Rotating machinery fault diagnosis method, device and storage medium

Abstract

The present invention discloses a rotating machinery fault diagnosis method, device, and storage medium in the field of mechanical fault diagnosis technology. The method includes: obtaining a demodulated signal after discretization processing; solving the demodulated signal after discretization processing by augmented Lagrange multiplier method and alternating direction multiplier method to obtain an iteratively optimized demodulated signal; calculating the instantaneous frequency increment based on the iteratively optimized demodulated signal, applying smoothness constraints and low-rank constraints to the instantaneous frequency increment, and obtaining an estimated instantaneous frequency by solving the problem through an iterative solution algorithm; based on a pre-acquired theoretical fault characteristic frequency and the estimated instantaneous frequency, determining the type of rotating machinery fault according to the matching result. The present invention can solve the technical problem that the instantaneous frequency exhibits non-stationary characteristics and is easily affected by background noise, resulting in difficulty in extracting the accurate instantaneous frequency and thus inability to accurately diagnose potential faults of rotating machinery.

Description

Technical Field

[0001] The present invention relates to the technical field of mechanical fault diagnosis, and in particular to a rotating machinery fault diagnosis method, device and storage medium. Background Art

[0002] Gear and bearing components in rotating machinery play an important role in modern industrial applications. In order to avoid catastrophic accidents, it is of great significance to develop advanced rotating machinery fault diagnosis technology to ensure system reliability.

[0003] When gears and bearings operate under time-varying speed conditions, their vibration signals are nonlinearly frequency modulated and exhibit complex characteristics. These nonlinear signals with complex time-varying amplitudes and frequencies are commonly referred to as nonlinear frequency-modulated signals. The time-varying instantaneous frequency in nonlinear frequency-modulated signals can reveal the signal's vibration patterns, making instantaneous frequency a key indicator for identifying gear and bearing faults under time-varying speed conditions. However, the instantaneous frequency in nonlinear frequency-modulated signals exhibits nonstationary characteristics and is easily affected by background noise, making it difficult to accurately extract the instantaneous frequency and, consequently, to accurately diagnose potential faults in rotating machinery.

[0004] Therefore, there is an urgent need for a rotating machinery fault diagnosis method, device and storage medium to solve the above technical problems. Summary of the Invention

[0005] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a method, device and storage medium for diagnosing rotating machinery faults, which can solve the technical problem that the instantaneous frequency in the nonlinear frequency modulation signal exhibits non-stationary characteristics and is easily affected by background noise, making it difficult to extract the accurate instantaneous frequency and thus unable to accurately diagnose potential faults of the rotating machinery.

[0006] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0007] In a first aspect, the present invention provides a rotating machinery fault diagnosis method, comprising:

[0008] Obtain vibration signals;

[0009] performing a demodulation operation on the vibration signal to obtain a demodulated signal corresponding to the vibration signal, and applying a smoothness constraint and a sparsity constraint to the demodulated signal to obtain a constrained demodulated signal;

[0010] Discretizing the constrained demodulated signal to obtain a demodulated signal after discretization;

[0011] Solving the demodulated signal after the discretization processing by using the augmented Lagrange multiplier method and the alternating direction multiplier method to obtain the demodulated signal after iterative optimization;

[0012] Calculating an instantaneous frequency increment based on the iteratively optimized demodulated signal, applying a smoothness constraint and a low-rank constraint to the instantaneous frequency increment, and obtaining an estimated instantaneous frequency by solving the problem through an iterative solution algorithm;

[0013] The type of the rotating machinery fault is determined based on the pre-acquired theoretical fault characteristic frequency and the estimated instantaneous frequency.

[0014] Furthermore, applying a smoothness constraint and a sparsity constraint to the demodulated signal to obtain a constrained demodulated signal includes:

[0015] The expression of the demodulated signal is:

[0016] ,

[0017] ,

[0018] Smoothness constraints:

[0019] Q1: ,

[0020] Sparsity constraints:

[0021] Q2: ,

[0022] Q3: ,

[0023] in, Indicates the modes, M represents the total number of modes, Indicates the moment, Respectively represent The mode in The first demodulated signal and the second demodulated signal are subjected to the smoothness constraint at every moment, g(t) is expressed as the constraint function, Respectively The second derivative of Indicates the modal The instantaneous amplitude at time, and Respectively represent modal The modulation frequency and demodulation frequency at the moment, the parameter s represents a variable in the interval [0, t] of the variable limit integral, and Respectively represent The modulation frequency and demodulation frequency of each mode at time s, represents the initial phase, and are the first demodulation operator and the second demodulation operator respectively, Indicates the The mode in The first demodulated signal and the second demodulated signal that are subject to sparsity constraints at all times, are the first penalty coefficient and the second penalty coefficient respectively, is the Fourier transform matrix.

[0024] Furthermore, discretizing the constrained demodulated signal to obtain the discretized demodulated signal includes:

[0025] Q4: ,

[0026] Q5: ,

[0027] Q6: ,

[0028] ,

[0029] ,

[0030] ,

[0031] ,

[0032] ,

[0033] ,

[0034] ,

[0035] in, represents the sampling duration from time 0 to time N-1, g represents the vibration signal, which is the representation of the vibration signal after discretization processing; and Respectively represent The first demodulated signal and the second demodulated signal after the modal discretization processing and smoothness constraint are and Respectively represent A first demodulated signal and a second demodulated signal after the modal discretization processing and the sparsity constraint; and express The general form after discretization; Expressed as The modulation frequency of each mode, are the first and second penalty coefficients respectively, is the second-order difference matrix; represents a diagonal matrix, is transposed; represents the kernel matrix, Expressed as The demodulation operator at time t is expressed as , Expressed as The demodulation operator at time t is expressed as , Represents the phase of the trigonometric function at time t.

[0036] Further, solving the demodulated signal after the discretization processing by using the augmented Lagrange multiplier method and the alternating direction multiplier method to obtain the demodulated signal after iterative optimization includes:

[0037] Solving Q4 by augmented Lagrange multipliers and alternating direction multiplier method yields:

[0038] ,

[0039] ,

[0040] ,

[0041] in, Indicates vibration signal, Corresponding to the qth mode in the The first demodulated signal value and the second demodulated signal value at the iteration, Respectively represent the qth mode in the The first kernel matrix value and the second kernel matrix value corresponding to the iteration;

[0042] Introducing the first auxiliary function The Q5 is constructed as a constrained optimization problem and solved by augmented Lagrange multipliers and alternating direction multipliers method:

[0043] ,

[0044] ,

[0045] ,

[0046] The second auxiliary function h is introduced to construct Q6 as a constrained optimization problem, which is solved by augmented Lagrange multipliers and alternating direction multiplier method:

[0047] ,

[0048] ,

[0049] ,

[0050] in, represents the first iteration number, represents the third penalty coefficient, represents the first Lagrange multiplier, represents the second iteration number, represents the fourth penalty coefficient, represents the second Lagrange multiplier, represents the soft threshold function, represents the third iteration number, h is the second auxiliary function, is the fifth penalty coefficient, is the third Lagrange multiplier.

[0051] Furthermore, calculating the instantaneous frequency increment based on the iteratively optimized demodulated signal, applying a smoothness constraint and a low-rank constraint to the instantaneous frequency increment, and obtaining the estimated instantaneous frequency by an iterative solution algorithm includes:

[0052] Based on the iteratively optimized demodulated signal, obtaining an instantaneous frequency increment by an inverse tangent demodulation method includes:

[0053] ,

[0054] Discretizing the instantaneous frequency increment to obtain a discretized instantaneous frequency increment, adding a smoothness constraint to the discretized instantaneous frequency increment, solving to obtain an expected instantaneous frequency increment, and obtaining an initially optimized estimated instantaneous frequency according to the expected instantaneous frequency increment.

[0055] ,

[0056] ,

[0057] ,

[0058] ,

[0059] in, is the sixth penalty coefficient, , is the desired instantaneous frequency increment, represents the identity matrix, Represented as an iteration The estimated instantaneous frequency of the initial optimization, Represented as an iteration The estimated instantaneous frequency of the initial optimization;

[0060] Constructing a noise measurement matrix according to the initially optimized estimated instantaneous frequency, adding a low-rank constraint to the noise measurement matrix, and obtaining the estimated instantaneous frequency includes:

[0061] Q7: ,

[0062] in, To estimate the instantaneous frequency, is a low-rank matrix, Initial optimization The noise observation matrix composed of is the seventh penalty coefficient, Representation matrix No. singular values, Representation matrix The Frobenius norm of ;

[0063] Solving Q7 by shrinking the singular values ​​of the noise measurement matrix yields:

[0064] ,

[0065] in, Both are matrices The orthogonal matrix obtained after applying singular value decomposition, is the The maximum singular value of Each row of represents the estimated instantaneous frequency.

[0066] Furthermore, determining the type of the rotating machinery fault based on the pre-acquired theoretical fault characteristic frequency and the estimated instantaneous frequency includes:

[0067] According to the structural parameters and rotation frequency of the rotating machinery, the theoretical fault characteristic frequency of the rotating machinery is calculated, the estimated instantaneous frequency is compared with the theoretical fault characteristic frequency, and the rotating machinery fault type is determined based on the matching results.

[0068] In a second aspect, the present invention provides a rotating machinery fault diagnosis device, comprising:

[0069] A signal acquisition module, used to acquire vibration signals;

[0070] a demodulation signal optimization module, configured to perform a demodulation operation on the vibration signal to obtain a demodulation signal corresponding to the vibration signal, and impose a smoothness constraint and a sparsity constraint on the demodulation signal to obtain a constrained demodulation signal;

[0071] A discretization module, configured to discretize the constrained demodulated signal to obtain the discretized demodulated signal;

[0072] A solution module, configured to solve the demodulated signal after the discretization process by using an augmented Lagrange multiplier method and an alternating direction multiplier method to obtain an iteratively optimized demodulated signal;

[0073] An estimated instantaneous frequency acquisition module is configured to calculate an instantaneous frequency increment based on the iteratively optimized demodulated signal, impose smoothness constraints and low-rank constraints on the instantaneous frequency increment, and obtain an estimated instantaneous frequency by solving the problem through an iterative solution algorithm;

[0074] The fault confirmation module is used to determine the type of rotating machinery fault based on the pre-acquired theoretical fault characteristic frequency and the estimated instantaneous frequency.

[0075] In a third aspect, the present invention provides an electronic terminal comprising a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of any of the above methods are performed.

[0076] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when executed by a processor.

[0077] Compared with the prior art, the present invention has the following beneficial effects:

[0078] The present invention first proposes a method for diagnosing rotating machinery faults. By applying sparse constraints to the demodulated signal, the estimation accuracy of the demodulated signal is improved and the subsequent instantaneous frequency estimation error is reduced. By applying low-rank constraints to the instantaneous frequency, the inherent proportional relationship of the instantaneous frequency is revealed and the inaccurate initial instantaneous frequency is optimized to reach the true instantaneous frequency. The hybrid constraints enable the present invention to effectively improve the instantaneous frequency estimation accuracy and noise robustness, and effectively process nonlinear frequency modulation signals with closely spaced instantaneous frequencies. Therefore, the present invention can still accurately extract the instantaneous frequency under a variety of complex interference conditions, realize accurate diagnosis of rotating machinery faults, and ensure the safe operation of the entire mechanical system. BRIEF DESCRIPTION OF THE DRAWINGS

[0079] Figure 1 This is a flow chart of a rotating machinery fault diagnosis method provided by an embodiment of the present invention;

[0080] Figure 2 Schematic diagram of a planetary gearbox test bench in a rotating machinery fault diagnosis method provided by an embodiment of the present invention;

[0081] Figure 3 1 is a schematic structural diagram of a planetary gearbox in a method for diagnosing faults in rotating machinery provided by an embodiment of the present invention;

[0082] Figure 4It is a time domain waveform diagram of a vibration signal in a rotating machinery fault diagnosis method provided by an embodiment of the present invention;

[0083] Figure 5 Schematic diagram of the rotation frequency of a motor in a rotating machinery fault diagnosis method provided by an embodiment of the present invention;

[0084] Figure 6 It is a short-time Fourier transform time-frequency diagram of a vibration signal in a rotating machinery fault diagnosis method provided by an embodiment of the present invention;

[0085] Figure 7 It is an initial instantaneous frequency graph obtained by ridge line detection from a short-time Fourier transform time-frequency graph in a rotating machinery fault diagnosis method provided by an embodiment of the present invention;

[0086] Figure 8 Schematic diagram of estimated instantaneous frequency in a rotating machinery fault diagnosis method provided by an embodiment of the present invention;

[0087] Figure 9 1 is a time-frequency diagram of an estimated instantaneous frequency in a rotating machinery fault diagnosis method provided by an embodiment of the present invention;

[0088] Figure 10 Schematic diagram of instantaneous frequency of conventional variational nonlinear frequency modulation mode decomposition estimation provided by an embodiment of the present invention;

[0089] Figure 11 1 is a time-frequency diagram of the instantaneous frequency of the conventional variational nonlinear frequency modulation mode decomposition estimation provided by an embodiment of the present invention;

[0090] Among them, 1. Drive motor; 2. Input encoder; 3. Planetary gearbox; 4. Output encoder; 5. Electromagnetic brake. DETAILED DESCRIPTION

[0091] The technical solution of the present invention is described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical solution of the present application, rather than limitations on the technical solution of the present application. Unless there is a conflict, the embodiments of the present application and the technical features in the embodiments can be combined with each other.

[0092] As used herein, the term "and / or" simply describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A alone, A and B, or B alone. Furthermore, the character " / " generally indicates an "or" relationship between the associated objects.

[0093] Example 1:

[0094] The rotating machinery in the present invention is introduced by taking a planetary gearbox as an example. Figure 2 The figure shows a planetary gearbox test bench. The test bench includes an electromagnetic brake 5, an output encoder 4, a planetary gearbox 3, an accelerometer mounted on the planetary gearbox (not shown), an input encoder 2, and a drive motor 1. The electromagnetic brake was used to load the output shaft, and the accelerometer was used to collect vibration signals. The signals were sampled at 5000 Hz with a sampling time of 2.5 seconds. Furthermore, during the experiment, the motor controller was manually adjusted to cause the speed to accelerate and decelerate. Figure 3 The schematic diagram of the planetary gearbox is given. The planetary gearbox includes a 20-tooth sun gear Z S , an 82-tooth ring gear Z R and three evenly distributed 31-tooth planetary gears Z p When the sun gear and planetary carrier are connected to the input shaft and output shaft respectively, the ring gear is in a stationary state. According to the structural parameters of the planetary gearbox, the theoretical fault characteristic frequency of the planetary gear, sun gear and ring gear is calculated as ,in is the rotation frequency.

[0095] Figure 1 This is a flow chart of the rotating machinery fault diagnosis method in the first embodiment of the present invention. This flow chart only shows the logical sequence of the method described in this embodiment. In other possible embodiments of the present invention, different methods may be used without conflict. Figure 1 The steps shown or described are accomplished in the order shown.

[0096] The rotating machinery fault diagnosis method provided in this embodiment can be applied to a terminal and can be executed by a mechanical equipment fault identification device. The device can be implemented by software and / or hardware and can be integrated into a terminal, such as any smartphone, tablet computer, or computer device with communication capabilities. The method of this embodiment specifically includes the following steps:

[0097] Step 1: Obtain the vibration signal. Install the accelerometer on the device under test to collect the vibration signal. Then intercept the 2.5s vibration signal and remove the mean. The vibration signal is recorded as The time domain waveform of the vibration signal is as follows: Figure 4 As shown in the figure, the motor's rotation frequency is as follows Figure 5 shown.

[0098] Step 2: Input the vibration signal into a pre-built fault diagnosis model, perform a demodulation operation on the vibration signal to obtain a demodulated signal corresponding to the vibration signal, and apply smoothness constraints and sparsity constraints to the demodulated signal to obtain a constrained demodulated signal. The expression of the demodulated signal is:

[0099] ,

[0100] ,

[0101] Among them hour, Has the narrowest bandwidth, that is, the demodulated signal, so these two demodulated signals The difference is based on the trigonometric transformation formula and the difference angle formula in the demodulation technology. Sine and cosine demodulation correspond to the orthogonal component and in-phase component of the signal respectively. The demodulation results are essentially different, and the subsequent processed demodulated signals are the same.

[0102] Smoothness constraints:

[0103] Q1: ,

[0104] Sparsity constraints:

[0105] Q2: ,

[0106] Q3: ,

[0107] in, Indicates the modes, M represents the total number of modes, Indicates the moment, Respectively represent The mode in The first demodulated signal and the second demodulated signal are subjected to the smoothness constraint at every moment, g(t) is expressed as the constraint function, Respectively The second derivative of Indicates the modal The instantaneous amplitude at time, and Respectively represent modal The modulation frequency and demodulation frequency at the moment, the parameter s represents a variable in the interval [0, t] of the variable limit integral, and Respectively represent The modulation frequency and demodulation frequency of each mode at time s, represents the initial phase, and are the first demodulation operator and the second demodulation operator respectively, Indicates the The mode in The first demodulated signal and the second demodulated signal that are subject to sparsity constraints at all times, are the first penalty coefficient and the second penalty coefficient respectively, is the Fourier transform matrix;

[0108] It is explained here that the constrained demodulated signal is a demodulated signal subjected to smoothness constraints and restriction constraints.

[0109] Step 3: Discretize the constrained demodulated signal to obtain the demodulated signal after discretization:

[0110] Q4: ,

[0111] Q5: ,

[0112] Q6: ,

[0113] ,

[0114] ,

[0115] ,

[0116] ,

[0117] ,

[0118] ,

[0119] ,

[0120] in, represents the sampling duration from time 0 to time N-1, g represents the vibration signal, which is the representation of the vibration signal after discretization processing; and Respectively represent The first demodulated signal and the second demodulated signal after the modal discretization processing and smoothness constraint are and Respectively represent A first demodulated signal and a second demodulated signal after the modal discretization processing and the sparsity constraint; and express The general form after discretization; Expressed as The modulation frequency of each mode, are the first and second penalty coefficients respectively, is the second-order difference matrix; represents a diagonal matrix, is transposed; represents the kernel matrix, Expressed as The demodulation operator at time t is expressed as , Expressed as The demodulation operator at time t is expressed as , Represents the phase of the trigonometric function at time t.

[0121] Step 4: Solve the demodulated signal after the discretization process by using the augmented Lagrange multiplier method and the alternating direction multiplier method to obtain the demodulated signal after iterative optimization:

[0122] Solving Q4 by augmented Lagrange multipliers and alternating direction multiplier method yields:

[0123] ,

[0124] ,

[0125] ,

[0126] in, Indicates vibration signal, Corresponding to the qth mode in the The first demodulated signal value and the second demodulated signal value at the iteration, Respectively represent the qth mode in the The first and second kernel matrix values ​​corresponding to the iteration (note that for the sake of simplicity of notation, the iteration counter (i.e., superscript n) of each variable is omitted on the right side of the equation);

[0127] Introducing the first auxiliary function The Q5 is constructed as a constrained optimization problem and solved by augmented Lagrange multipliers and alternating direction multipliers method:

[0128] ,

[0129] ,

[0130] ,

[0131] The second auxiliary function h is introduced to construct Q6 as a constrained optimization problem, which is solved by augmented Lagrange multipliers and alternating direction multiplier method:

[0132] ,

[0133] ,

[0134] ,

[0135] in, represents the first iteration number, represents the third penalty coefficient, represents the first Lagrange multiplier, represents the second iteration number, represents the fourth penalty coefficient, represents the second Lagrange multiplier, represents the soft threshold function, represents the third iteration number, h is the second auxiliary function, is the fifth penalty coefficient, is the third Lagrange multiplier.

[0136] Step 5: Calculating the instantaneous frequency increment based on the iteratively optimized demodulated signal, applying smoothness constraints and low-rank constraints to the instantaneous frequency increment, and obtaining the estimated instantaneous frequency through an iterative solution algorithm includes:

[0137] Based on the iteratively optimized demodulated signal, obtaining an instantaneous frequency increment by an inverse tangent demodulation method includes:

[0138] ,

[0139] Discretizing the instantaneous frequency increment to obtain a discretized instantaneous frequency increment, adding a smoothness constraint to the discretized instantaneous frequency increment, solving to obtain an expected instantaneous frequency increment, and obtaining an initially optimized estimated instantaneous frequency according to the expected instantaneous frequency increment.

[0140] ,

[0141] ,

[0142] ,

[0143] ,

[0144] in, is the sixth penalty coefficient, , is the desired instantaneous frequency increment, represents the identity matrix, Represented as an iteration The estimated instantaneous frequency of the initial optimization, Represented as an iteration The estimated instantaneous frequency of the initial optimization;

[0145] Constructing a noise measurement matrix according to the initially optimized estimated instantaneous frequency, adding a low-rank constraint to the noise measurement matrix, and obtaining the estimated instantaneous frequency includes:

[0146] Q7: ,

[0147] in, To estimate the instantaneous frequency, is a low-rank matrix, Initial optimization The noise observation matrix composed of is the seventh penalty coefficient, Representation matrix No. singular values, Representation matrix The Frobenius norm of ;

[0148] Solving Q7 by shrinking the singular values ​​of the noise measurement matrix yields:

[0149] ,

[0150] in, Both are matrices The orthogonal matrix obtained after applying singular value decomposition, is the The maximum singular value of Each row of represents the estimated instantaneous frequency.

