CN118565870B - Rail transit standard motor train unit high-voltage equipment monitoring method and device - Google Patents
Rail transit standard motor train unit high-voltage equipment monitoring method and device Download PDFInfo
- Publication number
- CN118565870B CN118565870B CN202411050242.1A CN202411050242A CN118565870B CN 118565870 B CN118565870 B CN 118565870B CN 202411050242 A CN202411050242 A CN 202411050242A CN 118565870 B CN118565870 B CN 118565870B
- Authority
- CN
- China
- Prior art keywords
- motor train
- information
- train unit
- monitoring
- standard motor
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 131
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000005534 acoustic noise Effects 0.000 claims abstract description 119
- 230000002159 abnormal effect Effects 0.000 claims abstract description 64
- 230000007613 environmental effect Effects 0.000 claims description 40
- 239000000463 material Substances 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 7
- 238000012806 monitoring device Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000012423 maintenance Methods 0.000 claims description 4
- 239000000725 suspension Substances 0.000 claims description 4
- 238000005259 measurement Methods 0.000 abstract description 2
- 238000001514 detection method Methods 0.000 description 3
- 230000003595 spectral effect Effects 0.000 description 3
- 238000011179 visual inspection Methods 0.000 description 3
- 238000004088 simulation Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/08—Railway vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
Abstract
The application discloses a method and a device for monitoring high-voltage equipment of a rail transit standard motor train unit, and relates to the technical field of acoustic wave measurement; the method comprises the following steps: acquiring acoustic monitoring data from at least one preset monitoring point to obtain first information; the monitoring points are used for monitoring acoustic data of high-voltage equipment in the standard motor train, and each high-voltage equipment is provided with at least one monitoring point; the first information characterizes the acoustic noise condition actually acquired by each high-voltage device in the running process; predicting acoustic noise of the standard motor train unit based on the running environment information of the standard motor train unit and the parameter information of the standard motor train unit to obtain second information; the second information represents ideal acoustic noise conditions of the standard motor train unit in the corresponding operation environment; and judging whether each high-voltage device is abnormal or not based on the difference between the first information and the second information. The scheme provided by the application can improve the comprehensiveness and reliability of the monitoring result of the high-voltage equipment.
Description
Technical Field
The application relates to the technical field of acoustic wave measurement, in particular to a method and a device for monitoring high-voltage equipment of a rail transit standard motor train unit.
Background
In actual running of the motor train unit, high-voltage equipment is easily influenced by external environments, such as high-voltage equipment of a pantograph, a transformer, a circuit breaker, a disconnecting switch and the like; therefore, real-time and accurate state monitoring is required to be carried out on the high-voltage equipment, and safe and stable operation of the high-voltage equipment of the motor train unit is ensured. In the related art, visual inspection can be adopted to inspect the appearance of the high-voltage equipment, and electric power parameters such as geometrical parameters of the overhead contact system, current-carrying parameters of the bow net, net pressure of the overhead contact system and the like can also be acquired in real time, and then the performances of each equipment are analyzed according to the acquired electric power parameters.
However, the high-voltage device monitoring means in the related art may not find potential problems in time, and the comprehensiveness and reliability of the monitoring result are not high.
Disclosure of Invention
In order to solve the related technical problems, the embodiment of the application provides a method and a device for monitoring high-voltage equipment of a rail transit standard motor train unit, which can improve the comprehensiveness and reliability of the monitoring result of the high-voltage equipment.
The embodiment of the application provides a rail transit standard motor train unit high-voltage equipment monitoring method, which comprises the following steps:
Acquiring acoustic monitoring data from at least one preset monitoring point to obtain first information; the monitoring points are used for monitoring acoustic data of high-voltage equipment in the standard motor train, and each high-voltage equipment is provided with at least one monitoring point; the first information characterizes the acoustic noise condition actually acquired by each high-voltage device in the running process;
predicting acoustic noise of the standard motor train unit based on the running environment information of the standard motor train unit and the parameter information of the standard motor train unit to obtain second information; the second information represents ideal acoustic noise conditions of the standard motor train unit in the corresponding operation environment;
And judging whether each high-voltage device is abnormal or not based on the difference between the first information and the second information.
In the above aspect, the determining whether each high voltage device is abnormal based on the difference between the first information and the second information includes:
determining the actual time domain features and the actual frequency domain features of the corresponding monitoring points based on the first information for each high-voltage device to obtain a first time domain feature and a first frequency domain feature;
determining target time domain features and target frequency domain features of corresponding monitoring points based on the second information to obtain second time domain features and second frequency domain features;
Judging whether the actually acquired acoustic noise has abnormal noise in the time domain dimension or not based on the comparison result of the first time domain feature and the second time domain feature, and obtaining a first judgment result;
Judging whether abnormal noise exists in the frequency domain dimension of the actually obtained acoustic noise or not based on the comparison result of the first frequency domain feature and the second frequency domain feature, and obtaining a second judgment result;
And judging that the corresponding high-voltage equipment is abnormal under the condition that the first judging result or the second judging result represents that the actually acquired acoustic noise has abnormal noise.
In the above solution, the determining whether the actually obtained acoustic noise has abnormal noise in the time domain dimension based on the comparison result of the first time domain feature and the second time domain feature, to obtain a first determination result includes:
based on the second time domain feature, determining a total time domain variance of acoustic data acquired by corresponding high-voltage equipment along a time sequence, and determining a time domain variance threshold based on the total time domain variance;
based on the first time domain feature, determining a sample time domain variance of acoustic data in an actually acquired sample group to be detected;
And judging whether the acoustic noise data actually acquired in the sample group to be detected is abnormal in the time domain dimension or not based on the sample time domain variance and the time domain variance threshold value, and obtaining a first judgment result.
In the above solution, the determining whether the actually obtained acoustic noise has abnormal noise in the frequency domain dimension based on the comparison result of the first frequency domain feature and the second frequency domain feature, to obtain a second determination result includes:
Determining an overall frequency domain standard deviation of acoustic data of corresponding high-voltage equipment based on the second frequency domain features, and determining a frequency domain standard deviation threshold based on the overall frequency domain standard deviation;
determining a sample frequency domain standard deviation of acoustic data in an actually acquired sample group to be detected based on the first frequency domain characteristic;
and judging whether the acoustic noise data actually acquired in the sample group to be detected is abnormal in the frequency domain dimension or not based on the sample frequency domain standard deviation and the frequency domain standard deviation threshold value, and obtaining a second judgment result.
