Fault detection method and device for rail vehicle axle box bearing

Abstract

This specification provides a fault detection method and device for rail vehicle axle box bearings. First, the sound signal, temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle, as well as the temperature signals of other axle box bearings are obtained; then, based on the above signal data, the first detection result based on the acoustic response, the second detection result based on the vibration response and the third detection result based on the temperature response are determined respectively; based on the above detection results, the first fault detection result of the target axle box bearing is determined; and based on the first fault detection result of the target axle box bearing and the mechanical response influencing parameters of the target axle box bearing, the second fault detection result of the target axle box bearing is determined; finally, based on the second fault detection result of the target axle box bearing, it is determined whether the target axle box bearing has a fault. In this way, the fault responses of multiple dimensions can be comprehensively and fully integrated to accurately determine whether the target axle box bearing has a fault.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a method and device for detecting faults of axle box bearings of rail vehicles. Background Art

[0002] As one of the key components of the running gear of rail vehicles such as EMUs, axle box bearings need to withstand complex alternating loads such as static pressure and radial non-stable dynamic loads during vehicle operation. When the axle box bearing fails, it will inevitably pose a threat to the safe operation of the vehicle. Therefore, it is necessary to frequently detect and determine whether the vehicle's axle box bearings are faulty.

[0003] Based on the existing detection methods, most of them are to collect and judge whether the axle box bearing has a fault based on the sound of the axle box bearing alone. However, when detecting faults based on the above methods, there are often technical problems such as large error and low accuracy in detecting axle box bearing faults.

[0004] To address the above issues, no effective and reasonable solutions have been proposed so far. Summary of the invention

[0005] The present specification provides a method and device for fault detection of axle box bearings of rail vehicles, which can comprehensively and fully integrate fault response characteristics of multiple dimensions and more accurately determine whether a target axle box bearing has a fault through multi-state perception.

[0006] This specification provides a method for detecting a fault of an axle box bearing of a rail vehicle, comprising:

[0007] Acquiring a sound signal, a temperature signal, and a vibration acceleration signal of a target axle box bearing of a target vehicle, as well as temperature signals of other axle box bearings of the target vehicle except the target axle box bearing;

[0008] Determine a first detection result based on an acoustic response according to a sound signal of a target axle box bearing; determine a second detection result based on a vibration response according to a vibration acceleration signal of the target axle box bearing; determine a third detection result based on a temperature response according to a temperature signal of the target axle box bearing and temperature signals of other axle box bearings;

[0009] Determine a first fault detection result of a target axle box bearing according to the first detection result, the second detection result and the third detection result;

[0010] Determine a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameter of the target axle box bearing; wherein the mechanical response influencing parameter of the target axle box bearing is determined according to the wheel-rail force detection data within the target time period;

[0011] According to the second fault detection result of the target axle box bearing, it is determined whether the target axle box bearing has a fault.

[0012] In one embodiment, obtaining a sound signal of a target axle box bearing of a target vehicle includes:

[0013] The trackside monitoring equipment is used to collect the sound signals of the target axle box bearing when the target vehicle passes the monitoring point during the test period.

[0014] In one embodiment, obtaining a temperature signal and a vibration acceleration signal of a target axle box bearing of a target vehicle, and temperature signals of other axle box bearings of the target vehicle except the target axle box bearing, includes:

[0015] The temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle during the test period, as well as the temperature signals of other axle box bearings of the target vehicle except the target axle box bearing, are collected through the on-board monitoring equipment.

[0016] In one embodiment, determining a first detection result based on an acoustic response according to a sound signal of a target axlebox bearing comprises:

[0017] Obtain the speed of the target vehicle when it passes through the monitoring point during the test period, and the bearing parameters of the target axle box bearing;

[0018] Calculating a first state perception parameter of the target axle box bearing based on the acoustic response according to the sound signal of the target axle box bearing, the speed of the target vehicle when passing through the monitoring point during the test period, and the bearing parameter of the target axle box bearing;

[0019] The first detection result is determined according to the first state perception parameter.

[0020] In one embodiment, determining a second detection result based on a vibration response according to a vibration acceleration signal of a target axle box bearing comprises:

[0021] By performing time-frequency analysis on the vibration acceleration of the target axle box bearing within the test period, a corresponding second state perception parameter based on the vibration response is obtained;

[0022] A second detection result is determined based on the second state perception parameter.

[0023] In one embodiment, determining a third detection result based on temperature response according to the temperature signal of the target axle box bearing and the temperature signals of other axle box bearings includes:

[0024] Get the duration of the test period and the ambient temperature during the test period;

[0025] Calculate the third state perception parameter of the target axle box bearing based on the current temperature response according to the temperature signal of the target axle box bearing, the duration of the test period, the temperature signals of other axle box bearings, and the ambient temperature of the test period;

[0026] The third detection result is determined according to the third state perception parameter.

[0027] In one embodiment, determining a first fault detection result of a target axle box bearing according to the first detection result, the second detection result and the third detection result includes:

[0028] Obtaining a preset weight coefficient; wherein the preset weight coefficient is determined according to the correlation between different types of fault responses and the axle box bearing fault at different stages in the entire life cycle of the axle box bearing;

[0029] According to the first detection result, the second detection result, the third detection result, and the preset weight coefficient, a first fault detection result of the target axle box bearing is obtained by weighted summation.

[0030] In one embodiment, the mechanical response influencing parameters of the target axle box bearing are determined in the following manner:

[0031] Counting the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period; wherein the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period are determined based on the wheel-rail force detection data within the target time period;

[0032] According to the number of first-type mechanical response risks and second-type mechanical response risks within the target time period, the mechanical response influencing parameters of the target axle box bearing are determined.

[0033] This specification also provides a fault detection device for a rail vehicle axle box bearing, comprising:

[0034] An acquisition module, used for acquiring a sound signal, a temperature signal and a vibration acceleration signal of a target axle box bearing of a target vehicle, and a temperature signal of other axle box bearings of the target vehicle except the target axle box bearing;

[0035] A first determination module is used to determine a first detection result based on an acoustic response according to a sound signal of a target axle box bearing; determine a second detection result based on a vibration response according to a vibration acceleration signal of the target axle box bearing; and determine a third detection result based on a temperature response according to a temperature signal of the target axle box bearing and temperature signals of other axle box bearings;

[0036] A second determination module, configured to determine a first fault detection result of a target axle box bearing according to the first detection result, the second detection result and the third detection result;

[0037] a third determination module, configured to determine a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and a mechanical response influencing parameter of the target axle box bearing; wherein the mechanical response influencing parameter of the target axle box bearing is determined according to wheel-rail force detection data within a target time period;

[0038] The fourth determination module is used to determine whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing.

[0039] The present specification also provides a computer-readable storage medium having computer instructions stored thereon, which, when executed by a processor, implement the following steps: obtaining a sound signal, a temperature signal and a vibration acceleration signal of a target axle box bearing of a target vehicle, as well as temperature signals of other axle box bearings of the target vehicle except the target axle box bearing; determining a first detection result based on an acoustic response according to the sound signal of the target axle box bearing; determining a second detection result based on a vibration response according to the vibration acceleration signal of the target axle box bearing; determining a third detection result based on a temperature response according to the temperature signal of the target axle box bearing and the temperature signals of other axle box bearings; determining a first fault detection result of the target axle box bearing according to the first detection result, the second detection result and the third detection result; determining a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameters of the target axle box bearing; wherein the mechanical response influencing parameters of the target axle box bearing are determined according to the wheel-rail force detection data within a target time period; determining whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing.

[0040] Based on the fault detection method and device of the rail vehicle axle box bearing provided in this specification, the sound signal, temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle, as well as the temperature signal of the axle box bearings of the target vehicle other than the target axle box bearing are first obtained; and according to the sound signal, vibration acceleration signal, temperature signal of the target axle box bearing, and the temperature signal of the axle box bearings of the target vehicle other than the target axle box bearing, the first detection result based on the acoustic response, the second detection result based on the vibration response and the third detection result based on the temperature response are respectively determined; then according to the first detection result, the second detection result and the third detection result, the first fault detection result of the target axle box bearing is determined; and according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameter of the target axle box bearing, the second fault detection result of the target axle box bearing is determined; finally, according to the second fault detection result of the target axle box bearing, it is determined whether the target axle box bearing has a fault. In this way, the fault response characteristics of multiple dimensions can be comprehensively and fully integrated, and through multi-state perception, it can be accurately and finely determined whether the target axle box bearing has a fault, which effectively improves the fault detection accuracy and reduces the detection error. Furthermore, different fault types are distinguished according to the second fault detection result, and processing rules matching the fault types are adopted to carry out targeted fault processing on the detected axle box bearing fault. Thus, the detected target axle box bearing fault can be processed more accurately and effectively, and the fault can be repaired and eliminated in time, while avoiding the waste of resources caused by excessive repair. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of this specification, the drawings required for use in the embodiments will be briefly introduced below. The drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0042] Figure 1 It is a flow chart of a method for detecting a fault of an axle box bearing of a rail vehicle provided by an embodiment of the present specification;

[0043] Figure 2 It is a schematic diagram of an embodiment of a fault detection method for a rail vehicle axle box bearing provided by an embodiment of this specification, in a scenario example;

[0044] Figure 3 It is a schematic diagram of an embodiment of a fault detection method for a rail vehicle axle box bearing provided by an embodiment of this specification, in a scenario example;

[0045] Figure 4It is a schematic diagram of an embodiment of a fault detection method for a rail vehicle axle box bearing provided by an embodiment of this specification, in a scenario example;

[0046] Figure 5 It is a schematic diagram of an embodiment of a fault detection method for a rail vehicle axle box bearing provided by an embodiment of this specification, in a scenario example;

[0047] Figure 6 It is a schematic diagram of an embodiment of a fault detection method for a rail vehicle axle box bearing provided by an embodiment of this specification, in a scenario example;

[0048] Figure 7 is a schematic diagram of the structure of an electronic device provided by an embodiment of this specification;

[0049] Figure 8 It is a schematic diagram of the structural composition of a rail vehicle axle box bearing fault detection device provided by an embodiment of the present specification. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments in this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0051] Considering that most of the existing rail vehicle axle box bearing fault detection methods only collect and rely on single sound data to diagnose whether the axle box bearing has a fault. The characteristics such as the performance degradation law and evolution law of the axle box bearing at different stages of the life cycle are not taken into account at all, and it is not considered that in the life cycle of the axle box bearing, there are not only acoustic-based fault responses, but also temperature-based fault responses and vibration-based fault responses. It is precisely because of the lack of the above ideas that technical problems such as large detection errors and low detection accuracy are prone to occur when fault diagnosis is performed based on the existing rail vehicle axle box bearing fault detection methods.

[0052] In view of the root cause of the above problems, this specification considers that the performance degradation law and evolution law of the axle box bearing at different stages of the whole life cycle can be fully considered. First, by studying the fault records of a large number of sample axle box bearings, the influence of different types of fault responses (including: acoustic-based fault response, temperature-based fault response, and vibration-based fault response) at different stages of the axle box bearing's full cycle on the axle box bearing fault can be determined, and then the preset weight coefficients for different types of fault responses can be determined. Then, the characteristic data of different dimensions of the axle box bearing (including: sound signal, temperature signal, vibration acceleration signal) can be fully collected and based on the characteristic data of different dimensions of the axle box bearing (including: sound signal, temperature signal, vibration acceleration signal), the detection results based on multiple types of fault responses (for example, the first detection result based on acoustic response, the second detection result based on vibration response, and the third detection result based on temperature response) can be obtained. Then, the above multiple detection results can be used to integrate the fault responses of multiple dimensions, and combined with the preset weight coefficients, through multi-state perception, it can be accurately determined whether the axle box bearing has a fault. Thereby, it is possible to accurately detect whether the axle box bearing has a fault, effectively improve the detection accuracy, and reduce the detection error.

[0053] See also Figure 1 As shown, the embodiment of this specification provides a method for detecting a fault of an axle box bearing of a rail vehicle. The method may include the following contents when it is specifically implemented:

[0054] S101: Acquiring a sound signal, a temperature signal, and a vibration acceleration signal of a target axle box bearing of a target vehicle, and temperature signals of other axle box bearings of the target vehicle except the target axle box bearing;

[0055] S102: determining a first detection result based on an acoustic response according to a sound signal of a target axle box bearing; determining a second detection result based on a vibration response according to a vibration acceleration of the target axle box bearing; determining a third detection result based on a temperature response according to a temperature signal of the target axle box bearing and temperature signals of other axle box bearings;

[0056] S103: determining a first fault detection result of a target axle box bearing according to the first detection result, the second detection result and the third detection result;

[0057] S104: determining a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameter of the target axle box bearing; wherein the mechanical response influencing parameter of the target axle box bearing is determined according to the wheel-rail force detection data within the target time period;

[0058] S105: Determine whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing.

[0059] Based on the above embodiments, by simultaneously collecting and utilizing the sound signal, vibration acceleration signal, temperature signal of the target axle box bearing, and the temperature signals of other axle box bearings in the target vehicle other than the target axle box bearing, a first detection result based on the acoustic response, a second detection result based on the vibration response, and a third detection result based on the temperature response can be obtained; and then, by comprehensively utilizing the first detection result, the second detection result, and the third detection result, fault responses in multiple dimensions can be comprehensively and fully integrated, and through multi-state perception, it can be accurately determined whether the target axle box bearing has a fault.

[0060] In some embodiments, the axle box bearings mentioned above may specifically refer to bearings in an axle box device. The axle box device (abbreviated as axle box) may specifically refer to a component on a rail vehicle (e.g., EMU, locomotive, etc.) that is sleeved on the axle neck to connect the wheelset and the bogie frame or the body of a two-axle vehicle, and is used to transfer the weight and load of the vehicle body to the wheelset, lubricate the axle neck, reduce friction, and reduce running resistance. Generally, the axle box mentioned above may specifically include two types: a sliding bearing axle box device and a rolling bearing axle box device.

[0061] In a specific implementation, the target axle box bearing of the target vehicle currently to be fault-detected (or fault-diagnosed) may be indicated by using a combination of the vehicle number of the vehicle and the number of the axle box bearing in the vehicle.

[0062] In some embodiments, the above-mentioned acquisition of the sound signal of the target axle box bearing of the target vehicle may include, when implemented specifically, collecting the sound signal of the target axle box bearing of the target vehicle when it passes through a monitoring point during a test time period through a trackside monitoring device (e.g., a trackside acoustic monitoring device).

[0063] Before specific implementation, a monitoring point can be set up at a preset distance (for example, 400 km) beside the track section where the target vehicle is to pass, and trackside monitoring equipment (for example, TADS acoustic detection station or other monitoring equipment, etc.) can be deployed at the monitoring point.

[0064] Among them, in addition to collecting the sound signals of each axle box bearing when the target vehicle passes the detection point, the above-mentioned trackside monitoring equipment also includes the ability to collect mechanical detection data (for example, wheel-rail force) of the wheels corresponding to each axle box bearing when the target vehicle passes the detection point to determine whether there is a mechanical response risk for each axle box bearing.

[0065] For example, the trackside TPDS-1 detection station in the trackside monitoring equipment can also be used to detect the wheel-rail impact force when the target vehicle passes the detection point as a kind of mechanical detection data; and by comparing the mechanical detection data with the preset mechanical threshold, it is determined whether there is a mechanical failure in the wheel to determine whether it will affect the axle box bearing, resulting in corresponding mechanical risks for the axle box bearing.

[0066] Specifically, when it is detected that the wheel-rail impact force is greater than or equal to the preset second mechanical threshold, it can be determined that the wheel-rail has a secondary mechanical fault, and then a risk record of the second type of mechanical risk of the axle box bearing can be generated and uploaded. When it is detected that the wheel-rail impact force is greater than or equal to the preset first mechanical threshold, it can be determined that the wheel-rail has a primary mechanical fault, and then a risk record of the first type of mechanical risk of the axle box bearing can be generated and uploaded. Among them, the preset second mechanical threshold is greater than the preset first mechanical threshold.

[0067] In some embodiments, the above-mentioned acquisition of the temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle, as well as the temperature signals of other axle box bearings of the target vehicle except the target axle box bearing, when implemented specifically, may include the following contents: collecting the temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle during the test time period, as well as the temperature signals of other axle box bearings of the target vehicle except the target axle box bearing through the on-board monitoring equipment.

[0068] The above-mentioned other axle box bearings can be specifically understood as axle box bearings other than the target axle box bearing in the same rail vehicle (target vehicle).

[0069] Specifically, the temperature signals of the target axle box bearing of the target vehicle and other axle box bearings of the same vehicle during the test period can be collected through the on-board temperature monitoring equipment; the vibration acceleration signals of the target axle box bearing of the target vehicle during the test period can be collected through the on-board vibration acceleration monitoring equipment.

[0070] In some embodiments, the above-mentioned determination of the first detection result based on the acoustic response according to the sound signal of the target axle box bearing may include the following contents during specific implementation:

[0071] S1: Obtain the speed of the target vehicle when it passes through the monitoring point during the test period, and the bearing parameters of the target axle box bearing;

[0072] S2: Calculate the first state perception parameter of the target axle box bearing based on the acoustic response according to the sound signal of the target axle box bearing, the speed of the target vehicle when passing through the monitoring point during the test period, and the bearing parameter of the target axle box bearing;

[0073] S3: Determine the first detection result according to the first state perception parameter.

[0074] The above-mentioned first state perception parameter based on acoustic response can be specifically understood as parameter data reflecting the state of the target axle box bearing based on acoustic fault response.

[0075] When determining the first test result, refer to Figure 2As shown, according to the preset first grading evaluation rule and the first state perception parameter, a corresponding first evaluation value can be determined through acoustic diagnosis as the first detection result.

[0076] Specifically, according to the preset first grading evaluation rule, when it is determined that the data value of the first state perception parameter is greater than the first preset value of the first state and less than or equal to the second preset value of the first state, it can be determined that the state is in a sub-healthy state, and the corresponding first evaluation value is determined to be x 11 As the first detection result; when it is determined that the data value of the first state perception parameter is greater than the second preset value of the first state and less than or equal to the third preset value of the first state, it can be determined that it is in a secondary fault state, and the corresponding first evaluation value is determined to be x 12 As the first detection result; when it is determined that the data value of the first state perception parameter is greater than the third preset value of the first state, it can be determined that it is in a first-level fault state, and the corresponding first evaluation value is determined to be x 13 As the first test result.

[0077] The preset first grading evaluation rule at least includes a first preset value of the first state, a second preset value of the first state, and a third preset value of the first state. The preset first grading scoring rule may be obtained by learning a large amount of sample data related to acoustic response in advance.

[0078] Specifically, for example, first, a microphone array set up beside the monitoring point can be used as a trackside monitoring device to obtain the sound signals of the axle box bearings at different wheel positions when the target vehicle passes through the monitoring point; at the same time, the parameters such as the running speed of the target vehicle are obtained and combined, and the time-frequency analysis methods such as demodulation analysis and envelope analysis are used on the basis of noise reduction processing to obtain the sound characteristic frequency of the axle box bearing. Then, the sound characteristic frequency can be compared with the theoretical fault frequency of different parts of the bearing (including: inner ring, outer ring, roller, cage, etc.) to determine the corresponding fault state and obtain the first detection result. Among them, the theoretical fault frequency can be determined according to the bearing parameters of the axle box bearing.

[0079] When making a specific judgment, it can be divided into: sub-health state (the corresponding first evaluation value is: x 11 ), secondary fault state (the corresponding first evaluation value is: x 12 ), secondary fault state (the corresponding first evaluation value is: x 13 ). Among them, the above fault states are arranged from light to heavy: sub-health state, secondary fault state, and primary fault state.

[0080] In some embodiments, the above-mentioned determination of the second detection result based on the vibration response according to the vibration acceleration signal of the target axle box bearing may include the following contents during specific implementation:

[0081] S1: by performing time-frequency analysis on the vibration acceleration of the target axle box bearing within the test period, the corresponding second state perception parameter based on the vibration response is obtained;

[0082] S2: Determine a second detection result according to the second state perception parameter.

[0083] The second state perception parameter based on vibration response can be specifically understood as parameter data that reflects the state of the target axle box bearing based on a vibration fault response.

[0084] When determining the second test result, refer to Figure 3 As shown, according to the preset second hierarchical evaluation rule and the second state perception parameter, a corresponding second evaluation value can be determined through vibration diagnosis as the second detection result.

[0085] Specifically, according to the preset second classification evaluation rule, when it is determined that the data value of the second state perception parameter is greater than the first preset value of the second state and less than or equal to the second preset value of the second state, it can be determined that the state is in a sub-healthy state, and the corresponding second evaluation value is determined to be x 21 As the second detection result; when it is determined that the data value of the second state perception parameter is greater than the second preset value of the second state and less than or equal to the third preset value of the second state, it can be determined that it is in a secondary fault state, and the corresponding second evaluation value is determined to be x 22 As the second detection result; when it is determined that the data value of the second state perception parameter is greater than the third preset value of the second state, it can be determined that it is in a first-level fault state, and the corresponding second evaluation value is determined to be x 23 As the second detection result.

[0086] The preset second grading evaluation rule at least includes a first preset value of the second state, a second preset value of the second state, and a third preset value of the second state. The preset second grading scoring rule may be obtained by learning a large amount of sample data related to vibration response in advance.

[0087] Specifically, for example, first, the axle box bearing vibration acceleration sensor installed on the vehicle can be used as a vehicle-mounted monitoring device to collect the vibration acceleration of the axle box bearing in real time; and based on the signal noise reduction processing, the time-frequency analysis means such as envelope analysis can be used to calculate the vibration characteristic frequency of the axle box bearing corresponding to different wheel positions. Furthermore, the vibration characteristic frequency can be compared with the theoretical fault frequency of different parts of the bearing to determine the corresponding fault state and obtain the second detection result.

[0088] When making a specific judgment, it can be divided into: sub-health state (the corresponding second evaluation value is: x 21 ), secondary fault state (the corresponding second evaluation value is: x 22 ), secondary fault state (the corresponding second evaluation value is: x 23 ). Among them, the above fault states are arranged from light to heavy: sub-health state, secondary fault state, and primary fault state.

[0089] In some embodiments, the third detection result based on the temperature response is determined according to the temperature signal of the target axle box bearing and the temperature signals of other axle box bearings. When implemented specifically, it may include the following:

[0090] S1: Obtain the duration of the test period and the ambient temperature during the test period;

[0091] S2: Calculate the third state perception parameter of the target axle box bearing based on the current temperature response according to the temperature signal of the target axle box bearing, the duration of the test period, the temperature signals of other axle box bearings, and the ambient temperature of the test period;

[0092] S3: Determine the third detection result according to the third state perception parameter.

[0093] The third state perception parameter based on temperature response can be specifically understood as parameter data that reflects the state of the target axle box bearing based on a temperature-based fault response.

[0094] When specifically calculating the third state perception parameter, the temperature signal of the target axle box bearing may be compared and analyzed with the temperature signals of other axle box bearings of the same vehicle to obtain a relatively more accurate third state perception parameter.

[0095] When determining the third test result, refer to Figure 4 As shown, according to the preset third grading evaluation rule and the third state perception parameter, a corresponding third evaluation value can be determined through temperature diagnosis as the third detection result.

[0096] Specifically, according to the preset third grading evaluation rule, when it is determined that the data value of the third state perception parameter is greater than the first preset value of the third state and less than or equal to the second preset value of the third state, it can be determined that the state is in a sub-healthy state, and the corresponding third evaluation value is determined to be x 31 As the third detection result; when it is determined that the data value of the third state perception parameter is greater than the second preset value of the third state and less than or equal to the third preset value of the third state, it can be determined that it is in a secondary fault state, and the corresponding third evaluation value is determined to be x 32As the third detection result; when it is determined that the data value of the third state perception parameter is greater than the third preset value of the third state, it can be determined that it is in a first-level fault state, and the corresponding third evaluation value is determined to be x 33 As the third test result.

[0097] The preset third grading evaluation rule includes at least a first preset value of the third state, a second preset value of the third state, and a third preset value of the third state. The preset third grading scoring rule may be obtained by pre-learning a large amount of sample data involving temperature response.

[0098] Specifically, for example, the axle box bearing temperature sensor installed on the vehicle can be used as a vehicle-mounted monitoring device to collect the temperature signal of the axle box bearing in real time; and combined with the test time, the axle box bearing temperature signal at other locations on the same vehicle, the ambient temperature and other information, through real-time calculation and based on the absolute temperature and temperature rise rate, a judgment is made to determine the corresponding fault state and obtain the third detection result.

[0099] When making a specific judgment, it can be divided into: sub-health state (the corresponding third evaluation value is: x 31 ), level 3 fault state (the corresponding third evaluation value is: x 32 ), level 3 fault state (the corresponding third evaluation value is: x 33 ). Among them, the above fault states are arranged from light to heavy: sub-health state, secondary fault state, and primary fault state.

[0100] In some embodiments, the first fault detection result of the target axle box bearing is determined according to the first detection result, the second detection result and the third detection result. When implemented specifically, the following contents may be included:

[0101] S1: obtaining a preset weight coefficient; wherein the preset weight coefficient is determined according to the correlation between different types of fault responses and the axle box bearing fault at different stages in the entire life cycle of the axle box bearing;

[0102] S2: Obtain a first fault detection result of a target axle box bearing by weighted summation based on the first detection result, the second detection result, the third detection result, and a preset weight coefficient.

[0103] In this embodiment, the first detection result based on acoustic response, the second detection result based on vibration response, and the third detection result based on temperature response can be integrated simultaneously to establish a multivariate comprehensive evaluation model under multivariate state input conditions based on acoustics, vibration, and temperature, so as to accurately determine the first fault detection result that can relatively comprehensively reflect the fault state of the target axle box bearing.

[0104] In specific implementation, the first fault detection result of the target axle box bearing can be calculated in the following manner:

[0105] f(x)=f v (x)*α+f a (x)*β+f t (x)*γ

[0106] Where, f(x) is the first fault detection result, f v (x) is the first detection result, f a (x) is the second detection result, f t (x) is the third detection result, α is the first weight coefficient corresponding to the first detection result in the preset weight coefficients, β is the second weight coefficient corresponding to the second detection result in the preset weight coefficients, and γ is the third weight coefficient corresponding to the third detection result in the preset weight coefficients.

[0107] In some embodiments, the preset weight coefficient may be determined in advance based on the correlation between different types of fault responses and axle box bearing faults in different stages within a full cycle of a large amount of sample data.

[0108] For details, please refer to Figure 5 As shown. The complete cycle from the initial fault of the axle box bearing to the serious fault leading to the failure of the axle box bearing is divided into three different stages: early, middle and late. Combined with engineering experience, it can be determined that the urgency in the late stage of the fault is higher than that in the middle stage, and the urgency in the middle stage of the fault is higher than that in the early stage; and then the urgency for different stages can be determined. At the same time, according to the sample data, the significance of different types of fault responses in different stages is analyzed, and it can be determined that: in the early stage of the fault, the significance of the acoustic-based fault response is higher than that of other types of fault responses; in the middle stage of the fault, the significance of the vibration-based fault response is higher than that of other types of fault responses; in the late stage of the fault, the significance of the temperature-based fault response is higher than that of other types of fault responses. Then, the preset weight coefficient can be determined based on the significance of different types of fault responses in different stages and the urgency of different stages.

[0109] Specifically, for example, in this embodiment, according to the above method, it can be determined that the first weight coefficient, the second weight coefficient and the third weight coefficient in the preset weight coefficients are respectively: 0.65, 0.75 and 0.85.

[0110] In some embodiments, taking into account the influence of the wheel-rail impact force (or wheel-rail force) on the axle box bearing fault through transmission, in order to determine a fault detection result with higher accuracy and better effect, the mechanical response influencing parameter (or mechanical additional influencing factor) obtained based on the wheel-rail impact force can also be introduced and utilized to improve the first fault detection result to obtain the corresponding second fault detection result.

[0111] Specifically, considering that the axle box bearing is an important component connecting the wheel-axle system, the axle box and the primary suspension system, it bears complex alternating loads. The load borne by the wheel is often transmitted to the axle box bearing. Therefore, in order to detect the axle box bearing failure more accurately, it is proposed that the wheel-rail impact force or load response of the wheel can be taken into consideration as an influencing factor of the fatigue reliability of the axle box bearing, so as to more accurately determine the fault detection result that can reflect the actual state of the axle box bearing.

[0112] For details, please refer to Figure 6 The wheel-rail impact force can be determined by mechanical diagnosis; then, based on the wheel-rail impact force, the parameters affecting the mechanical response of the axle box bearing can be determined.

[0113] In this embodiment, the second fault detection result of the target axle box bearing is determined according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameter of the target axle box bearing. In specific implementation, the second fault detection result of the target axle box bearing can be calculated according to the following formula:

[0114] F(x)=f(x)*κ i

[0115] Among them, κ i is the mechanical response influencing parameter, F(x) is the second fault detection result, and f(x) is the first fault detection result.

[0116] Among them, the mechanical response influencing parameter κ i The specific value of can be determined based on the wheel-rail impact force (a kind of mechanical detection data) collected by the trackside monitoring equipment when the target vehicle passes the monitoring point within the target time period.

[0117] The target time period may specifically be a time period before the test, for example, 10 days before the test, or one week before the test.

[0118] Specifically, when the trackside monitoring device detects that the wheel-rail impact force is greater than or equal to the preset second mechanical threshold, it can be determined that the wheel has a secondary mechanical fault, and then a risk record of the second type of mechanical response risk of the axle box bearing can be generated and uploaded. When the wheel-rail impact force is detected to be greater than or equal to the preset first mechanical threshold, it can be determined that the wheel has a primary mechanical fault, and then a risk record of the first type of mechanical response risk of the axle box bearing can be generated and uploaded.

[0119] In some embodiments, the mechanical response influencing parameters of the target axle box bearing can be determined specifically in the following manner:

[0120] S1: Count the number of first-type response risks and the number of second-type response risks within the target time period; wherein the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period are determined based on the wheel-rail force detection data within the target time period;

[0121] S2: Determine the mechanical response influencing parameters of the target axle box bearing according to the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period.

[0122] In specific implementation, if the target wheel position corresponding to the target axle box bearing has no first-level mechanical response failure within the target time period, or the number of second-level mechanical response failures is less than or equal to 1 (that is, the number of first-type mechanical risks is 0, or the number of second-type mechanical response risks is less than or equal to 1), then the value of the mechanical response influencing parameter of the target axle box bearing can be determined to be κ1.

[0123] If the number of first-level mechanical response failures that occur in the target wheel position corresponding to the target axle box bearing within the target time period is greater than or equal to 1 and less than or equal to 3, or the number of second-level mechanical response failures is greater than or equal to 2 and less than or equal to 5 (that is, the number of first-type mechanical risks is greater than or equal to 1 and less than or equal to 3, or the number of second-type mechanical risks is greater than or equal to 2 and less than or equal to 5), then the value of the mechanical response influencing parameter of the target axle box bearing can be determined to be κ2.

[0124] If the number of first-level mechanical response failures that occur in the target wheel position corresponding to the target axle box bearing within the target time period is greater than or equal to 4, or the number of second-level mechanical response failures is greater than or equal to 6 (that is, the number of first-type mechanical risks is greater than or equal to 4, or the number of second-type mechanical risks is greater than or equal to 6), then the value of the mechanical response influencing parameter of the target axle box bearing can be determined to be κ3.

[0125] Among them, κ1<κ2<κ3.

[0126] In some embodiments, the above-mentioned determining whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing may include the following contents during specific implementation:

[0127] S1: when it is determined that the second fault detection result is less than a preset first reference threshold (eg, λ1), determining that the target axle box bearing does not have a fault;

[0128] S2: When it is determined that the second fault detection result is greater than a preset first reference threshold, it is determined that a fault exists in the target axle box bearing.

[0129] In some embodiments, when it is determined that a target axle box bearing has a fault, the method may also include the following when implemented: determining the fault type of the target axle box bearing based on the second fault detection result; and performing corresponding fault processing on the target axle box bearing using matching processing rules based on the fault type of the target axle box bearing.

[0130] In some embodiments, specifically, the following contents may be included:

[0131] S1: when it is determined that the second fault detection result is greater than or equal to a preset first reference threshold and less than a preset second reference threshold (for example, λ2), it is determined that a potential fault exists in the target axle box bearing; accordingly, the target axle box bearing is continuously tracked and monitored;

[0132] S2: when it is determined that the second fault detection result is greater than or equal to a preset second reference threshold value and less than a preset third reference threshold value (e.g., λ3), it is determined that a slight fault exists in the target axle box bearing; accordingly, a slight fault prompt message is generated to prompt that the fault is repaired within a reference time period (e.g., prompting that the fault is repaired within one week);

[0133] S3: When it is determined that the second fault detection result is greater than or equal to a preset third reference threshold, it is determined that a severe fault exists in the target axle box bearing; accordingly, a severe fault prompt message is generated to prompt the fault to be repaired as soon as possible.

[0134] Among them, the above-mentioned preset first reference threshold, preset second reference threshold and preset third reference threshold can be specifically obtained by learning from a large amount of sample data.

[0135] The reference time period can be flexibly set according to specific circumstances, idle resources, security requirements, etc. Specifically, the reference time period can be set to one week, or three days, etc. This specification does not limit this.

[0136] Based on the above embodiments, different types of fault conditions can be accurately distinguished according to the severity of the fault, so as to reasonably use limited resources to repair the fault and effectively avoid excessive repair.

[0137] In some embodiments, after generating a minor fault prompt message, the minor fault prompt message can be pushed to the staff first to remind the staff to complete the corresponding fault repair within a reference time period; at the same time, the timing will start from the push time point, and when it is monitored that the staff has not completed the fault repair at the reminder time point before the end of the reference time period, the minor fault prompt message will be resent to the staff for a second reminder.

[0138] In some embodiments, after a severe fault prompt message is generated, the severe fault prompt message may be pushed to the staff first to remind the staff to complete the corresponding fault repair as soon as possible; at the same time, starting from the push time point, a smaller time interval (for example, every half an hour) is used to check whether the staff has completed the corresponding fault repair; when it is detected that the staff has not completed the corresponding fault repair, the severe fault prompt message is continuously resent to the staff to effectively remind the staff to complete the relevant fault repair in a timely manner.

[0139] As can be seen from the above, based on the fault detection method of the rail vehicle axle box bearing provided by the embodiment of this specification, the sound signal, temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle, as well as the temperature signal of the axle box bearings of the target vehicle other than the target axle box bearing are first obtained; then, according to the sound signal, vibration acceleration signal, temperature signal of the target axle box bearing, and the temperature signal of the axle box bearings of the target vehicle other than the target axle box bearing, the first detection result based on the acoustic response, the second detection result based on the vibration response and the third detection result based on the temperature response are respectively determined; then, according to the first detection result, the second detection result and the third detection result, the first fault detection result of the target axle box bearing is determined; and according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameter of the target axle box bearing, the second fault detection result of the target axle box bearing is determined; finally, according to the second fault detection result of the target axle box bearing, it is determined whether the target axle box bearing has a fault. Thus, the fault responses of multiple dimensions can be comprehensively and fully integrated, and through multi-state perception, it can be accurately determined whether the target axle box bearing has a fault, which effectively improves the fault detection accuracy and reduces the detection error. Different fault types are distinguished according to the second fault detection result, and the faults are handled in a targeted manner using processing rules that match the fault types. This allows the detected target axle box bearing fault to be handled more accurately and effectively, and the fault can be repaired and eliminated in a timely manner, while avoiding the waste of resources caused by excessive repairs.

[0140] The embodiment of the present specification also provides an electronic device, including a processor and a memory for storing instructions executable by the processor, wherein the processor can perform the following steps according to the instructions when implemented: obtaining a sound signal, a temperature signal and a vibration acceleration of a target axle box bearing of a target vehicle, and a temperature signal of other axle box bearings of the target vehicle except the target axle box bearing; determining a first detection result based on an acoustic response according to the sound signal of the target axle box bearing; determining a second detection result based on a vibration response according to the vibration acceleration signal of the target axle box bearing; determining a third detection result based on a temperature response according to the temperature signal of the target axle box bearing and the temperature signals of other axle box bearings; determining a first fault detection result of the target axle box bearing according to the first detection result, the second detection result and the third detection result; determining a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameters of the target axle box bearing; wherein the mechanical response influencing parameters of the target axle box bearing are determined according to the wheel-rail force detection data within the target time period; determining whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing.

[0141] In order to complete the above instructions more accurately, refer to Figure 7 As shown, the embodiment of this specification also provides another specific electronic device, wherein the electronic device includes a network communication port 701, a processor 702 and a memory 703, and the above structures are connected through internal cables so that each structure can perform specific data interaction.

[0142] The network communication port 701 can be specifically used to obtain the sound signal, temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle, as well as the temperature signal of other axle box bearings of the target vehicle except the target axle box bearing.

[0143] The processor 702 can be specifically used to determine a first detection result based on an acoustic response according to a sound signal of a target axle box bearing; determine a second detection result based on a vibration response according to a vibration acceleration signal of the target axle box bearing; determine a third detection result based on a temperature response according to a temperature signal of the target axle box bearing and temperature signals of other axle box bearings; determine a first fault detection result of the target axle box bearing according to the first detection result, the second detection result and the third detection result; determine a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and a mechanical response influencing parameter of the target axle box bearing; wherein the mechanical response influencing parameter of the target axle box bearing is determined according to wheel-rail force detection data within a target time period; and determine whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing.

[0144] The memory 703 may be specifically used to store corresponding instruction programs.

[0145] In this embodiment, the network communication port 701 can be a virtual port that is bound to different communication protocols so that different data can be sent or received. For example, the network communication port can be a port responsible for web data communication, a port responsible for FTP data communication, or a port responsible for email data communication. In addition, the network communication port can also be a physical communication interface or communication chip. For example, it can be a wireless mobile network communication chip, such as GSM, CDMA, etc.; it can also be a Wifi chip; it can also be a Bluetooth chip.

[0146] In this embodiment, the processor 702 may be implemented in any appropriate manner. For example, the processor may take the form of a microprocessor or processor and a computer-readable medium storing a computer-readable program code (such as software or firmware) executable by the (micro)processor, a logic gate, a switch, an application specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller, etc. This specification does not limit this.

[0147] In this embodiment, the memory 703 may include multiple levels. In a digital system, anything that can store binary data can be a memory; in an integrated circuit, a circuit with a storage function that has no physical form is also called a memory, such as RAM, FIFO, etc.; in a system, a storage device with a physical form is also called a memory, such as a memory stick, TF card, etc.

[0148] The embodiment of the present specification also provides a computer-readable storage medium based on the above-mentioned rail vehicle axle box bearing fault detection method, the computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed, the following are achieved: obtaining the sound signal, temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle, as well as the temperature signal of other axle box bearings of the target vehicle except the target axle box bearing; determining a first detection result based on acoustic response according to the sound signal of the target axle box bearing; determining a second detection result based on vibration response according to the vibration acceleration signal of the target axle box bearing; determining a third detection result based on temperature response according to the temperature signal of the target axle box bearing and the temperature signals of other axle box bearings; determining a first fault detection result of the target axle box bearing according to the first detection result, the second detection result and the third detection result; determining a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameters of the target axle box bearing; wherein the mechanical response influencing parameters of the target axle box bearing are determined according to the wheel-rail force detection data within the target time period; determining whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing.

[0149] In this embodiment, the storage medium includes, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a cache, a hard disk (HDD), or a memory card. The memory may be used to store computer program instructions. The network communication unit may be an interface for network connection communication set in accordance with the standard specified by the communication protocol.

[0150] In this embodiment, the functions and effects specifically implemented by the program instructions stored in the computer-readable storage medium can be explained in comparison with other implementations and will not be described in detail here.

[0151] See also Figure 8 As shown, at the software level, the embodiment of this specification also provides a fault detection device for a rail vehicle axle box bearing, which may specifically include the following structural modules:

[0152] The acquisition module 801 may be specifically used to acquire the sound signal, temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle, and the temperature signal of other axle box bearings of the target vehicle except the target axle box bearing;

[0153] The first determination module 802 may be specifically used to determine a first detection result based on an acoustic response according to a sound signal of a target axle box bearing; determine a second detection result based on a vibration response signal according to a vibration acceleration of the target axle box bearing; and determine a third detection result based on a temperature response according to a temperature signal of the target axle box bearing and temperature signals of other axle box bearings;

[0154] A second determination module 803 may be specifically configured to determine a first fault detection result of a target axle box bearing according to the first detection result, the second detection result and the third detection result;

[0155] The third determination module 804 may be specifically configured to determine a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameter of the target axle box bearing; wherein the mechanical response influencing parameter of the target axle box bearing is determined according to the wheel-rail force detection data within the target time period;

[0156] The fourth determination module 805 may be specifically configured to determine whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing.

[0157] In some embodiments, when the acquisition module 801 is implemented, the sound signal of the target axle box bearing of the target vehicle can be acquired in the following manner: the sound signal of the target axle box bearing of the target vehicle when passing the monitoring point during the test time period is collected by the trackside monitoring equipment.

[0158] In some embodiments, when the above-mentioned acquisition module 801 is implemented, the temperature signal, vibration acceleration signal of the target axle box bearing of the target vehicle, and the temperature signals of other axle box bearings of the target vehicle except the target axle box bearing can be acquired in the following manner: the temperature signal, vibration acceleration signal of the target axle box bearing of the target vehicle during the test time period, and the temperature signals of other axle box bearings of the target vehicle except the target axle box bearing are collected by the on-board monitoring equipment.

[0159] In some embodiments, when the above-mentioned first determination module 802 is implemented, the first detection result based on the acoustic response can be determined according to the sound signal of the target axle box bearing in the following manner: the speed of the target vehicle when passing the monitoring point during the test time period, and the bearing parameters of the target axle box bearing are obtained; according to the sound signal of the target axle box bearing, the speed of the target vehicle when passing the monitoring point during the test time period, and the bearing parameters of the target axle box bearing, the first state perception parameters of the target axle box bearing based on the acoustic response are calculated; according to the first state perception parameters, the first detection result is determined.

[0160] In some embodiments, when the above-mentioned first determination module 802 is implemented, the second detection result based on the vibration response can be determined according to the vibration acceleration signal of the target axle box bearing in the following manner: by performing time-frequency analysis on the vibration acceleration of the target axle box bearing within the test time period, the corresponding second state perception parameters based on the vibration response are obtained; and the second detection result is determined according to the second state perception parameters.

[0161] In some embodiments, when the above-mentioned first determination module 802 is implemented, the third detection result based on temperature response can be determined according to the temperature signal of the target axle box bearing and the temperature signals of other axle box bearings in the following manner: obtain the duration of the test time period and the ambient temperature of the test time period; calculate the current third state perception parameter of the target axle box bearing based on temperature response according to the temperature signal of the target axle box bearing, the duration of the test time period, the temperature signals of other axle box bearings, and the ambient temperature of the test time period; determine the third detection result according to the third state perception parameter.

[0162] In some embodiments, when the above-mentioned second determination module 803 is implemented, the first fault detection result of the target axle box bearing can be determined according to the first detection result, the second detection result and the third detection result in the following manner: obtaining a preset weight coefficient; wherein the preset weight coefficient is determined according to the correlation between different types of fault responses and the axle box bearing fault in different stages during the entire life cycle of the axle box bearing; according to the first detection result, the second detection result, the third detection result, and the preset weight coefficient, the first fault detection result of the target axle box bearing is obtained by weighted summation.

[0163] In some embodiments, the mechanical response influencing parameters of the target axle box bearing are determined in the following manner: counting the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period; wherein, the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period are determined based on the wheel-rail force detection data within the target time period; based on the number of first-type mechanical response risks and the number of second-type mechanical risks within the target time period, determine the mechanical response influencing parameters of the target axle box bearing.

[0164] It should be noted that the units, devices or modules described in the above embodiments can be implemented by computer chips or entities, or by products with certain functions. For the convenience of description, the above devices are described separately by functions divided into various modules. Of course, when implementing this specification, the functions of each module can be implemented in the same or more software and / or hardware, or the modules that implement the same function can be implemented by a combination of multiple sub-modules or sub-units. The device embodiments described above are only schematic. For example, the division of the 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.

[0165] As can be seen from the above, the fault detection device for the rail vehicle axle box bearing provided by the embodiment of this specification first obtains the sound signal, temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle, as well as the temperature signal of the axle box bearings of the target vehicle other than the target axle box bearing; then, according to the sound signal, vibration acceleration signal, temperature signal of the target axle box bearing, and the temperature signal of the axle box bearings of the target vehicle other than the target axle box bearing, respectively determine the first detection result based on the acoustic response, the second detection result based on the vibration response, and the third detection result based on the temperature response; then, according to the first detection result, the second detection result, and the third detection result, determine the first fault detection result of the target axle box bearing; and according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameter of the target axle box bearing, determine the second fault detection result of the target axle box bearing; finally, according to the second fault detection result of the target axle box bearing, determine whether the target axle box bearing has a fault. Thus, it is possible to comprehensively and fully integrate the fault responses of multiple dimensions, accurately determine whether the target axle box bearing has a fault through multi-state perception, effectively improve the fault detection accuracy, and reduce the detection error. Different fault types are distinguished according to the second fault detection result, and the faults are handled in a targeted manner using processing rules that match the fault types. This allows the detected target axle box bearing fault to be handled more accurately and effectively, and the fault can be repaired and eliminated in a timely manner, while avoiding the waste of resources caused by excessive repairs.

[0166] In a specific scenario example, the rail vehicle axle box bearing fault detection method provided in this specification can be applied to perform specific fault diagnosis on the axle box bearing of a certain EMU.

[0167] Before specific implementation, the severity of the fault impact can be analyzed based on knowledge methods, and the impact of acoustic, vibration, and temperature diagnostic faults in fault association or health assessment during the entire life cycle of the axle box bearing can be determined. Then, the preset weight coefficients α, β, and γ can be determined as 0.65, 0.75, and 0.8, respectively.

[0168] During the specific test, the TADS detection station of a trackside EMU passing the monitoring point can detect and diagnose that the state of the axle box bearing at position 1 of the 7th car of the train set (for example, the target axle box bearing of the target vehicle) is "level 1 fault" and assign a value of x 13 =20 (ie, the first detection result is determined).

[0169] During operation (during the test period), the onboard monitoring host of the train group can detect and diagnose the bearing vibration state of the shaft position as "secondary fault" and assign a value of x 22 =10 (i.e., the second detection result is determined); at the same time, the shaft temperature state is detected and diagnosed as "secondary fault", and the value x is assigned 32 =10 (ie, the third detection result is determined).

[0170] The comprehensive score may then be calculated: f(x)=20*0.65+10*0.75+10*0.8=28.5 (ie, the first fault detection result is determined).

[0171] In addition, the train set also passed the trackside TPDS-1 detection station during its operation that day. The wheel-rail impact diagnosed the wheel position corresponding to the bearing as a "secondary alarm". At the same time, the TPDS-1 alarm results of the wheel position in the past 10 days (for example, within the target time period) were checked, and no other alarm results were found. Therefore, the mechanical additional influence factor was assigned a value of κ1=1; (that is, the mechanical response influence parameter was determined).

[0172] Finally, the comprehensive diagnosis result can be calculated: F(x)=28.5*1=28.5 (ie, the second fault detection result is determined).

[0173] According to the comprehensive diagnosis result, it is determined that: F(x)>λ2=20, and, F(x)<λ3=30.

[0174] Therefore, it can be determined that the comprehensive health assessment result is "warning", and the corresponding recommended treatment measure is "handle within 1 week". (That is, generate a minor fault prompt information to prompt the fault to be repaired within the reference time period).

[0175] Through the above scenario examples, it is verified that the fault detection method for rail vehicle axle box bearings provided in this specification is derived from the on-board vibration and temperature monitoring data, as well as the trackside acoustic and mechanical monitoring data. Compared with the traditional single-dimensional fault diagnosis input, it is more comprehensive and can cover the different stages of the evolution of bearing performance, that is, it can take into account the different response characteristics caused by the fault, which can help to timely discover the axle box bearing fault, improve the fulfillment rate of fault diagnosis, and reduce the false alarm rate. In addition, the fault mechanism analysis results and expert experience are taken into account, and differentiated influencing factors are given to the multivariate state perception data, in which the impact of the performance degradation process on the safety state is fully considered, which can further improve the accuracy of fault diagnosis. In addition, it can also provide reliable technical methods and support for the precise identification of the state during the digital precision repair or extended repair process of the axle box bearing.

[0176] Although the present specification provides method operation steps as described in the embodiments or flow charts, more or less operation steps may be included based on conventional or non-creative means. The order of steps listed in the embodiments is only one way of executing the order of many steps, and does not represent a unique execution order. When the device or client product in practice is executed, it can be executed in sequence or in parallel according to the method shown in the embodiments or the drawings (for example, a parallel processor or a multi-threaded processing environment, or even a distributed data processing environment). The term "include", "include" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, product or device including a series of elements includes not only those elements, but also includes other elements that are not explicitly listed, or also includes elements inherent to such a process, method, product or device. In the absence of more restrictions, it is not excluded that there are other identical or equivalent elements in the process, method, product or device including the elements. The first, second, etc. words are used to represent the name, and do not represent any particular order.

[0177] Those skilled in the art also know that, in addition to implementing the controller in a purely computer-readable program code, the controller can be made to implement the same function in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, such a controller can be considered as a hardware component, and the devices for implementing various functions included therein can also be considered as structures within the hardware component. Or even, the devices for implementing various functions can be considered as both software modules for implementing the method and structures within the hardware component.

[0178] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, classes, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer-readable storage media including storage devices.

[0179] Through the description of the above embodiments, it can be known that those skilled in the art can clearly understand that the present specification can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present specification can essentially be embodied in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a mobile terminal, a server, or a network device, etc.) to execute the methods described in each embodiment of the present specification or some parts of the embodiments.

[0180] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. This specification can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc.

[0181] Although the present specification is described through embodiments, those skilled in the art will appreciate that there are many modifications and changes to the present specification without departing from the spirit of the present specification, and it is intended that the appended claims include these modifications and changes without departing from the spirit of the present specification.

Claims

1. A method for detecting a fault of an axle box bearing of a rail vehicle, characterized in that: include: Acquiring a sound signal, a temperature signal, and a vibration acceleration signal of a target axle box bearing of a target vehicle, as well as temperature signals of other axle box bearings of the target vehicle except the target axle box bearing; Determine a first detection result based on an acoustic response according to a sound signal of a target axle box bearing; determine a second detection result based on a vibration response according to a vibration acceleration signal of the target axle box bearing; determine a third detection result based on a temperature response according to a temperature signal of the target axle box bearing and temperature signals of other axle box bearings; Determine a first fault detection result of a target axle box bearing according to the first detection result, the second detection result and the third detection result; Determine a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and the mechanical response influencing parameter of the target axle box bearing; wherein the mechanical response influencing parameter of the target axle box bearing is determined according to the wheel-rail force detection data within the target time period; determining whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing; The mechanical response influencing parameters of the target axle box bearing are determined in the following manner: Counting the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period; wherein the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period are determined based on the wheel-rail force detection data within the target time period; According to the number of first-type mechanical response risks and second-type mechanical response risks within the target time period, the mechanical response influencing parameters of the target axle box bearing are determined.

2. The method according to claim 1, characterized in that Acquire the sound signal of the target axle box bearing of the target vehicle, including: The trackside monitoring equipment is used to collect the sound signals of the target axle box bearing when the target vehicle passes the monitoring point during the test period.

3. The method according to claim 1, characterized in that: Acquire the temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle, and the temperature signals of other axle box bearings of the target vehicle except the target axle box bearing, including: The temperature signal and vibration acceleration signal of the target axle box bearing of the target vehicle during the test period, as well as the temperature signals of other axle box bearings of the target vehicle except the target axle box bearing, are collected through the on-board monitoring equipment.

4. The method according to claim 2, characterized in that: Determining a first detection result based on an acoustic response according to a sound signal of a target axle box bearing includes: Obtain the speed of the target vehicle when it passes through the monitoring point during the test period, and the bearing parameters of the target axle box bearing; Calculating a first state perception parameter of the target axle box bearing based on the acoustic response according to the sound signal of the target axle box bearing, the speed of the target vehicle when passing through the monitoring point during the test period, and the bearing parameter of the target axle box bearing; The first detection result is determined according to the first state perception parameter.

5. The method according to claim 3, characterized in that: Determining a second detection result based on a vibration response according to a vibration acceleration signal of a target axle box bearing includes: By performing time-frequency analysis on the vibration acceleration of the target axle box bearing within the test period, a corresponding second state perception parameter based on the vibration response is obtained; A second detection result is determined based on the second state perception parameter.

6. The method according to claim 3, characterized in that Determining a third detection result based on temperature response according to the temperature signal of the target axle box bearing and the temperature signals of other axle box bearings includes: Get the duration of the test period and the ambient temperature during the test period; Calculate the third state perception parameter of the target axle box bearing based on the current temperature response according to the temperature signal of the target axle box bearing, the duration of the test period, the temperature signals of other axle box bearings, and the ambient temperature of the test period; The third detection result is determined according to the third state perception parameter.

7. The method according to claim 1, characterized in that Determining a first fault detection result of a target axle box bearing according to the first detection result, the second detection result and the third detection result includes: Obtaining a preset weight coefficient; wherein the preset weight coefficient is determined according to the correlation between different types of fault responses and the axle box bearing fault at different stages in the entire life cycle of the axle box bearing; According to the first detection result, the second detection result, the third detection result, and the preset weight coefficient, a first fault detection result of the target axle box bearing is obtained by weighted summation.

8. A fault detection device for a rail vehicle axle box bearing, characterized in that: include: An acquisition module, used for acquiring a sound signal, a temperature signal and a vibration acceleration signal of a target axle box bearing of a target vehicle, and a temperature signal of other axle box bearings of the target vehicle except the target axle box bearing; A first determination module is used to determine a first detection result based on an acoustic response according to a sound signal of a target axle box bearing; determine a second detection result based on a vibration response according to a vibration acceleration signal of the target axle box bearing; and determine a third detection result based on a temperature response according to a temperature signal of the target axle box bearing and temperature signals of other axle box bearings; A second determination module, configured to determine a first fault detection result of a target axle box bearing according to the first detection result, the second detection result and the third detection result; a third determination module, configured to determine a second fault detection result of the target axle box bearing according to the first fault detection result of the target axle box bearing and a mechanical response influencing parameter of the target axle box bearing; wherein the mechanical response influencing parameter of the target axle box bearing is determined according to wheel-rail force detection data within a target time period; A fourth determination module, configured to determine whether the target axle box bearing has a fault according to the second fault detection result of the target axle box bearing; The mechanical response influencing parameters of the target axle box bearing are determined in the following manner: Counting the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period; wherein the number of first-type mechanical response risks and the number of second-type mechanical response risks within the target time period are determined based on the wheel-rail force detection data within the target time period; According to the number of first-type mechanical response risks and second-type mechanical response risks within the target time period, the mechanical response influencing parameters of the target axle box bearing are determined.

9. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images