137results about How to "Reduce overfitting" patented technology

The invention discloses a rolled metal surface defect automatic labeling method based on a multi-task self-adaptive model, which comprises the following steps: S1, collecting a rolled metal surface image, preprocessing and enhancing the rolled metal surface image, performing data labeling, and constructing a rolled metal surface defect data set; s2, constructing a multi-task adaptive model, and training the multi-task adaptive model by using the data set to obtain an automatic defect labeling model; and S3, inputting a to-be-labeled metal surface image into the defect automatic labeling model, and outputting a surface defect labeling result by executing the target detection task. According to the method, a multi-task learning framework is combined, joint training of target detection and instance segmentation tasks of metal surface defects in the rolling technology is achieved, the target detection task is focused in the reasoning stage, the labeling efficiency is improved, the labor cost is remarkably reduced, and the labeling efficiency is improved. The method can be widely applied to industrial defect detection and data automatic labeling scenes of rolling process metal, and is suitable for defect image automatic labeling tasks in a complex industrial environment.

The invention belongs to the field of fault diagnosis, and particularly relates to a main shaft bending common characteristic diagnosis system based on a stacking integration method, and the system comprises the following modules: a sensor module which is used for collecting a vibration signal of a main shaft in real time; the data acquisition and processing module is used for converting an analog signal into a digital signal and preprocessing the signal acquired by the sensor; the feature extraction module is used for extracting features from the preprocessed vibration signals; the machine learning diagnosis module analyzes and classifies the extracted features by using stack integration based on a plurality of trained machine learning models, and judges the health state of the main shaft; and the output module is used for outputting the diagnosis result and sending out an alarm signal when abnormality is detected. Real-time monitoring and automatic diagnosis of the main shaft bending fault are achieved, compared with a traditional method depending on expert experience and manual detection, the fault detection efficiency and accuracy can be greatly improved, and misjudgment and missed judgment risks caused by human factors are reduced.

The invention relates to the technical field of lithium batteries, and discloses a lithium battery life decline quantitative prediction and health state intelligent evaluation method, which comprises the following steps: S1, multi-source data acquisition: arranging strain gauge sensors at battery electrode plates and a shell to acquire stress-strain data, integrating a gas sensor in a battery module to acquire gas data, and calculating the data of the stress-strain data; battery data and environment data are acquired by a high-precision synchronous acquisition system through nanosecond clock signals and are processed and stored, and the data quality is monitored at the same time; s2, data preprocessing: generating an extended data set through data transformation and combination and GAN-based data, and processing abnormal data by using a method based on statistics and machine learning; according to the invention, through multi-source data fusion acquisition, a stress-strain sensor and a plurality of gas sensors are added to monitor the internal mechanical change and gas component concentration of the battery, so that the problem that the accuracy and practicability of the model are greatly reduced due to a traditional method based on an electrochemical model is improved.

The invention provides a relation extraction model construction method and system based on semantic enhancement and knowledge distillation, relates to the technical field of relation extraction, and aims to solve the problem that in the prior art, when continuous learning is processed, a model is often difficult to keep memorizing an old relation when a new relation is learned, and forgetting is caused. Model overfitting is easily caused by excessive dependence on a small amount of data, so that a new relationship cannot be effectively generalized. The method comprises the steps of obtaining a relationship prototype of a training sample and a typical sample, performing semantic enhancement on the relationship prototype to obtain an expanded enhanced data set and an enhanced memory set, and performing feature extraction, relationship classification prediction and relationship extraction based on a student model and a multi-teacher model. According to the method, the overfitting problem caused by scarcity of small sample data is effectively relieved through a semantic enhancement technology, old relation forgetting caused by new relation learning in the continuous learning process is reduced through a multi-teacher knowledge distillation method, and the classification accuracy and generalization ability of the model facing different relations are improved.

