Quality tracing method for thermal forming process of high-performance component of carrying equipment

Abstract

The invention relates to a carrying equipment high-performance component thermal forming process quality tracing method, and belongs to the technical field of metal thermal forming machining, and the carrying equipment high-performance component thermal forming process quality tracing method comprises the following steps: carrying out data fusion on collected thermal forming process feature data to obtain fusion data, the thermoforming characteristic data comprises thermoforming process equipment state parameters, thermoforming process parameters, thermoformed workpiece macroscopic morphology and geometric dimension precision, microstructure grain size and phase size and distribution data; constructing a thermoforming digital twin model based on thermoforming process equipment, the geometric model of the thermoforming workpiece and the fusion data; and finishing quality tracing of the thermoforming process based on the thermoforming digital twin model. The problems that in the prior art, due to the fact that the technological process in the process can only be reversely traced from the final result, the hot forming quality traceability difficulty is large, the accuracy is poor, and the efficiency is low are effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of metal hot forming processing, and in particular to a quality tracing method for a hot forming process of a high-performance component of a carrier equipment. Background Art

[0002] As a highly developed high-performance lightweight process, hot forming technology has attracted widespread attention in the transportation equipment manufacturing industry due to its advantages such as low energy consumption, low pollution, high performance and safety. The hot forming process is complex, the workpiece has many heat treatments, and most of the processes have the characteristics of multi-scale, multi-variable, nonlinear and uncertain. It is difficult to obtain the macroscopic dimensional morphology and microstructural characteristics of the workpiece in real time during the processing. The quality problems left over from each hot forming process are usually multi-variable coupling problems, and the existing system lacks efficient quality diagnosis and traceability technology.

[0003] At present, the quality traceability of hot forming is to analyze the quality of the final formed workpiece and conduct reverse quality traceability. Based on this complex manufacturing data relationship, relying solely on the quality analysis of the final formed workpiece cannot effectively achieve the purpose of effective quality traceability and efficient process optimization of the product, and it is inconvenient to improve product quality and product yield.

[0004] Therefore, there is an urgent need for a quality traceability method for the hot forming process of high-performance components of launch equipment, which can realize positive quality traceability of the entire hot forming process step by step, thereby providing data-based analysis for the research and development of new high-performance hot forming processes and improving workpiece quality and yield rate. Summary of the invention

[0005] In view of this, it is necessary to provide a method for tracing the quality of the hot forming process of high-performance components of launch equipment, so as to solve the problem that the existing technology can only trace the process flow in the process backward from the final result, resulting in difficulty in tracing the quality of hot forming, low efficiency and poor accuracy.

[0006] In order to solve the above problems, the present invention provides a method for tracing the quality of a hot forming process of a high-performance component of a carrier equipment, comprising: Performing data fusion on the collected characteristic data of the hot forming process to obtain fused data, wherein the hot forming characteristic data includes: equipment state parameters of the hot forming process, hot forming process parameters, macroscopic morphology and geometric dimensional accuracy of the hot forming workpiece, and microstructure grain size and phase size and distribution data; Building a hot forming digital twin model based on the geometric models of the hot forming process equipment and the hot forming workpiece and the fusion data; Complete quality traceability of the hot forming process of high-performance components of launch equipment based on the hot forming digital twin model.

[0007] In a possible implementation, the equipment state parameters of the hot forming process include: forming speed, forming force, operating displacement and holding time; The hot forming process parameters include: billet size, upset size, heat treatment temperature, holding temperature, holding time, holding converter temperature, pre-forging and final forging force, forging temperature and deformation rate.

[0008] In a possible implementation, the thermoforming characteristic data may be in the form of digital quantity, analog quantity, image, video, and text.

[0009] In a possible implementation, the step of fusing the collected hot forming feature data includes: Preprocessing the hot forming feature data based on a long short-term memory neural network; The preprocessed hot forming feature data are fused based on the federated learning algorithm.

[0010] In a possible implementation, the preprocessing of the hot forming feature data based on the long short-term memory neural network includes: Recording missing items in the hot forming feature data and sorting them out to obtain a missing sequence; Normalizing the hot forming feature data and eliminating outliers to obtain training data; Training a long short-term memory neural network with a Dropout layer based on the training data; The missing sequence is input into a well-trained long short-term memory neural network to obtain hot forming feature data of the completed data.

