Fault identification method of rolling bearing and related equipment

Abstract

The embodiment of the invention provides a fault identification method for a rolling bearing and related equipment, and belongs to the technical field of data processing. The method comprises the following steps: acquiring acceleration data corresponding to a rolling bearing acquired by an acceleration sensor; decomposing the acceleration data corresponding to the rolling bearing through the genetic optimization model to obtain a plurality of modal components, and calculating a target result parameter according to the plurality of modal components; and calculating to obtain a fault identification result corresponding to the rolling bearing through a rolling bearing fault theoretical formula according to the target result parameters. According to the embodiment of the invention, the target result parameter can be calculated according to the plurality of modal components, and the fault identification result corresponding to the rolling bearing can be calculated according to the target result parameter through the rolling bearing fault theoretical formula, thereby achieving the precise identification and diagnosis of the type, part and severity of the early fault of the rolling bearing. The precision and accuracy of fault analysis on the rolling bearing can be improved.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a method and related equipment for fault identification of rolling bearings. Background Technology

[0002] As a critical component of rotating machinery, rolling bearings are susceptible to early-stage faults whose subtle impact characteristics are easily masked by strong background vibrations, making accurate identification difficult using traditional diagnostic methods. While Variational Mode Decomposition (VMD), as an advanced signal processing technique, can theoretically overcome the shortcomings of earlier methods such as mode aliasing, its performance is highly dependent on the proper setting of key parameters such as the number of modes and the penalty factor. Improper parameter selection can directly lead to decomposition failure. Therefore, solving this core parameter optimization problem is crucial for achieving accurate diagnosis of early-stage faults. Summary of the Invention

[0003] The main objective of this application is to propose a fault identification method and related equipment for rolling bearings, which can improve the accuracy and precision of fault analysis of rolling bearings.

[0004] To achieve the above objectives, one aspect of this application proposes a method for fault identification of rolling bearings, applied to an electronic device. The electronic device is communicatively connected to a rotating device, which is equipped with a rolling bearing and an acceleration sensor. The method includes: Acquire acceleration data corresponding to the rolling bearing shaft through the accelerometer; The acceleration data corresponding to the rolling bearing is decomposed using a genetic optimization model to obtain multiple modal components, and the target result parameters are calculated based on the multiple modal components. The fault identification result of the rolling bearing is calculated based on the target result parameters using the rolling bearing fault theory formula.

[0005] In some embodiments, the step of decomposing the acceleration data corresponding to the rolling bearing using a genetic optimization model to obtain component data under multiple modes, and calculating the target result parameters based on the multiple modal components, includes: The acceleration data corresponding to the rolling bearing is decomposed using the genetic optimization model to obtain component data under multiple modes, and the envelope entropy corresponding to the component data under each mode is determined. The envelope entropy corresponding to each modal component is used as the fitness function in the genetic optimization model for iterative calculation to obtain the minimum envelope entropy generated under multiple iterations. The combined parameters corresponding to the minimum envelope entropy of each iteration are taken as the local minimum envelope entropy of this iteration. The target result parameters are derived by iterating through the local minimum envelope entropy obtained in each iteration.

[0006] In some embodiments, the step of iteratively calculating the envelope entropy corresponding to the component data under each modality as the fitness function in the genetic optimization model includes: According to the formula Perform multiple iterative calculations, wherein, For the maximum crossover rate, the The value is 0.9; To achieve the minimum crossover rate, the The value is 0.6; The average fitness of individuals in each generation; The minimum fitness of each generation; For the fitness of each generation, the stated For the maximum variation rate, the The value is 0.1; To minimize the rate of variation, the The value is 0.01.

[0007] In some embodiments, the step of iterating the target result parameters based on the local minimum envelope entropy obtained in each iteration includes: The local minimum envelope entropy value is used as the fitness value for iteration to obtain the number of modes and penalty factor corresponding to the global minimum envelope entropy value, and the number of modes and penalty factor corresponding to the global minimum envelope entropy value are used as the target result parameters.

[0008] In some embodiments, before calculating the target result parameters based on the plurality of modal components, the method further includes: The multiple modal components are denoised and reconstructed using singular value matrices to obtain the denoised modal components; The calculation of the target result parameters based on the multiple modal components includes: The target result parameters are calculated based on the multiple noise-reduced modal components.

