11results about How to "Improve part quality" patented technology

The invention provides an electromagnetic-assisted nickel-based alloy laser melting deposition crack inhibition method and system, relates to the technical field of automatic control, constructs an intelligent control system, carries out deep fusion and real-time prediction on multi-source heterogeneous sensing data, generates a prediction result, sets a reward function and an action-value network, and improves the performance of the nickel-based alloy laser melting deposition crack inhibition system. Solving to obtain an optimization control strategy and analyzing and outputting the optimization control strategy; and constructing a three-dimensional electromagnetic field distribution matrix. In combination with real-time feedback of the shape of the molten pool, the molten pool is stimulated to flow directionally and oscillate non-linearly according to the resonance effect, oscillation parameters are obtained, thermodynamic behaviors corresponding to the molten pool are predicted according to the oscillation parameters, and a thermodynamic prediction result is fed back to the central control unit; the method comprises the following steps: detecting the surface appearance of a part, extracting defect characteristic parameter vectors, inverting defect influence factors, generating a dynamic regulation and control curve, dispersing the dynamic regulation and control curve into multi-dimensional control instruction vectors, updating a preset regulation and control model, outputting optimized regulation and control model parameters, and carrying out crack suppression operation again.

The invention discloses a community division method and device, electronic equipment and a readable storage medium, and the method comprises the steps: determining a target edge based on the edge betweenness of all edges in a network, the network being composed of a plurality of nodes and a plurality of edges, the target edge being an edge connecting two communities in the network; a first similarity and a second similarity are determined, the first similarity is the similarity between the first edge node and the second neighbor node, the second similarity is the similarity between the first edge node and the first neighbor node, and the first edge node and the second edge node are nodes at the two ends of the target edge respectively; the first edge node initially belongs to a first community in the two communities, the second edge node initially belongs to a second community in the two communities, the first neighbor node is a neighbor node of the first edge node in the first community, and the second neighbor node is a neighbor node of the second edge node in the second community; and adjusting the community to which the first edge node belongs based on the first similarity and the second similarity.

The invention discloses a wiring-driven FPGA (Field Programmable Gate Array) layout division method and system. The method comprises the following steps: generating a coarse-grained netlist through node clustering; performing initial division according to the netlist to obtain an initial division result; and based on an initial division result, node movement is performed layer by layer, and division optimization is performed by taking the minimum wiring cost of division as an optimization target. According to the scheme, occupation of interconnection resources can be reduced, and then the overall performance of a chip system is improved.

The invention discloses a machining method of a welding assembly with a narrow U-shaped circular ring ultra-thin wall high-temperature alloy sealing piece, which comprises the following steps: firstly, respectively forming a semi-finished product of an annular sealing piece A with an L-shaped section and a semi-finished product of an annular sealing piece B with an L-shaped section, then aligning and assembling welding surfaces of the two semi-finished products, then carrying out spot welding, and positioning by the welding surfaces; and one edge of the semi-finished product of the annular sealing piece A is pressed, one edge of the semi-finished product of the annular sealing piece B is subjected to flanging treatment, a final U-shaped face is obtained, and the surplus is cut according to a part drawing to obtain the final size. By the adoption of the machining method, the problem that a spot welding electrode cannot directly weld a U-shaped opening can be solved, the consistency of molded surfaces of a narrow U-shaped circular ring ultra-thin wall high-temperature alloy sealing piece welding assembly is guaranteed, the design requirement for size precision is met, and it is guaranteed that the requirements for sealing performance and consistency are met.

The invention discloses a numerical control roll bending method for a variable-curvature skin part of an airplane, which comprises the following steps of: firstly, carrying out trial production of the skin part, and recording the down-regulation depth of an upper roller at each time and the distance between roll bending marking lines on the left side and the right side of the part and the center line of the part for rolling of a preformed blank and each roll bending process in the trial production process; during subsequent skin part blank machining, the part blank is cut to be completely consistent with the blank used in the first step in size and shape, and the center line of each blank is determined; according to the same method as the first step, a section template is not needed in the numerical control machining process, and in the blank pre-forming process and each roll bending process, roll bending equipment is programmed through data recorded in the first step, so that the roll bending equipment adjusts the down-regulation depth and the rolling arc length of an upper roller according to the program, and the blank does not need to be taken down; the equipment finally completes machining of the whole part according to the sequence of preforming, first-time roll bending, second-time roll bending and the like.

The application discloses a semi-supervised HRRP noise label filtering method based on early learning guidance, comprising the following steps: constructing an HRRP training data set and a deep neural network model; pre-training the deep neural network model; predicting the HRRP training data set by using the pre-trained network model and dividing the HRRP training data set into two data sets according to the confidence; constructing a known label data set and an unknown label data set to form a semi-supervised training data set and performing data enhancement; semi-supervised training the network model by using the enhanced data; generating the label of the unknown label data set by using the semi-supervised trained network model and fully supervised training the network model; and target recognition of the HRRP data by using the fully supervised trained network model. The application uses a generalized cross-entropy loss function in the early learning training stage of the model, proposes a data enhancement scheme suitable for HRRP, can better reduce the influence of noise labels on the model, and has better stability and implementability.

