25results about How to "Avoid Gradient Explosion" patented technology

The invention discloses a T-S fuzzy and TD3-based slow dynamic unknown coal-fired power generation system coordination control method, which comprises the following steps: firstly, decomposing a coal-fired power generation system into a fast subsystem and a slow subsystem by using a singular perturbation theory, and decomposing an original control task into a stabilization task of the fast subsystem and a tracking task of the slow subsystem; for the fast subsystem, a fuzzy set is selected on a definition domain of the fast subsystem by using the slow variation characteristic of steam pressure, and a T-S fuzzy model is constructed; a fast subsystem controller is obtained by solving algebraic Riccati equations corresponding to a plurality of linear systems. For a slow subsystem, a double-Q network is adopted to reduce overestimation of a Q value, a dynamic learning rate and a batch size adjustment mechanism are introduced to accelerate training convergence, and learning is carried out under a TD3 algorithm framework to obtain control input of the slow subsystem. The fast subsystem and the slow subsystem control inputs to be combined and then act on the original system to obtain state information at the next moment, and the intelligent agent interacts with the original system to complete collaborative optimization.

The invention discloses an urban road network traffic state prediction method and device, equipment and a medium, and relates to the technical field of traffic, and the method comprises the steps: obtaining the basic parameters of a target urban region and the target traffic state data of a historical time period; determining road network density data according to the basic parameters of the target city area by using a road network density calculation formula; inputting the target traffic state data of the historical time period into the trained dynamic space-time residual convolutional neural network model to obtain traffic state prediction data of the next time period of the historical time period; the dynamic space-time residual convolutional neural network model comprises a residual convolution module, a dynamic convolution module based on road network density, a space-time attention mechanism module and a fusion module which are connected in sequence; and the weight corresponding to each dynamic convolution kernel in the dynamic convolution module based on the road network density is adjusted according to the road network density data. The prediction efficiency and accuracy are improved.

The invention relates to the field of image recognition or understanding, in particular to a face and tongue coat recognition and tea drink recommendation method and system based on artificial intelligence. The method comprises the following steps: identifying a plurality of image annotation labels, training a feature extraction model and a classification model by using the annotated images, obtaining a new image, performing feature extraction by using the trained feature extraction model, and inputting the feature into the trained classification model to obtain a label of the new image. The device is used for applying the method. The existing method and system for identifying the face and the tongue coating of the tea making machine and recommending the tea making have the problem that the identification of a face image and a tongue coating image is not accurate enough. The method for identifying the face and the tongue coating of the tea making machine and recommending the tea making based on the artificial intelligence provided by the invention is accurate in identification of the face image and the tongue coating image.

The invention provides a multi-modal agricultural disease and pest prediction method. The method comprises the following steps: acquiring image data and audio data by using a sensor, respectively preprocessing the image data and the audio data, extracting semantic features of the image data by using a CNN model, extracting MFCC features of the audio data by using a Mel system, and splicing and fusing the semantic features and the MFCC features to obtain fused features; the fusion features are input into a BiLSTM model according to time steps, an output result is obtained through training, the output result is input into a full connection layer for classification, probability distribution of all classes is obtained, a pest and disease damage prediction model is obtained, and a final model is obtained after verification set testing and parameter adjustment and used for prediction. Through feature extraction and fusion of the image and audio data, the BiLSTM model is used to carry out classification prediction on the fusion features, automatic prediction of agricultural diseases and insect pests is realized, and the prediction accuracy is higher on the basis of reducing manpower and time costs.

The invention discloses an attention neural network-based personnel ability automatic evaluation method and system. The method comprises the following steps of: dividing an ability evaluation data set # imgabs0 # into a training set # imgabs1 #, a verification set # imgabs2 # and a test set # imgabs3 #; setting a plurality of different neural network configurations to form a configuration set # imgabs4 #; the obtained hyper-parameter # imgabs5 # is selected, and a neural network model # imgabs6 # is initialized; using a training set # imgabs7 # to train a neural network model # imgabs8 # obtained through initialization; after a # imgabs9 # round is carried out, the neural network model trained in the # imgabs10 # round is recorded as # imgabs11 #, a verification set # imgabs12 # is used for evaluating the trained model, and the neural network model and the evaluation result after each round of training are stored; the model obtaining the highest evaluation index on the verification set in N rounds is selected to be tested and stored on a test set # imgabs13 #; and until all hyper-parameters are used for initializing the neural network models and tested by a test set # imgabs14 #, deploying the neural network model with the highest model evaluation result for personnel ability grade evaluation work. And the requirement on multi-dimensional personnel ability portraits in a personnel evaluation scene is met.

