CN111814278B - Data processing method, data processing device and terminal equipment - Google Patents

Data processing method, data processing device and terminal equipment Download PDF

Info

Publication number
CN111814278B
CN111814278B CN202010892158.XA CN202010892158A CN111814278B CN 111814278 B CN111814278 B CN 111814278B CN 202010892158 A CN202010892158 A CN 202010892158A CN 111814278 B CN111814278 B CN 111814278B
Authority
CN
China
Prior art keywords
evidence
matrix
product
vector
influence
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202010892158.XA
Other languages
Chinese (zh)
Other versions
CN111814278A (en
Inventor
蔡恒志
潘玲玲
刘辉
张超勇
黎建华
李永兴
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Leadwell Technology Co Ltd
Original Assignee
Shenzhen Leadwell Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Leadwell Technology Co Ltd filed Critical Shenzhen Leadwell Technology Co Ltd
Priority to CN202010892158.XA priority Critical patent/CN111814278B/en
Publication of CN111814278A publication Critical patent/CN111814278A/en
Application granted granted Critical
Publication of CN111814278B publication Critical patent/CN111814278B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/10—Geometric CAD
    • G06F30/17—Mechanical parametric or variational design
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/18—Manufacturability analysis or optimisation for manufacturability
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/30—Computing systems specially adapted for manufacturing

Abstract

The application is applicable to the technical field of data processing, and provides a data processing method, a data processing device, a terminal device and a computer readable storage medium, wherein the method comprises the following steps: acquiring a first set corresponding to each historical production product in n types of historical production products to obtain n first sets so as to construct an influence factor matrix; establishing an evidence matrix according to the influence factor matrix and a second set corresponding to the product to be produced; determining evidence weights corresponding to various influence factors to obtain an evidence weight distribution vector containing m evidence weights; based on the evidence weight distribution vector, carrying out fusion processing on elements in the evidence matrix to obtain the corresponding support degree of each first set; and determining the process parameter corresponding to the first set with the highest support degree as the target process parameter. By the method, reasonable process parameters can be rapidly made in the production of products, and the labor cost and the time cost of the production of the products are reduced.

