2results about How to "Forming accurately" patented technology

The invention provides a hot rolling preparation method for producing flat-bulb titanium and application, the method comprises the steps that S1, a square blank is preheated to T1 and then subjected to heat preservation for 1-2 h, the phase transformation point of the square blank is T2, T1 = T2-delta T, and delta T ranges from 20 DEG C to 30 DEG C; s2, rough rolling is conducted at the speed of 4.5 m / s to 5.5 m / s, a groove is formed, the blank temperature after rough rolling is larger than or equal to 880 DEG C, finish rolling is conducted in a continuous passing mode to conduct arc shaping on the blank, the symmetrical flat-bulb titanium profile with bulbs at the two ends and a web in the middle is obtained, the blank temperature after finish rolling is larger than or equal to 850 DEG C, and the total rolling deformation ranges from 75% to 85%; s3, the profile is conveyed to a line roller type tension straightening machine through a roller way to be subjected to tension straightening treatment, the speed is 0.4-0.6 m / s, and the temperature of the straightened profile is larger than or equal to 700 DEG C; and S4, air cooling treatment is carried out, then tongue-shaped parts at the head and the tail are cut off, oxide skin on the surface layer is cleaned, and two flat-bulb titanium profiles with the same specification are obtained through water cutting symmetric segmentation in the rolling direction. According to the method, the temperature difference between the head and the tail can be reduced, the structure property uniformity and the batch stability are improved, and the minimum length of the prepared flat-bulb titanium profile can reach 12-15 m.

This invention discloses a lane line annotation method. First, it acquires the point and surface results of lane line detection separately. Then, it fuses the point and surface results using a multi-model approach to obtain a fused point set. Next, it tracks the fused point set and selects consecutive frames for tracking and fusion to obtain a merged point set. Finally, it performs fitting based on the merged point set and uses the fitting result as the lane line annotation result. This method automates lane line annotation and significantly improves its accuracy. Furthermore, it can quickly and accurately generate a large amount of sample data, providing a training set for lane line detection models and increasing the efficiency of developing new lane line detection models.