[0009] In some embodiments, the step of denoising and reconstructing the plurality of modal components using a singular value matrix to obtain denoised modal components includes: Construct singular value matrices for the modal components of the global minimum envelope entropy; wherein, the singular value matrix is... Matrix elements satisfy: The multiple modal components are then denoised and reconstructed based on the singular value matrix to obtain the denoised modal components.

[0010] In some embodiments, the step of calculating the fault identification result corresponding to the rolling bearing based on the target result parameter using the rolling bearing fault theory formula includes: Through formula The energy operator data is calculated, wherein the... For the signal points of acceleration data Energy operator data at the location; the The current target result parameter; The parameter is the target result parameter of the previous one; For the parameters of the next target result; The fault identification result corresponding to the rolling bearing is determined based on the energy operator data.

[0011] To achieve the above objectives, another aspect of this application proposes a fault identification device for rolling bearings, applied to an electronic device. The electronic device is communicatively connected to a rotating device, which includes a rolling bearing and an acceleration sensor. The device comprises: The data acquisition module is used to acquire acceleration data corresponding to the rolling bearing shaft collected by the acceleration sensor; The parameter calculation module is used to decompose the acceleration data corresponding to the rolling bearing through a genetic optimization model to obtain multiple modal components, and calculate the target result parameters based on the multiple modal components. The result calculation module is used to calculate the fault identification result corresponding to the rolling bearing based on the target result parameters using the rolling bearing fault theory formula.

[0012] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the methods described above.

[0013] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the methods described above.

[0014] To achieve the above objectives, another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the methods described above. The embodiments of this application include at least the following beneficial effects: This application provides a method, device, electronic device, storage medium, and program product for fault identification of rolling bearings. This solution acquires acceleration data corresponding to the rolling bearing through an accelerometer; decomposes the acceleration data corresponding to the rolling bearing through a genetic optimization model to obtain multiple modal components, and calculates target result parameters based on these modal components; and calculates the fault identification result of the rolling bearing based on the target result parameters using the rolling bearing fault theory formula. Implementing the embodiments of this application decomposes the acceleration data into a series of modal components with definite center frequencies, effectively overcoming problems such as modal aliasing and noise interference in traditional methods. The target result parameters are calculated based on multiple modal components, and the fault identification result of the rolling bearing is calculated based on the target result parameters using the rolling bearing fault theory formula. This achieves accurate identification and diagnosis of early fault types, locations, and severity of rolling bearings. Through the organic combination of intelligent optimization and adaptive decomposition, the accuracy and precision of fault analysis for rolling bearings can be improved. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of an implementation environment provided in an embodiment of this application; Figure 2 This is a flowchart of the fault identification method for rolling bearings provided in the embodiments of this application; Figure 3 This is a schematic diagram of a rotating device equipped with a rolling bearing and an acceleration sensor in one embodiment; Figure 4 A flowchart of a genetic optimization model in one embodiment; Figure 5 This is a flowchart for fault identification of rolling bearings in one embodiment; Figure 6 This is a schematic diagram of the structure of the fault identification device for rolling bearings provided in the embodiments of this application; Figure 7 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0017] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0018] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0021] 1) VMD (Variational Mode Decomposition) is an adaptive and completely non-recursive modal variational and signal processing method. Its adaptability is reflected in determining the number of mode decompositions of a given sequence according to the actual situation. In the subsequent search and solution process, it can adaptively match the optimal center frequency and finite bandwidth of each mode, and can achieve effective separation of IMFs and frequency domain division of the signal, thereby obtaining the effective components of the given signal and finally obtaining the optimal solution of the variational problem.

[0022] In related technologies, rolling bearings are widely used in various rotating machinery as components to reduce friction and wear. When damage occurs on the surface of a rolling bearing, it will collide with mating components, thereby exciting vibrations at various natural frequencies of the rotating system, resulting in abnormal vibrations and noise in the machinery. However, the impact caused by early faults is often drowned out by strong background vibrations, making it difficult to extract the fault characteristic frequencies. Therefore, fault diagnosis of bearings, especially early and subtle fault diagnosis, has always been a hot topic of research.

