Method for virtual simulation verification and evaluation of reliability of speed reducer
By performing multi-body dynamics and thermodynamic analysis in the digital twin model, the problem that traditional testing methods cannot evaluate the reliability of the reducer is solved, and the accuracy of comprehensive evaluation and stability evaluation of the reducer under complex conditions is achieved.
Patent Information
- Application Number
- CN202411244484.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-26
AI Technical Summary
Traditional testing methods cannot meet the modern industry's demand for reducer performance and reliability, and it is difficult to evaluate the long-term stability and reliability of reducer under complex operating conditions.
By acquiring the load data and external conditions of the reducer under different working conditions, establishing the load spectrum, and inputting it into the digital twin model for multi-body dynamics and thermodynamic deduction, analyzing the fatigue intensity, dynamic response and thermal characteristics, and then determining the Reliability of reducer.
A comprehensive evaluation of the reducer under dynamic operating conditions is achieved, the accuracy of stability evaluation is improved, and its physical characteristics can be simulated and thermal characteristics are predicted, such as temperature distribution and thermal stress, to meet modern engineering needs.
Smart Images

Figure CN119026273A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of computer simulation, and in particular relates to a method for virtual simulation verification and evaluation of reducer reliability. Background Art
[0002] In the field of modern industry and mechanical design, as a key transmission component, the performance and reliability of the reducer are crucial to the stability and efficiency of the entire system. With the continuous advancement of industrial automation and precision manufacturing, the performance requirements for reducers are also increasing. Reducers must not only withstand various complex working conditions, but also maintain long-term stability and reliability. In order to meet these requirements, traditional testing methods can no longer meet the needs of modern engineering. Therefore, it is urgent to propose a new reliability evaluation method to evaluate the reliability of reducers. Summary of the invention
[0003] In view of this, the purpose of the present invention is to provide a method for virtual simulation verification and evaluation of reducer reliability to meet the needs.
[0004] In order to achieve the above object, the present invention provides the following technical solutions:
[0005] According to the first aspect, the present invention provides a method for virtual simulation verification and evaluation of reducer reliability, including: obtaining load data of the reducer under different working conditions and external conditions affecting the reliability of the reducer; establishing a load spectrum of the reducer according to the load data of the reducer under different working conditions and the external conditions affecting the reliability of the reducer; inputting the load spectrum into a digital twin model corresponding to the reducer, performing multi-body dynamics and thermodynamics deduction, and analyzing the fatigue strength, dynamic response and thermal characteristics of the reducer; determining the reliability of the reducer according to the simulation data of the fatigue strength, dynamic response and thermal characteristics of the reducer.
[0006] Optionally, the construction of the digital twin model includes: establishing a geometric model based on the physical structure of the reducer; defining the interaction and connection relationship between the reducer components based on multi-body dynamics; determining the remaining usage intensity of each component based on the service time of each component; constructing the reducer physical model based on the geometric model, the interaction and connection relationship between the reducer components and the remaining strength of each component; constructing the reducer digital twin model based on the reducer physical model as well as multi-body dynamics and thermodynamics.
[0007] Optionally, determining the reducer reliability according to the reducer fatigue strength, dynamic response and thermal characteristic simulation data includes: determining the reliability of each component of the reducer according to the fatigue strength, dynamic response and thermal characteristic simulation data of the reducer; determining the reducer reliability according to the reliability of each component of the reducer includes:
[0008]
[0009] Wherein, Re(rs) is the reliability of the reducer, Re1 is the reliability of the first component, Re2 is the reliability of the second component, α is the correlation coefficient, and C is the Copula distribution function.
[0010] Optionally, the reliability of each component of the reducer is determined based on the fatigue strength, dynamic response and thermal characteristics simulation data of the reducer, including: calculating the fatigue failure probability of the component within the expected service life based on the SN curve and the fatigue characteristics of the material; analyzing the vibration and impact response data of the component under working conditions to determine the risk probability of resonance or fatigue crack extension; evaluating the temperature distribution and thermal stability of the component under actual working conditions based on the thermal characteristics simulation data to determine the risk probability of overheating or thermal fatigue; and performing weighted calculation on the fatigue failure probability, the risk probability of resonance or fatigue crack extension, and the risk probability of overheating or thermal fatigue to obtain the reliability of the component.
