Comprehensive performance test system applied to speed reducer and detection method thereof

Abstract

The invention discloses a comprehensive performance test system applied to a speed reducer and a detection method thereof, and relates to the technical field of speed reducer performance tests.The method comprises the steps that first comprehensive data of the speed reducer are obtained and preprocessed; constructing a digital twinborn model based on the preprocessed first comprehensive data, and analyzing internal stress field distribution based on the digital twinborn model; adaptively correcting a weight coefficient of the digital twinborn model based on an analysis result of stress field distribution; and re-analyzing the internal stress field distribution according to the corrected digital twinborn model and verifying the internal stress field distribution. By constructing the digital twinborn model and combining equivalent stress early warning and a weight coefficient self-adaptive correction mechanism, accurate quantitative analysis and dynamic adaptation of the internal stress field of the speed reducer are achieved, the one-sidedness and static model limitation of traditional single physical field detection are broken through, and the detection accuracy is improved. And a full-process intelligent comprehensive performance detection scheme from data acquisition, model analysis to maintenance decision is provided for industrial transmission equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of speed reducer performance testing, in particular to a comprehensive performance testing system and a testing method thereof applied to a speed reducer. Background Art

[0002] As a core component of industrial transmission systems, reducers are widely used in wind power, metallurgy, mining and other fields. Their comprehensive performance directly affects the reliability and life of equipment operation. The performance testing of reducers needs to take into account multi-dimensional indicators such as mechanical load bearing capacity, thermal management efficiency and internal defect diagnosis. Traditional single parameter testing can no longer meet the comprehensive evaluation needs under complex working conditions. Faults such as gear meshing failure, bearing overheating or internal cracks are often accompanied by coordinated changes in mechanical stress, temperature field and acoustic signals. It is urgent to establish a comprehensive detection system with multi-physical field coupling; existing digital twin models are mostly static geometric modeling, lacking multi-field coupling calculation of mechanical stress, thermal stress and acoustic stress; the model weight coefficient relies on empirical setting and cannot adapt to equipment aging or operating condition fluctuations.

[0003] However, the current common solutions have many shortcomings, including: existing technologies only monitor single physical field data in isolation, and are unable to quantify the internal stress distribution generated by the coupling of mechanical, thermal, and acoustic fields, which can easily lead to the omission of early defects; the digital twin models of existing technologies are static, rely on fixed parameter modeling, lack a real-time data-driven weight adaptive correction mechanism, and are difficult to adapt to operating condition fluctuations and equipment aging, resulting in large stress prediction errors; the fault warning and root cause location of existing technologies rely on manual experience, lack quantitative judgment basis based on the mechanical properties of materials, and are unable to accurately distinguish stress state levels and quickly trace complex faults. Summary of the Invention

[0004] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the abstract and title of this application to avoid obscuring the purpose of this section, the abstract and the title of the invention, and such simplifications or omissions should not be used to limit the scope of the present invention.

[0005] In view of the above-mentioned problems existing in the existing comprehensive performance testing system and detection method for reducers, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide a comprehensive performance testing system and detection method for reducers, which is suitable for solving the problems that the existing technology only monitors a single physical field data in isolation, cannot quantify the internal stress distribution generated by the coupling of mechanical, thermal and acoustic fields, and easily leads to the omission of early defects; the digital twin model of the existing technology is static, relies on fixed parameter modeling, lacks a real-time data-driven weight adaptive correction mechanism, is difficult to adapt to working condition fluctuations and equipment aging, and causes large stress prediction errors; the fault warning and root cause location of the existing technology rely on manual experience, lack of quantitative judgment basis based on the mechanical properties of materials, and cannot accurately distinguish stress state levels and quickly trace complex faults.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, an embodiment of the present invention provides a comprehensive performance detection method applied to a reducer, which includes obtaining first comprehensive data of the reducer and preprocessing the first comprehensive data; constructing a digital twin model based on the preprocessed first comprehensive data, and analyzing the internal stress field distribution based on the digital twin model; adaptively correcting the weight coefficient of the digital twin model based on the analysis results of the stress field distribution; and re-analyzing the internal stress field distribution according to the corrected digital twin model and verifying it.

