Mechanical property-oriented 3D printing intelligent analysis method, device, equipment and medium

Abstract

The invention provides a mechanical property-oriented 3D printing intelligent analysis method, device and equipment and a medium, and the method comprises the steps that 3D printing request parameters input by a user are acquired through a large model interaction interface, and the 3D printing request parameters comprise element request parameters and process request parameters; generating a target element request parameter based on a sub-parameter corresponding to each element in the element request parameters, and generating a target process request parameter based on a sub-parameter corresponding to each process parameter in the process request parameters; determining a target alloy performance prediction model corresponding to a main element in the element request parameters, converting the request parameters into a programming language to call the target alloy performance prediction model, and performing alloy mechanical performance prediction on the target element request parameters and the target process request parameters; and a mechanical property prediction result is displayed on a large model interaction interface. In this way, a user-friendly and rapid alloy process and performance optimization can be achieved, and the 3D printing effect is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a 3D printing intelligent analysis method and device for mechanical properties, equipment and medium. BACKGROUND

[0002] Additive Manufacturing (AM), also known as Three-Dimensional (3D) printing, is an advanced manufacturing technology that builds three-dimensional physical components layer by layer based on digital models. In the field of metal additive manufacturing, the combination of alloy composition and process parameters (such as laser power, scanning speed, heat treatment system, etc.) directly affects the microstructure and mechanical properties of the formed components. Among them, yield strength (YS), ultimate strength (US) and fracture elongation (FE) are key mechanical performance indicators, and there is often a competitive relationship between these properties, and it is often difficult to achieve the coordinated optimization of multiple target properties relying only on traditional experimental methods.

[0003] In recent years, artificial intelligence technology has developed rapidly, providing new technical possibilities for intelligent design and accurate performance prediction of alloy composition and process parameters. Therefore, how to build an intelligent analysis system that combines domain knowledge and data-driven, and flexibly call coding languages through natural language, to achieve efficient optimization of user-friendly 3D printing alloy mechanical properties and rapid iteration of process, has become a key technical challenge that needs to be solved in the current field. SUMMARY

[0004] Therefore, the present application provides a 3D printing intelligent analysis method and device for mechanical properties, equipment and medium to at least solve the technical problems existing in the related art.

[0005] According to a first aspect of the present application, a 3D printing intelligent analysis method for mechanical properties is provided, the method comprising: obtaining a 3D printing request parameter input by a user through a large model interaction interface, the 3D printing request parameter comprising an element request parameter and a process request parameter; the element request parameter comprising a sub-parameter corresponding to each element, and the process request parameter comprising a sub-parameter corresponding to each process parameter; generating a target element request parameter based on the sub-parameter corresponding to each element in the element request parameter, and generating a target process request parameter based on the sub-parameter corresponding to each process parameter in the process request parameter; According to the main element indicated in the element request parameter, a target alloy performance prediction model corresponding to the main element is determined, and the target element request parameter and the target process request parameter are converted from natural language to programming language to call the target alloy performance prediction model; The target alloy performance prediction model is used to predict the mechanical properties of the alloy according to the target element request parameter and the target process request parameter, and a mechanical property prediction result is obtained, and the mechanical property prediction result is displayed on the large model interaction interface.

[0006] In an optional implementation, the target element request parameter is generated based on the sub-parameters corresponding to each element in the element request parameter, and the target process request parameter is generated based on the sub-parameters corresponding to each process parameter in the process request parameter, including: The sub-parameters corresponding to each element in the element request parameter are checked for numerical type and numerical range, and if the check passes, the target element request parameter is generated based on the sub-parameters corresponding to each element in the element request parameter; The sub-parameters corresponding to each process parameter in the process request parameter are checked for numerical type and numerical range, and if the check passes, the target process request parameter is generated based on the sub-parameters corresponding to each process in the process request parameter.

[0007] In an optional implementation, the sub-parameters include minimum value, maximum value and step length; the target element request parameter is generated based on the sub-parameters corresponding to each element in the element request parameter, and the target process request parameter is generated based on the sub-parameters corresponding to each process parameter in the process request parameter, including: The minimum value, maximum value and step length corresponding to each element in the element request parameter are spliced according to a preset format to generate the target element request parameter; The minimum value, maximum value and step length corresponding to each process parameter in the process request parameter are spliced according to the preset format to generate the target process request parameter.

[0008] In an optional implementation, the method further includes at least one of the following: In any case where a sub-parameter is empty, the sub-parameter content is set to a parameter default value; In any case where a sub-parameter check fails, the range of the sub-parameter is adjusted to meet the preset requirements; In any case where the range of a sub-parameter does not meet the preset requirements, an exception prompt information is generated, and the exception prompt information is displayed on the large model interaction interface.

[0009] In an optional implementation, the process request parameters include printing process parameters and heat treatment process parameters; the printing process parameters include laser power, scanning speed, layer thickness, and scanning spacing; and the heat treatment process parameters include treatment temperature and treatment time.

[0010] In an optional implementation, the alloy mechanical property prediction based on the target element request parameters and the target process request parameters includes: constructing a combined parameter space based on the target element request parameters and the target process request parameters; the combined parameter space includes a plurality of target combined parameters, and each target combined parameter group includes an element parameter group and a process parameter group; inputting each target combined parameter in the combined parameter space into the target alloy performance prediction model to obtain a mechanical property prediction result of the combined parameter space, and displaying the mechanical property prediction result on the large model interactive interface.

[0011] In an optional implementation, after obtaining the mechanical property prediction result, the method further includes: when the data amount of the mechanical property prediction result is greater than a preset threshold, storing the mechanical property prediction result in an object storage service in a way of drawing a histogram by writing code, for calling by the large model; and / or, when the data amount of the mechanical property prediction result is not greater than the preset threshold, caching the mechanical property prediction result to a remote dictionary server, for calling by the large model.

[0012] In an optional implementation, the mechanical property indicators include at least one of yield strength, elongation at break, and ultimate strength, and the displaying of the mechanical property prediction result on the large model interactive interface includes: displaying, on the large model interactive interface, a target 3D printing parameter corresponding to an optimal at least one mechanical property indicator; and / or, displaying, on the large model interactive interface, a distribution diagram of the prediction result of the at least one mechanical property indicator.

[0013] In an optional implementation, the method further includes: obtaining, through the large model interactive interface, a user input of an associated problem related to 3D printing; querying, by the large model, the associated problem, and generating a corresponding feedback result.

