CN114939643A

CN114939643A - Die-casting control method and device

Info

Publication number: CN114939643A
Application number: CN202210567878.8A
Authority: CN
Inventors: 王勇杰; 莫伟斌
Original assignee: Kunshan Laijie Colored & Fine Metal Alloy Co ltd
Current assignee: Kunshan Laijie Colored & Fine Metal Alloy Co ltd
Priority date: 2022-05-24
Filing date: 2022-05-24
Publication date: 2022-08-26
Anticipated expiration: 2042-05-24
Also published as: CN114939643B

Abstract

The embodiment of the specification provides a die-casting control method and a die-casting control device. The device includes: the device comprises a die casting machine, a sensing module, a control module and a display module; the control module is used for: acquiring casting characteristics and die-casting system characteristics of a target die-casting piece, wherein the casting characteristics comprise at least one of casting structural characteristics and casting alloy characteristics, and the casting structural characteristics comprise at least one of casting wall thickness, demoulding inclination, casting volume and casting structural complexity; acquiring a plurality of candidate die-casting schemes from a networked database based on the die-casting system characteristics; obtaining a plurality of second die casting schemes from a plurality of candidate die casting schemes based on the casting alloy characteristics; determining at least one first die casting scheme from a plurality of second die casting schemes based on the casting structure characteristics, wherein each first die casting scheme of the at least one first die casting scheme comprises a plurality of die casting process parameters; and optimizing a plurality of die-casting process parameters of the at least one first die-casting scheme based on the die-casting effect of the at least one first die-casting scheme.

Description

Die-casting control method and device

Technical Field

The present disclosure relates to the field of die-casting control technologies, and in particular, to a die-casting control method and apparatus.

Background

Die casting is one of the metal material forming methods. Vehicles such as automobiles are a major consumer of die castings. With the development of economy, the proportion of die castings in the manufacturing industry is higher and higher. With the digital transformation and upgrading of the traditional manufacturing industry, the requirement on the control accuracy of the die-casting process becomes higher and higher. The pressure casting control level of enterprises plays an important role in improving the pressure casting process.

Accordingly, it is desirable to provide a die-casting control method and apparatus that can improve the die-casting process and thus improve the quality of die-cast parts.

Disclosure of Invention

One of the embodiments of the present specification provides a die-casting control device, where the feeding device includes: the device comprises a die casting machine, a sensing module, a control module and a display module; and the control module is configured to: acquiring casting characteristics and casting system characteristics of a target die casting, wherein the casting characteristics comprise at least one of casting structural characteristics and casting alloy characteristics, and the casting structural characteristics comprise at least one of casting wall thickness, demolding inclination, casting volume and casting structural complexity; acquiring a plurality of candidate die-casting schemes from a networked database based on the die-casting system characteristics; obtaining a plurality of second die casting schemes from the plurality of candidate die casting schemes based on the casting alloy characteristics; determining at least one first die-casting scheme from the plurality of second die-casting schemes based on the casting structural characteristics, wherein each first die-casting scheme of the at least one first die-casting scheme comprises a plurality of die-casting process parameters; optimizing the plurality of die casting process parameters of the at least one first die casting scheme based on a die casting effect of the at least one first die casting scheme.

One of the embodiments of the present specification provides a die-casting control method executed by a control module, the die-casting control method including: acquiring casting characteristics and casting system characteristics of a target die casting, wherein the casting characteristics comprise at least one of casting structural characteristics and casting alloy characteristics, and the casting structural characteristics comprise at least one of casting wall thickness, demolding inclination, casting volume and casting structural complexity; acquiring a plurality of candidate die-casting schemes from a networked database based on the die-casting system characteristics; obtaining a plurality of second die casting schemes from the plurality of candidate die casting schemes based on the casting alloy characteristics; determining at least one first die-casting scheme from the plurality of second die-casting schemes based on the casting structural characteristics, wherein each first die-casting scheme of the at least one first die-casting scheme comprises a plurality of die-casting process parameters; optimizing the plurality of die casting process parameters of the at least one first die casting scheme based on a die casting effect of the at least one first die casting scheme.

One of the embodiments of the present specification provides a die-casting control system, which includes a sensing module, a control module, and a display module; the control module is used for: acquiring casting characteristics and casting system characteristics of a target casting, wherein the casting characteristics comprise at least one of casting structural characteristics and casting alloy characteristics, and the casting structural characteristics comprise at least one of casting wall thickness, demolding inclination, casting volume and casting structural complexity; acquiring a plurality of candidate die-casting schemes from a networked database based on the die-casting system characteristics; obtaining a plurality of second die casting solutions from the plurality of candidate die casting solutions based on the casting alloy characteristics; determining at least one first die-casting scheme from the plurality of second die-casting schemes based on the casting structural characteristics, wherein each first die-casting scheme of the at least one first die-casting scheme comprises a plurality of die-casting process parameters; optimizing the plurality of die casting process parameters of the at least one first die casting scheme based on a die casting effect of the at least one first die casting scheme.

One of the embodiments of the present specification provides a computer-readable storage medium storing computer instructions, and when the computer instructions in the storage medium are read by a computer, the computer executes the die-casting control method according to any one of the above.

Drawings

The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:

FIG. 1 is an exemplary block diagram of a die casting control system according to some embodiments herein;

FIG. 2 is an exemplary main flow diagram of a die casting control method according to some embodiments herein;

FIG. 3 is an exemplary flow diagram for cluster-based determination of a first die-casting scheme in accordance with some embodiments of the present description;

FIG. 4 is an exemplary flow diagram illustrating optimization of die casting process parameters based on die casting effects in accordance with some embodiments herein;

fig. 5 is an exemplary schematic diagram of a die casting parameter optimization model according to some embodiments described herein.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or stated otherwise, like reference numbers in the figures refer to the same structure or operation.

It should be understood that "system", "apparatus", "unit" and/or "module" as used herein is a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.

As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.

Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to or removed from these processes.

The die casting machine is a series of industrial casting machines which inject molten metal into a die under the action of pressure to cool and mold, and obtain a solid metal casting after die opening. With the requirement on the control accuracy of the die casting process becoming higher and higher, the die casting control method applied to the die casting machine plays an important role in improving the die casting process and improving the quality of die castings.

In view of this, some embodiments of the present disclosure provide a die-casting control method and device, which can optimize a plurality of die-casting process parameters of a die-casting scheme, so as to improve the quality of a die-casting.

In some embodiments, a die casting control apparatus may include a die casting machine, a sensing module, a control module, and a display module.

In some embodiments, a die casting machine may include a mold clamping device, an injection device, and the like. The control module can control a die-casting machine (a die closing device, an injection device and the like) to perform die-casting according to different die-casting schemes, so as to obtain different die-casting parts. Different die-casting schemes correspond to different die-casting processes. The different die casting processes may include a plurality of different die casting process parameters.

