5results about How to "Filter out noise" patented technology

This invention discloses a power equipment inspection method based on deep learning dual-light feature fusion, comprising: simultaneously acquiring visible light images and infrared thermal imaging images of the power equipment using a binocular acquisition module mounted on an inspection robot; extracting significant straight line features from the two images using a gradient-based edge detection operator, and solving the homography matrix using line segment descriptors and geometric constraints to achieve online spatiotemporal registration without a calibration board; constructing a deep learning-based dual-stream feature extraction network to map the registered infrared image as a spatial attention mask, and performing weighted fusion of the visible light feature map using Hadamard product; finally, outputting equipment category, location, and temperature information based on the fused feature map, and determining faults using a dual threshold of confidence and temperature. This invention effectively solves the problems of texture loss in traditional infrared detection and the failure of visible light nighttime detection, achieving accurate location and diagnosis of power equipment faults.

This invention relates to the fields of geotechnical engineering and intelligent construction technology, specifically to a large-section trenchless tunnel settlement control and optimization system based on interlocking pipe curtain support. The system includes a central processing unit and connected modules for fluid characteristic sensing, transient impedance inversion, working condition judgment, and dual-mode adaptive control. The fluid sensing module periodically executes pulse excitation and collects fluid dynamic responses. The transient impedance inversion module calculates the equivalent sealing stiffness index characterizing the interlocking seal based on a leakage model. The working condition judgment module marks the grouting area as loose or dense by comparing it with a safety threshold. The dual-mode adaptive control module generates instructions accordingly, driving the grouting mechanism to perform pulsed intermittent or quasi-continuous stepped pressurization injection operations. This invention achieves effective control of surface settlement while ensuring that the underground concealed structure is not damaged.

This invention discloses a method and device for detecting material level in a closed silo, relating to the field of industrial automation detection and control technology. It employs a photosensitive level gauge to continuously acquire the original optical feedback signal of the solid material pile within the silo, receiving the light source sensor signal as the original optical feedback signal, forming signal frames in chronological order, with each frame corresponding to the light intensity value at a sampling time. Dynamic baseline tracking is performed on the acquired multiple signal frames, updating the baseline in real time using the weighted moving average of historical signal frames, and extracting the current optical signal trend component. The baseline update rate is automatically adjusted according to the degree of signal fluctuation. A multi-frame fluctuation suppression algorithm determines the deviation between the current signal frame and the baseline, dynamically filtering out instantaneous spikes caused by dust adhesion based on the statistical characteristics of the deviation. This invention significantly improves the detection accuracy, anti-interference capability, and operational reliability of automatic feeding systems for solid materials in kilns, and is suitable for industrial sites with high dust levels, variable light paths, and long operating cycles.

The application provides an overcurrent detection circuit and a clothes processing device, and belongs to the field of home appliance control. A sampling module is connected with an intelligent power module, collects three-phase current signals, and obtains bus detection signals. A signal processing module is connected with the sampling module, compares the bus detection signals with reference voltage signals, obtains a comparison result signal, converts the comparison result signal, and obtains an overcurrent detection signal. The signal processing module is connected with the intelligent power module, and sends the overcurrent detection signal to the intelligent power module. The overcurrent detection is indirectly realized through the circuit, the collected three-phase current signals and the overcurrent detection signal are fully signal-isolated, the isolation between different signal ports of the intelligent power module is realized, and the problem of low overcurrent detection accuracy of the traditional circuit is solved.

This invention discloses an optical hydrophone structure based on Fresnel zone plate sensitization, belonging to the field of underwater acoustic signal detection technology. It includes a single-mode optical fiber, an elastic cylinder, a Fresnel zone plate, and a metal cavity. The single-mode optical fiber is uniformly and tightly wound around the elastic cylinder, which is located inside the metal cavity. One end of the metal cavity has an acoustic wave incident aperture. The Fresnel zone plate is fixed at the acoustic wave incident aperture of the metal cavity and has several concentric acoustic transmission rings and blocking rings. This invention employs the above-mentioned optical hydrophone structure based on Fresnel zone plate sensitization, which is simple in structure, has few components, and low cost. It possesses good water pressure resistance and electromagnetic interference resistance, making it suitable for complex underwater environments such as marine acoustic exploration and underwater weak target monitoring.