[0011] In a possible implementation, after the hot forming feature data are normalized, the hot forming feature data are reconstructed based on a sliding window.

[0012] In a possible implementation, the hot forming digital twin model is constructed based on the geometric model of the hot forming process equipment and the hot forming workpiece and the fusion data, including: A preliminary hot forming digital twin model is constructed based on the geometric models of hot forming process equipment and hot forming workpieces and fusion data; Performing finite element simulation based on the preliminary hot forming digital twin model to obtain simulation data; The preliminary hot forming digital twin model is optimized based on the simulation data and the fusion data to obtain a final hot forming digital twin model.

[0013] In a possible implementation, the quality traceability of the hot forming process of high-performance components of carrier equipment based on the hot forming digital twin model includes: Dynamically demonstrate each hot forming process and the hot processing result of the workpiece based on the hot forming digital twin model; The hot forming process parameters and forming quality of each step are recorded in real time to achieve quality traceability of the hot forming process of high-performance components of carrier equipment, wherein the forming quality includes: workpiece surface roughness, workpiece shape, and internal grain size and phase distribution.

[0014] The beneficial effect of the present invention is as follows: the present invention provides a method for tracing the quality of the hot forming process of high-performance components of carrier equipment. First, the collected characteristic data of the hot forming process are fused, and then a digital twin model is constructed based on the fused data and the geometric models of the hot forming equipment and the hot forming workpiece. Finally, the quality traceability of each process in the hot forming process is realized on the basis of the digital twin model. Since the data for establishing the digital twin model not only includes the parameters of the final hot forming result, but also includes a series of parameters in the process, and the fused data source is reliable and the data volume is sufficient, the digital twin model established based on the data has a high prediction accuracy while avoiding the limitation of tracing the quality of the whole process only from the final result, thereby solving the problem of low efficiency and poor accuracy of hot forming quality traceability in the prior art due to the fact that it can only trace the process flow in the process backwards from the final result. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A method flow chart of an embodiment of a method for tracing quality of a hot forming process of a high-performance component of a carrier provided by the present invention; Figure 2 for Figure 1 A method flow chart of an embodiment of step S101; Figure 3 for Figure 2 A method flow chart of an embodiment of step S201; Figure 4 A schematic diagram of the structure of a long short-term memory neural network provided by the present invention; Figure 5 for Figure 1 A method flow chart of an embodiment of step S102; Figure 6 for Figure 1 Flow chart of a method of an embodiment of step S103. DETAILED DESCRIPTION

[0016] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not used to limit the scope of the present invention.

[0017] In the description of the embodiments of the present invention, unless otherwise specified, "multiple" means two or more than two. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" may mean: A exists alone, A and B exist at the same time, and B exists alone.

[0018] The descriptions of "first", "second", etc. involved in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0019] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0020] In order to solve the above problems, Figure 1 As shown, the present invention provides a method for tracing the quality of a hot forming process of a high-performance component of a carrier equipment, comprising: S101, performing data fusion on the collected hot forming process characteristic data to obtain fused data.

[0021] Preferably, the hot forming characteristic data include: hot forming process equipment state parameters, hot forming process parameters, hot forming workpiece macro morphology and geometric dimensional accuracy, microstructure grain size and phase size and distribution data.

[0022] Preferably, the collection process includes blanking process, roughing process, heat treatment process, pre-forging process, final forging process and the like.

[0023] In one possible implementation, the equipment state parameters of the hot forming process include: forming speed, forming force, operating displacement and holding time; the hot forming process parameters include: billet size, upsetting size, heat treatment temperature, holding temperature, holding time, holding converter temperature, pre-forging and final forging force, forging temperature and deformation rate.

[0024] In a possible implementation, the hot forming characteristic data may be in the form of digital quantity, analog quantity, image, video, and text.

[0025] It should be noted that since the collected feature data include digital quantities, analog quantities, images, videos, text and other forms, it is necessary to carry out data fusion on these multi-source heterogeneous data to eliminate the island effect between different types of data from different sources.

