pushed; the collaborative response layer is used for triggering a preset decision tree, deploying a GAN dynamic honeypot to trap an attacker and reversely tracing; the Neo4j visually restores the attack path, and blocking is executed after the threat is confirmed by a progressive response mechanism.

The invention discloses an intelligent construction method based on data driving, and relates to the field of intelligent construction, and the method comprises the steps: collecting multi-source heterogeneous data of an intelligent construction project; performing feature selection on the acquired multi-source heterogeneous data by adopting a recursive feature elimination (RFE) algorithm to obtain a feature subset reflecting project progress, quality and safety; according to the feature subset, a multi-target model used for predicting project progress, quality and safety is constructed through a support vector machine (SVM) algorithm; a non-dominated sorting genetic algorithm NSGA-II is adopted to solve the multi-target model, a simulated annealing strategy is introduced in the iterative search process of the NSGA-II to jump out of a local optimal solution, and an optimized Pareto optimal solution set is output; and selecting an optimal parameter combination according to the Pareto optimal solution set, and adjusting the BIM model of the current intelligent construction project by using the optimal parameter combination. In view of low multi-objective optimization efficiency in intelligent construction project management in the prior art, the optimal model parameters considering different management objectives are obtained, and the efficiency is improved.

The invention discloses a distributed photovoltaic power station generating capacity prediction method based on qualified point meteorological data, and relates to the technical field of photovoltaic power generation, and the method comprises the steps: obtaining the geographic information and historical power generation data of a photovoltaic power station, carrying out the space matching through combining the historical grid point meteorological data, and building the grid point-position correlation; extracting a plurality of groups of historical data based on the association, performing weather scene classification, training a scene-based generating capacity prediction model, and constructing a prediction network; and inputting real-time grid point meteorological data into the prediction network, and performing power generation prediction through a dynamic feature selection mechanism to obtain a high-precision power generation prediction result. According to the method, the technical problems of low prediction precision and poor adaptability of a traditional photovoltaic power generation capacity prediction method in the prior art when coping with complex meteorological changes are solved, and the purpose of predicting the power generation capacity by introducing high-precision grid point meteorological data and a special scenario prediction model is achieved. And the prediction precision and adaptability of the photovoltaic generating capacity under the complex meteorological condition are improved.

The invention relates to the technical field of agricultural production data prediction, and discloses a tobacco plant number prediction method based on deep learning, and the method comprises the steps: collecting tobacco field environment data through a soil humidity sensor, a weather sensor, a laser radar point cloud sensor, a multispectral sensor and other multi-source agricultural sensors, carrying out the multi-source feature fusion through a dynamic feature selection network, and generating an environment feature vector. And inputting the model into a multi-modal time sequence prediction model adopting a space-time attention mechanism, and modeling a tobacco plant growth trend. And constructing an adaptive weighted regression model according to a prediction result, and dynamically adjusting the weight by using an improved particle swarm optimization algorithm. And constructing a hierarchical correction model to optimize prediction data. A real-time prediction updating method is provided, and newly-added data can be processed. The multispectral sensor data is subjected to dimension reduction, correlation modeling and interpolation fusion processing. According to the method, multi-source data is fully utilized, the accuracy, real-time performance and stability of tobacco plant number prediction are improved, and powerful support is provided for tobacco planting management.

The invention provides an equipment health management method and system for a wind generating set. The method belongs to the technical field of wind power generation, and comprises the following steps: acquiring multi-source data of a wind generating set, preprocessing the acquired multi-source data, and integrating the preprocessed multi-source data into a uniform data format by using a data fusion technology; based on domain knowledge and data characteristics, key features reflecting the health state of the equipment are extracted, and a feature subset with the highest prediction value for the health state of the equipment is screened out through a feature selection algorithm. Key components of the wind generating set are monitored in real time through a high-precision sensor network, and comprehensive collection of data is realized in combination with multi-source information such as a historical fault database and meteorological data.

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 an antagonism prompt detection method and device based on a large language model and a medium, and belongs to the technical field of artificial intelligence safety. The technical problem to be solved by the invention is how to overcome the defects of static rule lagging, high manual maintenance cost and insufficient context understanding in the security protection process of a large language model in the prior art, and dynamic, real-time and high-precision antagonism prompt detection is realized. According to the technical scheme, the method comprises the following steps: feature extraction: comprehensively analyzing semantic information, structural information and context information in a user text, extracting semantic features, structural features and context features, performing Min-Max normalization on the semantic features, the structural features and the context features, and splicing the semantic features, the structural features and the context features into a 128-dimensional joint vector, performing feature selection on the joint vector through an L1 regularization logistic regression model, compressing to 10-dimensional core features, and removing redundant information; carrying out resistance scoring; and dynamically defending.