The utility model belongs to the field of aviation heat treatment technology, concretely relates to a kind of part heat treatment anti-deformation tooling.A detachable multipurpose quenching rack, including partition disc, placing punched plate on partition disc, the diameter of through hole A on punched plate is less than the diameter of through hole B on partition disc, and through hole A, through hole B are communicated, for the vertical insertion of part;The number of through hole A, through hole B is multiple.The utility model has the following advantages: the part can be placed vertically, solves the problem that the existing part is easy to deform during heat treatment, and the deformation is minimized as much as possible;Increase the loading capacity of the part, simple operation, different part number parts are not easy to confuse, the appropriate tooling can be selected according to the size and type of the part, so that the heat treatment production efficiency and part quality are greatly improved;Tooling structure is simple, long service life, strong carrying capacity.

The invention discloses a finite element simulation method for accurately calculating an electric arc additive manufacturing temperature field and a stress field, and belongs to the technical field of additive manufacturing. The method comprises the steps that firstly, the geometric structure of an electric arc additive manufacturing deposition sample is obtained through a 3D contourgraph, then the fusion width, the fusion depth and the excess weld metal of each deposition layer are obtained through linear cutting, a simulation heat source model is constructed based on actual additive parameters of each deposition layer, three heat sources are considered in the simulation heat source model, and a simulation heat source model is constructed; and the heat distribution condition in the actual additive manufacturing process is fully considered. According to the method, the three-dimensional scanning technology is combined with electric arc additive manufacturing temperature field and stress field simulation, the actual geometric structure and morphology of the deposition layer are obtained through an external detection means, the temperature field and stress field of the electric arc additive manufacturing deposition layer are calculated based on the actual morphology of the deposition layer, and compared with existing electric arc additive manufacturing simulation at present, the method has the advantages that the calculation efficiency is high; and the reduction degree of distribution of the calculated temperature and stress in the deposition layer can be greatly improved.

The invention provides an internal high-pressure forming device and a forming method thereof.The forming device comprises a water expansion mold and further comprises a profiling assembly and a retaining assembly, and the profiling assembly is arranged on the water expansion mold and abuts against the end face of a to-be-machined workpiece clamped in the water expansion mold; the retaining assembly is arranged on the profiling assembly and used for retaining the profiling assembly in the feeding direction of abutting against the workpiece to be machined. By means of the retaining assembly arranged on the profiling assembly, the retaining assembly exerts constraint on the profiling assembly in the feeding direction in the water swelling process, it is ensured that the profiling assembly does not move backwards, and therefore the contact between the profiling assembly and a workpiece to be machined is kept in a stable state; therefore, the problems that material supplementing fails in the water swelling process of the bevel opening of the to-be-machined part and material supplementing fails due to retreating of the profiling assembly are solved.

The present invention provides a graph data partitioning method and device, which can be applied to the field of graph data processing technology. The method includes: determining at least one boundary vertex from the subgraph data of a computing node; determining the first expected benefit of migrating the boundary vertex to at least one adjacent computing node based on the benefit weight of the connecting edge between the boundary vertex and at least one neighbor vertex of the boundary vertex, wherein the benefit weight is determined according to the communication overhead between the adjacent computing nodes and the computing nodes, and the first expected benefit represents the saved communication overhead value; determining the boundary vertex to be migrated and the target adjacent computing node based on the first expected benefit of migrating at least one boundary vertex to at least one adjacent computing node; when it is determined that the boundary vertex to be migrated meets the migration condition, migrating the boundary vertex to be migrated to the target adjacent computing node to re-divide the subgraph data of the computing node.

The present invention relates to an efficient graph partitioning method, device and equipment for large-scale graphs. According to the purpose of graph partitioning and in combination with the power law of large-scale graphs, mirror vertices are created for high-degree vertices on each computing node. After the high-degree vertices in the large-scale graph are marked, the high-degree vertices and the edges connected to the high-degree vertices are temporarily removed. Then, the remaining vertices and edges in the large-scale graph are first partitioned to each computing node to improve the partitioning efficiency. Then, the high-degree vertex-low-degree vertex edges are allocated to the computing nodes where the low-degree vertices are located. Then, the high-degree vertex-high-degree vertex edges are allocated to the computing nodes with fewer stored edges to balance the number of edges actually stored in each computing node. Finally, the high-degree vertices are allocated to the computing nodes with fewer stored vertices to balance the number of vertices actually stored in each computing node, thereby greatly reducing the partitioning time overhead and improving the partitioning quality, thereby achieving improved computing performance for processing large-scale graphs.