Hidden Markov model-based mechanical product design method and system

Abstract

The invention provides a mechanical product design method and system based on a hidden Markov model, and relates to the field of mechanical product manufacturing, and the method comprises the steps: collecting the design information of a mechanical product; decomposing the mechanical product into a plurality of product modules according to the design information, and storing each product module into a database; through the three-dimensional sparse matrix, storing an interface connection relationship of each product module in a database; obtaining a user demand; extracting function requirements of mechanical products in the user requirements; constructing a hidden Markov model, and setting related parameters of the Markov model according to the historical product data and the database; inputting the function requirement into the hidden Markov model, and outputting design configuration; adding a connection relationship to the design configuration according to the interface connection relationship to generate a final design scheme; and carrying out mechanical product design according to the final design scheme. According to the invention, the design efficiency and the complex product design capability are improved.

Description

Technical Field

[0001] The present invention relates to the field of manufacturing mechanical products, and particularly to a mechanical product design method and system based on a Hidden Markov Model. Background Art

[0002] The Hidden Markov Model (HMM) is a statistical model for analyzing time series data, constructed based on a Markov process with hidden states. The HMM consists of a hidden state chain and an observation data chain related to the states. A significant feature of the HMM is its memorylessness, that is, the state transition depends only on the current state and is independent of the historical state of the system. This property makes the HMM have broad application potential in dealing with dynamic systems and sequence data, especially in scenarios where it is necessary to capture state changes and predict future states.

[0003] In a highly competitive market environment, manufacturing enterprises face the challenge of quickly responding to flexible and ever-changing user needs, and at the same time, they also need to accurately predict potential market demands. Therefore, shortening the product design cycle, adapting to market changes, and meeting the needs of potential users have become key tasks for the development of manufacturing enterprises.

[0004] However, in the existing mechanical product design process, designers need to rely on their own experience and knowledge to screen and combine modules. The design results are easily affected by the subjectivity of designers, and the design quality varies. There is a lack of effective tools and methods for efficiently screening and reorganizing modules, resulting in an overly long design cycle. There is a lack of the concept of using HMM for mechanical product design, leading to too low efficiency in mechanical design and unable to quickly generate design solutions that meet functional requirements. Summary of the Invention

[0005] In order to solve the technical problems in the existing mechanical product design process, where designers need to rely on their own experience and knowledge to screen and combine modules, the design results are easily affected by the subjectivity of designers, the design quality varies, there is a lack of effective tools and methods for efficiently screening and reorganizing modules, resulting in an overly long design cycle, and there is a lack of the concept of using HMM for mechanical product design, leading to too low efficiency in mechanical design and unable to quickly generate design solutions that meet functional requirements, the present invention provides a mechanical product design method and system based on a Hidden Markov Model.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] First aspect:

[0008] A mechanical product design method based on a Hidden Markov Model provided by an embodiment of the present invention includes:

[0009] S1: Collect the design information of mechanical products;

[0010] S2: Decompose the mechanical product into multiple product modules according to the design information, and store each product module in the database;

[0011] S3: Store the interface connection relationships of each product module in the database through a three-dimensional sparse matrix;

[0012] S4: Obtain user requirements;

[0013] S5: Extract the functional requirements of the mechanical product in the user requirements;

[0014] S6: Construct a hidden Markov model, and set the relevant parameters of the Markov model according to historical product data and the database;

[0015] S7: Input the functional requirements into the hidden Markov model and output the design configuration;

[0016] S8: Add connection relationships to the design configuration according to the interface connection relationships to generate the final design scheme;

[0017] S9: Perform the design of the mechanical product according to the final design scheme.

[0018] Second aspect:

[0019] A mechanical product design system based on a hidden Markov model provided by an embodiment of the present invention includes:

[0020] A processor;

[0021] A memory, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor, the mechanical product design method based on the hidden Markov model as in the first aspect is implemented.

[0022] Third aspect:

[0023] A computer-readable storage medium provided by an embodiment of the present invention, on which a computer program is stored. When the program is executed by the processor, the mechanical product design method based on the hidden Markov model as in the first aspect is implemented.