[0011] Optionally, the remaining usage intensity of each component is determined according to the service time of each component, including:
[0012]
[0013] Among them, Q(t) is the remaining usage intensity of the component, Q(0) is the initial usage intensity, σ max is the peak value of cyclic stress, t is the service time, L f is the time length corresponding to fatigue life, σ M is the stress amplitude, is the mean stress, Where a is the material constant.
[0014] Optionally, the reducer reliability is determined based on the simulation data of the fatigue strength, dynamic response and thermal characteristics of the reducer, including: inputting the simulation data of the fatigue strength, dynamic response and thermal characteristics of the reducer into a pre-trained neural network to obtain the reducer reliability; the training process of the neural network includes: obtaining the simulation data of the fatigue strength, dynamic response and thermal characteristics of the reducer under different working conditions; labeling the samples composed of the simulation data of the fatigue strength, dynamic response and thermal characteristics under different working conditions to obtain reliability labels; inputting the samples and reliability labels into the neural network model for supervised learning with the goal of minimizing the loss function until a preset accuracy is reached to obtain a trained neural network model.
[0015] Optionally, a method for virtual simulation verification and evaluation of reducer reliability also includes: receiving component defect simulation instructions, determining corresponding defect parameters according to the component defect simulation instructions; inputting the defect type parameters into the digital twin model, and changing the corresponding component parameters in the digital twin model.
[0016] Optionally, determining corresponding defect parameters according to component defect simulation instructions includes: obtaining component defect simulation instruction keywords; determining fuzzy sets corresponding to component defect simulation instruction keywords according to fuzzy rules pre-constructed based on expert knowledge; and randomly selecting parameters from at least one fuzzy set as corresponding defect parameters, the parameters in each fuzzy set being parameters that satisfy the membership of the fuzzy set members.
[0017] According to the second aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the method for virtual simulation verification and evaluation of reducer reliability described in the first aspect or any embodiment of the first aspect.
[0018] According to the third aspect, an embodiment of the present invention provides a computer storage medium having computer instructions stored thereon, which, when executed by a processor, implement the steps of the method for virtual simulation verification and evaluation of reducer reliability described in the first aspect or any embodiment of the first aspect.
[0019] An embodiment of the present invention provides a method for virtual simulation verification and evaluation of reducer reliability. The load spectrum is input into the digital twin model of the reducer, and multi-body dynamics and thermodynamics deduction can be performed. It can simulate the response of the reducer under dynamic working conditions and predict its thermal characteristics, such as temperature distribution, thermal stress, etc. It can effectively simulate the physical characteristics of the reducer to meet the needs of modern engineering. By collecting the load data of the reducer under different working conditions and the external conditions that affect its reliability, the performance of the reducer in the actual working environment can be comprehensively evaluated, thereby improving the accuracy of the stability evaluation.
[0020] Other advantages, objectives and features of the present invention will be described in the following description and will be apparent to those skilled in the art to some extent, or those skilled in the art may be taught from the practice of the present invention. The objectives and other advantages of the present invention may be realized and obtained through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to make the purpose, technical solution and beneficial effects of the present invention clearer, the present invention provides the following drawings for illustration:
[0022] Figure 1 A specific example flow chart of a method for virtual simulation verification and evaluation of reducer reliability of the present invention;
[0023] Figure 2 It is a principle block diagram of a specific example of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION
[0024] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0025] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, it can also be the internal connection of two components, it can be a wireless connection, or it can be a wired connection. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0026] In addition, the technical features involved in the different embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0027] The embodiment of the present invention provides a method for virtual simulation verification and evaluation of reducer reliability, such as Figure 1 As shown, including:
[0028] S101, obtaining load data of the reducer under different working conditions and external conditions affecting the reliability of the reducer;
[0029] Exemplarily, the load data may include torque, speed, temperature, vibration, etc. External conditions that affect the reliability of the reducer may include ambient temperature, humidity, etc. The method for obtaining the load data of the reducer under different working conditions may be to collect the load data of the reducer under different working conditions through field testing or historical data analysis; the method for obtaining the external conditions that affect the reliability of the reducer may be to use various sensors and record the sensor data.