In some embodiments, the control module can be used to obtain casting characteristics and die casting system characteristics of a target die casting, the casting characteristics including at least one of casting structural characteristics, casting alloy characteristics, wherein the casting structural characteristics include at least one of casting wall thickness, draft, casting volume, casting structural complexity. The control module may be configured to obtain a plurality of candidate die-casting solutions from a networked repository based on die-casting system characteristics; obtaining a plurality of second die casting schemes from a plurality of candidate die casting schemes based on the casting alloy characteristics; determining at least one first die casting scheme from a plurality of second die casting schemes based on the casting structure characteristics, wherein each first die casting scheme of the at least one first die casting scheme comprises a plurality of die casting process parameters; and optimizing a plurality of die-casting process parameters of the at least one first die-casting scheme based on the die-casting effect of the at least one first die-casting scheme.

In some embodiments, the control module may be further operable to determine the casting structure complexity based on a plurality of casting structure parameters including at least one of a number of axes of symmetry, a number of stiffening ribs, a surface area ratio, a number of sides, and a number of faces.

In some embodiments, the control module may be further operable to obtain the casting structure complexity by inputting a plurality of casting structure parameters into the machine learning model.

In some embodiments, the control module may be further operable to obtain a plurality of die casting solutions over a network; determining the die-casting schemes with the first die-casting system characteristics meeting a first preset condition and the first die-casting effect meeting a first preset effect as a plurality of candidate die-casting schemes based on the first cluster; determining the candidate die-casting schemes with the first die-casting effect meeting the second preset effect as a plurality of second die-casting schemes based on the second clustering, wherein the first casting alloy characteristics in the candidate die-casting schemes meet the second preset condition; and determining a second die-casting scheme with the first die-casting effect meeting a third preset effect as at least one first die-casting scheme based on the third clustering, wherein the first casting structure characteristics in the plurality of second die-casting schemes meet the third preset condition, and the first die-casting effect meets the third preset effect.

In some implementations, the weight of the first casting structural complexity in the first casting structural characteristic is greater than a preset threshold.

In some embodiments, the control module may be further configured to execute at least one first die casting scheme to obtain a die casting; detecting the die casting, and determining die casting defects and defect grades, wherein the die casting defects comprise surface defects and internal defects; and optimizing a plurality of die casting process parameters of at least one first die casting scheme based on the die casting defects and the defect grades.

In some embodiments, the control module may be further configured to determine, via the die-casting parameter optimization model, an adjustment amount for each of the plurality of die-casting process parameters of the first die-casting scheme.

In some embodiments, the control module may be further operable to determine a plurality of surface defect vectors for the surface defects via the image recognition model.

In some embodiments, the control module may be further configured to determine a confidence level of the adjustment amount for each of the plurality of die casting process parameters of the at least one first die casting scheme via the die casting parameter optimization model, wherein the confidence level is inversely related to the casting structure complexity and inversely related to the variance of the plurality of surface defect vectors; and manually adjusting each die-casting process parameter based on the confidence coefficient.

It should be noted that the above description of the feeding device and its various components is merely for convenience of description and should not limit the present disclosure to the scope of the illustrated embodiments. It will be understood by those skilled in the art that, having the benefit of this disclosure, any combination of components or sub-assembly may be made or connected to other components without departing from the scope of the disclosure.

FIG. 1 is an exemplary block diagram of a die casting control system according to some embodiments herein.

As shown in fig. 1, the die casting control system 100 may include a sensing module 110, a control module 120, and a display module 130.

In some embodiments, the sensing module 110 may be used to acquire sensing information of a die casting machine. In some embodiments, the sensing module 110 may include a temperature sensor, a pressure sensor, a position sensor, and the like. Different sensors can acquire different sensing information of the die casting machine.

In some embodiments, the control module 120 may be configured to obtain sensing information of the die casting machine via the sensing module 110. The control module 120 may be used to receive control information input by the display module 130. The control module 120 may be configured to issue a control command to the die casting machine based on the sensing information and the control information, and execute the die casting process.

In some embodiments, the display module 130 may be used to display die casting process parameters, the progress of a die casting process, and the like.

It should be understood that the system and its modules shown in FIG. 1 may be implemented in a variety of ways. It should be noted that the above description of the die-casting control system 100 and its modules is merely for convenience of description and should not be construed as limiting the present disclosure to the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. In some embodiments, the sensing module 110, the control module 120, and the display module 130 disclosed in fig. 1 may be different modules in a system, or may be a module that implements the functions of two or more modules described above. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present disclosure.

Fig. 2 is an exemplary main flow diagram of a die casting control method according to some embodiments described herein. As shown in fig. 2, the process 200 includes the following steps. In some embodiments, the process 200 may be performed by the control module 120.

And 210, acquiring casting characteristics and casting system characteristics of the target die casting, wherein the casting characteristics comprise at least one of casting structural characteristics and casting alloy characteristics, and the casting structural characteristics comprise at least one of casting wall thickness, demolding inclination, casting volume and casting structure complexity.

The target die cast is a die cast which requires die casting processing by a die casting machine.

The casting characteristic may refer to a die casting characteristic corresponding to the target die casting. Different target die castings have different casting characteristics. In some embodiments, the casting characteristics may include casting structural characteristics, casting alloy characteristics, and the like.

The casting structural characteristics refer to some inherent characteristics of the target die casting in structure. In some embodiments, the casting structural characteristics may include casting wall thickness, draft angle, casting volume, casting structural complexity, and the like.

The casting wall thickness refers to the wall thickness of the target die casting section. The reasonable design of the wall thickness of the casting is beneficial to improving the quality of the target die casting. In some embodiments, the casting wall thickness may be thinner while ensuring the desired strength and rigidity of the target die cast part. The target die castings of different alloy types have different casting wall thicknesses. For example, the zinc alloy casting may have a wall thickness of 1mm to 3 mm. The wall thickness of the casting of the aluminum alloy may be 1.5mm to 5 mm. The wall thickness of the cast copper alloy may be 2mm to 5 mm.

The draft refers to the draft designed on both sides of the cavity to facilitate the ejection of the die cast part. In some embodiments, the accuracy requirements of the target die cast part are higher, and a smaller draft angle may be selected. In some embodiments, the target die casting has a complex shape and is not easily demolded, and a larger demolding slope may be selected. The casting volume may refer to the volume of the target die casting.

The casting structure complexity refers to the complexity of the structure of the target die casting. The corresponding structures of different target die castings are different, and the structural complexity of the castings is different. The structural complexity of the casting can reflect the complexity of the die casting process of the target die casting.

The casting alloy properties refer to properties in terms of the alloy of the target die casting. The casting alloy characteristics may include alloy type (e.g., zinc alloy, aluminum alloy, etc.), crystallization temperature, fluidity, density, specific strength, and the like. In some embodiments, the casting alloy properties may include the metal content of the target die cast part. For example, the target die casting is a zinc alloy containing aluminum, copper, and the like. The metal contained in the target die casting can be represented by a vector, each element in the vector can represent a metal, and the corresponding value of the element can represent whether the metal is contained or not. For example, 1 represents that the metal is contained, and 0 represents that the metal is not contained. In some embodiments, the value corresponding to an element may represent the content of the corresponding contained metal. For example, 0.05 for one element means that the content of the metal corresponding to the element is 5%.

