Aluminum alloy casting process data filling method based on process association

Abstract

The invention discloses an aluminum alloy casting process data filling method based on process association. The method comprises the steps that aluminum alloy casting process data are obtained and preprocessed; dividing the preprocessed aluminum alloy casting process data into different process data sets according to product types; for each process data set, determining an equipment group execution sequence according to an aluminum alloy production process flow, and binding corresponding process parameters to each equipment group; constructing a technological parameter prediction model based on the elastic neural network, inputting technological parameters including the first equipment group to the ith equipment group, and outputting technological parameters including the ith equipment group; and filling the process parameters of each equipment group according to the execution sequence by using the process parameter prediction model. The data filling scheme inherits the time sequence constraint of the aluminum alloy casting process, the deep coupling relation of the process parameters of the multiple equipment sets is fused, and the filling precision of the aluminum alloy casting process data is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of production data processing, and in particular to a method for filling aluminum alloy melting and casting process data based on process association. Background Art

[0002] Currently, the aluminum processing industry is in a crucial stage of intelligent transformation, but most enterprises still face severe challenges in production data governance. Its aluminum alloy melting and casting workshop generates more than 2,000 process parameter records every day, and basically all are manually recorded, including core indicators such as melting temperature, holding temperature, electrolytic aluminum liquid temperature, degassing box rotation speed, casting cooling rate, etc. However, omissions in the manual input link result in a missing rate of key parameters reaching 15.2%.

[0003] Specifically manifested as: in the melting process, operators often miss filling in the standing time and slag skimming frequency due to the complex on-site environment (such as low visibility of instruments in the high-temperature furnace area); in the casting stage, when multiple-strand casting machines operate in parallel, workers are prone to confusing the cooling water flow records of different molds. This fragmented data status causes three typical problems when enterprises build quality prediction models: First, traditional interpolation methods are mostly unified interpolation, without considering the unique process characteristics of different product models; Second, traditional interpolation methods (such as mean filling, linear interpolation) ignore the process logic between processes. For example, the peak temperature of melting furnace 1# (normal range 680 - 720 °C) is wrongly filled into the slag skimming process of melting furnace 2# (process upper limit 650 °C), resulting in deviation in equipment energy consumption prediction; Third, single equipment parameters are processed in isolation, splitting the multi-process linkage relationship. For example, the non-linear mapping between the degassing box rotor speed and the casting defect rate is not established, resulting in a sharp increase in the scrap rate.

[0004] Therefore, there is an urgent need to develop a data filling solution that conforms to the characteristics of the aluminum processing melting and casting process, which not only inherits the time sequence constraints of the aluminum alloy melting and casting process but also can analyze the deep coupling relationship of multi-equipment parameters, providing data support for enterprises to establish an industrial big model for aluminum alloy melting and casting production subsequently. Summary of the Invention

[0005] The present invention provides a method for filling aluminum alloy melting and casting process data based on process association, aiming to quickly and accurately complete the filling of aluminum alloy melting and casting process data based on process association.

[0006] In a first aspect, a method for filling aluminum alloy melting and casting process data based on process association is provided, including the following steps: S1: Obtain aluminum alloy melting and casting process data and perform preprocessing; S2: Divide the preprocessed aluminum alloy melting and casting process data into different process data sets according to product types; S3: For each process dataset, determine the execution order of equipment groups according to the aluminum alloy production process flow, and bind corresponding process parameters to each equipment group; S4: Construct a process parameter prediction model based on an elastic neural network, whose input includes the process parameters of the 1st equipment group to the i-th equipment group, and whose output includes the process parameters of the i-th equipment group, where i ≥ 1; S5: Use the process parameter prediction model to fill in the process parameters of each equipment group in the execution order.

[0007] Further, in step S1, the preprocessing process includes: Numericalize the categorical variables in the process parameters; Filter outliers, replace outliers with NaN, and retain the missing markers; Unify the data types of all process parameters.