[0008] As a preferred solution of the comprehensive performance detection method applied to the reducer described in the present invention, wherein: the first comprehensive data includes mechanical characteristic data, thermal characteristic data and acoustic characteristic data; the mechanical characteristic data includes torque, vibration and speed; the thermal characteristic data includes temperature, gradient and oil parameters; the acoustic characteristic data includes acoustic emission and noise spectrum; the mechanical characteristic data is obtained through a torque sensor, a vibration sensor and a photoelectric encoder; the thermal characteristic data is obtained through a temperature sensor, a thermal mass flow sensor and a vibration viscosity sensor; the acoustic characteristic data is obtained through a broadband acoustic emission sensor and a microphone.

[0009] As a preferred solution of the comprehensive performance detection method applied to the reducer described in the present invention, the specific steps of constructing a digital twin model based on the first comprehensive data after preprocessing are as follows: by introducing the mechanical stress tensor, the mechanical characteristic data of torque, vibration, and speed are converted into the dynamic stress distribution inside the structure; by introducing the thermal stress tensor, the temperature field, thermal gradient, and oil parameter thermal characteristic data are converted into the stress distribution caused by thermal expansion mismatch; by introducing the acoustic stress tensor, the acoustic emission signal and noise spectrum acoustic characteristic data are inverted into the stress characteristics of internal microcracks and stress concentration defects; and the digital twin model is constructed by fusing the mechanical stress tensor, the thermal stress tensor, and the acoustic stress tensor.

[0010] As a preferred solution of the comprehensive performance detection method for a reducer according to the present invention, the specific formula of the digital twin model is as follows:

[0011] Where, is the fusion stress tensor; 、 、 is the field weight coefficient; is the mechanical stress tensor; is the thermal stress tensor; is the acoustic stress tensor; 、 、 is the cross-coupling weight; is the reference stress; is the inner product of the stress tensor; is the inner product of the stress tensor; is the inner product of the stress tensor.

[0012] As a preferred solution of the comprehensive performance detection method applied to the reducer described in the present invention, the specific content of the fused stress tensor is as follows: the fused stress tensor is converted into an equivalent stress; when the equivalent stress is less than the first threshold value, it means that the reducer is in a "healthy operating range", the material has not entered the damage stage, and the stress distribution of each component is within the design safety margin; when the equivalent stress is greater than the first threshold value and less than the second threshold value, it means that the reducer has entered a "stress abnormality warning range", the material has undergone plastic deformation, and if it continues to run, fatigue damage will be accelerated and the motor output power will be reduced. At the same time, auxiliary cooling will be started and further analysis will be carried out; when the equivalent stress is greater than the second threshold value, it means that the reducer has entered a "critical state of dangerous failure", the material has undergone plastic deformation, and the geometric dimensions of the components have undergone irreversible changes.

[0013] As an optimal solution of the comprehensive performance detection method applied to the reducer described in the present invention, the specific steps of adaptively correcting the weight coefficient of the digital twin model based on the analysis results of the stress field distribution are as follows: when the equivalent stress is judged to be in the healthy operating range, all weight coefficients are maintained unchanged, and only the stress distribution cloud map of the gear meshing area and the bearing seat is recorded; when the equivalent stress is judged to be in the warning range, further analysis is performed: if the mechanical special inspection confirms that the gear meshing is abnormal, the mechanical stress tensor weight coefficient is increased; if the thermal stress fault inspection finds that the oil circuit is abnormal, the thermal stress tensor weight coefficient is increased and the acoustic stress weight coefficient is reduced; if the acoustic defect is located to a surface crack, the acoustic stress tensor weight coefficient is increased, and the thermal stress weight coefficient is frozen; when entering the critical state of dangerous failure, the cross-coupling weight is reset to zero, and the basic field weight coefficient is retained.