The die-casting system characteristics refer to characteristics that can reflect respective characteristics of different die-casting systems. In some embodiments, the die casting system characteristics may include runner system characteristics, drain system characteristics, and the like. The runner is a passage through which the metal solution flows. The runner system characteristics may include runner resistance, heat dissipation rate, ingate rate, etc. The characteristics of the bleed system may include the layout of the exhaust passage, the cross-sectional area of the exhaust passage, the length of the exhaust passage, etc.

In some embodiments, the die casting system characteristics may be represented by a feature vector. The die casting system feature vector is constructed based on the related data of different die casting systems. A plurality of elements may be included in the die-casting system feature vector, with different elements corresponding to different data of the die-casting system. For example, the 1 st to 3 rd elements in the characteristic vector of the die casting system are runner resistance, heat dissipation rate and ingate rate, and respectively represent different runner resistance, heat dissipation rate and ingate rate corresponding to different die casting systems. The 4 th to 6 th elements in the characteristic vector of the die-casting system are exhaust passage layout, exhaust passage section area and exhaust passage length, and respectively represent different exhaust passage layout, exhaust passage section area and exhaust passage length corresponding to different die-casting systems.

In some embodiments, the control module 120 can determine the die casting system characteristics of the target die casting from the sensing data of the sensing module 110. For example, the control module 120 determines the runner resistance, the heat dissipation rate, the ingate speed, the exhaust passage layout, the exhaust passage cross-sectional area, the exhaust passage length, and the like by sensing information such as temperature, pressure, and position through the sensing module 110 (such as a temperature sensor, a pressure sensor, a position sensor, and the like), and then determines the die casting system characteristics of the target die casting.

In some embodiments, the control module 120 may determine the casting characteristics from the specification parameters of the die casting machine and/or the target die casting. For example, the control module 120 may determine the casting wall thickness, draft, etc. and thus the casting structural characteristics from the specification parameters of the die casting machine. As another example, the control module 120 can determine the alloy type, and thus the casting alloy characteristics, from the specification parameters of the target die casting.

In some embodiments, the casting structure complexity may be determined based on a plurality of casting structure parameters.

The casting structure parameter refers to a plurality of parameters that can indicate a casting structure related to the target die casting. In some embodiments, the plurality of casting structure parameters may include at least one of a number of axes of symmetry, a number of stiffening ribs, a surface area ratio, a number of sides, a number of faces, and the like.

The number of axes of symmetry can be used to characterize the structural complexity of the target die cast part. The more the number of symmetry axes is, the simpler the structure of the target die casting is. For example, a spherical structure has an approximation to an infinite number of axes of symmetry. For another example, there are 4 symmetry axes corresponding to a rectangular or cubic structure.

The number of stiffening ribs can also be used to characterize the structural complexity of the target die cast part. The larger the number of reinforcing ribs, the more complicated the structure of the target die cast.

The surface area ratio refers to the ratio of the surface area of the target die casting to the surface area of the sphere for the same volume. The surface area ratio can be used to characterize the structural complexity of the target die cast part. The larger the surface area ratio, the more complicated the structure of the target die cast article.

The number of sides and the number of faces may refer to the number of sides and the number of faces of the target die cast part. The number of sides and the number of faces of the target die casting can represent the structural complexity of the target die casting. The larger the number of sides and faces, the more complicated the structure of the target die cast article.

In some embodiments, the control module 120 may determine the casting structure complexity based on a plurality of casting structure parameters. For example, the greater the number of axes of symmetry, the fewer the number of reinforcing ribs, the smaller the surface area ratio, the fewer the number of sides and the number of faces, the smaller the structural complexity of the corresponding target die cast part. For example, the smaller the number of symmetry axes, the larger the number of reinforcing ribs, the larger the surface area ratio, and the larger the number of sides and faces, the greater the structural complexity of the corresponding target die cast part.

In some embodiments of the present description, the control module 120 can determine the casting structure complexity based on a plurality of casting structure parameters, and thus determine the casting characteristics of the target die casting, and thus help ensure the accuracy of the determined first die casting scheme, and thus help improve the quality of the die casting.

In some embodiments, the casting structure complexity may be obtained by inputting a plurality of casting structure parameters into a machine learning model.

The machine learning model refers to a model which can be used for acquiring the structural complexity of the casting. In some embodiments, the type of machine learning model may include a neural network model, a deep neural network model, and the like, and the selection of the model type may be contingent on the circumstances.

The inputs to the machine learning model may include a plurality of casting structure parameters, etc., and the outputs may include casting structure complexity.

In some embodiments, a machine learning model may be derived based on a plurality of training samples and label training.

In some embodiments, the training sample includes a plurality of casting structure parameter data for the sample. The label is the structural complexity of the sample casting. The training data can be obtained based on historical data, and the labels of the training data can be determined in a manual labeling mode or an automatic labeling mode.

In some embodiments, the control module 120 may determine the casting structure complexity based on a machine learning model. For example, the control module 120 may input a plurality of casting structure parameters, etc. into a machine learning model that outputs a casting structure complexity.

In some embodiments of the present disclosure, the control module 120 determines the structural complexity of the casting through the machine learning model, which may improve accuracy of the structural complexity of the casting, and thus improve accuracy of casting characteristics of the target die casting, and thus help ensure accuracy of the determined first die casting scheme, and thus help improve quality of the die casting.

In step 220, a plurality of candidate die-casting solutions are obtained from the networked repository based on the die-casting system characteristics.

The candidate die casting solutions may refer to alternative die casting solutions that approximate die casting system characteristics of the target die casting. An alternative diecasting solution may refer to a solution that may be used to diecast a target diecasting.

A networked repository may refer to a repository that is communicated over a network to store alternative die-casting solutions. The networked repository may include a number of alternative die-casting schemes. Multiple alternative die casting solutions can meet different casting characteristics and different die casting system characteristics.

In some embodiments, the control module 120 may obtain a plurality of candidate die-casting solutions from a networked repository based on die-casting system characteristics. For example, the control module 120 obtains a plurality of alternative die casting solutions in the networked repository that approximate the die casting system characteristics of the target die casting.

Step 230, obtaining a plurality of second die casting solutions from the plurality of candidate die casting solutions based on the casting alloy characteristics.

In some embodiments, the second die casting scheme may refer to a die casting scheme in which die casting alloy characteristics in the candidate die casting scheme are close to die casting alloy characteristics of the target die casting.

In some embodiments, the control module 120 may obtain a second plurality of die casting solutions from the plurality of candidate die casting solutions based on the casting alloy characteristics. For example, the control module 120 may obtain a plurality of second die-casting schemes from the candidate die-casting schemes that are close to the casting alloy characteristics of the target die-casting.

And 240, determining at least one first die casting scheme from a plurality of second die casting schemes based on the structural characteristics of the casting, wherein each first die casting scheme in the at least one first die casting scheme comprises a plurality of die casting process parameters.