In the above scheme, the predicting the acoustic noise of the standard motor train unit based on the operation environment information of the standard motor train unit and the parameter information of the standard motor train unit to obtain the second information includes:
Acquiring historical operation data of the standard motor train unit; the historical operation data comprise parameters and acquired acoustic noise data when the standard motor train unit normally operates in various operation scenes; the running environment information of different running scenes is different;
constructing an acoustic prediction model of the standard motor train unit based on the historical operation data;
Determining a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes based on the operation environment information of the standard motor train unit to obtain scene information;
and predicting the acoustic noise of the standard motor train unit in the current running scene by utilizing the acoustic prediction model based on the parameter information and the scene information of the standard motor train unit to obtain second information.
In the above scheme, the operation environment information includes a plurality of first environment factors; the determining, based on the operation environment information of the standard motor train unit, a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes to obtain scene information includes:
determining the matching degree of each first environmental factor in the operation environment information and a corresponding second environmental factor in the first operation scene aiming at each first operation scene in a plurality of preset operation scenes;
Carrying out weighted summation on the matching degree of each first environmental factor to obtain the matching score of the operation environment information and the corresponding first operation scene; the weight of each first environmental factor is determined according to the influence degree of the corresponding first environmental factor on the noise of the standard motor train unit;
and determining a second operation scene from the plurality of first operation scenes based on the matching score of the operation environment information and each first operation scene, and taking the second operation scene as a target operation scene of the standard motor train unit to obtain scene information.
In the above scheme, the operation environment information includes a first environment factor of at least one of:
An operating speed;
a track type;
Ambient temperature;
Humidity;
wind speed;
The wind direction included angle.
In the above scheme, the parameter information of the standard motor train unit comprises a structural parameter and a noise parameter; wherein,
The structural parameters include geometric and material properties;
the noise parameter includes at least one of a wheel-rail contact attribute, a vehicle mass distribution attribute, a vehicle suspension system attribute, a material attribute, and a vehicle maintenance condition.
In the above scheme, the method further comprises:
determining the association degree of acoustic noise and wind energy of each high-voltage device based on the historical noise data of each high-voltage device;
determining a configuration strategy of each high-voltage equipment monitoring point based on the structural characteristics and the corresponding association degree of each high-voltage equipment; the configuration strategy comprises configuration quantity and monitoring position; wherein, when the association degree increases, the configuration quantity increases.
The embodiment of the application also provides a monitoring device for the high-voltage equipment of the rail transit standard motor train unit, which comprises the following components:
The monitoring unit is used for collecting acoustic monitoring data from at least one preset monitoring point to obtain first information; the monitoring points are used for monitoring acoustic data of high-voltage equipment in the standard motor train, and each high-voltage equipment is provided with at least one monitoring point; the first information characterizes the acoustic noise condition actually acquired by each high-voltage device in the running process;
The computing unit is used for predicting the acoustic noise of the standard motor train unit based on the running environment information of the standard motor train unit and the parameter information of the standard motor train unit to obtain second information; the second information represents ideal acoustic noise conditions of the standard motor train unit in the corresponding operation environment;
and the processing unit is used for judging whether each high-voltage device is abnormal or not based on the difference between the first information and the second information.
According to the method and the device for monitoring the high-voltage equipment of the rail transit standard motor train unit, provided by the application, the acoustic noise of the high-voltage equipment is collected by arranging the plurality of monitoring points, and the acoustic noise which is actually collected is compared with the ideal acoustic noise, so that whether the high-voltage equipment is abnormal or not is judged according to whether the acoustic noise is abnormal or not, and therefore, the abnormal information of the high-voltage equipment can be timely obtained under the condition that the performance data of the high-voltage equipment is not abnormal but the structure has potential safety hazards, the detection of early abnormal signals of the equipment is realized, the omnibearing monitoring of the high-voltage equipment is ensured, the fault risk is reduced, and the comprehensiveness and the accuracy of the monitoring result of the high-voltage equipment are improved; further, because the actual operation environment information is introduced in the process of predicting the ideal acoustic noise, the comprehensiveness of the input information of the model is improved, so that the accuracy of the ideal acoustic noise output by the model can be improved, the accuracy of a final judgment result is further improved, and the safe and stable operation of the high-voltage equipment is ensured.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
Fig. 1 is a schematic flow chart of a method for monitoring high-voltage equipment of a rail transit standard motor train unit according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a monitoring device for high-voltage equipment of a rail transit standard motor train unit according to an embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the accompanying drawings and examples.
The motor train unit is used as an important transportation means, and brings great convenience to daily travel of people. However, the more powerful the system can provide, the more complex its structural composition and the more closely linked the parts, which results in greater difficulty in maintaining the system. How to ensure the effective and safe operation of the motor train unit becomes the urgent attention problem at present, and as such, the establishment of an effective and reliable monitoring means is particularly critical and important in improving the monitoring effect and the fault diagnosis capability.
In the related art, the high-voltage equipment of the motor train unit can be monitored in a visual inspection mode, namely, the visual inspection is carried out on the high-voltage equipment at regular intervals, and whether the structure of the high-voltage equipment is abnormal or not is judged; however, since faults of high-voltage equipment occur in the operation process, the real-time performance of the overhaul cannot be guaranteed in a regular overhaul mode, and a large potential safety hazard exists.
Aiming at the problems, the operation data of the high-voltage equipment can be collected in real time in the operation process, and then the performance of each equipment is analyzed according to the collected power parameters to judge whether the equipment is operated normally or not; however, the operation parameters can only reflect whether the equipment is normally operated at present, and the fatigue degree and the damage degree of the equipment cannot be timely and reliably detected, so that potential safety hazards cannot be timely detected, for example, failure of external devices of the motor train unit caused by vibration of the equipment structure cannot be detected, and for example, overstress, fatigue damage and the like of the structure and the equipment cannot be detected; therefore, a certain hysteresis exists in the mode of monitoring by utilizing the real-time operation data of the equipment, so that the comprehensiveness and reliability of the monitoring result are lower.
Based on the above, in various embodiments of the application, acoustic noise of the high-voltage equipment is collected by setting a plurality of monitoring points, and the acoustic noise which is actually collected is compared with ideal acoustic noise, so that whether the high-voltage equipment is abnormal or not is judged according to whether the acoustic noise is abnormal or not, and therefore, the abnormal information of the high-voltage equipment can be timely obtained under the condition that the performance data of the high-voltage equipment is not abnormal but the structure has potential safety hazards, the detection of early abnormal signals of the equipment is realized, the omnibearing monitoring of the high-voltage equipment is ensured, the fault risk is reduced, and the comprehensiveness and the accuracy of the monitoring result of the high-voltage equipment are improved; further, because the actual operation environment information is introduced in the process of predicting the ideal acoustic noise, the comprehensiveness of the input information of the model is improved, so that the accuracy of the ideal acoustic noise output by the model can be improved, the accuracy of a final judgment result is further improved, and the safe and stable operation of the high-voltage equipment is ensured.
