Automobile part digitization system and method based on digital twinning
Through the real-time monitoring of the operating status of automotive spare parts based on digital twins, the problem that the existing technology cannot reflect the operating status in real time is solved, the simulation accuracy and safety are improved, and the stable operation of spare parts is ensured.
Patent Information
- Application Number
- CN202411081729.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-08
- Publication Date
- 2024-12-06
AI Technical Summary
The existing digital methods of automotive spare parts cannot reflect the operating status of spare parts in real time, resulting in the inability to detect potential risks in time, affecting the performance and safety of the automobile. The simulation process relies on inherent programs rather than real-time working conditions, reducing the simulation accuracy of the digital twin model. sex.
Through a digital twin method, we can obtain three-dimensional information and historical operation data of automotive spare parts, build a virtual model, collect and compare real operation data with simulation data in real time, determine the simulation status, output allowable deviation or abnormal deviation, and make predictions and Correction processing to ensure model accuracy.
Real-time monitoring of automotive spare parts and timely discovery of potential risks, improve simulation accuracy, and ensure the safety and performance stability of spare parts.
Smart Images

Figure CN119089573A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of digital simulation of automobile parts and components, and specifically relates to a digital system and method for automobile parts and components based on digital twins. Background Art
[0002] With the rapid development of the automobile industry, the digital management of auto parts has become increasingly important. As an emerging digital technology, digital twin technology can simulate physical objects in the real world by creating virtual models, thereby achieving real-time monitoring and optimal management of the operation of auto parts, thereby improving the performance and reliability of auto parts and providing strong support for the intelligent development of the automobile industry.
[0003] However, existing digital methods for auto parts still often rely on static data analysis and cannot reflect the operating status of auto parts in real time, resulting in the inability to timely discover potential risks of auto parts during operation, which in turn affects the overall performance and safety of the car. In addition, traditional digital methods often rely too much on inherent programs when simulating and predicting the operating status of auto parts, and do not simulate according to real-time working conditions. As a result, when deviations occur in the simulation process, the simulation parameters cannot be adjusted in a timely manner, which will obviously continue to reduce the simulation accuracy of the digital twin model. Based on this, this solution provides a digital twin-based auto parts digitization method to solve the above problems. Summary of the invention
[0004] The purpose of the present invention is to provide a digital twin-based automobile parts digitization system and method, which can monitor the simulated operating status of automobile parts in real time, improve simulation accuracy, and promptly discover potential risks, thereby ensuring the safety of the actual operation of automobile parts.
[0005] The technical solution adopted by the present invention is as follows:
[0006] Digital twin-based automotive parts digitization methods include:
[0007] Mapping the auto parts into a virtual digital twin model according to the acquired three-dimensional information of the auto parts;
[0008] Collecting historical operating data of the automobile parts and components, and dynamically simulating the automobile parts and components in the digital twin model based on the historical operating data;
[0009] According to the real operation data of the automotive parts, the simulated operation data of the digital twin model are compared to determine the simulated state of the digital twin model, wherein the simulated state includes a normal simulated state and an abnormal simulated state;
[0010] In the normal simulation state, the allowable deviation between the simulated operation data and the real operation data is output, and the operation state of the automobile parts is simulated and predicted based on the allowable deviation, and the stable operation time period of the automobile parts is output according to the simulation prediction result;
[0011] In the abnormal simulation state, the abnormal deviation between the simulated operation data and the actual operation data is output, and an alarm signal is immediately issued, and the digital twin model is corrected according to the abnormal deviation.
[0012] In a preferred embodiment, the step of mapping the auto parts into a virtual digital twin model based on the acquired three-dimensional information of the auto parts comprises:
[0013] Scanning the automobile parts and outputting three-dimensional information of the automobile parts and outputting the ...
[0014] Constructing a three-dimensional model of the automobile parts according to the three-dimensional information of the automobile parts;
[0015] The three-dimensional model of the automobile parts is imported into the digital twin platform, and the digital twin model of the automobile parts is output.
[0016] In a preferred embodiment, the step of collecting the historical operation data of the automobile parts and dynamically simulating the automobile parts in the digital twin model according to the historical operation data includes:
[0017] Acquire the historical working conditions of the automobile parts and the historical operation data of the automobile parts under each of the historical working conditions, wherein the historical working conditions include temperature, humidity, load, speed and pressure;
[0018] Acquire the real-time working condition of the automobile parts at the current moment, and the real-time operation data of the automobile parts under the real-time working condition;
[0019] Compare the real-time operating condition with the historical operating condition, output a degree of fit between the real-time operating condition and the historical operating condition, and determine a benchmark simulation operating condition based on the degree of fit;
[0020] Performing predictive analysis on historical operating data of automobile parts under the benchmark simulation conditions, and outputting the data as simulated operating data of the digital twin model;
[0021] The automotive parts in the digital twin model are dynamically simulated based on the simulation operation data.
[0022] In a preferred embodiment, the step of determining the reference simulation working condition according to the degree of adaptation comprises:
[0023] Obtaining historical operating conditions and real-time operating conditions of the automotive parts;
[0024] Performing vector processing on the historical working conditions and the real-time working conditions, and converting the historical working conditions and the real-time working conditions into numerical vectors of the same dimension;
[0025] Calibrate the digitized vector corresponding to the historical operating condition as the historical operating condition vector, and calibrate the digitized vector corresponding to the real-time operating condition as the real-time operating condition vector;
[0026] Obtain a fitness calculation function, and input the historical operating condition vector and the real-time operating condition vector into the fitness calculation function together, and calibrate the output result of the fitness calculation function as the fitness of the historical operating condition and the real-time operating condition;
[0027] The fitness degrees are arranged in descending order, and the historical operating condition corresponding to the fitness degree with the highest ranking is output as the benchmark simulation operating condition.
[0028] In a preferred embodiment, the step of predicting and analyzing the historical operating data of the automobile parts under the reference simulation conditions and outputting the data as simulated operating data of the digital twin model comprises:
[0029] Acquire all similar historical operating conditions under the benchmark simulation operating condition, as well as historical operating data of automobile parts under similar historical operating conditions, and record the historical operating data of automobile parts under similar historical operating conditions as benchmark operating parameters;
[0030] Arrange all the reference operating parameters according to the time sequence of occurrence, perform difference processing on adjacent reference operating parameters according to the arrangement order of the reference operating parameters, and record the difference results of adjacent reference operating parameters as operating fluctuation parameters;
[0031] A first prediction function is obtained, and the operation fluctuation parameter is input into the first prediction function, and an output result of the first prediction function is calibrated as simulation operation data of the digital twin model.
[0032] In a preferred embodiment, the step of comparing the real operation data of the automotive parts with the simulated operation data of the digital twin model to determine the simulated state of the digital twin model comprises:
[0033] Acquire the real operation data of the automotive parts and components and the simulated operation data of the digital twin model at the same time;
[0034] Performing a difference processing on the real operation data and the simulated operation data, and calibrating the difference result between the real operation data and the simulated operation data as the simulated operation deviation;
[0035] Obtaining an evaluation threshold, and comparing the evaluation threshold with a simulation operation bias;
[0036] If the simulation operation deviation is less than the evaluation threshold, it indicates that the simulation process of the digital twin model fits the actual execution process of the automotive parts, and the simulation state of the digital twin model is recorded as a normal simulation state;
[0037] If the simulation operation deviation is greater than or equal to the evaluation threshold, it indicates that the simulation execution process of the digital twin model deviates from the actual execution process of the automotive parts, and the simulation state of the digital twin model is recorded as an abnormal simulation state.
[0038] In a preferred embodiment, the step of simulating and predicting the operating state of the automobile parts based on the allowable deviation and outputting the stable operating time period of the automobile parts according to the simulation prediction result includes:
[0039] Acquire the simulated operation deviation under the normal simulation state, and record the simulated operation deviation as the allowable deviation;
[0040] Obtaining the allowable deviation threshold of the automotive parts;
[0041] Obtaining a second prediction function, and inputting the allowable deviation threshold and the allowable deviation amount into the second prediction function, and marking the output result of the second prediction function as a stable operation period;
[0042] After the stable operation period is output, the length of the stable operation period is counted and recorded as a control condition parameter;
[0043] A control threshold is obtained, and the control threshold is compared with a control condition parameter. When the control condition parameter is less than or equal to the control threshold, the operating state of the automobile component is output as a risk state, and the operation of the automobile component is stopped. Otherwise, the normal operation of the automobile component is maintained.
[0044] In a preferred embodiment, the step of correcting the digital twin model according to the abnormal deviation comprises:
[0045] Acquire a simulated operation deviation under the abnormal simulation state, and record the simulated operation deviation as an abnormal deviation;
[0046] Correcting the simulation operation parameters under the digital twin model according to the abnormal deviation to obtain corrected parameters;
[0047] A trend evaluation function is obtained, and the actual operating parameters of the automotive parts are input into the trend evaluation function, and the output result of the trend evaluation function is calibrated as a trend evaluation value, and the digital twin model is dynamically simulated based on the trend evaluation value and the corrected parameters.
[0048] The present invention also provides a digital twin-based automobile parts digitization system, using the above-mentioned digital twin-based automobile parts digitization method, including:
[0049] A model building module, wherein the model building module is used to map the automobile parts into a virtual digital twin model according to the acquired three-dimensional information of the automobile parts;
[0050] A simulation module, the simulation module is used to collect historical operation data of the automobile parts and components, and dynamically simulate the automobile parts and components in the digital twin model according to the historical operation data;
[0051] A state evaluation module, wherein the state evaluation module is used to compare the real operation data of the automotive parts with the simulated operation data of the digital twin model to determine the simulated state of the digital twin model, wherein the simulated state includes a normal simulated state and an abnormal simulated state;
[0052] A first intervention module, the first intervention module is used to output the allowable deviation between the simulated operation data and the real operation data in the normal simulation state, simulate and predict the operation state of the automobile parts based on the allowable deviation, and output the stable operation time period of the automobile parts according to the simulation prediction result;
[0053] The first intervention module is used to output the abnormal deviation between the simulated operation data and the real operation data under the abnormal simulation state, immediately issue an alarm signal, and perform correction processing on the digital twin model according to the abnormal deviation.
[0054] And, an electronic device, the electronic device comprising:
[0055] at least one processor;
[0056] and a memory communicatively coupled to the at least one processor;
[0057] Among them, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the above-mentioned digital twin-based automotive parts digitization method.
[0058] The technical effects achieved by the present invention are:
[0059] The present invention can locate the benchmark simulation working condition by comparing the real-time working condition with the historical working condition, and then dynamically simulate the operation of the automobile parts by analyzing the historical operation data in the same type of historical working condition under the benchmark working condition, and determine the accuracy of the digital twin model based on the simulated operation data and the real operation data of the actual operation. When the digital twin model is accurate, it will output the stable operation time period to evaluate the stable operation time of the automobile parts, so as to avoid potential failures. When the digital twin model simulates an abnormality, it will perform corresponding correction processing, so as to timely discover and solve potential problems and ensure the execution accuracy of the digital twin model. BRIEF DESCRIPTION OF THE DRAWINGS
[0060] Figure 1 It is a schematic flow chart of the method of the present invention;
[0061] Figure 2 It is a schematic diagram of the system module of the present invention;
[0062] Figure 3 It is a schematic diagram of the structure of an electronic device of the present invention. DETAILED DESCRIPTION
[0063] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.
[0064] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.
[0065] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present invention. The phrase "in a preferred embodiment" that appears in different places in this specification does not refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.
[0066] See also Figure 1 As shown, the present invention provides a digital twin-based automotive parts digitization method, including:
[0067] S1. Mapping the auto parts into virtual digital twin models based on the acquired three-dimensional information of the auto parts;
[0068] S2. Collect historical operation data of auto parts and dynamically simulate the auto parts in the digital twin model based on the historical operation data;
[0069] S3. Determine the simulation state of the digital twin model by comparing the real operation data of the auto parts with the simulation operation data of the digital twin model, wherein the simulation state includes a normal simulation state and an abnormal simulation state;
[0070] S4. Under normal simulation conditions, output the allowable deviation between the simulated operation data and the actual operation data, simulate and predict the operation state of the auto parts based on the allowable deviation, and output the stable operation time period of the auto parts according to the simulation prediction results;
[0071] S5. In the abnormal simulation state, the abnormal deviation between the simulated operation data and the actual operation data is output, and an alarm signal is immediately issued, and the digital twin model is corrected according to the abnormal deviation.
[0072] As described in the above steps S1-S5, with the implementation of the automobile parts digitization method, real-time monitoring and predictive maintenance of automobile parts can be achieved, thereby improving the reliability and safety of the automobile. In this embodiment, the three-dimensional information of the automobile parts is first obtained through three-dimensional scanning technology. Then, the three-dimensional information of the automobile parts is used to map the actual automobile parts into a virtual digital twin model. The digital twin model not only matches the real parts in geometry, but also can be dynamically simulated in function and behavior. Next, the historical operation data of the automobile parts in the historical operation process is collected, including but not limited to parameters such as temperature, pressure, and vibration. The parts in the digital twin model can be dynamically simulated through the historical operation data so that it can reflect the performance under different working conditions. During the simulation process, the real operation of the automobile parts will be collected in real time. The data is compared and analyzed with the simulated operation data of the digital twin model. Through this comparison, the simulation state of the digital twin model can be determined, which includes normal simulation state and abnormal simulation state. In the normal simulation state, the allowable deviation between the simulated operation data and the actual operation data will be calculated. The allowable deviation can be used as a condition for simulating and predicting the future operation state of automotive parts and components, thereby predicting the stable operation period of the parts and components. In the abnormal simulation state, a significant abnormal deviation will be detected between the simulated operation data and the actual operation data. Once an abnormal simulation state occurs, an alarm signal will be immediately issued to prompt the operator that the digital twin model deviates from the actual situation. At the same time, based on the abnormal deviation, the digital twin model will be corrected to ensure the accuracy and reliability of the digital twin model, thereby effectively monitoring automotive parts and components.
[0073] In a preferred embodiment, the step of mapping the auto parts into a virtual digital twin model according to the acquired three-dimensional information of the auto parts includes:
[0074] S101, scanning and processing automobile parts, and outputting three-dimensional information of the automobile parts, where the three-dimensional information includes the size, material and shape of the automobile parts;
[0075] S102, constructing a three-dimensional model of the automobile parts according to the three-dimensional information of the automobile parts;
[0076] S103: Import the three-dimensional model of automobile parts into the digital twin platform, and output the digital twin model of automobile parts.
[0077] As described in the above steps S101-S103, when constructing a digital twin model, the auto parts must first be subjected to corresponding three-dimensional scanning processing. Specifically, the execution process of the auto parts can be captured through the corresponding three-dimensional scanning equipment, such as key information such as size, material and shape. Based on the three-dimensional information obtained by the scan, a three-dimensional model of the auto parts can be constructed. Specifically, the corresponding three-dimensional modeling software (such as SolidWorks, CATIA, etc.) needs to be used. Finally, the constructed three-dimensional model of the auto parts is imported into the digital twin platform, so that the entity of the auto parts can be mapped into a virtual digital twin model, so as to simulate the performance of the auto parts in actual use, such as stress distribution, thermal effect, etc., to provide corresponding support for subsequent design optimization, fault prediction and maintenance.
[0078] In a preferred embodiment, the steps of collecting historical operating data of automobile parts and dynamically simulating automobile parts in the digital twin model based on the historical operating data include:
[0079] S201, obtaining historical working conditions of automobile parts and components, and historical operation data of automobile parts and components under various historical working conditions, wherein the historical working conditions include temperature, humidity, load, speed, and pressure;
[0080] S202, obtaining the real-time working condition of the automobile parts at the current moment, and the real-time operation data of the automobile parts under the real-time working condition;
[0081] S203, comparing the real-time working condition with the historical working condition, outputting the degree of fit between the real-time working condition and the historical working condition, and determining the benchmark simulation working condition according to the degree of fit;
[0082] S204, predicting and analyzing the historical operating data of the automobile parts under the benchmark simulation conditions, and outputting the data as simulated operating data of the digital twin model;
[0083] S205. Dynamically simulate the automotive parts in the digital twin model based on the simulation operation data.
[0084] As described in the above steps S201-S205, when dynamically simulating the digital twin model, it is first necessary to collect the historical operating conditions of the auto parts, including but not limited to the records of various historical operating conditions such as temperature, humidity, load, speed and pressure. At the same time, it is also necessary to understand the real-time operating conditions at the current moment. The real-time operating conditions include parameters such as temperature, humidity, load, speed and pressure in the current environment. After collecting the operating data corresponding to the historical operating conditions and the real-time operating conditions, the historical operating data and the real-time operating data will be compared to evaluate the compatibility between the real-time operating conditions and the historical operating conditions, and a benchmark simulation condition will be determined accordingly. Then, the historical operating data under the benchmark simulation condition will be subjected to corresponding predictive analysis, so as to provide simulated operating data for the digital twin model. Finally, the simulated operating data will be used to dynamically simulate the auto parts in the digital twin model to simulate the performance of the auto parts in actual use.
[0085] In a preferred embodiment, the step of determining the reference simulation working condition according to the degree of fit includes:
[0086] Step 1. Obtain the historical and real-time working conditions of auto parts;
[0087] Step 2, perform vector processing on the historical working conditions and the real-time working conditions, and convert the historical working conditions and the real-time working conditions into numerical vectors of the same dimension;
[0088] Step 3, calibrate the numerical vector corresponding to the historical working condition as the historical working condition vector, and calibrate the numerical vector corresponding to the real-time working condition as the real-time working condition vector;
[0089] Step 4, obtain the fitness calculation function, and input the historical working condition vector and the real-time working condition vector into the fitness calculation function, and calibrate the output result of the fitness calculation function as the fitness of the historical working condition and the real-time working condition;
[0090] Step 5: Arrange the fitness degrees in descending order, and output the historical working condition corresponding to the fitness degree with the highest ranking as the benchmark simulation working condition.
[0091] As described in the above steps Step 1-Step 5, when outputting the degree of fit between the historical working condition and the real-time working condition, it is first necessary to collect the historical working condition and the real-time working condition of the auto parts, and perform vector processing on the historical working condition and the real-time working condition, specifically including converting various forms of working condition data into numerical vector form, ensuring that the historical working condition and the real-time working condition can be compared and analyzed under the same dimension. After the vectorization processing, the numerical vector of the converted historical working condition data will be marked as the historical working condition vector, and the numerical vector of the real-time working condition data will be marked as the real-time working condition vector, and then the degree of fit measurement function is introduced, wherein the degree of fit measurement function includes: Among them, R represents the degree of fit between the real-time working condition and the historical working condition, a i represents the historical operating condition vector, b i Represents the real-time operating condition vector, n represents the number of features in the historical operating condition vector and the real-time operating condition vector. By taking the historical operating condition vector and the real-time operating condition vector as input and inputting them into the fitness measurement function, the fitness between the historical operating condition and the real-time operating condition can be output. Finally, according to the result output by the fitness measurement function, all fitnesses will be sorted according to the numerical value, from high to low. The fitness with the highest ranking, that is, the historical operating condition corresponding to the fitness with the largest numerical value will be selected as the required benchmark simulation operating condition, so as to facilitate the subsequent analysis of the historical operating data of automotive parts under the benchmark simulation conditions.
[0092] In a preferred embodiment, the steps of predicting and analyzing the historical operating data of automobile parts under the benchmark simulation conditions and outputting the simulated operating data of the digital twin model include:
[0093] Step 6, obtaining all the same type of historical working conditions under the benchmark simulation working conditions, as well as the historical operating data of the auto parts under the same type of historical working conditions, and recording the historical operating data of the auto parts under the same type of historical working conditions as the benchmark operating parameters;
[0094] Step 7, all benchmark operating parameters are arranged in the order of occurrence, and adjacent benchmark operating parameters are subjected to difference processing according to the arrangement order of the benchmark operating parameters, and the difference results of adjacent benchmark operating parameters are recorded as operating fluctuation parameters;
[0095] Step 8. Obtain the first prediction function, input the operation fluctuation parameter into the first prediction function, and calibrate the output result of the first prediction function as the simulation operation data of the digital twin model.
[0096] As described in the above steps Step 6-Step 8, after the benchmark simulation condition is output, it is first necessary to analyze the historical operating data under the benchmark simulation condition to ensure that the performance of the spare parts in the actual working environment can be accurately simulated. First, it is necessary to collect all historical conditions of the same type under the benchmark simulation condition, and use the historical operating data of the historical automobile spare parts under the historical conditions of the same type as the benchmark simulation condition as the benchmark operating parameters. After the benchmark operating parameters are output, they will be arranged in the order of occurrence, so as to determine the operating fluctuation parameters between adjacent benchmark operating parameters, and then introduce the first prediction function to process these operating fluctuation parameters, wherein the first prediction function: Where U k represents the simulation running data, U drepresents the real-time operating parameters of auto parts at the current moment, t represents the time length between the prediction node and the current node, and there are multiple prediction nodes. Based on this, the simulation operation data of multiple digital twin models can be output to simulate the operation process of auto parts. m represents the number of operation fluctuation parameters, and U j It represents the operation fluctuation parameter. By inputting the operation fluctuation parameter into the first prediction function, the simulated operation data of the digital twin model can be obtained.
[0097] In a preferred embodiment, the step of comparing the real operation data of the automobile parts with the simulated operation data of the digital twin model to determine the simulation state of the digital twin model includes:
[0098] S301, obtaining the real operation data of the automobile parts and the simulated operation data of the digital twin model at the same time;
[0099] S302, performing difference processing on the real operation data and the simulated operation data, and calibrating the difference result between the real operation data and the simulated operation data as the simulated operation deviation;
[0100] S303, obtaining an evaluation threshold, and comparing the evaluation threshold with the simulation operation deviation;
[0101] If the simulation operation deviation is less than the evaluation threshold, it indicates that the simulation process of the digital twin model fits the actual execution process of the auto parts, and the simulation state of the digital twin model is recorded as a normal simulation state;
[0102] If the simulation operation deviation is greater than or equal to the evaluation threshold, it indicates that the simulation execution process of the digital twin model deviates from the actual execution process of the automotive parts, and the simulation state of the digital twin model is recorded as an abnormal simulation state.
[0103] As described in the above steps S301-S303, in order to ensure that the digital twin model can accurately simulate the actual operation of automobile parts, it is necessary to compare and analyze the real operation data and simulated operation data of automobile parts. First, it is necessary to collect the real operation data of automobile parts in the actual working environment at the same time point, and also obtain the simulated operation data of the digital twin model at the same time point, and perform difference processing on the real operation data and the simulated operation data, so as to obtain the simulated operation deviation, and determine the simulation state of the digital twin model by the simulated operation deviation, specifically by setting the preset evaluation threshold It is compared with the simulation operation deviation. If the simulation operation deviation is less than the evaluation threshold, it means that the simulation process of the digital twin model is consistent with the actual execution process of the automotive parts, indicating that the digital twin model can accurately reflect the actual operation status. In this case, the simulation status of the digital twin model is recorded as a normal simulation status. However, if the simulation operation deviation is greater than or equal to the evaluation threshold, it indicates that there is a deviation between the simulation execution process of the digital twin model and the actual execution process of the automotive parts, and the digital twin model fails to accurately simulate the actual operation status. At this time, the simulation status of the digital twin model will be recorded as an abnormal simulation status.
[0104] In a preferred embodiment, the step of simulating and predicting the operating state of the automobile parts based on the allowable deviation and outputting the stable operating time period of the automobile parts according to the simulation prediction result includes:
[0105] S401, obtaining a simulation operation deviation under a normal simulation state, and recording the simulation operation deviation as an allowable deviation;
[0106] S402, obtaining the allowable deviation threshold of automobile parts;
[0107] S403, obtaining a second prediction function, and inputting the allowable deviation threshold and the allowable deviation amount into the second prediction function, and marking the output result of the second prediction function as a stable operation period;
[0108] Among them, after the stable operation period is output, the length of the stable operation period is counted and recorded as the control condition parameter;
[0109] A control threshold is obtained, and the control threshold is compared with a control condition parameter. When the control condition parameter is less than or equal to the control threshold, the operating state of the automobile parts is output as a risk state, and the operation of the automobile parts is stopped. Otherwise, the normal operation of the automobile parts is maintained.
[0110] As described in the above steps S401-S403, in order to ensure the normal operation of automobile parts, when the digital twin model is in a normal simulation state, the operation state of the automobile parts will be predicted based on the allowable deviation. First, the simulated operation deviation under the normal simulation state needs to be recorded as the allowable deviation. At the same time, the allowable deviation threshold of the automobile parts will be introduced. The allowable deviation threshold is set according to the design standards and performance requirements of the automobile parts, representing the maximum deviation range that the parts can accept to ensure that they can operate safely and effectively. After the allowable deviation and the allowable deviation threshold are output, the second prediction function is introduced. The expression of the second prediction function is: Where, T w Indicates the stable operation period, T y represents the simulation running time of the digital twin model, U z Indicates the allowable deviation threshold, U d Indicates the simulation operation data at the current moment, U p Indicates the allowable deviation, U σ Represents the simulated operation data within the simulated operation period of the digital twin model, η represents the number of simulated operation data within the simulated operation period, the second prediction function comprehensively considers the allowable deviation and the allowable deviation threshold, and can predict the stable operation period of the spare parts. After the stable operation period is output, the length of the stable operation period will be counted and recorded as the control condition parameter, so as to judge whether the automotive spare parts are in a normal working state. This is specifically achieved by introducing a preset control threshold. The control threshold is set according to the historical operation data and maintenance experience of the automotive spare parts, and is used to judge whether the operating state of the spare parts is within an acceptable risk range. Specifically, it is necessary to compare the control threshold with the control condition parameter. If the control condition parameter is less than or equal to the control threshold, it means that there is a risk in the operating state of the automotive spare parts. At this time, the operating state of the automotive spare parts is output as a risk state. At this time, the operation of the automotive spare parts needs to be stopped to prevent potential failures or damage. On the contrary, if the control condition parameter is greater than the control threshold, it means that the operating state of the automotive spare parts is good and can continue to maintain its normal operation to ensure the overall performance and safety of the vehicle.
[0111] In a preferred embodiment, the step of correcting the digital twin model according to the abnormal deviation includes:
[0112] S501, obtaining a simulated operation deviation in an abnormal simulation state, and recording the simulated operation deviation as an abnormal deviation;
[0113] S502, correcting the simulation operation parameters under the digital twin model according to the abnormal deviation to obtain corrected parameters;
[0114] S503: Obtain a trend evaluation function, input the actual operating parameters of the automotive parts into the trend evaluation function, calibrate the output result of the trend evaluation function as a trend evaluation value, and dynamically simulate the digital twin model based on the trend evaluation value and the corrected parameters.
[0115] As described in the above steps S501-S503, when the simulation state of the digital twin model is determined to be an abnormal simulation state, the digital twin model needs to be corrected accordingly to correct the simulation state of the digital twin model so that it can accurately predict the operating state of automobile parts. First, it is necessary to obtain the simulation operation deviation under the abnormal simulation state and record it as the abnormal deviation. Based on it, the simulation operation parameters under the digital twin model are corrected accordingly to ensure that the digital twin model can more accurately reflect the actual operating conditions of automobile parts. After the digital twin model is corrected, the corrected parameters will be output synchronously, and then the trend evaluation function will be introduced. The expression of the trend evaluation function is: In the formula, Q represents the trend assessment value, T s represents the actual execution time length of the auto parts, ε represents the number of actual operation parameters, C υ Represents the real operating parameters. By inputting the real operating parameters of automobile parts into the trend evaluation function, the trend evaluation value can be obtained to reflect the performance trend of automobile parts in actual operation. Then, the digital twin model is dynamically simulated based on the trend evaluation value and the corrected parameters. The dynamic simulation process is consistent with the dynamic simulation process of the digital twin model under the normal simulation state, and will not be repeated here.
[0116] See also Figure 2 The digital twin-based automobile parts digitization system uses the above-mentioned digital twin-based automobile parts digitization method, including:
[0117] A model building module, which is used to map the auto parts into a virtual digital twin model based on the acquired three-dimensional information of the auto parts;
[0118] The simulation module is used to collect historical operating data of auto parts and dynamically simulate the auto parts in the digital twin model based on the historical operating data;
[0119] A state evaluation module, which is used to compare the real operation data of the automobile parts with the simulated operation data of the digital twin model to determine the simulated state of the digital twin model, wherein the simulated state includes a normal simulated state and an abnormal simulated state;
[0120] A first intervention module, wherein the first intervention module is used to output an allowable deviation between simulated operation data and real operation data under a normal simulation state, simulate and predict the operation state of the automobile parts based on the allowable deviation, and output a stable operation time period of the automobile parts according to the simulation prediction result;
[0121] The first intervention module is used to output the abnormal deviation between the simulated operation data and the real operation data under the abnormal simulation state, immediately send out an alarm signal, and correct the digital twin model according to the abnormal deviation.
[0122] In the above, the system includes a model construction module, a simulation module, a state evaluation module, a first intervention module and a second intervention module. The model construction module is responsible for receiving the three-dimensional information of automobile parts and components, and using the three-dimensional information to build a virtual digital twin model. The digital twin model not only reflects the geometric shape of the parts and components, but also contains multi-dimensional information such as material properties and structural characteristics, ensuring the high simulation and practicality of the automobile parts and components. The simulation module collects historical data of automobile parts and components in the actual operation process and dynamically simulates the digital twin model, so as to simulate the performance of automobile parts and components under different working conditions and provide basic data for subsequent analysis and optimization. The state evaluation module obtains the actual operation data of automobile parts and components in real time, and compares it with the simulated operation data of the digital twin model. Through this comparison, the current status of automotive parts can be evaluated to determine whether they are in normal working condition. The status evaluation module can identify normal simulation status and abnormal simulation status. The first intervention module is responsible for calculating the allowable deviation between the simulated operation data and the actual operation data under normal simulation status. Based on the allowable deviation, the system can predict the future operation status of automotive parts, thereby predicting the stable operation period of parts and providing corresponding data support for the stable operation of automotive parts. The second intervention module is responsible for detecting the abnormal deviation between the simulated operation data and the actual operation data under abnormal simulation status. Once such deviation is found, the system will immediately issue an alarm signal to prompt the operator to correct the simulation operation parameters of the digital twin model.
[0123] See also Figure 3 , an electronic device, the electronic device comprising:
[0124] at least one processor;
[0125] and a memory communicatively coupled to the at least one processor;
[0126] Among them, the memory stores a computer program that can be executed by at least one processor, and the computer program is executed by at least one processor so that the at least one processor can execute the above-mentioned digital twin-based automotive parts digitization method.
[0127] The processor of the above-mentioned electronic device may be a central processing unit (CPU), a graphics processing unit (GPU) or other types of microprocessors. These processors are responsible for executing computer programs stored in the memory, thereby realizing the various functions of the digitalization method of automotive parts based on digital twins. The memory of the electronic device may include random access memory (RAM), read-only memory (ROM), flash memory or other types of non-volatile memory. These memories are used to store computer programs, data and intermediate results, ensuring that the processor can quickly access the required information during execution. In practical applications, the electronic device may be a server, workstation, personal computer, embedded system or mobile device, etc. These devices are connected through a network, which can realize remote transmission and processing of data, thereby supporting real-time updating and optimization of the digital twin model. In addition, the electronic device may also include an operator and input and output devices, and the operator is used to perform various mathematical operations and logical operations to ensure that the processor can efficiently and accurately process data during the calculation process of the digital twin model. The input and output devices include keyboards, mice, displays, printers, etc., which are used to realize the interaction between users and electronic devices, so that users can input instructions, view results and output reports.
[0128] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.
[0129] The above is only a preferred embodiment of the present invention. It should be noted that, for those skilled in the art, several improvements and modifications can be made without departing from the principles of the present invention, and these improvements and modifications should also be considered as the protection scope of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention shall be implemented according to the conventional means in the art unless otherwise specified and limited.
Claims
1. A digital twin-based automotive parts digitization method, characterized by: include: Mapping the auto parts into a virtual digital twin model according to the acquired three-dimensional information of the auto parts; Collecting historical operating data of the automobile parts and components, and dynamically simulating the automobile parts and components in the digital twin model based on the historical operating data; According to the real operation data of the automotive parts, the simulated operation data of the digital twin model are compared to determine the simulated state of the digital twin model, wherein the simulated state includes a normal simulated state and an abnormal simulated state; In the normal simulation state, the allowable deviation between the simulated operation data and the real operation data is output, and the operation state of the automobile parts is simulated and predicted based on the allowable deviation, and the stable operation time period of the automobile parts is output according to the simulation prediction result; In the abnormal simulation state, the abnormal deviation between the simulated operation data and the actual operation data is output, and an alarm signal is immediately issued, and the digital twin model is corrected according to the abnormal deviation.
2. The method for digitizing automobile parts based on digital twins according to claim 1, characterized in that: The step of mapping the automobile parts into a virtual digital twin model according to the acquired three-dimensional information of the automobile parts comprises: Scanning the automobile parts and outputting three-dimensional information of the automobile parts and outputting the ... Constructing a three-dimensional model of the automobile parts according to the three-dimensional information of the automobile parts; The three-dimensional model of the automobile parts is imported into the digital twin platform, and the digital twin model of the automobile parts is output.
3. The method for digitizing automobile parts based on digital twins according to claim 1, characterized in that: The step of collecting the historical operation data of the automobile parts and dynamically simulating the automobile parts in the digital twin model according to the historical operation data includes: Acquire the historical working conditions of the automobile parts and the historical operation data of the automobile parts under each of the historical working conditions, wherein the historical working conditions include temperature, humidity, load, speed and pressure; Acquire the real-time working condition of the automobile parts at the current moment, and the real-time operation data of the automobile parts under the real-time working condition; Compare the real-time operating condition with the historical operating condition, output a degree of fit between the real-time operating condition and the historical operating condition, and determine a benchmark simulation operating condition based on the degree of fit; Performing predictive analysis on historical operating data of automobile parts under the benchmark simulation conditions, and outputting the data as simulated operating data of the digital twin model; The automotive parts in the digital twin model are dynamically simulated based on the simulation operation data.
4. The method for digitizing automobile parts based on digital twins according to claim 3 is characterized in that: The step of determining the reference simulation working condition according to the degree of adaptation comprises: Obtaining historical and real-time operating conditions of the automotive parts; Performing vector processing on the historical working conditions and the real-time working conditions, and converting the historical working conditions and the real-time working conditions into numerical vectors of the same dimension; Calibrate the digitized vector corresponding to the historical operating condition as the historical operating condition vector, and calibrate the digitized vector corresponding to the real-time operating condition as the real-time operating condition vector; Obtain a fitness calculation function, and input the historical operating condition vector and the real-time operating condition vector into the fitness calculation function together, and calibrate the output result of the fitness calculation function as the fitness of the historical operating condition and the real-time operating condition; The fitness degrees are arranged in descending order, and the historical operating condition corresponding to the fitness degree with the highest ranking is output as the benchmark simulation operating condition.
5. The method for digitizing automobile parts based on digital twins according to claim 3 is characterized in that: The step of predicting and analyzing the historical operating data of the automobile parts under the benchmark simulation conditions and outputting the data as simulated operating data of the digital twin model includes: Acquire all similar historical operating conditions under the benchmark simulation operating condition, as well as historical operating data of automobile parts under similar historical operating conditions, and record the historical operating data of automobile parts under similar historical operating conditions as benchmark operating parameters; Arrange all the reference operating parameters according to the time sequence of occurrence, perform difference processing on adjacent reference operating parameters according to the arrangement order of the reference operating parameters, and record the difference results of adjacent reference operating parameters as operating fluctuation parameters; A first prediction function is obtained, and the operation fluctuation parameter is input into the first prediction function, and an output result of the first prediction function is calibrated as simulation operation data of the digital twin model.
6. The method for digitizing automobile parts based on digital twins according to claim 1, characterized in that: The step of comparing the real operation data of the automotive parts with the simulated operation data of the digital twin model to determine the simulation state of the digital twin model includes: Acquire the real operation data of the automotive parts and components and the simulated operation data of the digital twin model at the same time; Performing a difference processing on the real operation data and the simulated operation data, and calibrating the difference result between the real operation data and the simulated operation data as the simulated operation deviation; Obtaining an evaluation threshold, and comparing the evaluation threshold with a simulation operation bias; If the simulation operation deviation is less than the evaluation threshold, it indicates that the simulation process of the digital twin model fits the actual execution process of the automotive parts, and the simulation state of the digital twin model is recorded as a normal simulation state; If the simulation operation deviation is greater than or equal to the evaluation threshold, it indicates that the simulation execution process of the digital twin model deviates from the actual execution process of the automotive parts, and the simulation state of the digital twin model is recorded as an abnormal simulation state.
7. The method for digitizing automobile parts based on digital twins according to claim 1, characterized in that: The step of simulating and predicting the operating state of the automobile parts based on the allowable deviation, and outputting the stable operating time period of the automobile parts according to the simulation prediction result, comprises: Acquire the simulated operation deviation under the normal simulation state, and record the simulated operation deviation as the allowable deviation; Obtaining the allowable deviation threshold of the automotive parts; Obtaining a second prediction function, and inputting the allowable deviation threshold and the allowable deviation amount into the second prediction function, and marking the output result of the second prediction function as a stable operation period; After the stable operation period is output, the length of the stable operation period is counted and recorded as a control condition parameter; A control threshold is obtained, and the control threshold is compared with a control condition parameter. When the control condition parameter is less than or equal to the control threshold, the operating state of the automobile component is output as a risk state, and the operation of the automobile component is stopped. Otherwise, the normal operation of the automobile component is maintained.
8. The method for digitizing automobile parts based on digital twins according to claim 1, characterized in that: The step of correcting the digital twin model according to the abnormal deviation comprises: Acquire a simulated operation deviation under the abnormal simulation state, and record the simulated operation deviation as an abnormal deviation; Correcting the simulation operation parameters under the digital twin model according to the abnormal deviation to obtain corrected parameters; A trend evaluation function is obtained, and the actual operating parameters of the automotive parts are input into the trend evaluation function, and the output result of the trend evaluation function is calibrated as a trend evaluation value, and the digital twin model is dynamically simulated based on the trend evaluation value and the corrected parameters.
9. The digital system of automobile parts based on digital twins is characterized by: The method for digitizing automobile parts based on digital twins according to any one of claims 1 to 8 comprises: A model building module, wherein the model building module is used to map the automobile parts into a virtual digital twin model according to the acquired three-dimensional information of the automobile parts; A simulation module, the simulation module is used to collect historical operation data of the automobile parts and components, and dynamically simulate the automobile parts and components in the digital twin model according to the historical operation data; A state evaluation module, wherein the state evaluation module is used to compare the real operation data of the automotive parts with the simulated operation data of the digital twin model to determine the simulated state of the digital twin model, wherein the simulated state includes a normal simulated state and an abnormal simulated state; A first intervention module, the first intervention module is used to output the allowable deviation between the simulated operation data and the real operation data in the normal simulation state, simulate and predict the operation state of the automobile parts based on the allowable deviation, and output the stable operation time period of the automobile parts according to the simulation prediction result; The second intervention module is used to output the abnormal deviation between the simulated operation data and the real operation data under the abnormal simulation state, immediately issue an alarm signal, and perform correction processing on the digital twin model according to the abnormal deviation.
10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the automotive parts digitization method based on digital twins as described in any one of claims 1 to 8.
Citation Information
Cited By
Method and device for calculating operation mode of nuclear power unit
CN119339983A