Description

Data processing method, data processing device and terminal equipment
Technical Field
The present application belongs to the field of data processing technologies, and in particular, to a data processing method, a data processing apparatus, a terminal device, and a computer-readable storage medium.
Background
Reasonable process parameters have great significance for improving the production efficiency of products and reducing the defects of the products. Taking die-casting production as an example, in the traditional die-casting production, the formulation of the injection process parameters generally adopts a trial and error method, namely the injection process parameters are qualitatively formulated by taking the experiences of die-casting operators and technologists as main factors and combining the model of a die-casting machine and the characteristics of a die. The empirical method is often used in a large-batch die-casting production with few varieties, and once the method is transferred to a small-batch die-casting production with many varieties, the labor cost and the time cost are often wasted because the reasonable injection process parameters are difficult to find in a short time.
Disclosure of Invention
In view of this, the present application provides a data processing method, a data processing apparatus, a terminal device and a computer readable storage medium, which can rapidly determine reasonable process parameters in product production, and reduce labor cost and time cost of product production.
In a first aspect, the present application provides a data processing method, including:
acquiring a first set corresponding to each historical production product in n historical production products to obtain n first sets so as to construct an influence factor matrix, wherein each first set comprises m types of influence factors which are set by process parameters influencing the corresponding historical production product, each row in the influence factor matrix corresponds to one first set, each column corresponds to one type of influence factor, n is an integer larger than 1, and m is a positive integer;
establishing an evidence matrix according to the influence factor matrix and a second set corresponding to the product to be produced, wherein the evidence matrix is used for indicating the similarity between the historical production product and the product to be produced, and the second set comprises m types of influence factors which are formulated according to the process parameters influencing the product to be produced;
determining evidence weights corresponding to various influence factors to obtain an evidence weight distribution vector containing m evidence weights, wherein the evidence weights are used for indicating the influence degree of the corresponding influence factors on the process parameter formulation;
based on the evidence weight distribution vector, carrying out fusion processing on elements in the evidence matrix to obtain the corresponding support degree of each first set;
and determining the process parameter corresponding to the first set with the highest support degree as a target process parameter so as to instruct a user to produce the product to be produced by using the target process parameter.
In a second aspect, the present application provides a data processing apparatus comprising:
the system comprises a factor set acquisition unit, a factor set acquisition unit and a factor analysis unit, wherein the factor set acquisition unit is used for acquiring a first set corresponding to each historical production product in n historical production products to obtain n first sets so as to construct an influence factor matrix, each first set comprises m types of influence factors which are set by process parameters influencing the corresponding historical production product, in the influence factor matrix, each row corresponds to one first set, each column corresponds to one type of influence factor, n is an integer larger than 1, and m is a positive integer;
an evidence matrix establishing unit, configured to establish an evidence matrix according to the impact factor matrix and a second set corresponding to a product to be produced, where the evidence matrix is used to indicate a similarity between the historical production product and the product to be produced, and the second set includes m types of impact factors that affect the process parameters of the product to be produced;
the evidence weight determining unit is used for determining evidence weights corresponding to various influence factors to obtain an evidence weight distribution vector containing m evidence weights, and the evidence weights are used for indicating the influence degree of the corresponding influence factors on the process parameter formulation;
a matrix fusion unit, configured to perform fusion processing on elements in the evidence matrix based on the evidence weight distribution vector to obtain a support degree corresponding to each first set;
and the process parameter determining unit is used for determining the process parameter corresponding to the first set with the highest support degree as a target process parameter so as to instruct a user to produce the product to be produced by using the target process parameter.
In a third aspect, the present application provides a terminal device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the method provided in the first aspect when executing the computer program.
In a fourth aspect, the present application provides a computer readable storage medium storing a computer program which, when executed by a processor, implements the method as provided in the first aspect.
In a fifth aspect, the present application provides a computer program product, which, when run on a terminal device, causes the terminal device to perform the method provided by the first aspect.
As can be seen from the above, in the present application, a first set corresponding to each historical production product in n historical production products is obtained, n first sets are obtained, so as to construct an influence factor matrix, where each first set includes m types of influence factors formulated by process parameters influencing the corresponding historical production product, in the influence factor matrix, each row corresponds to one first set, each column corresponds to one type of influence factor, n is an integer greater than 1, and m is a positive integer, an evidence matrix is established according to the influence factor matrix and a second set corresponding to the product to be produced, where the evidence matrix is used to indicate similarity between the historical production product and the product to be produced, the second set includes m types of influence factors formulated by process parameters influencing the product to be produced, evidence weights corresponding to the various types of influence factors are determined, and an evidence weight distribution vector including m evidence weights is obtained, the evidence weights are used for indicating the influence degree of the corresponding influence factors on the process parameter formulation, elements in the evidence matrix are subjected to fusion processing based on the evidence weight distribution vectors to obtain the support degree corresponding to each first set, and the process parameter corresponding to the first set with the highest support degree is determined as the target process parameter so as to indicate a user to produce the product to be produced by using the target process parameter. According to the scheme, firstly, historical production products are used as a basis, similarity comparison is conducted on the products to be produced and the historical production products to obtain an evidence matrix, then, correlation degrees between various influence factors and product quality are analyzed by using the historical production products as the basis, evidence weights are distributed to the various influence factors according to the correlation degrees, and finally, various evidences in the evidence matrix are fused according to the evidence weights, so that reasonable target process parameters are determined in the process parameters of the various historical production products to indicate a user to produce the products to be produced by using the target process parameters.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a schematic flowchart of a data processing method provided in an embodiment of the present application;
fig. 2 is an exemplary view of an injection principle of a die casting machine according to an embodiment of the present application;
fig. 3 is a block diagram of a data processing apparatus according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
It should also be understood that the term "and/or" as used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
As used in this specification and the appended claims, the term "if" may be interpreted contextually as "when", "upon" or "in response to" determining "or" in response to detecting ". Similarly, the phrase "if it is determined" or "if a [ described condition or event ] is detected" may be interpreted contextually to mean "upon determining" or "in response to determining" or "upon detecting [ described condition or event ]" or "in response to detecting [ described condition or event ]".
Furthermore, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used for distinguishing between descriptions and not necessarily for describing or implying relative importance.
Reference throughout this specification to "one embodiment" or "some embodiments," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of the present application. Thus, appearances of the phrases "in one embodiment," "in some embodiments," "in other embodiments," or the like, in various places throughout this specification are not necessarily all referring to the same embodiment, but rather "one or more but not all embodiments" unless specifically stated otherwise. The terms "comprising," "including," "having," and variations thereof mean "including, but not limited to," unless expressly specified otherwise.
Fig. 1 shows a flowchart of a data processing method provided in an embodiment of the present application, which is detailed as follows:
step 101, acquiring a first set corresponding to each historical production product in n types of historical production products to obtain n first sets so as to construct an influence factor matrix;
in this embodiment of the present application, the historical production products are the products produced before the data processing method in this embodiment of the present application is executed, and the first set corresponding to each of the n types of historical production products includes m types of influence factors that influence the process parameters of the corresponding historical production product. Wherein n is an integer greater than 1, m is a positive integer, and specific values of n and m can be selected according to actual requirements, which is not limited herein. After the n first sets are obtained, the impact factor matrix C may be constructed using the n first sets.
Figure 356477DEST_PATH_IMAGE001
