5results about How to "With precision" patented technology

The invention relates to a variable-rigidity multi-stable-state inerter type nonlinear energy trap damping device and a working method thereof. The device is composed of a bottom plate, a belleville spring, a loading head, a core fixing cylinder, a nylon gasket, a rubber center cylinder, a mass block, a screw, a ball screw, a flywheel and the like. A multistable energy dissipation mechanism is formed by connecting the belleville spring elements with the negative stiffness characteristic in series and in parallel. The pre-pressing displacement of the belleville spring can be accurately regulated and controlled by adjusting the fastening degree of the bolt and the position of the fixed baffle on the sliding rail, and non-linear rigidity adjustment of the device is achieved. An inerter element is formed through the combined design of a ball screw transmission system and a flywheel, efficient energy conversion and inertial mass effects are achieved, and therefore the vibration reduction effect and robustness of the system are remarkably improved. The device is compact in structure, excellent in performance and suitable for coping with a complex vibration environment.

The utility model discloses a bamboo shaving board film covering device which comprises an installation frame, a push plate is fixedly installed in the installation frame and located at the upper end of a conveying belt, a bamboo shaving board film covering assembly is fixedly installed on the upper surface of the installation frame, and the bamboo shaving board film covering assembly is perpendicularly opposite to the conveying belt. And a gluing assembly and a jacking assembly are fixedly installed on the lower surface in the mounting frame, a linear sliding table is fixedly installed on the lower surface of the mounting frame, and a scratching knife is fixedly installed on the lower surface of a movable block of the linear sliding table and located in the middle of the jacking assembly. By the adoption of the bamboo shaving board gluing device, in the bamboo shaving board film coating process, film bonding is firmer, generated bubbles are rolled, pushed and squeezed out, the gluing amount of each set of bamboo shaving boards is uniform in the gluing process, the gluing amount is increased along with the length of the bamboo shaving boards, and therefore the bamboo shaving boards have stability and deviation prevention performance in the bamboo shaving board conveying process.

The application belongs to the technical field of composite machining, and discloses a composite workpiece element automatic extraction method based on three-dimensional point cloud semantic segmentation, which comprises the following steps: obtaining a two-dimensional image and a three-dimensional point cloud of a composite workpiece element; respectively performing data preprocessing on the two-dimensional image and the three-dimensional point cloud of the composite workpiece element to obtain a co-configuration image set composed of a three-dimensional point set and a two-dimensional image; extracting the composite workpiece element in the two-dimensional image based on a convolutional neural network and obtaining a two-dimensional feature mapping set; establishing the corresponding relationship between the two-dimensional image and the three-dimensional point cloud of the composite workpiece element by using a multi-view aggregation model based on deep learning; and performing semantic segmentation on the three-dimensional point cloud to obtain corresponding point cloud sets of different composite workpiece elements. The application can realize the automatic denoising segmentation and extraction of a point cloud file scanned by a laser after the point cloud file is imported into an algorithm, and can segment the workpiece element according to the characteristics of the composite material, mark the belonging element into the belonging information of each point, and facilitate the extraction and calling.

This utility model relates to the technical field of depletion device modules, and discloses a key module of a depletion device, including a shell, bolts on the inner side of the shell, and two discharge plates on the top of the bolts. The two discharge plates are respectively designated as a first discharge plate and a second discharge plate. The first and second discharge plates are basically concave in shape, and the lower end of the concave body is provided with a flat surface with a flat area of ​​not less than 40 square millimeters. In this utility model, by adopting a concave structure for the first and second discharge plates and providing a flat surface at the lower end, with the flat surface being relatively parallel and having a flat area of ​​not less than 40 square millimeters, the unique shape is used to change the electric field distribution path. During normal energization, the current is conducted through the discharge plates. The flat surface expands the current-carrying area, while the concave structure allows the electric field lines to spread more evenly throughout the entire area. The uniform electric field distribution significantly reduces the problem of local overheating caused by electric field concentration.

The application discloses a kind of based on global to local modulation's unsupervised industrial anomaly detection method and system.The method includes extracting global feature using global encoder, extracting local feature using local encoder;The global feature is mapped as modulation parameter, and the local feature is modulated using the modulation parameter, to generate enhanced feature;Further, the enhanced feature is input to decoder for feature reconstruction;Based on the cosine distance between each corresponding hierarchical feature in the local encoder and the decoder, a pixel-level anomaly map is generated;And based on a plurality of preset scoring profiles, determine image-level anomaly score according to the pixel-level anomaly map.The application can realize high-precision, strong robustness detection of various industrial defects, especially unknown small defects, to meet the stringent requirements of complex industrial quality detection.