[0030] S102, establishing a reducer load spectrum according to the load data of the reducer under different working conditions and external conditions that affect the reliability of the reducer;
[0031] Exemplarily, the load spectrum defines different types of loads that the system may encounter, such as static loads, dynamic loads, impact loads, etc. The load spectrum describes the frequency or probability distribution of different load magnitudes, such as normal distribution, Weibull distribution or other statistical distributions.
[0032] When constructing the load spectrum, in order to reduce data complexity and improve data quality, the collected load data and external condition data can be sorted out first to remove outliers and noise, and then the key features in the load data, such as the size, frequency, duration of the load, and the frequency components of the load are identified, and the key features of the load data are clustered and divided into different load types, such as periodic loads, random loads, and impact loads. The specific clustering method can be K-means. The specific method of establishing the reducer load spectrum is not limited in this embodiment, and those skilled in the art can determine it as needed. According to the above analysis results, the load spectrum of the reducer is constructed. In order to improve the accuracy of the load spectrum, the present embodiment can also verify the accuracy of the load spectrum through actual testing or simulation. When the load spectrum passes the verification, it is used as the load spectrum finally established in this step.
[0033] S103, inputting the load spectrum into the digital twin model corresponding to the reducer, performing multi-body dynamics and thermodynamics deduction, and analyzing the fatigue strength, dynamic response, and thermal characteristics of the reducer;
[0034] Exemplarily, the digital twin model corresponding to the reducer is constructed based on the physical structure model, multi-body dynamics model and thermodynamics model of the reducer. The load spectrum data is input into the digital twin model to simulate the working state of the reducer under various load conditions, and the motion response and fatigue strength of the reducer under different loads are analyzed through multi-body dynamics, and the influence of the load on the temperature distribution and thermal characteristics of the reducer is evaluated through thermodynamics.
[0035] S104, determining the reducer reliability according to the reducer fatigue strength, dynamic response and thermal characteristic simulation data.
[0036] Exemplarily, based on the fatigue strength, dynamic response and thermal characteristics simulation data of the reducer, the reliability of the reducer can be determined by simulating and analyzing the fatigue strength data, dynamic response data and thermal characteristics data, determining the number of stress cycles and the corresponding fatigue failure risk of the reducer under different load conditions, the risk of resonance or fatigue crack propagation caused by the vibration, impact and torque transmission characteristics of the reducer during operation, and the temperature distribution and thermal stability of the reducer under different working conditions, to determine the risk of overheating or thermal fatigue.
[0037] The reliability of the reducer is comprehensively determined based on the risk of fatigue failure, the risk of resonance or fatigue crack extension, and the risk of overheating or thermal fatigue. The specific method can be determined by the fuzzy comprehensive evaluation method. First, a fuzzy set is defined for each risk factor (fatigue failure, resonance, crack extension, overheating, thermal fatigue). The elements in each set represent different levels of the risk factor. For each risk factor, a membership function is constructed to map the actual measured or calculated data to the [0,1] interval to represent the membership of the risk factor. The membership function can be a linear membership function. Based on professional knowledge and experience, the relative importance of each risk factor on the reliability of the reducer is determined, and a weight is assigned to each factor. Then, fuzzy rules are established to describe how different risk factors affect the reliability of the reducer. For example, "If the risk of fatigue failure is high and the risk of resonance is high, the reliability of the reducer is low." The membership of each risk factor is combined with its weight, and the comprehensive reliability index of the reducer is calculated by the fuzzy comprehensive evaluation method, so that the reliability of the reducer is divided into different levels of high, medium and low.