[0024] The beneficial effects brought by the technical solutions provided by the embodiments of the present invention at least include:

[0025] In the present invention, through the interface relationship of the three-dimensional sparse matrix storage module, the automatic module screening and configuration can be quickly realized, the design cycle can be shortened, the market demand can be quickly responded to. By constructing a hidden Markov model, the parametric simulation of the screening and matching process of existing modules is realized, the subjective influence of designers is weakened, the design space is effectively expanded, a variety of feasible design configurations are quickly provided for designers, the design workload is reduced, and it can effectively assist designers in quickly designing mechanical products to meet user needs, improving the design efficiency and the design ability of complex products. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other accompanying drawings without creative efforts based on these drawings.

[0027] Figure 1 It is a schematic flow chart of a mechanical product design method based on a hidden Markov model provided by an embodiment of the present invention;

[0028] Figure 2 It is a three-dimensional sparse matrix scatter diagram of the product module interface connection relationship provided by an embodiment of the present invention;

[0029] Figure 3 It is a schematic structural diagram of a mechanical product design system based on a hidden Markov model provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0030] The technical solutions in the present invention will be described below with reference to the accompanying drawings.

[0031] In the embodiments of the present invention, words such as "exemplarily", "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as more preferred or more advantageous than other embodiments or design solutions. Exactly speaking, the use of the word "example" is intended to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two.

[0032] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when their differences are not emphasized, the meanings they express are the same. "(of)", "corresponding" and "corresponding" can sometimes be used interchangeably. It should be noted that when their differences are not emphasized, the meanings they express are the same.

[0033] In the embodiments of the present invention, sometimes subscripts such as W 1 may be written in a non-subscript form such as W1. When the difference is not emphasized, the meanings they express are the same.

[0034] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0035] Referring to the attached Figure 1 of the specification, a schematic flowchart of a mechanical product design method based on a hidden Markov model provided by an embodiment of the present invention is shown.

[0036] An embodiment of the present invention provides a mechanical product design method based on a hidden Markov model. The method includes:

[0037] S1: Collect design information of mechanical products.

[0038] Among them, the design information of mechanical products refers to all the basic data and knowledge required in the mechanical product design process, including but not limited to functional requirements, performance parameters, appearance requirements, manufacturing costs, user requirements, and technical specifications and interface information related to product modules.

[0039] It should be noted that collecting the design information of mechanical products can provide sufficient data support for subsequent module decomposition and design scheme generation. By comprehensively and accurately collecting information, the design requirements can be ensured to be clear and definite, and design deviations caused by information missing can be avoided.

[0040] S2: According to the design information, decompose the mechanical product into multiple product modules and store each product module in a database.

[0041] Among them, the product module database refers to a dedicated database for storing mechanical product modules, including module functions, interfaces, structures, and other relevant information, which is convenient for calling and management during design.

[0042] It should be noted that decomposing the mechanical product into modules and storing them in the database can improve the reusability and design efficiency of the modules, avoid repeated design. The modular design is convenient for product function expansion and rapid iteration, and can shorten the product design cycle.

[0043] In the present invention, taking a hybrid additive manufacturing device as an example, product data of existing hybrid additive manufacturing and related devices of an enterprise is collected. The existing products are decomposed into different structural modules according to the connection relationship to form a product module library. The module types of the hybrid additive manufacturing device include a platform module, a platform attachment module, a processing module, a personalized module, and an interface module. The platform module provides a three-axis module and supports the configuration of a gantry frame and a column frame. The platform attachment module provides a four-axis module and a five-axis module and supports the multi-axis motion configuration of A-axis rotation and C-axis swing. The processing module covers an FDM 3D processing module, a carving processing module, and a laser processing module to meet different material and process requirements. The personalized module covers a function expansion module and has a configuration with reserved interface modules. The interface module supports the vertical and horizontal rotation switching functions for quick switching between modules. The overall design realizes an efficient and flexible device configuration through a modular structure to meet multi-scenario manufacturing requirements.

[0044] In a possible implementation manner, S2 is specifically:

[0045] According to the design information, the mechanical product is decomposed into product modules according to the functional relationship and the structural relationship.