In some embodiments, the first die casting scheme may refer to a die casting scheme in which the die casting structural characteristics are close to die casting alloy characteristics of a target die casting in the second die casting scheme.

The die-casting process parameters may refer to parameters corresponding to a die-casting process when a die-casting machine performs die-casting. In some embodiments, die casting process parameters may include mold clamping force, shot specific pressure, shot velocity, in-gate velocity, boost build-up time, hold time, mold dwell time, metal liquid temperature, mold temperature, and the like. And different die casting process parameters correspond to different target die castings in quality.

In some embodiments, the control module 120 may determine at least one first die-casting scheme from a plurality of second die-casting schemes based on casting structural characteristics. For example, the control module 120 may acquire one or more first die-casting schemes, of which the die-casting structural characteristics are close to those of the target die-casting, from a plurality of second die-casting schemes based on the casting structural characteristics.

And 250, optimizing a plurality of die casting process parameters of the at least one first die casting scheme based on the die casting effect of the at least one first die casting scheme.

The die-casting effect may refer to an evaluation result of the die-casting scheme. In some embodiments, the die casting effect may be determined by the related data of the die castings corresponding to the different die casting schemes. For example, the control module 120 can obtain data related to historical die castings corresponding to the first die casting schedule. The relevant data of the historical die castings can comprise die casting defects, defect levels, evaluations on the die castings and the like of the historical die castings. The evaluation of the die casting may include the grade (excellent, good, passing, failing, etc.) of the die casting, and the die casting score (0-100 points, etc.). For the related contents of die casting defects and defect levels, reference may be made to the related description of fig. 4.

In some embodiments, the control module 120 may optimize a plurality of die casting process parameters of the at least one first die casting scheme based on a die casting effect of the at least one first die casting scheme. For example, the control module 120 decreases a certain die casting process parameter and/or increases a certain die casting process parameter of the first die casting scheme based on the die casting effect of one or more first die casting schemes, and the like.

In some embodiments, the control module 120 may execute at least one first die casting scheme, obtaining a die casting; detecting the die casting, and determining die casting defects and defect grades, wherein the die casting defects comprise surface defects and internal defects; and optimizing a plurality of die casting process parameters of at least one first die casting scheme based on die casting defects and defect grades, and referring to the related description of the part of fig. 4 for specific description.

In some embodiments of the present description, a first die-casting scheme is determined according to casting characteristics and die-casting system characteristics of a target die-casting, and based on a die-casting effect of the first die-casting scheme, a plurality of die-casting process parameters are optimized, so that a die-casting process can be improved, and the quality of the die-casting can be improved.

Fig. 3 is an exemplary flow diagram for cluster-based determination of a first die-casting scheme in accordance with some embodiments of the present description. As shown in fig. 3, the process 300 includes the following steps. In some embodiments, the process 300 may be performed by the control module 120.

At step 310, a plurality of die casting schemes are obtained through networking.

The die casting scheme may refer to a scheme on how to obtain a die cast. The characteristics of the die castings produced corresponding to the different die casting schemes may include different first die casting system characteristics, first casting alloy characteristics, first casting structural complexity, and the like. In some embodiments, different die casting schemes may include different die casting corresponding first casting characteristics and first die casting system characteristics, and so on. The first casting characteristic may include a first casting alloy characteristic, a first casting structural characteristic, and/or the like. The first casting structural characteristic may include a first casting structural complexity, and the like.

Regarding the first die-casting system characteristic, the first casting characteristic (e.g., the first casting alloy characteristic, the first casting structural complexity, etc.) is similar to the die-casting system characteristic, the casting characteristic (e.g., the casting alloy characteristic, the casting structural complexity, etc.), and differs only in that the first die-casting system characteristic, the first casting characteristic (e.g., the first casting alloy characteristic, the first casting structural complexity, etc.), etc. are relevant characteristics of die castings in a die-casting scheme obtained through networking; the die casting system characteristics, casting characteristics ((e.g., casting alloy characteristics, casting structural complexity, etc.) and the like are relevant characteristics of the target die casting, so more about relevant characteristics of die castings in a die casting scheme obtained through networking is referred to the relevant description of FIG. 2.

In some embodiments, the control module 120 may obtain multiple die casting schemes through networking.

And 320, determining the die-casting schemes with the first die-casting system characteristics meeting the first preset conditions and the first die-casting effects meeting the first preset effects as a plurality of candidate die-casting schemes based on the first cluster.

The first cluster may refer to a cluster based on die casting system characteristics. The type of the clustering algorithm of the first cluster may include various types, for example, the clustering algorithm of the first cluster may include K-Means clustering, density-based clustering method (DBSCAN), and the like.

The first preset condition may refer to a condition that is set in advance to be satisfied with respect to the first die-casting system characteristic. In some embodiments, the first preset condition may be represented by a feature vector. Different elements in the feature vector of the first preset condition represent conditions that the corresponding first die-casting system characteristic needs to satisfy. For example, a characteristic vector (m1, m2, m3, …) of the first preset condition, where m1 may represent the runner resistance, and m1 corresponds to a value that the runner resistance in the first die-casting system characteristic needs to reach; m2 may represent the ingate speed, and m2 corresponds to the value that the ingate speed needs to reach in the first die casting system characteristic; m3 may represent the cross-sectional area of the vent passage, and m3 corresponds to a value to which the cross-sectional area of the vent passage in the first die-cast system characteristic needs to be reached, or the like. The numerical values of m1, m2, m3, and the like may be a range indicating that the corresponding first die-casting system characteristic needs to be within the range. For example, m1 corresponds to values of P1 to P2, which indicate a range of values that the runner resistance in the first die-casting system characteristic needs to satisfy. The first preset condition may be a first die-casting system characteristic that is close to (e.g., similarity greater than 80%) the die-casting system characteristic of the target die-casting. For example, the eigenvectors corresponding to the first die-casting system characteristics need to satisfy a similarity greater than 80% between eigenvectors corresponding to the die-casting system characteristics of the target die-casting.

The first die-casting effect may refer to a die-casting effect of a die-casting scheme obtained through networking. The first preset effect may refer to a die-casting effect that a die-casting scheme acquired through networking needs to satisfy.

In some embodiments, the control module 120 may cluster the plurality of die-casting schemes by using a clustering algorithm of the first clustering, so as to obtain a plurality of clustering centers. Different cluster centers include multiple die casting schemes. The plurality of cluster centers correspond to a plurality of first die-casting system characteristics. The control module 120 may obtain a first die-casting system characteristic that meets a first preset condition, and further obtain a cluster center corresponding to the first die-casting system characteristic. The control module 120 may determine, as a plurality of candidate die-casting schemes, a die-casting scheme in which a first die-casting effect of the plurality of die-casting schemes corresponding to the cluster center satisfies a first preset effect.