The embodiment of the application provides a rail transit standard motor train unit high-voltage equipment monitoring method which is applied to electronic equipment, and particularly can be applied to electronic equipment such as computers, motor train vehicle-mounted computers, servers, cloud servers and the like; as shown in fig. 1, the method may include:
Step 101: acquiring acoustic monitoring data from at least one preset monitoring point to obtain first information; the monitoring points are used for monitoring acoustic data of high-voltage equipment in the standard motor train, and each high-voltage equipment is provided with at least one monitoring point; the first information characterizes acoustic noise conditions actually acquired by each high-voltage device in the operation process.
In practical application, in order to ensure accuracy of acoustic monitoring data, a plurality of monitoring points can be configured for each high-voltage device.
In practical application, because the structural characteristics of the high-voltage equipment are different, the position points of noise generated by the high-voltage equipment can be different, and the degree of influence of wind power can be different; therefore, in order to improve accuracy of data collected by the monitoring points, how to set the monitoring points can be determined according to the association degree of structural features of the high-voltage equipment and performance parameters of wind.
Based on this, in an embodiment, the method may further include:
determining the association degree of acoustic noise and wind energy of each high-voltage device based on the historical noise data of each high-voltage device;
determining a configuration strategy of each high-voltage equipment monitoring point based on the structural characteristics and the corresponding association degree of each high-voltage equipment; the configuration strategy comprises configuration quantity and monitoring position; wherein, when the association degree increases, the configuration quantity increases.
In practical application, the association degree of the acoustic noise of the high-voltage equipment and wind energy is determined, which can be understood as the association degree of the acoustic noise of the high-voltage equipment and the performance parameters of wind; wherein, the performance parameters of the wind can comprise wind power and wind direction included angles; for the monitoring point of the high-voltage equipment, one side of the high-voltage equipment corresponding to the monitoring point can be called a monitoring surface, and the included angle of the wind direction can be understood as the included angle of the wind direction and the detecting surface.
In practical application, when determining the configuration strategy, a plurality of stress surfaces, namely the side surfaces which are affected by wind power, can be determined according to the structural characteristics of high-voltage equipment; and then determining at least one monitoring surface from the plurality of stress surfaces according to the association degree of each stress surface and wind energy, and configuring monitoring points on the monitoring surfaces.
Specifically, for each stress surface of the high-voltage equipment, according to historical noise data, determining acoustic noise of the stress surface under the condition of the same included angle of the same wind direction and the same included angle of different wind forces, and calculating the wind force association degree of the stress surface, specifically, calculating the wind force association degree of the stress surface according to the ratio of the acoustic noise to the wind force; then, according to the historical noise data, determining the acoustic noise of the stressed surface under the same wind force and different wind direction angles, so as to calculate the wind direction angle association degree of the stressed surface, specifically, the wind direction angle association degree of the stressed surface can be calculated according to the ratio of the acoustic noise to the wind direction angle; then, carrying out weighted summation on the wind power association degree and the wind direction included angle association degree to obtain the wind power association degree of the stress surface and wind energy; then judging whether the wind energy association degree of each stress surface is larger than a preset association degree threshold value, and taking the stress surface as a monitoring surface under the condition that the wind energy association degree of each stress surface is larger than the preset association degree threshold value; in practical application, the first N stress surfaces with the maximum wind energy association degree can be selected as monitoring surfaces, and N is an integer greater than or equal to 1.
In practical application, the configuration quantity of the monitoring points can be determined according to the structural characteristics of the high-voltage equipment, and specifically, the high-voltage equipment can be classified according to the structural characteristics of the high-voltage equipment to obtain a class of high-voltage equipment and a class of high-voltage equipment; the high-voltage equipment is equipment with a simple structure and small influence by wind energy, the configuration number of monitoring points can be N1, the high-voltage equipment is equipment with a complex structure and large influence by wind energy, the configuration number of the monitoring points can be N2, N1 and N2 are integers not smaller than 1, and N1 is smaller than N2; the number of N1 and N2 may be specifically configured according to the actual monitoring requirement, which is not limited in the embodiment of the present application.
Step 102: predicting acoustic noise of the standard motor train unit based on the running environment information of the standard motor train unit and the parameter information of the standard motor train unit to obtain second information; the second information characterizes ideal acoustic noise conditions of the standard motor train unit in a corresponding operation environment.
In practical application, an acoustic prediction model can be established according to simulation or historical data, and then a reference acoustic noise curve, namely a target acoustic noise curve, is predicted by utilizing the acoustic prediction model, so that whether the acoustic noise acquired in real time is abnormal or not is judged according to the difference of corresponding values in the acoustic noise and the target acoustic noise curve under the same running environment.
Based on this, in an embodiment, the predicting the acoustic noise of the standard motor train unit based on the operating environment information of the standard motor train unit and the parameter information of the standard motor train unit, to obtain the second information includes:
Acquiring historical operation data of the standard motor train unit; the historical operation data comprise parameters and acquired acoustic noise data when the standard motor train unit normally operates in various operation scenes; the running environment information of different running scenes is different;
constructing an acoustic prediction model of the standard motor train unit based on the historical operation data;
Determining a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes based on the operation environment information of the standard motor train unit to obtain scene information;
and predicting the acoustic noise of the standard motor train unit in the current running scene by utilizing the acoustic prediction model based on the parameter information and the scene information of the standard motor train unit to obtain second information.
In practical application, the running environments in different time periods are difficult to achieve complete consistency, so that the close running scenes can be retrieved from the model data according to the similarity between the running environment information, and the reliability of the output result of the acoustic prediction model is ensured.
Based on this, in one embodiment, the operating environment information includes a plurality of first environmental factors; the determining, based on the operation environment information of the standard motor train unit, a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes to obtain scene information includes:
determining the matching degree of each first environmental factor in the operation environment information and a corresponding second environmental factor in the first operation scene aiming at each first operation scene in a plurality of preset operation scenes;
Carrying out weighted summation on the matching degree of each first environmental factor to obtain the matching score of the operation environment information and the corresponding first operation scene; the weight of each first environmental factor is determined according to the influence degree of the corresponding first environmental factor on the noise of the standard motor train unit;
and determining a second operation scene from the plurality of first operation scenes based on the matching score of the operation environment information and each first operation scene, and taking the second operation scene as a target operation scene of the standard motor train unit to obtain scene information.
