Motor train unit key equipment running state monitoring method and system and storage medium thereof

Abstract

The invention discloses a motor train unit key equipment operation state monitoring method and system and a storage medium thereof. Comprising the following steps: collecting a plurality of operation parameter values of a multi-dimensional health state item corresponding to each piece of key equipment within a preset time range at a preset sampling frequency by utilizing a sensor and a vehicle-mounted camera which are arranged on the key equipment of the motor train unit; calculating and obtaining a health evaluation index value corresponding to each health state item by using the operation parameter value; calling a locally stored operation history evaluation index value; calculating the health evaluation index value, the equipment operation historical evaluation index value and the index weight to obtain an operation state comprehensive coefficient of the key equipment of the motor train unit; and according to the running state comprehensive coefficient and a preset operation and maintenance judgment reference threshold value, comprehensively judging whether to start the running state early warning scheme of the key equipment of the motor train unit. According to the monitoring method, the health state of the equipment can be evaluated more accurately.

Description

Technical Field

[0001] The present invention belongs to the technical field of EMU equipment, and in particular relates to a method and system for monitoring the operating status of key equipment of an EMU and a storage medium thereof. Background Art

[0002] With the rapid development of high-speed railways, the operating status monitoring of key equipment of EMUs has become increasingly important. Traditional monitoring methods often rely on regular manual inspections and maintenance, which is not only inefficient but also difficult to detect potential problems of equipment in real time. With the advancement of sensor technology and data processing technology, it has become possible to achieve real-time monitoring and intelligent analysis of the operating status of key equipment of EMUs. Although the existing monitoring system can collect a large number of operating parameters, it still has deficiencies in data processing and analysis, especially in the comprehensive evaluation and early warning of multi-dimensional health status items. Summary of the invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and to provide a method, system and storage medium for monitoring the operating status of key equipment of a multiple unit, which can more accurately evaluate the health status of the equipment, not only improving the accuracy and real-time performance of monitoring, but also by dynamically adjusting weights, enabling the evaluation model to adapt to changes in different equipment and operating conditions, thereby achieving more effective fault warning and maintenance.

[0004] To achieve the above object, the present invention is implemented by adopting the following technical solutions:

[0005] In a first aspect, the present invention provides a method for monitoring the operating status of key equipment of a train set, comprising the following steps:

[0006] The central processor uses sensors installed on key equipment of the EMU and onboard cameras to collect several operating parameter values ​​of multi-dimensional health status items corresponding to each key equipment within a predetermined time range at a predetermined sampling frequency; and uses the operating parameter values ​​to calculate and obtain the health evaluation index value corresponding to each health status item;

[0007] The central processor retrieves the locally stored operation history evaluation index values ​​of the multi-dimensional health status items corresponding to each key device for obtaining the device operation parameters;

[0008] The central processor calculates the health evaluation index value, equipment operation history evaluation index value and index weight to obtain the comprehensive operating status coefficient of the EMU key equipment; based on the comprehensive operating status coefficient and the preset operation and maintenance judgment benchmark threshold, it comprehensively judges whether to start the EMU key equipment operating status early warning plan.

[0009] Furthermore, a multi-dimensional health status item matrix corresponding to each key device is constructed, and a dynamic weight adaptive health status assessment model is constructed using logistic regression, topis multi-objective or variance-covariance-weight method.

[0010] Furthermore, constructing a dynamic weight adaptive health status assessment model includes the following steps:

[0011] Calculate the variance of each operating parameter feature in the multi-dimensional health status item matrix corresponding to each key device to measure the degree of fluctuation of a single operating parameter feature, and calculate the covariance between the status item matrices of the multi-dimensional health status items to construct a covariance matrix;

[0012] The entropy weight method is used to determine the weights of the equipment type of key equipment, the state item matrix of multi-dimensional health status items, and the operating parameter matrix according to the variance and covariance of different features in the equipment type matrix of each key equipment and the state item matrix of multi-dimensional health status items;

[0013] Use logistic regression algorithm or TOPIS multi-objective optimization algorithm to train and optimize the parameters of computer learning model, and update the covariance matrix and dynamically readjust the weights according to the real-time running parameter value data;

[0014] According to the health evaluation index value of each equipment component, the equipment operation history evaluation index value and the corresponding matrix weight, the comprehensive operating status coefficient of the key equipment of the EMU is calculated.

[0015] Furthermore, the multi-dimensional health status item matrix corresponding to each key device is:

[0016] The equipment type matrix of key equipment is [traction motor, braking system, control system, auxiliary power system];

[0017] The status item matrix of multi-dimensional health status items is [operating conditions, time series, environmental conditions, maintenance records];

[0018] Operating parameter matrix of operating conditions [standard, high speed, heavy load, light load];

[0019] The operating parameter matrix of the time series [within the week, before the week, within the month, before the month];

[0020] Operating parameter matrix of environmental conditions [normal, hot, humid, vibration];

[0021] Operation parameter matrix of maintenance records [no maintenance, minor maintenance, medium maintenance, major maintenance].

[0022] Furthermore, when the comprehensive coefficient of the operating status of each key equipment of the EMU is calculated, the operating status of each key equipment is comprehensively judged according to the preset operation and maintenance judgment benchmark threshold:

[0023] When 0<comprehensive coefficient of operation status<preset operation and maintenance judgment benchmark threshold - T, the operation status of key equipment is judged to be good;

[0024] When the preset operation and maintenance judgment benchmark threshold - T < the comprehensive coefficient of operation status < the preset operation and maintenance judgment benchmark threshold + T, the operation status of the key equipment is judged to be normal;

[0025] When the preset operation and maintenance judgment benchmark threshold + T < operation status comprehensive coefficient < 1, the operation status fault warning of the key equipment is determined;

[0026] After obtaining the operating status determination results of all traction motors, brake systems, control systems, and auxiliary power systems, analyze and determine again:

[0027] If there is a fault warning of the operating status of at least one key device in the traction motor, brake system, control system, and auxiliary power supply system, the first warning plan for the operating status of the key equipment of the EMU is activated;

[0028] If the operation status of three or more key equipment in the traction motor, brake system, control system, and auxiliary power system is normal and there is no operation status fault warning, the second tracking monitoring plan for the operation status of the EMU key equipment is activated;

[0029] If the operation status of two or less key equipment in the traction motor, brake system, control system, and auxiliary power system is normal, the third maintenance plan for the operation status of the key equipment of the EMU is initiated;

[0030] If the operating status of four key devices, namely the traction motor, braking system, control system and auxiliary power system, are all good at the same time, there is no need to start the EMU key equipment operating status plan.

[0031] In a second aspect, the present invention provides a system for monitoring the operating status of key equipment of a train set, comprising the following modules:

[0032] A data acquisition module is used to collect a number of operating parameter values ​​of multi-dimensional health status items corresponding to each key device within a predetermined time range using sensors and onboard cameras installed on key devices of the EMU at a predetermined sampling frequency, and transmit the data parameter values ​​to a central processor;

[0033] A data storage module is used to locally store the operation history evaluation index values ​​of the multi-dimensional health status items corresponding to each key device for obtaining the device operation parameters, and to store several operation parameter values ​​of the multi-dimensional health status items corresponding to each key device within each time range collected in real time by the data acquisition module;

[0034] The central processor is used to calculate the health evaluation index value corresponding to each health status item using the received operation parameter value, and retrieve the operation history evaluation index value of the multi-dimensional health status item corresponding to each key device stored in the data storage module;

[0035] At the same time, the health evaluation index value, equipment operation history evaluation index value and index weight are calculated to obtain the comprehensive operating status coefficient of the EMU key equipment, and a comprehensive judgment is made on whether to start the EMU key equipment operating status warning plan based on the comprehensive operating status coefficient and the preset operation and maintenance judgment benchmark threshold.

[0036] Furthermore, a multi-dimensional health status item matrix corresponding to each key device is constructed, and a dynamic weight adaptive health status assessment model is constructed using logistic regression, topis multi-objective or variance-covariance-weight method;

[0037] The construction of a dynamic weight adaptive health status assessment model includes the following steps:

[0038] Calculate the variance of each operating parameter feature in the multi-dimensional health status item matrix corresponding to each key device to measure the degree of fluctuation of a single operating parameter feature, and calculate the covariance between the status item matrices of the multi-dimensional health status items to construct a covariance matrix;

[0039] The entropy weight method is used to determine the weights of the equipment type of key equipment, the state item matrix of multi-dimensional health status items, and the operating parameter matrix according to the variance and covariance of different features in the equipment type matrix of each key equipment and the state item matrix of multi-dimensional health status items;

[0040] Use logistic regression algorithm or TOPIS multi-objective optimization algorithm to train and optimize the parameters of computer learning model, and update the covariance matrix and dynamically readjust the weights according to the real-time running parameter value data;

[0041] According to the health evaluation index value of each equipment component, the equipment operation history evaluation index value and the corresponding matrix weight, the comprehensive coefficient of the operation status of the key equipment of the EMU is calculated;

[0042] The multi-dimensional health status item matrix corresponding to each key device is:

[0043] The equipment type matrix of key equipment is [traction motor, braking system, control system, auxiliary power system];

[0044] The status item matrix of multi-dimensional health status items is [operating conditions, time series, environmental conditions, maintenance records];

[0045] Operating parameter matrix of operating conditions [standard, high speed, heavy load, light load];

[0046] The operating parameter matrix of the time series [within the week, before the week, within the month, before the month];

[0047] Operating parameter matrix of environmental conditions [normal, hot, humid, vibration];

[0048] Operation parameter matrix of maintenance records [no maintenance, minor maintenance, medium maintenance, major maintenance].

[0049] Further, when the comprehensive coefficient of the operating status of each key device of the EMU is calculated, the central processor comprehensively judges the operating status of each key device according to the preset operation and maintenance judgment benchmark threshold:

[0050] When 0<comprehensive coefficient of operation status<preset operation and maintenance judgment benchmark threshold - T, the operation status of key equipment is judged to be good;

[0051] When the preset operation and maintenance judgment benchmark threshold - T < the comprehensive coefficient of operation status < the preset operation and maintenance judgment benchmark threshold + T, the operation status of the key equipment is judged to be normal;

[0052] When the preset operation and maintenance judgment benchmark threshold + T < operation status comprehensive coefficient < 1, the operation status fault warning of the key equipment is determined;

[0053] After obtaining the operating status determination results of all traction motors, brake systems, control systems, and auxiliary power systems, analyze and determine again:

[0054] If there is a fault warning of the operating status of at least one key device in the traction motor, brake system, control system, and auxiliary power supply system, the first warning plan for the operating status of the key equipment of the EMU is activated;

[0055] If the operation status of three or more key equipment in the traction motor, brake system, control system, and auxiliary power system is normal and there is no operation status fault warning, the second tracking monitoring plan for the operation status of the EMU key equipment is activated;

[0056] If the operation status of two or less key equipment in the traction motor, brake system, control system, and auxiliary power system is normal, the third maintenance plan for the operation status of the key equipment of the EMU is initiated;

[0057] If the operating status of four key devices, namely the traction motor, braking system, control system and auxiliary power system, are all good at the same time, there is no need to start the EMU key equipment operating status plan.

[0058] In a third aspect, the present invention provides an electronic device, comprising:

[0059] processor;

[0060] a memory for storing instructions executable by the processor;

[0061] Wherein, the processor is configured to execute the instructions to implement the method for monitoring the operating status of key equipment of a multiple unit as described in any one of the first aspects.

[0062] In a fourth aspect, the present invention provides a computer-readable storage medium, which, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the method for monitoring the operating status of key equipment of a multiple unit as described in any one of the first aspects.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] The method for monitoring the operating status of key equipment of a multiple unit provided by the present invention constructs influencing factors of the operating status corresponding to the traction motor, braking system, control system and auxiliary power supply system, such as operating conditions, time series, environmental conditions and maintenance records, which have a direct or indirect impact on the health status of the equipment. By constructing a multi-dimensional health status item matrix and adopting logistic regression, topis multi-objective or variance-covariance-weight method to construct a dynamic weight adaptive health status assessment model, the health status of the equipment can be assessed more accurately, which not only improves the accuracy and real-time performance of monitoring, but also enables the assessment model to adapt to changes in different equipment and operating conditions by dynamically adjusting the weights, thereby achieving more effective fault warning and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 The present invention is a flowchart of a method for monitoring the operating status of key equipment of a train set provided according to an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0067] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and the like are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, features defined as "first", "second", and the like may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0068] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0069] Example

[0070] like Figure 1 As shown, an embodiment of the present invention provides a method for monitoring the operating status of key equipment of a train set, comprising the following steps:

[0071] The central processor uses sensors installed on key equipment of the EMU and onboard cameras to collect several operating parameter values ​​of multi-dimensional health status items corresponding to each key equipment within a predetermined time range at a predetermined sampling frequency; and uses the operating parameter values ​​to calculate and obtain the health evaluation index value corresponding to each health status item;

[0072] The central processor retrieves the locally stored operation history evaluation index values ​​of the multi-dimensional health status items corresponding to each key device for obtaining the device operation parameters;

[0073] The central processor calculates the health evaluation index value, equipment operation history evaluation index value and index weight to obtain the comprehensive operating status coefficient of the EMU key equipment; based on the comprehensive operating status coefficient and the preset operation and maintenance judgment benchmark threshold, it comprehensively judges whether to start the EMU key equipment operating status early warning plan.

[0074] In this embodiment, a multi-dimensional health status item matrix corresponding to each key device is constructed, and a dynamic weight adaptive health status assessment model is constructed using logistic regression, topis multi-objective or variance-covariance-weight method.

[0075] In this embodiment, constructing a dynamic weight adaptive health status assessment model includes the following steps:

[0076] Calculate the variance of each operating parameter feature in the multi-dimensional health status item matrix corresponding to each key device to measure the degree of fluctuation of a single operating parameter feature, and calculate the covariance between the status item matrices of the multi-dimensional health status items to construct a covariance matrix;

[0077] The entropy weight method is used to determine the weights of the equipment type of key equipment, the state item matrix of multi-dimensional health status items, and the operating parameter matrix according to the variance and covariance of different features in the equipment type matrix of each key equipment and the state item matrix of multi-dimensional health status items;

[0078] Use logistic regression algorithm or TOPIS multi-objective optimization algorithm to train and optimize the parameters of computer learning model, and update the covariance matrix and dynamically readjust the weights according to the real-time running parameter value data;

[0079] According to the health evaluation index value of each equipment component, the equipment operation history evaluation index value and the corresponding matrix weight, the comprehensive operating status coefficient of the key equipment of the EMU is calculated.

[0080] In this embodiment, the multi-dimensional health status item matrix corresponding to each key device is:

[0081] The equipment type matrix of key equipment is [traction motor, braking system, control system, auxiliary power system];

[0082] The status item matrix of multi-dimensional health status items is [operating conditions, time series, environmental conditions, maintenance records];

[0083] Operating parameter matrix of operating conditions [standard, high speed, heavy load, light load];

[0084] The operating parameter matrix of the time series [within the week, before the week, within the month, before the month];

[0085] Operating parameter matrix of environmental conditions [normal, hot, humid, vibration];

[0086] Operation parameter matrix of maintenance records [no maintenance, minor maintenance, medium maintenance, major maintenance].

[0087] In this embodiment, when the comprehensive coefficient of the operating status of each key device of the EMU is calculated, the operating status of each key device is comprehensively judged according to the preset operation and maintenance judgment benchmark threshold:

[0088] When 0<comprehensive coefficient of operation status<preset operation and maintenance judgment benchmark threshold - T, the operation status of key equipment is judged to be good;

[0089] When the preset operation and maintenance judgment benchmark threshold - T < the comprehensive coefficient of operation status < the preset operation and maintenance judgment benchmark threshold + T, the operation status of the key equipment is judged to be normal;

[0090] When the preset operation and maintenance judgment benchmark threshold + T < operation status comprehensive coefficient < 1, the operation status fault warning of the key equipment is determined;

[0091] After obtaining the operating status determination results of all traction motors, brake systems, control systems, and auxiliary power systems, analyze and determine again:

[0092] If there is a fault warning of the operating status of at least one key device in the traction motor, brake system, control system, and auxiliary power supply system, the first warning plan for the operating status of the key equipment of the EMU is activated;

[0093] If the operation status of three or more key equipment in the traction motor, brake system, control system, and auxiliary power system is normal and there is no operation status fault warning, the second tracking monitoring plan for the operation status of the EMU key equipment is activated;

[0094] If the operation status of two or less key equipment in the traction motor, brake system, control system, and auxiliary power system is normal, the third maintenance plan for the operation status of the key equipment of the EMU is initiated;

[0095] If the operating status of four key devices, namely the traction motor, braking system, control system and auxiliary power system, are all good at the same time, there is no need to start the EMU key equipment operating status plan.

[0096] In a second aspect, the present invention provides a system for monitoring the operating status of key equipment of a train set, comprising the following modules:

[0097] A data acquisition module is used to collect a number of operating parameter values ​​of multi-dimensional health status items corresponding to each key device within a predetermined time range using sensors and onboard cameras installed on key devices of the EMU at a predetermined sampling frequency, and transmit the data parameter values ​​to a central processor;

[0098] A data storage module is used to locally store the operation history evaluation index values ​​of the multi-dimensional health status items corresponding to each key device for obtaining the device operation parameters, and to store several operation parameter values ​​of the multi-dimensional health status items corresponding to each key device within each time range collected in real time by the data acquisition module;

[0099] The central processor is used to calculate the health evaluation index value corresponding to each health status item using the received operation parameter value, and retrieve the operation history evaluation index value of the multi-dimensional health status item corresponding to each key device stored in the data storage module;

[0100] At the same time, the health evaluation index value, equipment operation history evaluation index value and index weight are calculated to obtain the comprehensive operating status coefficient of the EMU key equipment, and a comprehensive judgment is made on whether to start the EMU key equipment operating status warning plan based on the comprehensive operating status coefficient and the preset operation and maintenance judgment benchmark threshold.

[0101] In this embodiment, a multi-dimensional health status item matrix corresponding to each key device is constructed, and a dynamic weight adaptive health status assessment model is constructed using logistic regression, topis multi-objective or variance-covariance-weight method;

[0102] The construction of a dynamic weight adaptive health status assessment model includes the following steps:

[0103] Calculate the variance of each operating parameter feature in the multi-dimensional health status item matrix corresponding to each key device to measure the degree of fluctuation of a single operating parameter feature, and calculate the covariance between the status item matrices of the multi-dimensional health status items to construct a covariance matrix;

[0104] The entropy weight method is used to determine the weights of the equipment type of key equipment, the state item matrix of multi-dimensional health status items, and the operating parameter matrix according to the variance and covariance of different features in the equipment type matrix of each key equipment and the state item matrix of multi-dimensional health status items;

[0105] Use logistic regression algorithm or TOPIS multi-objective optimization algorithm to train and optimize the parameters of computer learning model, and update the covariance matrix and dynamically readjust the weights according to the real-time running parameter value data;

[0106] According to the health evaluation index value of each equipment component, the equipment operation history evaluation index value and the corresponding matrix weight, the comprehensive coefficient of the operation status of the key equipment of the EMU is calculated;

[0107] The multi-dimensional health status item matrix corresponding to each key device is:

[0108] The equipment type matrix of key equipment is [traction motor, braking system, control system, auxiliary power system];

[0109] The status item matrix of multi-dimensional health status items is [operating conditions, time series, environmental conditions, maintenance records];

[0110] Operating parameter matrix of operating conditions [standard, high speed, heavy load, light load];

[0111] The operating parameter matrix of the time series [within the week, before the week, within the month, before the month];

[0112] Operating parameter matrix of environmental conditions [normal, hot, humid, vibration];

[0113] Operation parameter matrix of maintenance records [no maintenance, minor maintenance, medium maintenance, major maintenance].

[0114] In this embodiment, when the comprehensive coefficient of the operating status of each key device of the EMU is calculated, the central processor comprehensively judges the operating status of each key device according to the preset operation and maintenance judgment benchmark threshold:

[0115] When 0<comprehensive coefficient of operation status<preset operation and maintenance judgment benchmark threshold - T, the operation status of key equipment is judged to be good;

[0116] When the preset operation and maintenance judgment benchmark threshold - T < the comprehensive coefficient of operation status < the preset operation and maintenance judgment benchmark threshold + T, the operation status of the key equipment is judged to be normal;

[0117] When the preset operation and maintenance judgment benchmark threshold + T < operation status comprehensive coefficient < 1, the operation status fault warning of the key equipment is determined;

[0118] After obtaining the operating status determination results of all traction motors, brake systems, control systems, and auxiliary power systems, analyze and determine again:

[0119] If there is a fault warning of the operating status of at least one key device in the traction motor, brake system, control system, and auxiliary power supply system, the first warning plan for the operating status of the key equipment of the EMU is activated;

[0120] If the operation status of three or more key equipment in the traction motor, brake system, control system, and auxiliary power system is normal and there is no operation status fault warning, the second tracking monitoring plan for the operation status of the EMU key equipment is activated;

[0121] If the operation status of two or less key equipment in the traction motor, brake system, control system, and auxiliary power system is normal, the third maintenance plan for the operation status of the key equipment of the EMU is initiated;

[0122] If the operating status of four key devices, namely the traction motor, braking system, control system and auxiliary power system, are all good at the same time, there is no need to start the EMU key equipment operating status plan.

[0123] In a third aspect, the present invention provides an electronic device, comprising:

[0124] processor;

[0125] a memory for storing instructions executable by the processor;

[0126] Wherein, the processor is configured to execute the instructions to implement the method for monitoring the operating status of key equipment of a multiple unit as described in any one of the first aspects.

[0127] In a fourth aspect, the present invention provides a computer-readable storage medium, which, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the method for monitoring the operating status of key equipment of a multiple unit as described in any one of the first aspects.

[0128] Next, the working principle of the method for monitoring the operating status of key equipment of a train set of the present invention is described in combination with the operation of a specific embodiment.

[0129] First, assume that the operating conditions of the traction motor are such that a score matrix as shown in Table 1 is constructed, wherein each score is obtained by collecting data at a predetermined sampling frequency using sensors installed on key equipment of the EMU and on-board cameras and undergoing data preprocessing and normalization. Conventional data processing modes are used, which will not be elaborated here.

[0130] Table 1

[0131] Operating conditions standard high speed Overload Light load Traction motor 0.7 0.9 0.6 0.8

[0132] The sum of all scores of the operating conditions corresponding to the traction motor in the calculation table is calculated, and each score is normalized and weighted averaged, and the weights are assigned, as shown in Table 2.

[0133] Table 2

[0134] Operating conditions standard high speed Overload Light load Weight 0.25 0.35 0.1 0.3

[0135] Then, the weighted average score is calculated as follows:

[0136] Score (牵引电机-运行条件)

[0137] =(0.7×0.25)+(0.9×0.35)+(0.6×0.1)+(0.8×0.3)=0.175+0.315+0.06+0.24=0.8

[0138] It can be seen that the health evaluation index value of the health status item "operating condition" corresponding to the key equipment "traction motor" is 0.8. Similarly, the health evaluation index value corresponding to each health status item of all key equipment can be obtained, as shown in Table 3 below.

[0139] Key Equipment Operating conditions Time Series Environmental conditions Maintenance records Traction motor 0.8 0.9 0.7 0.6 Braking system 0.7 0.8 0.6 0.5 Control System 0.9 0.7 0.8 0.7 Auxiliary power supply 0.6 0.5 0.4 0.3

[0140] Assuming that the average value of each dimension is 0.75, it can be adjusted and determined according to the actual situation during the actual locomotive monitoring process. This is just an example.

[0141] The variance calculation formula is: For the operating conditions, time series, environmental conditions, maintenance records, etc. of the traction motor, calculate the health evaluation index value of the traction motor:

[0142] V (牵引电机) =41[(0.8-0.75)2+(0.7-0.75)2+(0.9-0.75)2+(0.6-0.75)2]=41×0.0375=0.00937.

[0143] Similarly, the health evaluation index value of each key equipment can be calculated.

[0144] The covariance calculation formula is: Calculate the covariance between the operating conditions and the time series of the traction motor:

[0145] C (牵引电机) =31[(0.8-0.75)(0.9-0.75)+(0.7-0.75)(0.8-0.75)+(0.9-0.75)(0.7-0.75)

[0146] +(0.6-0.75)(0.5-0.75)]=0.025.

[0147] In this embodiment, for the operating conditions of the traction motor, the probability is assumed to be 0.25. For the convenience of calculation, it is still assumed that the probability of each parameter index item is equal.

[0148] The entropy value calculation formula is: Calculate H (牵引电机) =-4×0.25log(0.25)=2.

[0149] Assuming that all devices have the same entropy value, the weight calculation formula is: Calculate the weight of each key device as:

[0150] Then, based on the weight and the score of each key equipment component, the comprehensive coefficient of the operating status of the key equipment is calculated. For example, the comprehensive coefficient of the operating status of the traction motor is:

[0151] T_S (牵引电机) =0.25×(0.8+0.9+0.7+0.6)=0.775.

[0152] In this embodiment, the preset operation and maintenance judgment benchmark thresholds of the traction motor are [0, 0.5], [0.5, 0.8], and [0.8, 1]. The operating status of the traction motor is comprehensively judged according to the preset operation and maintenance judgment benchmark thresholds. Because the comprehensive operating status coefficient of the traction motor 0.775 is between [0.5, 0.8], the operating status of the traction motor is judged to be general.

[0153] Similarly, the operating status of the braking system, control system, and auxiliary power system are determined in turn.

[0154] In this embodiment, after calculation, it is monitored within a preset time period that the operating status of the traction motor is general, the operating status of the braking system is general, the operating status of the control system is general, and the operating status of the auxiliary power supply system has a fault warning.

[0155] Then, if there is a fault warning for the operating status of at least one key device in the traction motor, braking system, control system, and auxiliary power supply system, the first warning plan for the operating status of the key equipment of the EMU is activated.

[0156] In this embodiment, the first early warning scheme for the operation status of the key equipment of the EMU can be to shut down the auxiliary power supply system for maintenance and replacement. At the same time, the operation status of each key equipment, the first early warning scheme for the operation status of the key equipment of the EMU, etc. are stored in the local storage module and used as the operation history evaluation index value of the multi-dimensional health status item corresponding to each key equipment.

[0157] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for monitoring the operating status of key equipment of a train set, characterized in that: The steps include: The central processor uses sensors installed on key equipment of the EMU and onboard cameras to collect several operating parameter values ​​of multi-dimensional health status items corresponding to each key equipment within a predetermined time range at a predetermined sampling frequency; The central processor uses the operating parameter value to calculate and obtain the health evaluation index value corresponding to each health status item; The central processor retrieves the locally stored operation history evaluation index values ​​of the multi-dimensional health status items corresponding to each key device for obtaining the device operation parameters; The central processor calculates the health evaluation index value, the equipment operation history evaluation index value and the index weight to obtain the comprehensive coefficient of the operation status of the key equipment of the EMU; The central processor comprehensively determines whether to activate the EMU key equipment operating status warning plan based on the comprehensive operating status coefficient and the preset operation and maintenance judgment benchmark threshold.

2. The method for monitoring the operating status of key equipment of a train set according to claim 1, characterized in that: Construct a multi-dimensional health status item matrix corresponding to each key device, and use logistic regression, topis multi-objective or variance-covariance-weight method to build a dynamic weight adaptive health status assessment model.

3. The method for monitoring the operating status of key equipment of a train set according to claim 2, characterized in that: The construction of a dynamic weight adaptive health status assessment model includes the following steps: Calculate the variance of each operating parameter feature in the multi-dimensional health status item matrix corresponding to each key device to measure the degree of fluctuation of a single operating parameter feature, and calculate the covariance between the status item matrices of the multi-dimensional health status items to construct a covariance matrix; The entropy weight method is used to determine the weights of the equipment type of key equipment, the state item matrix of multi-dimensional health status items, and the operating parameter matrix according to the variance and covariance of different features in the equipment type matrix of each key equipment and the state item matrix of multi-dimensional health status items; Use logistic regression algorithm or TOPIS multi-objective optimization algorithm to train and optimize the parameters of computer learning model, and update the covariance matrix and dynamically readjust the weights according to the real-time running parameter value data; According to the health evaluation index value of each equipment component, the equipment operation history evaluation index value and the corresponding matrix weight, the comprehensive operating status coefficient of the key equipment of the EMU is calculated.

4. The method for monitoring the operating status of key equipment of a train set according to claim 3 is characterized in that: The multi-dimensional health status item matrix corresponding to each key device is: The equipment type matrix of key equipment is [traction motor, braking system, control system, auxiliary power system]; The status item matrix of multi-dimensional health status items is [operating conditions, time series, environmental conditions, maintenance records]; Operating parameter matrix of operating conditions [standard, high speed, heavy load, light load]; The operating parameter matrix of the time series [within the week, before the week, within the month, before the month]; Operating parameter matrix of environmental conditions [normal, hot, humid, vibration]; Operation parameter matrix of maintenance records [no maintenance, minor maintenance, medium maintenance, major maintenance].

5. The method for monitoring the operating status of key equipment of a train set according to claim 3 is characterized in that: After the comprehensive coefficient of the operating status of each key equipment of the EMU is calculated, the operating status of each key equipment is comprehensively judged according to the preset operation and maintenance judgment benchmark threshold: When 0<comprehensive coefficient of operation status<preset operation and maintenance judgment benchmark threshold - T, the operation status of key equipment is judged to be good; When the preset operation and maintenance judgment benchmark threshold - T < the comprehensive coefficient of operation status < the preset operation and maintenance judgment benchmark threshold + T, the operation status of the key equipment is judged to be normal; When the preset operation and maintenance judgment benchmark threshold + T < operation status comprehensive coefficient < 1, the operation status fault warning of the key equipment is determined; After obtaining the operating status determination results of all traction motors, brake systems, control systems, and auxiliary power systems, analyze and determine again: If there is a fault warning of the operating status of at least one key device in the traction motor, brake system, control system, and auxiliary power supply system, the first warning plan for the operating status of the key equipment of the EMU is activated; If the operation status of three or more key equipment in the traction motor, brake system, control system, and auxiliary power system is normal and there is no operation status fault warning, the second tracking monitoring plan for the operation status of the EMU key equipment is activated; If the operation status of two or less key equipment in the traction motor, brake system, control system, and auxiliary power system is normal, the third maintenance plan for the operation status of the key equipment of the EMU is initiated; If the operating status of four key devices, namely the traction motor, braking system, control system and auxiliary power system, are all good at the same time, there is no need to start the EMU key equipment operating status plan.

6. A system for monitoring the operating status of key equipment of a train set, characterized in that: Includes the following modules: A data acquisition module is used to collect a number of operating parameter values ​​of multi-dimensional health status items corresponding to each key device within a predetermined time range using sensors and onboard cameras installed on key devices of the EMU at a predetermined sampling frequency, and transmit the data parameter values ​​to a central processor; A data storage module is used to locally store the operation history evaluation index values ​​of the multi-dimensional health status items corresponding to each key device for obtaining the device operation parameters, and to store several operation parameter values ​​of the multi-dimensional health status items corresponding to each key device within each time range collected in real time by the data acquisition module; The central processor is used to calculate the health evaluation index value corresponding to each health status item using the received operation parameter value, and retrieve the operation history evaluation index value of the multi-dimensional health status item corresponding to each key device stored in the data storage module; At the same time, the health evaluation index value, equipment operation history evaluation index value and index weight are calculated to obtain the comprehensive operating status coefficient of the EMU key equipment, and a comprehensive judgment is made on whether to start the EMU key equipment operating status warning plan based on the comprehensive operating status coefficient and the preset operation and maintenance judgment benchmark threshold.

7. The EMU key equipment operation status monitoring system according to claim 6 is characterized in that: Construct a multi-dimensional health status item matrix corresponding to each key device, and use logistic regression, topis multi-objective or variance-covariance-weight method to construct a dynamic weight adaptive health status assessment model; The construction of a dynamic weight adaptive health status assessment model includes the following steps: Calculate the variance of each operating parameter feature in the multi-dimensional health status item matrix corresponding to each key device to measure the degree of fluctuation of a single operating parameter feature, and calculate the covariance between the status item matrices of the multi-dimensional health status items to construct a covariance matrix; The entropy weight method is used to determine the weights of the equipment type of key equipment, the state item matrix of multi-dimensional health status items, and the operating parameter matrix according to the variance and covariance of different features in the equipment type matrix of each key equipment and the state item matrix of multi-dimensional health status items; Use logistic regression algorithm or TOPIS multi-objective optimization algorithm to train and optimize the parameters of computer learning model, and update the covariance matrix and dynamically readjust the weights according to the real-time running parameter value data; According to the health evaluation index value of each equipment component, the equipment operation history evaluation index value and the corresponding matrix weight, the comprehensive coefficient of the operation status of the key equipment of the EMU is calculated; The multi-dimensional health status item matrix corresponding to each key device is: The equipment type matrix of key equipment is [traction motor, braking system, control system, auxiliary power system]; The status item matrix of multi-dimensional health status items is [operating conditions, time series, environmental conditions, maintenance records]; Operating parameter matrix of operating conditions [standard, high speed, heavy load, light load]; The operating parameter matrix of the time series [within the week, before the week, within the month, before the month]; Operating parameter matrix of environmental conditions [normal, hot, humid, vibration]; Operation parameter matrix of maintenance records [no maintenance, minor maintenance, medium maintenance, major maintenance].

8. The EMU key equipment operation status monitoring system according to claim 7 is characterized in that: When the comprehensive coefficient of the operating status of each key device of the EMU is calculated, the central processor comprehensively judges the operating status of each key device according to the preset operation and maintenance judgment benchmark threshold: When 0<comprehensive coefficient of operation status<preset operation and maintenance judgment benchmark threshold - T, the operation status of key equipment is judged to be good; When the preset operation and maintenance judgment benchmark threshold - T < the comprehensive coefficient of operation status < the preset operation and maintenance judgment benchmark threshold + T, the operation status of the key equipment is judged to be normal; When the preset operation and maintenance judgment benchmark threshold + T < operation status comprehensive coefficient < 1, the operation status fault warning of the key equipment is determined; After obtaining the operating status determination results of all traction motors, brake systems, control systems, and auxiliary power systems, analyze and determine again: If there is a fault warning of the operating status of at least one key device in the traction motor, brake system, control system, and auxiliary power supply system, the first warning plan for the operating status of the key equipment of the EMU is activated; If the operation status of three or more key equipment in the traction motor, brake system, control system, and auxiliary power system is normal and there is no operation status fault warning, the second tracking monitoring plan for the operation status of the EMU key equipment is activated; If the operation status of two or less key equipment in the traction motor, brake system, control system, and auxiliary power system is normal, the third maintenance plan for the operation status of the key equipment of the EMU is initiated; If the operating status of four key devices, namely the traction motor, braking system, control system and auxiliary power system, are all good at the same time, there is no need to start the EMU key equipment operating status plan.

9. An electronic device, comprising: processor; a memory for storing instructions executable by the processor; Wherein, the processor is configured to execute the instructions to implement the method for monitoring the operating status of key equipment of a multiple unit as described in any one of claims 1 to 5.

10. A computer-readable storage medium, when the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method for monitoring the operating status of key equipment of a multiple unit as described in any one of claims 1 to 5.

Images