[0038] This embodiment does not limit the method of determining the reliability of the reducer based on the fatigue strength, dynamic response and thermal characteristics simulation data of the reducer, and those skilled in the art can determine it as needed.
[0039] An embodiment of the present invention provides a method for virtual simulation verification and evaluation of reducer reliability. The load spectrum is input into the digital twin model of the reducer, and multi-body dynamics and thermodynamics deduction can be performed. It can simulate the response of the reducer under dynamic working conditions and predict its thermal characteristics, such as temperature distribution, thermal stress, etc. It can effectively simulate the physical characteristics of the reducer to meet the needs of modern engineering. By collecting the load data of the reducer under different working conditions and the external conditions that affect its reliability, the performance of the reducer in the actual working environment can be comprehensively evaluated, thereby improving the accuracy of the stability evaluation.
[0040] As an optional implementation, the construction of the digital twin model includes:
[0041] A geometric model is established based on the physical structure of the reducer. The interaction and connection relationship between the reducer components is defined based on multi-body dynamics. The remaining usage intensity of each component is determined based on the service life of each component. A physical model of the reducer is constructed based on the geometric model, the interaction and connection relationship between the reducer components, and the remaining strength of each component. A digital twin model of the reducer is constructed based on the physical model of the reducer as well as multi-body dynamics and thermodynamics.
[0042] For example, first use CAD software to create an accurate three-dimensional geometric model based on the physical structure of the reducer, define the interaction between the various components in the reducer (such as gears, shafts, bearings, etc.), such as gear meshing, bearing support, etc., and determine the connection type of each component, such as rigid connection, elastic connection or hinge, etc. The establishment of a three-dimensional geometric model helps to accurately simulate the spatial relationship and interaction of the various components of the reducer, and provide an accurate basis for subsequent multi-body dynamics and thermodynamic analysis. Then, using the principle of multi-body dynamics, according to the service time, historical load data and material properties of the components, evaluate the wear, corrosion and fatigue damage of each component, and use the SN curve of the material or other life prediction methods to determine the residual strength and life of the component. Integrate the geometric model, the interaction and connection relationship between the components, and the residual strength of the components to build a complete physical model, and apply thermodynamics in the physical model to analyze the heat transfer and temperature distribution of the reducer during operation, so as to achieve a true restoration of the reducer at the digital level.
[0043] This embodiment provides the following calculation method for residual strength:
[0044] According to the service life of each component, determine the remaining usage intensity of each component, including:
[0045]
[0046] Among them, Q(t) is the remaining usage intensity of the component, Q(0) is the initial usage intensity, σ max is the peak value of cyclic stress, t is the service time, L f is the time length corresponding to fatigue life, σ M is the stress amplitude, is the mean stress, Where a is the material constant.
[0047] An embodiment of the present invention provides a method for virtual simulation verification and evaluation of reducer reliability. The remaining usage intensity of each component is introduced into the digital twin model, which can not only restore the actual usage of each component, but also help to implement targeted maintenance and replacement strategies, reduce the risk of failure, and extend the service life of the reducer.
[0048] As an optional implementation, the reducer reliability is determined based on the reducer fatigue strength, dynamic response and thermal characteristics simulation data, including:
[0049] The reliability of each component of the reducer is determined based on the fatigue strength, dynamic response and thermal characteristics simulation data of the reducer; the reliability of the reducer is determined based on the reliability of each component of the reducer.
[0050] Exemplarily, the method of determining the reliability of each component of the reducer based on the fatigue strength, dynamic response and thermal characteristics simulation data of the reducer specifically includes: calculating the fatigue failure probability of the component within the expected service life based on the SN curve and the fatigue characteristics of the material; analyzing the vibration and impact response data of the component under working conditions to determine the risk probability of resonance or fatigue crack extension; evaluating the temperature distribution and thermal stability of the component under actual working conditions based on the thermal characteristics simulation data to determine the risk probability of overheating or thermal fatigue; and obtaining the reliability of the component based on the fatigue failure probability, the risk probability of resonance or fatigue crack extension, and the risk probability of overheating or thermal fatigue.
