5 results about "Texture orientation" patented technology

This invention discloses a surface-coated cutting tool with a preferred texture orientation, its preparation method, and its application. The surface-coated cutting tool includes a tool substrate and a surface coating disposed on the tool substrate. At least one layer of the surface coating is an α-Al₂O₃ coating. The α-Al₂O₃ coating has a preferred texture orientation relative to the {1010} and {0012} crystal planes, and the texture coefficient satisfies the following characteristics: 5.0 ≤ TC(1010) + TC(0012) < 9.0, and 3.0 ≤ TC(1010) < 9.0, 0 < TC(0012) < 4.0. The preparation method includes depositing the coatings on the tool substrate using a CVD process. The surface-coated cutting tool of this invention possesses both excellent wear resistance and anti-chipping properties, exhibiting superior performance in the machining of materials such as cast iron, stainless steel, and alloy steel.

This invention relates to a texture primitive extraction method for tire X-ray images, addressing the challenge of accurately obtaining pixel-by-pixel texture information at the individual cord level while suppressing background interference. It falls under the field of computer vision and image processing technology. The method combines frequency domain analysis to obtain texture direction and spacing, utilizes this information to construct a mesh mask, and further combines background point extraction with real background reconstruction to filter out specific background regions in the original image. Under directional constraints, the remaining texture mesh is continuously tracked to obtain pixel-by-pixel texture information, thus achieving texture primitive extraction. This provides a more reliable foundation for subsequent pathological detection, structural analysis, and cord-level texture modeling.

The application relates to the technical field of image recognition, and discloses a metal plate defect point detection method and system. The method comprises the following steps: obtaining a surface image of a target plate as an original image of the target plate; performing noise suppression on the original image to obtain an enhanced image of the target plate; performing texture direction feature extraction on the enhanced image to obtain a texture trend distribution map of the target plate; performing differential analysis on the texture trend distribution map and a preset standard texture direction map to obtain direction abnormal points of the enhanced image; performing gray scale statistics on the direction abnormal points to obtain a local gray mean value of the target plate, and determining a pixel point with a gray value lower than the local gray mean value as a suspected defect point; and performing morphological clustering on the suspected defect point to obtain a defect area of the target plate. The application can improve the defect point detection efficiency of the metal plate.

This invention relates to a method for improving the texture orientation and processing properties of Fe-6.5%Si steel, belonging to the field of material modification technology. It includes composition adjustment, determining the normalization temperature range and cooling medium, cold rolling and annealing treatments, calculating the lattice slip energy of the cold-rolled non-oriented steel sheet, electrical pulse modification, and temperature control. This invention alters the magnetic and deformation properties of Fe-6.5%Si alloys through the addition of alloying elements and pulsed current treatment, resulting in low-iron-loss, low-noise, high-silicon electrical steel for power transformers that can be produced using rolling processes. The silicon steel sheets prepared using this invention have been validated in engineering applications. Third-party testing has shown that their performance indicators meet the requirements for silicon steel sheets used in transformers, demonstrating strong engineering practicality and enabling actual industrial production.

The application discloses a mutton thawing state endpoint judgment method and system based on machine vision, and particularly relates to the field of image recognition, and is used to solve the problems of image feature distortion and poor judgment accuracy caused by optical interference due to the mixed phase state of meat surface ice water in the thawing process of the existing method; the method comprises the following steps: acquiring a thawing process image and converting the image to a color space containing a brightness component; based on the brightness component, a mirror surface reflection area and a non-mirror surface reflection area are segmented; the mirror surface reflection area image is converted into a topological network graph to calculate a connectivity evolution parameter, and the non-mirror surface reflection area is subjected to texture direction field analysis to calculate a texture direction consistency recovery degree feature; then, the time sequence of the two types of features is subjected to collaborative mode analysis to obtain a feature vector; finally, the feature vector is input into a pre-trained classification model to judge the thawing stage, and the thawing endpoint is determined when the stage meets the preset endpoint.