The invention discloses an old people chronic disease risk prediction method and system based on a time sequence knowledge graph, and belongs to the technical field of medical health information, and the method comprises the following steps: S1, obtaining a health data set of an old people group; s2, on the basis of an ESOA-XGBoost algorithm, performing feature selection and sorting on each piece of health data in the health data set so as to determine correlation among variables, and generating a health data feature set; s3, constructing and training a time sequence knowledge graph prediction model including an STKGR-PR model and a T i PNN model, and predicting a relationship among the target entity, other entities and time sequence information through the time sequence knowledge graph prediction model; s4, predicting the old chronic disease risk of the old people group according to the trained time sequence knowledge graph prediction model; through the method, an elderly chronic disease risk prediction result with a good prediction effect and high accuracy can be obtained.

The invention discloses a multi-source heterogeneous data fusion and processing method based on a localized LLM model, and relates to the technical field of factory energy management.The method comprises the steps that multi-source heterogeneous data is collected from a factory energy management system, and the collected original data is preprocessed and standardized; performing feature selection, feature extraction and feature combination on the processed data; carrying out embedding dimensionality reduction by adopting principal component analysis and a localized LLM model; performing intelligent semantic analysis and fusion on the dimension reduction feature data by utilizing a localized LLM model, performing weighted fusion on embedded vectors by adopting a multi-head attention mechanism, and extracting semantic association among the data; and performing intelligent anomaly detection on the fused high-quality data by using localized LLM model embedding analysis and cosine similarity calculation. According to the method, the processing efficiency and quality of the multi-source heterogeneous data are comprehensively improved, high-quality data support is provided for comprehensive energy management of factories, and efficient and intelligent energy scheduling and management optimization are achieved.

The invention discloses a crop leaf area index estimation method coupled with a physical model and deep learning. The crop leaf area index estimation method comprises the following steps: step 1, data acquisition and preprocessing; 2, the reflectivity of a Sentinel-2 channel is simulated; 3, preferably selecting a spectral feature combination sensitive to the leaf area index; and step 4, constructing a PROSAIL-Transform coupling model to estimate the leaf area index of the crop. According to the method, the advantages of a canopy radiation transfer model PROSAIL and a deep learning model Transformer are fully utilized, and sample data closest to a Sentinel-2 image are selected by adopting a sample matching method, so that the change of a real world environment is more accurately captured. And identifying the most sensitive spectral feature combination in the leaf area index estimation of different crops by combining a maximum information coefficient (MIC) and recursive feature elimination (RFE) feature selection method. And the coupling model is trained by using the most representative and accurate data, so that the efficiency and accuracy of model training are improved.

The invention discloses a remote printer monitoring and fault prediction system based on the Internet of Things, and relates to the technical field of the Internet of Things and artificial intelligence, and the system comprises a data collection module which is used for collecting equipment state data of a remote printer in real time and carrying out the preprocessing of the equipment state data; the data processing module is used for integrating the preprocessed equipment state data into a data matrix and a label vector; the model construction module is used for outputting a final feature set by using a random forest model and combining a Gumbel-Sigmoid activation function; and the fault prediction module is used for constructing a fault prediction model by using the bidirectional LSTM to output the predicted fault probability of the current time point and dividing a fault interval data pool. By introducing the combination of a random forest algorithm and a Gumbel-Sigmoid activation function, a feature selection process can be automatically optimized, a feature set which is crucial to fault prediction can be accurately screened out, and a bidirectional LSTM model is adopted to capture time sequence information, so that the fault prediction precision and the real-time response capability are remarkably improved.

The invention discloses a metering error correction method and system based on electric power data acquisition, and the method comprises the steps: detecting an operation state through a self-inspection and data acquisition module, and obtaining environment data, electrical parameters and error information; key feature data are selected and standardized through a data preprocessing module; an LSTM model and an SVR model are constructed through a model establishment and fusion module, and prediction results are fused to generate error compensation output; real-time error compensation is carried out on a combined prediction result by utilizing an ARIMA model and error time sequence processing through a dynamic error compensation module; the data smoothing and evaluation module is used for smoothing the voltage data and evaluating the error compensation effect; an error compensation effect is monitored through a monitoring and optimizing module, and feature selection and model parameters are optimized regularly; through the fault diagnosis and emergency module, an abnormal condition is detected, and a corresponding standby scheme is triggered. According to the invention, the accuracy and anti-interference capability of electric power metering are effectively improved, and the method is suitable for complex and changeable metering environments.

