109 results about "Mechanical products" patented technology

The invention discloses a multi-feature quality prediction method for optimizing an FFN based on an improved Hereum algorithm, and the method comprises the steps: obtaining technological parameter data, and constructing a sample of an HO-FFN model after feature screening; an HO-FFN model is constructed; determining a network topology structure of the FFN, and optimizing the weight and bias parameters of the FFN by using an improved He-Map algorithm; the method comprises the following steps: collecting data of a preset threshold quantity of process parameter types in a mechanical product quality processing process, performing product quality real-time prediction output by utilizing an HO-FFN model to obtain a quality prediction result, and further performing real-time adjustment on the processing process of the mechanical product. According to the method, the feed-forward neural network is optimized by improving the Heima algorithm, the process parameter prediction precision and efficiency are effectively improved, the training time is shortened, meanwhile, the local optimum problem in a traditional method is effectively avoided, and higher accuracy and stability are ensured.

The utility model relates to the field of mechanical paint spraying, and discloses paint spraying equipment based on mechanical products, which comprises a machine body, a spray head is fixedly connected to the top end of the inner wall of the machine body, an external pipeline is fixedly connected to the top end of the outer wall of the machine body, and a rotating assembly is arranged at the bottom end of the inner wall of the machine body. A connecting plate is arranged at the top end of the outer wall of the rotating assembly, the bottom end of the outer wall of the external pipeline is fixedly connected with a spray head, three sets of arc-shaped guide grooves are formed in the surface of the rotating disc, the clamping blocks are slidably connected to the inner walls of the arc-shaped guide grooves of the rotating disc, and the inner walls of the fixing blocks are elastically connected with pressing blocks through limiting springs. According to the mechanical product spraying device, mechanical products with different sizes are clamped and fixed from the inside or the outside, and the fixed seat can be driven to rotate through the motor in the clamping process, so that the mechanical products are driven to rotate, the spraying effect on the mechanical products is better, and the position of the mechanical products does not need to be manually adjusted.

The invention provides a mechanical product assembly performance simulation uncertainty analysis method. According to the method, the influence of each uncertainty influence factor on the assembly performance in different links of the simulation process is considered, the uncertainty influence factors in the simulation process are divided into two types, and quantitative analysis of uncertainty is carried out respectively. The first class comprises a measurement link, a modeling link and a simulation analysis link in the early stage of simulation, and the influence factors of the class can be used for directly calculating the uncertainty u or error; the second type of influence factors are external loads, boundary conditions and assembly performance uncertainty caused by non-linear links caused by process parameters mainly including geometric error distribution, and for the type of influence factors, the method combines optimal SVR proxy model construction and Sobol global sensitivity analysis on the basis of a simulation analysis result of a physical digital twinborn model, so that the assembly performance uncertainty caused by the non-linear links caused by the process parameters mainly including the external loads, the boundary conditions and the process parameters mainly including the geometric error distribution is obtained. And quantitatively analyzing the sensitivity of the assembly performance to the process parameters. In conclusion, the method provides guidance for the product assembly process.

The invention discloses a straight tooth extrusion wheel for internal spline inverted conical teeth and a machining method for the internal spline inverted conical teeth, and belongs to the technical field of mechanical product machining. The method comprises the following steps: broaching a to-be-processed workpiece to form an internal spline straight tooth structure; the straight tooth structure of the internal spline is subjected to inverted conical tooth extrusion machining, and metal allowance generated by extrusion deformation synchronously flows to the tooth side area and the small-diameter area of the internal spline; a straight tooth extrusion tool matched with an inverted conical tooth extrusion tool is adopted, secondary extrusion machining is conducted on the straight tooth area of the internal spline, and metal allowance flowing to the tooth side area of the internal spline is completely transferred to the small-diameter area; and the small-diameter area of the internal spline is machined, a bulge structure formed by the transferred metal allowance is removed, and machining of the reverse taper teeth of the internal spline is completed. Secondary gear burnishing is used, the small-diameter allowance is removed through follow-up machining, and the problem that the machining cost of an original internal spline reverse taper gear is too high is solved.