[0014] As a preferred solution of the comprehensive performance detection method applied to the reducer described in the present invention, the internal stress field distribution is re-analyzed and verified according to the corrected digital twin model, including the following steps: after each weight adjustment, the fused stress tensor is regenerated and the equivalent stress is calculated; the stress field distribution before and after correction is compared: if the area of ​​the abnormal region is reduced by more than the observable degree, the weight correction is determined to be effective; if the stress concentration phenomenon is not alleviated, the multi-physical field sensor collaborative re-inspection is triggered; when three consecutive corrections fail to achieve the expected effect, the full parameter recalibration of the digital twin model is started.

[0015] On the second aspect, in order to further solve the above-mentioned technical problems, the embodiment of the present invention provides a comprehensive performance testing system for a reducer, which includes: a data acquisition module for acquiring the first comprehensive data of the reducer and preprocessing the first comprehensive data; a model construction module for constructing a digital twin model based on the preprocessed first comprehensive data, and analyzing the internal stress field distribution based on the digital twin model; a weight correction module for adaptively correcting the weight coefficient of the digital twin model based on the analysis results of the stress field distribution; a model verification module for re-analyzing the internal stress field distribution according to the corrected digital twin model and performing verification.

[0016] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the comprehensive performance detection method applied to a reducer as described in the first aspect of the present invention is implemented.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the comprehensive performance detection method applied to a reducer as described in the first aspect of the present invention is implemented.

[0018] The beneficial effects of the present invention are as follows: the present invention constructs a multi-field coupled digital twin model that integrates mechanical stress tensors, thermal stress tensors and acoustic stress tensors, and combines equivalent stress graded warning and weight coefficient adaptive correction mechanism to achieve accurate quantitative analysis and dynamic adaptation of the internal stress field of the reducer, breaking through the one-sidedness and static model limitations of traditional single physical field detection, and effectively solving the problems of multi-field data isolation, model staticization, and fault judgment experience in the existing technology, providing industrial transmission equipment with a full-process intelligent comprehensive performance detection solution from data acquisition, model analysis to maintenance decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort. Among them: Figure 1 This is a flow chart for implementing the present invention in Example 1.

[0020] Figure 2 This is a dynamic adjustment diagram of the digital twin model in Example 1. DETAILED DESCRIPTION

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0022] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. 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.

[0023] Secondly, the term "one embodiment" or "embodiment" 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 one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0024] Example 1 Reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a comprehensive performance detection method for a reducer, comprising the following steps: S1: Acquire first comprehensive data of the reducer and preprocess the first comprehensive data.

[0025] Furthermore, the first comprehensive data includes mechanical characteristic data, thermal characteristic data, and acoustic characteristic data.

[0026] Furthermore, the mechanical characteristic data includes torque, vibration, and rotational speed.

[0027] Furthermore, the thermal characteristic data includes temperature, gradient, and oil parameters.

[0028] Furthermore, the acoustic characteristic data includes acoustic emission and noise spectrum.

[0029] Specifically, the mechanical characteristic data is obtained through a torque sensor, a vibration sensor, and a photoelectric encoder.

[0030] Specifically, the thermal characteristic data is acquired through a temperature sensor, a thermal mass flow sensor, and a vibration viscosity sensor.

[0031] Specifically, the acoustic characteristic data is acquired through a broadband acoustic emission sensor and a microphone.

[0032] It should be noted that the preprocessing of mechanical characteristic data includes outlier removal, hardware accelerated filtering, noise reduction, pulse edge detection and time-frequency domain feature extraction; the preprocessing of thermal characteristic data includes multi-point temperature synchronization alignment, temperature drift compensation, spatial gradient calculation, viscosity temperature calculation, flow rate fluctuation filtering and multi-parameter correlation verification; the preprocessing of acoustic characteristic data includes feature parameter extraction, noise reduction and spectrum correction.