[0046] It should be noted that modularly decomposing the mechanical product according to the functional relationship and the structural relationship can clarify the module function boundaries, optimize the design logic, facilitate module reuse, and the efficient implementation of subsequent designs.

[0047] Refer to the attached Figure 2 illustrates a three-dimensional sparse matrix scatter plot of the interface connection relationship of the product modules provided by the embodiments of the present invention.

[0048] Such as Figure 2 , the horizontal axis (X-axis) and the vertical axis (Y-axis) represent the interface numbers of each module, and the depth axis (Z-axis) represents the interface type. The blue scatter points mark the positions of the non-zero elements in the sparse matrix, indicating the specific interface connection relationship and type distribution between the modules. This figure intuitively reflects the correlation between the modules and the sparse characteristics of the sparse matrix.

[0049] S3: Store the interface connection relationship of each product module in the database through a three-dimensional sparse matrix.

[0050] Among them, the three-dimensional sparse matrix is a special sparse matrix data structure that contains three-dimensional information and is used to efficiently store sparse data. In the present invention, its three dimensions respectively represent the interface number of the module, the connected module number, and the interface type, and are used to describe the connection relationship between the mechanical product modules. The interface connection relationship refers to the physical or functional connection method between different product modules, including the interface number and the interface type, and is used to realize the interaction and cooperation between the modules.

[0051] It should be noted that by storing the interface connection relationships of product modules in a three-dimensional sparse matrix, a large amount of module data can be efficiently managed, the storage space occupation can be reduced, and the matrix structure can clearly describe the connection information between modules, facilitating quick retrieval and updating of interface relationships during design.

[0052] In a possible implementation, the first and second dimensions of the three-dimensional sparse matrix represent the interfaces of each product module.

[0053] The third dimension of the three-dimensional sparse matrix represents the interface types of each product module.

[0054] It should be noted that the first, second, and third dimensions of the three-dimensional sparse matrix can intuitively and efficiently describe the connection relationships between modules and their type distributions, clearly reflecting the logical and functional relationships of complex module systems. At the same time, it can greatly reduce storage redundancy, improve data retrieval speed, facilitate the automation and standardization of modular design, and improve design efficiency and accuracy.

[0055] In a possible implementation, before S3, it also includes:

[0056] When there are connection relationships between each product module, the interface information of each product module is stored in advance.

[0057] It should be noted that storing the interface information of each product module in advance can provide basic data support for subsequent design, facilitate quick retrieval and matching of module connection relationships, improve design efficiency, and reduce design errors.

[0058] S4: Obtain user requirements.

[0059] In a possible implementation, user requirements specifically include: appearance requirements, function requirements, and cost requirements.

[0060] Among them, appearance requirements refer to the specific requirements of users for the appearance design of products, including aesthetic factors such as color, shape, and material. Function requirements refer to the expectations of users for the product to achieve specific functions or performances, such as usage efficiency, reliability, etc. Cost requirements refer to the cost limit requirements of users for product manufacturing and use, including material costs, production costs, and maintenance costs, etc.

[0061] In a possible implementation, clarifying user requirements can comprehensively understand user expectations, so as to better balance aesthetics, functionality, and economy in the design scheme.

[0062] S5: Extract the function requirements of the mechanical product in the user requirements.

[0063] For example, the functional requirements for extracting a hybrid additive manufacturing device are specifically as follows: By analyzing the functions and structures of current non-metal fused deposition modeling (FDM) devices and engraving machines, considering user requirements, processing requirements, and future expectations, a desktop-level, multi-functional, and cost-effective hybrid additive manufacturing device (Hybrid Additive Manufacturing, abbreviated as HAM) is created. Since the non-functional requirements of the HAM device do not affect the design method under discussion, the focus will be placed on functional requirements. The main factors that the HAM device needs to consider are the combination of various processing functions and the coordination of the resulting motion functions. Therefore, the functional requirements are divided into processing functions and motion functions. The processing functions include FDM printing, CNC engraving, and laser processing, while the motion functions involve three-axis, four-axis, and five-axis motions.

