656 results about "Simulated data" patented technology

The invention relates to an intelligent inversion method and system for well drilling overflow shaft gas distribution based on a self-encoder, and belongs to the technical field of oil gas and geothermal development drilling and completion engineering. Comprising the following steps: step 1, accurately solving multiphase flow parameters of a shaft; 2, in combination with the drilling working condition and the geological condition of a specific overflow high-risk well section, based on a Monte Carlo sampling method, eight parameters are changed, uniform sampling is carried out, and a high-precision simulation data set is formed; step 3, constructing a neural network model for gas cut state inversion based on an auto-encoder neural network; 4, training is carried out; 5, standardizing one-dimensional time sequence parameters in the monitoring data; and inputting into a trained neural network model for gas cut state inversion based on an auto-encoder neural network to obtain distribution data of the overflow gas in the shaft in a time period in which the time sequence parameter at the current moment is located. According to the invention, the real-time rapid inversion of the gas distribution in the parallel cylinder during the drilling overflow parallel control period is realized.

The invention discloses a hydroelectric generating set operation fault data enhancement method and device, and the method comprises the steps: firstly collecting a set vibration signal, selecting a time-frequency transformation method to convert a one-dimensional vibration signal into a two-dimensional time-frequency image, enhancing the feature dimension of the signal, constructing a diffusion feature migration model, gradually disturbing the data distribution to Gaussian noise through forward diffusion, and carrying out the recognition of the Gaussian noise. The method comprises the following steps of: performing inverse denoising to generate simulation data highly similar to a real fault sample, realizing relevance learning and migration sharing of fault features among different working conditions in combination with an adversarial feature migration architecture, and finally evaluating an enhancement effect by calculating similarity among samples, and inputting enhanced data into a fault diagnosis model to verify precision improvement. Through the combination of time-frequency transformation and a diffusion model, sample scarcity and working condition barriers are broken through, a remarkable effect is shown in the aspects of expanding the fault sample scale and enriching the sample dimension, the similarity of generated data and a real sample is improved, the diagnosis precision is improved, and the model generalization ability is remarkably enhanced.

The invention discloses a numerical simulation-based roadway surrounding rock deformation monitoring method and device. The method comprises the following steps of: constructing a three-dimensional geologic model of a roadway area; based on the three-dimensional geologic model, establishing a numerical model of heat conduction, stress action and seepage multi-physics field coupling, and based on elastic-plastic characteristics of rocks in the roadway area, simulating simulation data of surrounding rocks in the roadway area under the multi-physics field action by the numerical model; acquiring real-time monitoring data of various types of sensors arranged in a risk monitoring area of surrounding rock deformation corresponding to the simulation data; denoising, filtering and abnormal value processing are carried out on the real-time monitoring data, and then multi-source data fusion is carried out to calibrate the numerical model; and predicting the deformation trend of the surrounding rock based on the calibrated target numerical model and the real-time monitoring data. Therefore, by means of geological modeling, numerical model simulation, sensor arrangement optimization, numerical model optimization and surrounding rock deformation trend prediction, roadway surrounding rock monitoring precision is improved, and safe operation of a roadway is guaranteed.

The invention relates to the technical field of image analysis, and discloses a multi-modal emotion recognition method and system based on hypergraph diffusion and evidence fusion, a terminal and a storage medium, and the method comprises the steps: carrying out the random shielding of a data set through a randomly generated mask, thereby simulating the random data missing condition, and carrying out inverse sampling on the preprocessed simulation data by using a trained conditional diffusion model to obtain a training set in which missing modals are complemented so as to train an emotion classification network, and finally carrying out emotion recognition. According to the method, through dual-channel evidence fusion, uncertainty is estimated at a feature source level and a discrimination level at the same time, so that adaptive evidence fusion is realized, the condition of performance reduction caused by modal loss is reduced, potential features of the lost modal are explicitly recovered in a feature space, and the accuracy of final emotion recognition is improved.

The invention discloses a hydrological data prediction method based on a convolutional neural network and a physical information neural network. Comprising the following steps: 1) utilizing an HEC-RAS hydrological model to generate cross sectional area, flow and water level elevation data of a key section of a target river channel in a preset time period as training reference truth values; 2) constructing space-time coordinates corresponding to the data as an input data set; 3) space-time input is processed through a physical information neural network model based on a convolutional neural network, the convolutional neural network extracts local heterogeneity features of a spatial position of a river channel through one-dimensional convolution, and a continuity equation and a momentum equation of a Saint-Venant equation set are embedded into a training process in a residual form through physical information constraint; and 4) finally, directly outputting a hydrological parameter prediction result of the target river channel. Therefore, under the environment that the observation data is deficient or missing, the hydrological parameter prediction precision and the model generalization ability are remarkably improved by fusing the simulation data and the physical mechanism constraint.

