2results about How to "Solving Adaptive Problems" patented technology

The utility model discloses a curved surface pressure sensor based on a magnetic field, and aims to solve the problem that when an existing flexible pressure sensor based on the magnetic field is matched with a complex curved surface, wiring of a PCB is complex, or the consistency of readings of different Hall elements is low, and consequently the accuracy of a measurement result is reduced. The device comprises a flexible magnet layer, a hard shell layer and a flexible printed circuit board, the hard shell layer is a curved surface, and the inner wall of the hard shell layer is uniformly provided with mounting grooves for placing the stiffening plates; the flexible printed circuit board is provided with a plurality of reinforcing plates which are arranged at intervals, and the plurality of Hall elements are arranged on the plurality of reinforcing plates in a one-to-one correspondence manner; the flexible printed circuit board is connected with the hard printed circuit board through a connector; the problem of adaptation to a complex curved surface is solved, the consistency of the interlayer spacing of the Hall sensor and the flexible magnet is kept, the measurement result of the sensor is more accurate and stable, and the sensor has the capacity of covering the shape of a complex product in a large range.

The present application relates to the technical field of liquid crystal display backlight module detection, and discloses a backlight module light leakage determination method and system based on machine learning. The backlight module light leakage determination method based on machine learning comprises the following steps: collecting backlight module optical characteristic matrices; screening suspicious light leakage areas according to adaptive threshold segmentation of ambient light; implementing local contrast enhancement on the suspicious light leakage areas, combining multi-scale pyramid analysis to strengthen weak light leakage signals; quantifying micro-area light leakage structure complexity by means of box dimension calculation and multi-fractal spectrum analysis, and constructing a fractal feature vector; establishing a light leakage and defect mapping based on a machine learning correlation model, and outputting light leakage details and defect types after scoring. The present application combines fractal geometry theory, image enhancement technology and machine learning algorithms, realizes accurate quantification of light leakage morphology and automatic recognition of defect types, improves detection accuracy, reduces false positive rate, reduces missed detection rate, and improves detection sensitivity.