For example, the control module 120 obtains a plurality of cluster centers (e.g., a1, a2, A3, a4, etc.) corresponding to the plurality of die-casting schemes through a clustering algorithm of the first cluster. The first die-casting system characteristics respectively corresponding to the cluster centers a1, a2, A3, a4, and the like are B1, B2, B3, B4, and the like. Wherein the first die-casting system characteristic B3 satisfies a first preset condition (e.g., a similarity to a die-casting system characteristic of a target die-casting is greater than 80%, etc.). The control module 120 may determine, as the candidate die-casting schemes, a plurality of die-casting schemes of which a first die-casting effect satisfies a first preset effect in the die-casting schemes corresponding to the cluster center a 3.

In some embodiments, the control module 120 can determine a vector distance of the feature vector of the first die-casting system characteristic of the different cluster centers and the feature vector of the die-casting system characteristic of the target die-casting, and determine a similarity of the first die-casting system characteristic of the cluster centers and the die-casting system characteristic of the target die-casting based on the vector distance. The vector distance may include a cosine distance, a euclidean distance, a hamming distance, or the like.

And 330, determining the candidate die-casting schemes with the first die-casting effect meeting the second preset effect as a plurality of second die-casting schemes, wherein the first casting alloy characteristics of the candidate die-casting schemes meet the second preset condition and the first die-casting effect meets the second preset effect based on the second clustering.

The second cluster may refer to a cluster based on the characteristics of the first casting alloy.

The second predetermined condition may refer to a predetermined condition to be satisfied with respect to the characteristics of the alloy of the first casting. In some embodiments, the second preset condition may be represented by a feature vector. Different elements in the characteristic vector of the second preset condition represent conditions which need to be met by the corresponding alloy characteristics of the first casting. For example, a characteristic vector (a, b, c, …) of a second preset condition, wherein a can represent an alloy type, and the alloy type corresponding to the element a is a condition to be met by the alloy type in the alloy characteristics of the first casting; b may represent the metal content contained in the alloy, the value corresponding to b being the value to which the metal content contained in the alloy in the first cast alloy property is required to be reached; c may represent a range of crystallization temperatures, where c corresponds to a range of values that the crystallization temperature needs to achieve in the first cast alloy property, and so on. b, etc. may also be a range indicating that the corresponding first casting alloy property needs to be within the range. The second predetermined condition may be a first casting alloy characteristic that is similar to (e.g., greater than 90% similar to) a casting alloy characteristic of the target die casting. For example, the eigenvector corresponding to the first casting alloy characteristic is required to satisfy a similarity of more than 90% between eigenvectors corresponding to the casting alloy characteristics of the target die cast.

The second preset effect may refer to a die-casting effect that the candidate die-casting scheme needs to satisfy.

In some embodiments, the control module 120 may cluster the candidate die-casting schemes by using a clustering algorithm of the second clustering, so as to obtain a plurality of clustering centers. The different cluster centers include a plurality of candidate die-casting solutions. The plurality of cluster centers correspond to the plurality of first casting alloy properties. The control module 120 may obtain a first casting alloy characteristic satisfying a second preset condition, and further obtain a clustering center corresponding to the first casting alloy characteristic. The control module 120 may determine, as a plurality of second die-casting schemes, candidate die-casting schemes in which a first die-casting effect satisfies a second preset effect among the candidate die-casting schemes corresponding to the cluster center.

For example, the control module 120 obtains a plurality of cluster centers (e.g., C1, C2, C3, C4, etc.) corresponding to the plurality of candidate die-casting schemes through a clustering algorithm of the second cluster. The cluster centers C1, C2, C3, C4, etc. correspond to the first casting alloy properties D1, D2, D3, D4, etc., respectively. Wherein the first casting alloy characteristic D1 satisfies a second predetermined condition (e.g., greater than 90% similarity to the casting alloy characteristic of the target die casting, etc.). The control module 120 may determine, as the plurality of second die-casting schemes, a candidate die-casting scheme in which a first die-casting effect satisfies a second preset effect among a plurality of candidate die-casting schemes corresponding to the cluster center C1.

And 340, based on the third cluster, determining a second die-casting scheme with the first die-casting effect meeting a third preset effect in the plurality of second die-casting schemes as at least one first die-casting scheme, wherein the structural characteristics of the first casting meet a third preset condition.

The third cluster may refer to a cluster based on structural characteristics of the casting.

The third preset condition may refer to a preset condition that needs to be satisfied with respect to the structural characteristic of the first casting. In some embodiments, the third preset condition may be represented by a feature vector. Different elements in the feature vector of the third preset condition represent conditions which need to be met by the structural characteristics of the corresponding first casting. For example, the eigenvector (n1, n2, n3, n4, …) of the third preset condition, wherein n1 may represent the casting wall thickness, and the numerical range corresponding to the element n1 is the numerical range required by the casting wall thickness in the first casting structural characteristic; n2 may represent draft, the range of values for element n2 being the range of values that the draft in the first casting structural characteristic needs to achieve; n3 may represent the casting volume, the range of values for element n3 being the range of values that the casting volume in the first casting structural characteristic needs to achieve; n4 may represent the casting structural complexity, the numerical range to which the element n4 corresponds is the range of values to which the casting structural complexity in the first casting structural characteristic needs to be achieved, and so on. The third predetermined condition may be a first casting structural characteristic that is similar to the casting structural characteristic of the target die casting (e.g., a degree of similarity greater than 85%). For example, the eigenvectors corresponding to the first casting structural characteristic need to satisfy a similarity of more than 85% between eigenvectors corresponding to the casting structural characteristic of the target die casting.

The third preset effect may refer to a die-casting effect that the second die-casting scheme needs to satisfy. In some embodiments, the first preset effect, the second preset effect, the third preset effect, etc. may be the same or different. The control module 120 may preset a first preset effect, a second preset effect, a third preset effect, etc. according to actual requirements.

In some embodiments, the control module 120 may cluster the second die-casting schemes by using a clustering algorithm of the third clustering, so as to obtain a plurality of clustering centers. The different cluster centers include a plurality of second die-casting schemes. The plurality of cluster centers correspond to a plurality of first casting structural characteristics. The control module 120 may obtain the first casting structural characteristic meeting the third preset condition, and further obtain the clustering center corresponding to the first casting structural characteristic. The control module 120 may determine, as the at least one first die-casting scheme, a second die-casting scheme in which a first die-casting effect satisfies a third preset effect among a plurality of second die-casting schemes corresponding to the cluster center.

For example, the control module 120 obtains a plurality of cluster centers (e.g., E1, E2, E3, E4, etc.) corresponding to the plurality of second die-casting schemes through a clustering algorithm of the third cluster. The cluster centers E1, E2, E3, E4, etc. correspond to first casting alloy properties of F1, F2, F3, F4, etc., respectively. Wherein the first casting alloy property F2 satisfies a third predetermined condition. The control module 120 may determine, as the at least one first die-casting scheme, a plurality of second die-casting schemes of which the first die-casting effect satisfies a third preset effect, among a plurality of second die-casting schemes corresponding to the cluster center E2.

In some embodiments, the control module 120 clusters the plurality of second die-casting solutions through a clustering algorithm of the third clustering, obtains a plurality of clustering centers, and determines that different structural characteristics of the first casting structural characteristics corresponding to the die-casting produced by the plurality of second die-casting solutions correspond to different weights when determining at least one first die-casting solution. The control module 120 may perform clustering based on different weights corresponding to different structural characteristics. In some embodiments, the weight of the first casting structure complexity in the first casting structure characteristic is greater than a preset threshold.

The preset threshold may refer to a minimum weight of the first casting structure complexity in the casting structure characteristic. For example, the preset threshold is 0.5. The preset threshold of 0.5 represents a weight of the first casting structure complexity of the first casting structure characteristic of 0.5 or more. Illustratively, the first casting structural characteristic includes casting wall thickness, draft angle, casting volume, casting structural complexity, with corresponding weights of 0.2, 0.1, 0.6, respectively. The weight of the structural complexity of the first casting is greater than a preset threshold value of 0.5.

In some embodiments, when the control module 120 clusters the plurality of second die-casting schemes through the clustering algorithm of the third clustering, the weight of the structural complexity of the first casting corresponding to the die-casting produced by the plurality of second die-casting schemes is greater than the preset threshold. The control module 120 may cluster the plurality of second die-casting schemes through a clustering algorithm of a third cluster in which the weight of the structural complexity of the corresponding first casting is greater than a preset threshold value, so as to obtain a plurality of cluster centers. The control module 120 may obtain the first casting structural characteristic meeting the third preset condition, and further obtain the clustering center corresponding to the first casting structural characteristic. The control module 120 may determine, as the at least one first die-casting scheme, a plurality of second die-casting schemes, of the plurality of second die-casting schemes corresponding to the cluster center, where the first die-casting effect satisfies a third preset effect.

In some embodiments of the present description, the weight of the first casting structural complexity in the first casting structural characteristic is greater than a predetermined threshold when the control module 120 performs the third classification. And when clustering is ensured, clustering is preferentially carried out based on the structural complexity of the first casting, so that the obtained at least one first die-casting scheme can be close to the structural complexity of the casting of the target die-casting. And further, better die casting process parameters can be determined, and a better die casting effect can be obtained.

In some embodiments of the present description, the control module 120 determines the first die-casting scheme from the die-casting schemes based on the different first die-casting system characteristics and the first casting characteristics satisfying different preset conditions and preset effects, and may further ensure the die-casting effect of the determined first die-casting scheme.

FIG. 4 is an exemplary flow diagram illustrating optimization of die casting process parameters based on die casting effects according to some embodiments herein. As shown in fig. 4, the process 400 includes the following steps. In some embodiments, the flow 400 may be performed by the control module 120.

And step 410, executing at least one first die-casting scheme to obtain a die-casting piece.

The die cast may refer to a product produced by a die casting machine through the first die casting scheme.

In some embodiments, the control module 120 may obtain a first die-casting schedule, and control a die-casting machine to produce based on data associated with the first die-casting schedule to obtain a die-cast part.

And 420, detecting the die casting, and determining die casting defects and defect grades, wherein the die casting defects comprise surface defects and internal defects.

Die casting defects may refer to die castings that do not meet the associated defects of the target die casting. In some embodiments, die casting defects may include surface defects and internal defects. Surface defects can be a measure of the extent to which defects occur on the surface of a die cast part. Surface defects may include pull marks, cracks, deformations, burrs, depressions, flashes, desquamation, and the like. Internal defects can be a measure of the degree of defects occurring within a die cast part. Internal defects may include porosity, brittleness, leakage, hard spots, and the like.

In some embodiments, die casting defects may be represented by numerical values. For example, the number of pull marks, cracks, and the like in the surface defect is expressed by the number of the pull marks, the length of the cracks, and the number of the cracks (e.g., 2 cm in length, 3 in number, and the like). For example, the number of pores in the internal defect is represented by the numerical value such as the diameter and the number of pores (for example, the diameter is 0.1 to 0.3 cm, the number is 6).

In some embodiments, die casting defects may be referred to as being represented by a feature vector. Different elements in the eigenvector represent different defects of the die casting. For example, the surface defect vector represents a surface defect of a die casting. Different elements in the surface defect feature vector represent different defects of the surface of the die casting. The internal defect vector represents an internal defect of the die cast. Different elements in the surface defect feature vector represent different defects within the die cast part.

In some embodiments, the defect rating may represent a degree of defect of the die casting defect. The defect levels may include multiple types of defect levels. Different types of die casting defects have different defect levels. For example, a pull mark defect level, a crack defect level, a deformation defect level, a void defect level, and the like. The higher the defect grade is, the more serious the corresponding die casting defect is. In some embodiments, different elements in the surface defect feature vector and/or the internal defect feature vector may represent a defect level of the die casting defect.

In some embodiments, the control module 120 can determine die casting defects and defect levels by inspecting the die casting. For example, the control module 120 may detect a surface of the die casting via the camera and determine surface defects (e.g., pull marks, etc.) of the die casting. For another example, the control module 120 may determine internal defects (e.g., porosity, etc.) of the die cast part by controlling a cutting apparatus to cut the die cast part.

In some embodiments, the control module 120 may determine a plurality of surface defect vectors for the surface defects via an image recognition model, as described in detail with reference to FIG. 5.

And 430, optimizing a plurality of die casting process parameters of at least one first die casting scheme based on die casting defects and defect levels.

In some embodiments, the control module 120 may optimize a plurality of die casting process parameters of at least one first die casting scheme based on die casting defects and defect levels. For example, the control module 120 may obtain a corresponding preset strategy for each type of die casting defect based on different defect levels corresponding to different types of die casting defects. The preset strategy refers to a strategy for adjusting the parameters of the die-casting process. For example, increasing or decreasing certain die casting process parameters, etc. The preset policies may be pre-set policies based on experience and/or based on relevant documents, materials, etc. Illustratively, the type of the die casting defect is a crack, and the preset strategy corresponding to the crack comprises adjusting pressurization time, increasing die closing time and the like. The control module 120 may optimize process parameters (e.g., increase the mold clamping time, etc.) according to a predetermined strategy corresponding to the crack defect. The control module 120 may determine a specific value for increasing the clamp time (e.g., increasing by 10 seconds, 30 seconds, etc.) based on the crack defect level.

In some embodiments, if the die castings correspond to multiple types of die casting defects, the control module 120 may obtain an intersection of multiple preset strategies corresponding to the multiple types of die casting defects, and optimize the corresponding multiple die casting process parameters based on the intersection of the multiple preset strategies. When there is a predetermined policy opposite to the predetermined policy among the plurality of predetermined policies, the control module 120 may select the predetermined policy based on the defect level. For example, the die casting defects of the die casting 1 include die casting defect a (a defect level of 3) and die casting defect B (B defect level of 1). The preset strategy corresponding to the die casting defect A is 'increase parameter c'; the preset strategy corresponding to the die casting defect B is a reduction parameter c. The control module 120 can determine a preset strategy according to the defect levels of the die casting defects A and B. The a defect level 3 is greater than the B defect level 1, and the control module 120 may determine the preset strategy as the increase parameter c.

