Planetary mechanism needle bearing operation quality evaluation method

Abstract

The invention belongs to the technical field of planetary mechanism needle bearing operation quality evaluation, and particularly relates to a planetary mechanism needle bearing operation quality evaluation method, which comprises the following steps: by taking an envelope entropy as a fitness function, optimizing the maximum value of a parameter alpha of an SVMD method through an RBMO algorithm, and decomposing a vibration signal into a plurality of IMF components; calculating the correlation between the fault information of each IMF component and the original signal, selecting the optimal IMF component with high correlation for reconstruction, and eliminating noise interference; optimizing the filter length L of the MOMEDA method by using an RBMO algorithm, and enhancing the impact component in the reconstructed signal by using the MOMEDA method; and carrying out envelope analysis on the deconvolved signal to obtain a fault frequency corresponding to a spectral line with an obvious peak value in an envelope spectrum so as to realize fault diagnosis of the needle bearing. According to the signal processing method based on RBMO-SVMD-MOMEDA, signal features can be better stored, subjective interference and uncertainty possibly introduced in the parameter adjusting process are effectively avoided, and accurate extraction and efficient recognition of fault features are successfully achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of planetary mechanism needle roller bearing operation quality assessment, and in particular relates to a planetary mechanism needle roller bearing operation quality assessment method. Background Art

[0002] Needle roller bearings are a crucial carrier of motion and load transmission in planetary mechanisms. In a planetary mechanism, the planet gears are connected to the ring gear on the outside, the sun gear on the inside, and the inner bore is connected to the planet carrier pin via needle roller bearings. Needle roller bearings are the carrier of motion and load transmission for the planetary gears. To achieve medium to high power transmission in a confined space, needle roller bearings without inner and outer rings are selected. The outer cylindrical surface of the planet gear shaft serves as the inner bearing ring, while the inner cylindrical surface of the planet gear serves as the outer bearing ring, significantly improving the power density of the planetary transmission. Needle roller bearings offer advantages such as high speed, high reliability, low friction, low vibration, and low noise. As the speed of planetary gear systems increases and operating conditions become more complex, the reliability requirements for specialized radial needle roller and cage assemblies are becoming increasingly stringent. Therefore, evaluating the operating quality of needle roller bearings has become a critical engineering issue.

[0003] Needle roller bearings, as an indispensable core component of the planetary mechanism of high-power transmission systems, carry out multiple functions such as support, retention, and precise transmission. Their operating status is directly related to the performance and service life of the entire mechanical system. Signal processing technology is used to analyze the characteristics of vibration signals and has been widely used in the field of rotating machinery fault diagnosis. However, bearing vibration signals are affected by complex transmission paths and noise interference. The fault characteristics are weak and easily drowned out by noise, which increases the difficulty of fault feature extraction. There is an urgent need to conduct research on operation quality assessment methods to improve the efficiency and quality of bearing design and manufacturing processes, improve the bearing operation quality assessment system, and form relevant specifications to complete the closed loop of design and process collaboration, providing important support for product development and manufacturing.

[0004] Signal decomposition algorithms provide a powerful tool for analyzing complex vibration signals. By decomposing these nonstationary, nonlinear signals into a series of quasi-orthogonal modal signals with clear physical meaning, a deeper understanding of the signal's intrinsic characteristics and dynamic behavior can be achieved. Empirical Mode Decomposition (EMD), a typical signal decomposition algorithm, is widely used in rotating machinery fault diagnosis. However, the EMD algorithm is not robust to noise and is prone to modal aliasing. Variational Mode Decomposition (VMD) addresses the shortcomings of the EMD algorithm, effectively enhancing noise robustness and eliminating modal aliasing. However, it still requires the pre-specified number of modes, K, and overestimating or underestimating the number of modes can lead to erroneous extraction of fault features. Although a variety of quality assessment methods exist, they all have some drawbacks, and the identification and assessment of fault signals in the presence of strong noise interference is not very accurate. Summary of the Invention

[0005] (1) Technical issues to be resolved

[0006] The technical problem to be solved by the present invention is: how to solve the problem that the fault characteristics of needle roller bearings are difficult to effectively extract and identify under strong background noise, and realize the identification of needle roller bearing fault signals under strong noise background.

