CN116151093A - Method for acquiring part model, method for detecting part and related equipment thereof - Google Patents
Method for acquiring part model, method for detecting part and related equipment thereof Download PDFInfo
- Publication number
- CN116151093A CN116151093A CN202211498380.7A CN202211498380A CN116151093A CN 116151093 A CN116151093 A CN 116151093A CN 202211498380 A CN202211498380 A CN 202211498380A CN 116151093 A CN116151093 A CN 116151093A
- Authority
- CN
- China
- Prior art keywords
- model
- link
- ith
- ith device
- acquiring
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The disclosure provides a method for acquiring a part model, a method for detecting a part and related equipment thereof, and relates to the technical field of life cycle prediction of the part, wherein the method comprises the following steps: acquiring a first model of n devices in a part, and acquiring a second model of each device in each link in a life cycle, wherein n is a positive integer; carrying out model fusion on a first model of the ith device and a second model of the ith device under each link to obtain a third model of the ith device, wherein i is a positive integer, and i is more than or equal to 1 and less than or equal to n; and generating a part model of the part based on the third model of the n devices. The data analysis and the model establishment are carried out on each link of each device of the part, and the part model of the part is generated by fusion, so that the generated part model can simulate the working states of the part in different links in the life cycle, and is convenient for managing and tracking the life cycle of the part.
Description
Technical Field
The disclosure relates to the technical field of part life cycle prediction, and in particular relates to a part model acquisition method, a part detection method and related equipment thereof.
Background
With the wide application of business process management technology in product design, the production management and process tracking of parts are realized.
The tracking and management of the parts in the prior art are generally used for solving the problems of incomplete information collection, manual errors and the like in the management flow of the existing parts, or realizing the control of personnel on key links in the key links of the part flow in a mode of automatic reporting by a system so as to achieve the effects of quick response of the approval flow and the like.
Disclosure of Invention
The present disclosure aims to solve, at least to some extent, one of the technical problems in the related art.
To this end, an object of the present disclosure is to propose a method of acquiring a part model.
A second object of the present disclosure is to provide a method for detecting a component.
A third object of the present disclosure is to provide an acquisition apparatus for a part model.
A fourth object of the present disclosure is to provide a detection device for a component.
A fifth object of the present disclosure is to propose an electronic device.
A sixth object of the present disclosure is to propose a non-transitory computer readable storage medium.
A seventh object of the present disclosure is to propose a computer programme product.
To achieve the above object, an embodiment of a first aspect of the present disclosure provides a method for obtaining a part model, including: acquiring a first model of n devices in a part, and acquiring a second model of each device in each link in a life cycle, wherein n is a positive integer; carrying out model fusion on a first model of the ith device and a second model of the ith device under each link to obtain a third model of the ith device, wherein i is a positive integer, and i is more than or equal to 1 and less than or equal to n; and generating a part model of the part based on the third model of the n devices.
According to one embodiment of the present disclosure, obtaining a second model for each device at each link in a lifecycle includes: acquiring a sub-training sample set of an ith device in m links in a life cycle, wherein m is a positive integer; training the first initial model based on a sub-training sample set of the ith device in the jth link to obtain a second model of the ith device in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m.
According to one embodiment of the present disclosure, obtaining a sub-training sample set for an ith device at m links in a life cycle includes: acquiring a first training sample set of an ith device; from m links, determining a j-th link to which a first training sample in the first training sample set belongs; dividing the first training sample into a sub-training sample set of the ith device under the jth link.
According to one embodiment of the disclosure, performing model fusion on a first model of an ith device and a second model of the ith device under each link to obtain a third model of the ith device, including: acquiring a first weight of a first model of an ith device and a second weight of a second model of the ith device under each link; and carrying out model fusion on the first model of the ith device and the second model of the ith device under each link based on the first weight and the second weight to obtain a third model of the ith device.
According to one embodiment of the present disclosure, obtaining a second weight of a second model of an ith device under each link includes: acquiring an association relation between each link of the ith device; and determining a second weight of a second model of the ith device under each link based on the association relation.
According to one embodiment of the present disclosure, the method further comprises: acquiring a second training sample set of the part under a plurality of working conditions; training the second initial model based on the second training sample set to obtain a working condition model of the part; and updating the part model based on the working condition model.
According to one embodiment of the present disclosure, updating a part model based on a condition model includes: identifying coincident model parameters with the same categories of the working condition model and the part model; and updating the superposition model parameters of the part model based on the superposition model parameters of at least one working condition of the working condition model.
According to one embodiment of the present disclosure, obtaining a first model of n devices within a part includes: acquiring a fourth model of the ith part in each failure mode; and carrying out model fusion on the fourth model of the ith part in each failure mode to obtain a first model of the ith part.
