Rail sleeper health diagnosis method and device based on strain statistical characteristics and electronic equipment

Abstract

The application provides a sleeper health diagnosis method and device based on strain statistical characteristics and electronic equipment, and belongs to the technical field of fault diagnosis. The method comprises the following steps: acquiring the probability distribution of multiple types of wheel load strain ratios of sleepers in an operating state; the wheel load strain ratio is the ratio of strain monitoring values of two strain sensors at different spatial positions under the action of the same train axle; and the sleeper is subjected to health diagnosis according to the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding reference probability distribution. The application utilizes the space-time correlation of sleeper strain fields under the action of train loads, proposes different types of wheel load strain ratios to represent the stress state of the structure, and performs sleeper structure health diagnosis through the probability distribution, thereby improving the accuracy of fault diagnosis.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis technology, and in particular to a method, device and electronic equipment for sleeper health diagnosis based on strain statistical characteristics. Background Technology

[0002] As railways age, under the long-term effects of train loads and environmental factors, sleeper structures inevitably develop various types of defects such as cracks and damage, leading to performance degradation, affecting track smoothness, and even threatening train operation safety.

[0003] Traditional visual inspection and image-based damage identification methods can only provide an intuitive evaluation of the surface damage of sleepers, making it difficult to detect hidden damage inside the sleepers. Furthermore, due to the lack of information on the internal stress and strain state of the sleepers, it is also difficult to establish a correlation between the surface damage of the sleeper structure and its service performance. The intelligent self-sensing steel-concrete composite sleeper system, by embedding a fiber optic grating sensing system during the sleeper manufacturing stage, can directly measure the internal temperature and stress-strain state of the sleeper.

[0004] Traditional strain data analysis methods typically focus only on the low-frequency statistical characteristics of strain monitoring data or study its correlation with temperature. However, these characteristics are often insensitive to local damage, resulting in a low accuracy rate in sleeper health diagnosis. Summary of the Invention

[0005] This invention provides a method, device, and electronic device for sleeper health diagnosis based on strain statistical characteristics, which solves the problem of low accuracy in sleeper fault diagnosis in the prior art and improves the accuracy of sleeper health diagnosis.

[0006] In a first aspect, the present invention provides a method for sleeper health diagnosis based on strain statistical characteristics, comprising:

[0007] The probability distribution of wheel load strain ratios of various types of sleepers under operational conditions is obtained; the wheel load strain ratio is the ratio of the strain monitoring values ​​of two strain sensors located at different spatial positions under the action of the same train axle.

[0008] Health diagnosis of the sleepers is performed based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution.

[0009] According to the present invention, a sleeper health diagnosis method based on strain statistical characteristics is provided. The method involves diagnosing the sleeper's health based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution. This includes: using Hellinger distance to characterize the similarity, calculating the Hellinger distance between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution; determining the maximum Hellinger distance among all Hellinger distances; and performing a health diagnosis on the sleeper based on the maximum Hellinger distance and a preset Hellinger distance threshold.

[0010] According to the present invention, a method for diagnosing the health of a railway sleeper based on strain statistical characteristics is provided. The step of diagnosing the health of the sleeper based on the maximum Hellinger distance and a preset Hellinger distance threshold includes: determining that the sleeper is in a healthy state when the maximum Hellinger distance is less than or equal to the preset Hellinger distance threshold; and determining that the sleeper is in an abnormal state when the maximum Hellinger distance is greater than the preset Hellinger distance threshold.

[0011] According to the present invention, a sleeper health diagnosis method based on strain statistical characteristics is provided. The step of obtaining the probability distribution of multiple types of wheel load strain ratios of sleepers under operating conditions includes: obtaining a wheel load strain ratio dataset corresponding to each type of wheel load strain ratio; wherein, each type of wheel load strain ratio dataset contains multiple wheel load strain ratio data collected within a preset time period; and performing statistical analysis on the wheel load strain ratios in each type of wheel load strain ratio dataset to obtain the probability distribution of each type of wheel load strain ratio.