[0014] According to a second aspect of the present application, a 3D printing intelligent analysis device for mechanical properties is provided, the device comprising: a parameter acquisition module configured to acquire 3D printing request parameters input by a user through a large model interactive interface, wherein the 3D printing request parameters comprise element request parameters and process request parameters, the element request parameters comprise sub-parameters corresponding to each element, and the process request parameters comprise sub-parameters corresponding to each process parameter; a parameter generation module configured to generate target element request parameters based on the sub-parameters corresponding to each element in the element request parameters, and generate target process request parameters based on the sub-parameters corresponding to each process parameter in the process request parameters; a model calling module configured to determine a target alloy performance prediction model corresponding to a main element indicated in the element request parameters, and convert the target element request parameters and the target process request parameters from a natural language into a programming language to call the target alloy performance prediction model; a performance prediction module configured to perform alloy mechanical property prediction on the target element request parameters and the target process request parameters by using the target alloy performance prediction model, obtain a mechanical property prediction result, and display the mechanical property prediction result on the large model interactive interface.

[0015] In an optional implementation, the parameter generation module is specifically configured to: perform a numerical type and numerical range check on the sub-parameters corresponding to each element in the element request parameters, and generate target element request parameters based on the sub-parameters corresponding to each element in the element request parameters if the check is passed; perform a numerical type and numerical range check on the sub-parameters corresponding to each process parameter in the process request parameters, and generate target process request parameters based on the sub-parameters corresponding to each process parameter in the process request parameters if the check is passed.

[0016] In an optional implementation, the sub-parameters comprise minimum values, maximum values, and step lengths, and the parameter generation module is specifically configured to: splice the minimum values, the maximum values, and the step lengths corresponding to each element in the element request parameters according to a preset format to generate the target element request parameters; splice the minimum values, the maximum values, and the step lengths corresponding to each process parameter in the process request parameters according to the preset format to generate the target process request parameters.

[0017] In an optional implementation, the parameter generation module is further configured to perform at least one of the following: In any case where a sub-parameter input is empty, the content of the sub-parameter is set to a parameter default value; In any case where a sub-parameter check fails, the range of the sub-parameter is adjusted to meet the preset requirements; In any case where the range of a sub-parameter does not meet the preset requirements, an abnormal prompt information is generated and displayed on the large model interaction interface.

[0018] In an optional implementation, the process request parameters include printing process parameters and heat treatment process parameters; the printing process parameters include laser power, scanning speed, layer thickness, and scanning spacing; and the heat treatment process parameters include treatment temperature and treatment time.

[0019] In an optional implementation, the performance prediction module is specifically configured to: Based on the target element request parameters and the target process request parameters, a combined parameter space is constructed; the combined parameter space includes a plurality of target combined parameters, each target combined parameter group includes an element parameter group and a process parameter group; Each target combined parameter in the combined parameter space is input into the target alloy performance prediction model to obtain a mechanical performance prediction result of the combined parameter space, and the mechanical performance prediction result is displayed on the large model interaction interface.

[0020] In an optional implementation, the performance prediction module is further configured to: When the data amount of the mechanical performance prediction result is greater than a preset threshold, the mechanical performance prediction result is stored in an object storage service in a code writing histogram drawing manner for the large model to call; and / or, When the data amount of the mechanical performance prediction result is not greater than the preset threshold, the mechanical performance prediction result is cached to a remote dictionary server for the large model to call.

[0021] In an optional implementation, the mechanical performance indicators include at least one of yield strength, elongation at break, and ultimate strength, and the performance prediction module is specifically configured to: At least one mechanical performance indicator optimal corresponding target 3D printing parameter is displayed on the large model interaction interface; and / or, A distribution graph of the prediction result of at least one mechanical performance indicator is displayed on the large model interaction interface.

[0022] In an optional implementation, the parameter acquisition module is further configured to: An associated problem input by a user through the large model interaction interface is acquired; The large model is used to query the correlation problem, and a corresponding feedback result is generated.

[0023] According to a third aspect of the present application, an electronic device is provided, comprising a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor communicates with the memory through the bus, and the machine readable instructions are executed by the processor to perform the steps of the mechanical performance oriented 3D printing intelligent analysis method of the first aspect.

[0024] According to a fourth aspect of the present application, a computer readable storage medium is provided, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to perform the steps of the mechanical performance oriented 3D printing intelligent analysis method of the first aspect.

[0025] The mechanical performance oriented 3D printing intelligent analysis method, device, electronic device and storage medium provided by the present application can obtain the element request parameter and the process request parameter input by the user through the interactive interface of the large model, and can generate the target request parameter that can be recognized by the alloy performance prediction model based on the request parameter input by the user, and then call the target alloy performance prediction model to perform alloy performance prediction on the target request parameter, obtain the mechanical performance prediction result and display it on the interactive interface. In this way, the user can determine whether the current input 3D printing request parameter range is reasonable according to the mechanical performance prediction result, and can also select corresponding parameters for 3D printing according to the mechanical performance prediction result combined with different performance requirements, thereby facilitating rapid improvement of the performance effect of 3D printing. In addition, by embedding the alloy mechanical performance prediction agent in the large model, not only can the coding language be converted into natural language to ensure data processing and performance output from the large model dialogue box, realize automatic correction of parameters and flexibility and visibility of interaction, but also can reduce manual intervention and reduce error propagation risk, which is conducive to improving the robustness of the model prediction result.

[0026] In order to make the above-mentioned purposes, features and advantages of the present disclosure more obvious and easy to understand, the following preferred embodiments are specifically described below, and the accompanying drawings are described as follows. BRIEF DESCRIPTION OF DRAWINGS

[0027] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0028] Figure 1 This is a flowchart illustrating an exemplary embodiment of the present application of an intelligent analysis method for 3D printing oriented towards mechanical properties; Figure 2 This is a schematic diagram of a parameter input interface for a large model interactive interface, as illustrated in an exemplary embodiment of this application. Figure 3 This is a flowchart illustrating an exemplary embodiment of the present application of a method for predicting alloy properties using a model; Figure 4 This is a schematic diagram of a display interface for predicting mechanical properties, as shown in an exemplary embodiment of this application. Figure 5 This is a schematic diagram of a display interface for another mechanical performance prediction result, as illustrated in an exemplary embodiment of this application. Figure 6 This is a functional block diagram of an intelligent 3D printing analysis device for mechanical properties, as illustrated in an exemplary embodiment of this application. Figure 7 This is a schematic diagram of the structure of an electronic device shown in an exemplary embodiment of this application. Detailed Implementation

[0029] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0030] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0031] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0032] In this document, the term "and / or" merely describes a relationship, indicating that three relationships can exist. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Furthermore, the term "at least one" in this document means any combination of at least two of any one or more elements. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0033] All user-related data involved in the technical solution of this application are obtained with the user's authorization, such as through pop-up windows or by inviting individuals to upload their own data.