The invention discloses an oil reservoir production dynamic prediction method fusing discrete gradient information, and belongs to the technical field of oil reservoir development and artificial intelligence crossing, and the method comprises the steps: building a heterogeneous oil reservoir oil-water two-phase flow numerical simulation data set based on a numerical simulation method; designing a double-branch network structure and extracting spatial and physical characteristics of input field data in parallel, wherein the spatial and physical characteristics comprise a main characteristic coding branch and a differential operator branch; designing a backbone network to carry out deep nonlinear modeling; an efficient pressure and saturation field prediction neural network model is constructed based on a double-branch network structure and a backbone network, in a model training stage, spatial region observation points of part of time steps are used to participate in data item loss calculation, and meanwhile, physical control equation residuals are introduced into all time steps and a whole space to serve as physical loss items; a trained efficient pressure and saturation field prediction neural network model is obtained, and high-precision prediction of a full-time-sequence pressure field and a saturation field is achieved.

The invention relates to the technical field of crane stress analysis, in particular to a crane structure parameter stress analysis method and system. The method comprises the following steps: constructing an accurate three-dimensional structure simulation model by obtaining crane device data and operation logs, and carrying out crane operation analogue simulation based on the model; performing boom structure division on the simulation data, respectively obtaining simulation data of the truss boom type crane and the telescopic boom type crane, evaluating stress coupling increment of the truss boom type crane and telescopic boom type mechanical conduction response characteristics, and comprehensively detecting dynamic mechanical response of the crane; based on the dynamic response data, identifying the breakage risk of crane components, determining the chain type degradation condition of the components, and evaluating the operation stability gradient attenuation of the crane in combination with the three-dimensional structure model; carrying out structural mechanics optimization treatment according to the stability attenuation condition; through crane stress analysis, the crane can run more stably and efficiently.

The invention provides a power distribution network source network storage cooperative control method and system, and relates to the technical field of power distribution networks, and the method comprises the steps: collecting multi-dimensional power grid information of a power distribution network, and setting a target constraint condition according to the multi-dimensional power grid information; establishing a target optimization index and a cooperative control simulation model in cooperation with the target constraint condition, and performing cooperative control simulation on the power distribution network through the cooperative control simulation model to obtain a simulation record; a fitness evaluation strategy is introduced to analyze a plurality of simulation data sets in the simulation records, and an optimal cooperative control scheme is obtained through screening; and performing source network storage cooperative control of the power distribution network through the optimal cooperative control scheme. According to the invention, the technical problem that the power distribution network is difficult to realize effective coordination of the power generation source, the energy storage equipment and the load in the prior art can be solved, and the technical effects of improving the new energy consumption capability, reducing the operation cost, guaranteeing the operation safety of the power grid and improving the overall stability of the system are achieved.

The invention discloses a multi-mode rainy day area road flatness detection method by means of Carla training, and relates to the technical field of road flatness detection, and the method comprises the steps: collecting real rainy day road surface images and vehicle parameters, and constructing a real data set; a rainy day scene is simulated in Carla, and terrain, wet and slippery materials and weather are configured; the method comprises the following steps: acquiring multi-modal data such as simulation point cloud and acceleration through a laser radar and a vibration sensor, and constructing a simulation data set; fusing real and simulation data to train a multi-modal neural network; extracting and fusing point cloud and acceleration features; road height variances and ranges are predicted to assess flatness. According to the method, the problem of scarcity of real data in a rainy day environment is solved by using Carla to generate synthetic data, the real acquisition cost is reduced, the detection precision is remarkably improved, various rainfall intensities and terrains can be covered, data complementation of the laser radar and the vibration sensor is realized, and the robustness in a rainy day is improved through dynamic weighting of an attention mechanism.

A method for constructing a digital twin monitoring model for slopes based on a proxy model includes S101-S104. S101, a slope geometric model consisting of M triangular facets is constructed. S102, a first training dataset is constructed for pretraining a pre-proxy model by using the slope geometric model. S103, monitoring data of the M triangular facets are collected in real-time to construct a second training dataset for training the proxy model. S104, a warning cloud map of the slopes is generated. The method uses the slope geometric model to obtain simulation data under multiple physical field conditions. It constructs training dataset of pretraining pre-proxy model based on the simulation data, which greatly reduces training samples. Moreover, the multiple base learners in the proxy model can reduce the computational bias of a single time-series analysis model, improving the prediction accuracy of the proxy model.

