3results about How to "Achieve lossless" patented technology

The invention discloses a method for detecting potential electric leakage defects of an LED device, and relates to the technical field of semiconductor photoelectric device detection. Aiming at the technical pain point that recessive microdefects (such as a metal migration channel caused by a V-shaped pit and dislocation) cannot be identified by the existing single spectroscopic detection, the invention provides a detection logic of reference parameter acquisition, defect stress excitation, parameter acquisition after excitation and differential analysis and judgment. Specific stress is applied to primarily screened qualified products, ion migration at potential defects is excited in an oriented mode, and hidden electric leakage is dominated. Potential defective products are accurately rejected by calculating parameter drift distances (VFL, IR) before and after stress. The method is not only suitable for interactive screens, but also suitable for high-reliability scenes such as vehicle-mounted display and high-end illumination, and can effectively intercept hidden lamp beads causing'caterpillar 'failure or early light attenuation, thereby remarkably improving the product yield and the terminal reliability.

This invention provides a non-destructive characterization method for hollow anti-resonant optical fibers based on multimodal deep learning. The specific implementation path includes: (1) acquiring microscopic images (image modalities) of the end face of hollow anti-resonant optical fibers covering differentiated microstructures and their corresponding original transmission spectral data to construct a multimodal original sample set; (2) performing feature extraction and standardization processing on the multimodal data; (3) building a cascaded deep learning model integrating a visual feature capture subnetwork and a transmission spectral feature fusion regression subnetwork; (4) implementing joint training, using a convolutional neural network (CNN) to automatically extract the geometric feature parameters of the fiber core and cladding microstructures in the microscopic images, and fusing them with the transmission spectrum features, constructing a mapping relationship through a deep neural network (DNN); (5) inputting the microscopic image and transmission spectral data of the optical fiber under test into the model to achieve non-destructive prediction of loss characteristics. This invention features high characterization accuracy, fast speed, and zero material loss.

This invention relates to the field of identification technology for precious woods and medicinal materials, particularly a method for non-destructive testing of agarwood based on micro-CT to determine its authenticity and quality. The technical solution includes: acquiring complete three-dimensional data of the agarwood interior through micro-CT non-destructive scanning; extracting characteristic parameters such as the three-dimensional topological structure of the interstitial phloem, the distribution and fullness of agarwood resin, and abnormal structures; identifying authenticity by comparing these parameters with a pre-built database, particularly effective in identifying internal forgery traces such as high-pressure oil injection and mechanical compression; simultaneously, using a multi-parameter fusion model to quantitatively evaluate the spatiotemporal distribution characteristics of agarwood resin and the proportion of resin-containing interstitial phloem to determine its quality grade; achieving comprehensive, objective, and non-destructive testing of agarwood from the inside out, from authenticity to quality, especially suitable for identifying high-end crafts, collectibles, and precious agarwood raw materials, solving the industry pain point that traditional destructive testing methods cannot be applied to intact products.