[0023] Currently, rolling bearing fault diagnosis methods mainly include Empirical Mode Decomposition (EMD), Lumped Empirical Mode Decomposition (EEMD), Intrinsic Time Scale Decomposition (ITD), and Local Mean Decomposition (LMD). These methods lack rigorous mathematical theoretical derivation, leading to drawbacks such as mode aliasing, endpoint effects, and susceptibility to noise signals during the decomposition process. Variational Mode Decomposition (VMD), based on Wiener filtering, employs a non-recursive, adaptive variational signal decomposition method, completely solving the problems of the aforementioned methods. It has significant advantages in processing typical periodic and non-stationary rolling bearing fault signals. However, the initial given number of modes K and penalty factor... The parameters have a significant impact on the VMD decomposition results. If the parameters are not set properly, it can lead to over-decomposition or under-decomposition.

[0024] In view of this, this application provides a method for fault identification of rolling bearings, which can improve the accuracy and precision of fault analysis of rolling bearings.

[0025] The rolling bearing fault identification method provided in this application relates to the field of data processing technology. This rolling bearing fault identification method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or in-vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the rolling bearing fault identification method, but is not limited to the above forms.

[0026] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics devices, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0027] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0028] like Figure 1 The diagram shown is a schematic representation of an implementation environment provided in an embodiment of this application. (Refer to...) Figure 1 The implementation environment includes at least one terminal 102 and a server 101. The terminal 102 and the server 101 can be connected via a network, either wirelessly or via a wired connection, to complete data transmission and exchange.

[0029] Server 101 can be a standalone physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0030] Additionally, server 101 can also be a node server in a blockchain network. Blockchain is a novel application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0031] Terminal 102 can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, etc., but is not limited to these. Terminal 102 and server 101 can be directly or indirectly connected via wired or wireless communication, and this embodiment of the application does not impose any limitations.

[0032] For example, based on Figure 1 The implementation environment shown in this application embodiment provides an image auditing method. The following description uses the application of this image auditing method in server 101 as an example. It can be understood that the image auditing method can also be applied in terminal 102.

[0033] Figure 2 This is an optional flowchart of the fault identification method for rolling bearings provided in the embodiments of this application. The subject executing the fault identification method for rolling bearings can be any of the aforementioned electronic devices (including servers or terminals). Figure 2 The method may include, but is not limited to, steps S201 to S203.

[0034] Step S201: Obtain the acceleration data corresponding to the rolling bearing through the accelerometer.

[0035] In some embodiments, the electronic device is communicatively connected to the rotating equipment, which is equipped with a rolling bearing and an acceleration sensor. Specifically, a high-precision piezoelectric acceleration sensor can be installed radially or axially along the bearing housing to collect vibration acceleration data of the rolling bearing during operation in real time at a sampling frequency of not less than 20 kHz. Based on the piezoelectric effect, this acceleration sensor can convert the periodic impact vibration caused by localized damage to the bearing into a high-fidelity electrical signal. This signal is then subjected to anti-aliasing filtering and analog-to-digital conversion by the data acquisition system, ultimately forming a time-domain acceleration sequence containing rich state information, thus obtaining the acceleration data.

[0036] Figure 3 This is a schematic diagram of an embodiment where a rotating device includes a rolling bearing and an acceleration sensor, as shown. Figure 3As shown, a power transmission chain is formed by sequentially mounting components such as a drive motor, rolling bearings, couplings, and loads on the platform. Accelerometers are mounted close to the rolling bearings, collecting vibration signals in real time and transmitting them via signal lines to a data acquisition and analysis system for processing and analysis. The final results are displayed visually on the right-hand monitor, showing key parameters such as vibration amplitude and spectrum, facilitating operator monitoring of the equipment's operating status. Specifically, three accelerometers are placed: one on the motor body, one at the rolling bearing output end, and one on the mounting platform. After the motor has been running stably at a given speed for a period of time, acceleration signals are collected at each measuring point. For the acceleration data x(t) during rolling bearing operation, the sampling frequency is fs, the sampling time interval is dt, and the sampling time is T.

[0037] Step S202: Decompose the acceleration data corresponding to the rolling bearing using a genetic optimization model to obtain multiple modal components, and calculate the target result parameters based on the multiple modal components.

[0038] In some embodiments, a genetic optimization model with optimized parameters is used to adaptively decompose the preprocessed acceleration data. This genetic optimization model uses the modal components and penalty factor in variational mode decomposition as optimization variables, and the minimum envelope entropy as the fitness function. Through iterative genetic operations such as selection, crossover, and mutation, it ultimately obtains the parameter combination that achieves the optimal decomposition effect. Variational mode decomposition is then performed using the optimized parameters, adaptively decomposing the non-stationary original vibration signal into a series of eigenmode functions with specific center frequencies.

[0039] As an optional implementation, the acceleration data corresponding to the rolling bearing is decomposed using a genetic optimization model to obtain component data under multiple modes, and the envelope entropy corresponding to the component data under each mode is determined. The envelope entropy corresponding to each mode component is used as the fitness function in the genetic optimization model for iterative calculation to obtain the minimum envelope entropy generated in each iteration. The combination parameter corresponding to the minimum envelope entropy of each iteration is used as the local minimum envelope entropy of this iteration. The target result parameter is iterated based on the local minimum envelope entropy obtained in each iteration.

[0040] The acquired acceleration data x(t) is decomposed using Virtual Mode Decomposition (VMD). VMD of the acceleration signal yields several independent modal components. Its definition is as shown in formula (1).

[0041] Among them, phase Non-decreasing Instantaneous amplitude and instantaneous amplitude and instantaneous frequency Compared to The change is slow, that is, in Within the range, Can be regarded as amplitude , frequency is Harmonic signals.

[0042] VMD decomposition is essentially a problem of constructing and solving variational problems. First, for Perform a Hilbert transform to obtain the corresponding one-sided spectrum; then use exponential mixing modulation to modulate the spectrum of each mode function onto the fundamental frequency band of the response; use... Gaussian smoothing is used to estimate the demodulated signal, resulting in... The estimated bandwidth, under constraint, is determined by the variational model as follows:

[0043]

[0044] To solve the constrained variational problem, a quadratic penalty factor is used. and Lagrangian multiplication operator (Because the collected vibration acceleration signals generally contain Gaussian white noise, a second-order penalty factor) This ensures the accuracy of the reconstructed signal; Lagrangian multiplier operator. (To ensure the strictness of the constraints) it is transformed into an unconstrained variational problem, and the augmented Lagrangian function is:

[0045] Alternate updates using the alternating direction multiplier method , and Solve the optimization problem. Update the modes in the frequency domain. :

[0046] In the formula: This is the Fourier transform of the original signal.

[0047] Update the center frequency using the power spectrum centroid method :

[0048] Update Lagrange multipliers :

[0049] Convergence condition: when satisfied Stop iteration when Usually set to .

[0050] Furthermore, envelope entropy is used as the fitness function. Since envelope entropy is a characteristic index combining signal envelope analysis and information entropy, it reflects the sparsity of the signal; the less noise, the stronger the sparsity of the signal, and the smaller the envelope entropy. Therefore, the envelope entropy values ​​of each modal component generated by VMD decomposition are selected as the fitness function in the improved genetic algorithm parameter optimization. Hilbert transform is performed on each modal component to generate analytic signals.

[0051] The amplitude of the analytic signal is the envelope signal.

[0052] envelope signal Normalize to the [0, 1] interval:

[0053] The normalized envelope signal is divided into M equal-width intervals. The frequency of data points in each interval is counted, and the probability distribution is calculated. Calculate the envelope entropy using the Shannon entropy formula:

[0054] Wherein, the envelope entropy is , The probability distribution of data points within each interval.

[0055] According to the formula Perform multiple iterative calculations, among which, To achieve the maximum crossover rate, The value is 0.9; To minimize the crossover rate, The value is 0.6; The average fitness of individuals in each generation; Minimum fitness for each generation; For the fitness of each generation of individuals, For the maximum rate of variation, The value is 0.1; To minimize the rate of variation, The value is 0.01. The number of modes K and the penalty factor are randomly generated. As a combination parameter, the envelope entropy values ​​of each modal component generated by VMD decomposition are used as the fitness function in the genetic algorithm parameters. The minimum envelope entropy in each generation is denoted as the local minimum envelope entropy, and the corresponding combination parameter is the optimal component combination for this decomposition. To search for the globally optimal combination, the local minimum envelope entropy value is used as the fitness value. After iteration, the number of modes K and the penalty factor corresponding to the global minimum envelope entropy value are determined. This is the final parameter optimization target, which is the target result parameter. It avoids the problem of the target result parameter not meeting the actual needs due to unreasonable fitness value settings, thereby improving the efficiency and accuracy of iterating to obtain the target result parameter.

[0056] The acceleration data corresponding to the rolling bearing is decomposed using a genetic optimization model to obtain component data under multiple modes, and the envelope entropy corresponding to the component data under each mode is determined. The envelope entropy corresponding to each mode component is used as the fitness function in the genetic optimization model for iterative calculation to obtain the minimum envelope entropy generated in each iteration. The combination parameter corresponding to the minimum envelope entropy of each iteration is used as the local minimum envelope entropy of this iteration. The target result parameter is iterated based on the local minimum envelope entropy obtained in each iteration, which can further improve the efficiency of iterating the target result parameter and also improve the accuracy of the calculated target result parameter.

[0057] As an optional implementation, the local minimum envelope entropy value is used as the fitness value for iterative calculation to obtain the number of modes and penalty factor corresponding to the global minimum envelope entropy value. The number of modes and penalty factor corresponding to the global minimum envelope entropy value are then used as the target result parameters. Envelope entropy is used as the fitness evaluation index of the genetic algorithm. By iteratively calculating the fitness value corresponding to the local minimum envelope entropy value of each parameter combination, the global search capability of the genetic optimization model is utilized to perform selection, crossover, and mutation operations in the parameter space, ultimately finding the optimal combination of the number of modes and penalty factor that minimizes the global envelope entropy. Here, envelope entropy, as an indicator of signal sparsity, corresponds to the signal decomposition state that best highlights the fault impact characteristics at its minimum value; the number of modes determines the fineness of signal decomposition; and the penalty factor controls the bandwidth constraint of the modal components.

[0058] By iterating using the local minimum envelope entropy value as the fitness value, the number of modes and penalty factor corresponding to the global minimum envelope entropy value are obtained. The number of modes and penalty factor corresponding to the global minimum envelope entropy value are then used as the target result parameters. This effectively avoids the over-decomposition or under-decomposition problem caused by improper parameter settings in traditional methods, providing a reliable parameter guarantee for the accurate extraction of subsequent fault features and significantly improving the accuracy and reliability of fault diagnosis.

[0059] In some embodiments, before calculating the target result parameters based on multiple modal components, the multiple modal components can be denoised and reconstructed using a singular value matrix to obtain denoised modal components; the target result parameters are then calculated based on the denoised modal components. Each modal component is constructed into an initial matrix according to specific rules, and singular value decomposition is performed on this singular value matrix to obtain a singular value spectrum reflecting the characteristic structure of the signal. Based on the characteristics of singular value distribution, retaining the principal components representing fault information and removing the corresponding minor noise components can effectively improve the signal-to-noise ratio of the denoised modal components.

[0060] Furthermore, singular value matrices are constructed for the modal components of the global minimum envelope entropy; where the singular value matrix is... Matrix elements satisfy: The singular value matrix is ​​used to denoise and reconstruct multiple modal components, resulting in denoised modal components. Among these, there exists a matrix... , so that:

[0061] in, The calculation is as follows ; represents the positive singular values ​​of matrix H; 0 represents a matrix with zero elements. .

[0062] The singular value standard energy spectrum is:

[0063] The cumulative standard energy spectrum is used to determine the number of principal components, using the following formula:

[0064] The cumulative standard energy spectrum visually reveals that the energy is mainly concentrated in the patterns corresponding to the first few singular values, while the later singular values ​​mainly represent noise components. (Preserve the previous values.) k By taking a singular value and setting all subsequent singular values ​​to zero, the denoised matrix can be obtained. Its expression is:

[0065] in, for U The former k List; for forward k One singular value; for The former k Line. Matrix The denoised modal components can be obtained by averaging the elements at the corresponding positions.

[0066] Figure 4 A flowchart of the genetic optimization model in one embodiment is shown below. Figure 4 As shown, the population is first initialized and the fitness of individuals is evaluated. Then, a diamond-shaped decision box is used to check whether the termination condition is met. If it is met, the optimal solution is output and the algorithm ends. Otherwise, the loop optimization stage is entered: dynamic parameter adjustment, roulette wheel selection of parent individuals, adaptive crossover rate and mutation rate operations are performed in sequence. After generating a new population, the fitness is re-evaluated and the above process is repeated until the termination condition is reached. Finally, the optimal solution is output to complete the entire algorithm.

[0067] Step S203: The fault identification result of the rolling bearing is calculated based on the target result parameters using the rolling bearing fault theory formula.

[0068] In some embodiments, the fault identification results can be used to determine the current fault status of the rolling bearing, wherein the fault identification results may include the inner ring fault characteristic frequency, the outer ring fault frequency, the rolling element fault frequency, and the cage fault frequency.

[0069] As an optional implementation method, through the formula The energy operator data was calculated, where, For the signal points of acceleration data Energy operator data at the location; The parameters for the current target result; The target result parameter of the previous one; The parameters for the next target result are used to determine the fault identification result corresponding to the rolling bearing based on the energy operator data.

[0070] Fault characteristic frequencies of various components of a rolling bearing. When a bearing suffers damage during operation, such as pitting, cracking, or spalling of the inner ring, outer ring, rolling elements, or cage, specific fault characteristic frequencies will appear in the vibration signal.

[0071] The inner ring fault characteristic frequency BPFI is:

[0072] The outer ring fault frequency BPFO is:

[0073] The rolling element failure frequency (BSF) is:

[0074] The cage failure frequency (FTF) is:

[0075] in, The number of rolling elements; The rotational frequency of the axis; The diameter of the rolling element; The bearing pitch circle diameter; It represents the contact angle.

[0076] The envelope spectrum of the reconstructed modal components is obtained by performing FFT (Fast Fourier Transform) on the Teager energy operator data. By comparing the peak value of the envelope spectrum with the fault characteristic frequency calculated by the theory of rolling bearing, the fault type of rolling bearing can be quickly identified.

[0077] Figure 5 This is a flowchart for fault identification of rolling bearings in one embodiment, such as... Figure 5 As shown, a test system is first built to collect vibration acceleration signals, the genetic algorithm parameters are initialized, and VMD parameter combinations are randomly generated. The parameters are continuously optimized through an iterative process. After each VMD decomposition, the envelope entropy of each modal component is calculated, the optimal individual is recorded, and the parameter combination is adaptively updated until the maximum number of iterations is reached. Then, the characteristic frequencies are identified by combining fault theory, and the reconstructed modal components are subjected to Teager energy operator analysis and FFT transformation. Then, the singular value decomposition is used for noise reduction. Finally, the optimal parameter combination and the modal component with the minimum envelope entropy are output, completing the entire process from signal acquisition to fault feature extraction.

[0078] Steps S201 to S203 of this embodiment involve acquiring acceleration data corresponding to the rolling bearing via an accelerometer; decomposing the acceleration data of the rolling bearing corresponding to the rolling bearing using a genetic optimization model to obtain multiple modal components, and calculating target result parameters based on the multiple modal components; and calculating the fault identification result of the rolling bearing corresponding to the rolling bearing based on the target result parameters using the rolling bearing fault theory formula. By decomposing the acceleration data into a series of modal components with definite center frequencies, the problems of modal aliasing and noise interference in traditional methods are effectively overcome. The calculation of target result parameters based on multiple modal components and the calculation of the fault identification result of the rolling bearing corresponding to the rolling bearing based on the target result parameters achieve accurate identification and diagnosis of early fault types, locations, and severity of the rolling bearing. Through the organic combination of intelligent optimization and adaptive decomposition, the accuracy and precision of fault analysis of the rolling bearing can be improved.

[0079] Please see Figure 6 This application also provides a fault identification device for rolling bearings, which can implement the above-described method. The device includes: Data acquisition module 601 is used to acquire acceleration data corresponding to the rolling bearing shaft collected by the accelerometer; The parameter calculation module 602 is used to decompose the acceleration data corresponding to the rolling bearing through a genetic optimization model to obtain multiple modal components, and calculate the target result parameters based on the multiple modal components. The result calculation module 603 is used to calculate the fault identification result of the rolling bearing based on the target result parameters using the rolling bearing fault theory formula.

[0080] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0081] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0082] It is understood that the content of the above method embodiments is applicable to this device embodiment. The specific functions implemented by this device embodiment are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0083] Please see Figure 7 , Figure 7 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701 using the methods described in the embodiments of this application. The input / output interface 703 is used to implement information input and output; The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704); The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0084] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0085] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0086] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0087] It is understood that the content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0088] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0089] The rolling bearing fault identification method, device, electronic device, storage medium, and program product provided in this application embodiment acquire acceleration data corresponding to the rolling bearing through an accelerometer; decompose the acceleration data corresponding to the rolling bearing through a genetic optimization model to obtain multiple modal components, and calculate the target result parameters based on the multiple modal components; and calculate the fault identification result corresponding to the rolling bearing based on the target result parameters using the rolling bearing fault theory formula, which can improve the accuracy and precision of rolling bearing fault analysis.

[0090] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0091] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0092] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0093] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0094] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0095] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0096] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0097] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0098] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0099] If the integrated unit 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 this application, in essence, or the part that contributes to the prior art, or all or part 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 multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0100] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for fault identification of rolling bearings, characterized in that, Applied to an electronic device that is communicatively connected to a rotating device, the rotating device being equipped with a rolling bearing and an acceleration sensor, the method includes the following steps: Acquire acceleration data corresponding to the rolling bearing shaft through the accelerometer; The acceleration data corresponding to the rolling bearing is decomposed using a genetic optimization model to obtain multiple modal components, and the target result parameters are calculated based on the multiple modal components. The fault identification result of the rolling bearing is calculated based on the target result parameters using the rolling bearing fault theory formula.

2. The method according to claim 1, characterized in that, The acceleration data corresponding to the rolling bearing is decomposed using a genetic optimization model to obtain component data under multiple modes, and the target result parameters are calculated based on the multiple modal components, including: The acceleration data corresponding to the rolling bearing is decomposed using the genetic optimization model to obtain component data under multiple modes, and the envelope entropy corresponding to the component data under each mode is determined. The envelope entropy corresponding to each modal component is used as the fitness function in the genetic optimization model for iterative calculation to obtain the minimum envelope entropy generated under multiple iterations. The combined parameters corresponding to the minimum envelope entropy of each iteration are taken as the local minimum envelope entropy of this iteration. The target result parameters are derived by iterating through the local minimum envelope entropy obtained in each iteration.

3. The method according to claim 2, characterized in that, The step of iteratively calculating the envelope entropy corresponding to the component data under each modality as the fitness function in the genetic optimization model includes: According to the formula Perform multiple iterative calculations, wherein, For the maximum crossover rate, the The value is 0.9; To achieve the minimum crossover rate, the The value is 0.6; The average fitness of individuals in each generation; The minimum fitness of each generation; For the fitness of each generation, the stated For the maximum variation rate, the The value is 0.1; To minimize the rate of variation, the The value is 0.

01.

4. The method according to claim 3, characterized in that, The step of iterating the target result parameters based on the local minimum envelope entropy obtained in each iteration includes: The local minimum envelope entropy value is used as the fitness value for iteration to obtain the number of modes and penalty factor corresponding to the global minimum envelope entropy value, and the number of modes and penalty factor corresponding to the global minimum envelope entropy value are used as the target result parameters.

5. The method according to claim 1, characterized in that, Before calculating the target result parameters based on the plurality of modal components, the method further includes: The multiple modal components are denoised and reconstructed using singular value matrices to obtain the denoised modal components; The calculation of the target result parameters based on the multiple modal components includes: The target result parameters are calculated based on the multiple noise-reduced modal components.

6. The method according to any one of claims 1 to 5, characterized in that, The step of denoising and reconstructing the multiple modal components using singular value matrices to obtain denoised modal components includes: Construct singular value matrices for the modal components of the global minimum envelope entropy; wherein, the singular value matrix is... Matrix elements satisfy: The multiple modal components are then denoised and reconstructed based on the singular value matrix to obtain the denoised modal components.

7. The method according to any one of claims 1 to 5, characterized in that, The fault identification result of the rolling bearing is calculated based on the target result parameters using the rolling bearing fault theory formula, including: Through formula The energy operator data is calculated, wherein the... For the signal points of acceleration data Energy operator data at the location; the The current target result parameter; The parameter is the target result parameter of the previous one; For the parameters of the next target result; The fault identification result corresponding to the rolling bearing is determined based on the energy operator data.

8. A fault identification device for rolling bearings, characterized in that, Applied to an electronic device that is communicatively connected to a rotating device, the rotating device being equipped with a rolling bearing and an acceleration sensor, the device includes: The data acquisition module is used to acquire acceleration data corresponding to the rolling bearing shaft collected by the acceleration sensor; The parameter calculation module is used to decompose the acceleration data corresponding to the rolling bearing through a genetic optimization model to obtain multiple modal components, and calculate the target result parameters based on the multiple modal components. The result calculation module is used to calculate the fault identification result corresponding to the rolling bearing based on the target result parameters using the rolling bearing fault theory formula.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images