CN117436290B - Digital twin model response optimization method and system - Google Patents
Digital twin model response optimization method and system Download PDFInfo
- Publication number
- CN117436290B CN117436290B CN202311766564.1A CN202311766564A CN117436290B CN 117436290 B CN117436290 B CN 117436290B CN 202311766564 A CN202311766564 A CN 202311766564A CN 117436290 B CN117436290 B CN 117436290B
- Authority
- CN
- China
- Prior art keywords
- real
- sensing parameter
- time
- model
- fault
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000004044 response Effects 0.000 title claims abstract description 30
- 238000005457 optimization Methods 0.000 title claims abstract description 23
- 238000009877 rendering Methods 0.000 claims abstract description 76
- 238000012216 screening Methods 0.000 claims abstract description 14
- 230000006870 function Effects 0.000 claims description 54
- 238000004088 simulation Methods 0.000 claims description 26
- 238000001514 detection method Methods 0.000 claims description 15
- 238000005315 distribution function Methods 0.000 claims description 14
- 238000012360 testing method Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 11
- 238000013507 mapping Methods 0.000 claims description 10
- 239000000306 component Substances 0.000 claims description 7
- 239000008358 core component Substances 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims 1
- 238000004590 computer program Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007620 mathematical function Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a digital twin model response optimization method and a system, which relate to the technical field of digital twin, and the method comprises the following steps: acquiring a real-time sensing parameter set aiming at a physical product; for each sensing parameter type, detecting whether the sensing parameter fluctuation amplitude for the sensing parameter type exceeds a preset fluctuation amplitude threshold based on a real-time sensing parameter corresponding to the sensing parameter type and a historical sensing parameter set; screening a first real-time sensing parameter and a second real-time sensing parameter of which the fluctuation amplitude of the corresponding sensing parameter exceeds a fluctuation amplitude threshold value from the real-time sensing parameter set; updating a historical sensing parameter set of the corresponding sensing parameter type based on the first real-time sensing parameter and the second real-time sensing parameter, and rendering a digital twin model based on the second real-time sensing parameter. Therefore, the digital twin model is only rendered by using the parameters with larger fluctuation amplitude, the number of parameters needing to be rendered is reduced, and the quick rendering response of the digital twin model is realized.
Description
Technical Field
The invention relates to the technical field of digital twinning, in particular to a digital twinning model response optimization method and system.
Background
The digital twin refers to a digital model of a physical product in a virtual space, information technologies such as perception, calculation, modeling and the like are comprehensively utilized, and the physical product is described, diagnosed, predicted and decided through software definition, so that interactive mapping of a real space and a digital space is realized.
In addition, by installing the sensor on the physical product, the digital twin model can simulate the running condition of the physical product in real time according to the sensing parameters. At present, once the digital twin model receives the sensing parameters, the digital twin model updates the whole digital space of the digital twin model, so that the system consumes larger and larger delay, and the real-time simulation target cannot be realized.
Disclosure of Invention
The embodiment of the invention provides a digital twin model response optimization method, a digital twin model response optimization system, electronic equipment and a storage medium, which are used for at least solving one of the technical problems.
In a first aspect, an embodiment of the present invention provides a method for optimizing a response of a digital twin model, including: acquiring a real-time sensing parameter set and a historical sensing parameter set aiming at a physical product;
wherein the physical product is configured with a corresponding digital twin model; the real-time sensing parameter set comprises a plurality of real-time sensing parameters, and the real-time sensing parameters are used for updating the digital twin model; each real-time sensing parameter is provided with a unique sensing parameter type respectively;
Based on each sensing parameter type, detecting the sensing parameter fluctuation amplitude of each sensing parameter type by combining the real-time sensing parameter and the historical sensing parameter corresponding to the sensing parameter type, and judging whether the fluctuation amplitude of each sensing parameter exceeds a preset fluctuation amplitude threshold;
screening at least one first real-time sensing parameter from the real-time sensing parameter set, wherein the fluctuation amplitude of the sensing parameter corresponding to the first real-time sensing parameter does not exceed a fluctuation amplitude threshold; screening at least one second real-time sensing parameter from the real-time sensing parameter set, wherein the fluctuation amplitude of the sensing parameter corresponding to the second real-time sensing parameter exceeds a fluctuation amplitude threshold;
updating a historical sensing parameter set of the corresponding sensing parameter type based on each first real-time sensing parameter and each second real-time sensing parameter; a digital twin model is rendered based on each of the second real-time sensing parameters.
Optionally, rendering the digital twin model based on each of the second real-time sensing parameters includes:
determining a target model module matched with the sensing parameter type corresponding to each second real-time sensing parameter according to a preset parameter rendering module table; the parameter rendering module table comprises a plurality of mapping relations, wherein the mapping relations comprise: the association relation between the target model module of the digital twin model and the sensing parameter type;
Rendering each target model module in the digital twin model based on each second real-time sensing parameter;
the physical product is a new energy automobile, and the target model module is a battery model module of a battery pack aiming at the new energy automobile.
Optionally, rendering each target model module in the digital twin model based on each second real-time sensing parameter comprises:
determining the target display level dimension of each second real-time sensing parameter corresponding to the target model module; wherein the display hierarchy dimension includes at least one of a product failure display dimension, a product appearance display dimension, and a product interior component display dimension;
sequencing the rendering priority of each second real-time sensing parameter according to the target display level dimension of each second real-time sensing parameter to obtain a rendering priority sequence;
and calling each second real-time sensing parameter according to the rendering priority order, and rendering the target model module.
Optionally, the rendering priority corresponding to the product failure display dimension is p Failure of Rendering priority corresponding to display dimension of product internal part is P Inside part The rendering priority corresponding to the product appearance display dimension is P Appearance of Wherein p is Failure of ＞P Appearance of ＞P Inside part The method comprises the steps of carrying out a first treatment on the surface of the And preferentially calling each second real-time sensing parameter corresponding to the product fault display dimension to render the target model module.
Optionally, invoking each second real-time sensing parameter corresponding to the product failure display dimension to render the target model module, including:
constructing a target gradient model set corresponding to the battery model module; the target gradient model set comprises a type gradient model, a test gradient model and a state gradient model; the type gradient model is used for simulating the fault type of the battery pack; the test gradient model is used for simulating damage test results of each point in the battery pack; the state gradient model is used for simulating the real-time running state of the battery pack;
invoking each second real-time sensing parameter of the corresponding product fault display dimension, and determining at least one target gradient model associated with the second real-time sensing parameter in the gradient model set;
and updating the rendering process of the target gradient model based on each second real-time sensing parameter of the corresponding product fault display dimension aiming at each target gradient model.
Optionally, updating the rendering process of the target gradient model includes:
acquiring a real-time running state of the battery pack based on the state gradient model;
Determining a fault simulation result according to each second real-time sensing parameter and the historical sensing parameter set;
updating a preset fault simulation function according to a fault simulation result and a real-time running state, and updating the rendering process of the type gradient model;
wherein, the fault simulation function is:
；
wherein,indicating that the battery pack is currently operating T in the real-time operating state m k Fitting a function of faults after the week, wherein k is a positive integer; v t Represents the fault type at time t, ρ represents the fault v t Proportional coefficient of failure time and failure time of corresponding core component, < >>Representing a fault v t A corresponding fault simulation result; />Representing a fault v t Is a level of influence of (2); m= (1, 2, 3), 1 indicates that the operation state is good, 2 indicates that the operation state is general, and 3 indicates that the operation state is bad; μ represents a pre-calibrated weighting factor.
Optionally, determining a fault simulation result according to each second real-time sensing parameter and the historical sensing parameter set includes:
calculating a fault simulation result based on a preset fault probability prediction function, each second real-time fault sensing parameter and each historical sensing parameter set;
the fault probability prediction function adopts a fault detection probability density function, and the fault probability density corresponding to the preset fault type is determined according to the fault detection probability density function;
The fault detection probability density function adopts a mixed distribution model, and the mixed distribution model comprises a plurality of probability distribution functions; the probability distribution function comprises a Weibull probability distribution model and a modified Gamma probability distribution model;
the function formula of the mixed distribution model is:
；
wherein,a fault density function at time t is represented; />A weight representing each probability distribution function; />The probability density function representing the ith distribution function.
Optionally, the functional formula of the Weibull probability distribution model is:
；
wherein W (t) represents Weibull fault density function at time t, beta represents a first variation trend parameter of the fault rate, and eta represents a first occurrence speed of the fault rate; and the beta and eta are determined after fitting analysis of the second real-time fault sensing parameter and a preset fault observation sample set.
Optionally, the function formula of the modified Gamma probability distribution model is:
；
wherein G (t) represents a Gamma fault density function at time t, alpha represents a first variation trend parameter of the fault rate, and sigma represents a second occurrence speed of the fault rate; Γ () represents a Gamma function; and alpha and sigma are determined after fitting and analyzing the second real-time fault sensing parameter and a preset fault observation sample set.
Another aspect of the present invention provides a digital twin model response optimization system, comprising: the acquisition unit is used for acquiring a real-time sensing parameter set and a historical sensing parameter set aiming at a physical product;
wherein the physical product is configured with a corresponding digital twin model; the real-time sensing parameter set comprises a plurality of real-time sensing parameters, and the real-time sensing parameters are used for updating the digital twin model; each real-time sensing parameter is provided with a unique sensing parameter type respectively;
the detection unit is used for detecting the fluctuation amplitude of the sensing parameters of each sensing parameter type based on each sensing parameter type and combining the real-time sensing parameters and the historical sensing parameters corresponding to the sensing parameter type, and judging whether the fluctuation amplitude of each sensing parameter exceeds a preset fluctuation amplitude threshold value;
the screening unit is used for screening at least one first real-time sensing parameter from the real-time sensing parameter set, and the fluctuation amplitude of the sensing parameter corresponding to the first real-time sensing parameter does not exceed the fluctuation amplitude threshold; screening at least one second real-time sensing parameter from the real-time sensing parameter set, wherein the fluctuation amplitude of the sensing parameter corresponding to the second real-time sensing parameter exceeds a fluctuation amplitude threshold;
A rendering unit for updating a historical sensing parameter set of a corresponding sensing parameter type based on each first real-time sensing parameter and each second real-time sensing parameter; a digital twin model is rendered based on each of the second real-time sensing parameters.
In a third aspect, an embodiment of the present invention provides an electronic device, including: the system comprises at least one processor and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method described above.
In a fourth aspect, embodiments of the present invention provide a storage medium having stored therein one or more programs including execution instructions that are readable and executable by an electronic device (including, but not limited to, a computer, a server, or a network device, etc.) for performing the steps of the above-described methods of the present invention.
In a fifth aspect, embodiments of the present invention also provide a computer program product comprising a computer program stored on a storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the steps of the above-described method.
Compared with the prior art, the technical scheme has at least the following beneficial effects:
when the electronic equipment receives various real-time sensing parameters of the physical product, the fluctuation amplitude of the real-time sensing parameters relative to the historical sensing parameters is identified aiming at various sensing parameter types, and the digital twin model is rendered only by using the parameters with larger fluctuation amplitude, so that the number of parameters to be rendered is reduced, and the digital twin model can realize rendering response more quickly. In addition, the sensing parameters with smaller fluctuation range are not added into the rendering process, and the synchronization of the digital twin model is not influenced due to the small fluctuation range, so that the system resource consumption can be saved to a large extent especially when a large number of slightly-fluctuating sensing parameters exist. Optionally, various sensing parameters are stored in a historical sensing parameter set no matter whether the fluctuation amplitude is large or not, so that large fluctuation accumulated in the continuous micro-variation process of some sensing parameters can be identified and rendered when the large fluctuation is compared with the subsequent real-time sensing parameters, and the performance of the digital twin model is guaranteed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 illustrates a flow chart of an example of a digital twin model response optimization method according to an embodiment of the present invention;
FIG. 2 illustrates an example operational flow diagram for rendering a digital twin model based on a second real-time sensing parameter in accordance with an embodiment of the present invention;
FIG. 3 illustrates a flowchart of an example of rendering a target model module with respective second real-time sensing parameters that correspond to product failure display dimensions, according to an embodiment of the invention;
FIG. 4 illustrates a block diagram of an example of a digital twin model response optimization system in accordance with an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an embodiment of an electronic device of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without creative efforts, based on the described embodiments of the present invention fall within the protection scope of the present invention.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. Likewise, the terms "a," "an," or "the" and similar terms do not denote a limitation of quantity, but rather denote the presence of at least one. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.
It should be noted that "upper", "lower", "left", "right", "front", "rear", and the like are used in the present invention only to indicate a relative positional relationship, and when the absolute position of the object to be described is changed, the relative positional relationship may be changed accordingly.
FIG. 1 illustrates a flow chart of an example of a digital twin model response optimization method according to an embodiment of the present invention.
The execution subject of the method of the embodiment of the invention can be any controller or processor with computing or processing capability to achieve the goal of providing digital twin model simulation services to client users. In some examples, it may be configured integrally in a client or a server by means of software, hardware, or a combination of software and hardware, which should not be limited herein.
The details of the technical scheme related to the invention will be described below by taking a digital twin system as an exemplary implementation main body. It should be understood that one or more of the steps involved in the flow described below may be implemented by one or more controllers or software installed and deployed in a client or server.
As shown in fig. 1, in step S110, a real-time sensing parameter set for a physical product is acquired.
Here, the digital twin system is configured with a corresponding digital twin model for the physical product, and uses sensor data, the physical model and an algorithm to simulate the behavior and performance of the physical product, so as to monitor the state, the running condition, the fault risk and the like of the physical product. Furthermore, the real-time sensing parameter set contains a plurality of real-time sensing parameters for updating the digital twin model, and each real-time sensing parameter has a unique sensing parameter type, respectively.
It should be noted that the types of the physical products may be varied, such as subways, automobiles, batteries, or home appliances, etc., and should not be limited herein. Accordingly, the type of the sensing parameters can also be adjusted according to the applied physical products, for example, the sensing parameters of the automobile comprise accelerator depth information and brake information, and the sensing parameters of the battery comprise battery voltage and battery electric quantity.
In step S120, for each sensing parameter type, it is detected whether the sensing parameter fluctuation amplitude for the sensing parameter type exceeds a preset fluctuation amplitude threshold based on the real-time sensing parameter and the historical sensing parameter set corresponding to the sensing parameter type.
In some embodiments, the fluctuation range threshold corresponding to each sensing parameter type may be set or adjusted according to the service requirement. For example, a smaller fluctuation amplitude threshold may be set for more interesting sensing parameters. In addition, a larger fluctuation amplitude threshold may be set for a sensing parameter of lower attention.
In step S130, at least one first real-time sensing parameter whose corresponding sensing parameter fluctuation amplitude does not exceed the fluctuation amplitude threshold is screened from the real-time sensing parameter set, and at least one second real-time sensing parameter whose corresponding sensing parameter fluctuation amplitude exceeds the fluctuation amplitude threshold is screened.
In some implementations, the historical set of sensing parameters may be a set of sensing parameters corresponding to a preset fixed length of time (e.g., 5 minutes). Specifically, the average value of each historical sensing parameter in the historical sensing parameter set is subjected to difference with the real-time sensing parameter to obtain the fluctuation amplitude of the sensing parameter, and the fluctuation amplitude is compared with a corresponding fluctuation amplitude threshold value, so that classification between the first real-time sensing parameter and the second real-time sensing parameter is realized.
In step S140, a set of historical sensing parameters for the respective sensing parameter types is updated based on the respective first and second real-time sensing parameters, and a digital twin model is rendered based on the respective second real-time sensing parameters.
Specifically, only the second real-time sensing parameters with larger fluctuation range are used for rendering the digital twin model, and the first real-time sensing parameters with smaller fluctuation range are not used as rendering parameters. Furthermore, each real-time sensing parameter update is recorded to a set of historical sensing parameters, for example, a set of corresponding (5 minutes) historical sensing parameters is updated. That is, although the first real-time sensing parameter is not used as a rendering parameter, the first real-time sensing parameter is stored in the historical sensing parameter set, so that large fluctuation accumulated in the continuous micro-transformation process of some sensing parameters can be identified and rendered when the large fluctuation is compared with the subsequent real-time sensing parameter, and the performance of the digital twin model is guaranteed.
FIG. 2 illustrates an example operational flow diagram for rendering a digital twin model based on a second real-time sensing parameter in accordance with an embodiment of the present invention.
As shown in fig. 2, in step S210, a target model module matched with the sensing parameter category corresponding to each second real-time sensing parameter is determined according to a preset parameter rendering module table.
Here, the parameter rendering module table contains a plurality of mappings defining associations between model modules of the digital twin model and sensing parameter categories. In some embodiments, the digital twin model is divided into a plurality of model modules a, b, c, d, and the sensing parameter types are { U1, U2, U3, U4, U5, U6}, with a mapping relationship between model modules and sensing parameter types, such as { U1, U2} -a, { U3} -b.
In step S220, each target model module in the digital twin model is rendered based on each second real-time sensing parameter.
According to the embodiment of the invention, the digital twin model is divided into a plurality of model modules, and corresponding sensing parameter types are respectively associated, so that only the model modules corresponding to the sensing parameters with larger fluctuation range are rendered, other model modules are kept continuously, and the response performance of the digital twin model can be further optimized by using a model block rendering mode.
Regarding step S220 described above, in some embodiments, for each target model module, a rendering operation is performed that includes: and determining the target display level dimension of each second real-time sensing parameter corresponding to the target model module. Here, the display hierarchy dimension includes at least one of: a product failure display dimension, a product appearance display dimension, and a product interior component display dimension. Optionally, the rendering priorities of the second real-time sensing parameters are ordered according to the target display level dimension of the second real-time sensing parameters, and then the second real-time sensing parameters are called according to the rendering priority order to render the target model module.
According to the embodiment of the invention, when the model module is rendered, if a plurality of real-time sensing parameters to be rendered are simultaneously involved, the priority ranking is performed by using the display hierarchy dimension of each real-time sensing parameter to be rendered, and the sequential calling is performed on each real-time sensing parameter according to the ranking, so that the aim of performing layer-by-layer rendering according to the hierarchy importance is fulfilled, and the important hierarchy information is preferentially displayed.
In some examples of embodiments of the present invention, the rendering priority corresponding to the product failure display dimension is p Failure of Rendering priority corresponding to display dimension of product internal part is P Inside part The rendering priority corresponding to the product appearance display dimension is P Appearance of Wherein p is Failure of ＞P Appearance of ＞P Inside part . Therefore, the highest priority is given to the product fault dimension, when the digital twin system receives or detects the fault, the digital twin system preferentially renders each sensing parameter under the product fault display dimension, and the digital twin model can preferentially synchronize the fault information of the physical product in real time.
In some examples of embodiments of the invention, the physical product is a new energy automobile and the target model module comprises a battery model module for a battery pack of the new energy automobile.
FIG. 3 illustrates a flowchart of an example of rendering a target model module with respective second real-time sensing parameters that correspond to a product failure display dimension, according to an embodiment of the invention.
As shown in fig. 3, in step S310, a gradient model set corresponding to the battery model module is constructed.
The gradient model set comprises a type gradient model, a test gradient model and a state gradient model, wherein the type gradient model is used for simulating the fault type of the battery pack, the test gradient model is used for simulating damage test results of various points in the battery pack, and the state gradient model is used for simulating the real-time running state of the battery pack. This allows the battery model module to be simulated from multiple orientations.
In step S320, for each second real-time sensing parameter of the corresponding product failure display dimension, at least one target gradient model associated with the second real-time sensing parameter is determined in the gradient model set.
In step S330, for each target gradient model, the rendering for the target gradient model is updated based on each second real-time fault sensing parameter of the corresponding product fault display dimension.
According to the embodiment of the invention, when the rendering operation of the battery model module with the highest priority and the product fault display dimension is performed, a plurality of empty gradient models related to the battery model module and the fault display dimension are firstly constructed, then the gradient models are matched by utilizing the real-time sensing parameter pair with larger fluctuation amplitude, only the related gradient models are updated and rendered, and other gradient models can keep original appearance, so that the response efficiency of the digital twin model is improved.
In one example of an embodiment of the present invention, for each gradient model described above, it may be directly rendered with sensing parameters, for example, the sensing parameters include fault information, damage test result information, and operation state information, and so on. In another example of the embodiment of the present invention, the gradient model may further analyze the sensing parameters, and further render the sensing parameters by using the processing results, for example, analyze the fault level according to the sensing parameters, and further render the sensing parameters by using the fault level.
In some implementations, updating the rendering process for the type gradient model includes: and acquiring the real-time running state of the battery pack based on the state gradient model, determining a fault simulation result according to each second real-time fault sensing parameter and the corresponding historical sensing parameter set, and updating a preset fault simulation function according to the fault simulation result and the real-time running state so as to update the rendering of the type gradient model.
In some embodiments, the fault simulation function may employ a linear fitting function. It should be understood that the number of the devices,the fitting function is a mathematical function used for fitting the input data sequence with the observation data set or multiple groups of sample data corresponding to the fault development trend so as to realize the development trend of predicting the matching of the input data sequence. Specifically, for each sensing parameter type, the second real-time fault sensing parameter and the historical sensing parameter set corresponding to the sensing parameter type are formed into an input data sequence, and then a corresponding fault simulation result is obtained by utilizing a linear fitting function, for example, the fault development trend of a physical product in a future period of time is predicted, so that operation and maintenance personnel are reminded to conduct advanced operation and prevention and control.
More specifically, the fault simulation function is:
wherein,representing a fault fitting function of the battery pack after the battery pack is currently operated for k weeks in a real-time operation state m; v t Representing the fault type; ρ represents a fault v t The proportionality coefficient of failure time and failure time of the corresponding core component, for example, the core component corresponding to insulation failure is an insulating material, the core component corresponding to abnormal connection of the single battery is a connecting component, and the like; />Representing a fault v t The corresponding fault simulation result; />Representing a fault v t In some examples, by querying a fault level table recorded with a mapping relationship of the two; m= (1, 2, 3), 1 indicates that the operation state is good, 2 indicates that the operation state is general, and 3 indicates that the operation state is bad; μ represents a pre-calibrated weighting factor.
Therefore, the fault type, the fault development trend and the fault influence level of the battery pack are simulated through the fault simulation function, so that more comprehensive fault display and early warning are realized. In addition, the digital twin model rendering is also more beneficial to realizing personalized display effects, such as respectively adopting personalized rendering configuration for different fault types or fault influence grades.
It should be noted that, regarding the above-mentioned fault simulation resultsOn the one hand, it may be defined directly by the sensor parameters, e.g. the sensor parameter type contains fault information, and on the other hand, the sensor parameters do not contain fault information but are determined by means of prediction.
In some embodiments, the fault simulation result is calculated based on a preset fault probability prediction function and each of the second real-time fault sensing parameters. Here, the fault probability prediction function adopts a fault detection probability density function to determine, for each preset fault type, a fault probability density corresponding to the preset fault type, respectively. The fault detection probability density function adopts a mixed distribution model, the mixed distribution model fuses a plurality of probability distribution functions, and the probability distribution functions comprise a Weibull probability distribution model and a modified Gamma probability distribution model.
Specifically, the function formula of the hybrid distribution model is:
；
wherein,is a fault density function at time t; />Is the weight of each distribution function, representing the contribution of the distribution in the overall model; />Is the probability density function of the ith distribution function.
Through the bookIn the embodiment of the invention, different distribution functions are fused by adopting a mixed distribution model, so as to describe the fault behaviors more accurately. In the fault prediction of the battery pack, a Weibull probability distribution model and a modified Gamma probability distribution model are fused to capture the coexistence situation of a plurality of fault modes. Thus, different fault sources can be identified, and occurrence probabilities of different fault modes can be predicted. It should be noted that the number of the components, The mixed distribution model can be more close to the fault condition of an actual battery pack through reasonable arrangement or adjustment.
Optionally, the functional formula of the Weibull probability distribution model is:
；
wherein W (t) is a Weibull fault density function at time t, beta describes a first variation trend parameter of the fault rate, eta describes a first occurrence speed of the fault rate, and beta and eta are determined by fitting and analyzing a second real-time fault sensing parameter and a preset fault observation sample set.
According to the embodiment of the invention, the reliability theory-based Weibull distribution is utilized, and the life cycle and the fault characteristics of each component in the battery pack are learned to describe the fault detection probability density function of the battery pack more accurately.
Optionally, the function formula of the modified Gamma probability distribution model is:
；
wherein G (t) is a Gamma fault density function at time t, alpha describes a first trend parameter of the fault rate, and sigma describes a second occurrence rate of the fault rate; Γ () represents a Gamma function; and alpha and sigma are determined by fitting and analyzing the second real-time fault sensing parameter and a preset fault observation sample set.
In the embodiment of the invention, the modified Gamma distribution is used for describing the fault behavior of the battery, and the fault rate is reduced when alpha is larger than 1, so that the method is suitable for describing the modes of high fault rate and gradual decline in the later period of initial use of the battery pack. Furthermore, the average time interval for the occurrence of a fault event is described by σ. Thus, the failure detection probability density function of the battery pack is defined in conjunction with the use period of the battery pack.
According to the embodiment of the invention, the mixed distribution model is used, the probability distribution functions are fused to predict the fault detection probability density functions of the battery pack, the prediction capability of the battery pack fault is explored, the fault prediction of the probability distribution of each fault type is realized, and then the corresponding preset detection threshold is combined, so that the digital twin model can accurately and objectively reflect the operation fault condition of a real product.
The digital twin model response optimization system provided by the invention is described below, and the digital twin model response optimization system described below and the digital twin model response optimization method described above can be correspondingly referred to each other.
FIG. 4 illustrates a block diagram of an example of a digital twin model response optimization system in accordance with an embodiment of the present invention.
As shown in fig. 4, the digital twin model response optimizing system 400 includes an acquisition unit 410, a detection unit 420, a screening unit 430, and a rendering unit 440.
The acquiring unit 410 is configured to acquire a real-time sensing parameter set and a historical sensing parameter set for a physical product;
wherein the physical product is configured with a corresponding digital twin model; the real-time sensing parameter set comprises a plurality of real-time sensing parameters, and the real-time sensing parameters are used for updating the digital twin model; each real-time sensing parameter has a unique sensing parameter type.
The detecting unit 420 is configured to detect a sensing parameter fluctuation range of each sensing parameter type based on each sensing parameter type, and combine a real-time sensing parameter and a historical sensing parameter corresponding to the sensing parameter type, and determine whether the fluctuation range of each sensing parameter exceeds a preset fluctuation range threshold.
The screening unit 430 is configured to screen at least one first real-time sensing parameter from the real-time sensing parameter set, where a fluctuation amplitude of the sensing parameter corresponding to the first real-time sensing parameter does not exceed a fluctuation amplitude threshold; and screening at least one second real-time sensing parameter from the real-time sensing parameter set, wherein the fluctuation amplitude of the sensing parameter corresponding to the second real-time sensing parameter exceeds a fluctuation amplitude threshold.
The rendering unit 440 is configured to update the historical sensing parameter set of the corresponding sensing parameter type based on each first real-time sensing parameter and each second real-time sensing parameter; a digital twin model is rendered based on each of the second real-time sensing parameters.
It should be noted that, for simplicity of description, the foregoing method embodiments are all illustrated as a series of acts combined, but it should be understood and appreciated by those skilled in the art that the present invention is not limited by the order of acts, as some steps may be performed in other orders or concurrently in accordance with the present invention. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present invention. In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In some embodiments, embodiments of the present invention provide a non-transitory computer readable storage medium having stored therein one or more programs including execution instructions that are readable and executable by an electronic device (including, but not limited to, a computer, a server, or a network device, etc.) for performing the digital twin model response optimization method of the present invention described above.
In some embodiments, embodiments of the present invention also provide a computer program product comprising a computer program stored on a non-volatile computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the digital twin model response optimization method described above.
In some embodiments, the present invention further provides an electronic device, including: the system comprises at least one processor and a memory communicatively coupled to the at least one processor, wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a digital twin model response optimization method.
Fig. 5 is a schematic hardware structure of an electronic device for performing a response optimization method of a digital twin model according to another embodiment of the present invention, as shown in fig. 5, where the device includes:
one or more processors 510 and a memory 520, one processor 510 being illustrated in fig. 5.
The apparatus for performing the digital twin model response optimization method may further include: an input device 530 and an output device 540.
The processor 510, memory 520, input device 530, and output device 540 may be connected by a bus or other means, for example in fig. 5.
The memory 520 is used as a non-volatile computer readable storage medium for storing non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions/modules corresponding to the digital twin model response optimization method in the embodiment of the present invention. The processor 510 executes various functional applications of the server and data processing, i.e., implements the digital twin model response optimization method of the above-described method embodiments, by running non-volatile software programs, instructions, and modules stored in the memory 520.
Memory 520 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of the electronic device, etc. In addition, memory 520 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, memory 520 may optionally include memory located remotely from processor 510, which may be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input means 530 may receive input digital or character information and generate signals related to user settings and function control of the electronic device. The output 540 may include a display device such as a display screen.
The one or more modules are stored in the memory 520 that, when executed by the one or more processors 510, perform the digital twin model response optimization method of any of the method embodiments described above.
The product can execute the method provided by the embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method. Technical details not described in detail in this embodiment may be found in the methods provided in the embodiments of the present invention.
The electronic device of the embodiments of the present invention exists in a variety of forms including, but not limited to:
(1) Mobile communication devices, which are characterized by mobile communication functionality and are aimed at providing voice, data communication. Such terminals include smart phones, multimedia phones, functional phones, low-end phones, and the like.
(2) Ultra mobile personal computer equipment, which belongs to the category of personal computers, has the functions of calculation and processing and generally has the characteristic of mobile internet surfing. Such terminals include PDA, MID, and UMPC devices, etc.
(3) Portable entertainment devices such devices can display and play multimedia content. The device comprises an audio player, a video player, a palm game machine, an electronic book, an intelligent toy and a portable vehicle navigation device.
(4) Other on-board electronic devices with data interaction functions, such as on-board devices mounted on vehicles.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
From the above description of embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus a general purpose hardware platform, or may be implemented by hardware. Based on such understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the related art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. A method for optimizing digital twin model response, the method comprising:
acquiring a real-time sensing parameter set and a historical sensing parameter set aiming at a physical product;
wherein the physical product is configured with a corresponding digital twin model; the real-time sensing parameter set comprises a plurality of real-time sensing parameters, and the real-time sensing parameters are used for updating the digital twin model; each real-time sensing parameter is provided with a unique sensing parameter type;
based on each sensing parameter type, detecting sensing parameter fluctuation amplitude of each sensing parameter type by combining the real-time sensing parameter and the historical sensing parameter corresponding to the sensing parameter type, and judging whether the sensing parameter fluctuation amplitude exceeds a preset fluctuation amplitude threshold;
Screening at least one first real-time sensing parameter from the real-time sensing parameter set, wherein the fluctuation amplitude of the sensing parameter corresponding to the first real-time sensing parameter does not exceed the fluctuation amplitude threshold; screening at least one second real-time sensing parameter from the real-time sensing parameter set, wherein the fluctuation amplitude of the sensing parameter corresponding to the second real-time sensing parameter exceeds the fluctuation amplitude threshold;
updating a historical sensing parameter set of a corresponding sensing parameter type based on each of the first real-time sensing parameters and each of the second real-time sensing parameters; rendering the digital twin model based on each of the second real-time sensing parameters;
the rendering the digital twin model based on each of the second real-time sensing parameters includes:
determining a target model module matched with the sensing parameter type corresponding to each second real-time sensing parameter according to a preset parameter rendering module table; the parameter rendering module table comprises a plurality of mapping relations, wherein the mapping relations comprise: the association relation between the target model module of the digital twin model and the sensing parameter type;
rendering each target model module in the digital twin model based on each of the second real-time sensing parameters;
The physical product is a new energy automobile, and the target model module is a battery model module of a battery pack of the new energy automobile;
rendering each target model module in the digital twin model based on each of the second real-time sensing parameters, including:
determining a target display level dimension of each second real-time sensing parameter corresponding to the target model module; wherein the display hierarchy dimension includes at least one of a product failure display dimension, a product appearance display dimension, and a product interior component display dimension;
sequencing the rendering priority of each second real-time sensing parameter according to the target display level dimension of each second real-time sensing parameter to obtain a rendering priority sequence;
invoking each second real-time sensing parameter according to the rendering priority order, and rendering the target model module;
the rendering priority corresponding to the product fault display dimension is thatp Failure of The rendering priority corresponding to the display dimension of the product internal part isP Inside part The rendering priority corresponding to the product appearance display dimension is thatP Appearance of Whereinp Failure of ＞P Appearance of ＞P Inside part The method comprises the steps of carrying out a first treatment on the surface of the Preferentially calling each second real-time sensing parameter corresponding to the product fault display dimension to render the target model module;
invoking each second real-time sensing parameter corresponding to the product fault display dimension to render the target model module, including:
constructing a target gradient model set corresponding to the battery model module; the target gradient model set comprises a type gradient model, a test gradient model and a state gradient model; the type gradient model is used for simulating the fault type of the battery pack; the test gradient model is used for simulating damage test results of each point in the battery pack; the state gradient model is used for simulating the real-time running state of the battery pack;
invoking each second real-time sensing parameter corresponding to the product fault display dimension, determining at least one target gradient model associated with the second real-time sensing parameter in the gradient model set;
updating a rendering process of the target gradient model based on each second real-time sensing parameter corresponding to the product failure display dimension for each of the target gradient models.
2. The method of claim 1, wherein updating the rendering process of the target gradient model comprises:
acquiring a real-time running state of the battery pack based on the state gradient model;
determining a fault simulation result according to each second real-time sensing parameter and each historical sensing parameter set;
updating a preset fault simulation function according to the fault simulation result and the real-time running state, and updating the rendering process of the type gradient model;
wherein, the fault simulation function is:
；
wherein,ϑ m （T k ) Indicating that the battery pack is currently in real-time operationmRun underT k Fitting a function of faults after the week, wherein k is a positive integer;v t indicating the type of fault at time t,ρrepresenting faultsv t The corresponding core component failure time to failure time scaling factor,representing faultsv t A corresponding fault simulation result; />Representing faultsv t Is a level of influence of (2);m= (1, 2, 3), 1 indicates that the operation state is good, 2 indicates that the operation state is general, and 3 indicates that the operation state is bad; μ represents a pre-calibrated weighting factor.
3. The method of claim 2, wherein said determining a fault simulation result from each of said second real-time sensing parameters and said set of historical sensing parameters comprises:
Calculating a fault simulation result based on a preset fault probability prediction function and each of the second real-time fault sensing parameters and the historical sensing parameter set;
the fault probability prediction function adopts a fault detection probability density function, and the fault probability density corresponding to a preset fault type is determined according to the fault detection probability density function;
the fault detection probability density function adopts a mixed distribution model, and the mixed distribution model comprises a plurality of probability distribution functions; the probability distribution function includesWeibullProbability distribution model and modifiedGammaA probability distribution model;
the function formula of the mixed distribution model is as follows:
；
wherein,representation oftA fault density function of time; />A weight representing each probability distribution function; />Represent the firstiProbability density functions of the individual distribution functions.
4. A method according to claim 3, wherein theWeibullThe functional formula of the probability distribution model is:
；
wherein,W(t) Time of presentationtTime of dayWeibullA fault density function is provided that,βa first trend parameter representing the failure rate,ηa first occurrence rate indicative of a failure rate; wherein,βandηthe second real-time fault sensing parameters and a preset fault observation sample set are subjected to fitting analysis to determine.
5. The method of claim 3 or 4, wherein the correctionGammaThe functional formula of the probability distribution model is:
；
wherein,G(t) Time of presentationtA Gamma failure density function of time of day,αa first trend parameter representing the failure rate,a second occurrence rate indicative of a failure rate; />Representation ofGammaA function;αand->The second real-time fault sensing parameters and a preset fault observation sample set are subjected to fitting analysis to determine.
6. A digital twin model response optimization system, the system comprising:
the acquisition unit is used for acquiring a real-time sensing parameter set and a historical sensing parameter set aiming at a physical product;
wherein the physical product is configured with a corresponding digital twin model; the real-time sensing parameter set comprises a plurality of real-time sensing parameters, and the real-time sensing parameters are used for updating the digital twin model; each real-time sensing parameter is provided with a unique sensing parameter type;
the detection unit is used for detecting the fluctuation amplitude of the sensing parameters of each sensing parameter type based on each sensing parameter type and combining the real-time sensing parameters and the historical sensing parameters corresponding to the sensing parameter type, and judging whether the fluctuation amplitude of each sensing parameter exceeds a preset fluctuation amplitude threshold;
The screening unit is used for screening at least one first real-time sensing parameter from the real-time sensing parameter set, and the fluctuation amplitude of the sensing parameter corresponding to the first real-time sensing parameter does not exceed the fluctuation amplitude threshold; screening at least one second real-time sensing parameter from the real-time sensing parameter set, wherein the fluctuation amplitude of the sensing parameter corresponding to the second real-time sensing parameter exceeds the fluctuation amplitude threshold;
a rendering unit, configured to update a historical sensing parameter set of a corresponding sensing parameter type based on each of the first real-time sensing parameters and each of the second real-time sensing parameters; rendering the digital twin model based on each of the second real-time sensing parameters; the rendering the digital twin model based on each of the second real-time sensing parameters includes:
determining a target model module matched with the sensing parameter type corresponding to each second real-time sensing parameter according to a preset parameter rendering module table; the parameter rendering module table comprises a plurality of mapping relations, wherein the mapping relations comprise: the association relation between the target model module of the digital twin model and the sensing parameter type;
Rendering each target model module in the digital twin model based on each of the second real-time sensing parameters;
the physical product is a new energy automobile, and the target model module is a battery model module of a battery pack of the new energy automobile;
rendering each target model module in the digital twin model based on each of the second real-time sensing parameters, including:
determining a target display level dimension of each second real-time sensing parameter corresponding to the target model module; wherein the display hierarchy dimension includes at least one of a product failure display dimension, a product appearance display dimension, and a product interior component display dimension;
sequencing the rendering priority of each second real-time sensing parameter according to the target display level dimension of each second real-time sensing parameter to obtain a rendering priority sequence;
invoking each second real-time sensing parameter according to the rendering priority order, and rendering the target model module;
the rendering priority corresponding to the product fault display dimension is thatp Failure of The rendering priority corresponding to the display dimension of the product internal part is P Inside part The rendering priority corresponding to the product appearance display dimension is thatP Appearance of Whereinp Failure of ＞P Appearance of ＞P Inside part The method comprises the steps of carrying out a first treatment on the surface of the Preferentially calling each second real-time sensing parameter corresponding to the product fault display dimension to render the target model module;
invoking each second real-time sensing parameter corresponding to the product fault display dimension to render the target model module, including:
constructing a target gradient model set corresponding to the battery model module; the target gradient model set comprises a type gradient model, a test gradient model and a state gradient model; the type gradient model is used for simulating the fault type of the battery pack; the test gradient model is used for simulating damage test results of each point in the battery pack; the state gradient model is used for simulating the real-time running state of the battery pack;
invoking each second real-time sensing parameter corresponding to the product fault display dimension, determining at least one target gradient model associated with the second real-time sensing parameter in the gradient model set;
updating a rendering process of the target gradient model based on each second real-time sensing parameter corresponding to the product failure display dimension for each of the target gradient models.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311766564.1A CN117436290B (en) | 2023-12-21 | 2023-12-21 | Digital twin model response optimization method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311766564.1A CN117436290B (en) | 2023-12-21 | 2023-12-21 | Digital twin model response optimization method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117436290A CN117436290A (en) | 2024-01-23 |
| CN117436290B true CN117436290B (en) | 2024-03-08 |
Family
ID=89556927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311766564.1A Active CN117436290B (en) | 2023-12-21 | 2023-12-21 | Digital twin model response optimization method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117436290B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110442936A (en) * | 2019-07-24 | 2019-11-12 | 中国石油大学(北京) | Equipment fault diagnosis method, apparatus and system based on the twin model of number |
| CN114004168A (en) * | 2021-12-24 | 2022-02-01 | 武汉理工大学 | Fuel cell comprehensive management system and method based on digital twinning |
| CN114722625A (en) * | 2022-04-24 | 2022-07-08 | 上海玫克生储能科技有限公司 | Method, system, terminal and medium for establishing monomer digital twin model of lithium battery |
| CN114814691A (en) * | 2022-03-09 | 2022-07-29 | 中国科学技术大学 | Lithium battery system voltage sensor fault diagnosis method based on digital twinning |
| CN115422696A (en) * | 2022-04-24 | 2022-12-02 | 上海玫克生储能科技有限公司 | Module digital twin model establishing method, system, terminal and medium |
| CN115659160A (en) * | 2022-12-28 | 2023-01-31 | 北京中航路通科技有限公司 | Data quality measurement method for optimizing digital twin model |
| CN116380166A (en) * | 2023-04-04 | 2023-07-04 | 山推工程机械股份有限公司 | Equipment abnormality monitoring method, electronic equipment and storage medium |
| CN116842621A (en) * | 2023-07-27 | 2023-10-03 | 中国人民解放军陆军工程大学 | Evolution method of digital twin model of building physical mechanism |
| CN117090831A (en) * | 2023-07-27 | 2023-11-21 | 中国人民解放军海军潜艇学院 | Hydraulic system fault diagnosis framework with twinning application layer |
| CN117189713A (en) * | 2023-07-27 | 2023-12-08 | 中国人民解放军海军潜艇学院 | Hydraulic system fault diagnosis method based on digital twin driving |
-
2023
- 2023-12-21 CN CN202311766564.1A patent/CN117436290B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110442936A (en) * | 2019-07-24 | 2019-11-12 | 中国石油大学(北京) | Equipment fault diagnosis method, apparatus and system based on the twin model of number |
| CN114004168A (en) * | 2021-12-24 | 2022-02-01 | 武汉理工大学 | Fuel cell comprehensive management system and method based on digital twinning |
| CN114814691A (en) * | 2022-03-09 | 2022-07-29 | 中国科学技术大学 | Lithium battery system voltage sensor fault diagnosis method based on digital twinning |
| CN114722625A (en) * | 2022-04-24 | 2022-07-08 | 上海玫克生储能科技有限公司 | Method, system, terminal and medium for establishing monomer digital twin model of lithium battery |
| CN115422696A (en) * | 2022-04-24 | 2022-12-02 | 上海玫克生储能科技有限公司 | Module digital twin model establishing method, system, terminal and medium |
| CN115659160A (en) * | 2022-12-28 | 2023-01-31 | 北京中航路通科技有限公司 | Data quality measurement method for optimizing digital twin model |
| CN116380166A (en) * | 2023-04-04 | 2023-07-04 | 山推工程机械股份有限公司 | Equipment abnormality monitoring method, electronic equipment and storage medium |
| CN116842621A (en) * | 2023-07-27 | 2023-10-03 | 中国人民解放军陆军工程大学 | Evolution method of digital twin model of building physical mechanism |
| CN117090831A (en) * | 2023-07-27 | 2023-11-21 | 中国人民解放军海军潜艇学院 | Hydraulic system fault diagnosis framework with twinning application layer |
| CN117189713A (en) * | 2023-07-27 | 2023-12-08 | 中国人民解放军海军潜艇学院 | Hydraulic system fault diagnosis method based on digital twin driving |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117436290A (en) | 2024-01-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110009171B (en) | User behavior simulation method, device, equipment and computer readable storage medium | |
| CN105488539B (en) | The predictor method and device of the generation method and device of disaggregated model, power system capacity | |
| CN111046027A (en) | Missing value filling method and device for time series data | |
| CN115842347B (en) | Digital twinning-based micro-grid load dynamic balancing method, system and medium | |
| CN109886328B (en) | Electric vehicle charging facility fault prediction method and system | |
| CN109598052B (en) | Intelligent ammeter life cycle prediction method and device based on correlation coefficient analysis | |
| CN112037223B (en) | Image defect detection method and device and electronic equipment | |
| CN113286315A (en) | Load balance judging method, device, equipment and storage medium | |
| CN110069997B (en) | Scene classification method and device and electronic equipment | |
| CN117436290B (en) | Digital twin model response optimization method and system | |
| CN112595537B (en) | Equipment health state monitoring method and system based on signal analysis and storage medium | |
| CN110704614B (en) | Information processing method and device for predicting user group type in application | |
| CN111177564B (en) | Product recommendation method and device | |
| CN113296992A (en) | Method, device, equipment and storage medium for determining abnormal reason | |
| CN114153829B (en) | Cross-space-time bidirectional data missing value filling method and device for energy big data | |
| CN114267440B (en) | Medical order information processing method and device and computer readable storage medium | |
| CN115856641A (en) | Method and device for predicting remaining charging time of battery and electronic equipment | |
| CN115731420A (en) | Small sample target detection method based on twin network and related equipment | |
| CN113434690A (en) | Clustering algorithm-based electricity utilization prediction evaluation method, device, system and medium | |
| CN113673811A (en) | Session-based online learning performance evaluation method and device | |
| CN115080445B (en) | Game test management method and system | |
| CN113159773B (en) | Method and device for generating quantized transaction return data | |
| CN115561628A (en) | Breaker breaking capacity analysis method and device, computer equipment and medium | |
| CN116094148A (en) | Distribution substation room state display method and device and nonvolatile storage medium | |
| CN114647761A (en) | Image frame processing method and device, equipment and computer readable 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 |