The invention discloses a numerical control lathe tool wear monitoring method and system. The method comprises the steps that numerical control lathe tool operation process data are monitored in real time; a corresponding preset operation parameter threshold value is matched according to the operation process data, and when it is monitored that the preset operation parameter threshold value is exceeded, the operation process data of the numerical control lathe tool is transmitted to an edge computing node; matching a corresponding preset operation parameter combination and finishing operation parameter screening according to the operation process data by utilizing the edge computing node; based on the screened operation parameters, key features are selected and extracted by using a feature selection algorithm, and an optimal feature set is acquired and uploaded to a cloud platform; and matching a corresponding tool wear prediction model according to the operation process data at the cloud platform, inputting the optimal feature set into the matched tool wear prediction model, obtaining a wear value, a wear degree and a life prediction result, and performing early warning decision and early warning prompt. According to the invention, efficient, accurate and real-time tool wear monitoring under complex working conditions is realized.

The invention relates to the technical field of industrial equipment health monitoring and fault diagnosis, and discloses a centrifugal pump intelligent detection method and system based on multi-source data. The centrifugal pump intelligent detection method based on the multi-source data comprises the steps that centrifugal pump multi-source heterogeneous data are collected and preprocessed; extracting multi-scale features and constructing an optimal feature subset through hierarchical feature selection; constructing a multi-level dynamic Bayesian network to establish a probabilistic reasoning framework; calculating a feature credibility weight based on the signal quality, the feature stability and the diagnosis correlation; executing multi-source evidence fusion and Bayesian state reasoning; confidence self-calibration and parameter self-adaptive adjustment are realized through historical diagnosis result feedback; the method can effectively cope with the complex and changeable environment of an industrial site, can still keep stable diagnosis performance under the condition that the sensor part loses efficacy or the data quality is uneven, improves the accuracy and reliability of fault diagnosis, and provides powerful technical support for predictive maintenance of industrial equipment.

The invention provides a ship fault prediction system based on multi-source data fusion, and relates to the technical field of ship fault prediction, and the system comprises a data collection module which is used for obtaining original signal data; the data preprocessing module is used for aligning the original signal data from different sources, and after data alignment, preprocessing the original signal data after data alignment according to a preprocessing step to obtain preprocessed data; the data fusion module is used for performing multi-source fusion on the preprocessed data by using an improved Kalman filtering algorithm to obtain fused data; the feature engineering module is used for performing multi-dimensional feature extraction and feature selection on the fused data, and fusing the selected features to obtain fused features; and the fault prediction module is used for receiving the fusion features and performing ship fault prediction according to the fusion features based on a pre-trained fault prediction model. According to the invention, accurate prediction of ship faults can be realized, and finally the safety and reliability of ship operation are improved.

The invention discloses a converter steelmaking oxygen supply prediction method based on knowledge and data fusion driving. The converter steelmaking oxygen supply prediction method comprises the following steps: S1, constructing a method framework comprising a knowledge-based feature engineering and gating constraint module and a data-based dual-attention prediction module; s2, preprocessing and cutting the data; s3, performing feature generation and feature selection through the represented knowledge in a knowledge-based feature engineering and gating constraint module, and establishing a gating constraint mechanism; s4, constructing a multi-scale convolutional neural network and a time perception neural network in a data-based dual-attention prediction module, and training under obtained features and gating constraints; and S5, performing prediction by using the trained model, and performing weighted fusion on prediction results obtained by the multi-scale convolutional neural network and the time sensing neural network to obtain a final oxygen supply amount.

The invention provides a machine learning water quality monitoring model based on a random forest algorithm. The machine learning water quality monitoring model comprises the following steps: A, preprocessing water quality monitoring data; b, selecting features related to a water quality monitoring target from the preprocessed data; c, constructing a random forest model; d, training the constructed random forest model; e, predicting the trained random forest model; f, evaluating the predicted random forest model; g, parameters of the random forest model are adjusted according to the evaluation result for optimization, through historical data training, the model can automatically recognize and predict water quality abnormal events, and pollution can be found and prevented as soon as possible. The random forest algorithm can train a plurality of decision trees at the same time to form a forest, and random sampling and random feature selection are performed on a data set, so that the accuracy and robustness of the model are improved.

