A method and device for identifying and evaluating faults of multiple units

Abstract

The present invention discloses a method and device for fault identification and evaluation of a motor vehicle group, belonging to the technical field of fault identification, the method comprising: obtaining first sound data of a motor vehicle group from a sound collector, the sound collector being arranged outside the track of the motor vehicle group; discretizing the first sound data, and then extracting a plurality of instantaneous frequencies to obtain a first frequency set; establishing a Doppler relationship model between the original frequency and the instantaneous frequency of the motor vehicle group; fitting the parameters in the Doppler relationship model using the Newton iteration method to obtain a first parameter set; determining the original frequency based on the first parameter set, and performing fault identification on the bearing of the motor vehicle group based on the original frequency. The method can accurately and comprehensively identify the bearing fault of the motor vehicle group.

Description

Technical Field

[0001] The present invention relates to the technical field of fault identification, and in particular to a method and device for fault identification and evaluation of a motor vehicle unit. Background Art

[0002] The running gear is an important part of the EMU vehicle, responsible for the traction and braking of the vehicle, and its performance is directly related to the safe operation of the train. The running gear is composed of parts such as bogies, including mechanical structures such as bearings. During the long-term operation of the train, the bearings are prone to failure.

[0003] In the related technologies, infrared axle temperature monitoring or trackside acoustic detection system (TADS) is usually used to identify and evaluate EMU faults. TADS collects the vibration and sound signals of high-speed vehicle bearings by installing an acoustic sensor array on the trackside. Through signal processing technology, it analyzes the frequency, energy and other information of the bearing fault signal to determine the bearing fault type and the degree of fault defect. When a bearing fails, due to the high speed of the EMU, the faulty part will generate local high temperature due to abnormal impact and friction. When the local temperature is higher than the temperature of other parts of the bearing, the alarm function is realized through infrared monitoring. The disadvantage of this method is that it can only be detected when the bearing fault reaches the level of heating, and it is difficult to accurately detect bearing faults in other situations. Summary of the invention

[0004] The present invention provides a method and device for identifying and evaluating EMU faults, which can accurately and comprehensively identify EMU bearing faults. The technical solution at least includes the following solutions:

[0005] In a first aspect, a method for fault identification and evaluation of an EMU is provided, comprising: obtaining first sound data of the EMU from a sound collector, wherein the sound collector is arranged outside the EMU track; discretizing the first sound data, and then extracting multiple instantaneous frequencies to obtain a first frequency set; establishing a Doppler relationship model between the original frequency of the EMU and the instantaneous frequency; fitting the parameters in the Doppler relationship model using the Newton iteration method to obtain a first parameter set; determining the original frequency based on the first parameter set, and performing fault identification on the bearing of the EMU based on the original frequency.

[0006] Optionally, the Doppler relationship model is expressed by the following formula:

[0007]

[0008] in, is the i-th instantaneous frequency in the first frequency set, is the original frequency, is the speed of sound, is the speed of the EMU, is the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, is the distance between the sound collector and the center line of the EMU track, is the sampling time corresponding to the i-th instantaneous frequency, i is an integer, the value range of i is 1 to N, and N is the number of instantaneous frequencies in the first frequency set.

[0009] Optionally, the first parameter set includes the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, and the Newton iteration method is used to fit the parameters in the Doppler relationship model to obtain the first parameter set, including: performing dimensionality reduction processing on the Doppler relationship model to obtain a first implicit function, the first implicit function includes a first variable and a second variable, the first variable is determined based on the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, and the second variable is determined based on the speed of the EMU; iterating the first implicit function using the Newton iteration method to obtain the fitted first variable and the second variable; determining the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording based on the fitted first variable and the second variable.

[0010] Optionally, the first implicit function is expressed by the following formula:

[0011]

[0012] in, is the first implicit function corresponding to the i-th instantaneous frequency, , , , , is the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-th iteration, is the first variable, , is the second variable, , j is an integer, j is less than or equal to the number of iterations.

[0013] Optionally, the iterating the first implicit function using the Newton iteration method to obtain the fitted first variable and the second variable includes: determining the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1-th iteration based on the first variable and the second variable fitted in the j-1-th iteration; determining the first variable and the second variable fitted in the j-1-th iteration based on the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1-th iteration and the first variable and the second variable fitted in the j-1-th iteration; and when the difference between the first variable fitted in the j-th iteration and the first variable fitted in the j-1-th iteration is less than an error threshold, and when the difference between the second variable fitted in the j-th iteration and the second variable fitted in the j-1-th iteration is less than the error threshold, using the first variable and the second variable fitted in the j-th iteration as the first variable and the second variable fitted by the Newton iteration method.

[0014] In the second aspect, a device for identifying and evaluating faults of an EMU is also provided, comprising: an acquisition module for acquiring first sound data of the EMU from a sound collector, wherein the sound collector is arranged outside the EMU track; a discretization module for discretizing the first sound data, and then extracting multiple instantaneous frequencies to obtain a first frequency set; a modeling module for establishing a Doppler relationship model between the original frequency of the EMU and the instantaneous frequency; a fitting module for fitting the parameters in the Doppler relationship model using the Newton iteration method to obtain a first parameter set; a fault identification module for determining the original frequency based on the first parameter set, and performing fault identification on the bearing of the EMU based on the original frequency.

[0015] Optionally, in the modeling module, the Doppler relationship model is expressed by the following formula:

[0016]

[0017] in, is the i-th instantaneous frequency in the first frequency set, is the original frequency, is the speed of sound, is the speed of the EMU, is the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, is the distance between the sound collector and the center line of the EMU track, is the sampling time corresponding to the i-th instantaneous frequency, i is an integer, the value range of i is 1 to N, and N is the number of instantaneous frequencies in the first frequency set.

[0018] Optionally, the first parameter set includes the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, and the fitting module is also used to perform dimensionality reduction processing on the Doppler relationship model to obtain a first implicit function, the first implicit function includes a first variable and a second variable, the first variable is determined based on the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, and the second variable is determined based on the speed of the EMU; the first implicit function is iterated using the Newton iteration method to obtain the fitted first variable and the second variable; based on the fitted first variable and the second variable, the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording are determined.

[0019] Optionally, in the fitting module, the first implicit function is expressed by the following formula:

[0020]

[0021] in, is the first implicit function corresponding to the i-th instantaneous frequency, , , , , is the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-th iteration, is the first variable, , is the second variable, , j is an integer, j is less than or equal to the number of iterations.

[0022] Optionally, the fitting module is also used to determine the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1-th iteration based on the first variable and the second variable fitted in the j-1-th iteration; determine the first variable and the second variable fitted in the j-1-th iteration based on the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1-th iteration and the first variable and the second variable fitted in the j-1-th iteration; when the difference between the first variable fitted in the j-th iteration and the first variable fitted in the j-1-th iteration is less than an error threshold, and the difference between the second variable fitted in the j-th iteration and the second variable fitted in the j-1-th iteration is less than the error threshold, use the first variable and the second variable fitted in the j-th iteration as the first variable and the second variable fitted by the Newton iteration method.

[0023] In a third aspect, a computer device is also provided, comprising: a memory and a processor, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor, thereby executing the EMU fault identification and evaluation method described in the above embodiment.

[0024] In a fourth aspect, a computer-readable storage medium is also provided, wherein at least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by a processor, thereby executing the EMU fault identification and evaluation method described in the above embodiment.

[0025] In a fifth aspect, a computer program product is provided, comprising a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the method described in the first aspect is implemented.

[0026] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0027] In the embodiment of the present invention, only the first sound data needs to be obtained to realize the bearing fault identification of the EMU. The EMU can make a sound under any circumstances, so the method in the embodiment of the present invention can comprehensively identify the faults of the EMU under various circumstances. By establishing a Doppler relationship model between the original frequency and the instantaneous frequency of the EMU, the parameters in the Doppler relationship model are fitted using the Newton iteration method to obtain a first parameter set. Since the Newton iteration method has a high accuracy when fitting unknown parameters, the first parameter set fitted using the Newton iteration method is also relatively accurate. In this way, the accuracy of the original frequency finally determined based on the first parameter set is effectively improved, so that the bearing faults of the EMU can be accurately identified based on the original frequency. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0029] Figure 1 A flow chart showing a method for identifying and evaluating a fault of an EMU provided by an exemplary embodiment of the present invention is shown;

[0030] Figure 2 It is a schematic diagram of the Doppler relationship model;

[0031] Figure 3 A flow chart showing a method for identifying and evaluating a fault of an EMU provided by another exemplary embodiment of the present invention is shown;

[0032] Figure 4 A schematic diagram showing the structure of a motor vehicle multiple unit fault identification and evaluation device provided by an exemplary embodiment of the present invention is shown;

[0033] Figure 5 It is a structural diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] Unless otherwise defined, the technical or scientific terms used herein shall have the usual meanings understood by persons of ordinary skill in the field to which the invention belongs. The words "first", "second", "third" and similar terms used in the patent application specification and claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one" or "a" do not indicate a quantitative limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" and similar terms mean that the elements or objects appearing before "include" or "comprises" include the elements or objects listed after "include" or "comprises" and their equivalents, and do not exclude other elements or objects.

[0035] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0036] Figure 1 A flowchart of a method for identifying and evaluating a fault of a train set provided by an exemplary embodiment of the present invention is shown. The method can be executed by a computer device. Figure 1 , the method comprising:

[0037] In step 101, first sound data of the EMU is obtained from a sound collector.

[0038] The sound collector is arranged outside the EMU track. Exemplarily, the sound collector is a microphone array.

[0039] In step 102, the first sound data is discretized, and then a plurality of instantaneous frequencies are extracted to obtain a first frequency set.

[0040] Exemplarily, for example, STFT (Short-Time Fourier Transform) is used to discretize the first sound data.

[0041] In one possible implementation, the AGCD (Approximate Greatest Comm Divisor) method is used to extract the instantaneous frequency. AGCD is a method for extracting instantaneous frequency, which can accurately and reasonably extract multiple instantaneous frequencies, and the obtained multiple instantaneous frequencies are the first frequency set. There are many implementation methods of AGCD in the related art, and detailed description is omitted here.

[0042] In another possible implementation, the maximum value of the instantaneous frequency at each sampling time is used as multiple instantaneous frequencies in the first frequency set. During operation, the faulty part of the bearing will produce continuous and regular impacts with other mechanical structures, forming an acoustic signal with a natural frequency. During the movement, the signal will cause its natural frequency to be distorted due to the Doppler phenomenon, and the signal amplitude will be significantly greater than the ambient noise. Therefore, the maximum value of the instantaneous frequency at each sampling time can be directly used as multiple instantaneous frequencies in the first frequency set, thereby reducing the amount of calculation.

[0043] In step 103, a Doppler relationship model between the original frequency and the instantaneous frequency of the EMU is established.

[0044] Here, due to the Doppler effect, the instantaneous frequency analyzed from the sound data collected by the sound collector is not equal to the original frequency emitted by the EMU bearing. A Doppler relationship model between the original frequency and the instantaneous frequency of the EMU can be established, and then steps 105-106 are used to determine the original frequency.

[0045] Optionally, the Doppler relationship model is expressed using formula (1).

[0046] (1)

[0047] In formula (1), is the i-th instantaneous frequency in the first frequency set, is the original frequency, is the speed of sound, is the speed of the EMU, is the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording. is the distance between the sound collector and the center line of the EMU track, is the sampling time corresponding to the i-th instantaneous frequency, i is an integer, the value range of i is 1 to N, and N is the number of instantaneous frequencies in the first frequency set.

[0048] here, In fact, it is the distance between the bearing and the microphone. In the embodiment of the present invention, the distance between the sound collector and the center line of the EMU track is used as , which is fixed and known. Since the bearing in the EMU may be located at the edge of the EMU track or at a certain position in the EMU track, the actual distance between the bearing and the microphone is not necessarily equal to the distance between the sound collector and the center line of the EMU track, but there may be a slight error. In order to reduce the impact caused by this slight error, in the embodiment of the present invention, the sound collector needs to be set at a position far enough away from the EMU track so that the slight error can be ignored.

[0049] Figure 2 This is a schematic diagram of the Doppler relationship model. Figure 2 The derivation of the Doppler relationship model is explained.

[0050] Assume that the frequency of the train fault sound source is a fixed value (i.e. original frequency), the moving sound source maintains a speed of (m / s) uniform rectilinear motion, the wavelength of the sound wave is , the local speed of sound is (m / s).

[0051] Assume that the sound source emits the first wave at t=0 and the second wave at t=T. At time t after the second wave, t is greater than T. From the geometric relationship, we can get . After rearranging, we get formula (2).

[0052] (2)

[0053] In formula (2), is the wavelength of the sound wave, and the second wave is emitted at t = T. The meanings of other parameters in formula (2) are the same as those in formula (1), and detailed description is omitted here.

[0054] like Figure 2 As shown, t represents the current time, Represents the line between the location of the sound source (i.e., the EMU bearing) and the sound collector (i.e., the microphone) at time t and the speed of the EMU The angle between the sound source and the sound collector. , Substituting into formula (2) and decomposing the speed along the connecting line, we can obtain the frequency received by the sound collector at time t (that is, sampling frequency / instantaneous frequency) and the original frequency The relationship between is expressed by formula (3).

[0055] (3)

[0056] In formula (3), It is expressed by formula (4). The meanings of other parameters in formula (3) are the same as those in formula (1), and detailed description is omitted here.

[0057] (4)

[0058] In formula (4), Represents the line between the location of the sound source (i.e., the EMU bearing) and the sound collector (i.e., the microphone) at time t and the speed of the EMU The meanings of other parameters in formula (4) are the same as those in formula (1), and their detailed description is omitted here. Here, That is Figure 2 The physical meaning of the line between the point t=0 and the nearest point is the projection length of the line R between the EMU bearing and the sound collector on the EMU track when the sound collector starts recording.

[0059] When t in formula (4) is When , substitute formula (4) into formula (3) and rearrange to obtain formula (1).

[0060] In step 104, the parameters in the Doppler relationship model are fitted using the Newton iteration method to obtain a first parameter set.

[0061] In step 105, an original frequency is determined based on the first parameter set, and fault identification is performed on the bearing of the EMU based on the original frequency.

[0062] In the embodiment of the present invention, only the first sound data needs to be obtained to realize the bearing fault identification of the EMU. The EMU can make a sound under any circumstances, so the method in the embodiment of the present invention can comprehensively identify the faults of the EMU under various circumstances. By establishing a Doppler relationship model between the original frequency and the instantaneous frequency of the EMU, the parameters in the Doppler relationship model are fitted using the Newton iteration method to obtain a first parameter set. Since the Newton iteration method has a high accuracy when fitting unknown parameters, the first parameter set fitted using the Newton iteration method is also relatively accurate. In this way, the accuracy of the original frequency finally determined based on the first parameter set is effectively improved, so that the bearing faults of the EMU can be accurately identified based on the original frequency.

[0063] Figure 3 A flowchart of a method for identifying and evaluating a fault in a train set provided by another exemplary embodiment of the present invention is shown. The method can be executed by a computer device. Figure 3 , the method comprising:

[0064] In step 301, first sound data of the EMU is obtained from a sound collector.

[0065] The sound collector is installed outside the EMU track.

[0066] In step 302, the first sound data is discretized, and then a plurality of instantaneous frequencies are extracted to obtain a first frequency set.

[0067] In step 303, a Doppler relationship model between the original frequency and the instantaneous frequency of the EMU is established.

[0068] The relevant contents of steps 301 to 303 refer to the aforementioned steps 101 to 103, and detailed description is omitted here.

[0069] In step 304, the parameters in the Doppler relationship model are fitted using the Newton iteration method to obtain a first parameter set.

[0070] By analyzing the parameters in the Doppler relationship model through formula (1), it can be seen that , , are known and fixed parameters, and and is the unknown parameter that needs to be fitted. That is, the first parameter set includes two parameters: the speed of the EMU The projected length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording .

[0071] Optionally, step 304 includes the following steps ac.

[0072] Step a, performing dimensionality reduction processing on the Doppler relationship model to obtain the first implicit function.

[0073] The first implicit function includes a first variable and a second variable. The first variable is determined based on the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording. The second variable is determined based on the speed of the EMU.

[0074] Substituting the instantaneous frequencies in the first frequency set into the Doppler relationship model in turn, multiple equations can be constructed, and the number of these multiple equations is much greater than the number of parameters that need to be solved. These multiple equations are typical overdetermined equations. Usually, when using the Newton iteration method to solve the overdetermined equations, there are certain requirements for the form and dimension of the overdetermined equations. The Doppler relationship model in the embodiment of the present invention is relatively complex and has a high dimension, which does not meet the form and dimension requirements of the Newton iteration method, resulting in the inability to apply the Newton iteration method. In the embodiment of the present invention, the Doppler relationship model is reduced in dimension by step a, and the Doppler relationship model is converted into a first implicit function, so that the Newton iteration method can be applied to the Doppler relationship model.

[0075] Optionally, the first implicit function is expressed by formula (5):

[0076] (5)

[0077] In formula (5), is the first implicit function corresponding to the i-th instantaneous frequency, , , , , is the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-th iteration, is the first variable, , is the second variable, , j is an integer, j is less than or equal to the number of iterations.

[0078] The process of performing dimensionality reduction processing on the Doppler relationship model and converting the Doppler relationship model into the first implicit function can be described by using formulas (6) to (11).

[0079] First, the Doppler relationship model is transposed and squared to obtain formula (6).

[0080] (6)

[0081] The meanings of the parameters in formula (6) are the same as those in formula (5), and their detailed description is omitted here.

[0082] For formula (6), the intermediate variable is introduced , and then simplify formula (6) to obtain formula (7).

[0083] (7)

[0084] In formula (7), is the intermediate variable, The meanings of other parameters in formula (7) are the same as those in formula (5), and their detailed description is omitted here.

[0085] Substitute multiple instantaneous frequencies in the first frequency set into formula (7) respectively to establish a system of equations, which is expressed by formula (8).

[0086] (8)

[0087] In formula (8), , … In turn, the first instantaneous frequency corresponds to , the second instantaneous frequency corresponds to ...The Nth instantaneous frequency corresponds to The meanings of other parameters in formula (8) are the same as those in formula (5), and their detailed description is omitted here.

[0088] The right sides of the equations in formula (8) are all equal. Any two of the equations can be used to construct a new equation. Here, the i-th equation and the i+1-th equation are selected to construct a new equation as shown in formula (9).

[0089] (9)

[0090] The meanings of the parameters in formula (9) are the same as those in formula (8), and their detailed description is omitted here.

[0091] By transforming formula (9), we can get formula (10).

[0092] (10)

[0093] The meanings of the parameters in formula (10) are the same as those in formula (9), and their detailed description is omitted here.

[0094] When formula (10) is obtained, formula (11) can be obtained by introducing the first variable and the second variable and rearranging formula (10).

[0095] (11)

[0096] The meanings of the parameters in formula (11) are the same as those in formula (5) and formula (10), and their detailed description is omitted here.

[0097] After introducing constant coefficients into formula (11), formula (11) can be written in the form of formula (5), thus obtaining the first implicit function. The constant coefficients are , ; ; ; .

[0098] Step b: Iterate the first implicit function using Newton iteration method to obtain the fitted first variable and second variable.

[0099] According to Newton's iteration method, the first implicit function can be transformed into the form of formula (12).

[0100] (12)

[0101] In formula (12), is the first variable fitted in the j+1th iteration, is the second variable fitted at the j+1th iteration. is the first variable fitted in the jth iteration, is the second variable fitted in the jth iteration. is the Jacobian matrix, is the inverse matrix of the Jacobi matrix, which is expressed by formula (13). The meanings of other parameters in formula (12) are the same as those in formula (5), and their detailed description is omitted here.

[0102] (13)

[0103] In formula (13), represents the partial derivative of the first implicit function with respect to the first variable at the i-th instantaneous frequency, represents the partial derivative of the first implicit function with respect to the second variable at the i-th instantaneous frequency.

[0104] Exemplarily, the partial derivative of the first implicit function with respect to the first variable at the i-th instantaneous frequency is expressed by formula (14), and the partial derivative of the second implicit function with respect to the first variable at the i-th instantaneous frequency is expressed by formula (15).

[0105] (14)

[0106] (15)

[0107] The meanings of the parameters in formula (14) and formula (15) are the same as those in formula (5) and formula (13), and their detailed description is omitted here.

[0108] Before executing step b, you need to set the initial value of the iteration, that is, the initial first variable and the initial second variable . In the initial first variable and the initial second variable If we know the initial and , and then substitute any instantaneous frequency into the Doppler relationship model to get the initial original frequency , and then get the initial constant coefficients. Substituting these initial parameters into formula (12) can obtain the first variable fitted by the first iteration: and the second variable , and then repeat the above operation for multiple iterations.

[0109] Optionally, step b includes the following three steps.

[0110] In the first step, based on the first variable and the second variable fitted in the j-1th iteration, the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1th iteration is determined.

[0111] When the first variable and the second variable fitted in the j-1th iteration are known, the j-1th iteration can be solved and , and then substitute any instantaneous frequency into the Doppler relationship model to obtain the original frequency fitted by the j-1th iteration , and then get the constant coefficients fitted by the j-1th iteration.

[0112] In the second step, based on the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1-th iteration and the first variable and the second variable fitted in the j-1-th iteration, the first variable and the second variable fitted in the j-1-th iteration are determined.

[0113] Substituting the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1-th iteration and the first variable and the second variable fitted at the j-1-th iteration into formula (12), the first variable and the second variable fitted at the j-th iteration can be obtained.

[0114] Then, it is determined whether the difference between the first variable fitted by the j-th iteration and the first variable fitted by the j-1-th iteration is less than the error threshold, and whether the difference between the second variable fitted by the j-th iteration and the second variable fitted by the j-1-th iteration is less than the error threshold. At this time, there are the following four situations:

[0115] In the first case, the difference between the first variable fitted by the j-th iteration and the first variable fitted by the j-1-th iteration is greater than the error threshold, and the difference between the second variable fitted by the j-th iteration and the second variable fitted by the j-1-th iteration is greater than the error threshold.

[0116] In the second case, the difference between the first variable fitted by the j-th iteration and the first variable fitted by the j-1-th iteration is greater than the error threshold, and the difference between the second variable fitted by the j-th iteration and the second variable fitted by the j-1-th iteration is less than the error threshold.

[0117] In the third case, the difference between the first variable fitted by the j-th iteration and the first variable fitted by the j-1-th iteration is less than the error threshold, and the difference between the second variable fitted by the j-th iteration and the second variable fitted by the j-1-th iteration is greater than the error threshold.

[0118] In the fourth case, the difference between the first variable fitted by the j-th iteration and the first variable fitted by the j-1-th iteration is less than the error threshold, and the difference between the second variable fitted by the j-th iteration and the second variable fitted by the j-1-th iteration is less than the error threshold.

[0119] Only in the fourth case can the third step be executed. For the first to third cases, it means that the iteration results have not converged yet and further iteration is required.

[0120] Here, the error threshold is a very small number, usually , where m is greater than or equal to 8. When the difference between the results of two adjacent iterative fittings is less than the error threshold, it means that the two iterative processes are very close, that is, the iterative results have converged, and the third step can be executed.

[0121] The third step is to use the first variable and the second variable fitted by the jth iteration as the first variable and the second variable fitted by the Newton iteration method.

[0122] Step c: based on the fitted first variable and second variable, determine and .

[0123] The and These are the parameters in the first parameter set.

[0124] In step 305, an original frequency is determined based on the first parameter set, and fault identification is performed on the bearing of the EMU based on the original frequency.

[0125] When the first parameter set is determined, the final fitted original frequency can be obtained by substituting any instantaneous frequency into the Doppler relationship model. , the original frequency It can be used to identify faults in the bearings of EMUs.

[0126] Using the original frequency Before fault identification of the EMU bearing is performed, a second sound data generated by normal EMU operation can be recorded, and the second sound data can be processed in the manner of steps 301 to 305 to obtain a standard original frequency under normal conditions. Then, the original frequency obtained in step 305 is compared with the standard original frequency. If there is a difference between the original frequency obtained in step 305 and the standard original frequency, it means that the EMU bearing has a fault.

[0127] The following are device embodiments of the present application. For details not described in detail in the device embodiments, reference may be made to the above method embodiments.

[0128] Figure 4 FIG. 1 shows a schematic diagram of a structure of a fault identification and evaluation device for a train set according to an exemplary embodiment of the present invention. Figure 4 The EMU fault identification and evaluation device 400 includes: an acquisition module 401, a discretization module 402, a modeling module 403, a fitting module 404 and a fault identification module 405.

[0129] The acquisition module 401 is used to acquire the first sound data of the EMU from the sound collector, and the sound collector is arranged outside the EMU track;

[0130] The discretization module 402 is used to discretize the first sound data, and then extract multiple instantaneous frequencies to obtain a first frequency set;

[0131] The modeling module 403 is used to establish a Doppler relationship model between the original frequency of the EMU and the instantaneous frequency;

[0132] The fitting module 404 is used to fit the parameters in the Doppler relationship model using Newton iteration method to obtain a first parameter set;

[0133] The fault identification module 405 is used to determine the original frequency based on the first parameter set, and perform fault identification on the bearing of the EMU based on the original frequency.

[0134] Optionally, in the modeling module 403, the Doppler relationship model is expressed by the following formula:

[0135]

[0136] in, is the i-th instantaneous frequency in the first frequency set, is the original frequency, is the speed of sound, is the speed of the EMU, is the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, is the distance between the sound collector and the center line of the EMU track, is the sampling time corresponding to the i-th instantaneous frequency, i is an integer, the value range of i is 1 to N, and N is the number of instantaneous frequencies in the first frequency set.

[0137] Optionally, the first parameter set includes the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording. The fitting module 404 is also used to perform dimensionality reduction processing on the Doppler relationship model to obtain a first implicit function, the first implicit function includes a first variable and a second variable, the first variable is determined based on the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, and the second variable is determined based on the speed of the EMU; the first implicit function is iterated using the Newton iteration method to obtain the fitted first variable and the second variable; based on the fitted first variable and the second variable, the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording are determined.

[0138] Optionally, in the fitting module 404, the first implicit function is expressed by the following formula:

[0139]

[0140] in, is the first implicit function corresponding to the i-th instantaneous frequency, , , , , is the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-th iteration, is the first variable, , is the second variable, , j is an integer, j is less than or equal to the number of iterations.

[0141] Optionally, the fitting module 404 is further used to determine the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1-th iteration based on the first variable and the second variable fitted in the j-1-th iteration; determine the first variable and the second variable fitted in the j-1-th iteration based on the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1-th iteration and the first variable and the second variable fitted in the j-1-th iteration; when the difference between the first variable fitted in the j-th iteration and the first variable fitted in the j-1-th iteration is less than an error threshold, and the difference between the second variable fitted in the j-th iteration and the second variable fitted in the j-1-th iteration is less than the error threshold, use the first variable and the second variable fitted in the j-th iteration as the first variable and the second variable fitted by the Newton iteration method.

[0142] It should be noted that: when the EMU fault identification and evaluation device provided in the above embodiment performs EMU fault identification and evaluation, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the EMU fault identification and evaluation device provided in the above embodiment and the EMU fault identification and evaluation method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0143] The division of modules in the embodiments of the present invention is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0144] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions to enable a terminal device (which can be a personal computer, mobile phone, or communication device, etc.) or a processor (processor) to perform all or part of the steps of the method of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0145] Figure 5 Schematic diagram of the structure of a computer device provided by an embodiment of the present invention. Figure 5 As shown, the computer device 500 includes: a processor 501 and a memory 502 .

[0146] The processor 501 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 501 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 501 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 501 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 501 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0147] The memory 502 may include one or more computer-readable storage media, which may be non-transitory. The memory 502 may also include a high-speed random access memory and a non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in the memory 502 is used to store at least one instruction, which is used to be executed by the processor 501 to implement the EMU fault identification and evaluation method provided in the embodiment of the present invention.

[0148] Those skilled in the art will understand that Figure 5 The structure shown in the figure does not constitute a limitation on the computer device 500, and the computer device 500 may include more or less components than those shown in the figure, or combine some components, or adopt a different arrangement of components.

[0149] The embodiment of the present invention also provides a non-temporary computer-readable storage medium. When the instructions in the storage medium are executed by the processor of a computer device, the computer device can execute the EMU fault identification and evaluation method provided in the embodiment of the present invention.

[0150] The embodiment of the present invention further provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the EMU fault identification and evaluation method provided in the embodiment of the present invention.

[0151] The above descriptions are merely optional embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for identifying and evaluating faults in a train set, characterized in that: The method comprises: Acquire first sound data of the EMU from a sound collector, wherein the sound collector is arranged outside the EMU track; Discretize the first sound data, and then extract multiple instantaneous frequencies to obtain a first frequency set; Establishing a Doppler relationship model between the original frequency of the EMU and the instantaneous frequency; Using Newton iteration method to fit the parameters in the Doppler relationship model to obtain a first parameter set; Determine the original frequency based on the first parameter set, and perform fault identification on the bearing of the EMU based on the original frequency; The Doppler relationship model is expressed by the following formula: in, is the i-th instantaneous frequency in the first frequency set, is the original frequency, is the speed of sound, is the speed of the EMU, is the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, is the distance between the sound collector and the center line of the EMU track, is the sampling time corresponding to the i-th instantaneous frequency, i is an integer, the value range of i is 1 to N, and N is the number of instantaneous frequencies in the first frequency set.

2. The EMU fault identification and evaluation method according to claim 1 is characterized in that: The first parameter set includes the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording. The Newton iteration method is used to fit the parameters in the Doppler relationship model to obtain a first parameter set, including: Performing dimensionality reduction processing on the Doppler relationship model to obtain a first implicit function, wherein the first implicit function includes a first variable and a second variable, wherein the first variable is determined based on the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, and the second variable is determined based on the speed of the EMU; Iterating the first implicit function using Newton iteration method to obtain the first variable and the second variable that are fitted; Based on the fitted first variable and second variable, the speed of the EMU and the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording are determined.

3. The method for identifying and evaluating EMU faults according to claim 2, characterized in that: The first implicit function is expressed by the following formula: in, is the first implicit function corresponding to the i-th instantaneous frequency, , , , , is the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-th iteration, is the first variable, , is the second variable, , j is an integer, j is less than or equal to the number of iterations.

4. The method for identifying and evaluating EMU faults according to claim 3, characterized in that: The adopting Newton iteration method to iterate the first implicit function to obtain the fitted first variable and the second variable includes: Determine, based on the first variable and the second variable fitted in the j-1th iteration, a constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1th iteration; Determine the first variable and the second variable fitted in the j-th iteration based on the constant coefficient at the sampling time corresponding to the i-th instantaneous frequency in the j-1-th iteration and the first variable and the second variable fitted in the j-1-th iteration; When the difference between the first variable fitted by the j-th iteration and the first variable fitted by the j-1-th iteration is less than the error threshold, and the difference between the second variable fitted by the j-th iteration and the second variable fitted by the j-1-th iteration is less than the error threshold, the first variable and the second variable fitted by the j-th iteration are used as the first variable and the second variable fitted by the Newton iteration method.

5. A fault identification and evaluation device for a motor vehicle unit, characterized in that: The device comprises: An acquisition module, used for acquiring first sound data of the EMU from a sound collector, wherein the sound collector is arranged outside the EMU track; A discretization module, used for discretizing the first sound data, and then extracting a plurality of instantaneous frequencies to obtain a first frequency set; A modeling module, used for establishing a Doppler relationship model between the original frequency of the EMU and the instantaneous frequency; A fitting module, used for fitting the parameters in the Doppler relationship model by using Newton iteration method to obtain a first parameter set; a fault identification module, configured to determine the original frequency based on the first parameter set, and perform fault identification on the bearing of the EMU based on the original frequency; In the modeling module, the Doppler relationship model is expressed by the following formula: in, is the i-th instantaneous frequency in the first frequency set, is the original frequency, is the speed of sound, is the speed of the EMU, is the projection length of the line connecting the EMU bearing and the sound collector on the EMU track when the sound collector starts recording, is the distance between the sound collector and the center line of the EMU track, is the sampling time corresponding to the i-th instantaneous frequency, i is an integer, the value range of i is 1 to N, and N is the number of instantaneous frequencies in the first frequency set.

6. A computer device, characterized in that: The computer device comprises: a memory and a processor, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to implement the EMU fault identification and evaluation method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: At least one computer program is stored in the computer-readable storage medium, and the at least one computer program is loaded and executed by the processor to implement the EMU fault identification and evaluation method described in any one of claims 1 to 4.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by the processor, the EMU fault identification and evaluation method described in any one of claims 1 to 4 is implemented.

Images