The invention provides a high-strength aluminum alloy selective laser melting forming thermal stress prediction method based on deep learning. The method comprises the steps of 1, finite element model establishment and simulation, wherein a heat transfer model and a thermal coupling model are established; an SLM process is used as a simulation object, a Gaussian model is adopted to define a laser heat source, and thermal stress distribution under different process parameters and different sample sizes is simulated; wherein the process parameters comprise laser power, scanning speed and hatch spacing; step 2, data processing and deep learning model training; comprising the steps of data preprocessing, neural network model architecture determination, adversarial network part generation and model configuration and training. 3, evaluating and optimizing the model; and 4, thermal stress prediction and process optimization. By learning a complex mode in finite element simulation data through a deep learning model, efficient and accurate thermal stress prediction is achieved, and the problems that traditional finite element analysis is complex in calculation and large in resource consumption are solved.

The invention relates to the technical field of remote sensing image processing, in particular to an end-to-end neural network InSAR (Interferometric Synthetic Aperture Radar) phase unwrapping method based on mixed attention, which takes U-Net as a basic framework, extracts key features and improves resolution through down-sampling and up-sampling operations, thereby effectively recovering detail information. Specifically, a convolutional block attention module (CBAM) and two receptive field modules, namely cavity spatial pyramid pooling (ASPP) and a receptive field module (RFB) are combined to construct an RFAUNet network model, and then simulation data sets generated by two methods of digital elevation inversion and random matrix generation are used for training a neural network until a good unwrapping effect is obtained. And finally, carrying out a phase unwrapping experiment on simulation data and real data to verify the effectiveness and robustness of the RFAUNet network model.

The invention discloses a transformer substation switching operation risk pre-control method and system based on deep reinforcement learning, and relates to the technical field of power system automation, and the method comprises the steps: collecting transformer substation equipment data in real time, processing the collected data, generating a standardized time series data set, building a system topology structure represented by multiple graphs based on the processed data, and carrying out the pre-control of the transformer substation switching operation risk. Integrating dynamic characteristics, based on a system topological structure, generating a switching operation decision sequence, dynamically adjusting a risk boundary threshold, based on a real-time system state, evaluating the security of the decision sequence, intercepting operations which do not conform to a security boundary, performing reward attribution on contributions of operation sequence steps, and constructing a digital twin environment; the model performance is improved through interactive calibration of real data and simulation data. According to the substation switching operation risk pre-control method based on deep reinforcement learning, high-precision risk prediction is realized, the early warning time is sufficient, and the operation sequence is optimized, so that the safety of substation switching operation is remarkably improved.

The invention provides a data filling and abnormity monitoring method and system based on multi-task learning, and relates to the technical field of sensor data processing.The method comprises the steps that multiple types of sensor data are integrated and preprocessed, correlation among the multiple types of sensor data is comprehensively analyzed, and a correlation matrix is obtained; the method comprises the following steps: grouping multiple types of sensors, constructing a multi-task learning prediction model based on a correlation matrix, inputting monitoring data of related sensors at corresponding time of a certain measuring point in the trained model to obtain prediction data and simulation data, performing data filling based on the prediction data, and performing anomaly detection based on the simulation data. Through the multi-task learning prediction model, the inherent correlation among multiple types of monitoring data and the correlation of measuring points in time and space can be fully utilized, and the monitoring data prediction and filling precision is improved.

The invention relates to the technical field of scheme evaluation, in particular to a parameterized combination evaluation method, a weather forecast method, equipment, a medium and a product. The parameterization combination evaluation method comprises the steps of obtaining a forecasting mode of a target scene, combining multiple parameterization schemes according to multiple physical processes in a forecasting modulus, obtaining index variables and observation data of the index variables, conducting simulation forecasting on a combination constructed by the parameterization schemes through forecasting mode application, and obtaining corresponding simulation data. The index variables and the data errors of the index variables are fitted to a precision observation model, the precision observation model is analyzed to select a target parameterization combination of the index variables, and an observation result corresponding to the target parameterization combination is an observation result conforming to performance expectation. According to the method, the technical problems that the evaluation result through a single index variable is lack of comprehensiveness and the selected parameterized combination is lack of precision are solved, and the comprehensiveness and the accuracy of the evaluation result are improved.