The invention relates to a satellite-to-ground network adaptive image semantic communication method based on an NOMA technology, and the method comprises the following steps: S1, building a satellite-to-ground semantic communication frame integrated with the NOMA technology: carrying out the power superposition and serial interference elimination of different user transmission contents through the NOMA technology, a coding and decoding process is optimized through deep joint source channel coding based on hierarchical vision using a shift window; s2, establishing an adaptive semantic communication model: dynamically adjusting coding parameters based on a target bandwidth ratio and a signal-to-noise ratio of a satellite-ground channel; s3, proposing a dynamic weight adjustment algorithm: optimizing model convergence speed and transmission performance tradeoff under different channel conditions; and S4, designing a feature selection module: performing priority ranking on the image features, and selectively transmitting important features according to bandwidth resources. According to the method, the adaptive semantic communication model (ASeC-NOMA) which can be dynamically adjusted according to the target bandwidth ratio and the signal-to-noise ratio is constructed, and a large number of model storage parameters are saved while the transmission performance is ensured.

The invention discloses a reinforcement learning intrusion detection method and system based on dynamic network feature screening, and the method comprises the steps: constructing a self-adaptive reward reinforcement learning network based on Transform framework enhancement, carrying out the network flow feature screening in combination with a crayfish optimization algorithm, and constructing a self-adaptive reward reinforcement learning network based on Transform enhancement. Through combination of a Transform mechanism and reinforcement learning, adaptive learning and decision optimization capabilities in a dynamic network environment are significantly enhanced. A crayfish optimization algorithm is combined to perform feature extraction on the high-dimensional network traffic to capture a feature set which is most valuable for intrusion detection, so that a most representative feature subset can be efficiently extracted from complex and changeable network traffic data, and the automation and precision of a feature selection process are improved; the method effectively overcomes the defects of sample imbalance, feature selection, dynamic adaptability and the like in the prior art, and provides a more intelligent and efficient intrusion detection solution.

The invention discloses a satellite remote sensing image cloud classification method based on space-time coding guidance, and particularly relates to the technical field of satellite image processing and deep learning, and the method comprises the following steps: carrying out the preprocessing of the original data of a geostationary meteorological satellite and a Cloud Sat satellite; preprocessing operation such as cutting, projection conversion and feature selection is carried out on the geostationary meteorological satellite data, a top cloud type is selected for the Cloud Sat data to serve as a label, and space-time matching is carried out on the processed geostationary meteorological satellite data and the Cloud Sat data to obtain a training and testing data set; and establishing a GTCCT model, performing time and geocoding on the input data, inputting the coded feature data into a network for training, and finally obtaining the GTCCT model for cloud classification.

The invention relates to the technical field of solid state disk performance evaluation. The solid state disk performance evaluation method comprises the steps of obtaining solid state disk operation information, conducting exception analysis on the solid state disk operation information through a deep learning model to obtain solid state disk exception information, conducting correction and interpolation on the solid state disk exception information, and obtaining the solid state disk performance evaluation result. Performing feature extraction on the corrected operation information to obtain a plurality of performance features of the solid state disk, screening the plurality of performance features based on a feature selection method to obtain a target feature set required by performance evaluation, and analyzing the target feature set required by performance evaluation through a time sequence prediction model. Obtaining performance change trend information under different loads, predicting the residual life and the performance degradation condition of the solid state disk according to the performance change trend information, and obtaining a performance evaluation result. The method has the effect of improving the performance evaluation accuracy of the solid state disk.

The invention relates to a dam deformation prediction method with embedded feature selection, and belongs to the field of dam safety monitoring and artificial intelligence, and the method comprises the following steps: obtaining the original monitoring data of an environment quantity and a dam deformation quantity; performing preprocessing of data cleaning, data filling and data normalization on the original data; evaluating the importance of environmental features based on a random forest algorithm, and selecting an optimal feature set in combination with a recursive feature method; constructing a dam deformation prediction model based on a convolutional neural network, a long and short term memory neural network and an attention mechanism deep learning algorithm; and the optimal feature is used as the input of CNN-LSTM-Attention to predict the deformation of the dam. Through the method in the application, the environmental characteristics having significant influence on dam deformation can be effectively determined, the complex mapping relation between the deformation and the environmental characteristics is fully excavated, and accurate dam deformation prediction is realized.