7results about How to "Automatic extraction" patented technology

The invention discloses a turn-to-turn short circuit fault diagnosis method based on feature selection and a multi-scale residual network, which belongs to the field of motor fault diagnosis, and comprises the following steps: collecting a current signal of a permanent magnet synchronous motor under a turn-to-turn short circuit fault condition in an internal insulation fault of the permanent magnet synchronous motor, and preprocessing the current signal to obtain a pre-processed current signal; obtaining a training set and a test set; constructing a permanent magnet synchronous motor turn-to-turn short-circuit fault diagnosis model, training the permanent magnet synchronous motor turn-to-turn short-circuit fault diagnosis model by adopting the training set, and keeping the optimal structure of the permanent magnet synchronous motor turn-to-turn short-circuit fault diagnosis model; and putting the test set into the trained permanent magnet synchronous motor turn-to-turn short circuit fault diagnosis model for feature learning, and then inputting the test set into a Softmax classifier for fault diagnosis. The method can automatically and efficiently extract weak fault features in current signals, gets rid of dependence on traditional signal processing technologies and diagnosis experience, and has good robustness for noise-containing signals.

The invention belongs to the technical field of contract auditing, and discloses a contract comparison and recognition method based on deep learning, and the method comprises the specific steps: 1, importing a recognition system; step 2, training based on a deep learning OCR model; step 3, performing OCR operation on the picture; 4, identifying and uploading the content; 5, contract output or modification is judged; and step 6, risk prompting. By automatically comparing contract texts, the system can quickly identify key information, the complexity of manual operation is reduced, the system has good adaptability, contracts of different fields and types can be processed without manually adjusting parameters, the manual intervention requirement is greatly reduced due to the high automation degree, contract auditing is more efficient, and the contract auditing efficiency is improved. According to the method, multi-language texts can be easily processed, the automatic data extraction function provides great convenience for subsequent data analysis, and compared with manual text transcription, the OCR technology has better cost benefits in large-scale document processing.

This application discloses a cooling tower cleaning device, which includes a connecting pipeline with interconnected components: a first port extending into and communicating with the interior of the cooling tower; and a second port, the height of which is lower than that of the first port, connected to a water source interface. The second port is configured to be sequentially set to a first state and a second state during normal operation of the cooling tower. In the first state, the second port is connected to the water source interface to replenish water to the cooling tower and expel gas from the connecting pipeline. In the second state, the second port is disconnected from the water source interface and connected to the external environment to discharge liquid carrying impurities from the cooling tower based on a negative pressure siphon effect. The aim is to solve the technical problem of how to effectively clean a cooling tower while ensuring normal equipment operation.

The utility model belongs to the technical field of laser welding machines, and discloses a laser welding machine with a purification device, which comprises a box body, a fixed column is fixedly arranged at the top end of the box body, a support plate slides on the outer side of the fixed column in a reciprocating manner, a buckle is fixedly arranged on the outer side of the support plate, and an exhaust pipe is detachably arranged in the buckle. An air pump is fixedly arranged on the other side of the air inlet pipe, an air outlet of the air pump is fixedly connected with the water tank, a water pump is fixedly arranged on the outer side of the water tank, a water inlet of the water pump penetrates through the water tank, and a water outlet pipe is fixedly arranged on a water outlet of the water pump; the other end of the water outlet pipe penetrates through the inner wall of the water tank and is fixedly connected with the spraying plate, an exhaust port is formed in the inner wall of the upper portion of the water tank, a lead screw is rotationally arranged in the fixing column, and a hand wheel is fixedly arranged at the top end of the lead screw and rotates on the surface of the top end of the fixing column. The problem that toxic gas generated in the using process of the laser welding machine harms the human body is solved.

The application provides a wind turbine tower inherent frequency real-time identification method and electronic equipment, and belongs to the technical field of wind power generation equipment state monitoring and fault diagnosis. The method comprises the following steps: S1, collecting vibration signals of a wind turbine tower; S2, pre-processing the vibration signals to filter out direct current components and extremely low frequency noises; S3, performing grouping processing on the pre-processed signals, performing frequency spectrum analysis on each group of signals, and extracting effective frequency points; S4, performing clustering analysis on a plurality of the effective frequency points based on a density clustering algorithm, and identifying a characteristic cluster representing the inherent frequency of the tower; and S5, calculating the real-time inherent frequency of the tower according to the characteristic cluster. The application can stably and automatically extract the characteristic cluster representing the real inherent frequency of the tower from strong noise and non-stationary vibration data, finally realizes automatic identification and tracking of the inherent frequency without manual intervention, and provides reliable technical support for intelligent monitoring of the structure health of the wind turbine.

This invention proposes an automatic search method and system for acoustic-vibration coupling surface patches based on structural mechanics analysis software, belonging to the field of computer-aided engineering technology. This application includes: providing a structural finite element model and an acoustic field finite element model of the structure to be analyzed; screening structural elements in the coupled surface element structural finite element model, and constructing a candidate set of structures based on the screened structural elements; constructing an OBB hierarchical bounding box tree based on the acoustic field of the coupled surface elements; constructing each OBB structural bounding box for each structural element in the candidate set of coupled surface elements; screening acoustic field elements to obtain candidate acoustic field elements; screening structural elements to obtain coupled surface elements, and organizing the coupled surface elements into coupled surface patches; and storing the numbers of the coupled surface patches as named groups. This application can automatically and accurately extract coupled surface elements from the finite element structural model, realizing fully automatic search and identification of acoustic-vibration coupling surface patches.

The application discloses a kind of material attribute parallel extraction and conversion method and system for multiple CAD platforms, in response to material attribute extraction task, create and record the target CAD model path corresponding to task instance, target CAD platform type and output format information;Corresponding API interface is called from target CAD model path to carry out model file loading and parsing into structure tree, extract the multidimensional original attribute information bound to each component node;According to the preset field standardization template, multidimensional original attribute information is respectively mapped and unit converted, and a standardized data structure model is obtained;Generate structured XML file and perform verification, form the attribute extraction conversion file that meets the requirements of output format information, for external interface call.The application can automatically complete the extraction of material physical property field in CAD platform, structure standardization, format conversion and data verification, and finally output the extraction result as XML document format conforming to the aviation industry standard.