[0033] Preferably, by integrating mechanical, thermal and acoustic characteristic data and implementing targeted preprocessing, the one-sidedness problem of traditional single physical field detection is solved, the data integrity and reliability are improved, and the foundation is laid for multi-field coupling analysis.

[0034] For example, when an offshore wind turbine gearbox is running, the system synchronously collects mechanical data such as torque fluctuations, high-frequency vibrations and speed changes through torque sensors, vibration sensors and photoelectric encoders, and obtains thermal data such as bearing seat temperature rise, lubricating oil flow rate drop and viscosity reduction with the help of temperature sensor arrays, thermal flow sensors and viscosity sensors. It also uses broadband acoustic emission sensors and microphones to capture high-frequency sound energy surges and abnormal noise. After hardware-accelerated filtering to remove power frequency interference, multi-point temperature synchronization alignment to eliminate time delay deviation and wavelet noise reduction to improve the signal-to-noise ratio, the system extracts key features such as sudden increase in vibration intensity value, abnormal temperature gradient and increased acoustic emission event rate, providing reliable data support for subsequent modeling.

[0035] S2: Construct a digital twin model based on the preprocessed first comprehensive data, and analyze the internal stress field distribution based on the digital twin model.

[0036] Preferably, the specific steps of constructing the digital twin model based on the preprocessed first comprehensive data are as follows: By introducing the mechanical stress tensor, the torque, vibration, and speed mechanical characteristic data are converted into the dynamic stress distribution inside the structure. The specific formula is as follows:

[0037] Where, is the mechanical stress tensor, reflecting the dynamic stress distribution of the reducer structure; is the elastic matrix, which is used to calculate the stress-strain relationship; is the displacement vector, which is used to calculate the strain tensor; is the density, an intrinsic material property, used for mass correction of the dynamic stress integral term; is the body density, which comes from the load case setting and affects the static component of the stress field.

[0038] It should be explained that the role of the mechanical stress tensor is to convert mechanical characteristic data such as torque and vibration into dynamic stress distribution inside the reducer structure through the coupling of the elastic matrix and the displacement vector, thereby quantifying the structural stress state caused by the mechanical load and providing a data basis for the dynamic force analysis of gear meshing and bearing operation.

[0039] By introducing the thermal stress tensor, the temperature field, thermal gradient, and oil parameter thermal characteristic data are converted into stress distribution caused by thermal expansion mismatch. The specific formula is as follows:

[0040] Where, is the thermal stress tensor, reflecting the stress distribution caused by thermal deformation; is the elastic modulus, which determines the magnitude of thermal stress; is the coefficient of thermal expansion, which characterizes the rate of dimensional change under temperature change; is the temperature field, reflecting the internal thermal state of the reducer; is the reference temperature, used to calculate the temperature deviation; is thermal conductivity, which affects the heat conduction rate; is the internal heat source density, reflecting the energy loss and heat production; is the specific heat capacity, which is used in energy calculations of the heat conduction equation.

[0041] It should be noted that the role of the thermal stress tensor is based on the coupling relationship between the thermal expansion coefficient and the temperature field. It converts thermal characteristic data such as temperature gradient and oil parameters into stress distribution caused by material thermal expansion mismatch, which is used to characterize the influence of thermal deformation on structural stress and realize quantitative analysis of thermal-mechanical coupling effect.

[0042] By introducing the acoustic stress tensor, the acoustic emission signal and noise spectrum acoustic characteristic data are inverted into the stress characteristics of internal microcracks and stress concentration defects. The specific formula is as follows:

[0043] Where, is the acoustic stress tensor, used to detect internal stress concentrations and defects; is the acoustoelastic tensor, which represents the coupling relationship between sound velocity and stress; is the change in sound velocity, reflecting the change in internal stress state; is the reference sound speed; is the volume coupling coefficient, which characterizes the effect of displacement divergence on the sound velocity; is the sound pressure, reflecting the noise spectrum generated by structural vibration; is the speed of sound.