[0026] S102, constructing a hot forming digital twin model based on the geometric model of the hot forming process equipment and the hot forming workpiece and the fusion data; S103. Complete quality traceability of hot forming process of high-performance components of carrier equipment based on hot forming digital twin model.

[0027] Compared with the prior art, the present invention provides a method for tracing the quality of the hot forming process of high-performance components of carrier equipment. First, the collected characteristic data of the hot forming process are fused, and then a digital twin model is constructed based on the fused data and the geometric models of the hot forming equipment and the hot forming workpiece. Finally, the quality traceability of each process in the hot forming process is realized on the basis of the digital twin model. Since the data for establishing the digital twin model not only includes the parameters of the final hot forming result, but also includes a series of parameters in the process, and the fused data source is reliable and the data volume is sufficient, the digital twin model established based on the data has a high prediction accuracy while avoiding the limitation of tracing the quality of the whole process only from the final result, thereby solving the problem of low efficiency and poor accuracy of hot forming quality traceability in the prior art due to the fact that it can only trace the process flow in the process backwards from the final result.

[0028] like Figure 2 In a possible implementation, step S101 includes: S201, preprocessing the hot forming feature data based on the long short-term memory neural network; S202. Fusing the preprocessed hot forming feature data based on a federated learning algorithm.

[0029] Furthermore, when performing data fusion, a fusion algorithm for multi-source heterogeneous data based on Tucker decomposition is used. By extracting features from heterogeneous data, and based on homomorphic encryption and Shamir secret sharing technology, multi-source heterogeneous data can be securely fused without leaking factory data. Federated learning uses distributed machine learning with privacy protection and secure encryption technology to enable decentralized participants to collaborate on machine learning model training without disclosing private data to other participants.

[0030] like Figure 3 In a possible implementation, step S201 includes: S301, recording missing items in the hot forming feature data, and sorting them out to obtain a missing sequence; S302, normalizing the hot forming feature data and eliminating outliers to obtain training data; In a possible implementation, after normalizing the hot forming feature data, the hot forming feature data is reconstructed based on a sliding window. The specific process is as follows: The structure of the long short-term memory neural network is as follows Figure 4 As shown in the figure, assuming that the length of the original feature data sequence is L, the feature dimension is F, the sliding window length is W, the time step is 1, and the length of the new sequence is S, then S=W+1. The sliding window is used to loop through the original data. Each time the window slides, a new sequence can be obtained. The number of sliding window cycles is the number of samples N after data reconstruction (N=L+S), so the reconstructed process data is a three-dimensional array: (N, S, F). Encode the reconstructed data, the first S-1 rows of the sample are the input variable X, and the last row is the output variable Y. The input variable Xt at time t is combined with the state variables Ct-1 and ht-1 at the previous time, and passes through Ft, It and Ot in turn to obtain the state variable Ct and hidden layer state ht at time t. ht passes through the output layer, which is the output Yt of LSTM at time t.

[0031] S303, training the long short-term memory neural network with the Dropout layer introduced based on the training data; S304, inputting the missing sequence into a well-trained long short-term memory neural network to obtain hot forming feature data of the completed data.

[0032] like Figure 5 In a possible implementation, step S102 includes: S501, constructing a preliminary hot forming digital twin model based on the geometric model of the hot forming process equipment and the hot forming workpiece and the fusion data; S502, performing finite element simulation based on the preliminary hot forming digital twin model to obtain simulation data; It should be noted that the digital twin model has finite element function, based on which real-time simulation data can be obtained in actual application.

[0033] S503: Optimize the preliminary hot forming digital twin model based on the simulation data and the fusion data to obtain the final hot forming digital twin model.

[0034] It can be understood that based on the forming parameters and forming quality of each process, the forming state of the workpiece is evaluated and analyzed, so as to achieve positive quality traceability of each process and quickly find out the process and process parameters where the quality problems first occurred.

[0035] The quality traceability method of hot forming process of high-performance components of launch equipment based on digital twin can not only display the forming process of each process in real time, but also realize the forward quality traceability of each process, thus avoiding the continuous superposition effect of traceability caused by the influence of different processes on the quality of the workpiece being transmitted to the next process.

[0036] like Figure 6 In a possible implementation, step S103 includes: S601. Dynamically demonstrate each hot forming process and the hot processing results of the workpiece based on the hot forming digital twin model; S602, real-time recording of hot forming process parameters and forming quality of each process, to achieve quality traceability of hot forming process of high-performance components of carrier equipment; Preferably, the forming quality includes: workpiece surface roughness, workpiece shape, and internal grain size and phase distribution.

[0037] Those skilled in the art will appreciate that all or part of the processes of the above-mentioned embodiments can be implemented by instructing related hardware (such as a processor, a controller, etc.) through a computer program, and the computer program can be stored in a computer storage medium, wherein the computer storage medium is a disk, an optical disk, a read-only storage memory, or a random access memory, etc.

[0038] The quality traceability method for the hot forming process of high-performance components of carrier equipment provided by the present invention is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A quality tracing method for hot forming process of high-performance components of transport equipment, characterized in that: include: Performing data fusion on the collected characteristic data of the hot forming process to obtain fused data, wherein the hot forming characteristic data includes: equipment state parameters of the hot forming process, hot forming process parameters, macroscopic morphology and geometric dimensional accuracy of the hot forming workpiece, and microstructure grain size and phase size and distribution data; Building a hot forming digital twin model based on the hot forming process equipment, the geometric model of the hot forming workpiece and the fusion data; Complete hot forming process quality traceability based on the hot forming digital twin model.

2. The quality tracing method for hot forming process of high-performance components of carrier equipment according to claim 1 is characterized in that: The equipment status parameters of the hot forming process include: forming speed, forming force, manipulator transfer time, operating displacement and holding time; The hot forming process parameters include: billet size, upset size, heat treatment temperature, holding temperature, holding time, holding converter temperature, pre-forging and final forging force, forging temperature and deformation rate.

3. The quality tracing method for hot forming process of high-performance components of carrier equipment according to claim 1 is characterized in that: The forms of the thermoforming characteristic data include digital quantity, analog quantity, image, video and text.

4. The quality tracing method for hot forming process of high-performance components of carrier equipment according to claim 1 is characterized in that: The data fusion of the collected hot forming feature data includes: Preprocessing the hot forming feature data based on a long short-term memory neural network; The preprocessed hot forming feature data are fused based on the federated learning algorithm.

5. The method for tracing the quality of the hot forming process of high-performance components of carrier equipment according to claim 1 is characterized in that: The preprocessing of the hot forming feature data based on the long short-term memory neural network includes: Recording missing items in the hot forming feature data and sorting them out to obtain a missing sequence; Normalizing the hot forming feature data and eliminating outliers to obtain training data; Training a long short-term memory neural network with a Dropout layer based on the training data; The missing sequence is input into a well-trained long short-term memory neural network to obtain hot forming feature data of the completed data.

6. The method for tracing the quality of the hot forming process of high-performance components of carrier equipment according to claim 1 is characterized in that: After normalizing the hot forming feature data, the hot forming feature data is reconstructed based on a sliding window.

7. The method for tracing the quality of the hot forming process of high-performance components of carrier equipment according to claim 1 is characterized in that: The hot forming digital twin model is constructed based on the geometric model of the hot forming process equipment and the hot forming workpiece and the fusion data, including: A preliminary hot forming digital twin model is constructed based on the geometric models of hot forming process equipment and hot forming workpieces and fusion data; Performing finite element simulation based on the preliminary hot forming digital twin model to obtain simulation data; The preliminary hot forming digital twin model is optimized based on the simulation data and the fusion data to obtain a final hot forming digital twin model.

8. The method for tracing the quality of the hot forming process of high-performance components of carrier equipment according to claim 1 is characterized in that: The quality traceability of the hot forming process based on the hot forming digital twin model includes: Dynamically demonstrate each hot forming process and the hot processing result of the workpiece based on the hot forming digital twin model; The hot forming process parameters and forming quality of each step are recorded in real time to achieve quality traceability of the hot forming process of high-performance components of carrier equipment, wherein the forming quality includes: workpiece surface roughness, workpiece shape, and internal grain size and phase distribution.

Images