The invention discloses a mechanical product multi-field simulation and prediction system based on digital twinning, and relates to the technical field of thermal error digital twinning. A main shaft load current, a rotating speed, a bearing temperature, a workpiece surface temperature and a cooling liquid parameter are obtained in real time; rapidly predicting a first thermal error according to the load current and the rotating speed by using a preset multi-layer feed-forward neural network, dynamically calculating a thermal inertia time coefficient in combination with the cooling liquid efficiency and the thermal state of a workpiece, and filtering and extracting a slowly-changing thermal state from the temperature of a main shaft bearing according to the thermal inertia time coefficient, thereby obtaining second thermal error prediction; a fusion weight is generated according to the load current change rate and the thermal inertia time coefficient, weighted fusion is carried out on the two predicted values, and a compensation instruction is output; and by monitoring the stability of the fusion weight, the thermal inertia time is reversely and dynamically adjusted to suppress oscillation. According to the method, high-robustness and self-adaptive accurate compensation of complex thermal errors is realized in field processing with changeable environments and working conditions, and the long-term stability of processing precision is remarkably improved.

The invention discloses a mechanical product overhaul life determination method based on preventive maintenance, and relates to the technical field of mechanical product reliability and maintenance engineering, and the method comprises the following steps: S1, constructing a mechanical product disciplinary cross equation; s3, constructing a mechanical product performance degradation model based on preventive maintenance, and estimating unknown parameters by adopting a maximum likelihood estimation method so as to determine a relationship between a performance degradation amount and time; and S4, estimating parameters of the performance degradation model and finally determining the overhaul life of the mechanical product. According to the method, the influence of preventive maintenance on the mechanical product performance is comprehensively considered, the performance fluctuation and degradation process caused by the maintenance activity is described by constructing the segmented performance degradation function, and the relationship between the performance degradation amount and the time is determined by using the maximum likelihood estimation method; and the finally determined overhaul life of the mechanical product is more accurately applied to an actual engineering scene.

This application provides a method for uncertainty analysis in mechanical product assembly performance simulation. This method considers the impact of various uncertainty factors at different stages of the simulation process on assembly performance, classifying these factors into two categories for quantitative analysis. The first category includes the measurement, modeling, and simulation analysis stages in the early stages of simulation; the uncertainty u or error of these factors can be directly calculated. The second category consists of assembly performance uncertainties caused by external loads, boundary conditions, and nonlinear processes primarily based on geometric error distribution. For this category, this method uses simulation analysis results from a physical digital twin model, combined with the construction of an optimal SVR surrogate model and Sobol global sensitivity analysis, to quantitatively analyze the sensitivity of assembly performance to process parameters. In summary, this method provides guidance for the product assembly process.

The invention relates to semi-automatic material loading and unloading equipment, belongs to the technical field of production material logistics treatment devices, and is used for circulating and conveying materials such as raw materials, tools, semi-finished products and finished products in the production process of mechanical products. Comprising a transferring assembly, a supporting assembly, a sliding rail assembly and the like. The power roller drives the belt to load and unload materials, the electrode drives the transferring assembly and the supporting assembly to slide along the guide rail to carry the materials, and the equipment is good in stability, high in operation efficiency, simple in structure and light in self weight. The material circulation efficiency is improved, the production cost and the labor intensity are reduced, and safety accidents in the carrying process are effectively reduced.

1. Name of the designed product: adjusting screw. 2. Use of the designed product: used in engineering machinery and other mechanical products. 3. Design points of the designed product: in shape. 4. Picture or photo showing the design points: perspective view.

The invention provides a Composer-based pipeline fluid simulation and mechanical motion scene design method. The method comprises the following steps of: simulating a demonstration animation by mechanical structure motion; pipeline fluid flow simulation demonstration animation; and disassembling the simulation demonstration animation by the equipment assembly body. According to the invention, in daily digital design work, an existing digital product model can be conveniently and rapidly utilized to dynamically display the aspects of assembly, principles and the like, such as simulation demonstration of a complex pipeline system operation process and a system principle, simulation demonstration of technological process decomposition of a large-scale product, simulation demonstration of equipment maintenance and the like; and simulating and demonstrating a working scene of a mechanical product.