[0012] According to the present invention, a sleeper health diagnosis method based on strain statistical characteristics further includes, before performing health diagnosis on the sleeper based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding benchmark probability distribution, the following steps are taken: obtaining a benchmark wheel load strain ratio dataset corresponding to each type of wheel load strain ratio; wherein, the benchmark wheel load strain ratio dataset for each type includes multiple wheel load strain ratio data collected when the sleeper is in an initial healthy state; and performing statistical analysis on the wheel load strain ratios in the benchmark wheel load strain ratio dataset for each type to obtain the benchmark probability distribution of each type of wheel load strain ratio.

[0013] According to the present invention, a sleeper health diagnosis method based on strain statistical characteristics further includes, before performing health diagnosis on the sleeper based on the maximum Hellinger distance and a preset Hellinger distance threshold, the following steps are taken: acquiring a healthy wheel load strain ratio dataset corresponding to each type of wheel load strain ratio; each type of healthy wheel load strain ratio dataset includes multiple wheel load strain ratio data collected when the sleeper is in a healthy state; performing statistical analysis on the wheel load strain ratios in each type of healthy wheel load strain ratio dataset to obtain a health probability distribution for each type of wheel load strain ratio; calculating the Hellinger distance between each type of health probability distribution and the corresponding baseline probability distribution; and using the maximum Hellinger distance among all Hellinger distances as the preset Hellinger distance threshold.

[0014] According to the present invention, a sleeper health diagnosis method based on strain statistical characteristics includes multiple types of wheel load strain ratios: a first wheel load strain ratio, a second wheel load strain ratio, a third wheel load strain ratio, and a fourth wheel load strain ratio. The first wheel load strain ratio is the ratio of the strain monitoring values ​​of a first strain sensor to those of a third strain sensor. The second wheel load strain ratio is the ratio of the strain monitoring values ​​of a second strain sensor to those of a fourth strain sensor. The third wheel load strain ratio is the ratio of the strain monitoring values ​​of the first strain sensor to those of the second strain sensor. The fourth wheel load strain ratio is the ratio of the strain monitoring values ​​of the third strain sensor to those of the fourth strain sensor. The first and second strain sensors are disposed in one side of the sleeper block, and the third and fourth strain sensors are disposed in the other side of the sleeper block. Furthermore, the first and third strain sensors are configured to synchronize their monitoring data; the second and fourth strain sensors are also configured to synchronize their monitoring data.

[0015] According to the present invention, a sleeper health diagnosis method based on strain statistical characteristics is provided, wherein the strain monitoring value is the peak value of the strain response after removing the temperature trend term.

[0016] Secondly, the present invention also provides a sleeper health diagnosis device based on strain statistical characteristics, comprising:

[0017] The acquisition module is used to acquire the probability distribution of various types of wheel load strain ratios of sleepers under operating conditions; the wheel load strain ratio is the ratio of the strain monitoring values ​​of two strain sensors located at different spatial positions under the action of the same train axle;

[0018] The health analysis module is used to perform health diagnosis on the sleepers based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution.

[0019] Thirdly, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the sleeper health diagnosis method based on strain statistical characteristics as described above.

[0020] Fourthly, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the sleeper health diagnosis method based on strain statistical characteristics as described above.

[0021] The present invention provides a sleeper health diagnosis method, device and electronic equipment based on strain statistical characteristics. It utilizes the spatiotemporal correlation of the sleeper strain field under train load, proposes different types of wheel load strain ratios to characterize the structural stress state, and uses its probability distribution to perform sleeper structural health diagnosis, thereby improving the accuracy of fault diagnosis. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0023] Figure 1 This is one of the flowcharts of the sleeper health diagnosis method based on strain statistical characteristics provided by the present invention;

[0024] Figure 2 This is a front view of the intelligent self-sensing double-block steel tube concrete sleeper system provided by the present invention.

[0025] Figure 3 This is a top view of the intelligent self-sensing double-block steel tube concrete sleeper system provided by the present invention.

[0026] Figure 4 This is a side sectional view of the intelligent self-sensing double-block steel tube concrete sleeper system provided by the present invention.

[0027] Figure 5 This is the second flowchart of the sleeper health diagnosis method based on strain statistical characteristics provided by the present invention;

[0028] Figure 6 This is a flowchart illustrating the process of determining a preset Hellinger distance threshold provided by the present invention;

[0029] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention;

[0030] The attached figures are labeled as follows:

[0031] 1: First strain sensor; 2: Second strain sensor; 3: Third strain sensor;

[0032] 4: Fourth strain sensor; 5: First temperature sensor; 6: Second temperature sensor;

[0033] 7: Fiber Bragg grating sensing system. Detailed Implementation

[0034] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0035] It should be noted that in the description of the embodiments of the present invention, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element. The terms "upper," "lower," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Unless otherwise expressly specified and limited, the terms "installed," "connected," and "linked" should be interpreted broadly, for example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two elements. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0036] The terms "first," "second," etc., used in this application are used to distinguish similar objects and not to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of this application can be implemented in orders other than those illustrated or described herein, and the objects distinguished by "first," "second," etc., are generally of the same class and the number of objects is not limited; for example, a first object can be one or more.

[0037] The following is combined Figures 1-7 This invention describes a method and apparatus for sleeper health diagnosis based on strain statistical characteristics, provided by embodiments of the present invention.

[0038] Figure 1 This is one of the flowcharts of the sleeper health diagnosis method based on strain statistical characteristics provided by the present invention, such as... Figure 1 As shown, including but not limited to the following steps:

[0039] Step 101: Obtain the probability distribution of wheel load strain ratios for various types of sleepers under operational conditions.

[0040] The wheel load strain ratio is the ratio of the strain monitoring values ​​of two strain sensors located at different spatial positions under the action of the same train axle.

[0041] This invention utilizes an intelligent self-sensing dual-block steel-concrete composite sleeper system to acquire strain monitoring values. The intelligent self-sensing dual-block steel-concrete composite sleeper system consists of dual-block steel-concrete composite sleepers and a pre-embedded fiber optic grating sensing system.

[0042] The fiber optic grating sensing system consists of a single sensing fiber. This system connects several FBG strain sensors and several FBG temperature sensors in series. The FBG temperature sensors provide temperature compensation for the FBG strain sensors to ensure the accuracy of strain measurement. The FBG strain sensors are arranged symmetrically about the sleeper centerline.

[0043] Specifically, the pairwise ratios of strain monitoring values ​​at different spatial locations on the sleepers under the action of the same train axle are calculated. The formula is as follows:

[0044]

[0045] Among them, R i,j The ratio of the strain readings of the i-th strain sensor to those of the j-th strain sensor acting on the same train axle; S i and S j These are the strain monitoring values ​​of the i-th and j-th strain sensors under the action of the same train axle.

[0046] Optionally, the number of FBG strain sensors is four, that is, two are arranged in each of the two side sleeper blocks, and the arrangement positions are symmetrical about the center line of the sleeper. For specific arrangement, please refer to [link / reference]. Figures 2 to 4 .in, Figure 2 This is a front view of the intelligent self-sensing double-block steel tube concrete sleeper system provided by the present invention. Figure 3 This is a top view of the intelligent self-sensing double-block steel tube concrete sleeper system provided by the present invention. Figure 4 This is a side sectional view of the intelligent self-sensing double-block steel tube concrete sleeper system provided by the present invention.

[0047] Specifically, such as Figures 2 to 4 As shown, a fiber optic grating sensing system 7 is pre-embedded inside the intelligent self-sensing steel-concrete composite sleeper. This sensing system connects four strain sensors (1-4) and two temperature sensors (first temperature sensor 5 and second temperature sensor 6) in series. The temperature sensors provide temperature compensation for adjacent strain sensors to ensure the accuracy of strain measurement. The spatial positions of the strain sensors are symmetrical about the center of the sleeper. Therefore, under train load, the monitoring data of the first strain sensor 1 and the third strain sensor 3 are synchronized, and the monitoring data of the second strain sensor 2 and the fourth strain sensor 4 are synchronized.

[0048] Optionally, the strain monitoring value is the peak strain response after removing the temperature trend term.

[0049] Understandably, the original strain monitoring values ​​can be expressed in the following form:

[0050] S total =S T +S w +S r

[0051] Among them, S total This is the original strain monitoring value; S T This is the temperature trend term, related to environmental factors such as temperature, and exhibits diurnal and seasonal low-frequency variation components; S w S represents the train wheel load strain term, and S represents the sleeper strain response under local train wheel load action; r For random monitoring of noise, it can generally be considered as white noise, which has the characteristics of low amplitude and uniform distribution across the entire frequency band.

[0052] Step 102: Perform a health diagnosis on the sleepers based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution.

[0053] The following is based on the above. Figures 2 to 4 Based on the strain monitoring data acquired by the intelligent self-sensing dual-block steel tube concrete sleeper system, the implementation of the present invention will be described.

[0054] It can be seen that the different types of wheel load strain ratios in this invention include a first wheel load strain ratio, a second wheel load strain ratio, a third wheel load strain ratio, and a fourth wheel load strain ratio. Specifically, the first wheel load strain ratio is the ratio of the strain monitoring values ​​of the first strain sensor and the third strain sensor; the second wheel load strain ratio is the ratio of the strain monitoring values ​​of the second strain sensor and the fourth strain sensor; the third wheel load strain ratio is the ratio of the strain monitoring values ​​of the first strain sensor and the second strain sensor; and the fourth wheel load strain ratio is the ratio of the strain monitoring values ​​of the third strain sensor and the fourth strain sensor.

[0055] It should be noted that the embodiments described below are merely examples of the implementation of the present invention and do not limit the uniqueness of the embodiments of the present invention.

[0056] As an optional embodiment, the present invention provides a sleeper health diagnosis method based on strain statistical characteristics. The method involves diagnosing the sleeper's health based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution. This includes: using Hellinger distance to characterize the similarity, calculating the Hellinger distance between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution; determining the maximum Hellinger distance among all Hellinger distances; and performing a health diagnosis on the sleeper based on the maximum Hellinger distance and a preset Hellinger distance threshold.

[0057] Figure 5 This is the second flowchart of the sleeper health diagnosis method based on strain statistical characteristics provided by the present invention. Optionally, the Hellinger distance between the probability distribution of each type of wheel load strain ratio and the corresponding benchmark probability distribution is calculated, specifically:

[0058]

[0059] Among them, P i,j Q represents the baseline probability distribution of different types of wheel load strain ratios. i,j H represents the probability distribution of different types of wheel load strain ratios. i,j This represents the Hellinger distance between the probability distribution of different types of wheel load strain ratios and the corresponding baseline probability distribution.

[0060] The maximum Hellinger distance among all Hellinger distances is determined using the following formula:

[0061] H S =max(H i,j )(i,j)=(1,3),(2,4),(1,2),(3,4).

[0062] It is understandable that, at the maximum Hellinger distance H S Less than or equal to the preset Hellinger distance threshold H C If the maximum Hellinger distance is greater than a preset Hellinger distance threshold, the sleeper is determined to be in a healthy state; if the maximum Hellinger distance is greater than a preset Hellinger distance threshold, the sleeper is determined to be in an abnormal state.

[0063] Based on the above embodiments, as an optional embodiment, the sleeper health diagnosis method based on strain statistical characteristics provided by the present invention includes obtaining the probability distribution of multiple types of wheel load strain ratios of sleepers under operating conditions, comprising: obtaining a wheel load strain ratio dataset corresponding to each type of wheel load strain ratio; wherein, each type of wheel load strain ratio dataset contains multiple wheel load strain ratio data collected within a preset time period; performing statistical analysis on the wheel load strain ratios in each type of wheel load strain ratio dataset to obtain the probability distribution of each type of wheel load strain ratio.

[0064] The preset duration can be one day or one week, and the specific duration can be set as needed.

[0065] It should be noted that, in order to improve the accuracy of health diagnosis, the preset duration here should be the same as the duration for calculating the baseline probability.

[0066] As an optional embodiment, the sleeper health diagnosis method based on strain statistical features provided by the present invention further includes, before performing health diagnosis on the sleeper according to the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding benchmark probability distribution: obtaining a benchmark wheel load strain ratio dataset corresponding to each type of wheel load strain ratio; wherein, the benchmark wheel load strain ratio dataset of each type includes multiple wheel load strain ratio data collected when the sleeper is in an initial healthy state; and performing statistical analysis on the wheel load strain ratios in the benchmark wheel load strain ratio dataset of each type to obtain the benchmark probability distribution of each type of wheel load strain ratio.

[0067] To ensure the accuracy of the baseline probability distribution, the number of samples for each type of wheel load strain ratio should be no less than 1000.

[0068] Figure 6 This is a flowchart illustrating the process of determining a preset Hellinger distance threshold provided by the present invention, as shown below. Figure 6 As shown, refer to the following. Figure 6 The process of determining the preset Hellinger distance threshold is explained.

[0069] The sleeper health diagnosis method based on strain statistical features provided by this invention further includes, before performing health diagnosis on the sleeper according to the maximum Hellinger distance and a preset Hellinger distance threshold: acquiring a healthy wheel load strain ratio dataset corresponding to each type of wheel load strain ratio; each type of healthy wheel load strain ratio dataset includes multiple wheel load strain ratio data collected when the sleeper is in a healthy state; performing statistical analysis on the wheel load strain ratios in each type of healthy wheel load strain ratio dataset to obtain a health probability distribution for each type of wheel load strain ratio; calculating the Hellinger distance between each type of health probability distribution and the corresponding baseline probability distribution; and using the maximum Hellinger distance among all Hellinger distances as the preset Hellinger distance threshold.

[0070] In summary, the sleeper health diagnosis method based on strain statistical characteristics provided by this invention utilizes the spatiotemporal correlation of the sleeper strain field under train load, proposes different types of wheel load strain ratios to characterize the structural stress state, and uses their probability distribution to perform sleeper structural health diagnosis, thereby improving the accuracy of fault diagnosis.

[0071] The present invention also provides a sleeper health diagnosis device based on strain statistical characteristics, the device comprising:

[0072] The acquisition module is used to obtain the probability distribution of various types of wheel load strain ratios of sleepers under operational conditions.

[0073] The wheel load strain ratio is the ratio of the strain monitoring values ​​of two strain sensors located at different spatial positions under the action of the same train axle.

[0074] The health analysis module is used to perform health diagnosis on the sleepers based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution.

[0075] It should be noted that the sleeper health diagnosis device based on strain statistical characteristics provided in this embodiment of the invention can execute the sleeper health diagnosis method based on strain statistical characteristics described in any of the above embodiments during specific operation, which will not be elaborated in this embodiment.

[0076] Figure 7 This is a schematic diagram of the structure of the electronic device provided by the present invention, such as... Figure 7As shown, the electronic device may include a processor 710, a communication interface 720, a memory 730, and a communication bus 740, wherein the processor 710, the communication interface 720, and the memory 730 communicate with each other via the communication bus 740. The processor 710 can call logical instructions in the memory 730 to execute a sleeper health diagnosis method based on strain statistical characteristics. This method includes: acquiring the probability distribution of multiple types of wheel load strain ratios of sleepers under operational conditions; the wheel load strain ratio is the ratio of strain monitoring values ​​of two strain sensors located at different spatial positions under the action of the same train axle; and performing a health diagnosis on the sleeper based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution.

[0077] Furthermore, the logical instructions in the aforementioned memory 730 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0078] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer-readable storage medium, the computer program comprising program instructions, wherein when the program instructions are executed by a computer, the computer is able to execute the sleeper health diagnosis method based on strain statistical characteristics provided in the above embodiments, the method comprising: acquiring the probability distribution of multiple types of wheel load strain ratios of sleepers under operating conditions; the wheel load strain ratio being the ratio of strain monitoring values ​​of two strain sensors located at different spatial positions under the action of the same train axle; and performing health diagnosis on the sleeper based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution.

[0079] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the sleeper health diagnosis method based on strain statistical characteristics provided in the above embodiments. The method includes: acquiring the probability distribution of multiple types of wheel load strain ratios of sleepers under operating conditions; the wheel load strain ratio being the ratio of strain monitoring values ​​of two strain sensors located at different spatial positions under the action of the same train axle; and performing health diagnosis on the sleeper based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution.

[0080] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0081] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0082] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for sleeper health diagnosis based on strain statistical characteristics, characterized in that, include: The probability distribution of wheel load strain ratios of various types of sleepers under operational conditions is obtained; the wheel load strain ratio is the ratio of the strain monitoring values ​​of two strain sensors located at different spatial positions under the action of the same train axle. Various types of wheel load strain ratios include: first wheel load strain ratio, second wheel load strain ratio, third wheel load strain ratio, and fourth wheel load strain ratio; The first wheel load strain ratio is the ratio of the strain monitoring values ​​of the first strain sensor and the third strain sensor; the second wheel load strain ratio is the ratio of the strain monitoring values ​​of the second strain sensor and the fourth strain sensor; the third wheel load strain ratio is the ratio of the strain monitoring values ​​of the first strain sensor and the second strain sensor; and the fourth wheel load strain ratio is the ratio of the strain monitoring values ​​of the third strain sensor and the fourth strain sensor. The first strain sensor and the second strain sensor are disposed in one side of the sleeper block, and the third strain sensor and the fourth strain sensor are disposed in the other side of the sleeper block; and the first strain sensor and the third strain sensor are configured to monitor data synchronously; the second strain sensor and the fourth strain sensor are configured to monitor data synchronously; wherein the arrangement of the strain sensors is symmetrical about the center line of the sleeper. Based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution, a health diagnosis is performed on the sleepers, specifically including: The similarity is characterized by the Hellinger distance to calculate the Hellinger distance between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution. Determine the maximum Hellinger distance among all Hellinger distances; The sleeper is subjected to health diagnosis based on the maximum Hellinger distance and the preset Hellinger distance threshold.

2. The sleeper health diagnosis method based on strain statistical characteristics according to claim 1, characterized in that, The step of performing a health diagnosis on the sleepers based on the maximum Hellinger distance and a preset Hellinger distance threshold includes: If the maximum Hellinger distance is less than or equal to a preset Hellinger distance threshold, the sleeper is determined to be in a healthy state. If the maximum Hellinger distance is greater than a preset Hellinger distance threshold, the sleeper is determined to be in an abnormal state.

3. The sleeper health diagnosis method based on strain statistical characteristics according to claim 1, characterized in that, The probability distribution of various types of wheel load strain ratios for sleepers under operational conditions includes: Obtain the wheel load strain ratio dataset corresponding to each type of wheel load strain ratio; wherein, each type of wheel load strain ratio dataset contains multiple wheel load strain ratio data collected within a preset time period; Statistical analysis was performed on the wheel load strain ratios in the dataset for each type of wheel load strain ratio to obtain the probability distribution of each type of wheel load strain ratio.

4. The sleeper health diagnosis method based on strain statistical characteristics according to claim 1, characterized in that, Before performing a health diagnosis on the sleepers based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution, the following steps are also included: Obtain the benchmark wheel load strain ratio dataset corresponding to each type of wheel load strain ratio; wherein, each type of benchmark wheel load strain ratio dataset includes multiple wheel load strain ratio data collected when the sleepers are in the initial healthy state; Statistical analysis was performed on the wheel load strain ratios in the benchmark wheel load strain ratio dataset for each type to obtain the benchmark probability distribution of the wheel load strain ratio for each type.

5. The sleeper health diagnosis method based on strain statistical characteristics according to claim 1, characterized in that, Before performing a health check on the sleeper based on the maximum Hellinger distance and a preset Hellinger distance threshold, the procedure further includes: Obtain the healthy wheel load strain ratio dataset corresponding to each type of wheel load strain ratio; each type of healthy wheel load strain ratio dataset includes multiple wheel load strain ratio data collected when the sleepers are in a healthy state; Statistical analysis was performed on the wheel load strain ratios in the datasets for each type of healthy wheel load strain ratio to obtain the health probability distribution of each type of wheel load strain ratio. Calculate the Hellinger distance between the health probability distribution for each type and the corresponding baseline probability distribution; The maximum Hellinger distance among all Hellinger distances is used as the preset Hellinger distance threshold.

6. The method for sleeper health diagnosis based on strain statistical characteristics according to claim 1, characterized in that, The strain monitoring value is the peak strain response after removing the temperature trend term.

7. A sleeper health diagnosis device based on strain statistical characteristics, used to implement the sleeper health diagnosis method based on strain statistical characteristics as described in any one of claims 1 to 6, characterized in that, include: The acquisition module is used to acquire the probability distribution of various types of wheel load strain ratios of sleepers under operational conditions; The wheel load strain ratio is the ratio of the strain monitoring values ​​of two strain sensors located at different spatial positions under the action of the same train axle; The health analysis module is used to perform health diagnosis on the sleepers based on the similarity between the probability distribution of each type of wheel load strain ratio and the corresponding baseline probability distribution.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the sleeper health diagnosis method based on strain statistical characteristics as described in any one of claims 1 to 6.

Images