[0051] According to the SN curve and the fatigue properties of the material, the specific method for calculating the fatigue failure probability of the component within the expected service life can be to first determine the SN curve according to the fatigue properties of the material, that is, the relationship between the stress amplitude and the life (number of cycles). For each level of load, the equivalent cyclic stress is calculated according to its frequency of occurrence and duration. According to the SN curve, the calculated equivalent stress is converted into the corresponding fatigue life, and the cumulative damage is calculated according to the fatigue life at each stress level. The cumulative damage calculation method can be:
[0052]
[0053] Where D is the cumulative damage, N i is the number of cycles under the i-th stress level, N i0 is the corresponding fatigue life.
[0054] When the cumulative damage reaches 1, the component reaches fatigue failure. According to the number of cycles in the expected service life, the cumulative damage probability of failure is estimated as the fatigue failure probability. Fatigue life usually obeys a certain statistical distribution, such as Weibull distribution or lognormal distribution. The probability of fatigue failure of a component in the expected service life can be calculated using a statistical distribution function. Specifically, assuming that the damage value obeys the lognormal distribution, first, calculate the damage value D i The logarithm of the new random variable ln(D i ).
[0055] Assume that ln(D i ) obeys the normal distribution, and the probability that the cumulative damage reaches ln(1) is calculated as:
[0056]
[0057] Where Φ is the cumulative distribution function of the standard normal distribution, μ and σ are ln(D i )’s mean and standard deviation.
[0058] If the cumulative damage D reaches 1, it can be considered that the probability of fatigue failure of the material in the current service life is 1 (i.e. 100%). If D is less than 1, the fatigue failure probability P can be approximately calculated by the following formula: P = D; in this case, the cumulative damage probability D can be approximately used as the fatigue failure probability P.
[0059] The specific method of analyzing the vibration and impact response data of the component under working conditions and determining the risk probability of resonance or fatigue crack growth can be to determine the natural frequency and resonant frequency of the component through finite element analysis, perform fast Fourier transform (FFT) on the data, obtain a spectrum diagram, identify the frequency causing resonance, and determine the probability distribution of the vibration amplitude that reaches the resonance condition under working conditions by calculating the frequency at which the vibration amplitude exceeds the resonance threshold. When resonance exists, the Paris formula is used to evaluate the risk of fatigue crack growth caused by it. Specifically, the Paris formula can be used to calculate the number of cycles required for the crack to grow to the target length, such as the target length is 1mm. The number of cycles is matched to the risk value of fatigue crack growth. For example, when the cycle is 10 3 When the number of cycles is 100, the corresponding risk value of fatigue crack growth is 10%. This embodiment does not limit the corresponding relationship between the number of cycles and the risk value of fatigue crack growth, and those skilled in the art can determine it as needed.
[0060] The temperature distribution and thermal stability of the component under actual working conditions are evaluated based on the thermal characteristic simulation data, and the specific method for determining the risk probability of overheating or thermal fatigue can be to use a statistical method (such as Monte Carlo simulation) to calculate the probability of overheating or thermal fatigue events under given working conditions. This embodiment does not limit the specific method of the risk probability of overheating or thermal fatigue, and those skilled in the art can determine it as needed.
[0061] The process of obtaining the reliability of the component according to the fatigue failure probability, the risk probability of resonance or fatigue crack extension, and the risk probability of overheating or thermal fatigue can specifically be to calculate the reliability probability of the corresponding risk of each component according to the fatigue failure risk probability, the risk probability of resonance or fatigue crack extension, and the risk probability of overheating or thermal fatigue of each component, normalize the reliability probability corresponding to each risk, and weight and process the normalized reliability probability according to preset weights to obtain the reliability of the component, wherein reliability probability = 1-risk probability.
