21results about How to "Shorten design time" patented technology

The invention discloses a radiotherapy plan automatic optimization design method based on machine learning, and relates to the technical field of radiotherapy, and the method comprises the steps: firstly collecting and preprocessing radiotherapy core data to generate a training set, training feature extraction, dose prediction and optimization adjustment of a model; processing to-be-processed data through a feature extraction model, screening three optimal similar cases in combination with cosine similarity, and extracting effective features; based on the feature vectors and the effective features, outputting an initial dose plan, constraint parameters and a deposition matrix by a dose prediction model; and finally, constructing a target function, and iteratively optimizing the radiation field parameters and the photon flux by adopting an improved ant colony algorithm and a conjugate gradient method. According to the method, clinical experience and individual differences are fused, the radiotherapy plan is efficiently and accurately generated, and the quality stability and clinical suitability of the plan are improved.

This invention discloses a method and system for designing tunnel smooth blasting charge schemes, relating to the field of tunnel blasting engineering technology. The method includes: collecting and preprocessing basic parameter data required for tunnel smooth blasting design; calculating initial design parameter values ​​for the smooth blasting charge based on smooth blasting design theory and a pre-set parameter calculation model, generating an initial design scheme; inputting the initial design parameter values, cross-sectional geometric parameter data, surrounding rock condition parameter data, explosive parameter data, and historical blasting effect feedback index values ​​into a pre-trained neural network optimization model, outputting optimized smooth blasting charge design parameter values; automatically updating the peripheral hole layout and charge structure in the design scheme based on the optimized design parameter values, generating and outputting the final tunnel smooth blasting charge design scheme. This invention enables intelligent and adaptive design of tunnel smooth blasting charge parameters, improving engineering applicability and molding quality.

The invention discloses a molded line design method and device for an air valve of an engine and the engine, and belongs to the technical field of air valves of engines. Based on the working condition and the parameter sensitivity of the engine, a molded line scheme of a plurality of air valves is generated through mixed horizontal orthogonal test design; performing preliminary screening of molded line schemes based on the surface pressure of the mapping conical surface of the air valve and finite element simulation analysis; based on a dynamic model of the valve mechanism, performing dynamic simulation evaluation and weighted comparison on the molded line scheme subjected to preliminary screening to obtain a molded line scheme subjected to secondary screening; and performing gas circulation performance simulation evaluation on the molded line scheme subjected to secondary screening to obtain a final molded line scheme. The engine gas valve is improved and optimized by comprehensively considering the strength, the wear resistance, the valve seat, the sealing performance and the gas circulation performance of the gas valve; therefore, a standardized and reusable forward development method is provided for the molded line design of the air valve, and the method has both theoretical preciseness and engineering applicability.

The application provides a paper folding design method and system based on a diffusion model and a physical information neural network, and belongs to the technical field of paper folding structures, and comprises the following steps: obtaining point cloud data of a target three-dimensional paper folding shape and corresponding text description information; generating a two-dimensional crease pattern by using a graph diffusion model according to the point cloud data and the text description information, and ensuring that the crease pattern conforms to a specified three-dimensional shape by using conditional coding; and optimizing the two-dimensional crease pattern by using a physical information neural network to obtain a final two-dimensional paper folding diagram. By combining the diffusion model and the physical constraint neural network, high-precision modeling of the crease pattern is realized, it is ensured that the generated pattern can be folded in geometry and physics, and therefore the design efficiency and accuracy are improved.

The application provides an automatic landing method for a power inspection unmanned aerial vehicle in a landing stage, and the main design includes or is based on: 1, a landing gear structure design based on multiple sensors; 2, a judgment logic considering multiple ground contact conditions; 3, an automatic landing method for the power inspection unmanned aerial vehicle in the landing stage, which comprises landing area judgment and landing process sensing, that is, a complete landing detection scheme is provided in the landing-ground contact stage of the power inspection unmanned aerial vehicle, the ground sensor and the unmanned aerial vehicle antenna are integrated on the landing gear, the load of the machine body is reduced, the design complexity is reduced, the design cost and time of the machine body of the unmanned aerial vehicle are reduced, the safety of the unmanned aerial vehicle in the landing-ground contact stage is improved, the cost of the machine body of the unmanned aerial vehicle is reduced, and the inspection efficiency of the unmanned aerial vehicle is improved.