[0064] It should be noted that extracting the functional requirements from user requirements can accurately capture the core performance requirements of the product, provide a clear orientation for the design scheme, avoid design deviations, and improve the pertinence and practicality of the design.

[0065] S6: Construct a hidden Markov model and set the relevant parameters of the Markov model according to historical product data and the database.

[0066] Among them, the hidden Markov model is a statistical model composed of a hidden state chain (Markov chain) and an observation data chain related to the state, and is used to handle time series problems with uncertainty and randomness.

[0067] It should be noted that constructing a hidden Markov model and setting parameters according to historical product data and the database can effectively capture the randomness and dynamic change rules in module design. By setting parameters such as the state transition probability and the observation probability matrix, the HMM can simulate the module screening and matching logic in the design process, reduce manual participation, and improve the design accuracy and efficiency.

[0068] In a possible implementation manner, the relevant parameters specifically include: hidden state, observation state, state transition probability matrix, observation probability matrix, and initial state probability distribution.

[0069] In a possible implementation manner, S6 specifically includes:

[0070] S601: Set the hidden state:

[0071] S = {S 1 , S 2 ,..., S N}

[0072] q t ∈S

[0073] Among them, S represents the hidden state, Si represents the i-th hidden state, which is the i-th structural module during the design process, where i = 1, 2, ..., N, and N represents the total number of hidden states, i.e., the total number of structural modules, q t represents the hidden state at time t.

[0074] Specifically, the observation state represents the specific functional requirements of the user for the product. The set of functional requirements includes three-axis motion function (V1), extended motion function (V2), FDM function (V3), engraving function (V4), laser processing function (V5), and switching function (V6).

[0075] S602: Set the observation state:

[0076] V = {v 1 , v 2 ,..., v K}

[0077] o t ∈V

[0078] where V represents the observation state, and v j represents the j-th observation state, which is the j-th functional requirement during the design process, where j = 1, 2, ..., K, and K represents the total number of observation states, i.e., the total number of functional requirements, and o t represents the observation state at time t.

[0079] Specifically, the hidden state represents the actual module configuration adopted inside the product. The set of structural modules includes gantry frame (M1), column frame (M2), extended motion module (M3), FDM 3D printing module (M4), engraving module (M5), laser engraving module (M6), vertical rotation switching module (M7), and horizontal rotation switching module (M8).

[0080] S603: Set the state transition probability matrix:

[0081]

[0082] where A represents the state transition probability matrix, and a ij represents the transition probability from state a i to state a j at adjacent time nodes.

[0083] For example, the state transition probability can be specifically as shown in Table 1:

[0084] Table 1 State Transition Probability

[0085] M1 M2 M3 M4 M5 M6 M7 M8 M1 0 0 0.273 0.182 0.182 0.182 0.091 0.091 M2 0 0 0.231 0.154 0.154 0.154 0.154 0.154 M3 0.500 0.500 0 0 0 0 0 0 M4 0.143 0.143 0 0 0.143 0.143 0.214 0.214 M5 0.143 0.143 0 0.143 0 0.143 0.214 0.214 M6 0.143 0.143 0 0.143 0.143 0 0.214 0.214 M7 0.154 0.154 0 0.231 0.231 0.231 0 0 M8 0.154 0.154 0 0.231 0.231 0.231 0 0

[0086] Such as Figure 1As shown, by setting the state transition probability matrix, the conversion rules between design modules can be accurately described, the dynamic changes of module configurations can be captured, and the prediction ability and optimization efficiency of the design process can be improved.

[0087] S604: Set the observation probability matrix:

[0088] B = {b i (v k )}

[0089] b i (v k ) = P(o t = v k |q t = S i )

[0090] where B represents the observation probability matrix, and b i (v k ) represents the observation probability of observing the functional requirement v i under the hidden state S k , and P represents probability.

[0091] For example, the observation probability matrix can be specifically as shown in Table 2:

[0092] Table 2 Observation Probability Matrix

[0093] Observation state V1 V2 V3 V4 V5 V6 M1 0.8 0 0 0 0 0 M2 0.2 0 0 0 0 0 M3 0 1 0 0 0 0 M4 0 0 1 0 0 0 M5 0 0 0 1 0 0 M6 0 0 0 0 1 0 M7 0 0 0 0 0 0.5 M8 0 0 0 0 0 0.5

[0094] As Figure 2 shown, V1 represents the three-axis motion function, V2 represents the extended motion function, V3 represents the FDM function, V4 represents the engraving function, V5 represents the laser processing function, V6 represents the switching function. Setting the observation probability matrix can quantify the matching relationship between user functional requirements and specific design modules, clarify the implementation possibilities of functional requirements under different module configurations, and thus improve the rationality and accuracy of the design scheme.

[0095] S605: Set the initial state probability distribution:

[0096] π = {π ij}

[0097] where π represents the initial state probability distribution.

[0098] Specifically, in actual operation, the initial probability distribution can be set as:

[0099] π = [0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125, 0.125].

[0100] S7: Input the functional requirements into the Hidden Markov Model and output the design configuration.

[0101] For example, the design configuration may specifically include:

[0102] Design Configuration 1: Gantry frame, extended motion module, vertical rotation switch, engraving module, FDM module, laser engraving module;

[0103] Design Configuration 2: Gantry frame, extended motion module, horizontal rotation switch, engraving module, FDM module, laser engraving module;

[0104] Design Configuration 3: Column frame, extended motion module, vertical rotation switch, engraving module, FDM module, laser engraving module;

[0105] Design Configuration 4: Column frame, extended motion module, horizontal rotation switch, engraving module, FDM module, laser engraving module.

[0106] It should be noted that inputting the functional requirements into the Hidden Markov Model can, based on the dynamic association of user requirements and historical data, quickly generate a design configuration that meets the requirements, avoiding the subjectivity of manual screening, improving the efficiency and accuracy of the design scheme generation, and providing effective support for the intelligent design of complex module systems.

[0107] In a possible implementation manner, S7 specifically includes:

[0108] Take the real-time functional requirements as the observed state sequence, input them into the trained Hidden Markov Model, use the enumeration method to calculate all possible hidden state sequences, and output the design configuration:

[0109]

[0110] Among them, P(q 1 , o 1 , q 2 , o 2 , …, q T , o T |x) represents the joint probability of the hidden state sequence q 1 , q 2 ,..., q T and the observed sequence o 1 , o 2 ,..., o T occurring simultaneously, represents the initial state probability, represents the observation probability of observing the initial functional requirement o 1 under the initial hidden state q 1 of, Denote the observation function requirement o in the hidden state q t under the observation probability t of Denote the hidden state transition probability from time t - 1 to time t, where t = 2, 3, ..., T, and T represents the total duration of the observation sequence and the hidden state sequence.

[0111] Among them, the enumeration method is an algorithm for finding the optimal solution by exhaustively listing all possible solutions. In this step, the enumeration method is used to traverse all possible hidden state sequences in the hidden Markov model, calculate the joint probability of each sequence, and thus find the optimal design configuration.

[0112] It should be noted that by calculating all possible hidden state sequences through the enumeration method, the comprehensiveness and accuracy of the design configuration can be ensured, potential preferred solutions can be effectively avoided from being missed, and at the same time, it is ensured that the generated design solution meets the functional requirements, improving the reliability of the design decision.

[0113] S8: Add connection relationships to the design configuration according to the interface connection relationships to generate the final design solution. It should be noted that adding connection relationships to the design configuration according to the interface connection relationships can ensure the rationality of the connections between modules and the functional integrity, transform the abstract module design configuration into a specific implementable solution, and improve the feasibility of the design solution.

[0114] In a possible implementation manner, S9 specifically includes:

[0115] S901: Retrieve the interface connection relationships in the three-dimensional sparse matrix.

[0116] S902: Add connection information to all modules in the design configuration according to the interface connection relationships to generate the corresponding adjacency matrix.

[0117] S903: Generate the final design solution according to the adjacency matrix.

[0118] S9: Perform mechanical product design according to the final design solution.

[0119] The beneficial effects brought by the technical solutions provided in the embodiments of the present invention at least include:

[0120] In the present invention, by storing the module interface relationships in a three-dimensional sparse matrix, automatic module screening and configuration can be quickly achieved, the design cycle can be shortened, and the market demand can be quickly responded to. By constructing a hidden Markov model, parametric simulation of the screening and matching process of existing modules is realized, the subjective influence of designers is weakened, and the design space is effectively expanded. Multiple feasible design configurations are quickly provided for designers, the design workload is reduced, and it can effectively assist designers in quickly designing mechanical products to meet user needs, improving the design efficiency and the design ability of complex products.

[0121] Refer to the attached specification Figure 3 , which shows a schematic structural diagram of a mechanical product design system based on a hidden Markov model provided by the present invention.

[0122] The present invention also provides a mechanical product design system 20 based on a hidden Markov model, which is applied to the above-mentioned mechanical product design method based on a hidden Markov model, and includes:

[0123] A processor 201.

[0124] A memory 202, on which computer-readable instructions are stored. When the computer-readable instructions are executed by the processor 201, the mechanical product design method based on a hidden Markov model as in the method embodiment is implemented.

[0125] The mechanical product design system 20 provided by the present invention can execute the above-mentioned mechanical product design method based on a hidden Markov model and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate herein.

[0126] The beneficial effects brought by the technical solution provided in the embodiment of the present invention at least include:

[0127] In the present invention, through the three-dimensional sparse matrix storage module interface relationship, the automatic module screening and configuration can be quickly realized, the design cycle can be shortened, the market demand can be quickly responded to. By constructing a hidden Markov model, the parametric simulation of the screening and matching process of existing modules is realized, the subjective influence of designers is weakened, and the design space is effectively expanded. A variety of feasible design configurations are quickly provided for designers, the design workload is reduced, and it can effectively assist designers in quickly designing mechanical products to meet user needs, improve the design efficiency and the design ability of complex products.

[0128] It should be understood that the processor in the embodiment of the present invention may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0129] It should also be understood that the memory in the embodiments of the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0130] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions according to the embodiments of the present invention are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more collections of available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0131] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0132] In the present invention, "at least one" means one or more, and "a plurality" means two or more. "At least one of the following" or its similar expressions refer to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, and c can be single or multiple.

[0133] It should be understood that in various embodiments of the present invention, the magnitudes of the sequence numbers of the above processes do not mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0134] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0135] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the devices, apparatuses, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated herein.

[0136] In several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of devices or units can be electrical, mechanical, or other forms.

[0137] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they can be located in one place, or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0138] In addition, the functional units in each embodiment of the present invention can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit.

[0139] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0140] An embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, it implements the mechanical product design method based on the hidden Markov model as in the method embodiment.

[0141] The computer-readable storage medium provided by the present invention can implement the steps and effects of the mechanical product design method based on the hidden Markov model in the above method embodiment. To avoid repetition, the present invention will not elaborate further.

[0142] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0143] In the present invention, through the three-dimensional sparse matrix storage module interface relationship, the automated module screening and configuration can be quickly realized, the design cycle can be shortened, and the market demand can be quickly responded to. By constructing a hidden Markov model, the parametric simulation of the screening and matching process of existing modules is realized, the subjective influence of designers is weakened, and the design space is effectively expanded. A variety of feasible design configurations are quickly provided for designers, the design workload is reduced, and it can effectively assist designers in quickly designing mechanical products to meet user needs, improving the design efficiency and the design ability of complex products.

[0144] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0145] The following points need to be explained:

[0146] (1) The drawings of the embodiments of the present invention only relate to the structures involved in the embodiments of the present invention, and other structures can refer to the usual designs.

[0147] (2) For clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is enlarged or reduced, that is, these drawings are not drawn to actual scale. It can be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element or there can be intervening elements.