The invention discloses an urban underground space structure health detection method and detection system, and the method comprises the steps: S1, collecting the multi-modal data of an underground space structure through the deployment of diversified sensors; s2, preprocessing the collected data, wherein the preprocessing comprises filtering denoising and feature extraction; s3, performing pattern recognition and health state evaluation on the processed data by using a deep learning model; s4, dynamically adjusting a threshold value of health assessment according to the environmental parameters, and predicting a future health trend; and S5, the evaluation result is displayed through a visual platform, a corresponding health examination report is generated, the health condition of the underground space structure can be monitored in real time by integrating multiple sensors and utilizing a data processing technology, potential problems can be found in time, an early warning threshold value can be dynamically adjusted according to real-time monitoring data through a dynamic threshold value adjusting mechanism, and the early warning efficiency is improved. The problems of false alarm and missing alarm caused by a fixed threshold value are avoided, and the accuracy and reliability of early warning are improved. The method is suitable for various underground space structures.

The invention discloses a semi-supervised seismic wave impedance inversion method and system based on Swin Transform iterative gradient correction, and belongs to the technical field of earthquakes in geophysical exploration. According to the method, the impedance gradient is iteratively corrected in the model space through the deep neural network, and complex nonlinear prior information is captured; and each anisotropic structure direction regularization item is established, and constraint is carried out along the direction of the stratum structure, so that the space consistency of the prediction result is ensured. Meanwhile, the USTNet network designed by the invention combines the advantages of the local feature capture capability of the convolutional neural network and the global modeling capability of Transform, and reduces the non-uniqueness of solutions. The network is used for inverting synthetic data and actual data, and the effectiveness of the method is verified.

The invention relates to the technical field of battery management, and discloses a lithium battery thermal runaway feature recognition algorithm based on a BP neural network, and the algorithm comprises the following steps: data collection and preprocessing: employing a temperature sensor and a gas sensor to monitor the temperature and gas information of a lithium battery system in real time; the temperature change of the temperature sensor before and after the thermal runaway and the temperature change slope at the moment of the thermal runaway event are used as main characteristic parameters; for a gas sensor, gas concentration change before and after thermal runaway and gas concentration change slope are considered as main characteristic parameters; and taking the collected temperature, gas data and characteristic parameters as a data set. According to the invention, the temperature and gas changes of the lithium battery are monitored in real time through the temperature sensor and the gas sensor, the characteristics of thermal runaway can be quickly identified, and early warning can be timely given out, so that the real-time monitoring capability of the system is improved, and the accuracy and timeliness of thermal runaway prediction are enhanced.

The invention provides a Chinese electronic medical record named entity recognition method based on a multi-head attention mechanism and a pulse neural network (SNN), and the method comprises the steps: obtaining a dynamic word vector through a pre-training BERT model, obtaining a text code through a bidirectional long short-term memory network (BiLSTM) model, and screening the features of the code through the SNN network for a named entity in an electronic medical record; the multi-head attention mechanism calculates the dependency relationship between characters, enhances the relevance to the context, and finally outputs a final sequence through a conditional random field (CRF) module to obtain an entity recognition result. According to the method, the time cost is remarkably reduced, the efficiency and precision of identifying the named entities in the medical text are improved, and a more efficient and accurate technical solution is provided for the field of medical information processing.

The invention relates to the technical field of breach image processing, in particular to a breach rapid situation awareness method and system based on multi-source data. The method comprises the following steps: acquiring dam monitoring station data; performing hydrological sensor network setting on the dam monitoring station data to obtain dam hydrological sensor network data; performing ultrasonic water level change trend analysis on the dam hydrological sensor network data to generate an ultrasonic water level change trend chart; performing breach node sensing on the dam hydrological sensor network data according to the ultrasonic water level change trend chart to generate breach node data and breach prediction node data; and according to the breach node data, macroscopic disaster risk analysis is carried out on the breach area, and a breach area macroscopic disaster risk schematic diagram is generated. According to the invention, through real-time data integration, comprehensive risk assessment, unmanned aerial vehicle monitoring, dynamic prediction model and multi-party cooperative response, the accuracy and response speed of breach rapid situation awareness are improved.

The invention relates to an underwater acoustic target recognition system and method based on multi-modal depth feature fusion, and belongs to the field of underwater acoustic target recognition. The method comprises the following steps: firstly, performing preprocessing on an obtained underwater acoustic target original audio and associated metadata, and constructing a multi-modal data set; and then the constructed multi-modal sample is input into an identification model, the model extracts deep representation of each modal through a multi-branch feature coding network, depth alignment and complementary aggregation of different modal features are realized by using a cross-modal cross attention mechanism guided by potential query, and a target identification result is output based on a decision network of mixed experts. According to the method, experimental verification is carried out on two disclosed underwater acoustic data sets, the experimental result verifies the effectiveness of the multi-modal deep fusion and hybrid expert adaptive decision strategy adopted by the method, and through mining the complementary advantages of acoustic features and semantic priori, the multi-modal deep fusion and hybrid expert adaptive decision strategy is obtained. And the robustness and generalization ability of the underwater acoustic target recognition system in the strong-noise and multi-working-condition environment are remarkably improved.

The invention discloses a charger communication test method and system, a storage medium and a program product, and the method comprises the steps: obtaining a state parameter of a to-be-tested charger; collecting a communication message of the charger to be tested, and constructing a message time sequence queue; generating a message interval sequence reflecting the time sequence characteristics of the message; calculating a discrete degree coefficient of a message time sequence according to the message interval sequence; recording record data at an abnormal moment when the communication abnormality occurs, and inputting the record data into a preset state transition matrix to obtain a corresponding relationship; calculating probability distribution of communication abnormity under different state parameters to obtain a correlation model; generating a message sequence for testing based on the association model, wherein the time sequence characteristic of the message sequence for testing is the same as the state parameter and the dispersion degree coefficient corresponding to the high-probability abnormal scene of which the probability is greater than a preset probability threshold in the association model; and sending the test message sequence to the to-be-tested charger to detect response data of the to-be-tested charger. And the accuracy and efficiency of the communication test of the charger are improved.

The invention relates to a lightweight electrical equipment multi-target detection method and system, and the method comprises the steps: collecting multi-angle images of different types of electrical equipment, obtaining an experiment data set, constructing a Ghostnet lightweight network structure, introducing a CBAM attention mechanism and an SPPFCSPC convolution structure to improve a YOLOv8 model, and obtaining a multi-target detection model based on the improved YOLOv8 model. And training, verifying and evaluating the multi-target detection model based on the improved YOLOv8 model to obtain a multi-target detection optimal model for electrical equipment multi-target detection. According to the method and the system, the model complexity and the calculation amount can be reduced while the detection precision is ensured, and an effective solution is provided for multi-target identification detection of lightweight electrical equipment.

The invention provides an end-to-end automatic driving system and method. The system comprises an environment sensing module, a feature extraction module, a data fusion module, a decision generation model module and a decision analysis module. The environment sensing module comprises a plurality of types of sensors, and each sensor collects environment information data of different modes. The feature extraction module extracts features of each modal environment information data. And the data fusion module fuses the features of the modal environment information data to obtain fused features. The decision generation model module determines a driving decision by using a trained decision generation model based on the fusion features. And the decision analysis module converts the driving decision output by the decision generation model module into a specific vehicle control instruction. The method has higher adaptability to complex and dynamic driving scenes, reduces the cost of data annotation during training, and improves the generalization ability of the model in various driving scenes.

The invention is suitable for the technical field of medical image segmentation, and provides a semi-supervised segmentation method based on multi-modal teacher-student consistency learning, which comprises the following steps: constructing a teacher-double student model framework which comprises a multi-modal teacher model and two independent single-modal student models with different learning conditions, the two student models use segmentation networks of the same structure to respectively process images of two different modalities; in the data input and training stage, data with labels train a student model through real labels, and data without labels are trained through false labels generated by a teacher model; in the training process, the consistency prediction between the teacher model and the student model and between the two student models is ensured. According to the method, the problem of overfitting caused by insufficient annotation data is effectively relieved. In an actual medical scene with limited annotation data, the method can achieve a reliable segmentation result only by means of fewer labels, so as to relieve the pressure of medical conditions.

The invention provides a small sample image classification method fusing global and adaptive local information, and relates to the technical field of image processing, and the method comprises the steps: S1, obtaining small sample images to establish a data set, and dividing the data set into a support set and a query set; s2, inputting the data set into a global sensing network DCCP-Net for pre-training; s3, inputting the support set and the query set into a task aware network QSA-TAN for meta-training; s4, inputting a pre-training result and a meta-training result into a global-local knowledge collaborative network GLKC for joint training to output probability distribution differences of the small sample images, and classifying the small sample images according to the probability distribution differences to obtain a classification result; according to the method, through collaborative optimization of knowledge in the global data space and the local task space, image characteristics and category information to which the images belong can be better highlighted, generalization of a small sample image classification model is remarkably improved, and therefore the intra-class change problem of the images is effectively solved.

The embodiment of the invention provides a time sequence prediction method and device, equipment and a medium, and the method specifically comprises the steps: decomposing historical time sequence data, so as to obtain k components corresponding to the historical time sequence data; determining an error evaluation index of the ith component corresponding to the historical time sequence data under the jth neural network; selecting the neural network with the minimum error evaluation index from the M neural networks as a target neural network corresponding to the ith component; according to the data of the ith component in the historical time sequence data, performing optimization processing on the hyper-parameter of the target neural network; determining component prediction results respectively corresponding to k components of the to-be-predicted time sequence data by using the trained target neural network; and reconstructing the component prediction results corresponding to the k components to obtain a prediction result corresponding to the to-be-predicted time sequence data. According to the embodiment of the invention, the accuracy and reliability of time sequence prediction can be improved.

The invention belongs to the technical field of computer-aided diagnosis, and particularly relates to a dynamic brain network feature learning method based on Mamba, which comprises the following steps of: performing data processing, including data collection, data preprocessing, dynamic function network sequence construction and state conversion sequence construction; performing sample enhancement by taking the processed data as sample data; constructing a Mama model comprising a linear embedding layer, a Mama layer, a linear mapping layer I, an activation function and a loss function as a classification model; training the Mama model by using the state conversion sequence, and optimizing hyper-parameters of the Mama model; and based on the trained Mama model, predicting the enhanced sample data, and determining a classification result of the sample data through a label output by the Mama model. According to the method, the relation hidden in the dynamic brain network state transition sequence can be efficiently captured, and high-precision classification of each brain network sequence is realized.

The invention relates to the technical field of climate event simulation, in particular to an optimization method of climate mode simulation composite extreme wind and rain event frequency based on deep learning, and the method comprises the following steps: obtaining observation data of rainfall and wind speed of a target area and simulation data of a plurality of climate modes; calculating rainfall and wind speed thresholds by adopting a percentile threshold method, and determining the occurrence frequency of a composite extreme wind and rain event; evaluating a climate mode simulation result by using the observation data, selecting the frequency as a characteristic value of the deep learning model, and using the observation frequency as a true value; constructing a multi-layer perceptron neural network, and optimizing model training by fusing a mean square error, a standard deviation ratio and a weighted loss function constrained by a minimum value; and inputting the simulation result of the climate mode into the trained model, and generating the correction result of the composite extreme wind and rain event frequency, thereby improving the simulation precision of the composite extreme wind and rain event frequency, effectively reducing the deviation, and providing support for disaster estimation and decision-making under the climate change background.

The invention provides a tunnel disease monitoring data enhancement method and system based on CTGAN, and relates to the technical field of data enhancement, and the method comprises the steps: carrying out the disease type marking and disease feature preprocessing of a real data table of a tunnel site disease; extracting time sequence features and spatial position features from the preprocessed disease features; taking the time sequence features, the spatial position features and the disease types as conditional information to train a CTGAN, and using the CTGAN to generate synthetic data having similar distribution with the preprocessed real data table to obtain a new sample data table; after the new sample data table is generated, verifying a synthesis effect by adopting a mode of combining a statistical method and a support vector machine; according to the method, the confrontation network is generated by using the condition table, tunnel disease monitoring data is supplemented and optimized based on a real data table of tunnel field diseases, the problems of data scarcity and category imbalance are solved, and the training effect of a machine learning model is improved.

The invention relates to a place name recognition method and device, equipment, a storage medium and a program product, and relates to the technical field of natural language processing. By adopting the method, the problems of overfitting and knowledge forgetting can be relieved. The method comprises the following steps: performing format conversion on obtained initial training data to obtain current training data consisting of a text to be extracted and an extracted place name; querying a plurality of synonyms corresponding to the extracted place names, and performing data enhancement on the current training data based on the plurality of synonyms to obtain a target training data set; constructing an auxiliary classification task according to the plurality of synonyms, the negative examples and the classification loss; based on the target training data set and the auxiliary classification task, training the initial model until model parameters of the initial model are the same as target parameters, and obtaining a preliminary training model; obtaining model fine tuning loss, and adjusting the preliminary training model according to the model fine tuning loss to obtain a pre-training model; the pre-training model is used for place name identification.

The invention discloses a cumulonimbus radar echo image prediction method, and relates to the technical field of image processing. The method comprises the following steps of: constructing an AkEformer model, namely constructing an encoder-decoder backbone network structure on the basis of TrajGRU (TrajGRU); constructing an adjustable kernel convolution layer by adopting an AKConv mechanism, and performing feature extraction; the method comprises the following steps of: integrating an efficient attention mechanism in a Transform framework to generate a feature fusion structure layer based on an Officient Transform; obtaining a radar echo image of cumulonimbus; and inputting the radar echo image into the AkEform model and obtaining the predicted distribution condition of the cumulonage cloud. According to the invention, a new model AkEform is designed; distribution of cumulonage clouds can be predicted according to radar echo signals; physical priori knowledge is incorporated into model design, so that the accuracy of cumulonage cloud prediction is greatly improved, and accurate prediction is realized.

The invention discloses a rusted high-strength bolt connection pretightening force intelligent self-optimization prediction method and system, and belongs to the technical field of bolt pretightening force detection.The method specifically comprises the steps that a finite element database of bolt connection pretightening force loss is established, and a machine learning prediction model based on a neural network is trained; when the recognition accuracy of the machine learning prediction model reaches a preset value, pre-tightening force loss of the target bolt is monitored in real time, and real-time geometric feature information of connection of the target bolt is obtained; when the similarity between the real-time geometric feature information of the target bolt connection and a finite element model in the finite element database is greater than or equal to a preset value, calling the pre-tightening force loss of the existing finite element database; when the similarity is lower than a preset value, the trained machine learning prediction model is utilized to output actual bolt connection pre-tightening force loss in real time; the bolt looseness detection device realizes automatic and marker-free bolt looseness detection, is high in bolt image acquisition angle and distance tolerance, and can meet bolt looseness detection at different positions.

The invention discloses a coal mine fully-mechanized face production safety identification method, system and device, a medium and a product, and relates to the field of safety monitoring, and the method comprises the steps: obtaining video stream data of coal mining machines at different positions through a plurality of pan-tilt cameras in a fully-mechanized face; the pan-tilt camera is mounted on a hydraulic support of a fully-mechanized face; preprocessing the video stream data; the preprocessing comprises single frame processing, camera distortion correction, image edge blurring processing and batch normalization processing; constructing an identification detection model by using the preprocessed data and adopting a deep learning method; the identification detection model is used for performing target detection on the cutting head of the coal mining machine; according to an identification detection result, coal mine fully-mechanized face production safety identification is carried out; according to the invention, the robustness and accuracy of image recognition detection can be improved in an underground high-dust environment.

The present invention relates to the field of artificial intelligence technology, and discloses a network security situation awareness method based on artificial intelligence, including obtaining network security data; using a fully connected neural network based on dynamic population evolution optimization to extract features from network security data to obtain a first feature; using an autoencoder neural network based on contrast entropy to reduce the first feature to obtain a second feature; using a fractional-order neural network based on complexity perception to construct a classifier model, and using the second feature to train the classifier model; and using the trained classifier model to classify network security situation awareness. The present invention improves the ability to distinguish complex network security situations, can achieve more accurate classification effects, and enhances the applicability of the model in network security data and the accuracy of classification.

The invention discloses a pressure pipeline robot underground water supply pipeline leakage detection method based on a PSO-CNN-LSTM neural network algorithm, and the method comprises the steps: obtaining the monitoring data of a pressure pipeline robot, constructing a pipeline leakage data set, and dividing the pipeline leakage data set into a training set, a verification set and a test set according to a proportion; a PSO-CNN-LSTM model is constructed by using the pipeline leakage data set; a PSO-CNN-LSTM model is initialized, hyper-parameters are set, the training set is imported into the PSO-CNN-LSTM model, and model training is carried out; hyper-parameters are adjusted in sequence, a verification set data test model is introduced, change curves of loss values and accuracy rates of the model under different hyper-parameters are compared, and an optimal model is searched; and according to test set data, testing the optimal model, outputting various numerical evaluation indexes, and judging whether an expected value is reached or not. According to the invention, the leakage point in the pipeline can be accurately detected.

The invention discloses a drilling pump pressure prediction method based on an artificial neural network, and the method comprises the following steps: S1, data collection; s2, data preprocessing; s3, constructing a neural network model; s4, model training and optimization; and S5, model verification and deployment. According to the method, multi-channel data fusion and time synchronization optimization are innovatively adopted, so that the data quality and consistency are improved; in combination with a deep neural network and a self-adaptive optimization strategy, the precision and generalization ability of pump pressure prediction of the drilling pump are improved; and an online updating mechanism is introduced, so that the model can be dynamically optimized according to real-time data, the defects of low prediction precision, poor adaptability and difficulty in real-time updating of a traditional method are overcome, and an efficient and reliable prediction means is provided for intelligent drilling control.

The embodiment of the invention provides a business revenue prediction method and device, electronic equipment and a storage medium, and relates to the technical field of computers, the method comprises the following steps: obtaining a decision tree model and training data for a target business, the training data comprising historical business revenue data and expansion data, obtaining a probability model and a segment loss function aiming at the decision tree model, adjusting and optimizing hyper-parameters of the decision tree model according to the training data, the probability model and the segment loss function to obtain a business income prediction model, and performing weight prediction on the business income prediction model according to the training data and the segment loss function to obtain a business income prediction model; according to the method, the weight coefficients corresponding to the business income prediction models are obtained, then the business income prediction models are fused based on the weight coefficients, and the target fusion model for the target business is obtained, so that the accuracy of model prediction is effectively improved.

The invention belongs to the technical field of computer vision and artificial intelligence, and particularly relates to a deaf-mute gesture recognition method based on a DCGAN-Yolov5 algorithm, and the method comprises the following steps: 1, firstly, making a deaf-mute gesture original data set which comprises different gesture sample pictures of a deaf-mute; 2, expanding the different gesture sample pictures in the step 1 by using DCGAN to obtain a mixed data set; and step 3, performing label labeling operation on the mixed data set obtained in the step 2 to obtain a label corresponding to the mixed data set, and putting the label into a PostgreSQL database. According to the method, an original data set is expanded by adopting a DCGAN (deep convolutional generative adversarial network) model, so that the problem that an identification model is easy to over-fit under the condition of insufficient data volume is effectively solved. By means of the data enhancement technology, the recognition model can learn feature representation with richer samples, and therefore better generalization ability is shown in practical application.

The invention discloses a fine recognition method, device and system for a farmland protection forest, and a medium. The method comprises the following steps: acquiring a prototype network model; performing enhancement processing on the original sample by adopting a data enhancement algorithm to obtain a training sample; integrating the convolution attention module into the prototype network model, and training by adopting a training sample to obtain a farmland protection forest recognition model; migrating the farmland protection forest recognition model to a target domain by adopting a fine tuning migration learning method to obtain a fine recognition model for performing farmland protection forest recognition on the target domain; and inputting the remote sensing image data of the target domain into the fine recognition model, and performing fine recognition on the farmland protection forest according to an output result of the fine recognition model. By adopting the technical scheme, the farmland protection forest can be accurately recognized based on the remote sensing image data, the recognition efficiency of the farmland protection forest is obviously improved while the recognition precision is improved, and favorable data support is provided for agricultural development.

The invention provides an image processing method and device, computer equipment, a storage medium and a program product. The method relates to the technical field of computer vision of artificial intelligence, and comprises the following steps: acquiring sample data which comprises a sample image, a sample category to which the sample image belongs and a sample identifier set for the sample image; calling an image generation model to extract representation information of the sample identifier; calling an image generation model to predict noise added to a noise image corresponding to the sample image based on the representation information of the sample identifier to obtain predicted noise; the noise image is obtained by adding marking noise to the sample image; and according to the difference between the marked noise and the predicted noise and the difference between the semantics of the sample identifier and the semantics of the sample category, updating model parameters of the image generation model so as to train the image generation model. By adopting the embodiment of the invention, the overfitting degree of the image generation model can be reduced, and the training effect of the image generation model is improved.