The present application relates to the field of laser welding, especially to a mechanical product multi-station laser welding machine. The mechanical product multi-station laser welding machine comprises a workbench, a laser, a three-axis module, an inclination mechanism, a laser head, a feeding mechanism and the like; the workbench is internally provided with the laser, the top of the workbench is provided with the three-axis module, the laser head is installed on the three-axis module through the inclination mechanism, and the laser head can adjust the pitch angle under the action of the inclination mechanism. Through the clamping piece, in the process of clamping the workpiece, when one small semicircular block contacts the workpiece, the large semicircular block and the middle semicircular block will automatically rotate until the other small semicircular block contacts the workpiece, and then the large semicircular block and the middle semicircular block stop rotating, so that each small semicircular block clamps the workpiece, so that the workpiece can be fixed more stably, and the fixation of workpieces with different shapes can be adapted.

A cutting insert (1) comprising: a basic body (3), comprising a first area (9), a second surface (11) which is arranged on one of the sides opposite the first surface (9), a first side surface (13) which is connected to the first surface (9) and the second surface (11), a second side surface (15) connected to the first surface (9), the second surface (11) and the first side surface (13), a first recess (17) which leads into the first surface (9), the first side surface (13) and the second side surface (15), and a second recess (19) which leads into the second surface (11), the first side surface (13) and the second side surface (15), a first part (5) with a triangular plate shape, which is arranged in the first recess (17) and has a first cutting edge (21) which is arranged at an intersection of two adjacent surfaces, and a second part (7) with a triangular plate shape, which is arranged in the second recess (19) and has a second cutting edge (23) which is arranged at an intersection of two adjacent surfaces, wherein the first recess (17) has a first floor surface (25) which is arranged away from the first surface (9), a first wall surface (27) which is arranged between the first floor surface (25) and the first surface (9), and a first valley line (29) which is located at an intersection of the first floor surface (25) and the first wall surface (27), the second recess (19) a second floor surface (31) which is arranged away from the second surface (11), a second wall surface (33) which is arranged between the second floor surface (31) and the second surface (11), and a second valley line (35) which is located at an intersection of the second floor surface (31) and the second wall surface (33), and where the first valley line (29) intersects the second valley line (35) in a perspective view onto the first surface (9).

The utility model relates to the technical field of mechanical product detection, and discloses a high-precision detection device for long cylinder radial run-out, which comprises a supporting underframe, a guide rail platform is fixedly connected to the upper surface of the supporting underframe, and a lateral limiting frame is fixedly connected to the left side of the upper surface of the guide rail platform. A drivable bearing supporting device, a measuring meter supporting frame and a limiting bearing supporting device are slidably connected to the upper portion of the guide rail platform through sliding block connecting assemblies, and guide rail locking devices are fixedly connected to the outer side of the limiting bearing supporting device and the outer side of the drivable bearing supporting device through bolts. According to the utility model, through the cooperation of the guide rail platform, the servo motor, the drivable bearing supporting device, the measuring meter supporting frame, the limiting bearing supporting device and other structures, the adaptability of the device is improved, workpieces with different shaft diameters and lengths can be measured, one-machine detection of workpieces with multiple sizes is realized, and the detection efficiency is improved. And the use cost and the occupied space are greatly reduced.

The utility model discloses a stranding disc for a cable stranding machine, which relates to the technical field of mechanical products and comprises a main body, a first connecting plate is arranged in the middle of the main body, a wire winding plate is arranged on the inner side of the first connecting plate, a wire winding column is arranged in the wire winding plate, a connecting end is arranged on one side of the first connecting plate, and the connecting end is connected with the first connecting plate. A power box is arranged at the outer end of the connecting end, a support is arranged at the lower end of the connecting end, and a cut-off plate is arranged on one side of the connecting end. According to the device, a plurality of wire twisting discs can be spliced together, a plurality of strands of cables can be wound at the same time, the working efficiency of the device is improved, the wire twisting discs can buffer pressure generated when the cables are wound and stored, the situation that the cables are damaged due to extrusion and use of the cables is affected is prevented, and the service life of the device is prolonged. And the wire twisting disc can be detachably connected to the middle part of the fixed groove, so that the wire twisting disc is convenient to carry, and the convenience of the device is improved.

The utility model relates to the technical field of marking machine brackets, in particular to a portable bracket for a marking machine, which aims to solve the technical problem that the marking area and efficiency are limited by the shape of a bracket in the use process due to the irregular characteristics of mechanical products, and comprises a marking machine connecting bracket, the marking machine connecting support is connected to the lower portion of the portable marking machine, the bottom wall of the marking machine connecting support is connected with the positioning support, the length and the width of the positioning support are smaller than those of the surface of a marked workpiece, and the marking head can move in the marking machine connecting support and the positioning support. The shapes of the connecting support and the positioning support of the marking machine are directly machined in a punch forming or bending forming mode, the machining mode is simple, production and machining of products are facilitated, operation is easy during installation, in the using process, when mechanical products with irregular characteristics are marked, marking work can be completed more excellently and rapidly in a limited marking area, and the production efficiency is improved. And interference with other characteristics is avoided.