The invention discloses a gastrointestinal tract image classification method based on an improved Adam optimization algorithm, and belongs to the technical field of medical image processing. The method comprises the following steps: a data preprocessing module for acquiring gastrointestinal tract image data for preprocessing, constructing a data set, and randomly dividing the preprocessed gastrointestinal tract image into a training set and a test set; the feature extraction module is used for extracting key features from the preprocessed image; the image classification module is used for classifying the images subjected to feature extraction by adopting an improved Adam algorithm (AdaWAGC algorithm); the result output module is used for displaying an image classification result; and the evaluation module is used for evaluating the classification result. By adopting the method to classify the gastrointestinal tract image, the accuracy and efficiency of gastrointestinal tract image recognition can be improved.

The invention discloses a CNN-LSTM-based high-voltage user power consumption data prediction method, which takes high-voltage user power consumption data as a research object, cleans historical power consumption data of high-voltage users by using an LOF method, removes unreasonable outlier data, and reduces the influence of the outlier data on the performance of a prediction model. Through data classification and feature engineering, original data are converted into a more representative feature set, which is convenient for model learning. And the volatility of the data is reduced through data normalization, so that the stability and convergence speed of model training are improved. And then constructing a CNN-LSTM hybrid model, that is, adding a convolutional neural network CNN on the basis of a long short-term memory network LSTM. The hybrid model is composed of a CNN part and an LSTM part, the CNN part is used for extracting local features of data, the LSTM part is used for capturing a dependency relationship of a time sequence, and then more accurate power consumption prediction is carried out. After the construction and training of the model are completed, the prediction result of the model is effectively and intuitively evaluated through a mean square error and a graphical method.

The application discloses a kind of physical constraint under aero-magnetic data deep learning forward and inversion method and system. Including: constructing the forward network based on deep operator network DeepONet, the network adopts logarithm-linear dual space mechanism, to log resistivity profile and flight height as input, predicts log quadratic field;Inversion network is constructed, with the input of observed transient electromagnetic response and flight height, and the output of resistivity profile;When training, the forward network is pre-trained to convergence under data-driven loss and Maxwell equation physical constraint loss;Inversion network is trained under the joint supervision of its model space loss and physical data space loss, wherein the physical data space loss is obtained by comparing the re-synthesized response with the original observation after inputting the resistivity profile predicted by the inversion network into the frozen forward network.The application deeply integrates physical laws into data-driven models, and realizes the integrated efficient solution of aero-magnetic forward and inversion.

This design is a multi-task automatic EEG detection and prediction system for epilepsy. The system first receives the EEG signals from epilepsy patients to be identified or the collected patient EEG signals used for training the module through a preprocessing module. The preprocessing module performs noise reduction, filtering, segmentation, and normalization on the signals, and outputs the processed patient EEG signals to the training module. In the training module, the collected patient EEG signals are used for training and testing. First, feature extraction is performed using a multi-scale convolutional network. Then, the detection and prediction branches incorporating a dual attention mechanism are trained, and the trained model parameters are saved for use in the detection and prediction module. Finally, the detection and prediction module provides detection and prediction results for the EEG signals from epilepsy patients to be identified. This invention employs a modular design, achieving real-time detection and prediction of noisy, unbalanced EEG signals, providing a reliable system for practical applications.