The invention provides a robot body autonomous generation method and system based on artificial intelligence, and the method comprises the steps: carrying out the text coding of the text description of a robot structure, and generating text embedding; according to text embedding, a component generator is used for predicting and generating all components including component types and various attributes through multiple iterations; using a connection relation predictor to predict the connection probability between the components, and screening high-probability connections to form a component connection relation; according to the generated component types and connection relations of the components, father-child connection relations among the components are obtained, the components are connected to father components of the components through joints of the components, various attributes are assigned, a urdf model of the whole robot is formed, and the components in the urdf model are represented by simple geometries assigned by the shape and size attributes of the components; and replacing each simple geometry through a mesh library, and forming a three-dimensional entity model of the whole robot after all the component models are replaced. The robot body can be automatically generated.

The present application relates to the technical field of door and window large sample generation in architectural design, and discloses a door and window large sample generation method and system based on BIM, which quickly generates door and window large sample graph element basic data by using the existing door and window type data of a user in architectural plan and elevation design, quickly arranges by using a door and window large sample graph element dynamic arrangement method, provides a series of quick door and window large sample quick modification solutions, solves the problem of quick generation and modification of door and window large samples by the user, and can significantly save the design time of door and window large samples in architectural design.

The application discloses a jet far-field noise control method and device and a computer readable storage medium. The control method comprises the following steps: obtaining all sample points covering the whole design space by using a test design method; performing far-field sound pressure level calculation according to a physical simplified companion Green function to obtain jet far-field noise target functions of all sample points; establishing a correlation model of the jet far-field noise and the inner and outer curve wall surface shape according to the jet far-field noise target functions of all sample points; and searching for an optimal value of the jet far-field noise on the established correlation model with the jet pipe aerodynamic performance as a constraint to control the jet far-field noise. The application can control the jet far-field noise size by modifying the inner and outer curve wall surface without affecting the jet pipe aerodynamic performance, and automatically designs an optimal inner and outer curve configuration without interference, so that the jet far-field noise is minimized, thereby significantly reducing the jet far-field noise evaluation and noise reduction measure design time.

The application provides a bird flapping wing design method based on momentum theorem analysis of factors influencing lift, which comprises the following steps: firstly, determining basic thrust and lift design constraints according to task requirements; secondly, according to the momentum theorem, converting design parameters influencing the thrust and lift into contributions to the horizontal thrust and vertical lift of the flapping wing, and screening the design parameters according to the constraints; considering the influence of power consumption, determining corresponding design measures for reducing the power consumption; analyzing the realizability of the design measures to obtain the design parameters and corresponding design measures considering the realizability; sorting the importance of the design parameters, optimizing the design measures of the corresponding design parameters, and obtaining the preliminary design scheme of the bird flapping wing. The application converts complicated design constraints into simple requirements for the thrust and lift of the flapping wing, greatly shortens the design time of the flapping wing vehicle for different flight requirements, standardizes the overall design idea of the flapping wing, and has high theoretical support and engineering practical significance.

The utility model discloses a kind of 2.5D line sweep coaxial program-controlled light source, comprising: light source shell, the installation space is formed inside the light source shell, and the detection port and the light outlet of oppositely arranged are set on the light source shell;Between the detection port and the light outlet, there is a beam splitter, the beam splitter is obliquely inserted in the inside of the light source shell;The lower side of the beam splitter is sequentially provided with transparent plate, diffusion film, diffusion plate and LED lamp plate from top to bottom;Control surface circuit board fixed in the installation space and the driving circuit board connected with control surface circuit board, the driving circuit board is connected with the LED lamp plate.The utility model realizes the combination of 2.5D program-controlled line sweep light source and coaxial light source, can effectively improve the quality of light source detection and meet the detection needs of different products and scenes.

The invention provides a rapid mold generation method based on large model data application. The method comprises the following steps: acquiring engineering data information of a to-be-generated mold, matching the engineering data information with mold product instances in a database, if matching succeeds, outputting the successfully matched mold product instances, and if matching fails, executing the following steps: extracting a DL line from DL data of the to-be-generated mold; identifying a reference line matched with the DL line from the reference line sample set; obtaining a reference coordinate position of a part associated with the matched reference line in the to-be-generated mold; and calling a virtual model of the matched part associated with the reference line from the database, and placing the virtual model according to the reference coordinate position. The production speed and efficiency of the mold are improved, and the mold design time is further saved.