[0062] The reducer is composed of components with different characteristics, and its overall reliability is determined by the reliability of each component. In this embodiment, the Copula function is used to couple the components to obtain the overall reliability of the reducer.
[0063] Specifically:
[0064]
[0065] Wherein, Re(rs) is the reliability of the reducer, Re1 is the reliability of the first component, Re2 is the reliability of the second component, α is the correlation coefficient, and C is the Copula distribution function.
[0066] The embodiment of the present invention provides a method for virtual simulation verification and evaluation of reducer reliability, which comprehensively considers multiple aspects such as fatigue, vibration, impact and thermal characteristics, and provides a comprehensive risk assessment, which is more accurate and reliable than the analysis of a single factor. In addition, the scheme is based on actual data and simulation results, avoids errors in subjective judgment, and improves the objectivity and scientificity of risk assessment.
[0067] As an optional implementation, the reducer reliability is determined according to the reducer fatigue strength, dynamic response and thermal characteristic simulation data, including: inputting the reducer fatigue strength, dynamic response and thermal characteristic simulation data into a pre-trained neural network to obtain the reducer reliability;
[0068] The training process of the neural network includes: obtaining simulation data of fatigue strength, dynamic response and thermal characteristics of the reducer under different working conditions; labeling samples composed of simulation data of fatigue strength, dynamic response and thermal characteristics under different working conditions to obtain reliability labels; inputting samples and reliability labels into the neural network model for supervised learning with the goal of minimizing the loss function until the preset accuracy is reached to obtain a trained neural network model.
[0069] Exemplarily, first, collect simulation data such as fatigue strength, dynamic response and thermal characteristics of the reducer under different working conditions. These data can be generated by numerical simulation software, which can be ANSYS, COMSOL, etc., or obtained through experimental testing. This embodiment does not limit the acquisition method, and those skilled in the art can determine it as needed. According to different data sources, determine the sample labels corresponding to different data sources. For example, when the simulation data is obtained through experimental testing, the reliability assessment results represented by the test results are used as labels. When the simulation data is generated by numerical simulation software, the reliability assessment results represented by the simulated results are used as labels. The labels usually indicate the reliability status of the reducer under specific working conditions, such as normal operation, failure, end of life, etc.
[0070] Furthermore, in order to ensure data quality, outliers and missing values in the data can be removed. Then, according to business needs and data characteristics, select or construct features that have a significant impact on the prediction target, such as fatigue life, maximum stress, dynamic response frequency, thermal stress, etc., and select neural network models suitable for processing multi-input and multi-output problems, such as multi-input and multi-output neural networks (MIMO), long short-term memory networks (LSTM), etc.
[0071] The training process of the neural network model can include: dividing the collected data set into a training set, a validation set, and a test set, usually with a ratio of 70% training, 15% validation, and 15% testing. Use the training set data to build a neural network model. The model structure should include an input layer (corresponding to features such as fatigue strength, dynamic response, and thermal characteristics), a hidden layer (for data processing and feature learning), and an output layer (for predicting the reliability of the reducer). Select the target loss function and the optimization algorithm. The target loss function can be the mean squared error (MSE). Minimizing the target loss function is used as the goal of model optimization. The optimization algorithm can be stochastic gradient descent, Adam, etc., to minimize the loss function. Use the training set data to iteratively train the model and adjust the model parameters until the loss function reaches the preset minimum value or the preset number of training rounds is reached. Use the validation set data to evaluate the model performance and optimize the model by adjusting the model parameters or structure.
[0072] The embodiment of the present invention provides a method for virtual simulation verification and evaluation of reducer reliability, which determines the reducer reliability through a pre-trained neural network. Since the pre-trained neural network has learned a large number of mapping relationships between inputs and outputs, and does not require any precise mathematical expressions between inputs and outputs, as long as the network is trained with a known pattern, the network has the mapping ability between input-output pairs. Therefore, the neural network can effectively understand the mapping relationship between simulation data of fatigue strength, dynamic response and thermal characteristics and reliability, thereby improving the accuracy of reliability judgment.