[0148] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0149] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A mechanical product design method based on hidden Markov model, characterized in that: include: S1: Collect design information of mechanical products; S2: Decomposing the mechanical product into a plurality of product modules according to the design information, and storing each product module in a database; S3: storing the interface connection relationship of each product module in the database through a three-dimensional sparse matrix; S4: Obtain user needs; S5: extracting the functional requirements of the mechanical product from the user requirements; S6: constructing a hidden Markov model, and setting relevant parameters of the Markov model according to the historical product data and the database; S7: inputting the functional requirements into the hidden Markov model and outputting a design configuration; S8: adding a connection relationship to the design configuration according to the interface connection relationship to generate a final design solution; S9: Design mechanical products according to the final design plan.

2. The mechanical product design method based on hidden Markov model according to claim 1 is characterized in that: The S2 is specifically: According to the design information, the mechanical product is decomposed into product modules according to functional relationships and structural relationships.

3. The mechanical product design method based on hidden Markov model according to claim 1, characterized in that: The first dimension and the second dimension of the three-dimensional sparse matrix represent the interfaces of each product module; The third dimension of the three-dimensional sparse matrix represents the interface type of each product module.

4. The mechanical product design method based on hidden Markov model according to claim 1, characterized in that: S3 also previously included: When there is a connection relationship between various product modules, the interface information of each product module is stored in advance.

5. The mechanical product design method based on hidden Markov model according to claim 1, characterized in that: The user requirements specifically include: appearance requirements, functional requirements and cost requirements.

6. The mechanical product design method based on hidden Markov model according to claim 1, characterized in that: The relevant parameters specifically include: hidden state, observed state, state transition probability matrix, observation probability matrix and initial state probability distribution.

7. The mechanical product design method based on hidden Markov model according to claim 6 is characterized in that: The S6 specifically includes: S601: Setting the hidden state: S={S1,S2,...,S N } q t ∈S Among them, S represents the hidden state, S i represents the i-th hidden state, which is the i-th structural module in the design process, i = 1, 2, ..., N, N represents the total number of hidden states, i.e. the total number of structural modules, q t represents the hidden state at time t; S602: Setting the observation state: V={v1,v2,...,vK} the t ∈V Among them, V represents the observation state, v j represents the jth observed state, which is the jth functional requirement in the design process, j = 1, 2, ..., K, K represents the total number of observed states, i.e. the total number of functional requirements, o t represents the observed state at time t; S603: Setting the state transition probability matrix: Among them, A represents the state transition probability matrix, a ij Indicates that adjacent time nodes are represented by a i The state is transferred to a j The transition probability of the state. S604: Setting the observation probability matrix: B={b i (v k )} b i (v k )=P(o t =v k |q t =S i ) Among them, B represents the observation probability matrix, b i (v k ) indicates that in the hidden state S i Observation function requirement v k The observation probability, P represents the probability; S605: Setting the initial state probability distribution: π＝{π ij} Among them, π represents the initial state probability distribution.

8. The mechanical product design method based on hidden Markov model according to claim 1, characterized in that: The S7 specifically includes: The real-time functional requirements are used as observation state sequences and input into the trained hidden Markov model. All feasible hidden state sequences are calculated using the enumeration method and the design configuration is output: Among them, P(q1,o1,q2,o2,...,q T ,o T |x) means that under the model parameter x, the hidden state sequence q1,q2,...,q T and the observation sequence o1,o2,...,o T The joint probability of simultaneous occurrence, represents the initial state probability, represents the observation probability of observing the initial functional requirement o1 under the initial hidden state q1, Indicates that in the hidden state q t Observation function requirements t The observation probability of represents the hidden state transition probability from time t-1 to time t, t = 2, 3, ..., T, T represents the total duration of the observation sequence and the hidden state sequence.

9. The mechanical product design method based on hidden Markov model according to claim 1, characterized in that: The S9 specifically includes: S901: Retrieving the interface connection relationship in the three-bit sparse matrix; S902: adding connection information to all modules in the design configuration according to the interface connection relationship, and generating a corresponding adjacency matrix; S903: Generate a final design solution according to the adjacency matrix.

10. A mechanical product design system based on hidden Markov model, characterized in that: include: processor; A memory having computer-readable instructions stored thereon, wherein when the computer-readable instructions are executed by the processor, the mechanical product design method based on the hidden Markov model as described in any one of claims 1 to 9 is implemented.

Images