[0044] It should be explained that the role of the acoustic stress tensor is to utilize the relationship between the acoustic elastic tensor and the change in sound velocity to invert acoustic characteristic data such as acoustic emission signals and noise spectra into stress characteristics of defects such as internal microcracks and stress concentration, and realize stress field mapping and positioning of hidden defects through the acoustic-mechanical coupling mechanism.

[0045] The digital twin model is constructed by integrating the mechanical stress tensor, thermal stress tensor, and acoustic stress tensor. The specific formula is as follows:

[0046] Where, To integrate stress tensors and comprehensively reflect the stress distribution of multi-physics field coupling; 、 、 is the field weight coefficient, which is used to adjust the influence ratio of different physical fields; 、 、 is the cross-coupling weight, which characterizes the nonlinear interaction between physical fields; is the reference stress, used for dimensional unification of cross-coupling terms; is the inner product of the stress tensor, reflecting the coupling strength between mechanical stress and thermal stress; is the inner product of the stress tensor, reflecting the coupling strength between mechanical stress and acoustic stress; is the inner product of the stress tensor, reflecting the coupling strength between thermal stress and acoustic stress.

[0047] Specifically, the specific content of the fusion stress tensor is as follows: Convert the fused stress tensor into equivalent stress using the following formula:

[0048] Where, is the scalar equivalent stress; 、 、 for The principal stress components of When the equivalent stress is less than the first threshold, it means that the reducer is in the "healthy operating range", the material has not entered the damage stage, and the stress distribution of each component is within the design safety margin. It enters the "routine inspection mode" and collects and stores stress data every hour for equipment health trend analysis. It automatically generates a "health status report" and marks the stress distribution cloud map of the gear meshing area and bearing seat.

[0049] When the equivalent stress is greater than the first threshold and less than the second threshold, the reducer enters the "stress abnormality warning range" and the material has undergone plastic deformation. If it continues to operate, fatigue damage will be accelerated. The operation interface highlights the stress abnormality component and pushes the "load fluctuation warning". Check the motor speed, reduce the motor output power, start auxiliary cooling, and conduct further analysis: For special inspections of machinery: Use a vibration analyzer to collect frequency band signals. If the effective value of the characteristic frequency component is significantly higher than the historical baseline and the time domain waveform shows periodic shocks, it is determined that the gear meshing is abnormal. The following operations need to be performed: Measure the tooth side clearance. If the clearance exceeds the standard range, adjust the bearing seat to calibrate the clearance.

[0050] Disassemble the gearbox and inspect the tooth surfaces. If pitting or wear reaches an observable level, replace the gear pair immediately.

[0051] For thermal stress troubleshooting: Use an infrared thermal imager to scan the cabinet surface. If the temperature difference between a certain area and the average temperature exceeds the normal range, and the calculated thermal stress value increases significantly, then: Check the lubricating oil flow rate. If the flow rate is lower than the rated value, disassemble the oil circuit and check the filter. Replace the filter element when the resistance exceeds the preset threshold.

[0052] Collect oil samples for viscosity testing. If the viscosity drops beyond the allowable range, immediately replace the oil and clean the oil tank.

[0053] For acoustic characteristic defect location: Signals are collected through a broadband acoustic emission sensor array. If the acoustic stress contribution in a certain area exceeds the set proportion of the total stress and the energy proportion in a specific frequency band is abnormal, then: The time difference positioning method is used to calculate the coordinates of the sound source. When the positioning accuracy meets the requirements, non-destructive testing is performed on the area. If surface cracks are found, laser repair is used.

[0054] Analyze the sound pressure spectrum. If the amplitude at the gear meshing frequency exceeds the background noise to a certain extent, check the gear meshing line. If there is an offset load, regrind the tooth surface.