The invention relates to the technical field of reliability design analysis of mechanical products, in particular to a non-parametric reliability analysis method for a high-speed driving roller, which comprises the following steps of: S1, acquiring fault data of the high-speed driving roller, and combining the same fault time in the fault data into a fault time point ti; s2, calculating a risk value of each fault time point ti according to a Nelson-Aalen estimation method, and performing continuous accumulation to obtain an accumulation risk function # imgabs0 #; S3, calculating a reliability function # imgabs2 # according to the accumulation risk function # imgabs1 # to obtain reliability; s4, non-parametric reliability degree confidence evaluation based on Nelson-Aalen estimation is carried out; the problem of reliability calculation when the theoretical distribution of the fault time of the high-speed driving roller is uncertain in engineering practice can be solved.

The invention discloses a reliability evaluation method and device for a ship iterative mechanical product, a medium and a product, and relates to the field of reliability evaluation of ship mechanical products, and the method comprises the steps: obtaining a historical degradation and failure data set of a similar product of a target product; the historical degradation and failure data set is preprocessed; obtaining a degradation trend model of the similar product based on the preprocessed historical degradation and failure data set; acquiring supplementary test data of the target product; based on the supplementary test data, improving the degradation trend model to obtain a target product degradation trend model; and performing reliability evaluation on the target product based on the target product degradation trend model to obtain a multi-dimensional reliability evaluation index of the target product. According to the invention, the reliability evaluation efficiency, accuracy and real-time performance of the ship mechanical product can be improved.

The invention relates to the technical field of assembly task allocation, and discloses a mechanical product assembly task allocation method and system, which are used for solving the problems that when a plurality of available schemes exist during mechanical product assembly task allocation, the optimal scheme cannot be accurately selected, and the schemes cannot be adjusted in real time according to field state changes. Calculating and evaluating all the preliminary task allocation schemes to obtain a qualified task allocation scheme set, calculating a corresponding multi-dimensional normalized margin value for each qualified task allocation scheme in the qualified task allocation scheme set, selecting a final task allocation scheme, performing conflict detection on the final task allocation scheme, and if a conflict exists, determining that the final task allocation scheme does not exist. If yes, correcting the final task allocation scheme to obtain a final corrected task allocation scheme; and if the conflict item does not exist, the final task allocation scheme is directly regarded as the final corrected task allocation scheme, so that the continuity and intelligence of the mechanical product assembly process are effectively improved.

The invention relates to the field of simulation, in particular to a simulation test method and device for a mechanical product, electronic equipment and a storage medium, and the method comprises the steps: obtaining project information of a research and development product from a mechanical product research and development system, and controlling a design end to transmit the project information to a simulation end for display; controlling the simulation end to create a simulation task corresponding to the research and development product based on the project information, and controlling the simulation end to display the simulation task; a simulation report obtained after execution of the simulation task is completed is obtained, and the simulation end is controlled to display the simulation report; controlling the simulation end to transmit a verification result of the simulation report to the design end for display; responding to the test operation of the research and development product based on the verification result in the design end, generating a test task, and controlling the design end to send the test task to the test end for display; and obtaining a test report after the execution of the test task is completed, and displaying the test report at the design end, the test end and the simulation end. According to the invention, the research and development efficiency of mechanical products is improved.

The invention belongs to the technical field of mechanical product abrasion, and particularly relates to a method for testing abrasion of a rolling linear guide rail pair. The guide rail pairs are combined and installed in pairs, multiple sets of samples connected in series through the sliding blocks can be tested at the same time, the sliding blocks are static during testing, the reciprocating workbench pulls the tested guide rails to do reciprocating linear movement in two directions, and the tension effect on the guide rails along the center line of a raceway is formed. The multi-action hydraulic loading mechanism equivalently transmits a load to a position between a guide rail and a sliding block of each tested guide rail pair through a sample sliding block connected with the multi-action hydraulic loading mechanism, and can apply four types of loads: 1, horizontal force vertical to a reciprocating motion direction; 2, a couple moment acting along a horizontal plane; 3, a couple moment acting along a vertical plane parallel to the reciprocating movement direction; and 4, a couple moment acting along a vertical plane perpendicular to the reciprocating motion direction. On the basis, the abrasion and the service life change of the guide rail pair under the condition that the guide rail pair bears all kinds of loads can be tested and verified through two changes of sample combination and installation modes.