The invention discloses a deep learning-based less-data small-watershed water level forecasting method. The method comprises the following steps of: acquiring historical hourly rainfall data of a plurality of upstream rainfall stations of a small watershed and historical hourly water level data of a downstream water level station; preprocessing the acquired data, and screening rainfall sessions with the rainfall capacity of over 15mm per hour within 24 hours and corresponding water level data; the method comprises the following steps: performing data enhancement through a double-generation GAN model, generating simulated rainfall data by a first GAN model by taking white noise as input, generating simulated water level data by a second GAN model by taking rainfall data as input, combining historical data and simulated data, performing normalization, and dividing the data into a training set, a verification set and a test set according to a proportion; constructing a CNN-LSTM hybrid prediction model, training the model by taking a Nash coefficient as an optimization target, and verifying the prediction model by adopting a progressive verification strategy; and deploying the model for real-time water level prediction to obtain a water level prediction result. The method can break through the bottleneck of few data, and achieves the high-precision mountain torrent early warning of the small watershed water level.

The invention discloses a lake water level and water surface area conversion method and device. According to the invention, parameter optimization is carried out on an initial lake hydrodynamic model through actually measured water surface data, so that the fitting precision and simulation capability of the model to a lake dynamic change process are improved; the problem of insufficient precision caused by the fact that a traditional water level area conversion method only depends on static topographic data or single water level record is solved; meanwhile, a high-resolution water level-water surface area data set is constructed through space-time alignment of day-by-day water surface area simulation data of day-by-day scale simulation and actually measured water level data, so that a partition regression model is established under different hydrological process conditions, hysteresis and nonlinear characteristics in the water level change process are fully considered, and the accuracy of the water level change process is improved. Therefore, the adaptability and generalization ability of the water level area relation model are improved, and high-precision and two-way conversion between the lake water level and the water surface area under the complex dynamic hydrological condition is achieved.

The invention belongs to the technical field of flight testing, and discloses an aircraft testing method and system for simulating a flight environment, and the method comprises the steps: obtaining design parameters of an aircraft and environment data of a real scene, and constructing a simulation test model; in the simulation test model, generating a simulation scene based on a preset test task; collecting multi-source simulation data of a simulation scene where the virtual object is located; inputting the multi-source simulation data into a pre-constructed state perception prediction model, and predicting the state perception of the virtual object to obtain a state prediction result; the state prediction result is input into a pre-constructed test control model, a navigation control instruction is output, and the virtual object sails along a test track when responding to the navigation control instruction; the test trajectory is generated based on a preset trajectory planning algorithm; and recording test data of the virtual object in the process of sailing along the test track to obtain a simulation test result. The method has the advantages of low test cost, few limited conditions, high controllability and the like.

The invention discloses a method for realizing ocean sound field prediction based on a pre-training optimized physical information neural network, which comprises the following steps of: pre-training: constructing a hypothetical ocean environment, generating simulation data in a sound pressure envelope form by using an acoustic numerical calculation tool, and pre-training the physical information neural network to learn a physical rule of sound field propagation; fine tuning: adjusting an energy scale factor according to the proportion of the sound pressure amplitude of the actual measurement point to the sound pressure amplitude of the pre-trained environment, and performing fine tuning by using the envelope amplitude data of the actual measurement sound field for the pre-trained physical information neural network to obtain an ocean sound field prediction model through a pre-training-fine tuning dual-stage strategy; and ocean sound field prediction: according to the ocean sound field prediction model, obtaining a target position envelope from the to-be-predicted range, and then converting the target position envelope into a sound pressure result to realize ocean sound field prediction. The method can improve the high-frequency sound field modeling precision and training efficiency, and can be widely applied to the fields of ocean sound field modeling, sound source localization and environment inversion.

The invention discloses a product reliability evaluation method and system based on analog simulation, and the method comprises the steps: collecting the monitoring data and related data of a preset product, carrying out the fusion inversion of the related data and the monitoring data, obtaining simulation demand data, taking the environment data as an analog simulation background, and carrying out the simulation of the product. Performing accelerated analog simulation on the power battery system according to the simulation demand data and the analog simulation background to obtain analog data; performing life prediction on the simulation data to obtain simulation life data, performing life monitoring based on the to-be-analyzed data to obtain actual life data, and performing deviation analysis according to the simulation life data and the actual life data to obtain first data; performing aging parameter comparison analysis on the simulation data and the monitoring data to obtain second data, constructing a power battery reliability evaluation model according to the first data and the second data, and outputting an evaluation result.