The invention provides an intelligent die-casting manufacturability analysis method and device. The method converts a casting model into a triangular mesh and calculates structural features. And solving a candidate set in the draft direction through the triangular mesh. Aiming at each mold pulling direction, a mold opening available area, a mold opening lack area and a mold opening incapability area are determined; and determining a candidate area of each to-be-arranged sliding block and a core pulling direction of the candidate area on the basis of the under-mold-opening area and the non-mold-opening area. And constructing each manufacturability index of the added sliding block based on the content, analyzing a plurality of manufacturability index results of each sliding block loose core by utilizing a scoring model, generating an analysis report and outputting the analysis report. According to the method, material attributes, geometric structure characteristics, a draft scheme and specific die-casting forming process conditions of a casting are comprehensively considered, and the draft scheme design is taken as a core, so that evaluation and optimization of the draft scheme are realized. Therefore, the automation degree of the die-casting product draft scheme design process is greatly improved, the scheme design time consumption is remarkably reduced, and the operation difficulty is effectively reduced.

This utility model belongs to the field of air conditioning technology, specifically providing a heat exchanger and air conditioner with better overall performance. This utility model aims to solve the problem of poor overall performance in existing heat exchangers. To this end, the heat exchanger of this utility model includes refrigerant pipes and multiple fins. The diameter d of the refrigerant pipe is selected from any value between 5.8mm and 6.5mm, and the refrigerant pipe includes multiple pipe segments. The distance H between two adjacent pipe segments is selected from any value between 17.1mm and 22.5mm. Multiple fins are penetrated by the multiple pipe segments, and the width W of the fins is selected from any value between 18mm and 23mm. The distance L between two adjacent fins is selected from any value between 0.8mm and 1.5mm. This utility model effectively avoids increased air resistance while ensuring heat exchange, thus improving the overall performance of the heat exchanger.

This utility model discloses a locally adjustable enhanced heat dissipation liquid cooling plate, including a liquid cooling plate body and turbulence fins for achieving localized turbulence. The liquid cooling plate body includes a flat plate and a flow channel plate. The flow channel plate is a stamped integral structure with multiple flow channel grooves on its body. The flat plate and the flow channel plate are fixed together by brazing, forming a flow channel cavity for coolant flow between the flat plate and the flow channel grooves. An inlet and an outlet communicating with the flow channel cavity are respectively provided on both sides of the flat plate. The turbulence fins are installed in the flow channel cavity to achieve localized turbulence of the coolant within the cavity. This locally adjustable enhanced heat dissipation liquid cooling plate reduces design and mold costs, shortens design time, improves design efficiency, and shortens the design and development cycle. While achieving effective heat dissipation, it also saves costs to a large extent, making it highly practical.

The utility model discloses a kind of quick riveting flanging mould of battery top cover pole, including mould insert for accommodating the top cover assembled with pole, further including riveting pressure head connected with pneumatic punch press, riveting pressure head includes: riveting slider punch, its head shape is matched according to pole straight edge contour;Riveting slider riveting punch, for providing support force to the side surface of pole, its end is embedded in the lower end of riveting slider punch;Riveting inclined top, slidingly connected in the axial cavity of riveting slider riveting punch, be provided as gradually outwardly inclined structure from top to bottom. Thus, through the synergistic effect of riveting slider punch, riveting slider riveting punch and riveting inclined top, pole straight edge can be accurately turned into 90 °, and flanged rear surface flatness is high, meet the riveting accuracy and quality requirement of excessive current power battery top cover, guarantee the battery performance and security;Mould each component can be quickly adjusted and replaced according to different needs, reduce mould development design and debugging time.