[0008] Further, step S5 specifically includes: Fill in the process parameters of each equipment group in the execution order of the equipment group. When filling in the process parameters of the i-th equipment group, extract the process parameter data of the 1st equipment group to the i-th equipment group that have been filled in completely in the current process dataset to construct a sample set, and then train the process parameter prediction model corresponding to the i-th equipment group; for each piece of data with missing process parameters of the i-th equipment group, use the trained process parameter prediction model to predict the process parameters of the i-th equipment group in this piece of data, and use the predicted process parameters to fill in the missing process parameters of the i-th equipment group in this piece of data.

[0009] Further, before using the process parameter prediction model to fill in the process parameters of each equipment group in the execution order, it also includes: If in the current process dataset, the process parameters of a certain equipment group are all empty, it is considered that the production process of the current product does not include the process of this equipment group, and the process parameters of this equipment group do not need to be filled; otherwise, the process parameters of this equipment group need to be filled.

[0010] Further, for each piece of data with missing process parameters of the i-th equipment group, using the trained process parameter prediction model to predict the process parameters of the i-th equipment group in this piece of data specifically includes: For each piece of data with missing process parameters of the i-th equipment group, first use the median of the corresponding process parameters in the current process dataset to fill in the missing process parameters in this piece of data; Normalize the process parameters of the 1st equipment group to the i-th equipment group in this piece of data to form the input vector of the process parameter prediction model; Input the input vector into the trained process parameter prediction model to predict the process parameters of the i-th equipment group in this piece of data.

[0011] Further, in step S5, when the number of samples in the sample set is less than the threshold, for each piece of data with missing process parameters of the i-th equipment group, use the median of the corresponding process parameters in the current process dataset to fill the missing process parameters in this piece of data.

[0012] Further, in step S5, after filling the missing process parameters of the i-th equipment group in a piece of data with the process parameters predicted by the process parameter prediction model, if the filled process parameters exceed the preset range of the process parameters, use the median of the corresponding process parameters in the current process dataset to fill the missing process parameters in this piece of data.

[0013] In a second aspect, a system for filling aluminum alloy melting and casting process data based on process association is provided, including: A data acquisition module for acquiring aluminum alloy melting and casting process data and performing preprocessing; A data division module for dividing the preprocessed aluminum alloy melting and casting process data into different process datasets according to product types; An equipment group division module for determining the execution order of equipment groups according to the aluminum alloy production process flow for each process dataset, and binding corresponding process parameters to each equipment group; A model construction module for constructing a process parameter prediction model based on an elastic neural network, whose input includes the process parameters of the 1st equipment group to the i-th equipment group, and whose output includes the process parameters of the i-th equipment group, i≥1; A data filling module for filling the process parameters of each equipment group in execution order using the process parameter prediction model.

[0014] In a third aspect, an electronic device is provided, including: A memory on which a computer program or instruction is stored; A processor for loading and executing the computer program or instruction to implement the method for filling aluminum alloy melting and casting process data based on process association as described above.

[0015] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program or instruction is stored, and when the computer program or instruction is executed by a processor, the method for filling aluminum alloy melting and casting process data based on process association as described above is implemented.

[0016] The present invention proposes a method for filling aluminum alloy melting and casting process data based on process association, which has the following beneficial effects compared with the prior art: (1) The present invention divides the aluminum alloy melting and casting process data into different process data sets according to product types, and then performs independent data filling for each process data set, taking into account the unique process characteristics of different types of products, and avoiding errors caused by filling process parameters of different types of products mixedly. (2) The present invention realizes the prediction of missing process parameters through a process parameter prediction model based on an elastic neural network. Moreover, the process parameters of the current equipment group and the equipment groups in its previous process are jointly used as the input of the process parameter prediction model, and then the process parameters of the current equipment group are predicted to realize the filling of missing process parameters, fully considering the deep coupling relationship between equipment groups, establishing a non-linear mapping between process parameters based on the multi-process linkage relationship, and realizing the accurate prediction of missing process parameters. (3) Using the process parameter prediction model to fill the process parameters of each equipment group in the execution order, inheriting the time sequence constraint of the aluminum alloy melting and casting process, and further improving the prediction accuracy of missing process parameters. (4) The present invention can realize high-precision filling of aluminum alloy melting and casting process data, providing data support for enterprises to establish an industrial big model for aluminum alloy melting and casting production subsequently. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 It is a flowchart of a method for filling aluminum alloy melting and casting process data based on process association provided by an embodiment of the present invention. Detailed Embodiments

[0019] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions of the present invention will be described in detail below. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other implementation manners obtained by those of ordinary skill in the art without creative efforts fall within the scope protected by the present invention.