[0034] In additive manufacturing, different designs of alloy composition parameters and printing process parameters (such as laser power, scanning speed, heat treatment temperature and time) can significantly affect material properties.

[0035] Research has revealed that while existing machine learning models can be used for alloy process and performance optimization, they suffer from poor generalization ability, generally small parameter spaces, and a tendency for optimal solutions to local optima. Traditional general-purpose models lack expertise in alloys, are prone to "illusions" or significant biases in predicting alloy mechanical properties, and struggle to reliably handle complex alloy design and process optimization problems. Therefore, how to utilize artificial intelligence technology to design reasonable 3D printing parameters to meet the needs of alloy design and performance prediction is a pressing technical problem that needs to be solved.

[0036] Based on the above research, this application constructs a collaborative predictive agent that integrates domain knowledge and model reasoning by encapsulating HTTP (Hypertext Transfer Protocol) and embedding a dedicated intelligent agent. This aims to improve the reliability of large-scale model predictions of alloy mechanical properties and its ability to handle complex problems in this field, thereby guiding the optimization of 3D printing parameters to meet the needs of alloy design and performance prediction. Specifically, by gradually developing an HTTP encapsulation module and a dedicated intelligent agent embedding module for the alloy performance prediction model, alloy domain knowledge can be integrated into the large model. Then, the large model can directly call the alloy performance prediction intelligent agent (hereinafter referred to as the alloy performance prediction model) through a dialog box to predict alloy mechanical properties and optimize alloy composition design and processing technology.

[0037] For example, the alloy performance prediction agent can be designed for performance prediction scenarios guided by the composition of multiple alloying elements and processing technology, such as iron (Fe) alloys and titanium (Ti) alloys. Based on the relevant characteristics of the alloy performance prediction agent, the predicted properties include mechanical properties such as yield strength, ultimate strength, and elongation at break, and the mechanical properties can guide the design of alloy composition and optimization of processing technology.

[0038] Specifically, this application provides an intelligent analysis method for 3D printing oriented towards mechanical properties. It can obtain user-inputted 3D printing request parameters through a large model interactive interface. These parameters include element request parameters and process request parameters. The element request parameters include sub-parameters corresponding to each element, and the process request parameters include sub-parameters corresponding to each process parameter. Then, based on the sub-parameters corresponding to each element in the element request parameters, target element request parameters are generated, and based on the sub-parameters corresponding to each process parameter in the process request parameters, target process request parameters are generated. Next, according to the principal element indicated in the element request parameters, a target alloy performance prediction model corresponding to the principal element is determined and invoked. Finally, the target alloy performance prediction model is used to predict the mechanical properties of the alloy based on the target element request parameters and the target process request parameters, obtaining the mechanical property prediction results, which are then displayed on the large model interactive interface.

[0039] In this embodiment, the user-input element request parameters and process request parameters can be obtained through the interactive interface of the large model. Based on the user-input request parameters, a target request parameter that the alloy performance prediction model can recognize can be generated. Then, the target alloy performance prediction model is called to predict the alloy performance of the target request parameter, obtaining the mechanical performance prediction result, which is displayed on the interactive interface. In this way, users can judge whether the currently input 3D printing request parameters are reasonable based on the mechanical performance prediction results. Furthermore, based on the mechanical performance prediction results and different performance requirements, users can select corresponding parameters for 3D printing, thereby facilitating a rapid improvement in 3D printing performance. In addition, by embedding an alloy mechanical performance prediction intelligence into the large model, not only can automatic error correction be achieved, improving the flexibility and visibility of the interaction, but also reducing manual intervention and the risk of error propagation, which is beneficial to improving the robustness of the model's prediction results.

[0040] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0041] To facilitate understanding of this embodiment, the executing entity of the intelligent analysis method for 3D printing oriented towards mechanical properties will first be introduced. The executing entity of this intelligent analysis method for 3D printing oriented towards mechanical properties can be an electronic device. The electronic device can include a terminal device or a server. The terminal device can include mobile devices, user terminals, terminals, vehicle-mounted devices, computing devices, and wearable devices, etc. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data, and artificial intelligence platforms.

[0042] In some possible implementations, this intelligent analysis method for 3D printing oriented towards mechanical properties can be implemented by a processor calling computer-readable instructions stored in memory.

[0043] See Figure 1 The diagram shown is a flowchart of an intelligent analysis method for 3D printing oriented towards mechanical properties provided in an embodiment of this application. The method includes the following steps S101 to S105: S101, obtain the 3D printing request parameters input by the user through the large model interactive interface. The 3D printing request parameters include element request parameters and process request parameters. The element request parameters include sub-parameters corresponding to each element, and the process request parameters include sub-parameters corresponding to each process parameter.

[0044] Among them, large models refer to large artificial intelligence models, which are a class of artificial intelligence models with a large number of parameters constructed by artificial neural networks.

[0045] For example, each input parameter may include three sub-parameters: minimum value (min), maximum value (max), and step value (step). The minimum value, maximum value, and step value of each parameter constitute the parameter range.

[0046] In some embodiments, the element request parameters may include elemental content parameters for multiple elements. For example, the element request parameters may include iron, titanium, aluminum, silicon, etc., and the specific combination can be made according to the user's actual printing needs, without specific limitations. The process request parameters may include printing process parameters and heat treatment process parameters. Specifically, the printing process parameters may include laser power, scanning speed, scanning spacing, and layer thickness. The heat treatment process parameters include processing temperature (also known as holding temperature) and processing time (also known as holding time).

[0047] For example, such as Figure 2 As shown, users can input corresponding parameters in the interactive interface of the large model. For example, to facilitate parameter input, operation buttons such as "Add Element" can be displayed in the interactive interface. Users can click on these buttons to input the corresponding element name and its sub-parameters (minimum value, step size, maximum value). Here, element parameters refer to the parameters of the element content corresponding to the element.

[0048] In some embodiments, after the user enters the corresponding element name, the interface can display a range of sub-parameter suggestions for that element to avoid inappropriate input due to blind input. Furthermore, for printing process parameters and heat treatment process parameters, range suggestions can also be provided for each parameter, allowing the user to input an appropriate parameter range within the corresponding scope. Figure 2 As shown, for the laser power parameter, the corresponding minimum value is 100W, the maximum value is 4000W, and the step size is 500. Users can choose to input 200W~3000W and limit the step size to 500.