In some embodiments, the control module 120 may determine the adjustment amount of each of the plurality of die casting process parameters of the first die casting scheme through a die casting parameter optimization model, which is described in detail with reference to fig. 5.

In some embodiments, the control module 120 may determine a confidence level of the adjustment amount for each of the plurality of die casting process parameters of the at least one first die casting scheme via a die casting parameter optimization model, wherein the confidence level is negatively correlated with the casting structure complexity and with the variance of the plurality of surface defect vectors; and manually adjusting each die-casting process parameter based on the confidence coefficient, and referring to the relevant description in the part of fig. 5 for specific description.

In some embodiments of the present disclosure, the control module 120 determines a die casting defect by detecting a die casting corresponding to the first die casting scheme, and then optimizes a plurality of die casting process parameters of the first die casting scheme according to the die casting defect, so that a die casting process can be improved according to an actually produced die casting, and thus the quality of a target die casting can be improved.

Fig. 5 is an exemplary schematic diagram of a die casting parameter optimization model according to some embodiments described herein. In some embodiments, the process 500 may be performed by the control module 120.

In some embodiments, the control module 120 may determine the adjustment amount for each of the plurality of die casting process parameters of the first die casting schedule through the die casting parameter optimization model.

The adjustment 531 for each die casting process parameter may refer to an adjustment of the die casting process parameter. The adjustment amount of each die-casting process parameter is different. In some embodiments, the adjustment amount of the die casting process parameter can be represented by a specific numerical value. For example, the adjustment amount of the die casting process parameter a is + 0.5. The adjustment of the die casting process parameters can be expressed in percentage. For example, the adjustment amount of the die casting process parameter b is + 10%.

Die casting parameter optimization model 520 refers to a model that can optimize die casting parameters. The die-casting parameter optimization model is a machine learning model, in some embodiments, the type of the die-casting parameter optimization model may include a neural network model, a deep neural network model, and the like, and the selection of the model type may be determined as the case may be.

In some embodiments, the inputs 510 of the die casting parameter optimization model may include casting characteristics 511, die casting process parameters 513, die casting defects 512, defect levels 514, etc. of the target die casting. The casting characteristics 511 of the target die casting may include, among other things, the structural complexity of the casting. Die casting defects may include surface defect vectors, and the like.

In some embodiments, the die casting defects and defect levels input by the die casting parameter optimization model may be eigenvectors, elements in the eigenvectors representing different defect types, and values of the elements in the eigenvectors may represent the defect levels.

In some embodiments, the control module 120 may obtain the die casting defect and the feature vector corresponding to the defect level by adding an embedded layer in the die casting parameter optimization model. The input to the embedding layer is die casting defects and defect rating. And outputting the output of the embedding layer as a die casting defect and a characteristic vector corresponding to the defect grade. The output 530 of the die casting parameter optimization model may include an adjustment 531 for each die casting process parameter. If some die casting process parameters do not need to be adjusted, the adjustment amount of the die casting process parameters output by the die casting parameter optimization model can be 0.

In some embodiments, the control module 120 may derive the die-casting parameter optimization model based on multiple sets of training samples and label training.

In some embodiments, the training samples include sample casting characteristics, a plurality of sample die casting process parameters, sample die casting defects, sample defect levels, and the like, for a plurality of sets of target die castings. And labeling the adjustment amount of each die-casting process parameter of the sample of the target die-casting piece. The training data may be obtained based on historical data. For example, the control module 120 can use the casting characteristics, the plurality of die casting process parameters, the die casting defects and the defect levels of a target die casting in the historical data as a set of samples. The historical data comprises a plurality of target die castings. Each target die casting has casting characteristics, a plurality of die casting process parameters, die casting defects and defect grades of the corresponding target die casting. The control module 120 may obtain multiple sets of samples. The labels of the training data may be determined by manual labeling or automatic labeling. For example, the control module 120 can label the adjustment amount of each die casting process parameter of the target die casting as a label of the training sample.

In some embodiments, the control module 120 may determine the adjustment amount for each of the plurality of die casting process parameters of the first die casting scheme by processing a casting characteristic, a plurality of die casting process parameters, a die casting defect, a defect level, etc. of the target die casting through a die casting parameter optimization model.

In some embodiments of the present disclosure, the control module 120 determines the adjustment amount of each die-casting process parameter through the die-casting parameter optimization model, rather than determining the adjustment amount of each die-casting process parameter through actual tests, which can effectively save cost. In some embodiments of the present disclosure, the control module 120 determines the adjustment amount of each die-casting process parameter through the die-casting parameter optimization model, which may improve the accuracy of optimizing the die-casting process parameters, and may further ensure the die-casting effect of the determined first die-casting scheme.

In some embodiments, the die casting defects may include surface defects. The surface defects and corresponding defect levels may be determined by an image recognition model. In some embodiments, the control module 120 may determine a plurality of surface defect vectors for the surface defects via the image recognition model.

The surface defect vector may represent a surface defect of the die casting. Different elements in the surface defect vector represent different defects of the surface of the die casting. The numerical value of an element in the surface defect vector may represent a defect level. The larger the number, the larger the defect level, and the larger the corresponding surface defect.

The image recognition model refers to a model capable of recognizing the surface defects of the die casting. The image recognition model is a machine learning model, and in some embodiments, the type of the image recognition model may include a convolutional neural network model or the like, and the selection of the model type may be determined on a case-by-case basis.

In some embodiments, the input to the image recognition model may include die casting images or the like. The die casting images may include multiple die casting images, which may be die casting images captured by the control module 120 from multiple different angles by the camera, which may completely cover the surface of the die casting. The output of the image recognition model may include a surface defect vector.

In some embodiments, the image recognition model may be derived based on a plurality of training samples and label training.

In some embodiments, the training sample comprises a sample die cast image. The label is the sample surface defect vector. The training data may be obtained based on historical data. For example, the control module 120 may sample die casting images in the history. The labels of the training data may be determined by manual labeling or automatic labeling. For example, the control module 120 may set the label of a standard die casting image to 1, the standard die casting image being a defect-free die casting image. The defective die casting image labels are set to numerical values between 0 and 1, different numerical values represent defect levels, and the larger the numerical value is, the larger the defect level is. The defect levels may be labeled by manual labeling.

In some embodiments, control module 120 can process multiple die casting images, etc., through an image recognition model to determine surface defect vectors for die castings. In some embodiments, a surface defect vector may be a surface defect vector corresponding to an image of a die casting. The surface defect vector of the die casting can be obtained by weighted summation of the surface defect vectors corresponding to a plurality of die casting images shot at different angles.

In some implementations of the present description, the control module 120 determines the surface defect vector through the image recognition model, which is helpful for the die-casting parameter optimization model to determine the adjustment amount of each die-casting process parameter, so as to further improve the accuracy of optimizing the die-casting process parameter, and further ensure the die-casting effect of the determined first die-casting scheme.

In some embodiments, the control module 120 may determine a confidence level of the adjustment amount for each of the plurality of die casting process parameters of the at least one first die casting schedule through a die casting parameter optimization model. Wherein the confidence level is inversely related to the structural complexity of the casting and inversely related to the variance of the plurality of surface defect vectors. And manually adjusting each die-casting process parameter based on the confidence coefficient.

The confidence 532 of the adjustment of each die casting process parameter may refer to the confidence level of the adjustment of each die casting process parameter. In some embodiments, the confidence level may be a real number between 0 and 1. The larger the value, the higher the confidence that the corresponding adjustment amount is, and the more reliable the corresponding adjustment amount is. The smaller the value, the lower the confidence that the corresponding adjustment amount is, and the less reliable the corresponding adjustment amount is.

In some embodiments, the confidence is inversely related to the casting structure complexity. The greater the structural complexity of the casting, the more complex the structure of the die casting is represented, and the lower the confidence of the adjustment amount of the corresponding die casting process parameter.

In some embodiments, the confidence level is inversely related to the variance of the plurality of surface defect vectors. For example, for a plurality of die casting images shot at the same angle and/or close to the same angle, the larger the variance of a plurality of surface defect vectors corresponding to the output of the image recognition model, the less accurate the surface defect vector judged by the image recognition model, and when the surface defect vector input into the die casting parameter optimization model is less accurate, the lower the confidence of the adjustment of the corresponding die casting process parameter output by the die casting parameter optimization model.

In some embodiments, the control module 120 may determine a confidence 532 of the adjustment amount for each die casting process parameter through a die casting parameter optimization model. For example, based on the input casting characteristics (e.g., casting structure complexity, etc.) of the target die casting, a plurality of die casting process parameters, die casting defects (surface defect vectors, etc.), defect levels, etc., the die casting parameter optimization model outputs a confidence of the adjustment amount of each die casting process parameter.

Based on the confidence level, manual adjustments can be made to each die casting process parameter 540.

In some embodiments, each die casting process parameter may be manually adjusted based on a confidence in the amount of adjustment for each die casting process parameter. For example, when the confidence of the adjustment amount of the die casting process parameter is high, the confidence level is high, and manual adjustment can be performed according to the adjustment amount of the die casting process parameter. For another example, when the confidence of the adjustment amount of the die casting process parameter is low, the confidence level is low, and the die casting process parameter can be manually adjusted according to experience or preset rules.

In some embodiments of the description, the confidence level of the adjustment amount of each die-casting process parameter is determined by the die-casting parameter optimization model, so that the credibility of the adjustment amount of each die-casting process parameter output by the die-casting parameter optimization model can be determined, the accuracy of manual adjustment of the die-casting process parameters can be improved, and the die-casting effect of the determined first die-casting scheme can be further ensured.

It should be noted that the above description of the flow is for illustration and description only and does not limit the scope of the application of the present specification. Various modifications and alterations to the flow may occur to those skilled in the art, given the benefit of this description. However, such modifications and variations are intended to be within the scope of the present description.

Some embodiments of the present specification further disclose a computer-readable storage medium, which stores computer instructions, and when the computer reads the computer instructions in the storage medium, the computer executes the above-mentioned die-casting control method.

Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, though not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.

Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.

Additionally, the order in which the elements and sequences of the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.

Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to suggest that the viewer of the specification requires more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.

Where numerals describing the number of components, attributes or the like are used in some embodiments, it is to be understood that such numerals used in the description of the embodiments are modified in some instances by the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.

For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.

Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those explicitly described and depicted herein.

Claims

1. A die-casting control apparatus characterized by comprising:

the device comprises a die casting machine, a sensing module, a control module and a display module; and

the control module is used for:

acquiring casting characteristics and casting system characteristics of a target die casting, wherein the casting characteristics comprise at least one of casting structural characteristics and casting alloy characteristics, and the casting structural characteristics comprise at least one of casting wall thickness, demolding inclination, casting volume and casting structural complexity;

acquiring a plurality of candidate die-casting schemes from a networked database based on the die-casting system characteristics;

obtaining a plurality of second die casting solutions from the plurality of candidate die casting solutions based on the casting alloy characteristics;

determining at least one first die-casting scheme from the plurality of second die-casting schemes based on the casting structural characteristics, wherein each first die-casting scheme of the at least one first die-casting scheme comprises a plurality of die-casting process parameters;

optimizing the plurality of die casting process parameters of the at least one first die casting scheme based on a die casting effect of the at least one first die casting scheme.

2. The die-casting control device according to claim 1, wherein the casting structural complexity is determined based on a plurality of casting structural parameters including at least one of a number of symmetry axes, a number of reinforcing ribs, a surface area ratio, a number of sides, and a number of faces.

3. The die-casting control device according to claim 1, wherein the control module is further configured to:

obtaining a plurality of die-casting schemes through networking;

determining the die-casting schemes of which the first die-casting system characteristics meet a first preset condition and the first die-casting effect meets a first preset effect as the candidate die-casting schemes based on the first cluster;

determining the candidate die-casting schemes with the first die-casting effects meeting second preset conditions as the second die-casting schemes based on second clustering, wherein the first die-casting alloy characteristics of the candidate die-casting schemes meet second preset conditions;

and determining a second die-casting scheme with the first die-casting effect meeting a third preset effect as the at least one first die-casting scheme based on a third cluster, wherein the structural characteristics of the first casting in the plurality of second die-casting schemes meet a third preset condition.

4. The die-casting control apparatus according to claim 1, wherein the optimizing the plurality of die-casting process parameters of the at least one first die-casting scheme based on the die-casting effect of the at least one first die-casting scheme comprises:

executing the at least one first die-casting scheme to obtain a die-casting piece;

detecting the die casting, and determining die casting defects and defect grades, wherein the die casting defects comprise surface defects and internal defects;

optimizing the plurality of die casting process parameters of the at least one first die casting recipe based on the die casting defects and the defect levels.

5. A die-casting control method that is executed by a control module, the die-casting control method comprising:

6. The die-casting control method according to claim 5, wherein the casting structural complexity is determined based on a plurality of casting structural parameters including at least one of a number of symmetry axes, a number of reinforcing ribs, a surface area ratio, a number of sides, and a number of faces.

7. The die-casting control method according to claim 5, characterized by further comprising:

obtaining a plurality of die-casting schemes through networking;

determining candidate die-casting schemes of which the first casting alloy characteristics meet a second preset condition and the first die-casting effect meets a second preset effect as the second die-casting schemes based on the second clustering;

8. The die-casting control method according to claim 5, wherein the optimizing the plurality of die-casting process parameters of the at least one first die-casting scheme based on the die-casting effect of the at least one first die-casting scheme comprises:

9. The die-casting control system is characterized by comprising a sensing module, a control module and a display module;

the control module is used for:

acquiring casting characteristics and casting system characteristics of a target casting, wherein the casting characteristics comprise at least one of casting structural characteristics and casting alloy characteristics, and the casting structural characteristics comprise at least one of casting wall thickness, demolding inclination, casting volume and casting structural complexity;

10. A computer-readable storage medium, characterized in that the storage medium stores computer instructions which, when executed by a processor, implement the die-casting control method according to any one of claims 5 to 8.