阅读说明：本技术 一种轨道工程车辆走行传动部的监测方法及系统 (Monitoring method and system for running transmission part of rail engineering vehicle ) 是由 朱世昌 刘兴 王敏 邢佳 王琛 杨汉文 苗武 吴庆立 任涛龙 李子彤 朱红军 于 2021-08-04 设计创作，主要内容包括：本申请公开了一种轨道工程车辆走行传动部的监测方法及系统,以轨道工程车辆走行传动部的关键部件为重点监测对象,使用加速度传感器采集实时数据,可实现监测预警,进一步保障行车安全,还降低了操作人员的劳动强度。监测方法包括：在轨道工程车辆投入运行之前,获取轨道工程车辆走行传动部的初始车辆振动加速度信息；根据初始车辆振动加速度信息,分析得到初始状态标志CI指标；根据初始CI指标,得到报警阈值计算公式；当轨道工程车辆投入使用之后,获取轨道工程车辆走行传动部的实时车辆振动加速度信息；根据报警阈值计算公式及实时车辆振动加速度信息,得到实时报警阈值；根据实时报警阈值得到报警监测阈值,依据报警监测阈值对轨道工程车辆走行传动部进行报警监测识别。(The application discloses a monitoring method and a monitoring system for a track engineering vehicle walking transmission part, which take key components of the track engineering vehicle walking transmission part as key monitoring objects, use an acceleration sensor to collect real-time data, realize monitoring and early warning, further guarantee driving safety and reduce the labor intensity of operators. The monitoring method comprises the following steps: acquiring initial vehicle vibration acceleration information of a running transmission part of the rail engineering vehicle before the rail engineering vehicle is put into operation; analyzing to obtain an initial state mark CI index according to the initial vehicle vibration acceleration information; obtaining an alarm threshold value calculation formula according to the initial CI index; after the rail engineering vehicle is put into use, acquiring real-time vehicle vibration acceleration information of a walking transmission part of the rail engineering vehicle; obtaining a real-time alarm threshold according to an alarm threshold calculation formula and real-time vehicle vibration acceleration information; and obtaining an alarm monitoring threshold value according to the real-time alarm threshold value, and carrying out alarm monitoring identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value.)

1. A monitoring method for a running transmission part of a rail engineering vehicle is characterized by comprising the following steps:

acquiring initial vehicle vibration acceleration information of a running transmission part of the track engineering vehicle before the track engineering vehicle is put into operation;

analyzing to obtain an initial state mark CI index according to the initial vehicle vibration acceleration information;

obtaining an alarm threshold value calculation formula according to the initial CI index;

after the rail engineering vehicle is put into use, acquiring real-time vehicle vibration acceleration information of a walking transmission part of the rail engineering vehicle;

obtaining a real-time alarm threshold according to the alarm threshold calculation formula and the real-time vehicle vibration acceleration information;

and obtaining an alarm monitoring threshold value according to the real-time alarm threshold value, and carrying out alarm monitoring identification on the rail engineering vehicle running transmission part according to the alarm monitoring threshold value.

2. The method of claim 1, wherein analyzing an initial CI indicator based on the initial vehicle vibration acceleration information comprises:

according to the initial vehicle vibration acceleration information, carrying out feature statistics to obtain statistical features, wherein the statistical features comprise root mean square values, peak values, skewness, kurtosis, wave form factors, pulse factors, peak value factors, skewness, kurtosis, center-of-gravity frequency and/or root-mean-square frequency;

and calculating the statistical characteristics to obtain an initial CI index.

3. The method of claim 2, wherein deriving an alarm threshold calculation formula based on the initial CI indicator comprises:

carrying out normalization processing on the initial CI index to obtain a normalized initial CI index;

fusing the normalized initial CI indexes through a hypersphere support vector machine to obtain a health sign HI index;

calculating to obtain a probability distribution function of the HI index of the health sign;

and obtaining an alarm threshold value calculation formula according to the probability distribution function.

4. The method according to claim 3, wherein the obtaining real-time vehicle vibration acceleration information of the track-laying vehicle running transmission comprises:

setting a fixed-time acquisition cycle within a preset time period of the design life of the rail engineering vehicle;

and in each acquisition period, acquiring real-time vehicle vibration acceleration information of the track engineering vehicle walking transmission part.

5. The method of claim 4, wherein the acquisition periods are N, N being a positive integer greater than 1,

the method for obtaining the alarm monitoring threshold value according to the real-time alarm threshold value and carrying out alarm monitoring and identification on the rail engineering vehicle walking transmission part according to the alarm monitoring threshold value comprises the following steps:

calculating to obtain an initial alarm threshold value according to the alarm threshold value calculation formula and the initial CI index, wherein the initial alarm threshold value is used as a real-time alarm threshold value of the 0 th acquisition cycle;

comparing the real-time alarm threshold value of the M-th acquisition period with the real-time alarm threshold value of the M-1-th acquisition period, wherein M is a positive integer not less than 1 and not more than N;

when the real-time alarm threshold value of the Mth acquisition cycle is larger than the real-time alarm threshold value of the M-1 acquisition cycle, taking the real-time alarm threshold value of the Mth acquisition cycle as an alarm monitoring threshold value;

when the real-time alarm threshold value of the Mth acquisition cycle is not greater than the real-time alarm threshold value of the M-1 acquisition cycle, taking the real-time alarm threshold value of the M-1 acquisition cycle as an alarm monitoring threshold value;

and carrying out alarm monitoring and identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value.

6. A monitoring system of a running transmission part of a rail engineering vehicle is characterized by comprising: the system comprises an acquisition module and a monitoring server;

the acquisition module is used for acquiring initial vehicle vibration acceleration information of a running transmission part of the rail engineering vehicle before the rail engineering vehicle is put into operation;

the monitoring server is used for analyzing and obtaining an initial state mark CI index according to the initial vehicle vibration acceleration information;

the monitoring server is used for obtaining an alarm threshold value calculation formula according to the initial CI index;

the monitoring server is used for acquiring real-time vehicle vibration acceleration information of a running transmission part of the rail engineering vehicle after the rail engineering vehicle is put into use;

the monitoring server is used for obtaining a real-time alarm threshold value according to the alarm threshold value calculation formula and the real-time vehicle vibration acceleration information;

and the monitoring server is used for obtaining an alarm monitoring threshold value according to the real-time alarm threshold value and carrying out alarm monitoring identification on the rail engineering vehicle walking transmission part according to the alarm monitoring threshold value.

7. The system of claim 6,

the monitoring server is further used for carrying out feature statistics according to the initial vehicle vibration acceleration information to obtain statistical features, wherein the statistical features comprise root mean square values, peak values, skewness, kurtosis, wave form factors, impulse factors, peak value factors, skewness, kurtosis, center of gravity frequency and/or root mean square frequency;

and the monitoring server is also used for calculating the statistical characteristics to obtain an initial CI index.

8. The system of claim 7,

the monitoring server is also used for carrying out normalization processing on the initial CI index to obtain a normalized initial CI index;

the monitoring server is further used for fusing the normalized initial CI indexes through a hypersphere support vector machine to obtain health sign HI indexes;

the monitoring server is further used for calculating a probability distribution function of the health sign HI index;

and the monitoring server is also used for obtaining an alarm threshold value calculation formula according to the probability distribution function.

9. The system of claim 8,

the monitoring server is also used for setting a fixed-time acquisition cycle within a preset time period of the design life of the rail engineering vehicle;

the monitoring server is further used for acquiring real-time vehicle vibration acceleration information of the track engineering vehicle walking transmission part in each acquisition period.

10. The system of claim 9, wherein the acquisition periods are N, N being a positive integer greater than 1,

the monitoring server is further used for calculating an initial alarm threshold according to the alarm threshold calculation formula and the initial CI index, wherein the initial alarm threshold is used as a real-time alarm threshold of the 0 th acquisition cycle;

the monitoring server is further used for comparing the real-time alarm threshold value of the M-th acquisition cycle with the real-time alarm threshold value of the M-1-th acquisition cycle, wherein M is a positive integer not less than 1 and not more than N;

the monitoring server is further used for taking the real-time alarm threshold value of the Mth acquisition cycle as an alarm monitoring threshold value when the real-time alarm threshold value of the Mth acquisition cycle is larger than the real-time alarm threshold value of the M-1 th acquisition cycle;

the monitoring server is further used for taking the real-time alarm threshold value of the M-1 acquisition cycle as an alarm monitoring threshold value when the real-time alarm threshold value of the Mth acquisition cycle is not greater than the real-time alarm threshold value of the M-1 acquisition cycle;

and the monitoring server is also used for carrying out alarm monitoring and identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value.

Technical Field

The invention relates to the technical field of rail transit devices, in particular to a method and a system for monitoring a running transmission part of a rail engineering vehicle.

Background

With the rapid development of the rail transit industry in recent years, rail engineering vehicles have the application characteristics of high density, high frequency, high bearing capacity and the like, so that the driving safety is guaranteed, the operation and maintenance cost is reduced, and the rail engineering vehicles have great significance to the field of rail transit.

Although our country has started the research on train safety monitoring from the last 90 s and has achieved certain achievements in various host factories and related research institutes and colleges in terms of parts of rail vehicles such as braking, traction, pantograph, wheel rail, motor and system health management technology, the running transmission part is taken as a life-limiting key part of the rail vehicle, which is easy to cause large-scale accidents, and the existing research and application generally lacks a system for safety monitoring of the running transmission part.

The research and application of how to realize reliable monitoring of the walking transmission part and deeply mine the data value are the problems which are urgently needed to be solved by the technical personnel in the field at present.

Disclosure of Invention

In order to solve the technical problems, the invention aims to provide a method and a system for monitoring a track engineering vehicle walking transmission part, wherein the track engineering vehicle walking transmission part is a key monitoring object, and the functions of monitoring and early warning, fault diagnosis, service life prediction, big data analysis, intelligent maintenance and the like of key components can be realized, so that the full life cycle health management of the track engineering vehicle is realized, the driving safety is ensured, and the operation and maintenance cost is reduced.

The invention provides a monitoring method of a running transmission part of a rail engineering vehicle, which comprises the following steps:

acquiring initial vehicle vibration acceleration information of a running transmission part of the rail engineering vehicle before the rail engineering vehicle is put into operation;

analyzing to obtain an initial state mark CI index according to the initial vehicle vibration acceleration information;

obtaining an alarm threshold value calculation formula according to the initial CI index;

after the rail engineering vehicle is put into use, acquiring real-time vehicle vibration acceleration information of a walking transmission part of the rail engineering vehicle;

obtaining a real-time alarm threshold according to an alarm threshold calculation formula and real-time vehicle vibration acceleration information;

and obtaining an alarm monitoring threshold value according to the real-time alarm threshold value, and carrying out alarm monitoring identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value.

Further, according to the initial vehicle vibration acceleration information, an initial CI index is obtained through analysis, including:

according to the initial vehicle vibration acceleration information, carrying out feature statistics to obtain statistical features, wherein the statistical features comprise root mean square values, peak values, skewness, kurtosis, wave form factors, pulse factors, peak value factors, skewness, kurtosis, center-of-gravity frequency and/or root-mean-square frequency;

and calculating statistical characteristics to obtain an initial CI index.

Further, according to the initial CI index, an alarm threshold calculation formula is obtained, which includes:

carrying out normalization processing on the initial CI index to obtain a normalized initial CI index;

fusing the normalized initial CI indexes through a hypersphere support vector machine to obtain a health sign HI index;

calculating to obtain a probability distribution function of the HI index of the health sign;

and obtaining an alarm threshold value calculation formula according to the probability distribution function.

Further, the method for acquiring the real-time vehicle vibration acceleration information of the track engineering vehicle walking transmission part comprises the following steps:

setting a fixed-time acquisition cycle within a preset time period of the design life of the rail engineering vehicle;

and in each acquisition period, acquiring real-time vehicle vibration acceleration information of the track engineering vehicle walking transmission part.

Furthermore, the number of the acquisition periods is N, N is a positive integer greater than 1,

obtaining an alarm monitoring threshold value according to the real-time alarm threshold value, and carrying out alarm monitoring and identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value, wherein the alarm monitoring and identification comprises the following steps:

calculating to obtain an initial alarm threshold value according to an alarm threshold value calculation formula and an initial CI index, wherein the initial alarm threshold value is used as a real-time alarm threshold value of the 0 th acquisition cycle;

comparing the real-time alarm threshold of the Mth acquisition period with the real-time alarm threshold of the M-1 acquisition period, wherein M is a positive integer not less than 1 and not more than N;

when the real-time alarm threshold value of the Mth acquisition cycle is larger than the real-time alarm threshold value of the M-1 acquisition cycle, taking the real-time alarm threshold value of the Mth acquisition cycle as an alarm monitoring threshold value;

when the real-time alarm threshold value of the Mth acquisition cycle is not greater than the real-time alarm threshold value of the M-1 acquisition cycle, taking the real-time alarm threshold value of the M-1 acquisition cycle as an alarm monitoring threshold value;

and carrying out alarm monitoring and identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value.

The invention provides a monitoring system of a running transmission part of a rail engineering vehicle, which comprises the following components:

the system comprises an acquisition module and a monitoring server;

the system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring initial vehicle vibration acceleration information of a track engineering vehicle walking transmission part before the track engineering vehicle is put into operation;

the monitoring server is used for analyzing and obtaining an initial state mark CI index according to the initial vehicle vibration acceleration information;

the monitoring server is used for obtaining an alarm threshold value calculation formula according to the initial CI index;

the monitoring server is used for acquiring real-time vehicle vibration acceleration information of a track engineering vehicle walking transmission part after the track engineering vehicle is put into use;

the monitoring server is used for obtaining a real-time alarm threshold value according to an alarm threshold value calculation formula and the real-time vehicle vibration acceleration information;

and the monitoring server is used for obtaining an alarm monitoring threshold value according to the real-time alarm threshold value and carrying out alarm monitoring identification on the rail engineering vehicle walking transmission part according to the alarm monitoring threshold value.

Further, the monitoring server is also used for carrying out feature statistics according to the initial vehicle vibration acceleration information to obtain statistical features, wherein the statistical features comprise root mean square values, peak values, skewness, kurtosis, wave form factors, pulse factors, peak value factors, skewness, kurtosis, center of gravity frequency and/or root mean square frequency;

and the monitoring server is also used for calculating statistical characteristics to obtain an initial CI index.

Further, the monitoring server is also used for carrying out normalization processing on the initial CI index to obtain a normalized initial CI index;

the monitoring server is also used for fusing the normalized initial CI indexes through a hypersphere support vector machine to obtain a health sign HI index;

the monitoring server is also used for calculating a probability distribution function of the HI index of the health sign;

and the monitoring server is also used for obtaining an alarm threshold value calculation formula according to the probability distribution function.

Furthermore, the monitoring server is also used for setting a fixed-time acquisition cycle within a preset time period of the design life of the rail engineering vehicle;

and the monitoring server is also used for acquiring the real-time vehicle vibration acceleration information of the track engineering vehicle walking transmission part in each acquisition period.

Furthermore, the number of the acquisition periods is N, N is a positive integer greater than 1,

the monitoring server is also used for calculating to obtain an initial alarm threshold value according to an alarm threshold value calculation formula and an initial CI index, and the initial alarm threshold value is used as a real-time alarm threshold value of the 0 th acquisition cycle;

the monitoring server is also used for comparing the real-time alarm threshold of the Mth acquisition cycle with the real-time alarm threshold of the Mth-1 acquisition cycle, wherein M is a positive integer not less than 1 and not more than N;

the monitoring server is also used for taking the real-time alarm threshold value of the Mth acquisition cycle as an alarm monitoring threshold value when the real-time alarm threshold value of the Mth acquisition cycle is larger than the real-time alarm threshold value of the M-1 acquisition cycle;

the monitoring server is also used for taking the real-time alarm threshold value of the M-1 acquisition cycle as an alarm monitoring threshold value when the real-time alarm threshold value of the Mth acquisition cycle is not greater than the real-time alarm threshold value of the M-1 acquisition cycle;

and the monitoring server is also used for carrying out alarm monitoring and identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value.

As can be seen from the above, the monitoring system of the track engineering vehicle running transmission part takes key components (such as an axle box bearing, a gear box, a transmission shaft, an air compressor and the like) of the track engineering vehicle running transmission part as key monitoring objects, uses the acceleration sensor for real-time monitoring, can realize monitoring early warning and fault diagnosis, further guarantees driving safety, and also reduces the labor intensity of operators.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a schematic flow chart of an embodiment of a monitoring method for a running transmission of a railway engineering vehicle provided by the invention;

FIG. 2 is a schematic diagram of an alarm threshold calculation formula provided in an embodiment of the present invention;

FIG. 3 is a schematic diagram of alarm monitoring and identification of a running transmission part of a railway engineering vehicle provided by the embodiment of the invention;

FIG. 4 is a schematic structural diagram of an embodiment of a monitoring system of a running transmission part of the railway engineering vehicle provided by the invention;

Detailed Description

In order to make those skilled in the art better understand the technical solutions in the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

It will be understood that when an element is referred to as being "fixed" or "disposed" on another element, it can be directly on the other element or be indirectly disposed on the other element; when an element is referred to as being "connected to" another element, it can be directly connected to the other element or be indirectly connected to the other element.

It will be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like, refer to an orientation or positional relationship illustrated in the drawings for convenience in describing the present application and to simplify description, and do not indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present application.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the present application, "plurality" or "a plurality" means two or more unless specifically limited otherwise.

It should be understood that the structures, ratios, sizes, and the like shown in the drawings are only used for matching the disclosure of the specification, so as to be understood and read by those skilled in the art, and are not used to limit the practical limit conditions of the present application, so that the modifications of the structures, the changes of the ratio relationships, or the adjustment of the sizes, do not have the technical essence, and the modifications, the changes of the ratio relationships, or the adjustment of the sizes, are all within the scope of the technical contents disclosed in the present application without affecting the efficacy and the achievable purpose of the present application.

The embodiments of the present application are written in a progressive manner.

The invention is mainly applied to the monitoring scene of the rail engineering vehicle, and can also be applied to other scenes when in specific application, and no specific description is made. In the embodiments of the present invention, a rail construction vehicle is taken as an example for description.

Referring to fig. 1, an embodiment of the present invention provides a method for monitoring a running transmission of a rail engineering vehicle, including:

101. acquiring initial vehicle vibration acceleration information of a running transmission part of the rail engineering vehicle before the rail engineering vehicle is put into operation;

in the embodiment, before the rail engineering vehicle is put into operation and used, for example, within 5 hours before operation, the operation states as many as possible are completed under the permission of the rail traffic industry regulations and operation specifications, and vibration acceleration signals of each key component of the walking transmission part are acquired through the acceleration sensor. The running transmission part comprises: the hydraulic transmission device comprises a first transmission shaft, an elastic coupling, a diesel engine, a hydraulic transmission case, a second transmission shaft, a secondary axle gear case, a bogie, a third transmission shaft, a primary axle gear case, a transfer case and an air compressor. The acceleration sensor adopts a piezoelectric acceleration sensor, the piezoelectric acceleration sensor adopts two types of bidirectional acceleration sensors and one-way acceleration sensors, and the two-way acceleration sensors are preferably selected.

102. Analyzing to obtain an initial state mark CI index according to the initial vehicle vibration acceleration information;

in this embodiment, according to the description in step 101, according to the vehicle vibration acceleration information in the trial operation stage, an initial state Indicator (CI) index of the running transmission part of the rail engineering vehicle is obtained through analysis processing, which specifically includes:

optionally, according to the initial vehicle vibration acceleration information, performing feature statistics to obtain statistical features, where the statistical features include a root mean square value, a peak value, a skewness, a kurtosis, a form factor, a pulse factor, a peak factor, a skewness, a kurtosis, a center of gravity frequency, and/or a root mean square frequency;

and calculating statistical characteristics to obtain an initial CI index.

103. Obtaining an alarm threshold value calculation formula according to the initial CI index;

in this embodiment, an initial input sample is formed according to the initial CI index, and a calculation analysis is performed to obtain an alarm threshold calculation formula.

104. After the rail engineering vehicle is put into use, acquiring real-time vehicle vibration acceleration information of a walking transmission part of the rail engineering vehicle;

in this embodiment, after the track engineering vehicle is put into use, acquiring a real-time vehicle vibration acceleration signal of a track engineering vehicle walking transmission part specifically includes:

optionally, setting a fixed-time acquisition cycle within a preset time period of the design life of the rail engineering vehicle;

and in each acquisition period, acquiring real-time vehicle vibration acceleration information of the track engineering vehicle walking transmission part.

105. Obtaining a real-time alarm threshold according to an alarm threshold calculation formula and real-time vehicle vibration acceleration information;

in the embodiment, the real-time vehicle vibration acceleration information is brought into the alarm threshold value calculation formula, so that the real-time alarm threshold value can be obtained.

106. And obtaining an alarm monitoring threshold value according to the real-time alarm threshold value, and carrying out alarm monitoring identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value.

In this embodiment, after the alarm monitoring threshold is obtained according to the real-time alarm threshold, the system monitors the track engineering vehicle traveling transmission part according to comparison and analysis between the alarm monitoring threshold and the real-time acquired data, and performs alarm identification.

In the embodiment of the invention, the monitoring system of the rail engineering vehicle running transmission part takes key components (such as an axle box bearing, a gear box, a transmission shaft, an air compressor and the like) of the rail engineering vehicle running transmission part as key monitoring objects, uses the acceleration sensor for real-time monitoring, can realize monitoring early warning and fault diagnosis, further guarantees the driving safety, and also reduces the labor intensity of operators.

To explain in detail the alarm threshold calculation formula obtained according to the initial CI index in step 103 in the embodiment of fig. 1, as shown in fig. 2, fig. 2 is a schematic diagram of the alarm threshold calculation formula provided in the embodiment of the present invention, and includes:

201. carrying out normalization processing on the initial CI index to obtain a normalized initial CI index;

in this embodiment, the CI index is time-series, and normalization index expression processing is performed on each initial CI index according to the time-series, where the normalization index expression is:

wherein i 1, 2., 11 denotes the number of the CI index, j 1, 2.., n denotes the time series of the CI index, and CIⁱIndicates the i-th CI index,represents the jth numerical value of the ith CI index, and GCI represents the normalized CI index.

202. Fusing the normalized initial CI indexes through a hypersphere support vector machine to obtain a health sign HI index;

in this embodiment, the fusing the normalized initial CI index by the hypersphere support vector machine expression includes:

using a hypersphere support vector machine expression:

||X_j-c||²≤r²+ξ_j

wherein X is an input sample before the rail engineering vehicle is put into operation and consists of GCI;c is the center of the sphere of the hypersphere, r is the radius of the hypersphere, F is the regularization coefficient, xi_jFor relaxing variables, Lagrange coefficients alpha are introduced_i≥0,γ_iAnd (3) more than or equal to 0, converting the problem of solving the minimum value by the expression of the hypersphere support vector machine into a dual quadratic programming problem:

wherein, X_j、X_kRepresenting arbitrary input samples that are not identical, (X)_j,X_K) To representX_jAnd X_kThe inner product of (d). Introducing a kernel function phi (X) to map X to a high-dimensional space, and using K for the purpose<X_j,X_k>＝φ(X_j)·φ(X_k) Instead of (X)_j·X_k) And solving an equation to obtain the following supersphere sphere center expression and supersphere radius expression:

then according to a certain sample Z, the distance of the sphere center can be obtained as follows:

finally, a Health Indicator (HI) index expression is obtained:

203. calculating to obtain a probability distribution function of the HI index of the health sign;

in this embodiment, the calculating a probability distribution function of the health indicator HI index includes:

performing M equal division on the HI index, wherein the probability density function expression is as follows:

whereinNum [ m.DELTA.HI, (m + 1). DELTA.HI as equally spaced increments of HI index]Is the interval [ m.DELTA HI, (m + 1). DELTA HI]H betweenI number of indices, num [ min (HI), max (HI)]Is the total number of HI indicators;

according to the probability density function, obtaining a corresponding Probability Distribution Function (PDF) as:

204. and obtaining an alarm threshold value calculation formula according to the probability distribution function.

In the present embodiment, when the probability distribution function PDF_mWhen reaching 0.999, correspondingly, the minimum value of the HI index is an alarm threshold value, and the alarm threshold value calculation formula is as follows:

HI_alarm＝{min(HI_m)|PDF_m＞＝0.999}。

in step 106 of the embodiment in fig. 1, the number of the acquisition cycles of the embodiment is N, where N is a positive integer greater than 1, the alarm monitoring threshold is obtained according to the real-time alarm threshold, and the alarm monitoring and identification of the track engineering vehicle running transmission part are performed according to the alarm monitoring threshold, which is described in detail as follows:

as shown in fig. 3, fig. 3 is a schematic diagram of monitoring and identifying an alarm of a running transmission part of a railway engineering vehicle according to an embodiment of the present invention, and the schematic diagram includes:

301. calculating to obtain an initial alarm threshold value according to an alarm threshold value calculation formula and an initial CI index, wherein the initial alarm threshold value is used as a real-time alarm threshold value of the 0 th acquisition cycle;

in this embodiment, before the rail engineering vehicle is put into operation, an initial alarm threshold is obtained as an initial real-time alarm threshold for the initial CI index according to the alarm threshold calculation formula.

302. Comparing the real-time alarm threshold of the Mth acquisition period with the real-time alarm threshold of the M-1 acquisition period, wherein M is a positive integer not less than 1 and not more than N;

in this embodiment, after the rail engineering vehicle is put into operation, for example, the real-time alarm threshold generated in the first acquisition cycle is compared with the initial real-time alarm threshold.

303. When the real-time alarm threshold value of the Mth acquisition cycle is larger than the real-time alarm threshold value of the M-1 acquisition cycle, taking the real-time alarm threshold value of the Mth acquisition cycle as an alarm monitoring threshold value;

in this embodiment, taking step 302 as an example, if the real-time alarm threshold generated in the first acquisition cycle is greater than the initial real-time alarm threshold, the real-time alarm threshold generated in the first acquisition cycle is used as the alarm monitoring threshold.

304. When the real-time alarm threshold value of the Mth acquisition cycle is not greater than the real-time alarm threshold value of the M-1 acquisition cycle, taking the real-time alarm threshold value of the M-1 acquisition cycle as an alarm monitoring threshold value;

in this embodiment, taking step 302 as an example, if the real-time alarm threshold generated in the first acquisition cycle is smaller than or equal to the initial real-time alarm threshold, the initial real-time alarm threshold is used as the alarm monitoring threshold.

305. And carrying out alarm monitoring and identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value.

In this embodiment, the alarm monitoring threshold is used as a standard, and the monitoring data of the next sampling period is judged, so that the alarm monitoring of the running transmission part of the rail engineering vehicle is realized.

The monitoring method of the track-laying vehicle running transmission part is explained in detail in the above embodiment, and the following describes a monitoring system applying the track-laying vehicle running transmission part.

As shown in fig. 4, the present invention provides a monitoring system for a running transmission of a railway engineering vehicle, comprising:

an acquisition module 401 and a monitoring server 402;

the acquiring module 401 is configured to acquire initial vehicle vibration acceleration information of a running transmission part of the rail engineering vehicle before the rail engineering vehicle is put into operation;

the monitoring server 402 is used for analyzing and obtaining an initial state mark CI index according to the initial vehicle vibration acceleration information;

the monitoring server 402 is used for obtaining an alarm threshold value calculation formula according to the initial CI index;

the monitoring server 402 is used for acquiring real-time vehicle vibration acceleration information of a track engineering vehicle walking transmission part after the track engineering vehicle is put into use;

the monitoring server 402 is used for obtaining a real-time alarm threshold according to an alarm threshold calculation formula and real-time vehicle vibration acceleration information;

and the monitoring server 402 is used for obtaining an alarm monitoring threshold value according to the real-time alarm threshold value, and carrying out alarm monitoring identification on the track engineering vehicle walking transmission part according to the alarm monitoring threshold value.

In the embodiment of the invention, the monitoring system of the rail engineering vehicle running transmission part takes key components (such as an axle box bearing, a gear box, a transmission shaft, an air compressor and the like) of the rail engineering vehicle running transmission part as key monitoring objects, acquires signals through the acquisition module 401, for example, acquires real-time data by using an acceleration sensor, and realizes monitoring, early warning and fault diagnosis by using the monitoring server 402, so that the driving safety is further ensured, and the labor intensity of operators is reduced.

Alternatively, in some embodiments of the present invention,

the monitoring server 402 is further configured to perform feature statistics according to the initial vehicle vibration acceleration information to obtain statistical features, where the statistical features include a root mean square value, a peak value, a skewness, a kurtosis, a form factor, a pulse factor, a peak factor, a skewness, a kurtosis, a center of gravity frequency, and/or a root mean square frequency;

the monitoring server 402 is further configured to calculate statistical characteristics to obtain an initial CI indicator.

Alternatively, in some embodiments of the present invention,

the monitoring server 402 is further configured to perform normalization processing on the initial CI index to obtain a normalized initial CI index;

the monitoring server 402 is further configured to fuse the normalized initial CI index by a hypersphere support vector machine to obtain a health sign HI index;

the monitoring server 402 is further configured to calculate a probability distribution function of the health indicator HI index;

the monitoring server 402 is further configured to obtain an alarm threshold calculation formula according to the probability distribution function.

Alternatively, in some embodiments of the present invention,

the monitoring server 402 is further configured to set a fixed-time acquisition cycle within a preset time period of the design life of the rail engineering vehicle;

the monitoring server 402 is further configured to collect real-time vehicle vibration acceleration information of the track engineering vehicle traveling transmission part in each collection period.

Alternatively, in some embodiments of the present invention,

the number of the acquisition periods is N, N is a positive integer greater than 1,

the monitoring server 402 is further configured to calculate an initial alarm threshold according to an alarm threshold calculation formula and the initial CI index, where the initial alarm threshold is used as a real-time alarm threshold of the 0 th acquisition cycle;

the monitoring server 402 is further configured to compare the real-time alarm threshold of the mth acquisition cycle with the real-time alarm threshold of the M-1 acquisition cycle, where M is a positive integer not less than 1 and not greater than N;

the monitoring server 402 is further configured to use the real-time alarm threshold value of the mth acquisition cycle as an alarm monitoring threshold value when the real-time alarm threshold value of the mth acquisition cycle is greater than the real-time alarm threshold value of the M-1 acquisition cycle;

the monitoring server 402 is further configured to use the real-time alarm threshold value of the M-1 acquisition cycle as an alarm monitoring threshold value when the real-time alarm threshold value of the mth acquisition cycle is not greater than the real-time alarm threshold value of the M-1 acquisition cycle;

the monitoring server 402 is further configured to perform alarm monitoring and identification on the track engineering vehicle traveling transmission part according to the alarm monitoring threshold value.

The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.