[0073] As an optional implementation, a method for virtual simulation verification and evaluation of reducer reliability also includes:
[0074] receiving a component defect simulation instruction, and determining corresponding defect parameters according to the component defect simulation instruction;
[0075] Input the defect type parameters into the digital twin model and change the corresponding component parameters in the digital twin model.
[0076] Exemplarily, receiving a component defect simulation instruction, and determining a corresponding defect parameter according to the component defect simulation instruction includes: obtaining a component defect simulation instruction keyword; determining a fuzzy set corresponding to the component defect simulation instruction keyword according to a fuzzy rule pre-constructed based on expert knowledge; and randomly selecting a parameter from at least one fuzzy set as the corresponding defect parameter, wherein the parameters in each fuzzy set are parameters that satisfy the membership of the members of the fuzzy set.
[0077] Specifically, first, parse the received component defect simulation instructions to extract key information, such as defect type, severity, location and other keywords. According to the knowledge and experience of domain experts, construct a fuzzy rule base, which describes the relationship between different defect keywords and fuzzy sets. Then, define corresponding fuzzy sets for each defect keyword, such as "minor", "medium", "serious", etc. Each fuzzy set consists of a set of parameters, which reflect the membership of the members of the set. According to the extracted defect simulation instruction keywords, search the fuzzy rule base, determine the fuzzy set corresponding to the keyword, and randomly select a parameter from the determined fuzzy set. These parameters are parameters that meet the membership of the fuzzy set members, that is, they have a high membership in the fuzzy set. Through the above method, the user experience can be increased. The user only needs to enter the corresponding instructions to automatically modify the parameters of the corresponding components in the digital twin. In this way, it is more conducive to simulating the faulty or defective reducer and judging the stability of the reducer under different states.
[0078] The present application also provides an electronic device, such as Figure 2 As shown, a processor 501 and a memory 502, wherein the processor 501 and the memory 502 may be connected via a bus or other means.
[0079] The processor 501 may be a central processing unit (CPU). The processor 501 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or a combination of the above chips.
[0080] The memory 502 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as program instructions / modules corresponding to the method for virtual simulation verification and evaluation of reducer reliability in an embodiment of the present invention. The processor executes various functional applications and data processing of the processor by running the non-transient software programs, instructions and modules stored in the memory.
[0081] The memory 502 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the processor, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 502 may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0082] The one or more modules are stored in the memory 502, and when executed by the processor 501, the following is performed: Figure 1 A method for virtual simulation verification and evaluation of reducer reliability in the illustrated embodiment.
[0083] For details of the above electronic equipment, please refer to Figure 1 The corresponding related descriptions and effects in the illustrated embodiments can be understood and will not be repeated here.
[0084] This embodiment also provides a computer storage medium, which stores computer executable instructions, and the computer executable instructions can execute the method of virtual simulation verification and evaluation of reducer reliability in any of the above method embodiments. Wherein, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.
[0085] Finally, it should be noted that the above preferred embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail through the above preferred embodiments, those skilled in the art should understand that various changes can be made in form and details without departing from the scope defined by the claims of the present invention.
Claims
1. A method for virtual simulation verification and evaluation of reducer reliability, characterized in that: include: Obtain the load data of the reducer under different working conditions and the external conditions that affect the reliability of the reducer; According to the load data of the reducer under different working conditions and the external conditions affecting the reliability of the reducer, the load spectrum of the reducer is established; The load spectrum is input into the digital twin model corresponding to the reducer, and multi-body dynamics and thermodynamics deduction is performed to analyze the fatigue strength, dynamic response and thermal characteristics of the reducer; The reliability of the reducer is determined based on the reducer fatigue strength, dynamic response and thermal characteristics simulation data.