Wherein, CnA first set corresponding to the nth historical production product is represented. Each row in the impact factor matrix C corresponds to a first set, and each column corresponds to a class of impact factors. Taking die casting production as an example, each first set may include nine types of influence factors, namely pouring molten metal quality, casting and overflow quality, casting average wall thickness, pouring molten metal density, metal solidus temperature, metal liquidus temperature, pressure chamber diameter, pressure chamber length and pressure chamber fullness, and any of the nine types of influence factors may influence the establishment of the injection process parameters of the historical production product. In the influence factor matrix C, the influence factor of the first column may be the quality of the poured molten metal, the influence factor of the second column may be the quality of the cast product and the overflow, and so on, and the influence factor of the ninth column may be the plenum fullness. Optionally, the first set corresponding to each historical production product may be obtained from a preset historical production information base, and after each time a product is produced by die casting, the quality of the poured molten metal, the quality of the cast and the overflow, the average wall thickness of the cast, the density of the poured molten metal, the solidus temperature of the metal, the liquidus temperature of the metal, the diameter of the pressure chamber, the length of the pressure chamber, and the fullness of the pressure chamber in the current die casting production may be stored in the historical production information base.
102, establishing an evidence matrix according to the influence factor matrix and a second set corresponding to a product to be produced;
in this embodiment, the product to be produced is a product that needs to be produced currently, the second set includes m types of influence factors that influence the process parameters of the product to be produced, each first set mentioned in step 101 may include nine types of influence factors, based on the poured molten metal quality, the cast and overflow quality, the cast average wall thickness, the poured molten metal density, the metal solidus temperature, the metal liquidus temperature, the pressure chamber diameter, the pressure chamber length, and the pressure chamber fullness degree, the second set also includes nine types of influence factors, including the poured molten metal quality, the cast and overflow quality, the cast average wall thickness, the poured molten metal density, the metal solidus temperature, the metal liquidus temperature, the pressure chamber diameter, the pressure chamber length, and the pressure chamber fullness degree, it should be noted that the present embodiment does not limit the types of the influence factors in the first set and the second set, it is only necessary to ensure that the category of the impact factors in the first set is the same as the category of the impact factors in the second set. Alternatively, the second set may be input into the terminal device by a user, for example, the user currently needs to produce a die-casting product, and in order to determine the injection process parameters used for producing the die-casting product, the user needs to determine nine types of influence factors corresponding to the die-casting product, such as the quality of the casting molten metal, the quality of the casting and the overflow, the average wall thickness of the casting, the density of the casting molten metal, the solidus temperature of the metal, the liquidus temperature of the metal, the diameter of the pressure chamber, the length of the pressure chamber, and the fullness of the pressure chamber, in advance, and input the nine types of influence factors into the terminal device. And after the terminal equipment obtains the second set, establishing an evidence matrix according to the influence factor matrix and the second set. Specifically, each row in the impact factor matrix corresponds to one first set, and each first set corresponds to one historical production product, so that the similarity between various historical production products and the to-be-produced products can be obtained by respectively comparing each row in the impact factor matrix with the second set, and an evidence matrix is established, wherein the evidence matrix is used for indicating the similarity between the historical production products and the to-be-produced products.
Optionally, the step 102 may specifically include:
subtracting the row vectors corresponding to the influence factor matrix and the second set line by line and then taking an absolute value to obtain a distance discrimination matrix;
carrying out negative correlation mapping on the distance discrimination matrix according to columns to obtain a similarity matrix;
and carrying out normalization processing on the similarity matrix according to columns to obtain an evidence matrix.
In this embodiment of the present application, the row vector corresponding to the second set includes various kinds of influence factors in the second set, and an arrangement order of the various kinds of influence factors in the row vector corresponding to the second set is the same as an arrangement order of the various kinds of influence factors in the influence factor matrix. For example, the impact factor matrix has three columns, the first column is the quality of the poured molten metal, the second column is the average wall thickness of the casting, and the third column is the diameter of the pressure chamber, then the first element in the second set of corresponding row vectors is the quality of the poured molten metal, the second element is the average wall thickness of the casting, and the third element is the diameter of the pressure chamber.
The row vectors corresponding to the second set may be referred to as
Figure 377129DEST_PATH_IMAGE002
And subtracting the row vectors X corresponding to the influence factor matrix C and the second set row by row, then taking an absolute value to obtain a distance discrimination matrix D, carrying out negative correlation mapping on the distance discrimination matrix D according to columns to obtain a similarity matrix S, and carrying out normalization processing on the similarity matrix S to obtain an evidence matrix E. The step of computing the evidence matrix is formulated as follows:
Figure 574892DEST_PATH_IMAGE003
wherein S isijElements representing the ith row and jth column of the similarity matrix S, EijRepresenting the element in the ith row and jth column of the evidence matrix E.
Step 103, determining the evidence weights corresponding to the various influence factors to obtain an evidence weight distribution vector containing m evidence weights;
in the embodiment of the application, considering that the influence degrees of different types of influence factors on the process parameter formulation are different, for each type of influence factor, a corresponding evidence weight can be determined for the type of influence factor according to the influence degree of the type of influence factor on the process parameter formulation, and the evidence weight is used for indicating the influence degree of the corresponding influence factor on the process parameter formulation. The greater the influence degree of a certain kind of influence factors on the process parameter formulation, the greater the evidence weight corresponding to the kind of influence factors, and conversely, the smaller the influence degree of a certain kind of influence factors on the process parameter formulation, the smaller the evidence weight corresponding to the kind of influence factors. For convenience in subsequent calculation, the evidence weights corresponding to the m types of influence factors may be represented in the form of an evidence weight distribution vector, where each element in the evidence weight distribution vector is an evidence weight.
Optionally, the step 103 may specifically include:
a1, acquiring comprehensive quality scores corresponding to various historical production products to obtain a comprehensive quality score vector containing n comprehensive quality scores;
a2, carrying out non-dimensionalization processing on the influence factor matrix to obtain a non-dimensionalized matrix;
and A3, determining the evidence weights corresponding to the various influence factors according to the dimensionless matrix and the comprehensive quality score vector to obtain an evidence weight distribution vector.
In the embodiment of the present application, the composite quality score is used to indicate the quality of the corresponding historical production product, and the quality of the historical production product is higher when the corresponding composite quality score is higher, and conversely, the quality of the historical production product is lower when the corresponding composite quality score is lower. The n historical production products correspond to n comprehensive quality scores, and the comprehensive quality score vector comprises the n comprehensive quality scores, namely each element in the comprehensive quality score vector is a comprehensive quality score.
Since the physical meanings and unit dimensions of the various influence factors in the influence factor matrix C are different, in order to ensure the accuracy of the evidence weight, the influence factor matrix C can be subjected to non-dimensionalization to obtain a non-dimensionalized matrix C', and the step of performing non-dimensionalization on the influence factor matrix C is expressed by the following formula:
Figure 856969DEST_PATH_IMAGE004
wherein, cij'denotes the element in the ith row and the jth column of the dimensionless matrix C', CijThe elements representing the ith row, jth column,
Figure 807476DEST_PATH_IMAGE005
represents the average value of the j-th column element in the impact factor matrix C,
Figure 47965DEST_PATH_IMAGE006
represents the standard deviation of the jth column element in the impact factor matrix C. According to the dimensionless matrix and the comprehensive quality score vector, the evidence weights corresponding to the various influence factors can be determined, and therefore an evidence weight distribution vector containing m evidence weights is obtained.
Optionally, the step a1 may specifically include:
obtaining at least one product quality evaluation index corresponding to various historical production products;
and calculating comprehensive quality scores corresponding to various historical production products according to at least one product quality evaluation index corresponding to various historical production products to obtain comprehensive quality score vectors.
In the embodiment of the application, each of the n historically-produced products corresponds to at least one product quality evaluation index, for example, each of the n historically-produced products corresponds to two quality evaluation indexes, namely, equivalent stress and porosity of the product. Optionally, the product quality evaluation index may be obtained from a historical production information base, and after a product is produced each time, the quality evaluation index corresponding to the product produced this time is stored in the historical production information base. For each historical production product in the n historical production products, a comprehensive quality score corresponding to the historical production product can be calculated according to at least one product quality evaluation index corresponding to the historical production product. Taking the example that each historical production product corresponds to two quality evaluation indexes, namely the equivalent stress and the porosity of the product, recording the comprehensive quality score vector as