According to one embodiment of the present disclosure, the life cycle of the ith device includes m links, where m is a positive integer, and obtaining a second model of each device under each link in the life cycle includes: obtaining a fifth model of the ith device in each failure mode in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m; and carrying out model fusion on the fifth model of the ith device in each failure mode in the jth link to obtain a second model of the ith part in the jth link.
To achieve the above object, an embodiment of a second aspect of the present disclosure provides a method for detecting a component, including: acquiring operation parameters of parts; the operation parameters of the parts are input into the part model of the parts, and the target parameters for representing the operation states of the parts are output by the part model.
To achieve the above object, an embodiment of a third aspect of the present disclosure provides an apparatus for obtaining a model of a component, including: the acquisition module is used for acquiring first models of n devices in the part and acquiring second models of each device in each link in the life cycle, wherein n is a positive integer; the fusion module is used for carrying out model fusion on the first model of the ith device and the second model of the ith device under each link to obtain a third model of the ith device, wherein i is a positive integer which is more than or equal to 1 and less than or equal to n; and the generating module is used for generating a part model of the part based on the third model of the n devices.
According to one embodiment of the present disclosure, the obtaining module is further configured to: acquiring a sub-training sample set of an ith device in m links in a life cycle, wherein m is a positive integer; training the first initial model based on a sub-training sample set of the ith device in the jth link to obtain a second model of the ith device in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m.
According to one embodiment of the present disclosure, the obtaining module is further configured to: acquiring a first training sample set of an ith device; from m links, determining a j-th link to which a first training sample in the first training sample set belongs; dividing the first training sample into a sub-training sample set of the ith device under the jth link.
According to one embodiment of the present disclosure, the fusion module is further configured to: acquiring a first weight of a first model of an ith device and a second weight of a second model of the ith device under each link; and carrying out model fusion on the first model of the ith device and the second model of the ith device under each link based on the first weight and the second weight to obtain a third model of the ith device.
According to one embodiment of the present disclosure, the fusion module is further configured to: acquiring an association relation between each link of the ith device; and determining a second weight of a second model of the ith device under each link based on the association relation.
According to one embodiment of the present disclosure, the generating module is further configured to: acquiring a second training sample set of the part under a plurality of working conditions; training the second initial model based on the second training sample set to obtain a working condition model of the part; and updating the part model based on the working condition model.
According to one embodiment of the present disclosure, the generating module is further configured to: identifying coincident model parameters with the same categories of the working condition model and the part model; and updating the superposition model parameters of the part model based on the superposition model parameters of at least one working condition of the working condition model.
According to one embodiment of the present disclosure, the obtaining module is further configured to: acquiring a fourth model of the ith part in each failure mode; and carrying out model fusion on the fourth model of the ith part in each failure mode to obtain a first model of the ith part.
According to one embodiment of the present disclosure, the obtaining module is further configured to: obtaining a fifth model of the ith device in each failure mode in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m; and carrying out model fusion on the fifth model of the ith device in each failure mode in the jth link to obtain a second model of the ith part in the jth link.
To achieve the above object, a fourth aspect of the present disclosure provides a device for detecting a component, including: the acquisition module is used for acquiring the operation parameters of the parts; and the output module is used for inputting the operation parameters of the parts into the part model of the parts, and outputting the target parameters for representing the operation states of the parts by the part model.
To achieve the above object, an embodiment of a fifth aspect of the present disclosure proposes an electronic device including: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to implement the method for acquiring the part model according to the embodiment of the first aspect of the present disclosure or the method for detecting the part according to the second aspect.
To achieve the above object, an embodiment of a sixth aspect of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions for implementing the method for acquiring a part model according to the embodiment of the first aspect of the present disclosure or the method for detecting a part according to the second aspect.
To achieve the above object, an embodiment of a seventh aspect of the present disclosure proposes a computer program product, comprising a computer program for implementing the method for acquiring a part model according to the embodiment of the first aspect of the present disclosure or the method for detecting a part according to the second aspect when the computer program is executed by a processor.
The data analysis and the model establishment are carried out on each link of each device of the part, and the part model of the part is generated by fusion, so that the generated part model can simulate the working state of the part in the life cycle, and is convenient for managing and tracking the life cycle of the part.
Drawings
FIG. 1 is a schematic illustration of a method of obtaining a part model according to one embodiment of the present disclosure;
FIG. 2 is a schematic illustration of another method of obtaining a part model according to one embodiment of the present disclosure;
FIG. 3 is a schematic illustration of another method of obtaining a part model according to one embodiment of the present disclosure;
FIG. 4 is a schematic illustration of another method of obtaining a part model according to one embodiment of the present disclosure;
FIG. 5 is a schematic diagram of a method of inspecting components in accordance with one embodiment of the present disclosure;
FIG. 6 is a schematic diagram of an apparatus for acquiring a part model according to one embodiment of the present disclosure;
FIG. 7 is a schematic diagram of a device for inspecting a part model according to one embodiment of the present disclosure;
fig. 8 is a schematic diagram of an electronic device according to one embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present disclosure and are not to be construed as limiting the present disclosure.