A marine garbage cleaning device includes a frame, a conveyor belt is provided on the frame, a pulley is provided at the output end of the conveyor belt, an output wheel is connected to the pulley, a double-headed motor is connected to the output wheel, a front roller is provided at the input end of the conveyor belt, swingable outer swing arms are provided on both sides of the input end of the conveyor belt, and a garbage bin is provided below the output end of the conveyor belt. The beneficial effects of the present invention are: it can realize the automatic collection of marine garbage, greatly improve the efficiency of marine environmental sanitation cleaning, save time and labor, and can reduce the danger of marine garbage disposal, ensure the personal safety of workers, and as a mechanical product, it can help the majority of working people reduce their safety risks and meet the needs of marine garbage disposal in harsh environments.

This invention discloses a method for constructing a knowledge graph from 3D digital model design data for mechanical products. It primarily addresses the problem that existing technologies cannot acquire, represent, and reuse 3D model design data. The implementation scheme is as follows: 1) Integrating and processing the 3D model data; 2) Constructing a knowledge acquisition program to extract a total knowledge set from the 3D model; 3) Representing and constraining the total knowledge set to obtain a processed knowledge set; 4) Instantiating and tree-forming the processed knowledge set to generate feature trees representing functions, structures, and constraints; 5) Analyzing and processing the obtained feature trees to form sets of structure-structure, structure-function, and structure-constraint relationships; 6) Importing the obtained feature trees and relationship sets into triplet form into Neo4j to generate a knowledge graph. This invention can extract, represent, and reuse design data from 3D digital models and can be used for intelligent design of structural schemes for mechanical products.

The invention provides a complex mechanical product demand tracing method based on a demand management model, and the method comprises the steps: firstly analyzing a SysML demand model of a complex mechanical product, and constructing a heterogeneous graph structure with multiple attributes; constructing a heterogeneous graph neural network model based on an HGT architecture, and training the heterogeneous graph neural network model by adopting a training data set containing positive and negative samples and pseudo label data; verifying the correctness of the demand relationship in the SysML demand model of the complex mechanical product by using the trained heterogeneous graph neural network model, and identifying hidden demand association; and when a new demand or relationship is added, dynamically updating the heterogeneous graph neural network model through an incremental learning method. According to the method, automatic verification of the demand relationship and mining of potential association are realized, and the efficiency and reliability of demand management of complex mechanical products are remarkably improved.

A computer-implemented method of designing a 3D modeled object representing a mechanical product. The 3D modeled object has a feature tree and an original value of a set of semantic parameters. The method includes by a user graphically interacting with the 3D representation graphically selecting a semantic point of an outer surface of the 3D modeled object and graphically selecting one or more target 3D positions of the semantic point. The method further includes, automatically, iteratively modifying the value of the set of semantic parameters. Thereby the method obtains an updated value of the set of semantic parameters. The method further includes, automatically by the CAD system, updating the 3D representation of the 3D modeled object based on the updated value of the set of semantic parameters. This provides an improved solution for updating 3D modeled objects based on graphical interactions.

A robot joint component rapid splicing structure comprises a first joint connecting base and a second joint connecting base, two inclined bayonet platform parts are arranged on the upper side of the first joint connecting base, long-strip-shaped clamping inclined faces A are arranged on the opposite sides of the two inclined bayonet platform parts, and the long-strip-shaped clamping inclined faces A are obliquely arranged in the length direction and the width direction; an inclined clamping block platform part is arranged on the lower side of the second joint connecting base, long-strip-shaped clamping inclined faces B are arranged on the two opposite sides of the inclined clamping block platform part and matched with the long-strip-shaped clamping inclined faces A. Two stable limiting side platform faces are further arranged on the two sides of the inclined clamping block platform part. The two stable limiting side platform surfaces are tightly attached to the upper surfaces of the two inclined bayonet platform parts; a pulling locking device is further arranged between the first joint connecting base and the second joint connecting base. According to the utility model, the structure is simple and convenient to splice, convenient to disassemble, assemble, maintain and expand, and high in connection strength and stability, so that the overall performance and reliability of mechanical products are improved.