[0055] When the equivalent stress is greater than the second threshold, it means that the reducer has entered the "critical state of dangerous failure", the material has undergone plastic deformation, and the geometric dimensions of the components have undergone irreversible changes, which may cause tooth breakage and bearing locking at any time.

[0056] Preferably, three types of stress tensors, mechanical, thermal, and acoustic, are introduced to construct a multi-field coupling model, breaking through the limitations of traditional static modeling and realizing dynamic quantitative analysis of the internal stress field of the reducer and accurate inversion of early defects.

[0057] For example, when the rolling force of the main reducer of a hot rolling production line suddenly changes, the digital twin model converts the measured torque and vibration into tooth surface contact stress and tooth root bending stress through the mechanical stress tensor, calculates the additional stress caused by thermal expansion of the bearing seat based on the thermal stress tensor combined with the temperature field and thermal gradient, and uses the acoustic stress tensor to invert the acoustic emission signal to identify the stress concentration of microcracks on the edge of the gear; after fusing the three types of tensors, the calculated equivalent stress exceeds the yield strength of the material. Based on this, the system warns of the risk of plastic deformation and guides the adjustment of the rolling force parameters to avoid tooth surface bonding failure.

[0058] S3: Adaptively modify the weight coefficient of the digital twin model based on the analysis results of the stress field distribution.

[0059] Preferably, the specific steps of adaptively correcting the weight coefficient of the digital twin model based on the analysis results of the stress field distribution are as follows: When the equivalent stress is judged to be in the healthy operating range, all weight coefficients are kept unchanged, and only the stress distribution cloud diagrams of the gear meshing area and the bearing seat are recorded.

[0060] When the equivalent stress is judged to be in the warning range, further analysis is performed: If the mechanical special inspection confirms abnormal gear meshing, the mechanical stress tensor weight coefficient will be increased.

[0061] If thermal stress fault troubleshooting reveals oil circuit anomalies, increase the thermal stress tensor weight coefficient and reduce the acoustic stress weight coefficient.

[0062] If the acoustic defect is located on a surface crack, the acoustic stress tensor weight coefficient is increased and the thermal stress weight coefficient is frozen.

[0063] When entering the critical state of dangerous failure, all cross-coupling weights are reset to zero and only the basic field weight coefficients are retained.

[0064] Preferably, the model weight coefficient is dynamically adjusted based on the fault tracing results to solve the problem of fixed weights in traditional digital twin models, and significantly improve the model's dynamic adaptability to equipment status changes and fault diagnosis accuracy.

[0065] For example, after two years of operation, the equivalent stress of a port crane reducer entered the warning range. After the system determined gear wear through vibration spectrum analysis, eliminated oil circuit faults through infrared thermal imaging, and confirmed tooth surface cracks through acoustic emission positioning, it adaptively increased the weights of mechanical stress and acoustic stress tensors, maintained the thermal stress weight and increased the mechanical-acoustic coupling weight; the corrected model accurately predicted the stress concentration area of ​​the tooth root, provided data support for laser repair of the tooth surface, and avoided the expansion of the fault.

[0066] S4: Reanalyze the internal stress field distribution based on the revised digital twin model and perform verification.

[0067] Preferably, reanalyzing the internal stress field distribution and verifying it based on the revised digital twin model includes the following steps: After each weight adjustment, the fused stress tensor is regenerated and the equivalent stress is calculated.

[0068] Compare the stress field distribution before and after correction: If the area of ​​the abnormal region is reduced beyond the observable level, the weight correction is determined to be effective.

[0069] If the stress concentration phenomenon is not alleviated, the multi-physics field sensor collaborative re-inspection will be triggered.

[0070] When three consecutive corrections fail to achieve the expected results, full parameter recalibration of the digital twin model is initiated.

[0071] Preferably, a quantitative closed-loop mechanism of "analysis-correction-verification" is established to ensure that the model optimization effect can be evaluated, fault re-inspection can be coordinated, and parameter calibration can be traced, forming a complete technical chain from detection to maintenance.