[0007] (2) Technical solution

[0008] To solve the above technical problems, the present invention provides a method for evaluating the running quality of a needle roller bearing of a planetary mechanism, which comprises the following steps:

[0009] Step 1: Using envelope entropy as the fitness function, the RBMO algorithm is used to optimize the maximum value of the parameter α of the SVMD method and decompose the vibration signal into several IMF components;

[0010] Step 2: Calculate the correlation between the fault information of each IMF component and the original signal, select the optimal IMF component with high correlation for reconstruction, and eliminate noise interference;

[0011] Step 3: Use the RBMO algorithm to optimize the filter length L of the MOMEDA method, and enhance the impulse component in the reconstructed signal through the MOMEDA method;

[0012] Step 4: Perform envelope analysis on the deconvolved signal to obtain the fault frequency corresponding to the spectrum line with obvious peak in the envelope spectrum, thereby realizing fault diagnosis of the needle roller bearing.

[0013] Among them, the planetary mechanism needle roller bearing operation quality assessment method is based on the RBMO-SVMD-MOMEDA signal processing method, which can better preserve signal characteristics, reduce information loss, and effectively avoid subjective interference and uncertainty that may be introduced in the parameter adjustment process, ensuring the objectivity and accuracy of parameter setting, and successfully realizing the accurate extraction and efficient identification of fault characteristics.

[0014] In step 2, the bearing rotation frequency f can be observed from the envelope spectrum of the reconstructed signal. r , inner ring fault frequency f i and its frequency multiples (2f i 、3f i ), indicating that the signal reconstructed by the planetary mechanism needle roller bearing operation quality assessment method can effectively remove the noise components in the signal and reveal the key frequency components hidden in the complex vibration signal.

[0015] Among them, in step 3, the RBMO algorithm accurately locked the optimal fitness value after only two iterations. The results show that compared with other optimization algorithms, the RBMO algorithm has outstanding advantages in performance such as convergence speed and stability.

[0016] Among them, in step 4, the deconvolution time domain waveform shows obvious periodic impact components, and the frequency modulation and frequency multiplication attenuation phenomena in the envelope spectrum are improved, and the inner ring fault frequency f i and its frequency multiples (2~8f i ) becomes more obvious, from which it can be determined that the bearing has an inner ring failure.

[0017] Among them, in the planetary mechanism needle roller bearing operation quality assessment method, compared with other optimization algorithms, the RBMO algorithm shows excellent performance in optimization accuracy and convergence speed. Through the optimization of the RBMO algorithm, SVMD and MOMEDA can adaptively find the optimal parameter configuration, thereby effectively avoiding the subjective interference and uncertainty that may be introduced in the process of manual parameter adjustment, and ensuring the objectivity and accuracy of parameter setting.

[0018] Among them, compared with the SVMD-MOMEDA method without parameter optimization and the FMD-MCKD method, the SVMD-MOMEDA method with parameter optimization can effectively extract the bearing inner ring fault frequency and its frequency multiplication components (2nd to 6th frequency multiplication) under -10dB noise interference, successfully realizing the accurate extraction and efficient identification of fault characteristics.

[0019] Among them, the planetary mechanism needle roller bearing operation quality assessment method optimizes the SVMD and MOMEDA key parameters by using the RBMO algorithm, which can effectively extract the fault characteristic signal of the needle roller bearing from the complex vibration signal, and solve the problem of increased difficulty in fault identification and diagnosis caused by noise interference in the collected bearing vibration signal.

[0020] (3) Beneficial effects

[0021] In actual operating conditions, the collected vibration signals of needle roller bearings are subject to interference, making operational quality assessment more difficult. To effectively extract and identify needle roller bearing fault characteristics in the presence of strong background noise, this paper proposes optimizing the key parameters of SVMD and MOMEDA using the RBMO algorithm, targeting minimum envelope entropy. By performing envelope spectrum analysis on the fault signal, needle roller bearing fault diagnosis in this noisy environment is achieved. This method enables rapid and accurate decision-making for early-stage needle roller bearing fault diagnosis, and has important practical implications for needle roller bearing fault diagnosis.

[0022] In view of the defects of various signal decomposition algorithms, the present invention proposes a method for evaluating the operating quality of needle roller bearings in planetary mechanisms, which solves the problem that the fault characteristics of needle roller bearings are difficult to effectively extract and identify under strong background noise, and realizes the identification of needle roller bearing fault signals under strong noise background.