[0049] It should be noted that, in addition to the parameters mentioned above, the true value of the "room temperature heat treatment" parameter can be determined in the large model interactive interface. This "room temperature heat treatment" parameter is a Boolean variable, and whether the parameter is true or false indicates whether the influence of room temperature is considered.

[0050] S102, based on the sub-parameters corresponding to each element in the element request parameters, generate target element request parameters, and based on the sub-parameters corresponding to each process parameter in the process request parameters, generate target process request parameters.

[0051] After obtaining the sub-parameters corresponding to each parameter through the interactive interface of the large model, the target request parameters can be generated based on the sub-parameters corresponding to each parameter.

[0052] In some embodiments, in order to improve the performance of subsequent model prediction, each sub-parameter can be verified first, and the corresponding target request parameter can be generated only if the verification passes. Therefore, in this embodiment, when generating target element request parameters based on the sub-parameters corresponding to each element in the element request parameters, and generating target process request parameters based on the sub-parameters corresponding to each process parameter in the process request parameters, the following (1)~(2) can be included: (1) Validate the numerical type and numerical range of the sub-parameters corresponding to each element in the element request parameters, and generate the target element request parameters based on the sub-parameters corresponding to each element in the element request parameters if the validation passes. (2) Verify the numerical type and numerical range of the sub-parameters corresponding to each process parameter in the process request parameters, and generate the target process request parameters based on the sub-parameters corresponding to each process in the process request parameters if the verification passes.

[0053] Here, after obtaining the sub-parameters corresponding to each parameter, the type and value range of each sub-parameter can be validated first. Specifically, validation code can be pre-set, so that after obtaining the parameters, the pre-set code can be called to perform the validation. For example, taking the iron alloy performance prediction agent as an example, based on the elemental composition, processing technology, and heat treatment process, the mechanical properties of iron (Fe) alloy are predicted. The specific parameter range validation code is set as follows: :param Fe_min: Minimum value of iron (60.00-100.00) :param Fe_max: Maximum value of iron (60.00-100.00) :param Fe_step: Iron step value (0-20) :param Ti_min: Minimum value for titanium (0.00-1.50) :param Ti_max: Maximum value of titanium (0.00-1.50) :param Ti_step: Titanium step value (0.00-1.50) ...... :param room_temperature: Whether to perform room temperature control (True / False) :param laser_power_min: Minimum laser power (100-4000) :param laser_power_max: Maximum laser power (100-4000) :param laser_power_step: Laser power step value (0-500) :param scan_speed_min: Minimum scan speed (100-2000) :param scan_speed_max: Maximum scan speed (100-2000) :param scan_speed_step: Scan speed step value (0-500) ...... It should be noted that the parameter range verification settings described above for predicting the properties of ferroalloys are merely examples, and these parameter range verification settings can be extended to other alloy property prediction models.

[0054] Furthermore, in some embodiments, the method further includes setting the content of any sub-parameter to a default value when any sub-parameter is passed as empty. That is, when the user enters an empty parameter through the large model interaction interface, the default parameter value preset by the backend can be directly invoked. An example of setting the default value is as follows: # Elemental composition parameters Fe_min: float = Field(60, ge=0, description="Minimum value of iron element") #Fe element is the principal element and must be present. The default range is 60~100, and the default value is 60. Fe_max: float = Field(100, ge=0, description="Maximum value of iron") #ge=0 means the minimum value must be greater than or equal to 0 Fe_step: float = Field(5, ge=0, description="iron element step size") ...... # Room temperature heat treatment room_temperature: bool = Field(True, description="Whether to consider the effect of room temperature") # Process parameters laser_power_min: float = Field(200, gt=0, description="Minimum laser power") #gt=0 means the minimum value must be greater than 0 laser_power_max: float = Field(600, gt=0, description="maximum laser power") laser_power_step: float = Field(100, ge=0, description="laser power step size") scan_speed_min: float = Field(500, gt=0, description="Minimum scan speed") scan_speed_max: float = Field(1000, gt=0, description="maximum scan speed") scan_speed_step: float = Field(100, ge=0, description="scan speed step size") ...... In this way, by calling pre-set prompt words and codes, the sub-parameters of each parameter input by the user can be validated and passed in.

[0055] Optionally, in some embodiments, the method further includes: If any sub-parameter fails validation, the range of the sub-parameter is adjusted to meet preset requirements; and / or, If any sub-parameter does not meet the preset requirements, an error message is generated and displayed through the large model interactive interface.

[0056] Here, the sub-parameter can be a sub-parameter of any of the aforementioned parameters. For example, if the user inputs a laser scanning speed of 5000 mm / s through the large model's interactive interface (a speed that is too fast and difficult to achieve in actual working conditions), which is clearly unreasonable, the large model will directly adjust according to the parameter range prompts set in the backend to make it meet the preset requirements. In addition, abnormal prompts can be generated and displayed through the large model's interactive interface along with the adjustment content. In this way, on the one hand, the large model can automatically adjust its parameters to ensure normal operation; on the other hand, the user can iterate and correct the input parameters based on the abnormal prompts.

[0057] In some embodiments, when generating target element request parameters based on the sub-parameters corresponding to each element in the element request parameters, and generating target process request parameters based on the sub-parameters corresponding to each process parameter in the process request parameters, the following (I) to (II) may be included: (I) The minimum value, maximum value and step size corresponding to each element in the element request parameters are concatenated according to a preset format to generate the target element request parameters; (II) The minimum value, maximum value and step size of each process parameter in the process request parameters are concatenated according to the preset format to generate the target process request parameters.

[0058] For example, a pre-defined concatenation function can be used, followed by a custom concatenation function to concatenate the input parameters into a format that is convenient for the backend alloy performance prediction model to call. A specific example is as follows: DEFAULT_ELEMENTS_CONFIG = { 'Fe': {'min': 60.00, 'max': 100.00, 'step': 5}, 'Ti': {'min': 0.00, 'max': 1.5, 'step': 0.30}, 'Co': {'min': 0.00, 'max': 10.00, 'step': 5}, ... } DEFAULT_PROCESS_CONFIG = { 'laser_power': {'min': 100, 'max': 400, 'step': 100}, 'scan_speed': {'min': 100, 'max': 1500, 'step': 200}, 'hatch_spacing': {'min': 0.05, 'max': 0.2, 'step': 0.05}, 'layer_thickness': {'min': 0.02, 'max': 0.06, 'step': 0.02}, 'holding_temperature': {'min': 600, 'max': 1000, 'step': 100}, 'time': {'min': 1.5, 'max': 3, 'step': 0.5}, } room_temperature = False Where Fe represents iron, Ti represents titanium, and Co represents cobalt. `laser_power` represents laser power, `scan_speed` represents scanning speed, `hatch_spacing` represents the scanning spacing, `layer_thickness` represents layer thickness, `holding_temperature` represents the temperature, `time` represents processing time, and `room_temperature` indicates whether room temperature processing is performed.

[0059] S103, based on the primary element indicated in the element request parameters, determine the target alloy performance prediction model corresponding to the primary element, and convert the target element request parameters and the target process request parameters from natural language into programming language to call the target alloy performance prediction model.

[0060] It's understandable that 3D printing requires multiple alloying elements, and among these elements, a dominant element is necessary. Therefore, users can specify which element is the dominant element when inputting parameters. This allows the prediction of mechanical properties to be performed using the target alloy property prediction model corresponding to that dominant element, thus improving the accuracy of the model's predictions. For example, for... Figure 2 In the interactive interface shown, if the user does not explicitly specify the main element, the first element among the multiple input elements can be determined as the main element.

[0061] For example, several combined parameters can be pre-collected as training samples, each combined parameter including elemental parameters and process parameters. That is, experimental and literature data on 3D printed alloys can be extracted, alloy elements and process parameters (printing process and heat treatment process) can be selected as input parameters, and mechanical properties such as yield strength, elongation at break and ultimate strength can be used as target variables. The model can be trained based on various machine learning algorithms to obtain a trained alloy performance prediction model. Here, during training, different alloy performance prediction models can be trained for different principal elements.

[0062] In some embodiments, the alloy performance prediction model can be encapsulated as an HTTP interface, so that it can be called directly via an HTTP URL; on the other hand, large models can be called based on this interface through further encapsulation as described below.

[0063] For example, the HTTP prediction interface can be abstracted into a utility function, such as fe(), based on MCP (Model Context Protocol) technology, with MCP_name defined as PredictionFe. This encapsulates the prediction capabilities, making it easier for large models to translate the natural language in the front-end dialog box into programming language and directly call the prediction model. Furthermore, as mentioned earlier, only the input range of the parameters is set in the parameter passing section, ensuring flexibility in inputting to the front end of the large model.

[0064] In some embodiments, to enable direct viewing of the alloy performance prediction model's output from the large model's client, a REDISS (Remote Dictionary Server) data query interface can be created to ensure that the prediction results can be successfully returned to the large model's front-end. Optionally, the alloy performance prediction model's interface (Prediction_Blueprint) can be integrated with other services, and CORS (Cross-Origin Resource Sharing) configuration can be used to ensure cross-origin requests support calls to the large model's front-end page.

[0065] S104, using the target alloy performance prediction model to predict the target element request parameters and the target process request parameters, the mechanical properties of the alloy are predicted, the mechanical properties prediction results are obtained, and the mechanical properties prediction results are displayed on the large model interactive interface.

[0066] For step S104, see Figure 3 As shown, when using the target alloy performance prediction model to predict the target element request parameters and the target process request parameters to obtain the mechanical property prediction results, the following steps S1041~S1042 may be included: S1041, Based on the target element request parameters and the target process request parameters, construct a combined parameter space; the combined parameter space includes multiple target combined parameters, and each target combined parameter group includes an element parameter group and a process parameter group.

[0067] For example, after obtaining the target element request parameters in a pre-formatted, concatenated form, it is possible to iterate through various elements in the target element request parameters and construct the element parameter combination based on the parameter range of the element content parameters of each element, with the total content of all elements being 100% as the content constraint. That is, it is possible to iterate through all elements and sum them, and then filter for combinations where the total element content is 100%.

[0068] In some embodiments, a main component element, such as Fe or Ti, can be set. The content of this element is only restricted by upper and lower limits and not by step size, so as to ensure that the total sum of elements can still reach 100% under different element step precisions. For example, the element composition includes Fe / Ti / Co / Ni / Mo / C / Mn / Si / Cr / Al, which respectively represent iron, titanium, cobalt, nickel, molybdenum, carbon, manganese, silicon, chromium, and aluminum. For this set of element parameters, several groups of element parameters can be obtained.

[0069] In addition, for the obtained target process request parameters in the preset format after splicing, the printing process parameters can be traversed. According to the parameter ranges of each printing process parameter, a set of printing parameters that meet the volumetric energy density constraint conditions can be selected to construct the combination of printing parameters. After obtaining the combination of printing parameters, it can be combined with the heat treatment parameters respectively to obtain the combination of process parameters.

[0070] Here, the laser power, scanning speed, layer thickness, and scanning spacing in the printing process parameters can be restricted by the volumetric energy density (VED) constraint conditions. Therefore, after traversing all the printing process parameters, an effective combination with VED within a specific range (for example, 30 < VED < 200) can be selected to obtain the combination of process parameters. The volumetric energy density constraint condition can be that the ratio between the magnitude of the laser power and the target product is within a preset range, and the target product is the product of the scanning speed, the scanning spacing, and the layer thickness.

[0071] After obtaining the combination of process parameters and the combination of element parameters, the combination of element parameters and the combination of process parameters can be matched through the Cartesian product to obtain a combination parameter space including multiple target combination parameters.

[0072] S1042, input each target combination parameter in the combination parameter space into the target alloy property prediction model to obtain the mechanical property prediction results of the combination parameter space, and display the mechanical property prediction results on the large model interaction interface.

[0073] In some embodiments, the mechanical property indexes include at least one of yield strength, fracture elongation, and ultimate strength. When displaying the mechanical property prediction results on the large model interaction interface, it can include: displaying the target 3D printing parameters corresponding to the optimal at least one mechanical property index on the large model interaction interface.

[0074] See Figure 4As shown, the optimal parameter combination for each mechanical performance index can be displayed on the large model interactive interface. For example, when the yield strength performance is optimal, the corresponding performance parameters are: yield strength 1240.88 MPa, elongation at break 12.36%, ultimate strength 1183.67 MPa; the corresponding elemental composition is: Fe 100.00%, Ti 0.00%, Co 0.00%, Ni 0.00%, Mo 0.00%, C 0.00%, Mn 0.00%, Si 0.00%, Cr 0.00%, Al 0.00%; printing process parameters: laser power 200.00W, scanning speed 500.00 mm / s, layer thickness 0.06 mm, spacing 0.08 mm; heat treatment process: holding temperature 400.00°C, holding time 6.00h.