[0151] Step 6: Based on the pre-acquired theoretical fault characteristic frequency and the estimated instantaneous frequency, determine the type of rotating machinery fault according to the matching result:

[0152] According to the structural parameters and rotation frequency of the rotating machinery, the theoretical fault characteristic frequency of the rotating machinery is calculated, the estimated instantaneous frequency is compared with the theoretical fault characteristic frequency, and the type of rotating machinery fault is determined based on the matching results;

[0153] It should be noted that the calculation of the theoretical fault characteristic frequency here is simply to substitute parameters into the publicly available formula for the fault characteristic frequency of rotating machinery (in this embodiment, specifically the formula for the fault characteristic frequency of gears: sun gear, planetary gear, and ring gear; bearing: inner ring, outer ring, and roller). This is a prior art and will not be further described here.

[0154] The instantaneous frequency estimated by the method proposed in this patent has been shown in the above steps. Here, it is only compared with the theoretical fault characteristic frequency to determine the fault location of the rotating machinery. This is also a prior art and will not be repeated here.

[0155] Figure 6 and Figure 7The time-frequency diagram of the short-time Fourier transform of the vibration signal and the initial instantaneous frequency diagram obtained by ridge detection from the short-time Fourier transform time-frequency diagram are respectively given. From the initial instantaneous frequency diagram, it can be seen that the initial instantaneous frequencies are mutually aliased and seriously deviate from the true instantaneous frequency. Using these initial instantaneous frequencies, the instantaneous frequency estimated by the method of the present invention and its time-frequency diagram are respectively as follows: Figure 8 and Figure 9 As shown. Figure 8 It can be seen that the method of the present invention accurately estimates the rotation frequency , gear ring fault characteristic frequency and its harmonics , indicating that the planetary gearbox ring gear fault was accurately diagnosed; at the same time Figure 9 The time-frequency diagram of the estimated instantaneous frequency is given, in which the influence of noise is eliminated. This information verifies that the method of the present invention can effectively improve the accuracy of instantaneous frequency estimation even in the case of severe noise and inaccurate initial instantaneous frequency, and realize gearbox fault diagnosis. The instantaneous frequency estimated by traditional variational nonlinear frequency modulation mode decomposition and its time-frequency diagram are shown as follows: Figure 10 and Figure 11 As shown, from Figure 10 No fault-related frequencies can be identified in the simulation, and the estimated instantaneous frequency distribution is consistent with the initial instantaneous frequency, which shows that the traditional variational nonlinear frequency modulation mode decomposition has poor accuracy in estimating instantaneous frequencies due to its own limitations and cannot be used for planetary gearbox fault diagnosis.

[0156] It should be noted that Figure 10 Initial is translated as initial value, and Estimated is translated as estimated value.

[0157] The method of the present invention can be designed as rotating machinery fault diagnosis software, which is installed in a host computer. The host computer is connected to a signal acquisition device. The host computer processes the vibration signal in the above steps in real time to diagnose the rotating machinery fault and determine the fault type in a timely manner, thereby ensuring the safe operation of the entire mechanical system.

[0158] Example 2:

[0159] A second embodiment of the present invention provides a rotating machinery fault diagnosis device, comprising:

[0160] A signal acquisition module, used to acquire vibration signals;

[0161] a demodulation signal optimization module, configured to input the vibration signal into a pre-built fault diagnosis model, extract a demodulation signal from the decomposed nonlinear frequency modulation mode, and impose smoothness constraints and sparsity constraints on the demodulation signal to obtain a constrained demodulation signal;

[0162] A discretization module, configured to discretize the constrained demodulated signal to obtain the discretized demodulated signal;

[0163] A solution module, configured to solve the demodulated signal after the discretization process by using an augmented Lagrange multiplier method and an alternating direction multiplier method to obtain an iteratively optimized demodulated signal;

[0164] An estimated instantaneous frequency acquisition module is configured to calculate an instantaneous frequency increment based on the iteratively optimized demodulated signal, impose smoothness constraints and low-rank constraints on the instantaneous frequency increment, and obtain an estimated instantaneous frequency by solving the problem through an iterative solution algorithm;

[0165] The fault confirmation module is used to determine the type of rotating machinery fault based on the pre-acquired theoretical fault characteristic frequency and the estimated instantaneous frequency according to a matching result.

[0166] The rotating machinery fault diagnosis device provided in the second embodiment of the present invention can execute the rotating machinery fault diagnosis method provided in the first embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0167] Example 3:

[0168] The third embodiment of the present invention further provides an electronic terminal, comprising a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and the processor is configured to operate according to the instructions to execute the steps of the method described in the first embodiment.

[0169] The electronic terminal provided in the third embodiment of the present invention can execute the rotating machinery fault diagnosis method provided in the first embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0170] Example 4:

[0171] Embodiment 4 of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in embodiment 1 are implemented, and the computer program has functional modules and beneficial effects corresponding to the execution method.

[0172] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, apparatuses, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0173] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (apparatus), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0174] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0175] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0176] 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 diagnosing a rotating machinery fault, characterized in that: include: Obtain vibration signals; performing a demodulation operation on the vibration signal to obtain a demodulated signal corresponding to the vibration signal, and applying a smoothness constraint and a sparsity constraint to the demodulated signal to obtain a constrained demodulated signal; Discretizing the constrained demodulated signal to obtain a demodulated signal after discretization; Solving the demodulated signal after the discretization processing by using the augmented Lagrange multiplier method and the alternating direction multiplier method to obtain the demodulated signal after iterative optimization; Calculating an instantaneous frequency increment based on the iteratively optimized demodulated signal, applying a smoothness constraint and a low-rank constraint to the instantaneous frequency increment, and obtaining an estimated instantaneous frequency by solving the problem through an iterative solution algorithm; The type of the rotating machinery fault is determined based on the pre-acquired theoretical fault characteristic frequency and the estimated instantaneous frequency.

2. The rotating machinery fault diagnosis method according to claim 1, characterized in that: Applying a smoothness constraint and a sparsity constraint to the demodulated signal to obtain a constrained demodulated signal includes: The expression of the demodulated signal is: ， ， Smoothness constraints: Q1： ， Sparsity constraints: Q2： ， Q3： ， in, Indicates the modes, M represents the total number of modes, Indicates the moment, Respectively represent The mode in The first demodulated signal and the second demodulated signal are subjected to the smoothness constraint at every moment, g(t) is expressed as the constraint function, Respectively The second derivative of Indicates the modal The instantaneous amplitude at time and Respectively represent modal The modulation frequency and demodulation frequency at the moment, the parameter s represents a variable in the interval [0, t] of the variable limit integral, and Respectively represent The modulation frequency and demodulation frequency of each mode at time s, represents the initial phase, and are the first demodulation operator and the second demodulation operator respectively, Indicates the The mode in The first demodulated signal and the second demodulated signal that are subject to sparsity constraints at all times, are the first penalty coefficient and the second penalty coefficient respectively, is the Fourier transform matrix.

3. The rotating machinery fault diagnosis method according to claim 2, characterized in that: Discretizing the constrained demodulated signal to obtain the discretized demodulated signal includes: Q4： ， Q5： ， Q6： ， ， ， ， ， ， ， ， in, represents the sampling duration from time 0 to time N-1, g represents the vibration signal, which is the representation of the vibration signal after discretization processing; and Respectively represent The first demodulated signal and the second demodulated signal after the modal discretization processing and smoothness constraint are and Respectively represent A first demodulated signal and a second demodulated signal after the modal discretization processing and the sparsity constraint; and express The general form after discretization; Expressed as The modulation frequency of each mode, are the first and second penalty coefficients respectively, is the second-order difference matrix; represents a diagonal matrix, is transposed; represents the kernel matrix, Expressed as The demodulation operator at time t is expressed as , Expressed as The demodulation operator at time t is expressed as , Represents the phase of the trigonometric function at time t.

4. The rotating machinery fault diagnosis method according to claim 3, characterized in that: Solving the demodulated signal after the discretization processing by using the augmented Lagrange multiplier method and the alternating direction multiplier method to obtain the demodulated signal after iterative optimization includes: Solving Q4 by augmented Lagrange multipliers and alternating direction multiplier method yields: ， ， ， in, Indicates vibration signal, Corresponding to the qth mode in the The first demodulated signal value and the second demodulated signal value at the iteration, Respectively represent the qth mode in the The first kernel matrix value and the second kernel matrix value corresponding to the iteration; Introducing the first auxiliary function The Q5 is constructed as a constrained optimization problem and solved by augmented Lagrange multipliers and alternating direction multipliers method: ， ， ， The second auxiliary function h is introduced to construct Q6 as a constrained optimization problem, which is solved by augmented Lagrange multipliers and alternating direction multiplier method: ， ， ， in, represents the first iteration number, represents the third penalty coefficient, represents the first Lagrange multiplier, represents the second iteration number, represents the fourth penalty coefficient, represents the second Lagrange multiplier, represents the soft threshold function, represents the third iteration number, h is the second auxiliary function, is the fifth penalty coefficient, is the third Lagrange multiplier.

5. The rotating machinery fault diagnosis method according to claim 4, characterized in that: Calculating an instantaneous frequency increment based on the iteratively optimized demodulated signal, applying a smoothness constraint and a low-rank constraint to the instantaneous frequency increment, and obtaining an estimated instantaneous frequency by an iterative solution algorithm includes: Based on the iteratively optimized demodulated signal, obtaining an instantaneous frequency increment by an inverse tangent demodulation method includes: ， Discretizing the instantaneous frequency increment to obtain a discretized instantaneous frequency increment, adding a smoothness constraint to the discretized instantaneous frequency increment, solving to obtain an expected instantaneous frequency increment, and obtaining an initially optimized estimated instantaneous frequency according to the expected instantaneous frequency increment. ， ， ， ， in, is the sixth penalty coefficient, , is the desired instantaneous frequency increment, represents the identity matrix, Represented as an iteration The estimated instantaneous frequency of the initial optimization, Represented as an iteration The estimated instantaneous frequency of the initial optimization; Constructing a noise measurement matrix according to the initially optimized estimated instantaneous frequency, adding a low-rank constraint to the noise measurement matrix, and obtaining the estimated instantaneous frequency includes: Q7： ， in, To estimate the instantaneous frequency, is a low-rank matrix, Initial optimization The noise observation matrix composed of is the seventh penalty coefficient, Representation matrix No. singular values, Representation matrix The Frobenius norm of ; Solving Q7 by shrinking the singular values ​​of the noise measurement matrix yields: , in, Both are matrices The orthogonal matrix obtained after applying singular value decomposition, is the The maximum singular value of Each row of represents the estimated instantaneous frequency.

6. The rotating machinery fault diagnosis method according to claim 5, characterized in that: Determining the type of rotating machinery fault based on the pre-acquired theoretical fault characteristic frequency and the estimated instantaneous frequency includes: According to the structural parameters and rotation frequency of the rotating machinery, the theoretical fault characteristic frequency of the rotating machinery is calculated, the estimated instantaneous frequency is compared with the theoretical fault characteristic frequency, and the rotating machinery fault type is determined based on the matching results.

7. A rotating machinery fault diagnosis device, characterized in that: include: A signal acquisition module, used to acquire vibration signals; a demodulation signal optimization module, configured to perform a demodulation operation on the vibration signal to obtain a demodulation signal corresponding to the vibration signal, and impose a smoothness constraint and a sparsity constraint on the demodulation signal to obtain a constrained demodulation signal; A discretization module, configured to discretize the constrained demodulated signal to obtain the discretized demodulated signal; A solution module, configured to solve the demodulated signal after the discretization process by using an augmented Lagrange multiplier method and an alternating direction multiplier method to obtain an iteratively optimized demodulated signal; An estimated instantaneous frequency acquisition module is configured to calculate an instantaneous frequency increment based on the iteratively optimized demodulated signal, impose smoothness constraints and low-rank constraints on the instantaneous frequency increment, and obtain an estimated instantaneous frequency by solving the problem through an iterative solution algorithm; The fault confirmation module is used to determine the type of rotating machinery fault based on the pre-acquired theoretical fault characteristic frequency and the estimated instantaneous frequency.

8. An electronic terminal, characterized in that: The method comprises a processor and a memory connected to the processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are performed.

9. 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 method according to any one of claims 1 to 6 are implemented.

Images