2. A method for virtual simulation verification and evaluation of reducer reliability according to claim 1, characterized in that: The construction of the digital twin model includes: Establish a geometric model based on the physical structure of the reducer; Define the interactions and connections between reducer components based on multi-body dynamics; Determine the remaining usage intensity of each component based on its service life; Construct a physical model of the reducer based on the geometric model, the interaction and connection relationship between the reducer components, and the residual strength of each component; A digital twin model of the reducer is constructed based on the reducer physical model as well as multi-body dynamics and thermodynamics.
3. The method for virtual simulation verification and evaluation of reducer reliability according to claim 1 is characterized in that: Determine the reducer reliability based on the reducer fatigue strength, dynamic response and thermal characteristics simulation data, including: Determine the reliability of each component of the reducer based on the reducer fatigue strength, dynamic response and thermal characteristics simulation data; The reliability of the reducer is determined based on the reliability of each component of the reducer, including: Wherein, Re(rs) is the reliability of the reducer, Re1 is the reliability of the first component, Re2 is the reliability of the second component, α is the correlation coefficient, and C is the Copula distribution function.
4. The method for virtual simulation verification and evaluation of reducer reliability according to claim 3 is characterized in that: According to the reducer fatigue strength, dynamic response and thermal characteristics simulation data, the reliability of each reducer component is determined, including: Calculate the probability of fatigue failure of components within the expected service life based on the SN curve and the fatigue properties of the material; Analyze the vibration and impact response data of the components in working condition to determine the risk probability of resonance or fatigue crack growth; Evaluate the temperature distribution and thermal stability of components under actual working conditions based on thermal characteristic simulation data, and determine the risk probability of overheating or thermal fatigue; The reliability of the component is obtained by weighted calculation of the fatigue failure probability, the risk probability of resonance or fatigue crack extension, and the risk probability of overheating or thermal fatigue.
5. The method for virtual simulation verification and evaluation of reducer reliability according to claim 2 is characterized in that: According to the service life of each component, determine the remaining usage intensity of each component, including: Among them, Q(t) is the remaining usage intensity of the component, Q(0) is the initial usage intensity, σ max is the peak value of cyclic stress, t is the service time, L f is the time length corresponding to fatigue life, σ M is the stress amplitude, is the mean stress, Where a is the material constant.
6. The method for virtual simulation verification and evaluation of reducer reliability according to claim 1 is characterized in that: Determine the reducer reliability based on the reducer fatigue strength, dynamic response and thermal characteristics simulation data, including: The fatigue strength, dynamic response and thermal characteristics simulation data of the reducer are input into the pre-trained neural network to obtain the reliability of the reducer; The training process of a neural network includes: Obtain simulation data of fatigue strength, dynamic response and thermal characteristics of reducer under different working conditions; Labeling is performed on samples consisting of simulation data of fatigue strength, dynamic response and thermal characteristics under different working conditions to obtain reliability labels; The samples and reliability labels are input into the neural network model for supervised learning with the goal of minimizing the loss function until the preset accuracy is reached, thus obtaining a trained neural network model.
7. The method for virtual simulation verification and evaluation of reducer reliability according to claim 1 is characterized in that: Also includes: receiving a component defect simulation instruction, and determining corresponding defect parameters according to the component defect simulation instruction; Input the defect type parameters into the digital twin model and change the corresponding component parameters in the digital twin model.
8. The method for virtual simulation verification and evaluation of reducer reliability according to claim 7 is characterized in that: Determine the corresponding defect parameters according to the component defect simulation instruction, including: Get the component defect simulation instruction keywords; Determine the fuzzy set corresponding to the component defect simulation instruction keyword according to the fuzzy rules pre-constructed based on expert knowledge; Parameters are randomly selected from at least one fuzzy set as corresponding defect parameters, and the parameters in each fuzzy set are parameters that satisfy the membership degree of the members of the fuzzy set.
9. An electronic device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the steps of the method for virtual simulation verification and evaluation of reducer reliability as described in any one of claims 1 to 8.
10. A computer storage medium having computer instructions stored thereon, characterized in that: When the instruction is executed by the processor, the steps of the method for virtual simulation verification and evaluation of reducer reliability described in any one of claims 1-8 are implemented.