[0072] For example, after three weight adjustments, the stress of the main reducer of a cement plant did not reach the expected reduction. The system compared the stress cloud map and found that the abnormal area was not reduced enough, triggering a collaborative re-inspection of multiple sensors including vibration, acoustic emission and infrared thermal imaging, and located the fault of excessive bearing clearance. After recalibrating the material elastic modulus and thermal expansion coefficient, the stress calculation error was significantly reduced, and the area of ​​the abnormal area was reduced by more than 40%, effectively guiding the decision on bearing replacement.

[0073] In summary, the present invention constructs a multi-field coupled digital twin model that integrates mechanical stress tensors, thermal stress tensors and acoustic stress tensors, and combines equivalent stress graded warning and weight coefficient adaptive correction mechanism to achieve accurate quantitative analysis and dynamic adaptation of the internal stress field of the reducer, breaking through the one-sidedness and static model limitations of traditional single physical field detection, and effectively solving the problems of multi-field data isolation, model staticization, and fault judgment experience in the existing technology, providing industrial transmission equipment with a full-process intelligent comprehensive performance detection solution from data acquisition, model analysis to maintenance decision-making.

[0074] Example 2 is an embodiment of the present invention, which provides a comprehensive performance testing system for a reducer, including: a data acquisition module, used to obtain the first comprehensive data of the reducer and preprocess the first comprehensive data; a model construction module, used to construct a digital twin model based on the preprocessed first comprehensive data, and analyze the internal stress field distribution based on the digital twin model; a weight correction module, used to adaptively correct the weight coefficient of the digital twin model based on the analysis results of the stress field distribution; a model verification module, used to re-analyze the internal stress field distribution according to the corrected digital twin model and perform verification.

[0075] Example 3 is an embodiment of the present invention, which is different from the previous embodiment in that: If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0076] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0077] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, and then editing, interpreting, or processing in another suitable manner as necessary, and then storing it in a computer memory.

[0078] It should be understood that various components of the present invention may be implemented using hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof may be used: a discrete logic circuit having logic gate circuits for implementing logic functions on data signals, an application-specific integrated circuit having suitable combinational logic gate circuits, a programmable gate array (PGA), a field-programmable gate array (FPGA), etc.

[0079] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A comprehensive performance testing method for a reducer, characterized in that: include: Acquiring first comprehensive data of the reducer and preprocessing the first comprehensive data; Building a digital twin model based on the preprocessed first comprehensive data, and analyzing internal stress field distribution based on the digital twin model; Adaptively modify the weight coefficient of the digital twin model based on the analysis results of the stress field distribution; The internal stress field distribution is reanalyzed and verified based on the revised digital twin model.

2. The comprehensive performance detection method for a reducer according to claim 1, characterized in that: The first comprehensive data includes mechanical characteristic data, thermal characteristic data and acoustic characteristic data; The mechanical characteristic data includes torque, vibration and rotation speed; The thermal characteristic data includes temperature, gradient and oil parameters; The acoustic characteristic data includes acoustic emission and noise spectrum; The mechanical characteristic data is obtained through a torque sensor, a vibration sensor and a photoelectric encoder; The thermal characteristic data is obtained by a temperature sensor, a thermal mass flow sensor and a vibration viscosity sensor; The acoustic characteristic data is acquired through a broadband acoustic emission sensor and a microphone.

3. The comprehensive performance detection method for a reducer according to claim 2, characterized in that: The specific steps for building a digital twin model based on the preprocessed first comprehensive data are as follows: By introducing the mechanical stress tensor, the torque, vibration and speed mechanical characteristic data are converted into the dynamic stress distribution inside the structure; By introducing the thermal stress tensor, the temperature field, thermal gradient, and oil parameter thermal characteristic data are converted into stress distribution caused by thermal expansion mismatch; By introducing the acoustic stress tensor, the acoustic emission signal and noise spectrum acoustic characteristic data are inverted into the stress characteristics of internal microcracks and stress concentration defects; A digital twin model is constructed by integrating mechanical stress tensor, thermal stress tensor and acoustic stress tensor.

4. The comprehensive performance detection method for a reducer according to claim 3, wherein: The specific formula of the digital twin model is as follows:

5. In the formula, is the fusion stress tensor; 、 、 is the field weight coefficient; is the mechanical stress tensor; is the thermal stress tensor; is the acoustic stress tensor; 、 、 is the cross-coupling weight; is the reference stress; is the inner product of the stress tensor; is the inner product of the stress tensor; is the inner product of the stress tensor.

6. The comprehensive performance detection method for a reducer according to claim 4, characterized in that: The specific content of the fusion stress tensor is as follows: Convert the fused stress tensor into equivalent stress; When the equivalent stress is less than the first threshold, it means that the reducer is in the "healthy operating range", the material has not entered the damage stage, and the stress distribution of each component is within the design safety margin; When the equivalent stress is greater than the first threshold and less than the second threshold, the reducer enters the "stress abnormality warning zone" and the material has undergone plastic deformation. Continuing operation will accelerate fatigue damage and reduce motor output power. Auxiliary cooling is initiated and further analysis is performed. When the equivalent stress is greater than the second threshold, it means that the reducer has entered a "critical state of dangerous failure", the material has undergone plastic deformation, and the geometric dimensions of the components have undergone irreversible changes.

7. The comprehensive performance detection method for a reducer according to claim 4, characterized in that: The specific steps for adaptively correcting the weight coefficient of the digital twin model based on the analysis results of the stress field distribution are as follows: When the equivalent stress is judged to be in the healthy operating range, all weight coefficients are kept unchanged and only the stress distribution cloud diagram of the gear meshing area and the bearing seat is recorded; When the equivalent stress is judged to be in the warning range, further analysis is performed: If the mechanical special inspection confirms abnormal gear meshing, the mechanical stress tensor weight coefficient will be increased; If thermal stress troubleshooting reveals oil circuit anomalies, increase the thermal stress tensor weight coefficient and reduce the acoustic stress weight coefficient; If the acoustic defect is located at a surface crack, the acoustic stress tensor weight coefficient is increased and the thermal stress weight coefficient is frozen; When entering the critical state of dangerous failure, the cross-coupling weight is reset to zero and the basic field weight coefficient is retained.

8. The comprehensive performance detection method for a reducer according to claim 1, wherein: Reanalyzing and verifying the internal stress field distribution based on the revised digital twin model includes the following steps: After each weight adjustment, the fused stress tensor is regenerated and the equivalent stress is calculated; Compare the stress field distribution before and after correction: If the area of ​​the abnormal region is reduced beyond the observable level, the weight correction is determined to be effective; If the stress concentration phenomenon is not alleviated, trigger the multi-physics field sensor collaborative re-inspection; When three consecutive corrections fail to achieve the expected results, full parameter recalibration of the digital twin model is initiated.

9. A comprehensive performance testing system for a reducer, based on the comprehensive performance testing method for a reducer according to any one of claims 1 to 7, characterized in that: include, A data acquisition module, configured to acquire first comprehensive data of the reducer and preprocess the first comprehensive data; a model building module, configured to build a digital twin model based on the preprocessed first comprehensive data, and analyze the internal stress field distribution based on the digital twin model; The weight correction module is used to adaptively correct the weight coefficient of the digital twin model based on the analysis results of the stress field distribution; The model verification module is used to reanalyze the internal stress field distribution and perform verification based on the revised digital twin model.

10. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the comprehensive performance detection method applied to the reducer as described in any one of claims 1 to 7 are implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the comprehensive performance detection method applied to a reducer as described in any one of claims 1 to 7 are implemented.

Images