Fig. 1 is a schematic diagram of an exemplary embodiment of a method for obtaining a part model according to the present disclosure, as shown in fig. 1, the method for obtaining a part model includes the following steps:
s101, acquiring a first model of n devices in the part, and acquiring a second model of each device in each link in a life cycle, wherein n is a positive integer.
The component includes at least one device for a particular use or for a particular use in cooperation with other components. The components may be divided into various types, and the types of components in the present disclosure are not limited in any way. For example, the components are classified by material, and may be classified into metal components, nonmetal components, and the like, and classified by use of the components, and may be classified into manufacturing components, maintenance components, and the like. A device refers to a mechanism for a particular purpose or to perform a particular function, for example, a diode, a triode, etc.
It should be noted that, the life cycle mentioned in the embodiment of the present disclosure refers to the time length or the number of times from the start of use to the absence of use conditions of the parts, through which whether the parts are suitable for corresponding products or systems can be accurately analyzed, and meanwhile whether the parts have defects can be analyzed.
The first model in the embodiment of the disclosure refers to a model of a device, and the second model refers to a model of each element of a component under each link in a life cycle, and it should be noted that different links may further include a plurality of sub-links. Links may include a variety of links, and for example, may include production, assembly, testing (experiment), etc., and links may include generation process 1, generation process 2, generation process 3, generation process 4, etc. for producing corresponding sub-links, without limitation. Certain sequence relation may exist between different links, and meanwhile, certain sequence relation exists between sub links under the links, and specific needs are determined according to actual conditions.
In the embodiment of the disclosure, the first model may be a model generated according to factory data of the device, and the second model may be a model generated according to failure data of the device under different links. It should be noted that, the failure data is operation data of the device in the life cycle, and the method for obtaining the failure data may be various, which is not limited in any way. For example, the failure data can be obtained by counting the actual production data and the working condition failure data of the whole part; failure modes can be classified, and data of each failure mode is counted respectively to obtain failure data; fitting different failure modes of the whole life cycle of the part can be realized through data sets of multiple layers of links so as to acquire failure data; and can also be used as failure data by continuously accumulating data during production and use.
Alternatively, the failure probability function corresponding to the device may be determined by analyzing the failure data, and then the first model may be generated according to the corresponding failure probability function. It should be noted that the failure probability function may be various, and for example, may include a normal distribution function, a lognormal distribution function, a weibull distribution function, an exponential distribution, and the like, which are not limited in any way, and specifically need to be determined according to actual data and design requirements. Meanwhile, since there is a case where a link may include a plurality of sub-links, it is also necessary to add an interaction factor between the sub-links to generation of a model, for example, to assign different weights to different sub-links, and then determine a second model based on the weights and a failure probability function of each sub-link. For example, the interrelationship of the multiple sub-links may be parallel, series, mixed, etc.
Optionally, the first model and the second model may be selected from a set of models set in advance, and an adapted model is selected as the first model or the second model according to corresponding data. The set of models may be pre-set.
Optionally, the operation data under different links can be input into the first model for training to obtain the second model.
S102, carrying out model fusion on a first model of the ith device and a second model of the ith device under each link to obtain a third model of the ith device, wherein i is a positive integer, and i is more than or equal to 1 and less than or equal to n.
And the third model of the ith device applicable to all links can be obtained by carrying out model fusion on the first model of the ith device and the second model of the ith device under each link. It should be noted that, since there may be a certain order in each link, when the second model and the first model are fused, there may be mutual influence between the second models of each link, and when the models are fused, it is necessary to consider the influence factors between each link, and generate the third model based on the influence factors. For example, the interaction relationship between the plurality of second models may be parallel, series, mixed, or the like.
In the embodiment of the present disclosure, the method of model fusion may be various, for example, may include Boosting method, random forest method, etc., and is not limited herein, and specific needs are set according to actual design needs.
S103, generating a part model of the part based on the third model of the n devices.
In the embodiment of the disclosure, after the third model of the n devices is obtained, a part model of the part may be generated. The method for generating the part model based on the third model of the n devices may be various, and for example, may be based on a part method, a Boosting method, a random forest, etc., and is not limited in any way herein.
Since the n devices may have an influence on each other due to the connection sequence, when the third model of the n devices is generated into the part model, the influence factors of the n devices need to be considered, so that a more accurate third model is generated. The n third models may be weighted based on the interaction factors between the n devices, and then the part model of the part may be generated based on the weights of the n third models and the third models.
In the embodiment of the disclosure, first models of n devices in a part are obtained, second models of each device in each link in a life cycle are obtained, n is a positive integer, then the first models of the ith device and the second models of the ith device in each link are subjected to model fusion to obtain a third model of the ith device, i is a positive integer, i is more than or equal to 1 and less than or equal to n, and finally the part model of the part is generated based on the third models of the n devices. The data analysis and the model establishment are carried out on each link of each device of the part, and the part model of the part is generated by fusion, so that the generated part model can simulate the working state of the part in the life cycle, and is convenient for managing and tracking the life cycle of the part.
In the embodiment of the disclosure, the first models of n devices in the component are obtained, and the first model of the ith component can be obtained by obtaining the fourth model of the ith component in each failure mode and then carrying out model fusion on the fourth model of the ith component in each failure mode. The failure mode refers to the whole failure process from the failure causing factor, failure mechanism, failure development process to reaching of the failure critical state, and the like.
In the above embodiment, the second model of each device under each link in the life cycle is obtained, which may be further explained by fig. 2, and the method includes:
s201, a sub-training sample set of an ith device in m links in a life cycle is obtained, wherein m is a positive integer.
In the embodiment of the disclosure, a first training sample set of an ith device may be first obtained, then a jth link to which a first training sample in the first training sample set belongs is determined from m links, and finally the first training sample is divided into sub-training sample sets of the ith device under the jth link. Therefore, the first training sample set can be divided into m links respectively, and the model can be trained based on the sub-training sample sets under the m links respectively.
S202, training the first initial model based on a sub-training sample set of the ith device in the jth link to obtain a second model of the ith device in the jth link, wherein j is a positive integer, and j is more than or equal to 1 and less than or equal to m.
In the embodiment of the disclosure, the first model of the ith device may be trained based on the sub-training sample set under the jth link to obtain the second model of the ith device under the jth link.
Based on the above description, the ith device may include a plurality of sub-links in the jth link, and each sub-link may divide the sub-training sample set into a plurality of refined training sample sets. Because a certain implementation sequence exists in the plurality of sub-links, when the model is trained, a certain sequence also exists in a plurality of thinned training sample sets input into the first model, so that the influence on the accuracy of the generated second model due to the mutual influence relationship among the plurality of sub-links can be reduced.
In the embodiment of the disclosure, a sub-training sample set of an ith device in m links in a life cycle is firstly obtained, wherein m is a positive integer, and then training is performed on a first initial model based on the sub-training sample set of the ith device in a j link to obtain a second model of the ith device in the j link, wherein j is a positive integer, and j is more than or equal to 1 and less than or equal to m. Therefore, by acquiring the sub-training sample set corresponding to each link under the device and respectively training the first model, a second model of each device adapted to each link can be generated, and the robustness and accuracy of the second model are improved.
It should be noted that, the second model of each device under each link in the life cycle may be further obtained by obtaining a fifth model of the ith device under each failure mode in the jth link, where j is a positive integer, and j is 1 and less than or equal to m, and then performing model fusion on the fifth model of the ith device under each failure mode in the jth link to obtain the second model of the ith part under the jth link.
In the above embodiment, the model fusion is performed on the first model of the ith device and the second model of the ith device under each link to obtain the third model of the ith device, which may be further explained by fig. 3, and the method includes:
s301, acquiring a first weight of a first model of the ith device and a second weight of a second model of the ith device under each link.
In the embodiment of the disclosure, the first weight of the first model of the i-th device may be determined based on the association relationship between each device and then based on the association relationship. It should be noted that, the relationship between each device is determined by the system function, and the method for determining the association relationship between the devices may be various, which is not limited in any way.
Meanwhile, the association relation between each link of the ith device can be obtained, and then the second weight of the second model of the ith device under each link is determined based on the association relation. It should be noted that, the relationship between each link is determined by the operation flow between links.
The association relationship between each link can comprise parallel connection, series connection, mixed connection and the like. And are not intended to be limiting in any way. The second weight of the second model of each device under each link can be determined through the association relation and the operation data between each link.
S302, based on the first weight and the second weight, carrying out model fusion on the first model of the ith device and the second model of the ith device under each link to obtain a third model of the ith device.
In the embodiment of the disclosure, first a first weight of a first model of an ith device and a second weight of a second model of the ith device under each link are acquired, and then model fusion is performed on the first model of the ith device and the second model of the ith device under each link based on the first weight and the second weight to obtain a third model of the ith device. Therefore, by determining the first weight of the first model and the second weight of the second model of the device and fusing the first model and the second model according to the weights, a third model with higher accuracy can be determined based on the mutual influence relation among the devices, the influence among the devices and links is reduced, and the robustness and accuracy of the third model are improved.
In the actual operation link, the influence on the parts under different working conditions is also larger. For example, the factors affecting the device are temperature, at which the device will behave specifically, whereas different temperatures behave more differently. In the embodiment of the disclosure, the generation of models under different working conditions may be further explained based on fig. 4, as shown in fig. 4:
s401, acquiring a second training sample set of the part under a plurality of working conditions.
In the embodiments of the present disclosure, the working conditions may include various types, for example, temperature, humidity, etc., and are not limited in any way herein, and specific needs are defined according to actual design needs. It should be noted that the influencing conditions of different parts may be different, and may be one or more, and the specific requirement is determined according to the actual parts.
S402, training the second initial model based on the second training sample set to obtain a working condition model of the part.
It can be understood that the training of the model is a repeated iterative process, and the training is performed by continuously adjusting the network parameters of the model until the overall loss function value of the model is smaller than a preset value, or the overall loss function value of the model is not changed or the change amplitude is slow, and the model converges, so that a working condition model after the training is completed is obtained.
S403, updating the part model based on the working condition model.
In the embodiment of the disclosure, the superposition model parameters of the part model can be updated by identifying that the superposition model parameters with the same category exist between the working condition model and the part model and then based on the superposition model parameters of the working condition model under at least one working condition. For example, the factor affecting the device is temperature, at which the device will behave specifically, where the formula is:
p (characteristic 1|temperature 1) =f (x)
As can be seen by the formula, i.e. the property 1 occurrence is conditioned on the occurrence of temperature 1, while the probability function of the condition of occurrence is f (x); the f (x) function may be a theoretical-based continuous probability distribution, such as a normal distribution, and then the part model is updated based on f (x).
In the embodiment of the disclosure, a second training sample set of the part under a plurality of working conditions is firstly obtained, then a second initial model is trained based on the second training sample set to obtain a working condition model of the part, and finally the part model is updated based on the working condition model. Therefore, the second model is trained by adding the working condition data, the models of the components under different working conditions can be generated, a basis is provided for follow-up life cycle management and tracking of the components under different working conditions, and the practicability of the component models is improved.
As shown in fig. 5, a schematic diagram of an exemplary embodiment of a method for detecting a component according to the present disclosure, the method for obtaining a component model includes the following steps:
s501, acquiring the operation parameters of the parts.
The operation parameters of the components may be obtained by referring to the content in the above embodiments, and will not be described herein.
S502, inputting the operation parameters of the parts into a part model of the parts, and outputting target parameters for representing the operation states of the parts by the part model, wherein the part model is obtained by adopting the method for obtaining the part model in the embodiment.
In the disclosed embodiments, the target parameters may be various, and may include failure modes, failure probabilities, reliability metrics, lifetimes, and the like, for example. The specific requirements are set according to the actual design requirements, and are not limited in any way. The reliability of each link of the part can be subjected to data modeling through the output target parameters, so that the influence of each link on the reliability can be more fully known, the whole process of the part is controlled, the basis is laid for future failure mode analysis, the failure modes of the part under different working conditions can be analyzed, the failure contribution weight under different links can be analyzed, and the targeted production, management, upgrading and optimization of the part at the front end can be facilitated.
Corresponding to the method for acquiring the part model provided by the above embodiments, an embodiment of the present disclosure further provides an apparatus for acquiring the part model, and since the apparatus for acquiring the part model provided by the embodiment of the present disclosure corresponds to the method for acquiring the part model provided by the above embodiments, implementation of the method for acquiring the part model is also applicable to the apparatus for acquiring the part model provided by the embodiment of the present disclosure, and will not be described in detail in the following embodiments.
Fig. 6 is a schematic diagram of an acquiring device for a part model according to the present disclosure, and as shown in fig. 6, the acquiring device 600 for a part model includes an acquiring module 610, a fusion module 620, and a generating module 630.
The acquiring module 610 is configured to acquire a first model of n devices in the component, and acquire a second model of each device in each link in the life cycle, where n is a positive integer.
And a fusion module 620, configured to perform model fusion on the first model of the ith device and the second model of the ith device under each link to obtain a third model of the ith device, where i is a positive integer, and i is greater than or equal to 1 and less than or equal to n.
The generating module 630 is configured to generate a part model of the part based on the third model of the n devices.
In one embodiment of the present disclosure, the obtaining module 610 is further configured to: acquiring a sub-training sample set of an ith device in m links in a life cycle, wherein m is a positive integer; training the first initial model based on a sub-training sample set of the ith device in the jth link to obtain a second model of the ith device in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m.
In one embodiment of the present disclosure, the obtaining module 610 is further configured to: acquiring a first training sample set of an ith device; from m links, determining a j-th link to which a first training sample in the first training sample set belongs; dividing the first training sample into a sub-training sample set of the ith device under the jth link.
In one embodiment of the present disclosure, the fusion module 620 is further configured to: acquiring a first weight of a first model of an ith device and a second weight of a second model of the ith device under each link; and carrying out model fusion on the first model of the ith device and the second model of the ith device under each link based on the first weight and the second weight to obtain a third model of the ith device.
In one embodiment of the present disclosure, the fusion module 620 is further configured to: acquiring an association relation between each link of the ith device; and determining a second weight of a second model of the ith device under each link based on the association relation.
In one embodiment of the present disclosure, the generating module 630 is further configured to: acquiring a second training sample set of the part under a plurality of working conditions; training the second initial model based on the second training sample set to obtain a working condition model of the part; and updating the part model based on the working condition model.
In one embodiment of the present disclosure, the generating module 630 is further configured to: identifying coincident model parameters with the same categories of the working condition model and the part model; and updating the superposition model parameters of the part model based on the superposition model parameters of at least one working condition of the working condition model.
In one embodiment of the present disclosure, the obtaining module 610 is further configured to: acquiring a fourth model of the ith part in each failure mode; and carrying out model fusion on the fourth model of the ith part in each failure mode to obtain a first model of the ith part.
In one embodiment of the present disclosure, the obtaining module 610 is further configured to: obtaining a fifth model of the ith device in each failure mode in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m; and carrying out model fusion on the fifth model of the ith device in each failure mode in the jth link to obtain a second model of the ith part in the jth link.
Fig. 7 is a schematic diagram of a detection device for a part according to the present disclosure, and as shown in fig. 7, an acquisition device 700 for a part model includes an acquisition module 710 and an output module 720.
The acquisition module 710 is configured to acquire an operation parameter of the component.
An output module 720, configured to input the operation parameters of the component into a component model of the component, and output, by the component model, the target parameters for characterizing the operation state of the component, where the component model is obtained by using the method for obtaining the component model according to the embodiment of the claims.
In order to implement the above embodiments, the embodiments of the present disclosure further provide an electronic device 800, as shown in fig. 8, where the electronic device 800 includes: the processor 801 and the memory 802 communicatively coupled to the processors, the memory 802 storing instructions executable by the at least one processor, the instructions being executable by the at least one processor 801 to implement a method of obtaining a model of a part as an embodiment of the first aspect of the present disclosure.
To achieve the above-described embodiments, the embodiments of the present disclosure also propose a non-transitory computer-readable storage medium storing computer instructions for causing a computer to implement the method of acquiring the part model as the embodiments of the first aspect of the present disclosure.
In order to implement the above-mentioned embodiments, the embodiments of the present disclosure also propose a computer program product comprising a computer program which, when executed by a processor, implements a method for obtaining a model of a component as in the embodiments of the first aspect of the present disclosure.
In the description of the present disclosure, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings are merely for convenience in describing the present disclosure and simplifying the description, and do not indicate or imply that the device or element being referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present disclosure.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more such feature. In the description of the present disclosure, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present disclosure. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Although embodiments of the present disclosure have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the present disclosure, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the present disclosure.
Claims (23)
1. A method of obtaining a model of a component, comprising:
Acquiring a first model of n devices in a part, and acquiring a second model of each device in each link in a life cycle, wherein n is a positive integer;
carrying out model fusion on a first model of an ith device and a second model of the ith device under each link to obtain a third model of the ith device, wherein i is a positive integer which is more than or equal to 1 and less than or equal to n;
and generating a part model of the part based on the third model of the n devices.
2. The method of claim 1, wherein the obtaining a second model for each device at each link in the lifecycle comprises:
acquiring a sub-training sample set of the ith device in m links in a life cycle, wherein m is a positive integer;
training the first initial model based on a sub-training sample set of the ith device in the jth link to obtain a second model of the ith device in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m.
3. The method of claim 2, wherein the obtaining the sub-training sample set for the ith device at m segments of the life cycle comprises:
acquiring a first training sample set of the ith device;
Determining a j-th link to which a first training sample in the first training sample set belongs from the m links;
dividing the first training sample into a sub-training sample set of the ith device in the jth link.
4. The method according to claim 1, wherein the model fusing the first model of the ith device and the second model of the ith device under each link to obtain the third model of the ith device includes:
acquiring a first weight of a first model of the ith device and a second weight of a second model of the ith device under each link;
and carrying out model fusion on the first model of the ith device and the second model of the ith device under each link based on the first weight and the second weight to obtain a third model of the ith device.
5. The method of claim 4, wherein obtaining the second weight of the second model of the ith device at each link comprises:
acquiring an association relation between each link of the ith device;
and determining a second weight of a second model of the ith device under each link based on the association relation.
6. The method as recited in claim 1, further comprising:
acquiring a second training sample set of the part under a plurality of working conditions;
training a second initial model based on the second training sample set to obtain a working condition model of the part;
and updating the part model based on the working condition model.
7. The method of claim 6, wherein updating the part model based on the operating mode model comprises:
identifying coincident model parameters with the same categories of the working condition model and the part model;
and updating the superposition model parameters of the part model based on the superposition model parameters of at least one working condition of the working condition model.
8. The method of any of claims 1-7, wherein the obtaining a first model of n devices within a part comprises:
acquiring a fourth model of the ith part in each failure mode;
and carrying out model fusion on the fourth model of the ith part in each failure mode to obtain a first model of the ith part.
9. The method of any of claims 1-7, wherein the lifecycle of the ith device includes m bins, where m is a positive integer, the obtaining a second model for each device at each bin within the lifecycle comprising:
Obtaining a fifth model of the ith device in each failure mode in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m;
and carrying out model fusion on the fifth model of the ith device in each failure mode in the jth link to obtain a second model of the ith device in the jth link.
10. A method of detecting a component, comprising:
acquiring operation parameters of parts;
inputting the operation parameters of the component into a component model of the component, and outputting target parameters for representing the operation state of the component by the component model, wherein the component model is obtained by adopting the component model obtaining method according to any one of claims 1-9.
11. An acquisition apparatus for a model of a component, comprising:
the acquisition module is used for acquiring first models of n devices in the part and acquiring second models of each device in each link in the life cycle, wherein n is a positive integer;
the fusion module is used for carrying out model fusion on the first model of the ith device and the second model of the ith device under each link to obtain a third model of the ith device, wherein i is a positive integer which is more than or equal to 1 and less than or equal to n;
And the generating module is used for generating a part model of the part based on the third model of the n devices.
12. The apparatus of claim 11, wherein the acquisition module is further configured to:
acquiring a sub-training sample set of the ith device in m links in a life cycle, wherein m is a positive integer;
training the first initial model based on a sub-training sample set of the ith device in the jth link to obtain a second model of the ith device in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m.
13. The apparatus of claim 12, wherein the acquisition module is further configured to:
acquiring a first training sample set of the ith device;
determining a j-th link to which a first training sample in the first training sample set belongs from the m links;
dividing the first training sample into a sub-training sample set of the ith device in the jth link.
14. The apparatus of claim 11, wherein the fusion module is further configured to:
acquiring a first weight of a first model of the ith device and a second weight of a second model of the ith device under each link;
And carrying out model fusion on the first model of the ith device and the second model of the ith device under each link based on the first weight and the second weight to obtain a third model of the ith device.
15. The apparatus of claim 14, wherein the fusion module is further configured to:
acquiring an association relation between each link of the ith device;
and determining a second weight of a second model of the ith device under each link based on the association relation.
16. The apparatus of claim 11, wherein the generating module is further configured to:
acquiring a second training sample set of the part under a plurality of working conditions;
training a second initial model based on the second training sample set to obtain a working condition model of the part;
and updating the part model based on the working condition model.
17. The apparatus of claim 16, wherein the generating module is further configured to:
identifying coincident model parameters with the same categories of the working condition model and the part model;
and updating the superposition model parameters of the part model based on the superposition model parameters of at least one working condition of the working condition model.
18. The apparatus of any one of claims 11-17, wherein the acquisition module is further configured to:
acquiring a fourth model of the ith part in each failure mode;
and carrying out model fusion on the fourth model of the ith part in each failure mode to obtain a first model of the ith part.
19. The apparatus of any one of claims 11-17, wherein the lifecycle of the ith device includes m links, where m is a positive integer, the obtaining module further configured to:
obtaining a fifth model of the ith device in each failure mode in the jth link, wherein j is a positive integer which is more than or equal to 1 and less than or equal to m;
and carrying out model fusion on the fifth model of the ith device in each failure mode in the jth link to obtain a second model of the ith device in the jth link.
20. A device for detecting a component, comprising:
the acquisition module is used for acquiring the operation parameters of the parts;
an output module, configured to input the operation parameter of the component into a component model of the component, and output, by the component model, a target parameter for characterizing an operation state of the component, where the component model is obtained by using the component model obtaining method according to any one of claims 1 to 9.
21. An electronic device, comprising a memory and a processor;
wherein the processor runs a program corresponding to executable program code stored in the memory by reading the executable program code for implementing the method according to any one of claims 1-9 or the method according to claim 10.
22. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any one of claims 1-9 or the method according to claim 10.
23. A computer program product comprising a computer program which, when executed by a processor, implements the method of any one of claims 1-9 or the method of claim 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211498380.7A CN116151093B (en) | 2022-11-28 | 2022-11-28 | Method for acquiring part model, method for detecting part and related equipment thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211498380.7A CN116151093B (en) | 2022-11-28 | 2022-11-28 | Method for acquiring part model, method for detecting part and related equipment thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116151093A true CN116151093A (en) | 2023-05-23 |
| CN116151093B CN116151093B (en) | 2023-07-14 |
Family
ID=86349718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211498380.7A Active CN116151093B (en) | 2022-11-28 | 2022-11-28 | Method for acquiring part model, method for detecting part and related equipment thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116151093B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504296A (en) * | 2015-01-16 | 2015-04-08 | 湖南科技大学 | Gaussian mixture hidden Markov model and regression analysis remaining life prediction method |
| CN111680466A (en) * | 2020-05-15 | 2020-09-18 | 中国科学院微电子研究所 | Method and device for simulating integrated circuit device |
| CN113420776A (en) * | 2021-04-02 | 2021-09-21 | 上海师范大学 | Multi-side joint detection article classification method based on model fusion |
| CN114218710A (en) * | 2021-12-17 | 2022-03-22 | 浙江万里学院 | Automobile part big data optimization production design method |
| US20220121800A1 (en) * | 2020-10-19 | 2022-04-21 | Samsung Electronics Co., Ltd. | Methods of generating circuit models and manufacturing integrated circuits using the same |
| CN114580602A (en) * | 2022-03-18 | 2022-06-03 | 苏州浪潮智能科技有限公司 | Model training method, model training device, product life cycle prediction method, product life cycle prediction device, product life cycle prediction equipment and product life cycle prediction medium |
-
2022
- 2022-11-28 CN CN202211498380.7A patent/CN116151093B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504296A (en) * | 2015-01-16 | 2015-04-08 | 湖南科技大学 | Gaussian mixture hidden Markov model and regression analysis remaining life prediction method |
| CN111680466A (en) * | 2020-05-15 | 2020-09-18 | 中国科学院微电子研究所 | Method and device for simulating integrated circuit device |
| US20220121800A1 (en) * | 2020-10-19 | 2022-04-21 | Samsung Electronics Co., Ltd. | Methods of generating circuit models and manufacturing integrated circuits using the same |
| CN113420776A (en) * | 2021-04-02 | 2021-09-21 | 上海师范大学 | Multi-side joint detection article classification method based on model fusion |
| CN114218710A (en) * | 2021-12-17 | 2022-03-22 | 浙江万里学院 | Automobile part big data optimization production design method |
| CN114580602A (en) * | 2022-03-18 | 2022-06-03 | 苏州浪潮智能科技有限公司 | Model training method, model training device, product life cycle prediction method, product life cycle prediction device, product life cycle prediction equipment and product life cycle prediction medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116151093B (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Thelen et al. | A comprehensive review of digital twin—part 2: roles of uncertainty quantification and optimization, a battery digital twin, and perspectives | |
| Aizpurua et al. | Supporting group maintenance through prognostics-enhanced dynamic dependability prediction | |
| Kang et al. | Development of a Bayesian belief network model for software reliability quantification of digital protection systems in nuclear power plants | |
| CN112052172B (en) | Rapid test method and device for third-party channel and electronic equipment | |
| CN115356639B (en) | Intelligent health monitoring method and system for bidirectional lithium ion battery | |
| KR20150018681A (en) | Apparatus and method for predicting product condition by using datamining in manufacturing process | |
| CN118011990B (en) | Industrial data quality monitoring and improving system based on artificial intelligence | |
| Baraldi et al. | Uncertainty treatment in expert information systems for maintenance policy assessment | |
| CN116151093B (en) | Method for acquiring part model, method for detecting part and related equipment thereof | |
| CN101142559B (en) | Monitoring computer-controlled processes and systems | |
| CN113721182A (en) | Method and system for evaluating reliability of online performance monitoring result of power transformer | |
| US11531669B2 (en) | Systems and methods to assess and repair data using data quality indicators | |
| US20200311326A1 (en) | Self-service artificial intelligence platform leveraging data-based and physics-based models for providing real-time controls and recommendations | |
| CN105447518A (en) | Remote measurement data interpretation system based on K-means | |
| CN111459804B (en) | Node optimization method, device and storage medium in system test | |
| CN117310500A (en) | Battery state classification model construction method and battery state classification method | |
| CN111652379B (en) | Model management method, device, electronic equipment and storage medium | |
| CN112580823A (en) | Data processing method and device, readable storage medium and electronic equipment | |
| Mateo Casalí et al. | An industry maturity model for implementing Machine Learning operations in manufacturing | |
| Yang et al. | On investigation of the Bayesian anomaly in multiple imprecise dependent information aggregation for system reliability evaluation | |
| Nwadinobi et al. | Improved Markov stable state simulation for maintenance planning | |
| CN116071340A (en) | Method, apparatus and computer readable storage medium for checking target quantity | |
| CN116303038A (en) | Software testability analysis, design and evaluation method | |
| Nicholls | An objective look at predictions—Ask questions, challenge answers | |
| CN117852929A (en) | Vehicle quality control management method, device and storage medium |
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 |