[0075] In some embodiments, see Figure 5 As shown, when displaying the mechanical performance prediction results on the large model interactive interface, the method may further include: displaying a distribution map of the predicted values ​​of at least one mechanical performance index on the large model interactive interface. For example, if the combined parameter space contains 10,000 target combined parameters, predictions can be made for these 10,000 combined parameters to obtain the performance distribution of the 10,000 samples at yield strength, elongation at break, and ultimate strength, respectively. In this embodiment, the user can select the result of any performance index to display through the display interface, and can also switch between different performance indices.

[0076] In some embodiments, the mechanical performance prediction results may include at least one of the following: the range of predicted values ​​of mechanical performance indicators, the distribution of predicted values ​​of mechanical performance indicators, the predicted values ​​of mechanical performance indicators, and the corresponding printing parameters.

[0077] That is, the obtained mechanical property prediction results may also include: the optimal values ​​of each mechanical property and the corresponding alloy composition and process parameters, the summary of the entire performance space, the input parameters and mechanical properties corresponding to the 50 points with the best performance (or other values), the input parameters and mechanical properties corresponding to the 50 points with uniform performance distribution (or other values), and the performance distribution map of the entire prediction space.

[0078] Understandably, after obtaining the mechanical property prediction results, the results can be returned directly. For example, after obtaining the performance prediction results, the target alloy performance prediction model can directly output and display them through its own web interface. Optionally, the mechanical property prediction results can also be cached in Redis for use by larger models.

[0079] Here, different caching methods can be used for output results with different memory sizes. Considering that the mechanical performance data of the entire prediction space obtained after prediction is often large, we use code to draw histograms and save them to OSS (Object Storage Service) for convenient subsequent transmission and retrieval. Prediction results with smaller memory footprints are directly cached in Redis. Furthermore, to facilitate interaction with large models, the prediction results can be written to a unified JSON file according to partitions and cached in Redis. At this point, only image URLs are cached in the JSON, so the memory usage is small. Separating large memory (images) from regular data can speed up transmission.

[0080] Therefore, in some embodiments, after obtaining the predicted mechanical properties, the method further includes: When the amount of data in the mechanical performance prediction results exceeds a preset threshold, the mechanical performance prediction results are stored in an object storage service by writing code to draw a histogram, so that the large model can call them; and / or, When the amount of data in the mechanical performance prediction results is not greater than the preset threshold, the mechanical performance prediction results are cached to a remote dictionary server for use by the large model.

[0081] Furthermore, large models can optimize prediction performance and adjust for errors that occur during the prediction process, such as... Figure 4 As shown at point A, while displaying the performance prediction results, an alarm message is also displayed to remind the user that the element limit has been adjusted. Additionally, corresponding code can be set to provide feedback on the running status, such as "Prediction successful," "Ineffective execution," and "Model prediction failed; please check parameter settings."

[0082] Understandably, in some embodiments, the large model can not only obtain the 3D printing request parameters input by the user, but also provide feedback on user-inputted questions related to 3D printing. Therefore, the method may further include the following steps (a) to (b): (a) Obtain user-inputted questions related to 3D printing through the large model interactive interface; (b) Query the related questions based on the large model and generate corresponding feedback results.

[0083] As described in the foregoing embodiments, after inputting the corresponding parameters into the large model's interactive interface, the large model can first consider and judge the data, and then call the corresponding alloy performance prediction model. During this process, the large model can also determine whether the input parameters are reasonable. If unreasonable, it can correct them based on the backend description and the large model's own reasoning ability, and then call the alloy performance prediction model again for subsequent predictions. If reasonable, it directly performs predictions based on the input parameters. After the alloy performance prediction model finishes its prediction, the large model can call the performance prediction results according to user needs and directly return the mechanical performance prediction results in the dialog interface. For example, this could be the optimal mechanical properties and their corresponding composition and process parameters. The ferroalloy performance prediction model could return the optimal yield strength, optimal fracture elongation, and optimal ultimate strength.

[0084] Furthermore, warning messages and corresponding adjustments that may occur during the prediction process will also be displayed in the dialog interface. Additionally, it can respond to user requests to view a bar chart of the overall prediction performance for a preset number of samples (100,000 points), and the image can be dynamically switched between different performance levels (e.g., ...). Figure 5 (As shown). Additionally, if the user enters a dialogue in the interactive interface, such as "the top 20 points with optimal yield strength," a corresponding response can be returned in the dialog box. If the user enters "please state the application of this alloy proportion," the large model's own knowledge base and reasoning capabilities can be invoked to provide a corresponding answer. In summary, embedding the alloy performance prediction model into the large model not only demonstrates the advantages of a flexible and user-friendly interface but also effectively improves the accuracy of the large model's alloy performance predictions and its ability to optimize complex issues such as alloy composition design and processing technology.

[0085] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0086] Based on the same technical concept, this disclosure also provides an intelligent analysis device for 3D printing oriented towards mechanical performance, which corresponds to the intelligent analysis method for 3D printing oriented towards mechanical performance. Since the principle of the device in this disclosure for solving the problem is similar to the intelligent analysis method for 3D printing oriented towards mechanical performance described above, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0087] Reference Figure 6 The diagram shown is a schematic of an intelligent 3D printing analysis device for mechanical properties provided in an embodiment of this disclosure. The device 600 includes: The parameter acquisition module 601 acquires the 3D printing request parameters input by the user through the large model interactive interface. The 3D printing request parameters include element request parameters and process request parameters. The element request parameters include sub-parameters corresponding to each element, and the process request parameters include sub-parameters corresponding to each process parameter. The parameter generation module 602 generates target element request parameters based on the sub-parameters corresponding to each element in the element request parameters, and generates target process request parameters based on the sub-parameters corresponding to each process parameter in the process request parameters. The model invocation module 603 determines the target alloy performance prediction model corresponding to the main element indicated in the element request parameters, and converts the target element request parameters and the target process request parameters from natural language into programming language to invoke the target alloy performance prediction model. The performance prediction module 604 is used to predict the mechanical properties of the alloy using the target alloy performance prediction model for the target element request parameters and the target process request parameters, obtain the mechanical property prediction results, and display the mechanical property prediction results on the large model interactive interface.

