Multi-stage planetary gearbox detection method and device, electronic equipment and storage medium

Abstract

The invention provides a multi-stage planetary gearbox detection method and device, electronic equipment and a storage medium. The method comprises the following steps: respectively acquiring vibration acceleration data corresponding to the input end and the output end of the multi-stage planetary gearbox; based on the vibration acceleration data, respectively constructing a first mixed state data set corresponding to the output end and a second mixed state data set corresponding to the input end; respectively determining a first probability density matrix between the input end and the output end and a second probability density matrix corresponding to the output end based on the first mixed state data set and the second mixed state data set; respectively determining characteristic values corresponding to the first probability density matrix and the second probability density matrix, and calculating a spatial coupling entropy based on the characteristic values; and when the space coupling entropy exceeds a preset threshold range, determining that the multi-stage planetary gearbox has a fault. According to the invention, the fault detection precision of the multi-stage planetary gearbox can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a detection method, device, electronic equipment and storage medium for a multi-stage planetary gearbox. Background Art

[0002] Multi-stage planetary gearbox is a complex mechanical transmission device, which is widely used in wind power generation, ships, shield machines and other application scenarios that require high transmission ratio and high torque.

[0003] The multi-stage planetary gearbox is the core component of high-speed tracked vehicles. The multi-stage planetary gearbox contains three to four planetary gears, and the operation parts control the combination and separation of different planetary gears to realize the shifting function of high-speed tracked vehicles. The operating state of the multi-stage planetary gearbox will seriously affect the working state of the high-speed tracked vehicle. Therefore, it is necessary to monitor the operating state of the multi-stage gearbox in real time to ensure the safe and smooth operation of the high-speed tracked vehicle.

[0004] In the related art, most of the methods are to detect whether a multi-stage planetary gearbox has a fault by analyzing the vibration signal of the multi-stage planetary gearbox. However, there are multiple pairs of meshing gears inside the multi-stage planetary gearbox, and the structure is relatively complex, which makes the vibration signal have strong nonlinearity, asymmetry and time variability. These characteristics make the analysis of vibration signals more difficult, and the fault characteristics are easily masked or confused by noise. In addition, the vibration signals of different gears will couple with each other, resulting in complex and non-stationary components of the vibration response. This coupling effect makes it difficult to identify the fault component from the original vibration signal.

[0005] In summary, the existing vibration signal analysis method is not suitable for multi-stage planetary gearboxes with complex structures, and the fault state detection accuracy of multi-stage planetary gearboxes is low. Summary of the invention

[0006] Embodiments of the present invention provide a detection method, device, electronic device and storage medium for a multi-stage planetary gearbox to improve the fault state detection accuracy of the multi-stage planetary gearbox.

[0007] In a first aspect, an embodiment of the present invention provides a method for detecting a multi-stage planetary gearbox, comprising:

[0008] Respectively obtain vibration acceleration data corresponding to the input end and the output end of the multi-stage planetary gearbox;

[0009] Based on the vibration acceleration data, construct a first mixed state data set corresponding to the output end and a second mixed state data set corresponding to the input end respectively;

[0010] Based on the first mixed state data set and the second mixed state data set, respectively determine a first probability density matrix between the input end and the output end, and a second probability density matrix corresponding to the output end;

[0011] Determine the eigenvalues ​​corresponding to the first probability density matrix and the second probability density matrix respectively, and calculate the spatial coupling entropy based on the eigenvalues; the spatial coupling entropy is used to reflect the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end of the multi-stage planetary gearbox;

[0012] When the spatial coupling entropy exceeds a preset threshold range, it is determined that the multi-stage planetary gearbox fails.

[0013] In a possible implementation, a plurality of measuring points are respectively set at the input end and the output end of the multi-stage planetary gearbox; the first mixed state data set includes: vibration acceleration data corresponding to a plurality of first subsystems; the vibration acceleration data corresponding to each first subsystem includes: vibration acceleration data at different measuring points of the output end at different times; the second mixed state data set includes: vibration acceleration data corresponding to a plurality of second subsystems; the vibration acceleration data corresponding to each second subsystem includes: vibration acceleration data at different measuring points of the input end at different times;

[0014] The determining, based on the first mixed state data set and the second mixed state data set, respectively a first probability density matrix between the input end and the output end, and a second probability density matrix corresponding to the output end, comprises:

[0015] Determine the conditional probability distribution between different first subsystems and second subsystems based on the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem;

[0016] Determining conditional probability distributions of different first subsystems based on the vibration acceleration data corresponding to each first subsystem;

[0017] Based on the conditional probability distribution between different first subsystems and second subsystems, construct a first probability density matrix;

[0018] Based on the conditional probability distributions of different first subsystems, a second probability density matrix is ​​constructed.

[0019] In a possible implementation, determining the conditional probability distribution between different first subsystems and second subsystems based on the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem includes:

[0020] Sequentially sampling and mapping the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem, respectively, to obtain a first integer sequence corresponding to each first subsystem and a second integer sequence corresponding to each second subsystem;

[0021] according to determining a conditional probability distribution between the kth first subsystem and the kth second subsystem;

[0022] Among them, p k (x i-w |x i-1-w ,y i-t ) represents the conditional probability distribution between the kth first subsystem and the kth second subsystem, x i-w represents the vibration acceleration data of the kth first subsystem at the iwth moment, x i-1-w represents the vibration acceleration data of the kth first subsystem at the i-1-wth moment, y i-t represents the vibration acceleration data of the kth second subsystem at the itth moment, p k (v i-w ,v i-1-w ,u i-t ) indicates v i-w 、v i-1-w and u i-t The joint probability of occurrence, v i-w represents the data set at time iw in the first integer sequence corresponding to the kth first subsystem, v i-1-w represents the data at time i-1-w in the first integer sequence corresponding to the kth first subsystem, u i-t represents the data at time it in the second integer sequence corresponding to the kth second subsystem, p k (v i-w ,u i-t ) indicates v i-1-w and u i-t The joint probability of occurrence.

[0023] In a possible implementation, determining the conditional probability distribution of different first subsystems based on the vibration acceleration data corresponding to each first subsystem includes:

[0024] according to Determine the conditional probability distribution of the kth first subsystem;

[0025] Among them, p k (x i-w |x i-1-w ) represents the conditional probability distribution of the kth first subsystem.

[0026] In a possible implementation, constructing a first probability density matrix based on conditional probability distributions between different first subsystems and second subsystems includes:

[0027] according to Constructing a first probability density matrix;

[0028] in, represents the first probability density matrix, K represents the total number of the second subsystems, ω k represents the weight of the kth second subsystem.

[0029] In a possible implementation, constructing a second probability density matrix based on conditional probability distributions of different first subsystems includes:

[0030] according to Constructing a second probability density matrix;

[0031] in, represents the second probability density matrix, L represents the total number of the first subsystems, ω l represents the weight of the lth first subsystem, p l (x i-w |x i-1-w ) represents the conditional probability distribution of the lth first subsystem.

[0032] In a possible implementation manner, calculating the spatial coupling entropy based on the eigenvalue includes:

[0033] according to Calculate spatial coupling entropy;

[0034] Among them, MSCE Y→X represents the spatial coupling entropy, τ represents the scale parameter, represents the jth eigenvalue in the first probability density matrix, Indicates the first eigenvalues, and n represents the number of eigenvalues.

[0035] In a second aspect, an embodiment of the present invention provides a detection device for a multi-stage planetary gearbox, comprising:

[0036] An acquisition module, used to respectively acquire vibration acceleration data corresponding to the input end and the output end of the multi-stage planetary gearbox;

[0037] Compute module for:

[0038] Based on the vibration acceleration data, construct a first mixed state data set corresponding to the output end and a second mixed state data set corresponding to the input end respectively;

[0039] Based on the first mixed state data set and the second mixed state data set, respectively determine a first probability density matrix between the input end and the output end, and a second probability density matrix corresponding to the output end;

[0040] Determine the eigenvalues ​​corresponding to the first probability density matrix and the second probability density matrix respectively, and calculate the spatial coupling entropy based on the eigenvalues; the spatial coupling entropy is used to reflect the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end of the multi-stage planetary gearbox;

[0041] The detection module is used to determine that the multi-stage planetary gearbox fails when the spatial coupling entropy exceeds a preset threshold range.

[0042] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the processor implements the steps of the method described in the first aspect or any possible implementation manner of the first aspect.

[0043] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation method of the first aspect are implemented.

[0044] The embodiment of the present invention provides a detection method, device, electronic device and storage medium for a multi-stage planetary gearbox, which converts vibration acceleration data into mixed state data, and determines a first probability density matrix and a second probability density matrix based on the mixed state data, thereby determining spatial coupling entropy, wherein the spatial coupling entropy can reflect the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end. The embodiment of the present invention quantitatively calculates the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end, and is used to determine whether a multi-stage planetary gearbox has a fault, without the need to perform a step-by-step signal analysis on the multi-stage vibration signals inside the multi-stage planetary gearbox, which can not only effectively simplify the fault detection method, but also will not be affected by the complex gear meshing structure inside the multi-stage planetary gearbox, thereby improving the fault detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0046] Figure 1 is a simplified structural diagram of a multi-stage planetary gearbox provided by an embodiment of the present invention;

[0047] Figure 2 is a flow chart of an implementation of a detection method for a multi-stage planetary gearbox provided by an embodiment of the present invention;

[0048] Figure 3 is a schematic diagram of measuring point layout provided by an embodiment of the present invention;

[0049] Figure 4 is a comparison schematic diagram before and after the dual time delay processing provided by an embodiment of the present invention;

[0050] Figure 5 is a spatial coupling entropy variation trend diagram of a multi-stage planetary gearbox provided by an embodiment of the present invention;

[0051] Figure 6 is a schematic structural diagram of a detection device for a multi-stage planetary gearbox provided in an embodiment of the present invention;

[0052] Figure 7 is a schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.

[0054] In the related art, most of them detect whether the multi-stage planetary gearbox has a fault by analyzing the vibration signal of the multi-stage planetary gearbox. However, there are multiple pairs of gears meshing inside the multi-stage planetary gearbox, and the structure is relatively complicated. For example, Figure 1The multi-stage planetary gearbox commonly used in high-speed tracked vehicles shown in the figure has three brakes, three clutches and six shifting elements. The complex internal structure makes the vibration signal highly nonlinear, asymmetric and time-variable. These characteristics make the vibration signal analysis more difficult, and the fault characteristics are easily masked or confused by noise. In addition, the vibration signals of different gears are coupled with each other, resulting in complex and non-stationary components of the vibration response. This coupling effect makes it difficult to identify the fault component from the original vibration signal.

[0055] With the idea of ​​improving the fault state detection accuracy of a multi-stage planetary gearbox, an embodiment of the present invention converts macroscopic vibration acceleration data into microscopic mixed state data, and determines the spatial coupling entropy based on the mixed state data to realize fault detection for a multi-stage planetary gearbox. Here, the spatial coupling entropy can reflect the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end. The embodiment of the present invention quantitatively calculates the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end to determine whether a multi-stage planetary gearbox has a fault. There is no need to perform a step-by-step signal analysis on the multi-stage vibration signals inside the multi-stage planetary gearbox. This can not only effectively simplify the fault detection method, but also will not be affected by the complex gear meshing structure inside the multi-stage planetary gearbox, thereby improving the fault detection accuracy.

[0056] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0057] Figure 2 The implementation flow chart of the detection method of the multi-stage planetary gearbox provided by the embodiment of the present invention is described in detail as follows:

[0058] Step 201 : respectively obtain vibration acceleration data corresponding to the input end and the output end of the multi-stage planetary gearbox.

[0059] The embodiment of the present invention comprehensively considers the influence of nonlinear and non-smooth factors such as the fault vibration signal transmission path, and can arrange multiple groups of vibration acceleration sensors at key positions on the surface of the multi-stage planetary gearbox, with 3-4 three-way sensors in each group, to establish a sensor array, and synchronously collect vibration acceleration signals in the three directions of X, Y and Z. The embodiment of the present invention mainly sets multiple measuring points on the surface of the multi-stage planetary gearbox, near the input shaft and the output shaft, to collect vibration acceleration near the input shaft and the output shaft. Or, for example, see Figure 3 Different measuring points can also be set at different positions between the input shaft and the output shaft to increase the data acquisition range and improve the calculation accuracy of the spatial coupling entropy.

[0060] Among them, when collecting vibration acceleration, the vibration acceleration data under different gears and different loads can be collected. For example, the multi-stage planetary gearbox has seven gears, including 5 forward gears and 2 reverse gears, the speed is set to 2500rpm, and the torque at the input end is set to three loads of no-load, 50% of the rated torque (1425N·m), and rated torque (2850N·m). Three typical gears, namely the second gear, the third gear, and the fourth gear, are selected as test conditions. The sampling frequency of the sensor is 40960Hz, the test time is 1min, and the data of the third channel (i.e., the z direction) of the sensor is used for subsequent calculations. The basic sample number of each gear condition is 10240, and the vibration acceleration data of different gears and different loads are collected respectively.

[0061] Step 202, based on the vibration acceleration data, construct a first mixed state data set corresponding to the output end and a second mixed state data set corresponding to the input end respectively;

[0062] Mixed state is an important concept in quantum mechanics, which is used to describe the states of quantum systems that cannot be represented by a single state vector. Mixed states are usually composed of multiple pure states with a certain probability distribution, and this combination can be mathematically described by a density matrix.

[0063] The embodiment of the present invention can convert the vibration acceleration data information collected in the macroscopic physical system into mixed state data in the microscopic quantum system.

[0064] Here, the first mixed state data set includes: vibration acceleration data corresponding to multiple first subsystems; the vibration acceleration data corresponding to each first subsystem includes: vibration acceleration data at different measuring points of the output end at different times. The second mixed state data set includes: vibration acceleration data corresponding to multiple second subsystems; the vibration acceleration data corresponding to each second subsystem includes: vibration acceleration data at different measuring points of the input end at different times.

[0065] The subsystem can be simply understood as the concept of pure state. Each first subsystem mainly refers to each pure state corresponding to the output end. Each second subsystem mainly refers to each pure state corresponding to the input end.

[0066] The first mixed state data set can be expressed as: X = {X1, X2, ... X l ,…,X L The second mixed state data set can be expressed as: Y = {Y1, Y2, ... Y k ,…,Y K}.

[0067] Where X represents the first mixed state data set, X 1、 X 2、 X l and XL They represent the second subsystem in the first mixed state data set, L represents the total number of the first subsystems, Y represents the second mixed state data set, and Y 1、 Y 2、 Y k and Y K They respectively represent the first subsystems in the second mixed state data set, and K represents the total number of second subsystems.

[0068] Step 203: Based on the first mixed state data set and the second mixed state data set, respectively determine a first probability density matrix between the input end and the output end, and a second probability density matrix corresponding to the output end.

[0069] The probability density matrix represents the synergistic fusion of multi-source asymmetric time series in the mixed state at the joint conditional probability level. This synergistic fusion relationship is established under the dynamic instantaneous transmission and coupling of potential information between each measuring point, and encompasses the scales of space and time.

[0070] When determining the first probability density matrix and the second probability density matrix, the embodiment of the present invention can first determine the conditional probability distribution between different first subsystems and second subsystems based on the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem; then, determine the conditional probability distribution of different first subsystems based on the vibration acceleration data corresponding to each first subsystem; then, construct the first probability density matrix based on the conditional probability distribution between different first subsystems and second subsystems; and construct the second probability density matrix based on the conditional probability distribution of different first subsystems.

[0071] In some embodiments, when determining the conditional probability distribution between different first subsystems and second subsystems, the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem may be sequentially sampled and mapped to obtain a first integer sequence corresponding to each first subsystem and a second integer sequence corresponding to each second subsystem; then, according to determining a conditional probability distribution between the kth first subsystem and the kth second subsystem;

[0072] Among them, p k (x i-w |x i-1-w ,y i-t ) represents the conditional probability distribution between the kth first subsystem and the kth second subsystem, x i-w represents the vibration acceleration data of the kth first subsystem at the iwth moment, x i-1-w represents the vibration acceleration data of the kth first subsystem at the i-1-wth moment, y i-trepresents the vibration acceleration data of the kth second subsystem at the itth moment, p k (v i-w ,v i-1-w ,u i-t ) indicates v i-w 、v i-1-w and u i-t The joint probability of occurrence, v i-w represents the data set at time iw in the first integer sequence corresponding to the kth first subsystem, v i-1-w represents the data at time i-1-w in the first integer sequence corresponding to the kth first subsystem, u i-t represents the data at time it in the second integer sequence corresponding to the kth second subsystem, p k (v i-w ,u i-t ) indicates v i-1-w and u i-t The joint probability of occurrence.

[0073] In some embodiments, the Determine the conditional probability distribution of the kth first subsystem;

[0074] Among them, p k (x i-w |x i-1-w ) represents the conditional probability distribution of the kth first subsystem.

[0075] Conditional probability distribution p k (x i-w |x i-1-w ,y i-t ) represents the kth first subsystem X k and the kth second subsystem Y k For the future moment iX k The influence of the state. Conditional probability distribution p k (x i-w |x i-1-w ) represents X k For the future moment iX k the impact of the status.

[0076] Considering the existence of information transmission and coupling relationship Y k and X k The impact on future processes at time scales t and w respectively. Therefore, the embodiment of the present invention adopts a dual time delay method to establish a spatial coupling entropy surface. Figure 4 This is a schematic diagram of the comparison of the double time delay processing of the vibration acceleration data collected by the sensor, see Figure 4 , the solid line represents the time series with time lag relationship, x i-w and xi-1-w For the time series X k A subset of y i-t is the time series Y k A subset of , and x i-w 、x i-1-w and i-t All have the same dimension, and ultimately explore the process X through time delays t and w k and Y k Future Process X at the Information and Energy Level k impact.

[0077] On the basis of the above conditional probability distribution, a quasi-quantization feature fusion is performed, and the state vector function set {|p k (x i-w |x i-1-w ,y i-t )>|k=1…K} and {|p l (x i-w |x i-1-w )>|l=1…L} respectively constitute a mixed state of two different separable states. The probability density matrix represents the synergistic fusion of the characteristic information in the mixed state at the level of joint conditional probability. This synergistic fusion relationship is established under the dynamic transmission and coupling of information between each measuring point, and encompasses the scale of space and time.

[0078] In some embodiments, the

[0079] Constructing a first probability density matrix;

[0080] in, represents the first probability density matrix, K represents the total number of the second subsystems, ω k represents the weight of the kth second subsystem.

[0081] In some embodiments, the

[0082] Construct a second probability density matrix;

[0083] in, represents the second probability density matrix, L represents the total number of the first subsystem, ω l represents the weight of the lth first subsystem, p l (x i-w |x i-1-w ) represents the conditional probability distribution of the lth first subsystem.

[0084] here,

[0085] Step 204, determining the eigenvalues ​​corresponding to the first probability density matrix and the second probability density matrix respectively, and calculating the spatial coupling entropy based on the eigenvalues.

[0086] Here, the spatial coupling entropy is used to reflect the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end of the multi-stage planetary gearbox.

[0087] The probability density matrix ρ (for example, the first probability density matrix ρ K and the second probability density matrix ρ L ) are mostly reversible matrices. Here, let’s assume that the eigenvalue of the probability density matrix ρ is {λ i |i=1,2,...,n}, where {λ i <0|i=1,2,…,k'},{λ i >0|i=k'+1,…,n}. To better handle zero items, the embodiment of the present invention can take the eigenvalue set {λ i >0|i=k'+1,...,n} is a calculation sample. To avoid NAN in the calculation, the embodiment of the present invention selects {λ i >0|i=k'+1,...,n} eigenvalue sets are used to calculate the spatial coupling entropy.

[0088] When calculating the spatial coupling entropy, let the eigenvalue set be The reversible matrix The equivalent invertible matrix with the same set of eigenvalues ​​is And in τ The set of elements located on the diagonal position in is Similarly, let the eigenvalue set be {λ j >0|j=k'+1,...,n} reversible matrix Equivalent invertible matrices with the same set of eigenvalues And in Υ τ The set of elements located on the diagonal position in is {r 11 ,r 22 ,...,r (n-k')(n-k')}.

[0089] On this basis, the embodiment of the present invention defines a method for effectively measuring and quantifying the causal transmission relationship and coupling degree between dynamic information within a space physical system - multidimensional space coupling entropy. The specific mathematical expression is as follows:

[0090]

[0091] In the formula, MSCE Y→Xrepresents the spatial coupling entropy between Y and X, τ represents the scale parameter, and τ∈(0,1)∪(1,∞), t and w represent the time delay of Y and X respectively. Different from the density matrix defined by the relevant Rényi entropy, in the above formula Indicates that in x i-1-w and i-t Under the condition of co-occurrence, x i-1-w and i-t Common future time series x i-w The probability density matrix formed by the influence of Indicates that in x i-1-w Under the condition that i-w The probability density matrix formed by the influence of and r jj Respectively represent matrices and elements of ; n-k'-c are the matrix dimensions.

[0092] In order to study the relevant Rényi entropy , let the eigenvalue set be The reversible matrix Equivalent invertible matrices with the same set of eigenvalues Then take:

[0093]

[0094] The formula can be further simplified to:

[0095]

[0096] In the above formula, tr[ln(Ψ τ )]and Expand separately:

[0097]

[0098]

[0099] After the expansion, tr[ln(Ψ τ )]and Further integration:

[0100]

[0101] Substituting the integrated formula into the mathematical expression of spatial coupling entropy, we get:

[0102]

[0103] Here, λ includes and

[0104] According to the above formula, the embodiment of the present invention can be derived according to

[0105] Calculate spatial coupling entropy;

[0106] Among them, MSCE Y→X represents the spatial coupling entropy, τ represents the scale parameter, represents the jth eigenvalue in the first probability density matrix, Indicates the first eigenvalues, and n represents the number of eigenvalues.

[0107] Step 205: When the spatial coupling entropy exceeds a preset threshold range, it is determined that the multi-stage planetary gearbox fails.

[0108] Here, the preset threshold range can be determined according to the numerical range of the spatial coupling entropy of the multi-stage planetary gearbox in healthy operation. This embodiment of the present invention does not specifically limit this.

[0109] Spatial coupling entropy has the ability to reveal and identify the changing laws of information patterns caused by different states of physical systems, and can, to a certain extent, judge the influence of each time series on the coupling relationship and complexity of the internal information of the future overall system. Spatial coupling entropy can be used to characterize the changes in information coupling relationship and complexity in time series under the full life cycle conditions of complex systems (i.e., multi-stage planetary gearboxes), thereby revealing the potential state evolution process in physical systems.

[0110] For example, Figure 5 The figure shows the spatial coupling entropy variation trend of the multi-stage planetary gearbox, and the variation trend of the spatial coupling entropy accurately represents the operating state of the multi-stage planetary gearbox throughout its life cycle. Figure 5As shown in the figure, before 285 minutes, the amplitude of the multi-stage planetary gearbox was relatively flat, and the entropy value was stable between -4.164 and -4.157. At this time, the size and path of the information transmission energy between the data were in a relatively stable state, indicating that the multi-stage planetary gearbox was in a healthy state and in good operating condition. At the 285th minute of the test, the entropy value suddenly changed, with an amplitude of -4.171, showing a downward trend, indicating that the multi-stage planetary gearbox entered the initial fault state, the energy peak of the fault characteristic frequency continued to rise, the components of the internal information of the system increased, the correlation between the signals changed, and the coupling degree and complexity of the overall information of the system increased. After the test reached the 300th minute (that is, the fault degree of the multi-stage planetary gearbox entered the middle and late stages), the minimum entropy value was -4.197 and the maximum entropy value was -4.141. Compared with the fluctuation range of the multi-stage planetary gearbox in a healthy state, the fluctuation degree increased to 800%, and the entropy value fluctuated violently, indicating that with the continuous deterioration of the fault of the multi-stage planetary gearbox, the energy of the fault characteristic signal and the increase of the harmonic type, the coupling relationship and complexity of the internal information of the overall system changed in a non-smooth form.

[0111] according to Figure 5 It can be seen that the spatial coupling entropy describes the complexity of the coupling relationship between the vibration signals at the input and output ends, and can accurately describe the entire evolution of the early weak faults of the multi-stage planetary gearbox from nothing to something, from small to large. The spatial coupling entropy can represent the information coupling relationship and complexity in the time series through the probability density matrix, and thus effectively reveal the potential state evolution process of the rotating machinery.

[0112] Compared with the prior art, the embodiment of the present invention converts the vibration acceleration data into mixed state data, and determines the first probability density matrix and the second probability density matrix based on the mixed state data, thereby determining the spatial coupling entropy, wherein the spatial coupling entropy can reflect the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end. The embodiment of the present invention quantitatively calculates the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end, and is used to determine whether a multi-stage planetary gearbox has a fault. There is no need to perform a step-by-step signal analysis on the multi-stage vibration signals inside the multi-stage planetary gearbox, which can not only effectively simplify the fault detection method, but also will not be affected by the complex gear meshing structure inside the multi-stage planetary gearbox, thereby improving the fault detection accuracy.

[0113] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.

[0114] The following is an embodiment of the device of the present invention. For details not described in detail therein, reference may be made to the corresponding method embodiment described above.

[0115] Figure 6 The structure diagram of the detection device of the multi-stage planetary gearbox provided by the embodiment of the present invention is shown. For the convenience of description, only the part related to the embodiment of the present invention is shown, which is described in detail as follows:

[0116] like Figure 6 As shown, the detection device 6 of the multi-stage planetary gearbox includes: an acquisition module 61 , a calculation module 62 and a detection module 63 .

[0117] An acquisition module 61 is used to respectively acquire vibration acceleration data corresponding to the input end and the output end of the multi-stage planetary gearbox;

[0118] The calculation module 62 is used for:

[0119] Based on the vibration acceleration data, a first mixed state data set corresponding to the output end and a second mixed state data set corresponding to the input end are respectively constructed;

[0120] Based on the first mixed state data set and the second mixed state data set, respectively determine a first probability density matrix between the input end and the output end, and a second probability density matrix corresponding to the output end;

[0121] Determine the eigenvalues ​​corresponding to the first probability density matrix and the second probability density matrix respectively, and calculate the spatial coupling entropy based on the eigenvalues; the spatial coupling entropy is used to reflect the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end of the multi-stage planetary gearbox;

[0122] The detection module 63 is used to determine that the multi-stage planetary gearbox fails when the spatial coupling entropy exceeds a preset threshold range.

[0123] In a possible implementation, a plurality of measuring points are respectively set at the input end and the output end of the multi-stage planetary gearbox; the first mixed state data set includes: vibration acceleration data corresponding to a plurality of first subsystems; the vibration acceleration data corresponding to each first subsystem includes: vibration acceleration data at different measuring points of the output end at different times; the second mixed state data set includes: vibration acceleration data corresponding to a plurality of second subsystems; the vibration acceleration data corresponding to each second subsystem includes: vibration acceleration data at different measuring points of the input end at different times;

[0124] The calculation module 62 is specifically used for:

[0125] Determine the conditional probability distribution between different first subsystems and second subsystems based on the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem;

[0126] Determining conditional probability distributions of different first subsystems based on the vibration acceleration data corresponding to each first subsystem;

[0127] Based on the conditional probability distribution between different first subsystems and second subsystems, construct a first probability density matrix;

[0128] Based on the conditional probability distributions of different first subsystems, a second probability density matrix is ​​constructed.

[0129] In a possible implementation, the calculation module 62 is specifically configured to:

[0130] Sequentially sampling and mapping the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem, respectively, to obtain a first integer sequence corresponding to each first subsystem and a second integer sequence corresponding to each second subsystem;

[0131] according to determining a conditional probability distribution between the kth first subsystem and the kth second subsystem;

[0132] Among them, p k (x i-w |x i-1-w ,y i-t ) represents the conditional probability distribution between the kth first subsystem and the kth second subsystem, x i-w represents the vibration acceleration data of the kth first subsystem at the iwth moment, x i-1-w represents the vibration acceleration data of the kth first subsystem at the i-1-wth moment, y i-t represents the vibration acceleration data of the kth second subsystem at the itth moment, p k (v i-w ,v i-1-w ,u i-t ) indicates v i-w 、v i-1-w and u i-t The joint probability of occurrence, v i-w represents the data set at time iw in the first integer sequence corresponding to the kth first subsystem, v i-1-w represents the data at time i-1-w in the first integer sequence corresponding to the kth first subsystem, u i-t represents the data at time it in the second integer sequence corresponding to the kth second subsystem, p k (v i-w ,ui-t ) indicates v i-1-w and u i-t The joint probability of occurrence.

[0133] In a possible implementation, the calculation module 62 is specifically configured to:

[0134] according to Determine the conditional probability distribution of the kth first subsystem;

[0135] Among them, p k (x i-w |x i-1-w ) represents the conditional probability distribution of the kth first subsystem.

[0136] In a possible implementation, the calculation module 62 is specifically configured to:

[0137] according to Constructing a first probability density matrix;

[0138] in, represents the first probability density matrix, K represents the total number of the second subsystems, ω k represents the weight of the kth second subsystem.

[0139] In a possible implementation, the calculation module 62 is specifically configured to:

[0140] according to Constructing a second probability density matrix;

[0141] in, represents the second probability density matrix, L represents the total number of the first subsystem, ω l represents the weight of the lth first subsystem, p l (x i-w |x i-1-w ) represents the conditional probability distribution of the lth first subsystem.

[0142] In a possible implementation, the calculation module 62 is specifically configured to:

[0143] according to Calculate spatial coupling entropy;

[0144] Among them, MSCE Y→X represents the spatial coupling entropy, τ represents the scale parameter, represents the jth eigenvalue in the first probability density matrix, Indicates the first eigenvalues, and n represents the number of eigenvalues.

[0145] The device embodiment can be used to implement the above method embodiment. Its technical principles and implementation effects can be found in the above method embodiment in detail and will not be repeated here.

[0146] Figure 7 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 7 As shown, the electronic device 7 of this embodiment includes: a processor 70, a memory 71, and a computer program 72 stored in the memory 71 and executable on the processor 70. When the processor 70 executes the computer program 72, the steps in the above-mentioned detection method embodiments of the multi-stage planetary gearbox are implemented, for example Figure 2 Alternatively, when the processor 70 executes the computer program 72, the functions of each module / unit in the above-mentioned device embodiments are realized, for example, Figure 6 The functions of modules 61 to 63 are shown.

[0147] Exemplarily, the computer program 72 may be divided into one or more modules / units, which are stored in the memory 71 and executed by the processor 70 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program 72 in the electronic device 7. For example, the computer program 72 may be divided into Figure 6 Modules 61 to 63 are shown.

[0148] The electronic device 7 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 7 may include, but is not limited to, a processor 70 and a memory 71. Those skilled in the art will appreciate that Figure 7 It is only an example of the electronic device 7 and does not constitute a limitation of the electronic device 7. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0149] The processor 70 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0150] The memory 71 may be an internal storage unit of the electronic device 7, such as a hard disk or memory of the electronic device 7. The memory 71 may also be an external storage device of the electronic device 7, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 7. Further, the memory 71 may also include both an internal storage unit and an external storage device of the electronic device 7. The memory 71 is used to store the computer program and other programs and data required by the electronic device. The memory 71 may also be used to temporarily store data that has been output or is to be output.

[0151] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0152] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0153] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0154] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0155] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0156] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0157] If the integrated module / unit is implemented in the form of 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 present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned detection method embodiments of each multi-stage planetary gearbox can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for detecting a multi-stage planetary gearbox, characterized in that: include: Respectively obtain vibration acceleration data corresponding to the input end and the output end of the multi-stage planetary gearbox; Based on the vibration acceleration data, construct a first mixed state data set corresponding to the output end and a second mixed state data set corresponding to the input end respectively; Based on the first mixed state data set and the second mixed state data set, respectively determine a first probability density matrix between the input end and the output end, and a second probability density matrix corresponding to the output end; Determine the eigenvalues ​​corresponding to the first probability density matrix and the second probability density matrix respectively, and calculate the spatial coupling entropy based on the eigenvalues; The spatial coupling entropy is used to reflect the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end of the multi-stage planetary gearbox; When the spatial coupling entropy exceeds a preset threshold range, it is determined that the multi-stage planetary gearbox fails.

2. The detection method of a multi-stage planetary gearbox according to claim 1, characterized in that: A plurality of measuring points are respectively arranged at the input end and the output end of the multi-stage planetary gearbox; The first mixed state data set includes: vibration acceleration data corresponding to a plurality of first subsystems; the vibration acceleration data corresponding to each first subsystem includes: vibration acceleration data at different measuring points of the output end at different times; the second mixed state data set includes: vibration acceleration data corresponding to a plurality of second subsystems; the vibration acceleration data corresponding to each second subsystem includes: vibration acceleration data at different measuring points of the input end at different times; The determining, based on the first mixed state data set and the second mixed state data set, respectively a first probability density matrix between the input end and the output end, and a second probability density matrix corresponding to the output end, comprises: Determine the conditional probability distribution between different first subsystems and second subsystems based on the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem; Determining conditional probability distributions of different first subsystems based on the vibration acceleration data corresponding to each first subsystem; Based on the conditional probability distribution between different first subsystems and second subsystems, construct a first probability density matrix; Based on the conditional probability distributions of different first subsystems, a second probability density matrix is ​​constructed.

3. The detection method of a multi-stage planetary gearbox according to claim 2, characterized in that: The determining of the conditional probability distribution between different first subsystems and second subsystems based on the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem includes: Sequentially sampling and mapping the vibration acceleration data corresponding to each first subsystem and the vibration acceleration data corresponding to each second subsystem, respectively, to obtain a first integer sequence corresponding to each first subsystem and a second integer sequence corresponding to each second subsystem; according to determining a conditional probability distribution between the kth first subsystem and the kth second subsystem; Among them, pk(xi-w|xi-1-w,yi-t) represents the conditional probability distribution between the kth first subsystem and the kth second subsystem, x i-w represents the vibration acceleration data of the kth first subsystem at the iwth moment, x i-1-w represents the vibration acceleration data of the kth first subsystem at the i-1-wth moment, y i-t represents the vibration acceleration data of the kth second subsystem at the itth moment, p k (v i-w ,v i-1-w ,u i-t ) indicates v i-w 、v i-1-w and u i-t The joint probability of occurrence, v i-w represents the data set at time iw in the first integer sequence corresponding to the kth first subsystem, v i-1-w represents the data at time i-1-w in the first integer sequence corresponding to the kth first subsystem, u i-t represents the data at time it in the second integer sequence corresponding to the kth second subsystem, p k (v i-w ,u i-t ) indicates v i-1-w and u i-t The joint probability of occurrence.

4. The detection method of a multi-stage planetary gearbox according to claim 3, characterized in that: The determining of the conditional probability distribution of different first subsystems based on the vibration acceleration data corresponding to each first subsystem includes: according to Determine the conditional probability distribution of the kth first subsystem; Wherein, pk(xi-w|xi-1-w) represents the conditional probability distribution of the kth first subsystem.

5. The detection method of a multi-stage planetary gearbox according to claim 3, characterized in that: The constructing a first probability density matrix based on the conditional probability distribution between different first subsystems and second subsystems includes: according to Constructing a first probability density matrix; in, represents the first probability density matrix, K represents the total number of the second subsystems, ω k represents the weight of the kth second subsystem.

6. The detection method of a multi-stage planetary gearbox according to claim 4, characterized in that: The constructing of a second probability density matrix based on conditional probability distributions of different first subsystems includes: according to Constructing a second probability density matrix; in, represents the second probability density matrix, L represents the total number of first subsystems, ωl represents the weight of the l-th first subsystem, and pl(xi-w|xi-1-w) represents the conditional probability distribution of the l-th first subsystem.

7. The detection method of a multi-stage planetary gearbox according to claim 1, characterized in that: The calculating the spatial coupling entropy based on the eigenvalue comprises: according to Calculate spatial coupling entropy; Among them, MSCE Y→X represents the spatial coupling entropy, τ represents the scale parameter, represents the jth eigenvalue in the first probability density matrix, Indicates the first eigenvalues, and n represents the number of eigenvalues.

8. A detection device for a multi-stage planetary gearbox, characterized in that: include: An acquisition module, used to respectively acquire vibration acceleration data corresponding to the input end and the output end of the multi-stage planetary gearbox; Compute module for: Based on the vibration acceleration data, construct a first mixed state data set corresponding to the output end and a second mixed state data set corresponding to the input end respectively; Based on the first mixed state data set and the second mixed state data set, respectively determine a first probability density matrix between the input end and the output end, and a second probability density matrix corresponding to the output end; Determine the eigenvalues ​​corresponding to the first probability density matrix and the second probability density matrix respectively, and calculate the spatial coupling entropy based on the eigenvalues; The spatial coupling entropy is used to reflect the causal transmission relationship and coupling degree between the vibration acceleration data at the input end and the vibration acceleration data at the output end of the multi-stage planetary gearbox; The detection module is used to determine that the multi-stage planetary gearbox fails when the spatial coupling entropy exceeds a preset threshold range.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the detection method of the multi-stage planetary gearbox as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the detection method of a multi-stage planetary gearbox as described in any one of claims 1 to 7 are implemented.

Images