The invention discloses an underwater acoustic transducer design method based on weighted Bayesian optimization and finite element simulation, and relates to the technical field of electroacoustic transducers. The underwater acoustic transducer design method based on weighted Bayesian optimization and finite element simulation comprises the steps of establishing a finite element simulation model, establishing constraint conditions, normalizing parameters, constructing an objective function, constructing a performance evaluation model, iterating the parameters and selecting an optimal solution. The invention aims to dynamically adjust the optimization weight of each shell structure parameter aiming at the underwater acoustic transducer which needs to consider two or more output characteristics (emission current response, resonant frequency, working bandwidth and the like) by utilizing a multi-objective optimization thought and aiming at different effects of different shell structure parameters on the output characteristics, so as to realize the dynamic optimization of the output characteristics of the underwater acoustic transducer. The shell structure parameters of the underwater acoustic transducer are subjected to optimization design, an underwater acoustic transducer model meeting the output characteristics is obtained, and the design, research and development cycle of the underwater acoustic transducer is shortened.

The invention relates to the technical field of tumor radiotherapy and computer-aided therapy planning, in particular to a space segmentation radiotherapy lattice point automatic optimization method and system based on integer linear programming. The objective of the invention is to solve the problems of low efficiency, strong subjectivity, incapability of perfectly adapting to the shape of an irregular target region, and poor stability caused by dependence of spatial segmentation radiotherapy lattice point layout on artificial experience or a simple geometric normal form in the prior art. And optimization of the filling quantity is difficult to realize under the condition that multiple geometric constraints (lattice point diameter, lattice spacing and edge distance) are met. The result obtained through optimization has automation, objectivity, optimality, high adaptability, flexibility, high efficiency and high compatibility.

The application discloses a framework-support building structure design method and system based on a generative adversarial network and a computer. The design method comprises four steps of pre-training a generative adversarial network, inputting and identifying a building drawing, sequentially arranging columns, supports and a structure drawing based on the building drawing and outputting the structure drawing. Evaluation indexes of the generative adversarial network comprise not only picture quality but also subjective and objective evaluations of the building structure. According to a conditional probability formula and characteristics of the generative adversarial network, the design method decomposes a design process into two steps, improves accuracy of a design result, realizes component arrangement design of the building structure in a short time, is very accurate, has little difference in performance from a design result of a senior structure designer, is simple to use, can obtain a corresponding structure drawing by inputting a processed building drawing, can assist a building designer to complete component design of the building structure and has strong popularization.

This application relates to a design method, apparatus, and thrust prediction method for a magnetic thrust assembly. The method includes: obtaining the structural type and constraints of the magnetic thrust assembly, wherein the structural type corresponds to at least one basic structure; constructing structural parameter conditions based on the structural type; determining at least one set of target parameters for the magnetic thrust assembly based on the structural parameter conditions and constraints, using an optimization algorithm and a thrust prediction model; and automating the design of the magnetic thrust assembly through the optimization algorithm and a pre-trained thrust prediction model, thereby reducing the design time and further reducing the design cost of the magnetic thrust assembly.

The invention belongs to the technical field of integrated photoelectronics, and particularly relates to a heat insulation photonic device design method based on a constant heat insulation principle. The method comprises the following steps: step 1, system modeling and parameter acquisition; 2, analyzing and extracting core physical factors; and step 3, geometric generation based on a constant adiabaticity principle PCA. The invention aims to solve the technical problems of lengthy device size, dependence on a large amount of numerical iteration in the design process, high calculation cost, sensitivity of performance to parameters, lack of physical interpretability and the like in the existing design method of the heat insulation photonic device. According to the method, traditional geometric tuning and numerical iteration are abandoned, and the optimal structure is deterministically generated by establishing an analytical relation between physical invariants and device geometry.

The application belongs to the field of microwave technology, and particularly relates to a W-waveband ultra-wideband waveguide filter, the filter structure comprising a resonant cavity and metal-loaded capacitance, wherein a downlink filter port and an uplink filter port are arranged at the front end of the cavity; the resonant unit is composed of nine resonant cavities, and two adjacent resonant cavities are connected through direct coupling; a metal column is inserted into the H plane of each resonant cavity through the capacitive loading technology, so as to realize ultra-wideband, high out-of-band suppression and miniaturization; the structure of the application is composed of nine rectangular resonant cavities offset coupling, a circular metal is inserted into the resonant cavity, and the overall structure is symmetrical about the fifth resonant cavity; the structure has fewer parameters in simulation optimization, reduces the design time, and improves the design efficiency.