[0088] In one alternative implementation, the parameter generation module 602 is specifically used for: The numerical type and numerical range of the sub-parameters corresponding to each element in the element request parameters are validated. If the validation passes, the target element request parameters are generated based on the sub-parameters corresponding to each element in the element request parameters. The numerical type and range of the sub-parameters corresponding to each process parameter in the process request parameters are validated. If the validation passes, the target process request parameters are generated based on the sub-parameters corresponding to each process in the process request parameters.

[0089] In one optional implementation, the sub-parameters include a minimum value, a maximum value, and a step size; the parameter generation module 602 is specifically used for: The minimum value, maximum value, and step size corresponding to each element in the element request parameters are concatenated according to a preset format to generate the target element request parameters; The minimum, maximum, and step size of each process parameter in the process request parameters are concatenated according to the preset format to generate the target process request parameters.

[0090] In an optional implementation, the parameter generation module 602 is further configured to perform at least one of the following: If any sub-parameter is passed as empty, the content of the sub-parameter is set to the default value. If any sub-parameter fails the verification, the range of the sub-parameter is adjusted to meet the preset requirements; If any sub-parameter does not meet the preset requirements, an error message is generated and displayed through the large model interactive interface.

[0091] In one optional implementation, the process request parameters include printing process parameters and heat treatment process parameters; the printing process parameters include laser power, scanning speed, layer thickness, and scanning spacing; the heat treatment process parameters include processing temperature and processing time.

[0092] In one alternative implementation, the performance prediction module 604 is specifically used for: Based on the target element request parameters and the target process request parameters, a combined parameter space is constructed; the combined parameter space includes multiple target combined parameters, and each target combined parameter group includes an element parameter group and a process parameter group. Each target combination parameter in the combined parameter space is input into the target alloy performance prediction model to obtain the mechanical performance prediction results of the combined parameter space, and the mechanical performance prediction results are displayed on the large model interactive interface.

[0093] In an optional implementation, the performance prediction module 604 is further configured to: When the amount of data in the mechanical performance prediction results exceeds a preset threshold, the mechanical performance prediction results are stored in an object storage service by writing code to draw a histogram, so that the large model can call them; and / or, When the amount of data in the mechanical performance prediction results is not greater than the preset threshold, the mechanical performance prediction results are cached to a remote dictionary server for use by the large model.

[0094] In one optional embodiment, the mechanical performance indicators include at least one of yield strength, elongation at break, and ultimate strength, and the performance prediction module 604 is specifically used for: The large model interactive interface displays the target 3D printing parameters corresponding to at least one optimal mechanical performance index; and / or, The large model's interactive interface displays a distribution map of the predicted results for at least one mechanical performance index.

[0095] In an optional implementation, the parameter acquisition module 601 is further configured to: The user's input regarding 3D printing is obtained through the large model interactive interface; The large model is used to query the related questions and generate corresponding feedback results.

[0096] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this application according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0097] Based on the same technical concept, this disclosure also provides an electronic device. (See also...) Figure 7 The diagram shown is a structural schematic of an electronic device 700 provided in an embodiment of this disclosure, including a processor 701, a memory 702, and a bus 703. The memory 702 is used to store execution instructions and includes a main memory 7021 and an external memory 7022. The main memory 7021, also called internal memory, is used to temporarily store computational data in the processor 701, as well as data exchanged with external memory 7022 such as a hard disk. The processor 701 exchanges data with the external memory 7022 through the main memory 7021.

[0098] In this embodiment, the memory 702 is specifically used to store application code that executes the solution of this application, and its execution is controlled by the processor 701. That is, when the electronic device 700 is running, the processor 701 communicates with the memory 702 through the bus 703, so that the processor 701 executes the application code stored in the memory 702, and then executes the method described in any of the foregoing embodiments.

[0099] The memory 702 may be, but is not limited to, random access memory (RAM), read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0100] Processor 701 may be an integrated circuit chip with signal processing capabilities. The aforementioned processor can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor.

[0101] It is understood that the structures illustrated in the embodiments of this application do not constitute a specific limitation on the electronic device 700. In other embodiments of this application, the electronic device 700 may include more or fewer components than illustrated, or combine some components, or split some components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0102] This disclosure also provides a computer-readable storage medium storing a computer program that, when executed by a processor, performs the steps of the intelligent analysis method for 3D printing oriented towards mechanical properties described in the above-described method embodiments. The storage medium can be a volatile or non-volatile computer-readable storage medium.

[0103] This disclosure also provides a computer program product carrying program code. The program code includes instructions that can be used to execute the steps of the intelligent analysis method for 3D printing oriented towards mechanical performance in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0104] The aforementioned computer program product can be implemented through hardware, software, or a combination thereof. In one optional embodiment, the computer program product is specifically embodied in a computer storage medium; in another optional embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0105] Furthermore, embodiments of the subject matter and functional operation described in this specification can be implemented in the following ways: digital electronic circuits, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or combinations thereof. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions encoded on a tangible, non-transitory program carrier for execution by a data processing apparatus or for controlling the operation of a data processing apparatus. Alternatively or additionally, program instructions may be encoded on artificially generated propagation signals, such as machine-generated electrical, optical, or electromagnetic signals, which are generated to encode information and transmit it to a suitable receiving device for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or combinations thereof.

[0106] The processing and logic flow described in this specification can be executed by one or more programmable computers that execute one or more computer programs to perform corresponding functions by operating on input data and generating output. The processing and logic flow can also be executed by dedicated logic circuitry—such as FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits), and the device can also be implemented as dedicated logic circuitry.

[0107] Suitable computers for executing computer programs include, for example, general-purpose and / or special-purpose microprocessors, or any other type of central processing unit. Typically, the central processing unit receives instructions and data from read-only memory and / or random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices for storing data, such as disks, magneto-optical disks, or optical disks, or the computer will be operatively coupled to such mass storage devices to receive data from or transfer data to them, or both. However, a computer is not required to have such devices. Furthermore, a computer can be embedded in another device, such as a mobile phone, a personal digital assistant (PDA), a mobile audio or video player, a game console, a global positioning system (GPS) receiver, or a portable storage device such as a universal serial bus (USB) flash drive, to name a few.

[0108] Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, such as semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., internal hard disks or removable disks), magneto-optical disks, and CD-ROM and DVD-ROM disks. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0109] While this specification contains numerous specific implementation details, these should not be construed as limiting the scope of any invention or the scope of the claims, but rather are primarily intended to describe features of specific embodiments of a particular invention. Certain features described in the various embodiments herein may also be implemented in combination in a single embodiment. Conversely, various features described in a single embodiment may also be implemented separately in various embodiments or in any suitable sub-combination. Furthermore, while features may function in certain combinations as described above and even initially claimed in this way, one or more features from a claimed combination may be removed from that combination in some cases, and a claimed combination may refer to a sub-combination or a variation thereof.

[0110] Similarly, although the operations are depicted in a specific order in the accompanying drawings, this should not be construed as requiring these operations to be performed in the specific order shown or sequentially, or requiring all illustrated operations to be performed to achieve the desired result. In some cases, multitasking and parallel processing may be advantageous. Furthermore, the separation of various system modules and components in the above embodiments should not be construed as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.

[0111] Thus, specific embodiments of the subject matter have been described. Other embodiments are within the scope of the appended claims. In some cases, the actions recited in the claims may be performed in a different order and still achieve the desired result. Furthermore, the processes depicted in the drawings are not necessarily shown in a specific order or sequence to achieve the desired result. In some implementations, multitasking and parallel processing may be advantageous.

[0112] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for intelligent analysis of mechanical properties in 3D printing, characterized in that, The method includes: The 3D printing request parameters input by the user are obtained through the large model interactive interface. The 3D printing request parameters include element request parameters and process request parameters. The element request parameters include sub-parameters corresponding to each element, and the process request parameters include sub-parameters corresponding to each process parameter. Based on the sub-parameters corresponding to each element in the element request parameters, target element request parameters are generated, and based on the sub-parameters corresponding to each process parameter in the process request parameters, target process request parameters are generated. Based on the primary element indicated in the element request parameters, determine the target alloy performance prediction model corresponding to the primary element, and convert the target element request parameters and the target process request parameters from natural language into programming language to call the target alloy performance prediction model. The target alloy performance prediction model is used to predict the mechanical properties of the target element request parameters and the target process request parameters, and the mechanical property prediction results are obtained and displayed on the large model interactive interface.

2. The method according to claim 1, characterized in that, The process of generating target element request parameters based on the sub-parameters corresponding to each element in the element request parameters, and generating target process request parameters based on the sub-parameters corresponding to each process parameter in the process request parameters, includes: The numerical type and numerical range of the sub-parameters corresponding to each element in the element request parameters are validated. If the validation passes, the target element request parameters are generated based on the sub-parameters corresponding to each element in the element request parameters. The numerical type and range of the sub-parameters corresponding to each process parameter in the process request parameters are validated. If the validation passes, the target process request parameters are generated based on the sub-parameters corresponding to each process in the process request parameters.

3. The method according to claim 1 or 2, characterized in that, The sub-parameters include a minimum value, a maximum value, and a step size; the generation of target element request parameters based on the sub-parameters corresponding to each element in the element request parameters, and the generation of target process request parameters based on the sub-parameters corresponding to each process parameter in the process request parameters, includes: The minimum value, maximum value, and step size corresponding to each element in the element request parameters are concatenated according to a preset format to generate the target element request parameters; The minimum, maximum, and step size of each process parameter in the process request parameters are concatenated according to the preset format to generate the target process request parameters.

4. The method according to claim 2, characterized in that, The method further includes at least one of the following: If any sub-parameter is passed as empty, the content of the sub-parameter is set to the default value of the parameter; If any sub-parameter fails the verification, the range of the sub-parameter is adjusted to meet the preset requirements; If any sub-parameter does not meet the preset requirements, an error message is generated and displayed through the large model interactive interface.

5. The method according to claim 1, characterized in that, The process request parameters include printing process parameters and heat treatment process parameters; the printing process parameters include laser power, scanning speed, layer thickness, and scanning spacing; the heat treatment process parameters include processing temperature and processing time.

6. The method according to claim 1, characterized in that, The step of using the target alloy performance prediction model to predict the target element request parameters and the target process request parameters to obtain the mechanical property prediction results includes: Based on the target element request parameters and the target process request parameters, a combined parameter space is constructed; the combined parameter space includes multiple target combined parameters, and each target combined parameter group includes an element parameter group and a process parameter group. Each target combination parameter in the combined parameter space is input into the target alloy performance prediction model to obtain the mechanical performance prediction results of the combined parameter space, and the mechanical performance prediction results are displayed on the large model interactive interface.

7. The method according to claim 1, characterized in that, After obtaining the predicted mechanical properties, the method further includes: When the amount of data in the mechanical performance prediction results exceeds a preset threshold, the mechanical performance prediction results are stored in an object storage service by writing code to draw a histogram, so that the large model can call them; and / or, When the amount of data in the mechanical performance prediction results is not greater than the preset threshold, the mechanical performance prediction results are cached to a remote dictionary server for use by the large model.

8. The method according to claim 1, characterized in that, The mechanical performance indicators include at least one of yield strength, elongation at break, and ultimate strength. The display of the predicted mechanical performance results on the large model interactive interface includes: The large model interactive interface displays the target 3D printing parameters corresponding to at least one optimal mechanical performance index; and / or, The large model's interactive interface displays a distribution map of the predicted results for at least one mechanical performance index.

9. The method according to claim 1, characterized in that, The method further includes: The user's input regarding 3D printing is obtained through the large model interactive interface; The large model is used to query the related questions and generate corresponding feedback results.

10. A 3D printing intelligent analysis device for mechanical properties, characterized in that, The device includes: The parameter acquisition module acquires the 3D printing request parameters input by the user through the large model interactive interface. The 3D printing request parameters include element request parameters and process request parameters. The element request parameters include sub-parameters corresponding to each element, and the process request parameters include sub-parameters corresponding to each process parameter. The parameter generation module generates target element request parameters based on the sub-parameters corresponding to each element in the element request parameters, and generates target process request parameters based on the sub-parameters corresponding to each process parameter in the process request parameters. The model invocation module determines the target alloy performance prediction model corresponding to the main element indicated in the element request parameters, and converts the target element request parameters and the target process request parameters from natural language into programming language to invoke the target alloy performance prediction model. The performance prediction module is used to predict the mechanical properties of the alloy using the target alloy performance prediction model based on the target element request parameters and the target process request parameters, obtain the mechanical property prediction results, and display the mechanical property prediction results on the large model interactive interface.

11. An electronic device, characterized in that, include: The device includes a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor communicates with the memory via the bus. When the machine-readable instructions are executed by the processor, they perform the steps of the intelligent analysis method for 3D printing oriented towards mechanical properties as described in any one of claims 1-9.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, performs the steps of the intelligent analysis method for 3D printing oriented towards mechanical properties as described in any one of claims 1-9.

Images