[0020] As Figure 1 shown, an embodiment of the present invention discloses a method for filling aluminum alloy melting and casting process data based on process association, including the following steps: S1: Obtain aluminum alloy melting and casting process data and perform preprocessing.

[0021] Specifically, the aluminum alloy melting and casting process data is stored in an Excel file, which contains the process parameters of each process of the aluminum alloy production process, and the process parameters are sorted by column.

[0022] After reading the Excel file including the aluminum alloy melting and casting process data, data preprocessing is required. The preprocessing process includes: Numericalization of categorical variables: Numerically transform the categorical variables in the process parameters; for example, convert the "qualified" type fields (such as quality inspection results) in the process parameters into binary values ("all qualified" → 1, others → 0) to ensure that the model can process them. Outlier filtering: Replace outliers with NaN and retain the missing markers; where outliers include missing values and values of the current process parameter that exceed the set range of the process parameter. Unification of data types: Unify the data types of all process parameters, such as forcefully converting to the float32 type to optimize memory occupancy and calculation efficiency.

[0023] S2: Divide the preprocessed aluminum alloy melting and casting process data into different process data sets according to the product type.

[0024] Since different types of products have their unique process characteristics, in order to avoid errors caused by filling in the process parameters of different types of products mixedly, divide them into different process data sets according to the product type. Each process data set corresponding to a product is filled independently without affecting each other, and the filling of multiple process data sets can be processed in parallel. In this embodiment, the first column of the Excel file including the aluminum alloy melting and casting process data is the product number. Therefore, during implementation, the division of the process data set can be quickly realized according to the product number in the first column.

[0025] S3: For each process data set, determine the execution order of the equipment groups according to the aluminum alloy production process flow, and bind the corresponding process parameters to each equipment group.

[0026] Force the execution order of the equipment groups to follow the production process flow order to ensure that the data filling conforms to the time-dependent relationship of actual production. After determining the execution order of the equipment groups, it is necessary to bind the column range of the corresponding process parameters for each equipment group. Each process parameter corresponds to a column number, and the equipment groups can be classified through the column numbers.

[0027] In an example, the equipment groups and their order are divided as follows: ("Smelting 1", (1, 9)), ("Smelting 1 Standing", (10, 11)), ("Skimming of Smelting 1", (12, 13)), ("Slagging of Smelting 2", (14, 15)), ("Smelting 2", (16, 18)), ("Smelting 2 Standing", (19, 20)), ("Skimming of Smelting 2", (21, 22)), ("Tapping of Smelting 2", (23, 24)), ("Insulation 1", (25, 28)), ("Skimming of Insulation 1", (29, 30)), ("Insulation 2", (31, 35)), ("Rotor 1 of Degassing Tank 1#", (36, 43)), ("Rotor 1 of Degassing Tank 2#", (44, 49)), ("Rotor 2 of Degassing Tank 1#", (50, 55)), ("Rotor 2 of Degassing Tank 2#", (56, 61)), ("Casting", (62, 80)). Taking ("Smelting 1", (1, 9)) as an example, it means that the process parameters corresponding to the "Smelting 1" equipment group are the data in columns 1 - 9. Due to excessive process parameters, some representative data are selected for display as shown in Table 1: ; In Table 1, for better display, the data of equipment groups such as "Skimming of Smelting 1", "Slagging of Smelting 2", "Smelting 2", and "Smelting 2 Standing" are omitted.

[0028] S4: Construct a process parameter prediction model based on an elastic neural network. Its input includes the process parameters of the 1st equipment group to the ith equipment group, and its output includes the process parameters of the ith equipment group, where i ≥ 1.

[0029] Aiming at the problem of large differences in the scale of equipment group process parameters (e.g., the "Smelting 1" equipment group has 9 dimensions and the "Casting" equipment group has 19 dimensions), design an elastic neural network structure to adapt to different process scenarios by dynamically adjusting the input and output dimensions. Dynamic dimension adjustment: The dimension of the input layer automatically expands with the number of process parameters of the equipment group, and the decoding layer synchronously matches the reconstruction requirements. Anti - overfitting design: The Dropout layer (with a probability of 0.2) randomly masks neurons to enhance the generalization ability of sparse data. Gradient clipping (clip_grad_norm_(1.0)) limits the parameter update amplitude to prevent training divergence; Early stopping mechanism: Terminate training when the loss has not improved for 20 consecutive rounds to balance efficiency and accuracy; where the loss can choose the mean square error loss between the input and output.

[0030] S5: Fill in the process parameters of each equipment group according to the execution order using the process parameter prediction model; when filling in the process parameters of the i-th equipment group, extract the process parameter data of the first to i-th equipment groups that have been filled in completely in the current process dataset to construct a sample set, and then train the process parameter prediction model corresponding to the i-th equipment group; for each piece of data with missing process parameters in the i-th equipment group, predict the process parameters of the i-th equipment group in this piece of data through the trained process parameter prediction model, and use the predicted process parameters to fill in the missing process parameters in the i-th equipment group of this piece of data.

[0031] For example, when filling in the first equipment group, i.e., "Smelting 1": Find the rows with complete "Smelting 1" process parameters (all data in columns 1-9 are complete) (as valid data), select the complete "Smelting 1" process data in each row as a sample to construct a sample set, and then use the sample set to train the process parameter prediction model; for the missing process parameters in the remaining "Smelting 1" process parameters, temporarily fill them with the median of the corresponding column first to construct the model input so that the data can be completely input into the model. Input the constructed model input into the trained process parameter prediction model to predict the "Smelting 1" process parameters, and then cover the predicted process parameters to the positions filled with the median before to complete the process parameter filling process of the first equipment "Smelting 1".

[0032] When filling in the second equipment group, i.e., "Smelting 1 Standing": First select the rows with complete data of both "Smelting 1" and "Smelting 1 Standing" (all data in columns 1-11 are complete) (as valid data). In this filling process, when training and predicting the process parameter prediction model, the model input is composed of all the process parameters of "Smelting 1" and "Smelting 1 Standing" to complete the cross-process parameter transfer. The principles of other processing procedures are the same as those of the aforementioned filling of "Smelting 1", and finally complete the data filling of the second equipment group "Smelting 1 Standing".

[0033] And so on. When filling in the third equipment group, rows that simultaneously meet the complete data of the first to third equipment groups need to be found for training, and finally the filling is completed. And so on, until the filling of the last equipment group is finally carried out. The missing values are processed through this "temporary median filling → model prediction → coverage correction" strategy. Finally, the entire subsequent filling process inherits the previous process parameter filling results, which is consistent with the actual project (subsequent processes are adjusted according to the previous processes).

[0034] A method for filling aluminum alloy melting and casting process data based on process association provided by the above embodiments has the following beneficial effects: By dividing the aluminum alloy melting and casting process data into different process data sets according to product types, and then independently filling the data for each process data set, the unique process characteristics of different types of products are considered, avoiding errors caused by filling process parameters of different types of products mixedly; The prediction of missing process parameters is realized through a process parameter prediction model based on an elastic neural network. Moreover, the process parameters of the current equipment group and the equipment groups in its previous processes are jointly used as the input of the process parameter prediction model, and then the process parameters of the current equipment group are predicted to realize the filling of missing process parameters, fully considering the deep coupling relationship between equipment groups, establishing a non-linear mapping between process parameters based on the multi-process linkage relationship, and realizing the accurate prediction of missing process parameters; The process parameter prediction model is used to fill the process parameters of each equipment group in the execution order, inheriting the time sequence constraint of the aluminum alloy melting and casting process, and further improving the prediction accuracy of missing process parameters; High-precision filling of aluminum alloy melting and casting process data can be realized, providing data support for the enterprise to establish an aluminum alloy melting and casting production industrial big model in the future.

[0035] Considering that the production process flows of different products may be different, therefore, in some embodiments, before filling the process parameters of each equipment group in the execution order by using the process parameter prediction model, dynamic detection of process integrity is also required, specifically including: Full-empty determination: If in the current process data set, the process parameters of a certain equipment group are all empty, it is considered that the production process of the current product does not include the process of this equipment group, and the process parameters of this equipment group do not need to be filled; As shown in Table 1, it is detected that the data in the equipment group "Melting 2 Skimming" are all empty, then it is considered that this product has not passed through the process of this equipment group, so it is considered that the process parameters in this equipment group do not need to be filled. Execution status decision: Only when there is at least one valid data point in the equipment group, start the filling process; otherwise skip it to avoid interfering with unexecuted processes. For example, it is detected that in the equipment group "Melting 1", except for "Melting 1 slagging agent dosage" and "Refining 1 temperature", other process parameters have data, then it is defaulted that this product needs to go through all the processes in the equipment group "Melting 1", and it is defaulted that all processes should have data, and the missing values need to be filled.

[0036] Since process parameters have different dimensions, in order to eliminate the dimensional differences, in some embodiments, when predicting the process parameters of the i-th equipment group in a piece of data with missing process parameters through the trained process parameter prediction model, the process includes: For each piece of data with missing process parameters of the $i$-th equipment group, first use the median of the corresponding process parameters in the current process dataset to fill in the missing process parameters in this piece of data; Normalize the process parameters of the first equipment group to the $i$-th equipment group in this piece of data using MinMaxScaler to form the input vector of the process parameter prediction model and eliminate the dimension difference; Input this input vector into the trained process parameter prediction model to predict the process parameters of the $i$-th equipment group in this piece of data; of course, since the predicted process parameters correspond to the normalized values, an inverse normalization process is also required.

[0037] In specific implementation, when predicting the process parameters of the $i$-th equipment group, the output of the process parameter prediction model can be selected to have the same dimension as the input, that is, the model input is composed of the process parameters of the first equipment group to the $i$-th equipment group, and at the same time, the model outputs the process parameters of the first equipment group to the $i$-th equipment group; of course, the output of the process parameter prediction model can also be selected to have a different dimension from the input, that is, the model input is composed of the process parameters of the first equipment group to the $i$-th equipment group, and at the same time, the model outputs the process parameters of the $i$-th equipment group.

[0038] Of course, in some cases, the process parameter prediction model may not be able to accurately fill in the missing process parameters. Therefore, in some embodiments, a hybrid filling method is adopted: (1) when the number of samples in the sample set is less than the threshold (such as the number of samples is less than 10) resulting in the failure of training the process parameter prediction model, for each piece of data with missing process parameters of the $i$-th equipment group, use the median of the corresponding process parameters in the current process dataset to fill in the missing process parameters in this piece of data; (2) after filling in the missing process parameters of the $i$-th equipment group in a piece of data using the process parameters predicted by the process parameter prediction model, if the filled process parameters exceed the preset range of this process parameter, use the median of the corresponding process parameters in the current process dataset to fill in the missing process parameters in this piece of data.

[0039] It should be noted that the filling of process data must be carried out strictly in accordance with the execution order of the equipment groups; whenever the filling of the process parameters of an equipment group is completed, it is also necessary to verify whether the filled process parameter values are within the preset range of this process parameter. Only after passing the verification can this data be used for the filling of the process parameters of the subsequent equipment groups to prevent over-limit data from contaminating the subsequent processes.

[0040] The embodiment of the present invention also discloses an aluminum alloy melting and casting process data filling system based on process association, including: A data acquisition module for acquiring aluminum alloy melting and casting process data and performing preprocessing; A data division module, configured to divide the preprocessed aluminum alloy casting process data into different process data sets according to product types; An equipment group division module, configured to, for each process data set, determine the execution order of equipment groups according to the aluminum alloy production process flow, and bind corresponding process parameters to each equipment group; A model construction module, configured to construct a process parameter prediction model based on an elastic neural network, where the input thereof includes the process parameters of the 1st equipment group to the i-th equipment group, and the output thereof includes the process parameters of the i-th equipment group, i≥1; A data filling module, configured to fill the process parameters of each equipment group in the execution order by using the process parameter prediction model.

[0041] It should be understood that the functional unit modules in the embodiments of the present invention may be concentrated in one processing unit, or each unit module may exist physically alone, or two or more unit modules may be integrated in one unit module, and may be implemented in the form of hardware or software.

[0042] The embodiments of the present invention also disclose an electronic device, including: A memory, on which a computer program or instruction is stored; A processor, configured to load and execute the computer program or instruction to implement the aluminum alloy casting process data filling method based on process association as described above.

[0043] The embodiments of the present invention also disclose a computer-readable storage medium, on which a computer program or instruction is stored, and when the computer program or instruction is executed by a processor, the aluminum alloy casting process data filling method based on process association as described above is implemented.

[0044] It can be understood that the same or similar parts in the above embodiments may be referred to each other, and the content not detailed in some embodiments may be referred to the same or similar content in other embodiments.

[0045] Those skilled in the art should understand that the embodiments of the present application may be provided as a method, a system, or a computer program product. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0046] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing device produce means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0047] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including instruction means for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more of the flows Figure 1 one or more of the flows and / or blocks Figure 1 or means for implementing the functions specified in one or more of the blocks.

[0049] Although the embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for filling aluminum alloy casting process data based on process association, characterized in that: The steps include: S1: Acquire aluminum alloy casting process data and perform preprocessing; S2: Divide the pre-processed aluminum alloy casting process data into different process data sets according to product types; S3: For each process data set, the execution order of the equipment groups is determined according to the aluminum alloy production process flow, and each equipment group is bound to the corresponding process parameters; S4: construct a process parameter prediction model based on an elastic neural network, whose input includes process parameters of the 1st equipment group to the i-th equipment group, and whose output includes process parameters of the i-th equipment group, i≥1; S5: Use the process parameter prediction model to fill in the process parameters of each equipment group according to the execution order.

2. The aluminum alloy casting process data filling method based on process association according to claim 1 is characterized in that: In step S1, the preprocessing process includes: Numericalize the categorical variables in process parameters; Outlier filtering, replacing outliers with NaN and retaining missing markers; Unify the data types of all process parameters.

3. The aluminum alloy melting and casting process data filling method based on process association according to claim 1 is characterized in that: Step S5 specifically includes: The process parameters of each equipment group are filled in according to the execution order of the equipment groups. When filling in the process parameters of the ith equipment group, multiple pieces of filled process parameter data from the 1st equipment group to the ith equipment group in the current process data set are extracted to construct a sample set, and then the process parameter prediction model corresponding to the ith equipment group is trained; for each piece of data with missing process parameters of the ith equipment group, the process parameter prediction model obtained by training is used to predict the process parameters of the ith equipment group in the data, and the predicted process parameters are used to fill in the missing process parameters of the ith equipment group in the data.

4. The method for filling aluminum alloy casting process data based on process association according to claim 1 is characterized in that: Before filling the process parameters of each equipment group in the execution order using the process parameter prediction model, it also includes: If in the current process data set, there is a certain equipment group whose process parameters are all empty, it is considered that the production process of the current product does not include the process of this equipment group, and the process parameters of this equipment group do not need to be filled; otherwise, the process parameters of this equipment group need to be filled.

5. The aluminum alloy melting and casting process data filling method based on process association according to claim 3 is characterized in that: For each piece of data in which the process parameters of the i-th equipment group are missing, the process parameters of the i-th equipment group in the data are predicted by the trained process parameter prediction model, specifically including: For each piece of data with missing process parameters of the i-th equipment group, first use the median of the corresponding process parameters in the current process data set to fill in the missing process parameters in the data; Normalize the process parameters of the first equipment group to the i-th equipment group in the data to form an input vector of the process parameter prediction model; The input vector is input into the trained process parameter prediction model to predict the process parameters of the i-th equipment group in the data.

6. The aluminum alloy melting and casting process data filling method based on process association according to claim 3 is characterized in that: In step S5, when the number of samples in the sample set is less than the threshold, for each piece of data with missing process parameters of the i-th equipment group, the median of the corresponding process parameters in the current process data set is used to fill in the missing process parameters in the data.

7. The aluminum alloy melting and casting process data filling method based on process association according to claim 3 is characterized in that: In step S5, after filling in the missing process parameters in the i-th equipment group in a certain data using the process parameters predicted by the process parameter prediction model, if the filled process parameters exceed the preset range of the process parameters, the median of the corresponding process parameters in the current process data set is used to fill in the missing process parameters in the data.

Images