Figure 733024DEST_PATH_IMAGE007
，giThe comprehensive quality score corresponding to the ith historical production product is shown
Figure 349950DEST_PATH_IMAGE008
Wherein P isiRepresenting the equivalent stress of the ith historically produced product,
Figure 922008DEST_PATH_IMAGE009
showing the porosity of the ith historically produced product.
Optionally, the step a3 may specifically include:
respectively calculating the gray correlation degree between each column in the dimensionless matrix and the comprehensive quality score vector to obtain a gray correlation degree vector containing m gray correlation degrees;
and carrying out normalization processing on the grey correlation degree vector to obtain an evidence weight distribution vector.
In this embodiment of the present application, a gray correlation degree between each column in the dimensionless matrix and the composite quality score vector may be calculated, specifically, each column in the dimensionless matrix may be used as a comparison number column in a gray correlation analysis method, and the composite quality score vector may be used as a reference number column in the gray correlation analysis method, so as to calculate a gray correlation degree between each column in the dimensionless matrix and the composite quality score vector. The grey correlation is calculated as follows:
Figure 598977DEST_PATH_IMAGE010
wherein the content of the first and second substances,
Figure 771333DEST_PATH_IMAGE011
，xirepresenting the comparison sequence, x0Denotes a reference number sequence, riRepresenting the comparison sequence xiAnd reference sequence x0The gray correlation degree between the two, s is the total number of comparison series, i ⊆ [1, s]N is the number of elements in each array,
Figure 660791DEST_PATH_IMAGE012
the minimum difference of the two levels is represented,
Figure 867782DEST_PATH_IMAGE013
the maximum difference of the two levels is represented,
Figure 450073DEST_PATH_IMAGE014
the resolution factor is expressed and is usually 0.5. The dimensionless matrix has m columns in total, so the grey correlation can be recorded as
Figure 358992DEST_PATH_IMAGE015
The gray relevance degree vector R is normalized to obtain an evidence weight distribution vector R', and the step of normalizing the gray relevance degree vector R is expressed by a formula as follows:
Figure 317720DEST_PATH_IMAGE016
wherein r isi' represents the evidence weight corresponding to the i-th type influence factor in the influence factor matrix C.
104, based on the evidence weight distribution vector, carrying out fusion processing on elements in the evidence matrix to obtain the support degree corresponding to each first set;
in the embodiment of the present application, the evidence weight distribution vector R' includes evidence weights of various impact factors, and based on each evidence weight, elements in the evidence matrix may be fused, so as to obtain a support degree corresponding to each first set.
Optionally, the step 104 may specifically include:
based on the evidence weight distribution vector, fusing each column in the evidence matrix into an evidence fusion column vector;
generating an evidence fusion matrix according to the evidence fusion column vector;
and fusing each column in the evidence fusion matrix by using a synthesis rule of the DS evidence theory to obtain the corresponding support degree of each first set.
In the embodiment of the present application, one column in the evidence matrix E corresponds to a class of influence factors, and one element in the evidence weight distribution vector RThe pixels represent evidence weights of a class of influence factors, and therefore, under the action of an evidence weight distribution vector R' (with the vector size of m × 1), each column in an evidence matrix E (with the matrix size of n × m) can be fused into an evidence fusion column vector F (with the vector size of n × 1), and the evidence fusion column vector F
Figure 848059DEST_PATH_IMAGE017
. According to the evidence fusion column vector, an evidence fusion matrix can be generated, each column of the evidence fusion matrix is an evidence fusion column vector, specifically, the evidence fusion matrix can be a matrix with n rows and n-1 columns, that is, the evidence fusion matrix includes n-1 columns of evidence fusion column vectors. For the evidence fusion matrix, the synthesis rule (i.e., Dempster synthesis rule) of DS evidence theory can be used to fuse the columns in the evidence fusion matrix, i.e., n-1 evidence fusion column vectors F are fused, so as to obtain the support corresponding to each first set.
The synthesis rules for DS evidence theory are illustrated as follows: for the
Figure 866830DEST_PATH_IMAGE018
Identifying a finite number of mass functions m on a frame U1，m2，…，mnThe Dempster synthesis rule of (A) is formulated as follows:
Figure 13778DEST_PATH_IMAGE019
the evidence fusion matrix can be used as an identification frame U, K is a conflict factor and reflects the conflict degree of the evidence, and A is a proposition.
Illustratively, each column in the evidence matrix may be fused into an evidence fusion column vector according to a preset fusion formula, where the fusion formula is
Figure 776198DEST_PATH_IMAGE020
Where F denotes an evidence fusion column vector, E denotes an evidence matrix, and R' denotes an evidence weight assignment vector.
And 105, determining the process parameter corresponding to the first set with the highest support degree as a target process parameter.
In the embodiment of the present application, after the support degrees corresponding to the first sets are obtained, the first set with the highest support degree may be determined. The process parameters of the historical production products corresponding to the first set with the highest support degree are closest to the reasonable process parameters required by the products to be produced, so that the process parameters of the historical production products corresponding to the first set with the highest support degree can be determined as the target process parameters. The terminal equipment can output the target process parameters to instruct a user to produce the product to be produced by using the process parameters. It should be noted that the target process parameter may still have a slight difference from the reasonable process parameter required by the product to be produced, but the user only needs to slightly adjust the target process parameter according to the actual situation to obtain the reasonable process parameter required by the product to be produced. This will greatly reduce the time for the user to set up the process parameters.
The data processing method in the embodiment of the present application is further described below by a specific example.
This specific example applies to die casting production, the mechanism of injection is as follows:
referring to fig. 2, fig. 2 shows a schematic injection diagram of a die casting machine, and the injection process can be generally divided into three stages, namely a slow injection stage, a fast injection stage and a pressurization stage.
And (3) a slow injection stage: the punch slowly pushes the molten metal to the front end of the pressure chamber, so that the molten metal fills the pressure chamber and flows to the front end of the inner sprue. In the stage, if the speed is too low or the stroke is too long, the tail part of the pressure chamber is trapped, and meanwhile, the temperature of the inner wall of the pressure chamber is lower than that of the molten metal, so that the heat loss of the molten metal is too much, the fluidity of the molten metal is poor, and the mold filling capacity is weakened; if the speed is too fast or the stroke is too short, the phenomenon of air entrainment can be caused, and finally the castings (products) are porous and loose. The process parameters considered at this stage are primarily slow shot speed and slow shot stroke.
And (3) a fast injection stage: after the molten metal in the pressing chamber is filled, the punch presses the molten metal into the die cavity at a high speed through the inner pouring gate, and simultaneously, the air in the die cavity is discharged to achieve the purpose of casting molding. The selection of process parameters at this stage is similar to that of the slow shot stage, with the main considerations of fast shot speed and fast shot stroke.
A pressurization stage: at this time, the cavity is filled with molten metal, the punch head continues to move forward and applies larger pressure, and the molten metal further exhausts doped gas under the pressure to reduce pores and porosity of the finished product. If the pressurizing stroke is too short, the casting is crystallized and formed under lower pressure, so that the casting is not compact enough, and the probability of air holes and looseness is increased; if the pressurizing stroke is too long, the internal stress of the casting is too large, and the adverse phenomena of casting cracks, damaged cores, molten aluminum flying and the like can be caused. The process parameter primarily considered at this stage is the pressurization stroke.
The influence factors influencing the process parameter establishment are as follows:
influencing factor Influencing factor Influencing factors considered herein
Relevant parameters of product mold Parameters of mold runner, parameters of mold overflow system and parameters of mold exhaust system Number, quality of pouring metal, quality of casting and overflow, average wall thickness of casting Quality of poured metal, castings and overflows Quality, average wall thickness of cast
Material related parameter Metal type, density of poured metal liquid, coefficient of thermal expansion of metal, metal solid Phase line temperature, metal liquidus temperature Density and solidus of metal for pouring molten metal Temperature, liquidus temperature of metal
Structural parameters of processing equipment Number of Mold locking force, injection force, pressure chamber diameter, pressure chamber length and pressure chamber fullness Pressure chamber diameter, pressure chamber length, pressure chamber charge Fullness level
Auxiliary equipment related parameters Die temperature machine parameters and pouring equipment parameters Is free of
Processing environment Ambient temperature and ambient humidity Is free of
In this specific example, the influence factors influencing the injection process parameter setting are set to 9 types, namely, the pouring molten metal density, the pouring molten metal quality, the casting quality and overflow quality, the metal solidus temperature, the metal liquidus temperature, the casting average wall thickness, the pressure chamber diameter, the pressure chamber length and the pressure chamber fullness. Selecting 15 historical production products for experimental verification, wherein the specific numerical values are as follows:
Figure 692201DEST_PATH_IMAGE021
the product to be produced is ADC12 shell, and the density of the casting metal liquid is 2.64g/cm3The mass of the poured molten metal is 1703g, the mass of the casting and the overflow mass are 1754g, the solidus temperature of the metal is 612 ℃, the liquidus temperature of the metal is 634 ℃, the average wall thickness of the casting is 2.6mm, the diameter of a pressure chamber is 70mm, and the length of the pressure chamber is 460mm, pressure chamber fullness 0.36. That is, the row vector X = [2.64, 1703, 1754, 612, 634, 2.6, 70, 460, 0.36 corresponding to the second set]。