The present invention relates to the field of smart contract security, and discloses a smart contract vulnerability detection method based on artificial intelligence, which aims to reduce the false alarm rate of smart contract vulnerability detection. The method comprises: obtaining an unlabeled smart contract data set; obtaining a labeled smart contract data set according to the smart contract vulnerability type; converting the smart contract bytecode in the smart contract data set into an operation code sequence, and using the operation code sequence as a training sample, including an unlabeled sample and a labeled sample; a smart contract vulnerability detection model comprises a pre-trained model and a vulnerability classification model; training the pre-trained model with the unlabeled training samples and training the smart contract vulnerability detection model with the labeled training samples to obtain a trained smart contract vulnerability detection model; converting the smart contract to be detected into an operation code sequence, and inputting it into the trained smart contract vulnerability detection model to obtain a vulnerability detection result corresponding to the smart contract.

The application discloses a secure communication trajectory planning method for unmanned aerial vehicles with integrated control of an adaptive antenna, constructs an air-ground secure communication model containing rigid body dynamics constraints, and determines that the attitude of the unmanned aerial vehicle body is uniquely determined by the translational acceleration vector and the gravity acceleration; for horizontal-horizontal (HH) and vertical-vertical (VV) two kinds of airborne antenna configurations, an explicit coupling model of the antenna gain with respect to the acceleration is established; a non-convex trajectory optimization problem is constructed to maximize the average secrecy capacity; a sequential convex approximation combined with a convex difference programming strategy is adopted for solving, wherein the implicit function differentiation method is adopted to solve the gradient singularity problem of the VV antenna null point; and finally, a flight strategy containing an optimal acceleration sequence is output. The application utilizes the active change of the flight attitude of the unmanned aerial vehicle to realize mechanical beamforming, significantly improves the secrecy capacity through "active drift" or "null alignment" maneuvering, and the generated trajectory strictly satisfies the physical feasibility.

This invention discloses a method for constructing a road cavity detection model based on 3D ground-penetrating radar (GPR). The method includes constructing a hybrid spatiotemporal detection model, which comprises a feature preprocessing module, a soft clipping module, a spatiotemporal feature extraction module, and an output module. The feature preprocessing module performs feature pre-extraction on preprocessed and labeled data, outputting a pre-extracted feature map. The soft clipping module performs spatiotemporal perception on the pre-extracted feature map, outputting a clipped feature map. The spatiotemporal feature extraction module analyzes the clipped feature map, outputting feature information with global spatiotemporal information. The output module integrates the feature information and predicts the existence of cavities and the range of their occurrence channels. By combining the correlations between data in the spatiotemporal dimension, it accurately detects underground cavities, solving the problems of high computational load and difficulty in adjusting model parameters in existing 3D GPR high-resolution data interpretation. This provides an efficient and reliable technical solution for intelligent road cavity detection and infrastructure safety maintenance.

The invention provides a multi-beam synthesis method and device based on a collaborative null generation strategy, and belongs to the technical field of antenna design. The method provided by the invention comprises the following steps: randomly generating a design index in a beam direction range, and constructing a mask matrix based on the design index; constructing a multi-beam comprehensive model, inputting the mask matrix into the multi-beam comprehensive model, and training the multi-beam comprehensive model to output amplitude excitation and phase excitation of each beam; constructing a target mask matrix according to beam performance indexes in an actual application scene; and inputting the target mask matrix into a trained multi-beam comprehensive model, outputting amplitude excitation and phase excitation of each array unit for different beams, loading the amplitude excitation and the phase excitation to a multi-beam phased array, and generating a multi-beam far-field directional diagram. The invention provides a multi-beam synthesis method and device based on a collaborative null generation strategy. The method and the device are used for reducing the loss of equivalent omnidirectional radiation power on the premise of effectively suppressing multi-beam interference.

The invention discloses an intelligent network attack detection method based on traffic analysis and electronic equipment. The method comprises the following steps: acquiring traffic data in a network; a pre-trained automatic encoder AE is constructed, the automatic encoder AE comprises an encoder module, a potential space and a decoder module, the encoder module adopts two layers of long short-term memory networks, and a Dropout layer is inserted between the two layers of long short-term memory networks and is used for receiving input traffic data and performing data compression and feature extraction to obtain key traffic features; and the potential space adopts a bidirectional gating circulation unit to carry out key traffic feature classification, and outputs a detection result indicating whether the traffic data has an abnormal traffic type or not through a decoder module. According to the method, the important traffic characteristics in the traffic can be fully extracted, and the problems of low detection rate and high false alarm rate caused by solving the problem of data imbalance by using a sampling technology are avoided while data dimension reduction is completed.

The invention discloses a construction method of a generative adversarial network, which comprises the following steps: adopting a basic architecture based on the generative adversarial network GAN, adopting an FPN feature pyramid structure for a generator, and adopting a CNN convolutional neural network structure for a discriminator; adding a self-attention module in each layer of structure of the FPN to obtain an improved generative adversarial network; wherein the self-attention module receives a feature map from the FPN as input, converts the feature map into a query matrix Q, a key value matrix K and a value matrix V in a matrix space, determines weight distribution of the V by calculating similarity between the Q and the K, and obtains output fused with a self-attention feature vector; the deblurred image quality is high, the training efficiency is high, and the training process is stable.

The present invention relates to a universal multi-level fusion attention model for ship detection in SAR images of urban coasts, comprising establishing submodules DFEM, CMAFM and SMAFM. Firstly, DFEM is designed to extract rich features with different resolutions and semantic information for multi-scale ship detection; then CMAFM and SMAFM are designed to fuse channel attention blocks and spatial attention blocks on feature maps of different levels to better learn dependent features from channel and spatial dimensions to enhance feature representation; finally, the fused feature maps are input into an existing ship detection network to obtain detection results; the model can focus on more important part of the input image, enhance the position information of the ship, weaken unimportant feature information, improve model performance through a small number of additional parameters, and improve the accuracy of identifying large and small ships under the complex urban coast background.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training diffusion neural networks using differentiatable reward functions.

This invention discloses a multi-level land resource segmentation migration fine-tuning method with input alignment, comprising the following steps: acquisition and processing of remote sensing image data and label data related to the land resource segmentation task; selection and slicing of sampling areas based on prior knowledge of the study area; data augmentation to expand the dataset and pixel value normalization; partitioning the model dataset using stratified sampling techniques; determining the optimal initial learning rate through hyperparameter optimization, entering input feature alignment, and establishing a quick connection between the input alignment module and the model output; employing three Transformer architectures and their pre-trained models for land resource segmentation, and optimizing the model training process using gradient-value-constrained gradient clipping and two-stage training strategies; step six: segmentation prediction and visualization. This invention improves the model's training efficiency and segmentation performance, achieving high-precision multi-level land resource segmentation and recognition.

The present application discloses a consulting question optimization method and system based on a large language model prompt engineering, the consulting question optimization method comprising constructing a prompt template for model input reconstruction; obtaining a legal consulting question data set, reconstructing the original questions in the legal consulting question data set using the prompt template to obtain corresponding input data; for each input data, using an existing large model to generate optimization questions, and performing expert judgment and re-optimization to obtain a final optimization question data set; using the generated optimization question data set as fine-tuning data to fine-tune a small base model to obtain a question optimization model; when a user consults on a legal question, optimizing the user's question based on the question optimization model, the present application can utilize the prompt engineering to generate data and construct a question optimization model in a data-scarce scenario, thereby improving the professionalism and accuracy of the user's expression of legal consulting questions.

This invention discloses a recurrent neural network training method and system based on Ising machine optimization, belonging to the field of neural network training technology. The method transforms the weight training task of a recurrent neural network into a quadratic unconstrained binary optimization problem, mapped to an Ising model; it utilizes the physical evolution or annealing process of the Ising machine to obtain the spin configuration of the minimum energy state; finally, it decodes and restores the optimized weights and loads them into the recurrent neural network to complete the training. This invention achieves accurate representation of continuous weights through binary discrete encoding and offset matrices, supporting accelerated solutions using various Ising machine hardware (such as optical Ising machines, quantum annealing machines, etc.). Compared with existing gradient-based training methods, this invention completely avoids the gradient vanishing and gradient exploding problems, significantly improving the stability and accuracy of long sequence predictions. Simultaneously, based on advanced Ising machine computing equipment, the core training time can be shortened from seconds to milliseconds, providing a new technical path for efficient, low-power AI systems.

The application discloses a kind of based on sub-domain self-adaptive multi-channel synthetic aperture radar moving target detection method, obtains the simulation and measured data of multi-channel synthetic aperture radar, makes network training and verification dataset, adds label for clutter and moving target;Subdomain self-adaptive residual network for ground moving target detection is built;The network training and verification data are preprocessed, input into subdomain self-adaptive residual network, save the optimal network after training ends;The radar data to be measured is slid window, and network test dataset is made;The preprocessed network test data are input into the saved network, and the predicted label is obtained;All prediction results are windowed, and the ground moving target detection result is obtained.The application trains network by using labeled simulation data and unlabeled measured data, reduces the difference between simulation and measured data by subdomain self-adaptive, solves the problem of lack of labeled data in the field of radar, and effectively improves the detection performance of ground moving target.

The invention belongs to the technical field of casting production workshop scheduling, and particularly discloses a casting workshop multi-target full-process scheduling method and device, equipment and a storage medium. According to the invention, the deep reinforcement learning environment is established according to the production data and the workshop scheduling task; performing agent training based on the target neural network framework to obtain a process scheduling agent model of the casting enterprise; wherein the target neural network framework comprises an action network and a plurality of evaluation networks; and carrying out multi-target full-process scheduling on the production tasks of the workshops of the casting enterprises according to the scheduling targets of the workshop scheduling tasks based on the process scheduling agent model. Through the above mode, the feature vector generalization deep reinforcement learning algorithm capable of describing the global state of the casting workshop and the casting task is utilized, that is, agent training is performed in a deep reinforcement learning environment, and multi-target full-process scheduling is performed based on the process scheduling agent model, so that the efficiency and accuracy of scheduling the casting workshop can be effectively improved.

The present invention discloses a standard text classification method based on machine learning, which belongs to the field of data recognition technology, including adopting the BERT algorithm based on constrained attention to vectorize the standard text; adopting the generative adversarial network algorithm based on semantic focus to generate samples, thereby realizing the expansion of the standard text data after vectorization; and adopting the neural network algorithm based on perturbation fuzzy fusion to extract features and classify the standard text data after vectorization. The present invention uses an interactive attention mechanism and a dynamic context perception mechanism, so that the model can not only capture the semantic association within the text, but also better understand the relationship between the standard text and the classification task instructions, significantly improving the classification model's ability to understand the context. A generative adversarial network based on semantic focus is used to generate additional sample data, and the semantic quality and consistency of the generated data are ensured through a semantic refocusing mechanism, solving the problem of insufficient samples in the standard text classification task.

The present invention provides a medium- and long-term prediction method and system for photovoltaic power generation, and relates to the technical field of photovoltaic power generation prediction. The present invention first collects photovoltaic power generation historical data including relevant factors affecting photovoltaic power generation according to weather categories, and sorts and screens the relevant factors; then clusters the screened relevant factors to obtain K clustering results, and divides a day into K similar time periods based on the clustering results; then trains a Bi‑LSTM neural network using the relevant factors and photovoltaic power generation historical data corresponding to each similar time period, thereby obtaining K medium- and long-term photovoltaic power generation prediction models; finally, performs medium- and long-term photovoltaic power generation prediction based on the K medium- and long-term photovoltaic power generation prediction models. The present invention realizes high-precision prediction of renewable energy, thereby reducing resource waste in photovoltaic power station operation and maintenance, and reducing power generation losses.

The invention relates to the technical field of image processing, in particular to a tunnel lining defect ground penetrating radar image enhancement method, medium and equipment, and the method comprises the following steps: constructing a data set; constructing a generative adversarial network model based on improved deep convolution; the obtained tunnel lining structure defect ground penetrating radar image data set is used for training in the constructed improved deep convolution-based generative adversarial network model, and hyper-parameters of a generator and a discriminator are continuously adjusted through a test result, so that the adversarial network model is globally optimal; and generating a tunnel lining structure defect ground penetrating radar image by using the improved deep convolution generative adversarial network model. According to the invention, the technical problem that the difference between the image generated by the existing image processing method and the real ground penetrating radar image is large for the ground penetrating radar image of the internal defect of the tunnel lining is solved.