4results about How to "Solve collection difficulties" patented technology

The application discloses a sensor fault robust multi-output soft measurement method and system based on adversarial learning, relates to a sensor fault robust multi-output soft measurement method and system, and belongs to the technical field of soft measurement. The application discloses a sensor fault robust multi-output soft measurement method and system based on adversarial learning, relates to a sensor fault robust multi-output soft measurement method and system, and belongs to the technical field of soft measurement. The application discloses a sensor fault robust multi-output soft measurement method and system based on adversarial learning, relates to a sensor fault robust multi-output soft measurement method and system, and belongs to the technical field of soft measurement. The application discloses a sensor fault robust multi-output soft measurement method and system based on adversarial learning, relates to a sensor fault robust multi-output soft measurement method and system, and belongs to the technical field of soft measurement. The application discloses a sensor fault robust multi-output soft measurement method and system based on adversarial learning, relates to a sensor fault robust multi-output soft measurement method and system, and belongs to the technical field of soft measurement. The application discloses a sensor fault robust multi-output soft measurement method and system based on adversarial learning, relates to a sensor fault robust multi-output soft measurement method and system,

The application discloses a kind of complex lighting conditions underwater artificial crack dataset construction method, it is related to image dataset production technical field, including, collection crack picture and extract crack curve generation coordinate information, based on this, construct crack 3D model and prepare concrete standard test block;The test block is placed in water, and underwater crack image under conventional, dim and uneven illumination is collected, and is classified after pre-processing according to illumination condition;Stable Diffusion model based on LoRA fine-tuning is used, and different illumination condition images are input respectively to train and optimize, and style expansion image is generated, and pre-processing image constitutes unlabeled data together;Through image enhancement algorithm processing the data, after the enhanced image is labeled, the label is corresponded with the original image, and the underwater artificial crack dataset under complex lighting conditions is constructed, the application solves the problem that actual underwater crack disease is difficult to collect, meets the core demand of engineering practice, and provides richer data support for underwater structure crack detection and segmentation model training.

The utility model relates to the technical field of aluminum alloy production, in particular to an auxiliary device for drilling a component sample of a small aluminum alloy test block, and aims to solve the problems that when the component sample is drilled on a round cake test block taken from an aluminum alloy solution and a small test block cut from a cast ingot or a finished product at present, the sample is difficult to collect, the safety is lower in the collecting process, and the sampling cost is low. And the collection efficiency is low. The device is mainly composed of a sample sleeve and a movable clamping block penetrating through the sample sleeve, two clamping block holes are symmetrically formed in the sample sleeve and tightly attached to the cylindrical wall of the bottom face, each clamping block hole is provided with a lining plate blocking part tightly attached to the wall of the sample sleeve, the lining plates can slide up and down along the cylindrical wall, the clamping block holes are opened when the lining plates slide upwards, and the lining plates fall to block the clamping block holes after the lining plates are loosened. The clamping blocks are embedded into the sleeve from the two sides of the outer side of the sample sleeve wall, one end of the outer side of the sleeve is clamped on the bench clamp, one end of the inner side of the sleeve clamps a sample, and the purpose of firmly fixing the sample is achieved under the action of the anti-skid teeth.

The invention relates to the technical field of image recognition, in particular to an FPC connector appearance defect detection system and method based on image generation, and the system comprises a constraint definition module, a warping field generation module, a base material reconstruction module, a pseudo soldering cavity grid construction module and a defect synthesis module. According to the method, the problem that a real object warping sample is difficult to collect is solved by extracting a defect-free image gray abrupt change boundary, constructing a mechanical fixed end constraint line, establishing a flexible base material warping offset field in combination with a nonlinear mapping function and reconstructing base material physical deformation characteristics by utilizing a coordinate migration and bilinear interpolation technology; a mapping grid is constructed according to radial sector division of a bonding pad area, a dark pixel cluster generated by poor welding in a metal bonding pad is simulated by adopting a random walk algorithm, and a composite defect image with high fidelity and diversity is synthesized under the condition that a real defect sample is not needed. And the blank of specific form defect data in the detection sample library is filled.