When the method is actually applied, when the matching degree of the first environmental factor and the corresponding second environmental factor is determined, the ratio of the first environmental factor to the corresponding second environmental factor can be calculated to obtain the environmental matching degree, the calculated environmental matching degree is compared with a preset matching degree threshold value, whether the environmental matching degree is larger than the preset matching degree threshold value is judged, and the corresponding first operation scene is used as a candidate scene under the condition that the environmental matching degree is larger than the preset matching threshold value; and then selecting the to-be-selected scene with the highest environment matching degree from the determined to-be-selected scenes as a target operation scene, namely, the to-be-selected scene is used as the current operation scene, and obtaining the scene information of the target operation scene.
In one embodiment, the operating environment information includes a first environmental factor of at least one of:
An operating speed;
a track type;
Ambient temperature;
Humidity;
wind speed;
The wind direction included angle.
In an embodiment, the parameter information of the standard motor train unit includes a structural parameter and a noise parameter; wherein,
The structural parameters include geometric and material properties;
the noise parameter includes at least one of a wheel-rail contact attribute, a vehicle mass distribution attribute, a vehicle suspension system attribute, a material attribute, and a vehicle maintenance condition.
In practical application, the parameter information of the standard motor train unit can be parameters which are configured in advance in the production process.
In practical application, the appearance parameters, the operation parameters and the high-voltage equipment types of different motor train units are also different, so that the operation data and the acoustic noise characteristics in the same operation environment are also different, and the acoustic noise prediction is performed by adopting the same prediction model, so that the accuracy is lower; therefore, more accurate and reliable prediction can be achieved by building different prediction models for different types of motor train units.
Based on this, in an embodiment, the constructing an acoustic prediction model of the standard motor train unit based on the historical operation data may include:
constructing an acoustic prediction model of at least one type of standard motor train unit based on the historical operation data to obtain at least one first acoustic prediction model; the parameter information of the motor train units with different types of standards is different.
Based on this, in an embodiment, the predicting, based on the parameter information of the standard motor train unit and the scene information, the acoustic noise of the standard motor train unit in the current running scene by using the acoustic prediction model to obtain the second information may include:
determining a target acoustic prediction model from the constructed at least one first acoustic prediction model based on the parameter information of the standard motor train unit;
And predicting the acoustic noise of the standard motor train unit in the current running scene by using the target acoustic prediction model and the corresponding scene information to obtain second information.
Step 103: and judging whether each high-voltage device is abnormal or not based on the difference between the first information and the second information.
In practical application, in order to ensure the comprehensiveness of the judgment result and thus improve the accuracy of the judgment result, the judgment can be performed from two dimensions of the time domain and the frequency domain.
Based on this, in an embodiment, the determining whether each high voltage device is abnormal based on the difference between the first information and the second information may include:
determining the actual time domain features and the actual frequency domain features of the corresponding monitoring points based on the first information for each high-voltage device to obtain a first time domain feature and a first frequency domain feature;
determining target time domain features and target frequency domain features of corresponding monitoring points based on the second information to obtain second time domain features and second frequency domain features;
Judging whether the actually acquired acoustic noise has abnormal noise in the time domain dimension or not based on the comparison result of the first time domain feature and the second time domain feature, and obtaining a first judgment result;
Judging whether abnormal noise exists in the frequency domain dimension of the actually obtained acoustic noise or not based on the comparison result of the first frequency domain feature and the second frequency domain feature, and obtaining a second judgment result;
And judging that the corresponding high-voltage equipment is abnormal under the condition that the first judging result or the second judging result represents that the actually acquired acoustic noise has abnormal noise.
In an embodiment, the determining whether the actually obtained acoustic noise has abnormal noise in the time domain dimension based on the comparison result of the first time domain feature and the second time domain feature, to obtain a first determination result may include:
based on the second time domain feature, determining a total time domain variance of acoustic data acquired by corresponding high-voltage equipment along a time sequence, and determining a time domain variance threshold based on the total time domain variance;
based on the first time domain feature, determining a sample time domain variance of acoustic data in an actually acquired sample group to be detected;
And judging whether the acoustic noise data actually acquired in the sample group to be detected is abnormal in the time domain dimension or not based on the sample time domain variance and the time domain variance threshold value, and obtaining a first judgment result.
In practical application, the method comprises the steps of determining the overall time domain variance of acoustic data acquired by corresponding high-voltage equipment along a time sequence based on the second time domain features, and determining a time domain variance threshold based on the overall time domain variance, wherein the method can be used for firstly averaging noise samples acquired by the high-voltage equipment corresponding to monitoring points at the same moment, then constructing a sample time sequence according to the average number of data acquired at each moment, then determining an overall standard variance, namely the overall time domain variance, by utilizing the time sample sequence, and finally determining the time domain variance threshold according to the overall standard variance and a preset coefficient extreme time domain variance threshold.
In practical application, when determining the sample time domain variance of the acoustic data in the actually acquired sample group to be tested based on the first time domain feature, it can be understood that the data set acquired by monitoring can be periodically acquired, each acquired data set includes a plurality of samples to be tested in the current acquisition period, the sample data to be tested at the same moment in each monitoring point are subjected to data fusion, then arranged according to time extraction, the sample group to be tested is formed, and the sample time domain variance of the acoustic data in the sample group to be tested is calculated.
In practical application, when judging whether the acoustic noise data actually acquired in the sample group to be detected has an abnormality in the time domain dimension based on the sample time domain variance and the time domain variance threshold, it may be judged whether the time domain variance of each sample in the sample group to be detected is greater than the time domain variance threshold, and when the time domain variance is greater than the time domain variance threshold, it may be considered that the variance of the current sample is far greater than the normal range, so as to judge that the acquired acoustic noise data has an abnormality.
Illustratively, the process of obtaining the first determination result is expressed as:
(1) Constructing a sample sequence X with the number of samples of N:
；
；
；
Wherein, Representing the average value of the sample set,The variance of the samples is represented and,Representing the ith sample in the sample group, wherein i is more than or equal to 1 and less than or equal to N;
(2) Establishing a normal range:
To determine the normal range, the variance of all samples needs to be calculated and a threshold is determined to determine if the variance is abnormal; one common approach is to define the threshold using standard deviation (i.e., square root of variance);
；
；
Wherein, The overall variance is represented as such,Represents the total standard deviation, M represents the number of sample groups,Representing the variance of the j-th sample set;
(3) Calculating a threshold T:
；
Wherein k is more than or equal to 3 and less than or equal to 5;
(4) Judging a sample to be tested:
for each sample to be tested, judging the variance of the sample to be tested Relationship with a threshold T;
When (when) The variance of the sample is considered to be far larger than the normal range, namely, the first judgment result represents that the acquired acoustic noise data is abnormal;
When (when) And considering that the variance of the sample is far away from the normal range, namely, the first judgment result represents that the acquired acoustic noise data is not abnormal.
In practical application, for acoustic noise, it is possible to determine whether certain frequency components in the frequency spectrum are significantly higher than the normal range; to identify abnormal noise.
