Wind power product casting design method combined with environmental assessment

Abstract

The present invention relates to a method for designing castings for wind power products in combination with environmental assessment, and belongs to the field of casting design technology. The present invention constructs a digital twin model of castings based on a time series, and then captures the change trend from the digital twin model of castings based on a time series, and constructs a final digital twin model of castings, thereby constructing a wind power product casting life prediction model based on a deep neural network and the final digital twin model of castings, predicting the life data of wind power product castings through the wind power product casting life prediction model, and finally dynamically designing and adjusting the initial process parameter characteristic data based on the life data of wind power product castings. The present invention fully considers the working conditions and working environment of the castings to estimate the life of the wind power product castings at the time of initial design, thereby optimizing the design parameters according to the life of the wind power product castings at the time of initial design, and improving the rationality of the parameter design.

Description

Technical Field

[0001] The present invention relates to the technical field of casting design, and in particular to a wind power product casting design method combined with environmental assessment. Background Art

[0002] Castings are metal shaped objects obtained by various casting methods. That is, smelted liquid metal is poured into a pre-prepared mold by pouring, injection, suction or other casting methods. After cooling, it is polished and other subsequent processing methods to obtain an object with a certain shape, size and performance. The requirements for wind power product castings are as follows: (1) Mechanical properties: Wind turbine castings should have sufficient strength and hardness to ensure that they can operate in harsh environments and withstand harsh weather conditions and wind forces. (2) Corrosion resistance: Since wind turbine castings are often in high altitudes and humid environments, the material needs to be corrosion-resistant. (3) Wear resistance: Castings are easily worn during use, so they need to have certain wear resistance. (4) Thermal stability: During the casting process, it is necessary to select materials that can withstand high temperatures to ensure that the castings will not be deformed or damaged. Among them, if the design of wind power product castings is unreasonable, it will cause problems with the castings and high maintenance costs. Summary of the Invention

[0003] The present invention overcomes the deficiencies of the prior art and provides a wind power product casting design method combined with environmental assessment.

[0004] In order to achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides a method for designing a wind power product casting in combination with an environmental assessment, characterized in that the method comprises the following steps:

[0006] Obtaining initial process parameter characteristic data of the wind power product casting and characteristics of the working environment of the wind power product casting, and constructing a time series-based casting digital twin model based on the initial process parameter characteristic data of the wind power product casting and characteristics of the working environment of the wind power product casting;

[0007] capturing change trends from the time series-based digital twin model of the casting and constructing a final digital twin model of the casting;

[0008] Constructing a wind power product casting life prediction model based on a deep neural network and the final casting digital twin model, and predicting the life data of the wind power product casting using the wind power product casting life prediction model;

[0009] The initial process parameter characteristic data is dynamically designed and adjusted based on the life data of the wind power product casting.

[0010] Furthermore, in the wind power product casting design method combined with environmental assessment, a time series-based casting digital twin model is constructed based on the initial process parameter characteristic data of the wind power product casting and the environmental characteristics of the wind power product casting, specifically including:

[0011] Constructing a three-dimensional model of the wind power product casting using three-dimensional modeling software based on the initial process parameter characteristic data of the wind power product casting, and combining the working environment characteristics of the wind power product casting as constraint conditions;

[0012] Simulating through digital twin technology, constructing and initializing timestamps, obtaining three-dimensional model feature data of the wind power product casting in each timestamp under the constraints, and sorting the three-dimensional model feature data of the wind power product casting in each timestamp in chronological order;

[0013] By sorting in chronological order, a digital twin model of the casting based on the time series is obtained, and the digital twin model of the casting based on the time series is output.

[0014] Furthermore, in the wind power product casting design method combined with environmental assessment, the change trend is captured from the time series-based casting digital twin model to construct the final casting digital twin model, specifically:

[0015] Acquire model feature data of the digital twin model of the casting from the time series-based digital twin model of the casting, and count the model feature data of the digital twin model of the casting to obtain model change feature data of the digital twin model of the casting within a preset time;

[0016] Calculating a model change amount based on the model change characteristic data of the casting digital twin model within a preset time, setting a model change amount threshold, and determining whether the model change amount is greater than the model change amount threshold;

[0017] When the model change amount is greater than the model change amount threshold, reducing the time window length in the time series;

[0018] When the model change is not greater than the model change threshold, the time window length in the time series is maintained unchanged, and the final casting digital twin model is constructed.

[0019] Furthermore, in the wind power product casting design method combined with environmental assessment, a wind power product casting life prediction model is constructed based on the deep neural network and the final casting digital twin model. Specifically:

[0020] Constructing a wind power product casting life prediction model based on a deep neural network, obtaining device resource data of a data processing device, and initializing the model complexity of the wind power product casting life prediction model;

[0021] According to the model complexity of the wind power product casting life prediction model, the model features of the final casting digital twin model are input into the wind power product casting life prediction model for coding learning to obtain the model prediction speed and prediction accuracy of the wind power product casting life prediction model;

[0022] Setting a model parameter evaluation index, and when the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, maintaining the model complexity of the wind power product casting life prediction model unchanged;

[0023] When the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, the model complexity of the current wind power product casting life prediction model is reduced.

[0024] Furthermore, in the wind power product casting design method combined with environmental assessment, the life data of the wind power product casting is predicted by the wind power product casting life prediction model, specifically:

[0025] Acquiring service data information of wind power product castings within a preset time, and inputting the service data information of wind power product castings within the preset time into the wind power product casting life prediction model for prediction;

[0026] The life data of the wind power product casting is obtained through prediction, and the life data of the wind power product casting is output.

[0027] Furthermore, in the wind power product casting design method combined with environmental assessment, the initial process parameter characteristic data is dynamically adjusted based on the life data of the wind power product casting, specifically including:

[0028] Setting a threshold range of life data of a wind power product casting, and determining whether the life data of the wind power product casting is within the threshold range of the life data of the wind power product casting;

[0029] When the life data of the wind power product casting is within a life data threshold range of the wind power product casting, designing is performed according to the initial process parameter characteristic data;

[0030] When the life data of the wind power product casting is not within the life data threshold range of the wind power product casting, the initial process parameter characteristic data is adjusted until the life data of the wind power product casting is within the life data threshold range of the wind power product casting.

[0031] A second aspect of the present invention provides a wind power product casting design system combined with environmental assessment, comprising a memory and a processor, wherein the memory includes a wind power product casting design method program combined with environmental assessment, and when the wind power product casting design method program combined with environmental assessment is executed by the processor, any step of the wind power product casting design method combined with environmental assessment is implemented.

[0032] The third aspect of the present invention provides a computer-readable storage medium, including a wind power product casting design method program combined with environmental assessment. When the wind power product casting design method program combined with environmental assessment is executed by a processor, it implements any step of the wind power product casting design method combined with environmental assessment.

[0033] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0034] The present invention obtains the initial process parameter characteristic data of the wind power product casting and the working environment characteristics of the wind power product casting, and constructs a casting digital twin model based on a time series according to the initial process parameter characteristic data of the wind power product casting and the working environment characteristics of the wind power product casting, and then captures the change trend from the casting digital twin model based on the time series, constructs a final casting digital twin model, and thus constructs a wind power product casting life prediction model based on a deep neural network and the final casting digital twin model, predicts the life data of the wind power product casting through the wind power product casting life prediction model, and finally dynamically designs and adjusts the initial process parameter characteristic data based on the life data of the wind power product casting. The present invention fully considers the working conditions and working environment of the casting to estimate the life of the wind power product casting at the time of initial design, thereby optimizing the design parameters according to the life of the wind power product casting at the time of initial design, and improving the rationality of the parameter design. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, without paying any creative work, they can also obtain drawings of other embodiments based on these drawings.

[0036] Figure 1 The overall flow chart of the wind power product casting design method combined with environmental assessment is shown;

[0037] Figure 2 The system block diagram of the wind power product casting design system combined with environmental assessment is shown. DETAILED DESCRIPTION

[0038] In order to more clearly understand the above-mentioned objects, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that, in the absence of conflict, the embodiments of the present application and the features therein can be combined with each other.

[0039] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0040] like Figure 1 As shown, the first aspect of the present invention provides a method for designing a wind power product casting in combination with an environmental assessment, which is characterized by comprising the following steps:

[0041] S102: Acquire initial process parameter characteristic data of the wind power product casting and characteristics of the working environment of the wind power product casting, and construct a time series-based casting digital twin model based on the initial process parameter characteristic data of the wind power product casting and characteristics of the working environment of the wind power product casting;

[0042] S104: Capture the change trend from the casting digital twin model based on the time series and build the final casting digital twin model;

[0043] S106: Constructing a wind power product casting life prediction model based on the deep neural network and the final casting digital twin model, and predicting the life data of the wind power product casting through the wind power product casting life prediction model;

[0044] S108: Dynamically adjust the initial process parameter characteristic data based on the life data of the wind power product casting.

[0045] It should be noted that the present invention estimates the life of wind power product castings during the initial design by fully considering the working conditions and working environment of the castings, thereby optimizing the design parameters according to the life of the wind power product castings during the initial design and improving the rationality of the parameter design.

[0046] Furthermore, in the wind power product casting design method combined with environmental assessment, a time series-based casting digital twin model is constructed based on the initial process parameter characteristic data of the wind power product casting and the environmental characteristics of the wind power product casting. Specifically, the model includes:

[0047] Based on the initial process parameter characteristic data of the wind power product casting, a 3D model diagram of the wind power product casting is constructed using 3D modeling software, and the working environment characteristics of the wind power product casting are combined as constraints;

[0048] Through digital twin technology, simulation is performed to construct and initialize timestamps, obtain the three-dimensional model feature data of the wind power product casting at each timestamp under the constraints, and sort the three-dimensional model feature data of the wind power product casting at each timestamp in chronological order;

[0049] By sorting in chronological order, a digital twin model of the casting based on the time series is obtained, and the digital twin model of the casting based on the time series is output.

[0050] It should be noted that the initial process parameter characteristic data for wind power product castings includes outline dimensions and external dimensions, and 3D modeling software includes SolidWorks and Maya. By sorting the data in chronological order, a time-series digital twin model of the casting is obtained, forming a dynamic model diagram. The environmental characteristics of wind power product castings include operating parameter characteristics (such as wear rate per unit time, number of contacts with other objects per unit time), and operating environment characteristics (such as temperature and humidity).

[0051] Furthermore, in the wind power product casting design method combined with environmental assessment, the change trend is captured from the time series-based casting digital twin model to construct the final casting digital twin model. Specifically:

[0052] Obtaining model feature data of the casting digital twin model from the casting digital twin model based on the time series, and statistically analyzing the model feature data of the casting digital twin model to obtain model change feature data of the casting digital twin model within a preset time;

[0053] Calculating a model change amount based on the model change feature data of the casting digital twin model within a preset time, setting a model change amount threshold, and determining whether the model change amount is greater than the model change amount threshold;

[0054] When the model change is greater than the model change threshold, the time window length in the time series is reduced;

[0055] When the model change is not greater than the model change threshold, the time window length in the time series is maintained unchanged, and the final digital twin model of the casting is constructed.

[0056] It should be noted that when the model change is greater than the model change threshold, it means that the data has changed significantly. By reducing the time window length in the time series to collect more data for this period, more data can be collected to improve the prediction accuracy of the model.

[0057] Furthermore, in the wind power product casting design method combined with environmental assessment, a wind power product casting life prediction model is constructed based on the deep neural network and the final casting digital twin model. Specifically:

[0058] Constructing a wind power product casting life prediction model based on a deep neural network, obtaining equipment resource data of a data processing device, and initializing the model complexity of the wind power product casting life prediction model based on the equipment resource data of the data processing device;

[0059] Based on the model complexity of the wind power product casting life prediction model, the model features of the final casting digital twin model are input into the wind power product casting life prediction model for coding learning to obtain the model prediction speed and prediction accuracy of the wind power product casting life prediction model;

[0060] Setting a model parameter evaluation index, when the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, maintaining the model complexity of the wind power product casting life prediction model unchanged;

[0061] When the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, the model complexity of the current wind power product casting life prediction model is reduced.

[0062] It should be noted that when the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, the model complexity of the current wind power product casting life prediction model is reduced to adapt to the equipment resource data of the data processing equipment (equipment memory, computing power, etc.). The method can improve the rationality of model training, avoid model collapse during training, and continuously update model parameters at the edge to adapt to changes in equipment degradation patterns and avoid model drift problems.

[0063] Furthermore, in the wind power product casting design method combined with environmental assessment, the life data of the wind power product casting is predicted by the wind power product casting life prediction model, specifically:

[0064] Obtaining service data information of wind power product castings within a preset time, and inputting the service data information of wind power product castings within the preset time into a wind power product casting life prediction model for prediction;

[0065] Through prediction, the life data of the wind power product castings are obtained and output.

[0066] Furthermore, in the wind power product casting design method combined with environmental assessment, dynamic design adjustments are made to the initial process parameter characteristic data based on the life data of the wind power product casting, specifically including:

[0067] Setting a life data threshold range for a wind power product casting, and determining whether the life data of the wind power product casting is within the life data threshold range for the wind power product casting;

[0068] When the life data of the wind power product casting is within the life data threshold range of the wind power product casting, the design is performed according to the initial process parameter characteristic data;

[0069] When the life data of the wind power product casting is not within the life data threshold range of the wind power product casting, the initial process parameter characteristic data is adjusted until the life data of the wind power product casting is within the life data threshold range of the wind power product casting.

[0070] It should be noted that when the life data of the wind power product casting is not within the threshold range of the life data of the wind power product casting, the initial process parameter characteristic data is adjusted until the life data of the wind power product casting is within the threshold range of the life data of the wind power product casting. In this way, the design of the wind power product casting can be optimized and the service life of the wind power product casting can be improved.

[0071] In addition, the method further comprises:

[0072] After inputting the model features of the final casting digital twin model into the wind power product casting life prediction model for coding learning, the SHAP value of each model feature when predicting the wind power product casting life prediction model is calculated;

[0073] Setting a SHAP data threshold, and determining whether the SHAP value data of each model feature when predicting the wind power product casting life prediction model is greater than the SHAP data threshold;

[0074] The model features corresponding to the SHAP value data when predicting the life prediction model of the wind power product casting are lower than the SHAP data threshold are deleted, and the model features of the final casting digital twin model are updated;

[0075] The model characteristics corresponding to the SHAP value data when predicting the life prediction model of wind power product castings are not lower than the SHAP data threshold are maintained unchanged, and the wind power product casting life prediction model is trained and updated according to the model characteristics of the updated final casting digital twin model.

[0076] It should be noted that the SHAP value explains the model by calculating the marginal contribution of the feature, that is, the impact of the feature on the prediction result when it is added to the model. These marginal contributions are obtained by averaging all possible feature combinations, thereby ensuring fairness. The characteristics of SHAP values ​​include consistency, local interpretability, and global interpretability. They can be used for feature importance ranking, explaining individual predictions, and anomaly detection. For the wind power product casting life prediction model, when the SHAP value data is lower than the model feature corresponding to the SHAP data threshold during prediction, the model features are deleted, thereby updating the model features of the final casting digital twin model, deleting irrelevant model features, optimizing data training, reducing the amount of calculation during training, and improving training speed.

[0077] In addition, obtaining device resource data of the data processing device also includes:

[0078] Obtaining device resource data of data processing equipment under different working environments through big data, and constructing a knowledge graph, and inputting the device resource data of the data processing equipment under the different working environments into the knowledge graph for storage;

[0079] Acquire working environment data of a data processing device, and input the working environment data of the data processing device into the knowledge graph for data matching;

[0080] Obtain the device resource data of the data processing equipment in the current working environment through data matching;

[0081] The device resource data of the data processing device is generated according to the device resource data of the data processing device under the current working environment, and the device resource data of the data processing device is output.

[0082] It should be noted that the working environment includes temperature, humidity, etc. The device resource data of the data processing equipment is different under different working temperatures. This method can further improve the rationality of the model during training, further optimize and avoid the collapse of the model during training, and continuously update the model parameters at the edge to adapt to changes in the device degradation mode and avoid model drift problems.

[0083] like Figure 2 As shown, the second aspect of the present invention provides a wind power product casting design system 4 combined with environmental assessment, including a memory 41 and a processor 42. The memory 41 includes a wind power product casting design method program combined with environmental assessment. When the wind power product casting design method program combined with environmental assessment is executed by the processor 42, the following steps are implemented:

[0084] Obtain the initial process parameter characteristic data of the wind power product casting and the working environment characteristics of the wind power product casting, and build a time series-based casting digital twin model based on the initial process parameter characteristic data of the wind power product casting and the working environment characteristics of the wind power product casting;

[0085] Capture change trends from the time series-based digital twin model of castings and build the final digital twin model of castings;

[0086] A wind power product casting life prediction model is constructed based on a deep neural network and the final casting digital twin model. The wind power product casting life prediction model is used to predict the life data of wind power product castings.

[0087] Dynamic design adjustment of initial process parameter characteristic data is performed based on the life data of wind power product castings.

[0088] It should be noted that the present invention estimates the life of wind power product castings during the initial design by fully considering the working conditions and working environment of the castings, thereby optimizing the design parameters according to the life of the wind power product castings during the initial design and improving the rationality of the parameter design.

[0089] Furthermore, in the wind power product casting design system combined with environmental assessment, a time series-based casting digital twin model is constructed based on the initial process parameter characteristic data of the wind power product casting and the environmental characteristics of the wind power product casting. Specifically, it includes:

[0090] Based on the initial process parameter characteristic data of the wind power product casting, a 3D model diagram of the wind power product casting is constructed using 3D modeling software, and the working environment characteristics of the wind power product casting are combined as constraints;

[0091] Through digital twin technology, simulation is performed to construct and initialize timestamps, obtain the three-dimensional model feature data of the wind power product casting at each timestamp under the constraints, and sort the three-dimensional model feature data of the wind power product casting at each timestamp under the constraints in chronological order;

[0092] By sorting in chronological order, a digital twin model of the casting based on the time series is obtained, and the digital twin model of the casting based on the time series is output.

[0093] It should be noted that the initial process parameter characteristic data for wind power product castings includes outline dimensions and external dimensions, and 3D modeling software includes SolidWorks and Maya. By sorting the data in chronological order, a time-series digital twin model of the casting is obtained, forming a dynamic model diagram.

[0094] Furthermore, in the wind power product casting design system combined with environmental assessment, the change trend is captured from the time series-based casting digital twin model to construct the final casting digital twin model. Specifically:

[0095] Obtaining model feature data of the casting digital twin model from the casting digital twin model based on the time series, and statistically analyzing the model feature data of the casting digital twin model to obtain model change feature data of the casting digital twin model within a preset time;

[0096] Calculating a model change amount based on the model change feature data of the casting digital twin model within a preset time, setting a model change amount threshold, and determining whether the model change amount is greater than the model change amount threshold;

[0097] When the model change is greater than the model change threshold, the time window length in the time series is reduced until the model change is no greater than the model change threshold;

[0098] When the model change is greater than the model change threshold, the time window length in the time series is maintained unchanged, and the final digital twin model of the casting is constructed.

[0099] It should be noted that when the model change is greater than the model change threshold, it means that the data has changed significantly. By reducing the time window length in the time series to collect more data for this period, more data can be collected to improve the prediction accuracy of the model.

[0100] Furthermore, in the wind power product casting design system combined with environmental assessment, a wind power product casting life prediction model is constructed based on the deep neural network and the final casting digital twin model. Specifically:

[0101] Constructing a wind power product casting life prediction model based on a deep neural network, obtaining equipment resource data of a data processing device, and initializing the model complexity of the wind power product casting life prediction model based on the equipment resource data of the data processing device;

[0102] Based on the model complexity of the wind power product casting life prediction model, the model features of the final casting digital twin model are input into the wind power product casting life prediction model for coding learning to obtain the model prediction speed and prediction accuracy of the wind power product casting life prediction model;

[0103] Setting a model parameter evaluation index, when the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, maintaining the model complexity of the wind power product casting life prediction model unchanged;

[0104] When the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, the model complexity of the current wind power product casting life prediction model is reduced.

[0105] It should be noted that when the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, the model complexity of the current wind power product casting life prediction model is reduced to adapt to the equipment resource data (equipment memory, computing power, etc.) of the data processing equipment. This method can improve the rationality of model training and avoid model crashes during training.

[0106] Furthermore, in the wind power product casting design system combined with environmental assessment, the life data of the wind power product casting is predicted by the wind power product casting life prediction model, specifically:

[0107] Obtaining service data information of wind power product castings within a preset time, and inputting the service data information of wind power product castings within the preset time into a wind power product casting life prediction model for prediction;

[0108] Through prediction, the life data of the wind power product castings are obtained and output.

[0109] Furthermore, in the wind power product casting design system combined with environmental assessment, dynamic design adjustments are made to the initial process parameter characteristic data based on the life data of the wind power product casting, specifically including:

[0110] Setting a life data threshold range for a wind power product casting, and determining whether the life data of the wind power product casting is within the life data threshold range for the wind power product casting;

[0111] When the life data of the wind power product casting is within the life data threshold range of the wind power product casting, the design is performed according to the initial process parameter characteristic data;

[0112] When the life data of the wind power product casting is not within the life data threshold range of the wind power product casting, the initial process parameter characteristic data is adjusted until the life data of the wind power product casting is within the life data threshold range of the wind power product casting.

[0113] It should be noted that when the life data of the wind power product casting is not within the threshold range of the life data of the wind power product casting, the initial process parameter characteristic data is adjusted until the life data of the wind power product casting is within the threshold range of the life data of the wind power product casting. In this way, the design of the wind power product casting can be optimized and the service life of the wind power product casting can be improved.

[0114] The third aspect of the present invention provides a computer-readable storage medium, including a method program for designing a casting for a wind power product in combination with environmental assessment. When the method program for designing a casting for a wind power product in combination with environmental assessment is executed by a processor, any step of the method for designing a casting for a wind power product in combination with environmental assessment is implemented.

[0115] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0116] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed across multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0117] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0118] Those skilled in the art will appreciate that all or part of the steps of the above-mentioned method embodiments may be implemented by hardware associated with program instructions, and the aforementioned program may be stored in a computer-readable storage medium. When the program is executed, the program executes the steps of the above-mentioned method embodiments. The aforementioned storage medium includes various media that can store program codes, such as mobile storage devices, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0119] Alternatively, if the integrated units described above are implemented as software modules and sold or used as standalone products, they can also be stored on a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product, stored on a storage medium, includes instructions for enabling a computer device (such as a personal computer, server, or network device) to execute all or part of the methods of the various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as removable storage devices, ROM, RAM, magnetic disks, or optical disks.

[0120] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. Any modifications or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A wind power product casting design method combined with environmental assessment, characterized in that: The following steps are involved: Obtaining initial process parameter characteristic data of the wind power product casting and characteristics of the working environment in which the wind power product casting is located, and constructing a time series-based casting digital twin model based on the initial process parameter characteristic data of the wind power product casting and characteristics of the working environment in which the wind power product casting is located; capturing change trends from the time series-based digital twin model of the casting and constructing a final digital twin model of the casting; Constructing a wind power product casting life prediction model based on a deep neural network and the final casting digital twin model, and predicting the life data of the wind power product casting using the wind power product casting life prediction model; Dynamically designing and adjusting the initial process parameter characteristic data based on the life data of the wind power product casting; Capture the change trend from the time series-based casting digital twin model and build the final casting digital twin model, specifically: Acquire model feature data of the digital twin model of the casting from the time series-based digital twin model of the casting, and count the model feature data of the digital twin model of the casting to obtain model change feature data of the digital twin model of the casting within a preset time; Calculating a model change amount based on the model change characteristic data of the casting digital twin model within a preset time, setting a model change amount threshold, and determining whether the model change amount is greater than the model change amount threshold; When the model change amount is greater than the model change amount threshold, reducing the time window length in the time series; When the model change amount is not greater than the model change amount threshold, the time window length in the time series is maintained unchanged, and the final casting digital twin model is constructed; Based on the deep neural network and the final casting digital twin model, a wind power product casting life prediction model is constructed. Specifically: Constructing a wind power product casting life prediction model based on a deep neural network, obtaining device resource data of a data processing device, and initializing the model complexity of the wind power product casting life prediction model; According to the model complexity of the wind power product casting life prediction model, the model features of the final casting digital twin model are input into the wind power product casting life prediction model for coding learning to obtain the model prediction speed and prediction accuracy of the wind power product casting life prediction model; Setting a model parameter evaluation index, and when the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, maintaining the model complexity of the wind power product casting life prediction model unchanged; When the model prediction speed and prediction accuracy of the wind power product casting life prediction model are greater than the model parameter evaluation index, the model complexity of the current wind power product casting life prediction model is reduced.

2. The method for designing wind power product castings in combination with environmental assessment according to claim 1, characterized in that: A time series-based casting digital twin model is constructed based on the initial process parameter characteristic data of the wind power product casting and the working environment characteristics of the wind power product casting, specifically including: Constructing a three-dimensional model of the wind power product casting using three-dimensional modeling software based on the initial process parameter characteristic data of the wind power product casting, and combining the working environment characteristics of the wind power product casting as constraint conditions; Simulating through digital twin technology, constructing and initializing timestamps, obtaining three-dimensional model feature data of the wind power product casting in each timestamp under the constraints, and sorting the three-dimensional model feature data of the wind power product casting in each timestamp in chronological order; By sorting in chronological order, a digital twin model of the casting based on the time series is obtained, and the digital twin model of the casting based on the time series is output.

3. The method for designing wind power product castings in combination with environmental assessment according to claim 1, characterized in that: The life data of wind power product castings is predicted by the wind power product casting life prediction model, specifically: Acquiring service data information of wind power product castings within a preset time, and inputting the service data information of wind power product castings within the preset time into the wind power product casting life prediction model for prediction; The life data of the wind power product casting is obtained through prediction, and the life data of the wind power product casting is output.

4. The method for designing wind power product castings in combination with environmental assessment according to claim 1, characterized in that: Dynamically designing and adjusting the initial process parameter characteristic data based on the life data of the wind power product casting specifically includes: Setting a threshold range of life data of a wind power product casting, and determining whether the life data of the wind power product casting is within the threshold range of the life data of the wind power product casting; When the life data of the wind power product casting is within a life data threshold range of the wind power product casting, designing is performed according to the initial process parameter characteristic data; When the life data of the wind power product casting is not within the life data threshold range of the wind power product casting, the initial process parameter characteristic data is adjusted until the life data of the wind power product casting is within the life data threshold range of the wind power product casting.

5. A wind power product casting design system combined with environmental assessment, characterized by: It comprises a memory and a processor, wherein the memory comprises a method program for designing a casting for a wind power product in combination with an environmental assessment, and when the method program for designing a casting for a wind power product in combination with an environmental assessment is executed by the processor, the steps of the method for designing a casting for a wind power product in combination with an environmental assessment as described in any one of claims 1 to 4 are implemented.

6. A computer-readable storage medium, characterized in that The invention comprises a method program for designing a casting of a wind power product in combination with environmental assessment, which, when executed by a processor, implements the steps of the method for designing a casting of a wind power product in combination with environmental assessment as claimed in any one of claims 1 to 4.

Images