The present invention relates to a method for predicting the remaining life of a small sample machine based on a support vector machine model, comprising the following steps: selecting a number of measurement variables with obvious trends from the operation signal data of a mechanical product as characteristic quantities describing the mechanical degradation process, and obtaining characteristic values ​​of each characteristic quantity; preprocessing the characteristic values: using a Butterworth filter algorithm to smooth the characteristic quantities of each mechanical degradation process; mapping the characteristic values ​​to the same range by a normalization method; converting the remaining life of the machine at each time point in the existing data into the proportion of the remaining life to the total life, and normalizing it to the range of [0, 1]; dividing a plurality of training sets and validation sets into combinations, each combination corresponding to a support vector machine model; training each support vector machine model; and using each support vector machine model to perform online remaining life prediction. The method makes full use of limited mechanical operation data and can realize accurate prediction of the remaining life of the machine.

The present application relates to the technical field of assembly task allocation, and discloses a mechanical product assembly task allocation method and system, which are used to solve the problems that when mechanical product assembly task allocation is performed, multiple available schemes exist, the optimal scheme cannot be accurately selected, and the scheme cannot be adjusted in real time according to the change of the field state, and comprise the following steps: calculating and evaluating qualified task allocation scheme sets in all preliminary task allocation schemes, calculating a corresponding multi-dimensional normalized margin value for each qualified task allocation scheme in the qualified task allocation scheme sets, and selecting a final task allocation scheme; performing conflict detection on the final task allocation scheme, if there is a conflict, modifying the final task allocation scheme to obtain a final modified task allocation scheme; and if there is no conflict item, directly regarding the final task allocation scheme as the final modified task allocation scheme, thereby effectively improving the continuity and intelligence of the mechanical product assembly process.

A cutting insert (1), comprising: a first surface (3) having a corner (9) with a convex-curved shape in an outward direction and a first side (11) and a second side (13) extending each from the corner (9), a second surface (5) which is arranged on one of the sides opposite the first surface (3), and a third surface (7) arranged between the first surface (3) and the second surface (5), wherein an imaginary plane that is orthogonal to a central axis (O1) passing through a center point of the first surface (3) and a center point of the second surface (5), and is arranged between the first surface (3) and the second surface (5), is assumed to be the reference plane, the first surface (3) further has an inclined surface (17) which approaches the reference plane with increasing distance from the corner (9), the inclined surface (17) a first inclined surface (19) which is inclined at a first angle (θ1), a second inclined surface (21) which is arranged further away from the corner (9) than the first inclined surface (19) and is inclined at a second angle (θ2), and a third inclined surface (23) which is arranged further away from the corner (9) than the second inclined surface (21) and is inclined at a third angle (θ3), the first inclined surface (19) has a concave-curved shape in a cross-section orthogonal to an angle bisector (L1) of the corner (9), the second inclined surface (21) is a flat surface, and, in a cross-section that includes the angle bisector (L1) of the corner (9) and is orthogonal to the reference plane, the second angle (θ2) is smaller than the first angle (θ1) and the third angle (θ3), wherein in a top view of the first surface (3) a length (L32) of the third inclined surface (23) in a direction orthogonal to the angle bisector (L1) of the corner (9) is greater than a length (L22) of the second inclined surface (21) in the direction orthogonal to the angle bisector (L1) of the corner (9).

The invention discloses a machine learning and case-based reasoning hybrid-driven mechanical product design method, which comprises the following steps: firstly, constructing an alternative case set, and then constructing a product demand-product parameter correlation matrix and a product function clustering relation matrix based on domain knowledge; decomposing a new mechanical product design task into a plurality of parallel subtasks, and constructing a clustering model of the subtasks by utilizing the clustering relationship; solving the clustering model by adopting a genetic algorithm to obtain a solved product function clustering relation matrix; on the basis of values of clustering relations in the product function clustering relation matrix, product parameters with the same clustering relation serve as a subtask; obtaining a demand parameter associated with each sub-task through the matrix, sorting the sub-tasks, obtaining an available case set through demand parameter retrieval, constructing a classification model, and training a neural network model; and for each subtask, obtaining a design result of the subtask through the classification model and the neural network model.