According to the specific values of the influence factors in the table above and the row vector X corresponding to the second set, an evidence matrix E can be obtained as follows:
Figure 116096DEST_PATH_IMAGE022
the dimensionless matrix C' is as follows:
Figure 750340DEST_PATH_IMAGE023
the composite quality score vector G is as follows:
Figure 50871DEST_PATH_IMAGE024
obtaining an evidence weight distribution vector R' according to the dimensionless matrix and the comprehensive quality score vector G as follows:
Figure 821381DEST_PATH_IMAGE025
it can be seen that the evidence weights corresponding to the two types of influence factors, namely the average wall thickness of the casting and the diameter of the pressure chamber, are smaller, that is, the two types of influence factors, namely the average wall thickness of the casting and the diameter of the pressure chamber, have smaller influence degrees on the formulation of the injection process parameters of the product to be produced.
By fusion of formulae
Figure 916376DEST_PATH_IMAGE020
An evidence fusion column vector F can be obtained as follows:
Figure 37916DEST_PATH_IMAGE026
fusing each column in the evidence fusion matrix by using a synthesis rule of DS evidence theory to obtain each first set (namely historical production product)Article) are as follows:
historical production product 1 2 3 4 5 6 7 8
Degree of support 1.03×10-10 3.04×10-13 9.15×10-10 9.53×10-6 4.65×10-6 1.33×10-5 4.25×10-2 3.22×10-2
Historical production product 9 10 11 12 13 14 15 Is unknown
Degree of support 2.21×10-1 1.08×10-1 4.46×10-1 9.62×10-2 4.55×10-2 8.45×10-3 7.03×10-3 3.78×10-3
Wherein the first set corresponding to the historically produced product 11 has the highest support degree of 0.446, and therefore, the shot process parameters of the historically produced product 11 can be used as the target process parameters.
As can be seen from the above, in the scheme of the application, a first set corresponding to each historical production product in n historical production products is obtained, and n first sets are obtained to construct an influence factor matrix; establishing an evidence matrix according to the influence factor matrix and a second set corresponding to the product to be produced; determining evidence weights corresponding to various influence factors to obtain an evidence weight distribution vector containing m evidence weights; based on the evidence weight distribution vector, carrying out fusion processing on elements in the evidence matrix to obtain the corresponding support degree of each first set; and determining the process parameter corresponding to the first set with the highest support degree as the target process parameter. According to the scheme, firstly, historical production products are used as a basis, similarity comparison is conducted on the products to be produced and the historical production products to obtain an evidence matrix, then, correlation degrees between various influence factors and product quality are analyzed by using the historical production products as the basis, evidence weights are distributed to the various influence factors according to the correlation degrees, and finally, various evidences in the evidence matrix are fused according to the evidence weights, so that reasonable target process parameters are determined in the process parameters of the various historical production products to indicate a user to produce the products to be produced by using the target process parameters.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
Fig. 3 shows a block diagram of a data processing apparatus according to an embodiment of the present application, and only shows portions related to the embodiment of the present application for convenience of description.
The data processing apparatus 300 includes:
a factor aggregation obtaining unit 301, configured to obtain a first set corresponding to each historical production product in n types of historical production products, to obtain n first sets, so as to construct an influence factor matrix, where each first set includes m types of influence factors that influence process parameters of the corresponding historical production product, in the influence factor matrix, each row corresponds to one first set, each column corresponds to one type of influence factor, n is an integer greater than 1, and m is a positive integer;
an evidence matrix establishing unit 302, configured to establish an evidence matrix according to the impact factor matrix and a second set corresponding to a product to be produced, where the evidence matrix is used to indicate a similarity between the historical production product and the product to be produced, and the second set includes m types of impact factors that affect the process parameters of the product to be produced;
an evidence weight determining unit 303, configured to determine evidence weights corresponding to various impact factors, to obtain an evidence weight distribution vector including m evidence weights, where the evidence weights are used to indicate degrees of impact of the corresponding impact factors on the process parameter setting;
a matrix fusion unit 304, configured to perform fusion processing on elements in the evidence matrix based on the evidence weight distribution vector to obtain a support degree corresponding to each first set;
the process parameter determining unit 305 is configured to determine, as a target process parameter, a process parameter corresponding to the first set with the highest support degree, so as to instruct a user to produce the product to be produced by using the target process parameter.
Optionally, the evidence matrix creating unit 302 includes:
a distance discrimination matrix establishing subunit, configured to subtract the row vector corresponding to the second set from the line vector corresponding to the first set line by line, and then take an absolute value to obtain a distance discrimination matrix, where an arrangement order of each kind of influence factors in the row vector corresponding to the first set is the same as an arrangement order of each kind of influence factors in the influence factor matrix;
the negative correlation mapping subunit is used for performing negative correlation mapping on the distance discrimination matrix according to columns to obtain a similarity matrix;
and the similarity matrix normalization subunit is used for performing normalization processing on the similarity matrix according to columns to obtain the evidence matrix.
Optionally, the evidence weight determining unit 303 includes:
the comprehensive quality score acquiring subunit is used for acquiring comprehensive quality scores corresponding to various historical production products to obtain a comprehensive quality score vector containing n comprehensive quality scores, and the comprehensive quality scores are used for indicating the quality of the corresponding historical production products;
the dimensionless subunit is used for carrying out dimensionless processing on the influence factor matrix to obtain a dimensionless matrix;
and the evidence weight determining subunit is used for determining the evidence weights corresponding to the various influence factors according to the dimensionless matrix and the comprehensive quality score vector to obtain the evidence weight distribution vector.
Optionally, the comprehensive quality score obtaining subunit includes:
the evaluation index obtaining subunit is used for obtaining at least one product quality evaluation index corresponding to various historical production products;
and the comprehensive quality score calculating subunit is used for calculating the comprehensive quality scores corresponding to the various historical production products according to at least one product quality evaluation index corresponding to the various historical production products to obtain the comprehensive quality score vector.
Optionally, the evidence weight determining subunit includes:
the gray correlation degree calculation operator unit is used for calculating the gray correlation degree between each column in the dimensionless matrix and the comprehensive quality score vector respectively to obtain a gray correlation degree vector containing m gray correlation degrees;
and the grey correlation degree vector normalization subunit is used for performing normalization processing on the grey correlation degree vector to obtain the evidence weight distribution vector.
Optionally, the matrix fusion unit 304 includes:
a first fusion subunit, configured to fuse, based on the evidence weight distribution vector, each column in the evidence matrix into an evidence fusion column vector;
an evidence fusion matrix generation subunit, configured to generate an evidence fusion matrix according to the evidence fusion column vector, where each column in the evidence fusion matrix is the evidence fusion column vector;
and the second fusion subunit is used for fusing the columns in the evidence fusion matrix by using a synthesis rule of the DS evidence theory to obtain the corresponding support degree of each first set.
Optionally, the first fusing subunit is specifically configured to fuse, according to a preset fusing formula, each column in the evidence matrix into an evidence fusion column vector, where the fusing formula is
Figure 407717DEST_PATH_IMAGE020
Wherein, F is the evidence fusion column vector, E is the evidence matrix, and R' is the evidence weight distribution vector.
As can be seen from the above, in the scheme of the application, a first set corresponding to each historical production product in n historical production products is obtained, and n first sets are obtained to construct an influence factor matrix; establishing an evidence matrix according to the influence factor matrix and a second set corresponding to the product to be produced; determining evidence weights corresponding to various influence factors to obtain an evidence weight distribution vector containing m evidence weights; based on the evidence weight distribution vector, carrying out fusion processing on elements in the evidence matrix to obtain the corresponding support degree of each first set; and determining the process parameter corresponding to the first set with the highest support degree as the target process parameter. According to the scheme, firstly, historical production products are used as a basis, similarity comparison is conducted on the products to be produced and the historical production products to obtain an evidence matrix, then, correlation degrees between various influence factors and product quality are analyzed by using the historical production products as the basis, evidence weights are distributed to the various influence factors according to the correlation degrees, and finally, various evidences in the evidence matrix are fused according to the evidence weights, so that reasonable target process parameters are determined in the process parameters of the various historical production products to indicate a user to produce the products to be produced by using the target process parameters.
Fig. 4 is a schematic structural diagram of a terminal device according to an embodiment of the present application. As shown in fig. 4, the terminal device 4 of this embodiment includes: at least one processor 40 (only one shown in fig. 4), a memory 41, and a computer program 42 stored in the memory 41 and executable on the at least one processor 40, wherein the processor 40 executes the computer program 42 to perform the following steps:
acquiring a first set corresponding to each historical production product in n historical production products to obtain n first sets so as to construct an influence factor matrix, wherein each first set comprises m types of influence factors which are set by process parameters influencing the corresponding historical production product, each row in the influence factor matrix corresponds to one first set, each column corresponds to one type of influence factor, n is an integer larger than 1, and m is a positive integer;
establishing an evidence matrix according to the influence factor matrix and a second set corresponding to the product to be produced, wherein the evidence matrix is used for indicating the similarity between the historical production product and the product to be produced, and the second set comprises m types of influence factors which are formulated according to the process parameters influencing the product to be produced;
determining evidence weights corresponding to various influence factors to obtain an evidence weight distribution vector containing m evidence weights, wherein the evidence weights are used for indicating the influence degree of the corresponding influence factors on the process parameter formulation;
based on the evidence weight distribution vector, carrying out fusion processing on elements in the evidence matrix to obtain the corresponding support degree of each first set;
and determining the process parameter corresponding to the first set with the highest support degree as a target process parameter so as to instruct a user to produce the product to be produced by using the target process parameter.
Assuming that the above is the first possible implementation manner, in a second possible implementation manner provided on the basis of the first possible implementation manner, the establishing an evidence matrix according to the impact factor matrix and the second set corresponding to the product to be produced includes:
subtracting the row vectors corresponding to the second set from the influence factor matrix line by line and then taking an absolute value to obtain a distance discrimination matrix, wherein the arrangement sequence of various influence factors in the row vectors corresponding to the second set is the same as the arrangement sequence of various influence factors in the influence factor matrix;
carrying out negative correlation mapping on the distance discrimination matrix according to columns to obtain a similarity matrix;
and carrying out normalization processing on the similarity matrix according to columns to obtain the evidence matrix.
In a third possible implementation manner provided on the basis of the first possible implementation manner, the determining the evidence weights corresponding to the various types of influence factors to obtain an evidence weight distribution vector including m evidence weights includes:
acquiring comprehensive quality scores corresponding to various historical production products to obtain a comprehensive quality score vector containing n comprehensive quality scores, wherein the comprehensive quality scores are used for indicating the quality of the corresponding historical production products;
carrying out dimensionless processing on the influence factor matrix to obtain a dimensionless matrix;
and determining the evidence weights corresponding to various influence factors according to the dimensionless matrix and the comprehensive quality score vector to obtain the evidence weight distribution vector.
In a fourth possible implementation manner provided as a basis for the third possible implementation manner, the obtaining of the composite quality scores corresponding to the various historical production products to obtain a composite quality score vector including n composite quality scores includes:
obtaining at least one product quality evaluation index corresponding to various historical production products;
and calculating comprehensive quality scores corresponding to various historical production products according to at least one product quality evaluation index corresponding to various historical production products to obtain the comprehensive quality score vector.
In a fifth possible implementation manner provided based on the third possible implementation manner, the determining, according to the dimensionless matrix and the comprehensive quality score vector, the evidence weights corresponding to the various types of influence factors to obtain the evidence weight distribution vector includes:
respectively calculating the gray correlation degree between each column in the dimensionless matrix and the comprehensive quality score vector to obtain a gray correlation degree vector containing m gray correlation degrees;
and carrying out normalization processing on the gray correlation degree vector to obtain the evidence weight distribution vector.
In a sixth possible embodiment based on the first possible embodiment, the obtaining a support degree corresponding to each first set by performing fusion processing on elements in the evidence matrix based on the evidence weight assignment vector includes:
fusing each column in the evidence matrix into an evidence fusion column vector based on the evidence weight distribution vector;
generating an evidence fusion matrix according to the evidence fusion column vector, wherein each column in the evidence fusion matrix is the evidence fusion column vector;
and fusing the columns in the evidence fusion matrix by using a synthesis rule of a DS evidence theory to obtain the corresponding support degree of each first set.
In a seventh possible embodiment based on the sixth possible embodiment, the fusing the columns in the evidence matrix into an evidence-fused column vector based on the evidence weight assignment vector includes:
fusing each column in the evidence matrix into an evidence fusion column vector according to a preset fusion formula, wherein the fusion formula is
Figure 485264DEST_PATH_IMAGE027
Wherein, F is the evidence fusion column vector, E is the evidence matrix, and R' is the evidence weight distribution vector.
The terminal device 4 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. The terminal device may include, but is not limited to, a processor 40, a memory 41. Those skilled in the art will appreciate that fig. 4 is merely an example of the terminal device 4, and does not constitute a limitation of the terminal device 4, and may include more or less components than those shown, or combine some components, or different components, such as an input-output device, a network access device, and the like.
The Processor 40 may be a Central Processing Unit (CPU), and the Processor 40 may be other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 41 may be an internal storage unit of the terminal device 4, such as a hard disk or a memory of the terminal device 4. In other embodiments, the memory 41 may also be an external storage device of the terminal device 4, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like provided on the terminal device 4. Further, the memory 41 may include both an internal storage unit and an external storage device of the terminal device 4. The memory 41 is used for storing an operating system, an application program, a BootLoader (BootLoader), data, other programs, and the like, such as program codes of the computer programs. The above-mentioned memory 41 may also be used to temporarily store data that has been output or is to be output.
As can be seen from the above, in the scheme of the application, a first set corresponding to each historical production product in n historical production products is obtained, and n first sets are obtained to construct an influence factor matrix; establishing an evidence matrix according to the influence factor matrix and a second set corresponding to the product to be produced; determining evidence weights corresponding to various influence factors to obtain an evidence weight distribution vector containing m evidence weights; based on the evidence weight distribution vector, carrying out fusion processing on elements in the evidence matrix to obtain the corresponding support degree of each first set; and determining the process parameter corresponding to the first set with the highest support degree as the target process parameter. According to the scheme, firstly, historical production products are used as a basis, similarity comparison is conducted on the products to be produced and the historical production products to obtain an evidence matrix, then, correlation degrees between various influence factors and product quality are analyzed by using the historical production products as the basis, evidence weights are distributed to the various influence factors according to the correlation degrees, and finally, various evidences in the evidence matrix are fused according to the evidence weights, so that reasonable target process parameters are determined in the process parameters of the various historical production products to indicate a user to produce the products to be produced by using the target process parameters.
It should be noted that, for the information interaction, execution process, and other contents between the above-mentioned devices/units, the specific functions and technical effects thereof are based on the same concept as those of the embodiment of the method of the present application, and specific reference may be made to the part of the embodiment of the method, which is not described herein again.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned functions may be distributed as different functional units and modules according to needs, that is, the internal structure of the apparatus may be divided into different functional units or modules to implement all or part of the above-mentioned functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
The embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored, and the computer program, when executed by a processor, implements the steps in the above method embodiments.
Embodiments of the present application provide a computer program product, which, when running on a terminal device, causes the terminal device to execute the steps in the above-mentioned method embodiments.
The integrated unit may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, all or part of the processes in the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium and can implement the steps of the embodiments of the methods described above when the computer program is executed by a processor. The computer program includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file or some intermediate form. The computer-readable medium may include at least: any entity or apparatus capable of carrying computer program code to a terminal device, recording medium, computer Memory, Read-Only Memory (ROM), Random-Access Memory (RAM), electrical carrier wave signals, telecommunications signals, and software distribution medium. Such as a usb-disk, a removable hard disk, a magnetic or optical disk, etc. In certain jurisdictions, computer-readable media may not be an electrical carrier signal or a telecommunications signal in accordance with legislative and patent practice.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other ways. For example, the above-described apparatus/network device embodiments are merely illustrative, and for example, the division of the above modules or units is only one logical function division, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.

Claims (10)

1. A data processing method, comprising:
acquiring a first set corresponding to each historical production product in n historical production products to obtain n first sets so as to construct an influence factor matrix, wherein each first set comprises m types of influence factors which are set by process parameters influencing the corresponding historical production product, each row in the influence factor matrix corresponds to one first set, each column corresponds to one type of influence factor, n is an integer larger than 1, and m is a positive integer;
establishing an evidence matrix according to the influence factor matrix and a second set corresponding to the product to be produced, wherein the evidence matrix is used for indicating the similarity between the historical production product and the product to be produced, and the second set comprises m types of influence factors which influence the process parameters of the product to be produced;
determining evidence weights corresponding to various influence factors to obtain an evidence weight distribution vector containing m evidence weights, wherein the evidence weights are used for indicating the influence degree of the corresponding influence factors on the process parameter formulation;
based on the evidence weight distribution vector, carrying out fusion processing on elements in the evidence matrix to obtain the corresponding support degree of each first set;
and determining the process parameter corresponding to the first set with the highest support degree as a target process parameter so as to instruct a user to produce the product to be produced by using the target process parameter.
2. The data processing method according to claim 1, wherein the establishing of the evidence matrix according to the impact factor matrix and the second set corresponding to the product to be produced comprises:
subtracting the row vectors corresponding to the second set from the influence factor matrix line by line, and then taking an absolute value to obtain a distance discrimination matrix, wherein the arrangement sequence of various influence factors in the row vectors corresponding to the second set is the same as the arrangement sequence of various influence factors in the influence factor matrix;
carrying out negative correlation mapping on the distance discrimination matrix according to columns to obtain a similarity matrix;
and carrying out normalization processing on the similarity matrix according to columns to obtain the evidence matrix.
3. The data processing method according to claim 1, wherein the determining the evidence weights corresponding to the various types of influence factors to obtain an evidence weight distribution vector including m evidence weights comprises:
acquiring comprehensive quality scores corresponding to various historical production products to obtain a comprehensive quality score vector containing n comprehensive quality scores, wherein the comprehensive quality scores are used for indicating the quality of the corresponding historical production products;
carrying out dimensionless processing on the influence factor matrix to obtain a dimensionless matrix;
and determining the evidence weights corresponding to various influence factors according to the dimensionless matrix and the comprehensive quality score vector to obtain an evidence weight distribution vector.
4. The data processing method of claim 3, wherein the obtaining of the composite quality scores corresponding to the various historical production products to obtain a composite quality score vector comprising n composite quality scores comprises:
obtaining at least one product quality evaluation index corresponding to various historical production products;
and calculating comprehensive quality scores corresponding to various historical production products according to at least one product quality evaluation index corresponding to various historical production products to obtain the comprehensive quality score vector.
5. The data processing method according to claim 3, wherein the determining the evidence weights corresponding to the various types of influence factors according to the dimensionless matrix and the comprehensive quality score vector to obtain the evidence weight distribution vector comprises:
respectively calculating the gray correlation degree between each column in the dimensionless matrix and the comprehensive quality score vector to obtain a gray correlation degree vector containing m gray correlation degrees;
and carrying out normalization processing on the grey correlation degree vector to obtain the evidence weight distribution vector.
6. The data processing method according to claim 1, wherein the performing fusion processing on the elements in the evidence matrix based on the evidence weight distribution vector to obtain the support degree corresponding to each first set includes:
fusing each column in the evidence matrix into an evidence fusion column vector based on the evidence weight distribution vector;
generating an evidence fusion matrix according to the evidence fusion column vector, wherein each column in the evidence fusion matrix is the evidence fusion column vector;
and fusing all columns in the evidence fusion matrix by using a synthesis rule of a DS evidence theory to obtain the corresponding support degree of each first set.
7. The data processing method according to claim 6, wherein said fusing the columns in the evidence matrix into an evidence-fused column vector based on the evidence weight assignment vector comprises:
fusing each column in the evidence matrix into an evidence fusion column vector according to a preset fusion formula, wherein the fusion formula is
Figure 244015DEST_PATH_IMAGE001
And F is the evidence fusion column vector, E is the evidence matrix, and R' is the evidence weight distribution vector.
8. A data processing apparatus, comprising:
the system comprises a factor set acquisition unit, a factor set acquisition unit and a factor analysis unit, wherein the factor set acquisition unit is used for acquiring a first set corresponding to each historical production product in n historical production products to obtain n first sets so as to construct an influence factor matrix, each first set comprises m types of influence factors which are set by process parameters influencing the corresponding historical production product, in the influence factor matrix, each row corresponds to one first set, each column corresponds to one type of influence factor, n is an integer larger than 1, and m is a positive integer;
the evidence matrix establishing unit is used for establishing an evidence matrix according to the influence factor matrix and a second set corresponding to the product to be produced, the evidence matrix is used for indicating the similarity between the historical production product and the product to be produced, and the second set comprises m types of influence factors which influence the process parameters of the product to be produced;
the evidence weight determining unit is used for determining evidence weights corresponding to various influence factors to obtain an evidence weight distribution vector containing m evidence weights, and the evidence weights are used for indicating the influence degree of the corresponding influence factors on the process parameter formulation;
the matrix fusion unit is used for performing fusion processing on elements in the evidence matrix based on the evidence weight distribution vector to obtain the support degree corresponding to each first set;
and the process parameter determining unit is used for determining the process parameter corresponding to the first set with the highest support degree as a target process parameter so as to instruct a user to produce the product to be produced by using the target process parameter.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.
CN202010892158.XA 2020-08-31 2020-08-31 Data processing method, data processing device and terminal equipment Active CN111814278B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010892158.XA CN111814278B (en) 2020-08-31 2020-08-31 Data processing method, data processing device and terminal equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010892158.XA CN111814278B (en) 2020-08-31 2020-08-31 Data processing method, data processing device and terminal equipment

Publications (2)

Publication Number Publication Date
CN111814278A CN111814278A (en) 2020-10-23
CN111814278B true CN111814278B (en) 2020-12-18

Family

ID=72859791

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010892158.XA Active CN111814278B (en) 2020-08-31 2020-08-31 Data processing method, data processing device and terminal equipment

Country Status (1)

Country Link
CN (1) CN111814278B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112597435B (en) * 2020-12-24 2023-06-09 华能国际电力股份有限公司 Thermal power equipment quality data processing method and device based on equipment supervision
CN115730738B (en) * 2022-11-30 2024-01-05 中国电子产品可靠性与环境试验研究所（（工业和信息化部电子第五研究所）（中国赛宝实验室）） Process parameter determination method, device, computer equipment and storage medium

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102819673A (en) * 2012-07-26 2012-12-12 中国农业科学院农田灌溉研究所 Multisource irrigation information fusion method and device
CN107578141A (en) * 2017-07-25 2018-01-12 南京航空航天大学 Airfield runway Decision of Allocation method based on Fuzzy Level Analytic Approach and evidence theory

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008019434A1 (en) * 2006-08-14 2008-02-21 Victorian Tissue Engineering Pty Ltd The use of growth factors in a method of improving fat-graft survival
CN103235859B (en) * 2013-05-04 2015-08-05 四川虹欧显示器件有限公司 The defining method of optimal processing parameter combination in plasma panel manufacture process
US20170298270A1 (en) * 2016-04-14 2017-10-19 Schlumberger Technology Corporation Environmental gelling agent for gravel packing fluids
CN106919800A (en) * 2017-03-08 2017-07-04 郑州大学 The conflicting evidence management method of low similarity collision in a kind of evidence theory
CN108228853A (en) * 2018-01-11 2018-06-29 北京信息科技大学 A kind of microblogging rumour recognition methods and system
CN109272417A (en) * 2018-09-14 2019-01-25 北方民族大学 A kind of product manufacture sustainability multi-population discriminating conduct for supporting contradiction to handle
CN111428793A (en) * 2020-03-27 2020-07-17 东南大学 Evidence fusion method based on improved evidence dissimilarity

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102819673A (en) * 2012-07-26 2012-12-12 中国农业科学院农田灌溉研究所 Multisource irrigation information fusion method and device
CN107578141A (en) * 2017-07-25 2018-01-12 南京航空航天大学 Airfield runway Decision of Allocation method based on Fuzzy Level Analytic Approach and evidence theory

Also Published As

Publication number Publication date
CN111814278A (en) 2020-10-23

Similar Documents

Publication Publication Date Title
CN111814278B (en) Data processing method, data processing device and terminal equipment
TWI752455B (en) Image classification model training method, image processing method, data classification model training method, data processing method, computer device, and storage medium
CN115230067B (en) Intelligent determining method and system for injection molding process parameters
CN111143597A (en) Image retrieval method, terminal and storage device
US11734341B2 (en) Information processing method, related device, and computer storage medium
JP7450741B2 (en) Lithium battery SOC estimation method, device and computer readable storage medium
CN109783640A (en) One type case recommended method, system and device
CN110765292A (en) Image retrieval method, training method and related device
WO2019196238A1 (en) Speech recognition method, terminal device, and computer readable storage medium
CN110598993B (en) Data processing method and device
CN113111201B (en) Digital twin model lightweight method and system
CN110895533A (en) Form mapping method and device, computer equipment and storage medium
CN111552812A (en) Method and device for determining relation category between entities and computer equipment
CN114782125A (en) Product configuration method, device, computer equipment and storage medium
CN112506979A (en) Recommendation method and device for mold design
CN113204839A (en) Evaluation method for reliability of extrusion casting process parameter data
CN112926724A (en) Grading method and device for yield of injection molding product and electronic equipment
CN113034422A (en) Method and device for detecting yield of injection molding product and electronic equipment
CN111177170A (en) Compression updating method for multidimensional limited enumeration data
CN113850340A (en) Wind control feature generation method and electronic equipment
CN110704433A (en) Brin index construction method of columnar storage data, data retrieval method and device
CN111400343B (en) Query method and device for matched product mold and computer equipment
CN110210691A (en) Resource recommendation method, device, storage medium and equipment
CN110032652B (en) Media file searching method and device, storage medium and electronic device
CN111061830B (en) Method and device for processing automobile repair data

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant