7results about How to "Reduce generalization" patented technology

The invention relates to the technical field of fault detection, and discloses a fault detection method and system for a charger, and the method comprises the steps: obtaining the charging state of a battery, and the charging state of the battery comprises the charging current, the charging power, the state of charge, and the temperature of the battery; performing feature extraction on the battery charging state, and constructing a charging feature matrix; inputting the charging characteristic matrix into a battery health prediction model to obtain a battery charging demand prediction value; performing state analysis and calculation according to the battery charging state to obtain a charger state; performing correlation analysis according to the charger state and the battery charging demand prediction value to obtain fault prediction information; and obtaining a charger fault detection result according to the fault prediction information. The method can improve the fault detection efficiency of the charger.

The present invention discloses a visual inspection multi-task learning method based on multimodal prompt collaboration, and uses a multimodal prompt collaborative multi-task learning network as a visual-language model to implement visual inspection multi-task learning. The multimodal prompt collaborative multi-task learning network includes a language prompt encoder and a visual encoder, and the language prompt encoder includes a parallel frozen language encoder and a language encoder; the frozen language encoder is used to ensure that the adjustment of the language encoder is not greater than a threshold limit; the language encoder and the visual encoder use a coupling function to calculate the cosine similarity of the features of the two to measure the similarity of the two tasks, so as to maximize the consistency of the visual and language representations of the task group with high total similarity, and realize efficient joint training of visual inspection multi-task learning. The present invention improves the adjustment effect of the visual inspection multi-task model and ensures the pertinence and generalization of the visual inspection multi-task learning method.

This invention relates to the field of image processing technology, specifically disclosing a zero-shot text attribute graph learning method based on prototype mutual prompting enhancement. The method calculates instance-aware contrast loss and constrains the similarity of the same node's embedding in two views. It performs PCA dimensionality reduction on the token embedding of the LLM, extracts the first P principal components to form an aligned coordinate system C, maps the components to this coordinate system, and calculates the informative-aware contrast loss. It freezes the pre-trained GNN and the LLM backbone network, extracts node structural embeddings Z from the pre-trained GNN, generates K prototype embeddings through K linear projectors, and injects them as soft prompts into the LLM instructions. The LLM outputs K expert prompts. It calculates the weights of each expert prompt through a router model. It freezes the LLM training of related projectors and routers, freezes the GNN training of the LLM prompt adaptation layer, and iterates and optimizes 1-3 times. This method can cover complex cross-modal information in text and images while reducing the accumulation of zero-shot transfer bias.

The application discloses a targeted adversarial attack enhancement method based on channel feature selection, belongs to the technical field of artificial intelligence security, and comprises the following steps: a heat map is calculated through a Grad-CAM algorithm, and a significant region is obtained; the significant region is supplemented to a significant map; a local image is obtained by randomly cutting the significant map; the local image is scaled to the same size as the original image; the original image and the local image are input into a CNN with the same adversarial perturbation; and a channel feature selection method is applied to optimize the adversarial perturbation. The application can improve the transferability of adversarial samples to a greater extent in the case of targeted attack; the application creatively applies model attention to targeted adversarial attack, so that the perturbation learns how to better transfer the significant features of the original image to the target category. The application focuses on improving the transferability of adversarial samples, thereby improving the success rate of black-box attack.

This invention discloses a multi-model fusion method and system for permanent magnet motor fault diagnosis, belonging to the field of permanent magnet motor fault diagnosis technology. It aims to improve the flexibility and adaptability of models in multi-task learning and hierarchical classification by introducing multiple Softmax-layer CNNs and fusing them with multiple models, while effectively solving the problems of weak noise resistance and insufficient generalization ability of single models. Specifically, the technical solution of this invention first collects the vibration and current signals of the faulty permanent magnet motor, then uses Markov transfer fields to adaptively enhance the time-domain signals into images. Using a multi-Softmax-layer CNN and XGboost as base learners and an IWOA-SVM model as the meta-learner, a high-precision fault diagnosis result is finally obtained. This invention combines the advantages of multiple Softmax layers and multi-model fusion, effectively solving the multi-task fault diagnosis problem under complex working conditions, and improving the accuracy, reliability, and adaptability of fault diagnosis.

This invention relates to the field of agricultural environmental monitoring and prediction technology, and discloses a method and system for predicting agricultural non-point source pollution in coastal zones. The method involves acquiring basic data of coastal watersheds; extracting pollutant production and transport factors at the sub-watershed scale, including at least source TP concentration, farmland area ratio, erosion, and distance attenuation factors; obtaining tidal-corrected measured TP flux at the estuary; constructing and training a random forest model based on this data; using SHAP analysis to screen dominant factors; retraining the model based on the dominant factors to obtain a prediction model; inputting dominant raster data; and outputting pollution flux prediction results. This invention provides a method and system for predicting agricultural non-point source pollution in coastal zones, enabling rapid prediction of the risk of agricultural TP non-point source pollution discharge into the sea based on existing shared basic data and supplementary monitoring and sampling data.

The invention relates to the field of industrial wireless network physical layer security, in particular to an industrial mobile device physical layer security authentication method based on a Vision Transform (ViT). The method is suitable for a physical layer authentication problem of wireless equipment in an industrial scene, and comprises three stages of data preprocessing, offline training and online authentication. Specifically, in the data preprocessing stage, channel impulse response is converted into channel frequency response (CFR), then CFR samples are converted into double-channel CFR images, request positions are spliced into position vectors, and finally the double-channel CFR images, the position vectors and corresponding sample labels form labeled training samples; in the off-line training stage, the labeled training samples constructed in the data preprocessing stage are used for carrying out supervised learning training on the designed deep neural network (DNN) model; and in the online authentication stage, acquiring an authentication request signal in real time, and judging the legality of authentication request equipment according to the trained DNN model.