7results about How to "Strong noise" patented technology

This invention discloses a multi-channel electromagnetic induction detection method and system based on uniform magnetic field constraint. A uniform magnetic field is constructed within the detection area of ​​the structure under test. Electromagnetic induction response signals are acquired through multiple channels under the constraint of the uniform magnetic field, and the spatial coordinates of each acquisition channel are marked. The raw electromagnetic induction signals acquired by each channel are preprocessed, including noise reduction filtering, envelope extraction, and amplitude normalization. A deep learning model is then used to extract structural features from the preprocessed multi-channel electromagnetic response signals. Based on the spatial position information of each acquisition channel, magnetic field uniformity parameters, and response characteristics, a channel correlation weight matrix is ​​constructed to describe the spatial consistency and physical coupling relationships between channels. A multi-channel joint optimization model is constructed, and the equivalent electromagnetic parameter distribution inside the structure under test is reconstructed through iterative solution. This invention improves the reliability, repeatability, and engineering applicability of electromagnetic induction detection results.

The application provides a kind of ultra-low noise microphone gain preamplifier circuit, it is related to microphone field, including pickup head, input terminal, JFET buffer module, voltage stabilizing filter module, capacitive coupling module, amplification module and output terminal, the pickup head is connected with the input terminal of input terminal, the output terminal of input terminal is connected with the input terminal of JFET buffer module, the output terminal of JFET buffer module is connected with the input terminal of voltage stabilizing filter module, the input terminal of capacitive coupling module, the output terminal of voltage stabilizing filter module, the output terminal of capacitive coupling module is connected with the input terminal of amplification module respectively, the output terminal of amplification module is connected with the output terminal;The utility model increases amplification module in originally's microphone gain preamplifier circuit, can inhibit power noise intensity by amplification module, improve common-mode rejection ratio, strong anti-interference ability, distortion THD is small, and noise processing effect is good.

A method for dynamic adjustment of frequency locking feedback phase in strong interference is disclosed, which comprises the following steps: scanning laser frequency by modulating driving current of semiconductor laser, collecting transmission cavity mode signal of optical resonant cavity by photoelectric detector, obtaining error signal for controlling feedback phase based on asymmetry and amplitude of transmission cavity mode signal, amplifying error signal by high voltage amplifier and then applying it to piezoelectric ceramic material with mirror adhered, controlling expansion and contraction of piezoelectric ceramic, and realizing dynamic adjustment of feedback phase. The method has very wide phase adjustment range based on asymmetry and amplitude of transmission cavity mode signal, and can realize stability of feedback system even in harsh environment.

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.

The invention relates to the technical field of three-dimensional point cloud data processing, and discloses a three-dimensional point cloud classification segmentation method based on geometric perception fitting convolution, and the method comprises the following specific steps: S1, selecting a public data set, reading point cloud coordinates, labels and RGB information, dividing a point cloud into a plurality of local fields, and extracting the initial features of the point cloud; s2, a bidirectional geometric normalization pooling module is adopted, and non-uniform point cloud density and feature difference are relieved through forward and reverse two-dimensional normalization and adaptive aggregation; s3, designing a fitting convolution module based on Taylor expansion, enhancing geometric expression ability and structural robustness of the features, processing the features by the module, constructing a segmentation model, and extracting feature representation fusing local geometry and global context; and S4, classifying and segmenting the point cloud data based on the output features generated by the network model, so that a local geometric structure and a neighborhood change rule can be more fully described while the calculation efficiency is maintained, and a more accurate three-dimensional point cloud classification and segmentation result is realized.

This invention discloses an image structured representation method based on adaptive multi-granularity sphere computation, comprising: S1: preprocessing the input image and calculating the gradient of the entire image; S2: selecting the pixel with the smallest gradient intensity from the unvisited pixel set as the center point of the current sphere rectangle; S3: starting from the center point, iteratively expanding the rectangular region in the horizontal and vertical directions, calculating the purity value of the rectangular region after each expansion, stopping the expansion when the purity reaches a preset threshold, and confirming the current rectangular region as a sphere rectangle; S4: repeating the above process until all pixels are covered, obtaining an adaptive multi-granularity sphere rectangle set; S5: using each sphere rectangle as a region unit, establishing region relationship connections based on the relationships between different sphere rectangles to obtain the region relationship structure or graph structure corresponding to the image. This method has the advantages of good adaptability, high computational efficiency, strong robustness, and good interpretability.

The invention discloses a novel power system-oriented regional load uncertainty perception modeling and prediction method, and particularly relates to the technical field of load prediction. According to the method, a three-level structured influence factor system and an influence relation model are constructed based on distributed new energy output characteristics, charging and discharging states of an energy storage device and charging behaviors of an electric vehicle, and a load uncertainty influence factor characteristic library is formed; then, a multi-scale feature representation library is generated by extracting distribution features, fluctuation features and time sequence response features; a Bayesian long-short-term memory network is combined with an attention mechanism to serve as a basic framework, and a regional load uncertainty perception model is constructed through scene disturbance training, noise enhancement training and multi-target optimization training; and finally, reasoning and outputting a load distribution range, a confidence interval and a fluctuation trend through the model. According to the method, multi-dimensional and precise representation and prediction of regional load uncertainty are realized, and reliable data support is provided for scheduling decisions of a novel power system.