Based on this, in an embodiment, the determining whether the actually obtained acoustic noise has abnormal noise in the frequency domain dimension based on the comparison result of the first frequency domain feature and the second frequency domain feature, to obtain a second determination result may include:
Determining an overall frequency domain standard deviation of acoustic data of corresponding high-voltage equipment based on the second frequency domain features, and determining a frequency domain standard deviation threshold based on the overall frequency domain standard deviation;
determining a sample frequency domain standard deviation of acoustic data in an actually acquired sample group to be detected based on the first frequency domain characteristic;
and judging whether the acoustic noise data actually acquired in the sample group to be detected is abnormal in the frequency domain dimension or not based on the sample frequency domain standard deviation and the frequency domain standard deviation threshold value, and obtaining a second judgment result.
In practical application, when determining the total frequency domain standard deviation of acoustic data of corresponding high-voltage equipment and determining the frequency domain standard deviation threshold based on the total frequency domain standard deviation, calculating the amplitude or Power Spectral Density (PSD) of each frequency component in the frequency spectrum, further calculating statistical features such as mean and standard deviation, and then establishing a normal range according to the statistical features, namely determining the frequency domain standard deviation threshold.
Illustratively, the process of determining the second judgment result may be expressed as:
(1) Calculating spectral features:
converting the time domain signal into a frequency domain signal by using Fast Fourier Transform (FFT) to obtain a spectrogram;
(2) Establishing a normal range:
；
；
；
Wherein, Representing the mean value of each frequency component f,Representing the spectral value at frequency f i, M representing the number of samples,The overall mean value is represented as such,Representing the overall standard deviation;
(2) Calculating a threshold T:
；
wherein k is more than or equal to 3 and less than or equal to 5;
(3) Judging abnormality:
For each frequency component f, if And considering that the frequency component is abnormal, namely, the second judgment result represents that abnormal noise exists in the frequency domain dimension of the actually acquired acoustic noise.
It should be noted that, in the embodiment of the present application, the preset threshold may be set according to historical experience, or may be determined by using a corresponding simulation model, which is not limited in the embodiment of the present application.
In summary, according to the rail transit standard motor train unit high-voltage equipment monitoring method provided by the embodiment of the application, the acoustic noise of the high-voltage equipment is acquired by setting a plurality of monitoring points, and the acoustic noise acquired in practice is compared with the ideal acoustic noise, so that whether the high-voltage equipment is abnormal or not is judged according to whether the acoustic noise is abnormal or not, and therefore, the abnormal information of the high-voltage equipment can be timely acquired under the condition that the performance data of the high-voltage equipment is not abnormal but the structure has potential safety hazards, the detection of early abnormal signals of the equipment is realized, the omnibearing monitoring of the high-voltage equipment is ensured, the fault risk is reduced, and the comprehensiveness and the accuracy of the monitoring result of the high-voltage equipment are improved; further, because the actual operation environment information is introduced in the process of predicting the ideal acoustic noise, the comprehensiveness of the input information of the model is improved, so that the accuracy of the ideal acoustic noise output by the model can be improved, the accuracy of a final judgment result is further improved, and the safe and stable operation of the high-voltage equipment is ensured.
In order to implement the method for monitoring the high-voltage equipment of the rail transit standard motor train unit, the embodiment of the application also provides a device for monitoring the high-voltage equipment of the rail transit standard motor train unit, which is arranged on the electronic equipment, as shown in fig. 2, and the device can comprise:
The monitoring unit 201 is configured to collect acoustic monitoring data from at least one preset monitoring point to obtain first information; the monitoring points are used for monitoring acoustic data of high-voltage equipment in the standard motor train, and each high-voltage equipment is provided with at least one monitoring point; the first information characterizes the acoustic noise condition actually acquired by each high-voltage device in the running process;
A computing unit 202, configured to predict acoustic noise of the standard motor train unit based on the operating environment information of the standard motor train unit and the parameter information of the standard motor train unit, to obtain second information; the second information represents ideal acoustic noise conditions of the standard motor train unit in the corresponding operation environment;
A processing unit 203 for determining whether each high-voltage device is abnormal based on the difference between the first information and the second information
In an embodiment, the processing unit 203 may specifically be configured to:
determining the actual time domain features and the actual frequency domain features of the corresponding monitoring points based on the first information for each high-voltage device to obtain a first time domain feature and a first frequency domain feature;
determining target time domain features and target frequency domain features of corresponding monitoring points based on the second information to obtain second time domain features and second frequency domain features;
Judging whether the actually acquired acoustic noise has abnormal noise in the time domain dimension or not based on the comparison result of the first time domain feature and the second time domain feature, and obtaining a first judgment result;
Judging whether abnormal noise exists in the frequency domain dimension of the actually obtained acoustic noise or not based on the comparison result of the first frequency domain feature and the second frequency domain feature, and obtaining a second judgment result;
And judging that the corresponding high-voltage equipment is abnormal under the condition that the first judging result or the second judging result represents that the actually acquired acoustic noise has abnormal noise.
In an embodiment, the determining whether the actually obtained acoustic noise has abnormal noise in the time domain dimension based on the comparison result of the first time domain feature and the second time domain feature, to obtain a first determination result includes:
based on the second time domain feature, determining a total time domain variance of acoustic data acquired by corresponding high-voltage equipment along a time sequence, and determining a time domain variance threshold based on the total time domain variance;
based on the first time domain feature, determining a sample time domain variance of acoustic data in an actually acquired sample group to be detected;
And judging whether the acoustic noise data actually acquired in the sample group to be detected is abnormal in the time domain dimension or not based on the sample time domain variance and the time domain variance threshold value, and obtaining a first judgment result.
In an embodiment, the determining whether the actually obtained acoustic noise has abnormal noise in the frequency domain dimension based on the comparison result of the first frequency domain feature and the second frequency domain feature, to obtain a second determination result includes:
Determining an overall frequency domain standard deviation of acoustic data of corresponding high-voltage equipment based on the second frequency domain features, and determining a frequency domain standard deviation threshold based on the overall frequency domain standard deviation;
determining a sample frequency domain standard deviation of acoustic data in an actually acquired sample group to be detected based on the first frequency domain characteristic;
and judging whether the acoustic noise data actually acquired in the sample group to be detected is abnormal in the frequency domain dimension or not based on the sample frequency domain standard deviation and the frequency domain standard deviation threshold value, and obtaining a second judgment result.