[0023] The effectiveness of the present invention is analyzed through simulation signals. A simulation signal of the inner ring of a needle roller bearing is constructed and Gaussian white noise is added to verify the effectiveness of the present invention. The simulation signal model of the inner ring fault is as follows:

[0024]

[0025] Where, the number of impulses in the fault signal is z = 75; A k is the amplitude of the kth impact; A0 = 0.4; rotation frequency f r =20Hz; attenuation coefficient a=600; resonance frequency f n =4000Hz; inner ring fault characteristic frequency f i =1 / T=120Hz; sampling frequency f s =13000Hz; n(t) represents Gaussian white noise with a signal-to-noise ratio of -10dB. The time domain waveform and spectrum of the simulated signal are shown in the attached figure. Figure 2-1 and Figure 2-2 As shown. Figure 2-1 and Figure 2-2 As can be seen from the time-domain waveform of the simulated signal, the fault impulse component is severely interfered with by strong background noise, and the fault pulse sequence in the signal is almost completely submerged by the noise. Observing its envelope spectrum, no effective fault feature information can be identified. The method proposed in this invention is used to process the simulated signal to extract the fault feature frequency.

[0026] The present invention includes:

[0027] Step 1: Using envelope entropy as the fitness function, the RBMO algorithm is used to optimize the maximum value of the SVMD parameter α to obtain the optimal value of the parameter.

[0028] Step 2: Based on the correlation coefficient of each IMF component, select the optimal component for reconstruction. The time domain waveform and envelope spectrum of the reconstructed signal are shown in the attached figure. Figure 3-1 and Figure 3-2 shown.

[0029] From the envelope spectrum of the reconstructed signal, it can be clearly observed that the bearing rotation frequency f r , inner ring fault frequency f i and its frequency multiples (2f i 、3f i ), indicating that the signal reconstructed by the method of the present invention can effectively remove the noise components in the signal and reveal the key frequency components hidden in the complex vibration signal.

[0030] Step 3: Use the RBMO algorithm to optimize the filter length L of MOMEDA, and enhance the impulse component in the reconstructed signal through the MOMEDA method;

[0031] To prove the superiority of RBMO in parameter optimization, it is compared with three common methods: Grey Wolf Optimizer (GWO), Particle Swarm Optimization (PSO) and Whale Optimization Algorithm (WOA). The population size is set to 10 and the number of iterations is set to 20. After 10 independent experiments, the average optimal parameter values and fitness values of each model are shown in the attached figure. Figure 12 One of the fitness iteration processes is shown in the attached Figure 4 shown.

[0032] From the attached Figure 4 It can be seen that the RBMO algorithm accurately locked the optimal fitness value after only two iterations. The results show that compared with other optimization algorithms, the RBMO algorithm has excellent advantages in performance such as convergence speed and stability.

[0033] Due to the attached Figure 3-2The frequency modulation and frequency multiplication attenuation in the envelope spectrum will affect the accuracy of diagnosis. The parameter optimization MOMEDA method is further used to enhance the fault impact component. Based on the envelope spectrum of the reconstructed signal, it can be preliminarily determined that the signal may have an inner ring defect. The filter period T is determined to be [107,109]. The RBMO algorithm is used to optimize the filter length L, and the result is L = 1328. The time domain waveform and spectrum after deconvolution are shown in the attached figure. Figure 5-1 and Figure 5-2 shown.

[0034] Step 4: Perform envelope analysis on the deconvolved signal to obtain the fault frequency corresponding to the spectrum line with obvious peak in the envelope spectrum, thereby realizing fault diagnosis of the needle roller bearing.

[0035] From the attached Figure 5-1 It can be seen that the deconvolution time domain waveform shows obvious periodic impact components, and the frequency modulation and frequency multiplication attenuation phenomena in the envelope spectrum are improved. The inner ring fault frequency f i and its frequency multiples (2~8f i ) becomes more obvious, from which it can be determined that the bearing has an inner ring failure.

[0036] The strong interference fault signal experiment verifies the effectiveness of the fault detection method in the present invention. The actual test bench structure is shown in the attached figure. Figure 6 In the experiment, the motor speed is 1797r / min, the sampling frequency is 12kHz, and the inner ring of the bearing is machined by electrospark machining to produce a fault defect with a diameter of 0.5334mm and a depth of 0.2794mm. The calculated bearing rotation frequency is f r =29.95Hz, the characteristic frequency of the inner race fault is f i =162.2Hz. To verify the effectiveness of the method of the present invention under strong noise interference, -10dB Gaussian white noise is added to the original data to simulate the signal quality under actual working conditions. Figure 7-1 and Figure 7-2 The figure shows the time domain waveform and envelope spectrum of the vibration signal containing -10dB Gaussian white noise.

[0037] Step 1: Using envelope entropy as the fitness function, the RBMO algorithm is used to optimize the SVMD parameter α and decompose the vibration signal into several IMF components.

[0038] The experimental signal with -10dB Gaussian white noise was adaptively decomposed using the parameter-optimized SVMD method (ISVMD). Figure 8 The correlation index Corr of each modal component and the original signal is shown in the attached Figure 9 shown.

[0039] Step 2: Calculate the correlation between each component fault information and the original signal, select the optimal component with high correlation for reconstruction, and eliminate noise interference;

[0040] IMF components 4 and 5 with high correlation coefficients are selected for reconstruction. The time domain waveform and spectrum of the reconstructed signal are shown in the attached figure. Figure 10-1 and Figure 10-2 As shown. Figure 10-2 It can be seen from the envelope spectrum of the reconstructed signal that the ISVMD method effectively eliminates most of the noise interference, and the characteristic frequency f that is similar to the bearing rotation frequency can be observed in the spectrum diagram. r (30.01Hz), the approximate characteristic frequency f of the bearing inner ring fault i (161.87Hz) and its frequency components (2~3f i However, the frequency modulation phenomenon in the figure is serious, which can easily affect the diagnosis results. Therefore, the parameter optimization MOMEDA method is further used to enhance the fault characteristic frequency.

[0041] Step 3: Use the RBMO algorithm to optimize the filter length L of MOMEDA, and enhance the impulse component in the reconstructed signal through the MOMEDA method;

[0042] By the attached Figure 10-2 It can be preliminarily determined that the bearing is damaged. Therefore, the filter period T is set to [73,74]. The RBMO algorithm is used to iterate 20 times to optimize the filter length L. The optimal filter length is 3734. The time domain waveform and spectrum after deconvolution are shown in the attached figure. Figure 11-1 and Figure 11-2 shown.

[0043] Step 4: Perform envelope analysis on the deconvolved signal to obtain the fault frequency corresponding to the spectrum line with obvious peak in the envelope spectrum, thereby realizing fault diagnosis of the needle roller bearing.

[0044] From the attached Figure 11-1 It can be seen from the time domain waveform that the signal impact component is significantly enhanced. Figure 11-2 There is little noise interference in the envelope spectrum, and the component f that is close to the bearing inner ring fault frequency can be observed very clearly. i (162.60Hz) and its multiples (2~6f i ), indicating that the proposed RBMO-SVMD-MOMEDA method can effectively extract the fault characteristic frequency of the bearing from the vibration signal under strong background noise interference. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is the flow chart of bearing operation quality assessment based on this method;

[0046] Figure 2-1 and Figure 2-2 It is the time domain waveform and envelope spectrum of the simulation signal;

[0047] Figure 3-1 and Figure 3-2 To reconstruct the signal time domain waveform and envelope spectrum;

[0048] Figure 4 Iterative curve diagram of fitness value for different optimization algorithms;

[0049] Figure 5-1 and Figure 5-2 It is the time domain waveform and envelope spectrum of the deconvolution signal;

[0050] Figure 6 A test bench for simulating needle roller bearing failures;

[0051] Figure 7-1 and Figure 7-2 It is the time domain waveform and envelope spectrum of the experimental signal;

[0052] Figure 8 It is the IMF component diagram of ISVMD decomposition;

[0053] Figure 9 is the correlation index of each modal component;

[0054] Figure 10-1 and Figure 10-2 To reconstruct the signal time domain waveform and envelope spectrum;

[0055] Figure 11-1 and Figure 11-2 It is the time domain waveform and envelope spectrum of the deconvolution signal;

[0056] Figure 12 Optimize results for different models. DETAILED DESCRIPTION

[0057] In order to make the purpose, content, and advantages of the present invention more clear, the specific implementation methods of the present invention are further described in detail below with reference to the accompanying drawings and examples.

[0058] In order to more accurately identify the fault characteristics of bearings, the present invention discloses a method for evaluating the operation quality of planetary mechanism needle roller bearings. Compared with other optimization algorithms, the RBMO algorithm shows excellent performance in terms of optimization accuracy and convergence speed. Through the optimization of the RBMO algorithm, SVMD and MOMEDA can adaptively find the optimal parameter configuration, thereby effectively avoiding the subjective interference and uncertainty that may be introduced in the process of manual parameter adjustment, and ensuring the objectivity and accuracy of parameter setting; compared with the SVMD-MOMEDA method and FMD-MCKD method without parameter optimization, the parameter-optimized SVMD-MOMEDA method can effectively extract the bearing inner ring fault frequency and its frequency multiplication component (2 to 6 times) under -10dB noise interference, successfully realizing the accurate extraction and efficient identification of fault characteristics. The invention mainly includes the following steps:

[0059] Step 1: Using envelope entropy as the fitness function, the RBMO algorithm is used to optimize the SVMD parameter α and decompose the vibration signal into several IMF components.

[0060] Step 2: Calculate the correlation between each component fault information and the original signal, select the optimal component with high correlation for reconstruction, and eliminate noise interference;

[0061] Step 3: Use the RBMO algorithm to optimize the filter length L of MOMEDA, and enhance the impulse component in the reconstructed signal through the MOMEDA method;

[0062] Step 4: Perform envelope analysis on the deconvolved signal to obtain the fault frequency corresponding to the spectrum line with obvious peak in the envelope spectrum, thereby realizing fault diagnosis of the needle roller bearing.

[0063] The present invention optimizes the key parameters of SVMD and MOMEDA by using the RBMO algorithm, which can effectively extract the fault characteristic signal of the needle roller bearing from the complex vibration signal, and solve the problem of increased difficulty in fault identification and diagnosis caused by noise interference in the collected bearing vibration signal.

[0064] Example 1

[0065] To solve the above technical problems, the present invention provides a method for evaluating the running quality of a needle roller bearing of a planetary mechanism, which comprises the following steps:

[0066] Step 1: Using envelope entropy as the fitness function, the RBMO algorithm is used to optimize the maximum value of the parameter α of the SVMD method and decompose the vibration signal into several IMF components;

[0067] Step 2: Calculate the correlation between the fault information of each IMF component and the original signal, select the optimal IMF component with high correlation for reconstruction, and eliminate noise interference;

[0068] Step 3: Use the RBMO algorithm to optimize the filter length L of the MOMEDA method, and enhance the impulse component in the reconstructed signal through the MOMEDA method;

[0069] Step 4: Perform envelope analysis on the deconvolved signal to obtain the fault frequency corresponding to the spectrum line with obvious peak in the envelope spectrum, thereby realizing fault diagnosis of the needle roller bearing.

[0070] Among them, the planetary mechanism needle roller bearing operation quality assessment method is based on the RBMO-SVMD-MOMEDA signal processing method, which can better preserve signal characteristics, reduce information loss, and effectively avoid subjective interference and uncertainty that may be introduced in the parameter adjustment process, ensuring the objectivity and accuracy of parameter setting, and successfully realizing the accurate extraction and efficient identification of fault characteristics.

[0071] In step 2, the bearing rotation frequency f can be observed from the envelope spectrum of the reconstructed signal. r , inner ring fault frequency f i and its frequency multiples (2f i 、3f i ), indicating that the signal reconstructed by the planetary mechanism needle roller bearing operation quality assessment method can effectively remove the noise components in the signal and reveal the key frequency components hidden in the complex vibration signal.

[0072] Among them, in step 3, the RBMO algorithm accurately locked the optimal fitness value after only two iterations. The results show that compared with other optimization algorithms, the RBMO algorithm has outstanding advantages in performance such as convergence speed and stability.

[0073] Among them, in step 4, the deconvolution time domain waveform shows obvious periodic impact components, and the frequency modulation and frequency multiplication attenuation phenomena in the envelope spectrum are improved, and the inner ring fault frequency f i and its frequency multiples (2~8f i ) becomes more obvious, from which it can be determined that the bearing has an inner ring failure.

[0074] Among them, in the planetary mechanism needle roller bearing operation quality assessment method, compared with other optimization algorithms, the RBMO algorithm shows excellent performance in optimization accuracy and convergence speed. Through the optimization of the RBMO algorithm, SVMD and MOMEDA can adaptively find the optimal parameter configuration, thereby effectively avoiding the subjective interference and uncertainty that may be introduced in the process of manual parameter adjustment, and ensuring the objectivity and accuracy of parameter setting.

[0075] Among them, compared with the SVMD-MOMEDA method without parameter optimization and the FMD-MCKD method, the SVMD-MOMEDA method with parameter optimization can effectively extract the bearing inner ring fault frequency and its frequency multiplication components (2nd to 6th frequency multiplication) under -10dB noise interference, successfully realizing the accurate extraction and efficient identification of fault characteristics.

[0076] Among them, the planetary mechanism needle roller bearing operation quality assessment method optimizes the SVMD and MOMEDA key parameters by using the RBMO algorithm, which can effectively extract the fault characteristic signal of the needle roller bearing from the complex vibration signal, and solve the problem of increased difficulty in fault identification and diagnosis caused by noise interference in the collected bearing vibration signal.

[0077] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for evaluating the running quality of a planetary mechanism needle roller bearing, characterized in that: It includes the following steps: Step 1: Using envelope entropy as the fitness function, the RBMO algorithm is used to optimize the maximum value of the parameter α of the SVMD method and decompose the vibration signal into several IMF components; Step 2: Calculate the correlation between the fault information of each IMF component and the original signal, select the optimal IMF component with high correlation for reconstruction, and eliminate noise interference; Step 3: Use the RBMO algorithm to optimize the filter length L of the MOMEDA method, and enhance the impulse component in the reconstructed signal through the MOMEDA method; Step 4: Perform envelope analysis on the deconvolved signal to obtain the fault frequency corresponding to the spectrum line with obvious peak in the envelope spectrum, thereby realizing fault diagnosis of the needle roller bearing.

2. The planetary mechanism needle roller bearing operation quality assessment method according to claim 1, characterized in that: The planetary mechanism needle roller bearing operation quality assessment method is based on the RBMO-SVMD-MOMEDA signal processing method, which can better preserve signal characteristics, reduce information loss, and effectively avoid subjective interference and uncertainty that may be introduced in the parameter adjustment process, ensuring the objectivity and accuracy of parameter setting, and successfully achieving accurate extraction and efficient identification of fault characteristics.

3. The planetary mechanism needle roller bearing operation quality assessment method according to claim 1, characterized in that: In step 2, the bearing rotation frequency f can be observed from the envelope spectrum of the reconstructed signal. r , inner ring fault frequency f i and its frequency multiples (2f i 、3f i ), indicating that the signal reconstructed by the planetary mechanism needle roller bearing operation quality assessment method can effectively remove the noise components in the signal and reveal the key frequency components hidden in the complex vibration signal.

4. The planetary mechanism needle roller bearing operation quality assessment method according to claim 1, characterized in that: In step 3, the RBMO algorithm accurately locked the optimal fitness value after only two iterations. The results show that compared with other optimization algorithms, the RBMO algorithm exhibits outstanding advantages in performance such as convergence speed and stability.

5. The planetary mechanism needle roller bearing operation quality assessment method according to claim 1, characterized in that: In step 4, the deconvolution time domain waveform shows obvious periodic impact components, and the frequency modulation and frequency multiplication attenuation phenomena in the envelope spectrum are improved. The inner ring fault frequency f i and its frequency multiples (2~8f i ) becomes more obvious, from which it can be determined that the bearing has an inner ring failure.

6. The planetary mechanism needle roller bearing operation quality assessment method according to claim 1, characterized in that: In the planetary mechanism needle roller bearing operation quality assessment method, the RBMO algorithm demonstrates superior performance in optimization accuracy and convergence speed compared to other optimization algorithms. Through the optimization of the RBMO algorithm, SVMD and MOMEDA can adaptively find the optimal parameter configuration, thereby effectively avoiding the subjective interference and uncertainty that may be introduced in the process of manual parameter adjustment, and ensuring the objectivity and accuracy of parameter setting.

7. The planetary mechanism needle roller bearing operation quality assessment method according to claim 1, characterized in that: Compared with the SVMD-MOMEDA method without parameter optimization and the FMD-MCKD method, the SVMD-MOMEDA method with parameter optimization can effectively extract the bearing inner ring fault frequency and its frequency multiple components (2nd to 6th multiples) under -10dB noise interference, successfully realizing the accurate extraction and efficient identification of fault characteristics.

8. The planetary mechanism needle roller bearing operation quality assessment method according to claim 1, characterized in that: The planetary mechanism needle roller bearing operation quality assessment method optimizes the SVMD and MOMEDA key parameters using the RBMO algorithm, and can effectively extract the fault characteristic signals of the needle roller bearing from the complex vibration signals, thereby solving the problem of increased difficulty in fault identification and diagnosis caused by noise interference in the collected bearing vibration signals.

9. The planetary mechanism needle roller bearing operation quality assessment method according to claim 1, characterized in that: The method solves the problem that the fault features of needle roller bearings are difficult to effectively extract and identify under strong background noise, and realizes the identification of needle roller bearing fault signals under strong noise background.

10. The planetary mechanism needle roller bearing operation quality assessment method according to claim 1, characterized in that: The method belongs to the technical field of planetary mechanism needle roller bearing operation quality assessment.

Images