The invention discloses a deep sea color inversion method fusing satellite radiation simulation under a multi-level sea color background, and the method comprises the steps: carrying out the simulation through employing a simulation algorithm based on an OSOAA radiation transmission model, obtaining simulation data including simulation wave band apparent reflectivity, and constructing a multi-level sea color data set; secondly, constructing a deep sea color inversion network with the orientation and wave band feature joint characterization capability, including a residual network and a binary attention mechanism, and performing sea color inversion based on multi-level sea color data; and finally, evaluating by using a test part of the data set, collecting real satellite remote sensing and sea color data, and testing. According to the method, the problems of low robustness and reliability of deep learning in a complex scene and the like caused by scarcity of current sea color marking data are solved, the problem of end-to-end inversion of sea color parameters such as chlorophyll concentration is solved, and the inversion efficiency is improved.

The invention relates to a profile drifting buoy state monitoring method, which belongs to the technical field of state monitoring, and comprises the following steps: constructing a digital twinborn model of a profile drifting buoy, and updating parameters of the digital twinborn model according to a preset fault type to obtain fault simulation data; segmenting the fault simulation data according to a preset sliding window, and extracting multi-dimensional statistical features; inputting the multi-dimensional statistical features into a multi-layer perceptron for calculation to obtain feature scores, converting the feature scores into probability values through a discrete distribution sampling layer, and screening the probability values through binarization coding according to a preset threshold to obtain screened feature vectors; and inputting the screened feature vectors into the gradient elevator for state monitoring to obtain a state monitoring result, performing adaptive feature screening by using a multi-layer perceptron to avoid limitation of manual feature selection, realizing state monitoring through the gradient elevator, and combining feature selection and classification advantages to obtain a state monitoring result. And the monitoring result has high precision and interpretability.

The invention provides a three-dimensional fault detection self-supervision pre-training method based on a multistage mask auto-encoder, and aims to improve fault detection performance in three-dimensional seismic data analysis through self-supervision learning. Data preprocessing and view generation are carried out on three-dimensional seismic data, small-scale, medium-scale and large-scale sub-volume views are generated, and local features, local and global features and global structure information are concerned respectively. A mask operation is adopted to simulate data missing, a mask view is generated, and a model is forced to reconstruct a missing part through known part information, so that robust feature representation is learned. A mask view is coded and reconstructed through an auto-encoder, the feature extraction capacity is optimized, and then the adaptability of the model to complex seismic data is improved. And finally, through weighted combination multi-scale reconstruction loss and global multi-scale consistency loss calculation, a training process is optimized, so that the model shows excellent performance in a downstream task.

The invention discloses a glacier material balance simulation method and system based on feature interaction, and belongs to the technical field of glacier hydrology and climate change monitoring, and the method comprises the steps: sequentially carrying out the uniform format processing and slope feature enhancement of a multi-source data set of a glacier, and dividing the multi-source data set into a simulation data set and an observation data set; training a model based on a trans-attention Transform encoder framework by using the simulation data set to obtain a pre-training model; when one-glacier-leaving cross validation is carried out on the pre-trained model, multi-stage fine tuning training is carried out by using the observation data set to obtain a plurality of fine-tuned models; performing model integration based on performance index screening on the fine-tuned models, and constructing an integrated simulation model; and preprocessing the meteorological dynamic characteristics and the static topographic characteristics of the target glacier, inputting the preprocessed meteorological dynamic characteristics and static topographic characteristics into the integrated simulation model, and carrying out glacier material balance simulation to obtain a glacier material balance simulation result. According to the method, the simulation uncertainty is reduced, and the high-precision simulation of the glacier material balance is realized.

The invention relates to the technical field of piano pedal control, in particular to a pedal control method and system, the method is applied to a pedal system, the pedal system comprises an external unit and an additional unit, the external unit comprises an external pedal module, and the additional unit comprises a pedal driving module. The treading driving module is used for treading corresponding piano pedals according to the treading data; the external unit comprises a first external unit; correspondingly, the method comprises the following steps: acquiring a first external data source through a first external unit; generating a first analog signal according to the first external data source by adopting a first screening rule; the method comprises the steps that whether a pedal value is larger than a preset first treading threshold value or not is judged; if yes, identifying the pedal value as a to-be-simulated data source; generating a first analog signal according to the to-be-simulated data source; the first analog signal is transmitted to a treading driving module, and the treading driving module responds to the first analog signal to drive a piano pedal. According to the invention, the efficiency of practicing the pedaling technology by the user can be greatly improved.

The invention discloses a BIM and block chain-based construction whole process quality tracing method and system, and relates to the technical field of building construction quality management. In a material entering stage, material information is collected through the Internet of Things and is associated with a BIM component identifier, and an initial block is generated by using an intelligent contract; in the process execution stage, BIM 4D / 5D simulation data is associated with a construction log, and a Hash chain algorithm is adopted to generate a process block containing IPFS Hash; in the acceptance inspection stage, the consistency of detection results is verified through zero-knowledge proof, and a new block is generated; checking the block data through a consensus mechanism to obtain a complete data set; constructing a graph database index based on the BIM component tree, and generating a chain path graph; responding to a query request, traversing path diagram nodes, comparing hash values and outputting a tracing result; trusted communication, tamper-proof evidence storage and intelligent tracing of data in the whole construction process are achieved, and the accuracy and reliability of project quality management are remarkably improved.

The invention provides a forest degeneration process identification and degeneration degree division method based on a time sequence, and relates to the field of forest resource degeneration restoration. The method comprises the following steps: acquiring surface reflectance data, and calculating an NBR index after preprocessing; fitting an NBR time sequence through a LandTrendr algorithm, and extracting sample place time sequence data based on random sampling and visual interpretation; generating an adversarial network and expanding sample point fitting data into a simulation data set in combination with a self-supervised learning technology; training CNN, random forest and BOSSVS time sequence classification models, and constructing a hybrid classification model through an integrated voting strategy; and identifying a forest degeneration process by using a hybrid classification model, and generating a degeneration degree diagram through reclassification. The method can achieve the efficient recognition of the complex degradation process of the forest region, has good time sequence adaptability and regional applicability, and provides technical support for the monitoring and management of ecological restoration of regional forests.

The invention relates to the technical field of data assimilation processing, in particular to a WRFDA assimilation method, system and device based on GIIRS data. The method comprises the following steps: acquiring GIIRS data, extracting data from the GIIRS data, and merging and checking the data to obtain checked GIIRS observation information; performing deviation correction on the background field data of the numerical weather forecasting mode by using an RTTOV rapid radiation transmission mode to obtain simulation data after stable deviation correction; performing cloud pollution screening on the GIIRS observation information after inspection and the simulation data after deviation correction to obtain GIIRS observation information without cloud pollution; wRFDA numerical assimilation is carried out on the GIIRS observation information without cloud pollution, an initial field file is obtained, and the initial field file is used for adjusting and optimizing an output weather forecast result. According to the method, a more accurate initialization file is obtained, and the simulation accuracy of the typhoon precipitation area is more accurately improved.

The invention discloses a fault intelligent identification method for an electromechanical actuator, and the method comprises the following steps: carrying out the normalization of fault simulation data of the electromechanical actuator, carrying out the slicing processing through a sliding window, and dividing the data into a training data set and a test data set according to a proportion; then, the training data set serves as input of a multi-scale liquid attention convolutional network model, the training data set is subjected to space fault feature extraction through multi-scale convolution, then time sequence fault features are added through a liquid time sequence processing module, meanwhile, a time attention mechanism is introduced to highlight important time steps, and finally, a classification output layer is used for classifying the time sequence fault features. A trained fault intelligent identification model is obtained; and finally, testing the trained fault intelligent identification model by using the test data set to obtain an electromechanical actuator fault intelligent identification result. In addition, the method is simple and easy to implement and suitable for fault feature extraction and recognition of the electromechanical actuator, and recognition accuracy and stability are remarkably improved.

The invention discloses a traffic industry carbon reduction method and system based on multi-Agent-SD decision model simulation, and relates to the technical field of urban traffic, and the method comprises the steps: obtaining a historical data set of the traffic industry in a to-be-researched region; processing the historical data set, and dividing the historical data set into a training data set and an inspection data set; constructing a multi-Agents-SD decision model, performing comparative analysis on simulation data simulated by the training data set and the test data set, and calibrating parameters of the multi-Agents-SD decision model; corresponding parameters are designed according to different development situations, the adjusted parameters are input into the multi-Agent-SD decision model for simulation, a differentiation result is obtained, and then the traffic industry carbon reduction strategy is obtained. According to the method, the advantages of the two models are combined, the multi-Agents model for exploring micro individual behavior changes and the SD model for a macroscopic complex system are combined, and a more suitable traffic carbon reduction scheme is researched from multiple angles.