In an embodiment, the computing unit 202 may be specifically configured to:
Acquiring historical operation data of the standard motor train unit; the historical operation data comprise parameters and acquired acoustic noise data when the standard motor train unit normally operates in various operation scenes; the running environment information of different running scenes is different;
constructing an acoustic prediction model of the standard motor train unit based on the historical operation data;
Determining a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes based on the operation environment information of the standard motor train unit to obtain scene information;
and predicting the acoustic noise of the standard motor train unit in the current running scene by utilizing the acoustic prediction model based on the parameter information and the scene information of the standard motor train unit to obtain second information.
In one embodiment, the operating environment information includes a plurality of first environmental factors; the determining, based on the operation environment information of the standard motor train unit, a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes to obtain scene information includes:
determining the matching degree of each first environmental factor in the operation environment information and a corresponding second environmental factor in the first operation scene aiming at each first operation scene in a plurality of preset operation scenes;
Carrying out weighted summation on the matching degree of each first environmental factor to obtain the matching score of the operation environment information and the corresponding first operation scene; the weight of each first environmental factor is determined according to the influence degree of the corresponding first environmental factor on the noise of the standard motor train unit;
and determining a second operation scene from the plurality of first operation scenes based on the matching score of the operation environment information and each first operation scene, and taking the second operation scene as a target operation scene of the standard motor train unit to obtain scene information.
In one embodiment, the operating environment information includes a first environmental factor of at least one of:
An operating speed;
a track type;
Ambient temperature;
Humidity;
wind speed;
The wind direction included angle.
In an embodiment, the parameter information of the standard motor train unit includes a structural parameter and a noise parameter; wherein,
The structural parameters include geometric and material properties;
the noise parameter includes at least one of a wheel-rail contact attribute, a vehicle mass distribution attribute, a vehicle suspension system attribute, a material attribute, and a vehicle maintenance condition.
In an embodiment, the processing unit 203 may be further configured to:
determining the association degree of acoustic noise and wind energy of each high-voltage device based on the historical noise data of each high-voltage device;
determining a configuration strategy of each high-voltage equipment monitoring point based on the structural characteristics and the corresponding association degree of each high-voltage equipment; the configuration strategy comprises configuration quantity and monitoring position; wherein, when the association degree increases, the configuration quantity increases.
It should be noted that: in the rail transit standard motor train unit high voltage equipment monitoring device provided in the above embodiment, when the high voltage equipment is monitored, only the division of each program module is used for illustration, in practical application, the processing allocation can be completed by different program modules according to needs, that is, the internal structure of the device is divided into different program modules, so as to complete all or part of the processing described above. In addition, the track traffic standard motor train unit high voltage equipment monitoring device and the track traffic standard motor train unit high voltage equipment monitoring method provided in the foregoing embodiments belong to the same concept, and specific implementation processes thereof are detailed in the method embodiments and are not described herein again.
It should be noted that: "first," "second," etc. are used to distinguish similar objects and not necessarily to describe a particular order or sequence.
In addition, the embodiments of the present application may be arbitrarily combined without any collision.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the present application.
Claims (7)
1. A method for monitoring high-voltage equipment of a rail transit standard motor train unit, which is characterized by comprising the following steps:
Acquiring acoustic monitoring data from at least one preset monitoring point to obtain first information; the monitoring points are used for monitoring acoustic data of high-voltage equipment in the standard motor train, and each high-voltage equipment is provided with at least one monitoring point; the first information characterizes the acoustic noise condition actually acquired by each high-voltage device in the running process;
predicting acoustic noise of the standard motor train unit based on the running environment information of the standard motor train unit and the parameter information of the standard motor train unit to obtain second information; the second information represents ideal acoustic noise conditions of the standard motor train unit in the corresponding operation environment;
Judging whether each high-voltage device is abnormal or not based on the difference between the first information and the second information; wherein,
The predicting the acoustic noise of the standard motor train unit based on the running environment information of the standard motor train unit and the parameter information of the standard motor train unit to obtain second information comprises the following steps: acquiring historical operation data of the standard motor train unit; the historical operation data comprise parameters and acquired acoustic noise data when the standard motor train unit normally operates in various operation scenes; the running environment information of different running scenes is different; constructing an acoustic prediction model of the standard motor train unit based on the historical operation data; determining a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes based on the operation environment information of the standard motor train unit to obtain scene information; based on the parameter information and the scene information of the standard motor train unit, predicting the acoustic noise of the standard motor train unit in the current running scene by using the acoustic prediction model to obtain second information;
the operating environment information includes a plurality of first environmental factors; the determining, based on the operation environment information of the standard motor train unit, a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes to obtain scene information includes: determining the matching degree of each first environmental factor in the operation environment information and a corresponding second environmental factor in the first operation scene aiming at each first operation scene in a plurality of preset operation scenes; carrying out weighted summation on the matching degree of each first environmental factor to obtain the matching score of the operation environment information and the corresponding first operation scene; the weight of each first environmental factor is determined according to the influence degree of the corresponding first environmental factor on the noise of the standard motor train unit; determining a second operation scene from the plurality of first operation scenes based on the matching score of the operation environment information and each first operation scene, and taking the second operation scene as a target operation scene of the standard motor train unit to obtain scene information;
The method further comprises the steps of: determining the association degree of acoustic noise and wind energy of each high-voltage device based on the historical noise data of each high-voltage device; determining a configuration strategy of each high-voltage equipment monitoring point based on the structural characteristics and the corresponding association degree of each high-voltage equipment; the configuration strategy comprises configuration quantity and monitoring position; when the association degree is increased, the configuration quantity is increased; wherein,
The determining the association degree of the acoustic noise and the wind energy of each high-voltage device comprises the following steps: determining the association degree of the acoustic noise of the high-voltage equipment and the performance parameters of wind; the performance parameters of the wind comprise wind power and a wind direction included angle; aiming at a monitoring point of high-voltage equipment, one side of the high-voltage equipment corresponding to the monitoring point is called a monitoring surface, and the included angle of the wind direction is the included angle between the wind direction and the monitoring surface;
The method further comprises the steps of: when a strategy is configured, a plurality of stress surfaces are determined according to the structural characteristics of high-voltage equipment, wherein the stress surfaces are side surfaces affected by wind power; then, according to the association degree of each stress surface and wind energy, at least one monitoring surface is determined from a plurality of stress surfaces, and monitoring points are configured on the monitoring surfaces;
Determining at least one monitoring surface from a plurality of stress surfaces according to the association degree of each stress surface and wind energy, wherein the monitoring surface comprises: for each stress surface of the high-voltage equipment, determining acoustic noise of the stress surface under different wind forces under the condition of the same wind direction included angle according to historical noise data, and calculating the wind force association degree of the stress surface, wherein the wind force association degree of the stress surface is calculated according to the ratio of the acoustic noise to the wind force; then, according to the historical noise data, determining the acoustic noise of the stressed surface under the same wind force and different wind direction angles, so as to calculate the wind direction angle correlation degree of the stressed surface, wherein the wind direction angle correlation degree of the stressed surface is calculated according to the ratio of the acoustic noise to the wind direction angle; then, carrying out weighted summation on the wind power association degree and the wind direction included angle association degree to obtain the wind power association degree of the stress surface and wind power; then judging whether the wind energy association degree of each stress surface is larger than a preset association degree threshold value, and taking the stress surface as a monitoring surface under the condition that the wind energy association degree of each stress surface is larger than the preset association degree threshold value; or the first N stress surfaces with the maximum wind energy association degree are selected as monitoring surfaces, and N is an integer greater than or equal to 1.
2. The method of claim 1, wherein the determining whether each high voltage device is abnormal based on the difference between the first information and the second information comprises:
determining the actual time domain features and the actual frequency domain features of the corresponding monitoring points based on the first information for each high-voltage device to obtain a first time domain feature and a first frequency domain feature;
determining target time domain features and target frequency domain features of corresponding monitoring points based on the second information to obtain second time domain features and second frequency domain features;
Judging whether the actually acquired acoustic noise has abnormal noise in the time domain dimension or not based on the comparison result of the first time domain feature and the second time domain feature, and obtaining a first judgment result;
Judging whether abnormal noise exists in the frequency domain dimension of the actually obtained acoustic noise or not based on the comparison result of the first frequency domain feature and the second frequency domain feature, and obtaining a second judgment result;
And judging that the corresponding high-voltage equipment is abnormal under the condition that the first judging result or the second judging result represents that the actually acquired acoustic noise has abnormal noise.
3. The method of claim 2, wherein the determining whether the actually acquired acoustic noise has abnormal noise in the time domain dimension based on the comparison result of the first time domain feature and the second time domain feature, to obtain a first determination result, includes:
based on the second time domain feature, determining a total time domain variance of acoustic data acquired by corresponding high-voltage equipment along a time sequence, and determining a time domain variance threshold based on the total time domain variance;
based on the first time domain feature, determining a sample time domain variance of acoustic data in an actually acquired sample group to be detected;
And judging whether the acoustic noise data actually acquired in the sample group to be detected is abnormal in the time domain dimension or not based on the sample time domain variance and the time domain variance threshold value, and obtaining a first judgment result.
4. The method of claim 2, wherein the determining whether the actually obtained acoustic noise has abnormal noise in the frequency domain dimension based on the comparison result of the first frequency domain feature and the second frequency domain feature, to obtain a second determination result, includes:
Determining an overall frequency domain standard deviation of acoustic data of corresponding high-voltage equipment based on the second frequency domain features, and determining a frequency domain standard deviation threshold based on the overall frequency domain standard deviation;
determining a sample frequency domain standard deviation of acoustic data in an actually acquired sample group to be detected based on the first frequency domain characteristic;
and judging whether the acoustic noise data actually acquired in the sample group to be detected is abnormal in the frequency domain dimension or not based on the sample frequency domain standard deviation and the frequency domain standard deviation threshold value, and obtaining a second judgment result.
5. The method of claim 1, wherein the operating environment information includes a first environmental factor of at least one of:
An operating speed;
a track type;
Ambient temperature;
Humidity;
wind speed;
The wind direction included angle.
6. The method of claim 1, wherein the parameter information of the standard motor train unit includes a structural parameter and a noise parameter; wherein,
The structural parameters include geometric and material properties;
the noise parameter includes at least one of a wheel-rail contact attribute, a vehicle mass distribution attribute, a vehicle suspension system attribute, a material attribute, and a vehicle maintenance condition.
7. A rail transit standard motor train unit high voltage equipment monitoring device, characterized in that the device comprises:
The monitoring unit is used for collecting acoustic monitoring data from at least one preset monitoring point to obtain first information; the monitoring points are used for monitoring acoustic data of high-voltage equipment in the standard motor train, and each high-voltage equipment is provided with at least one monitoring point; the first information characterizes the acoustic noise condition actually acquired by each high-voltage device in the running process;
The computing unit is used for predicting the acoustic noise of the standard motor train unit based on the running environment information of the standard motor train unit and the parameter information of the standard motor train unit to obtain second information; the second information represents ideal acoustic noise conditions of the standard motor train unit in the corresponding operation environment;
A processing unit configured to determine whether or not abnormality occurs in each high-voltage device based on a difference between the first information and the second information; wherein,
The predicting the acoustic noise of the standard motor train unit based on the running environment information of the standard motor train unit and the parameter information of the standard motor train unit to obtain second information comprises the following steps: acquiring historical operation data of the standard motor train unit; the historical operation data comprise parameters and acquired acoustic noise data when the standard motor train unit normally operates in various operation scenes; the running environment information of different running scenes is different; constructing an acoustic prediction model of the standard motor train unit based on the historical operation data; determining a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes based on the operation environment information of the standard motor train unit to obtain scene information; based on the parameter information and the scene information of the standard motor train unit, predicting the acoustic noise of the standard motor train unit in the current running scene by using the acoustic prediction model to obtain second information;
the operating environment information includes a plurality of first environmental factors; the determining, based on the operation environment information of the standard motor train unit, a target operation scene of the standard motor train unit from a plurality of preset prediction model standby scenes to obtain scene information includes: determining the matching degree of each first environmental factor in the operation environment information and a corresponding second environmental factor in the first operation scene aiming at each first operation scene in a plurality of preset operation scenes; carrying out weighted summation on the matching degree of each first environmental factor to obtain the matching score of the operation environment information and the corresponding first operation scene; the weight of each first environmental factor is determined according to the influence degree of the corresponding first environmental factor on the noise of the standard motor train unit; determining a second operation scene from the plurality of first operation scenes based on the matching score of the operation environment information and each first operation scene, and taking the second operation scene as a target operation scene of the standard motor train unit to obtain scene information;
The monitoring unit is further configured to: determining the association degree of acoustic noise and wind energy of each high-voltage device based on the historical noise data of each high-voltage device; determining a configuration strategy of each high-voltage equipment monitoring point based on the structural characteristics and the corresponding association degree of each high-voltage equipment; the configuration strategy comprises configuration quantity and monitoring position; when the association degree is increased, the configuration quantity is increased; wherein,
The determining the association degree of the acoustic noise and the wind energy of each high-voltage device comprises the following steps: determining the association degree of the acoustic noise of the high-voltage equipment and the performance parameters of wind; the performance parameters of the wind comprise wind power and a wind direction included angle; aiming at a monitoring point of high-voltage equipment, one side of the high-voltage equipment corresponding to the monitoring point is called a monitoring surface, and the included angle of the wind direction is the included angle between the wind direction and the monitoring surface;
The monitoring unit is further configured to: when a strategy is configured, a plurality of stress surfaces are determined according to the structural characteristics of high-voltage equipment, wherein the stress surfaces are side surfaces affected by wind power; then, according to the association degree of each stress surface and wind energy, at least one monitoring surface is determined from a plurality of stress surfaces, and monitoring points are configured on the monitoring surfaces;
Determining at least one monitoring surface from a plurality of stress surfaces according to the association degree of each stress surface and wind energy, wherein the monitoring surface comprises: for each stress surface of the high-voltage equipment, determining acoustic noise of the stress surface under different wind forces under the condition of the same wind direction included angle according to historical noise data, and calculating the wind force association degree of the stress surface, wherein the wind force association degree of the stress surface is calculated according to the ratio of the acoustic noise to the wind force; then, according to the historical noise data, determining the acoustic noise of the stressed surface under the same wind force and different wind direction angles, so as to calculate the wind direction angle correlation degree of the stressed surface, wherein the wind direction angle correlation degree of the stressed surface is calculated according to the ratio of the acoustic noise to the wind direction angle; then, carrying out weighted summation on the wind power association degree and the wind direction included angle association degree to obtain the wind power association degree of the stress surface and wind power; then judging whether the wind energy association degree of each stress surface is larger than a preset association degree threshold value, and taking the stress surface as a monitoring surface under the condition that the wind energy association degree of each stress surface is larger than the preset association degree threshold value; or the first N stress surfaces with the maximum wind energy association degree are selected as monitoring surfaces, and N is an integer greater than or equal to 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411050242.1A CN118565870B (en) | 2024-08-01 | 2024-08-01 | Rail transit standard motor train unit high-voltage equipment monitoring method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411050242.1A CN118565870B (en) | 2024-08-01 | 2024-08-01 | Rail transit standard motor train unit high-voltage equipment monitoring method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118565870A CN118565870A (en) | 2024-08-30 |
| CN118565870B true CN118565870B (en) | 2024-10-15 |
Family
ID=92469668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411050242.1A Active CN118565870B (en) | 2024-08-01 | 2024-08-01 | Rail transit standard motor train unit high-voltage equipment monitoring method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118565870B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118914925A (en) * | 2024-10-11 | 2024-11-08 | 青岛融创信为技术有限公司 | High-voltage fault positioning detection method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106198062A (en) * | 2016-07-27 | 2016-12-07 | 哈尔滨市科佳通用机电有限公司 | The vehicle-mounted acoustic testing system of track vehicle fault and detection method |
| CN109211556A (en) * | 2018-10-19 | 2019-01-15 | 广州益牛科技有限公司 | A kind of track vehicle components detection system |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9026305B2 (en) * | 2012-07-19 | 2015-05-05 | Hunter Engineering Company | System and method for wheel assembly acoustical evaluation |
| CN109406147B (en) * | 2018-10-29 | 2020-11-13 | 安徽大学 | Train bearing rail side acoustic diagnosis method under variable speed working condition |
| CN112082781B (en) * | 2019-06-12 | 2022-03-15 | 比亚迪股份有限公司 | Vehicle and fault detection method and fault detection device thereof |
| CN110606093A (en) * | 2019-09-26 | 2019-12-24 | 中国第一汽车股份有限公司 | Vehicle performance evaluation method, device, equipment and storage medium |
| CN112182765B (en) * | 2020-09-30 | 2023-05-23 | 中车长春轨道客车股份有限公司 | Noise data acquisition method and device |
| CN116256179B (en) * | 2023-01-07 | 2023-10-27 | 深圳市超越科技开发有限公司 | Vehicle fault diagnosis method, system and storage medium |
| CN117755345A (en) * | 2023-12-21 | 2024-03-26 | 北京谛声科技有限责任公司 | High-speed railway running part working condition load recording system based on voiceprint characteristics |
-
2024
- 2024-08-01 CN CN202411050242.1A patent/CN118565870B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106198062A (en) * | 2016-07-27 | 2016-12-07 | 哈尔滨市科佳通用机电有限公司 | The vehicle-mounted acoustic testing system of track vehicle fault and detection method |
| CN109211556A (en) * | 2018-10-19 | 2019-01-15 | 广州益牛科技有限公司 | A kind of track vehicle components detection system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118565870A (en) | 2024-08-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Advances of research on high-speed railway catenary | |
| CN118565870B (en) | Rail transit standard motor train unit high-voltage equipment monitoring method and device | |
| Song et al. | Accurate demagnetization faults detection of dual-sided permanent magnet linear motor using enveloping and time-domain energy analysis | |
| CN110926778A (en) | Mechanical fault diagnosis method for gas insulated switchgear assembly based on abnormal vibration | |
| CN112307950A (en) | Detail feature extraction and intelligent analysis method for GIS vibration defect identification | |
| CN106199305A (en) | Underground coal mine electric power system dry-type transformer insulation health state evaluation method | |
| El-Hag | Application of machine learning in outdoor insulators condition monitoring and diagnostics | |
| CN103076168A (en) | Diagnosis method for mechanical faults of circuit breaker | |
| CN112990678B (en) | Icing early warning judgment method based on multi-source data fusion | |
| CN115796059A (en) | Electrical equipment service life prediction method and system based on deep learning | |
| CN104390710A (en) | Power transmission line conductive wire temperature online detection system and method | |
| CN108844612A (en) | A kind of identification method of transformer internal faults based on mathematical statistics probabilistic model | |
| CN118777794B (en) | A monitoring and alarm system for power lines | |
| CN118380013A (en) | A switch cabinet monitoring and fault diagnosis method based on voiceprint recognition technology | |
| CN119575016A (en) | A vehicle-mounted boost inductor monitoring simulation test system and test method thereof | |
| Zhao et al. | A structural health monitoring system of the overhead transmission line conductor | |
| CN110673024A (en) | A high-voltage circuit breaker fault early warning method based on the power Internet of things | |
| CN108871449A (en) | A kind of transmission line online monitoring system with electric field monitoring | |
| Sinha et al. | Machine learning-based explainable stator fault diagnosis in induction motor using vibration signal | |
| Zarei et al. | Broken rotor bars detection via Park's vector approach based on ANFIS | |
| CN111948528A (en) | Diagnostic method and device for opening and closing device | |
| CN110716133A (en) | High-voltage circuit breaker fault studying and judging method based on Internet of things and big data technology | |
| CN113504302A (en) | Method and system for monitoring fan blade state, electronic equipment and storage medium | |
| Liu et al. | Multi-time-scale variational mode decomposition-based robust fault diagnosis of railway point machines under multiple noises | |
| Yongxiang et al. | Gas-insulated switchgear (GIS) equipment mechanical fault detection based on feature learning of vibration signal images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |