CN113792487A - Method and device for predicting overtemperature fault of motor train unit traction system - Google Patents
Method and device for predicting overtemperature fault of motor train unit traction system Download PDFInfo
- Publication number
- CN113792487A CN113792487A CN202111075173.6A CN202111075173A CN113792487A CN 113792487 A CN113792487 A CN 113792487A CN 202111075173 A CN202111075173 A CN 202111075173A CN 113792487 A CN113792487 A CN 113792487A
- Authority
- CN
- China
- Prior art keywords
- traction system
- temperature
- data
- neural network
- overtemperature
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012423 maintenance Methods 0.000 claims abstract description 95
- 238000013528 artificial neural network Methods 0.000 claims abstract description 87
- 238000012549 training Methods 0.000 claims abstract description 83
- 238000009423 ventilation Methods 0.000 claims description 62
- 238000003062 neural network model Methods 0.000 claims description 31
- 238000004140 cleaning Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 29
- 238000005070 sampling Methods 0.000 claims description 24
- 238000001816 cooling Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 13
- 230000017525 heat dissipation Effects 0.000 description 29
- 238000010586 diagram Methods 0.000 description 21
- 230000006870 function Effects 0.000 description 13
- 239000000498 cooling water Substances 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 6
- 230000009467 reduction Effects 0.000 description 6
- 230000007547 defect Effects 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 238000012952 Resampling Methods 0.000 description 4
- 238000007664 blowing Methods 0.000 description 4
- 239000000872 buffer Substances 0.000 description 4
- 230000036541 health Effects 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 230000003449 preventive effect Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000192 social effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Electric Propulsion And Braking For Vehicles (AREA)
- Control Of Electric Motors In General (AREA)
Abstract
The invention provides a method and a device for predicting overtemperature faults of a traction system of a motor train unit, wherein the method comprises the following steps: acquiring vehicle-mounted data and weather temperature data of a motor train unit; determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and a pre-trained neural network overtemperature early warning model; the neural network overtemperature early warning model is obtained by carrying out neural network training in advance according to historical vehicle-mounted data and historical weather temperature data; and predicting the overtemperature fault according to the determined traction system temperature and the traction system temperature alarm value under different maintenance conditions. And determining the temperature of the traction system under different maintenance conditions to carry out overtemperature fault prediction, evaluating overtemperature fault risks according to overtemperature early warning results, and simultaneously carrying out early warning in real time according to the overtemperature early warning results.
Description
Technical Field
The invention relates to a fault early warning technology of a motor train unit, in particular to an overtemperature fault prediction method and device of a motor train unit traction system.
Background
The traction system overtemperature fault is one of common real vehicle faults of the motor train unit. Two main parts in the traction system of the motor train unit comprise: the motor train unit comprises a traction converter and a traction motor, wherein the traction converter and the traction motor are both likely to have overtemperature faults, and after the overtemperature faults occur, a motor train unit vehicle-mounted control system automatically cuts off the corresponding traction converter and the corresponding traction motor to protect equipment faults from being diffused through real-time monitoring once the real-time temperature exceeds an alarm value, however, partial power loss of the motor train unit after traction is cut off, and the train delay is caused.
In the prior art, a fault prediction and health management method of a motor train unit is mainly based on a threshold judgment method, namely, an early warning value which is 3-10 ℃ lower than a vehicle-mounted alarm temperature value is set for real-time early warning by obtaining the vehicle-mounted alarm temperature values of a transformer, a converter and a traction motor in a traction system, and the method has two defects: firstly, early warning trouble reports more: in practical application, after the motor train unit returns to a motor train station at night, the motor train unit with temperature early warning records in a ground system can be checked by a traction system, and due to the fact that fault early warning reported by a ground monitoring system or a data center is more and lower in accuracy, early warning and rechecking workload of each road bureau is increased; secondly, real-time intervention cannot be performed after early warning is reported, the primary repair of the motor train unit is 48 hours or 5000 +/-500 km, and after some motor train units running on the way reach early warning values, due to dirty and blocked parts of a traction system, the temperature can still be raised to a vehicle-mounted warning value, so that the motor train unit cuts off over-temperature traction parts, power is lost, late points are caused, the traveling of passengers is influenced, and adverse social effects are caused.
Disclosure of Invention
In order to overcome at least one defect in overtemperature fault early warning of a motor train unit in the prior art, the invention provides an overtemperature fault prediction method of a motor train unit traction system, which comprises the following steps:
acquiring vehicle-mounted data and weather temperature data of a motor train unit;
determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and a pre-trained neural network overtemperature early warning model; the neural network overtemperature early warning model is obtained by carrying out neural network training in advance according to historical vehicle-mounted data and historical weather temperature data;
and predicting the overtemperature fault according to the determined traction system temperature and the traction system temperature alarm value under different maintenance conditions.
In the embodiment of the present invention, the vehicle-mounted data includes: motor current, train speed, traction system temperature data and preset maintenance coefficients.
In the embodiment of the invention, the method comprises the following steps: performing neural network training according to historical vehicle-mounted data and historical weather temperature data to determine a neural network overtemperature early warning model; wherein, include:
sampling the historical vehicle-mounted data and the historical weather temperature data according to a preset sampling rate to determine training sample data of motor current square, train speed, environment temperature, traction system temperature and maintenance coefficient;
determining ventilation training sample data of a traction system according to the speed of the train and the temperature data of the traction system;
the method comprises the steps of taking the square of motor current, train speed, environment temperature, maintenance coefficient and traction system ventilation volume as input training sample data of a neural network model, taking the traction system temperature as output training sample data of the neural network model, training the GRU neural network model, and determining the neural network overtemperature early warning model.
In the embodiment of the present invention, the determining the traction system temperature under different maintenance conditions according to the vehicle-mounted data, the weather temperature data, and the pre-trained neural network over-temperature early warning model includes:
determining a maintenance coefficient, a square value of motor current, ventilation of a traction system and train speed according to the vehicle-mounted data;
and determining the temperature of the traction system under different maintenance conditions by taking the maintenance coefficient, the square value of the motor current, the ventilation quantity of the traction system, the train speed and the weather temperature data as the input of a neural network overtemperature early warning model.
In the embodiment of the invention, the overtemperature fault prediction according to the determined traction system temperature and the traction system temperature alarm value under different maintenance conditions comprises the following steps:
carrying out real-time early warning according to the determined temperature of the traction system and the temperature warning value of the traction system; and/or
And determining the cleaning operation of the cooling device of the converter of the motor train unit according to the determined temperature of the traction system and the temperature alarm value of the traction system under different maintenance conditions.
Meanwhile, the invention also provides a device for predicting the overtemperature fault of the traction system of the motor train unit, which comprises the following components:
the data acquisition module is used for acquiring vehicle-mounted data and weather temperature data of the motor train unit;
the neural network processing module is used for determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and a pre-trained neural network overtemperature early warning model; the neural network overtemperature early warning model is obtained by carrying out neural network training in advance according to historical vehicle-mounted data and historical weather temperature data;
and the early warning processing module is used for predicting the overtemperature fault according to the determined traction system temperature and the alarm value of the traction system temperature under different maintenance conditions.
In the embodiment of the present invention, the apparatus further includes: the model training module is used for carrying out neural network training according to the historical vehicle-mounted data and the historical weather temperature data to determine a neural network overtemperature early warning model; it includes:
the sampling unit is used for sampling the historical vehicle-mounted data and the historical weather temperature data according to a preset sampling rate to determine training sample data of motor current square, train speed, environment temperature, traction system temperature and maintenance coefficient;
the ventilation sample data determining unit is used for determining ventilation training sample data of the traction system according to the train speed and the temperature data of the traction system;
and the training unit is used for training the GRU neural network model by taking the square of the motor current, the train speed, the environment temperature, the maintenance coefficient and the ventilation volume of the traction system as input training sample data of the neural network model, and taking the temperature of the traction system as output training sample data of the neural network model, so as to determine the neural network overtemperature early warning model.
In an embodiment of the present invention, the neural network processing module includes:
the data processing unit is used for determining a maintenance coefficient, a square value of motor current, ventilation of a traction system and train speed according to the vehicle-mounted data;
and the model processing unit is used for taking the maintenance coefficient, the square value of the motor current, the ventilation quantity of the traction system, the train speed and the weather temperature data as the input of the neural network overtemperature early warning model and determining the temperature of the traction system under different maintenance conditions.
In the embodiment of the invention, the early warning processing module comprises:
the real-time early warning unit is used for carrying out real-time early warning according to the determined temperature of the traction system and the alarm value of the temperature of the traction system;
and the cleaning operation early warning unit is used for determining cleaning operation on the cooling device of the converter of the motor train unit according to the determined temperature of the traction system and the temperature alarm value of the traction system under different maintenance conditions.
Meanwhile, the invention also provides computer equipment which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the method when executing the computer program.
Meanwhile, the invention also provides a computer readable storage medium, and a computer program for executing the method is stored in the computer readable storage medium.
The method comprises the steps of training a deep learning neural network by utilizing the train-mounted stored traction system temperature value, train speed, motor current, environment temperature, ventilation volume data of a heat dissipation system, the conditions of maintenance procedures such as cleaning of a heat dissipation device, blowing cleaning of a filter screen, cleaning of the filter screen and the like carried out on a motor train every day, and determining the temperature of the traction system under different maintenance conditions according to the train-mounted data, weather temperature data and a trained neural network overtemperature early warning model; and predicting the overtemperature fault according to the determined temperature of the traction system and the temperature alarm value of the traction system under different maintenance conditions, evaluating the overtemperature fault risk of the traction system on the second day according to the overtemperature early warning result, avoiding the overtemperature fault of the traction system on the second day, and simultaneously carrying out early warning in real time according to the overtemperature early warning result.
In order to make the aforementioned and other objects, features and advantages of the invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for predicting an overtemperature fault of a traction system of a motor train unit provided by the invention;
FIG. 2 is a schematic diagram of an embodiment of the present invention;
FIG. 3 is a schematic diagram of an embodiment of the present invention;
FIG. 4 is a schematic illustration of an embodiment of the present invention;
FIG. 5 is a block diagram of an overtemperature fault prediction device of a traction system of a motor train unit provided by the invention;
FIG. 6 is a block diagram of an embodiment of the present invention;
FIG. 7 is a block diagram of an embodiment of the present invention;
FIG. 8 is a block diagram of an embodiment of the present invention;
FIG. 9 is a block diagram of an embodiment of the present invention;
fig. 10 is a schematic diagram of an electronic device provided in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention provides a method for predicting the overtemperature fault of a motor train unit traction system based on a deep learning neural network, aiming at the defects of the motor train unit fault prediction system in the prior art, and the method can be used for reducing the overtemperature fault risk of the traction system.
As shown in fig. 1, the invention provides a flow chart of a method for predicting an over-temperature fault of a traction system of a motor train unit, which comprises the following steps:
step S101, acquiring vehicle-mounted data and weather temperature data of a motor train unit;
step S102, determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and a pre-trained neural network overtemperature early warning model; the neural network overtemperature early warning model is obtained by carrying out neural network training in advance according to historical vehicle-mounted data and historical weather temperature data;
and S103, carrying out overtemperature fault prediction according to the determined traction system temperature and the traction system temperature alarm value under different maintenance conditions.
The method for predicting the overtemperature fault of the traction system of the motor train unit, provided by the invention, utilizes historical vehicle-mounted data and historical weather temperature data to carry out neural network training to obtain a neural network overtemperature early warning model, utilizes the neural network overtemperature early warning model to determine the temperature of the traction system under different maintenance and repair conditions, according to the predicted temperature of the traction system and the temperature alarm value of the traction system, provides a method for predicting the over-temperature fault of the traction system applied to the motor train unit, the over-temperature fault risk of the traction system on the second day can be evaluated at the night after the motor train unit enters the motor train unit, if the risk is identified, preventive maintenance measures such as cleaning of a heat dissipation device of the traction system and the like are taken at night, the over-temperature fault of the traction system on the next day is avoided, by multi-factor multivariable information fusion, the defect of high false alarm rate of a threshold model is overcome, and the early warning accuracy of the model is improved.
In the embodiment of the invention, neural network training is carried out according to historical vehicle-mounted data and historical weather temperature data to determine a neural network overtemperature early warning model; wherein, include:
sampling the historical vehicle-mounted data and the historical weather temperature data according to a preset sampling rate to determine training sample data of motor current square, train speed, environment temperature, traction system temperature and maintenance coefficient;
determining ventilation training sample data of a traction system according to the speed of the train and the temperature data of the traction system;
the method comprises the steps of taking the square of motor current, train speed, environment temperature, maintenance coefficient and traction system ventilation volume as input training sample data of a neural network model, taking the traction system temperature as output training sample data of the neural network model, training the GRU neural network model, and determining the neural network overtemperature early warning model.
Specifically, in the embodiment of the present invention, the determining the neural network overtemperature early warning model by training the neural network according to the historical vehicle data includes:
step one, extracting historical MVB vehicle-mounted data of a motor train unit in a preset time period, and screening out a traction motor stator TmotorTraction converter cooling water temperature TconverterTrain speed v, motor current ImotorAmbient temperature TenvironmentIn the embodiment of the invention, the sampling rate of the vehicle-mounted data is 5 Sample/s; maintenance cleaning data F provided by data extraction for motor train unit traction system heat dissipation devicemaintainAnd the three states are simplified as historical maintenance coefficients, namely 0 represents that the heat dissipation system is not maintained and cleaned in the previous night, 1 represents common cleaning such as cleaning or blowing and the like, and 2 represents deep cleaning such as disassembly cleaning and the like. In the embodiment of the present invention, the vehicle-mounted data includes: motor current, train speed, traction system temperature data and preset maintenance coefficients. In the embodiment, the required vehicle-mounted data is determined according to the historical MVB vehicle-mounted data of the motor train unit.
In this example, traction system temperature dataThe method comprises the following steps: traction motor stator TmotorTraction converter cooling water temperature TconverterThat is, in this embodiment, the traction motor stators T can be utilized separatelymotorTraction converter cooling water temperature TconverterAnd carrying out temperature early warning on the traction motor stator and the traction converter, thereby realizing the temperature early warning on the traction system of the motor train unit.
Step two, further data preprocessing is carried out on the collected data to be used as training data of the neural network model; the training data of the neural network model in this embodiment specifically includes: maintenance data of heat dissipation system FmaintainSquare value of motor current
Train speed v, fan draft Q of traction convertermotorAmbient temperature TenvironmentFive characteristic quantities are used as input to draw the converter cooling water temperature value Tconvert。
In the embodiment, resampling is carried out, the sampling rate is 1Sample/s, and the temperature T of the stator of the traction motor after resampling is obtainedmotorTrain speed v and motor current Imotor；
Electric current I of motormotorAfter square treatment to obtain
As one of training data of a neural network model;
in this embodiment, the ventilation data Q of the cooling system passes through the temperature T of the stator of the motor and the traction motormotorThe motor train unit speed v is obtained by judging, and the specific rule is as follows:
the ventilation quantity of the traction motor is determined by adopting the following rule:
if the speed v of the train is more than or equal to 10 and less than 60km/h, TmotorIf the temperature is more than 85 ℃, the ventilation volume of a fan of the traction motor is as follows: qmotor＝2.5m3/s；
If the train speed v is more than or equal to 60km/h, TmotorIf the temperature is more than 140 ℃, the ventilation volume of the fan of the traction motor is as follows: qmotor＝5m3/s；
If the train speed v is less than 10km/h, the ventilation volume of the draught fan of the traction motor is as follows: qmotor＝0m3/s。
The ventilation of the traction converter is determined by the following rule:
if the train speed is more than 1 v and less than 65km/h or 35 and less than or equal to TconverterIf the temperature is less than 45 ℃, the ventilation volume of a fan of the traction converter is as follows: qconverter＝2.5m3/s；
If the train speed v is more than or equal to 65km/h or TconverterIf the temperature is higher than 45 ℃, the ventilation volume of a fan of the traction converter is as follows: qconverter＝5m3/s；
If the train speed v is less than 1km/h, the fan ventilation volume of the traction converter is as follows: qconverter＝0m3/s。
The draft Q sampling rate should be set to also 1 Sample/s.
The maintenance data F of the heat dissipation system of the converter in the second stepmaintainSquare value of motor current
Train speed v, draft Q of traction motorconvertAmbient temperature TenvironmentFive characteristic quantities are used as input, and the cooling temperature value T of the traction converter is used as a cooling temperature value TconvertFor output, a GRU neural network overtemperature warning model is trained and constructed (the specific steps are as follows:
1. and (4) constructing a GRU neural network which takes the characteristic value obtained in the step two as input and takes the cooling water temperature value of the traction converter as output.
In the embodiment of the invention, the initial setting of the model training parameters comprises the following steps: the number of hidden nodes is set to 200, the feature quantity is 5, the output is 1, the gradient critical value is 1, the initial learning rate is 0.005, the learning rate reduction period is 1.25, and the learning rate reduction factor is 0.2.
2. Inputting the training sample into a GRU neural network, and completing training after the iteration times are 250 times at maximum and reach 250 times.
3. Using three days of feature values not involved in trainingInputting the prediction sample into the GRU neural network which is trained to obtain an output value TpredictWill TpredictAnd actual TrealAnd comparing and calculating the error of the root mean square RMSE, wherein the RMSE calculation formula is as follows:
4. when RMSE is less than or equal to 1.5 ℃, the GRU neural network model training is completed, when RMSE is more than 1.5 ℃, 50 hidden nodes are added, the training is continued according to 1-3, the training is stopped until RMSE is less than or equal to 1.5 ℃, and the GRU neural network model is taken for the last time.
In the embodiment of the invention, the method for constructing the temperature model of the traction motor is the same as the method for constructing the temperature model of the traction converter, namely maintenance data F of the converter cooling system in the second step is usedmaintainSquare value of motor current
Train speed v, draft Q of traction motormotorAmbient temperature TenvironmentFive characteristic quantities are used as input, and the cooling temperature value T of the traction converter is used as a cooling temperature value TmotorFor output, a GRU neural network overtemperature early warning model is trained and constructed, and the specific training steps are the same as the training process of the temperature model of the traction converter, which is not repeated herein.
In the embodiment of the present invention, the determining the traction system temperature under different maintenance conditions according to the vehicle-mounted data, the weather temperature data, and the pre-trained neural network over-temperature early warning model includes:
determining a maintenance coefficient, a square value of motor current, ventilation of a traction system and train speed according to the vehicle-mounted data;
and determining the temperature of the traction system under different maintenance conditions by taking the maintenance coefficient, the square value of the motor current, the ventilation quantity of the traction system, the train speed and the weather temperature data as the input of a neural network overtemperature early warning model.
Well-trained GRU neural netOperating line data and weather forecast data of the next day are input after the model is connected, the motor current, the speed of the motor train unit, the draught fan ventilation volume of the traction converter, the ambient temperature and the like are respectively predicted according to the operating line data and the weather forecast data by utilizing a simulation method, and the maintenance data F of the heat dissipation system of the converter at the nightmaintainSet to 0, 1 and 2, respectively. Namely, the maintenance coefficient, the square value of the motor current, the ventilation quantity of a traction system and the train speed are determined according to the vehicle-mounted data.
FmaintainRespectively setting the parameters to be 0, 1 and 2, inputting the other 4 simulation prediction characteristic quantities into a GRU neural network model to respectively obtain Tpredict0，Tpredict1，Tpredict2. And taking the maintenance coefficient, the square value of the motor current, the ventilation quantity of the traction system, the train speed and the weather temperature data as the input of the neural network overtemperature early warning model, and determining the temperature of the traction system under different maintenance conditions.
In this embodiment, when T ispredict0，Tpredict1，Tpredict2The current transformer heat dissipation device is smaller than the vehicle-mounted alarm value of the vehicle-mounted current transformer, namely the current transformer heat dissipation device is not cleaned at night;
when T ispredict0，Tpredict1，Tpredict21 value is larger than the vehicle-mounted alarm value of the vehicle-mounted converter, and the converter heat dissipation device is normally cleaned at night;
when T ispredict0，Tpredict1，Tpredict22 or 3 values are larger than the vehicle-mounted alarm value of the vehicle-mounted converter, and the converter heat dissipation device is deeply cleaned at night.
Namely, in the embodiment of the present invention, the predicting of the over-temperature fault according to the determined temperature of the traction system and the alarm value of the temperature of the traction system under different maintenance conditions includes:
carrying out real-time early warning according to the determined temperature of the traction system and the temperature warning value of the traction system; and/or
And determining the cleaning operation of the cooling device of the converter of the motor train unit according to the determined temperature of the traction system and the temperature alarm value of the traction system under different maintenance conditions.
The embodiment of the invention can evaluate the over-temperature fault risk of the traction system on the second day, if the risk is identified, preventive maintenance measures such as cleaning of a heat dissipation device of the traction system and the like are taken at night, the over-temperature fault of the traction system on the second day is avoided, the defect of high false alarm rate of the threshold model is overcome through multi-factor multivariable information fusion, and the early warning accuracy of the model is improved.
Meanwhile, when the motor current of the model, the speed of the motor train unit, the draught fan ventilation volume of the traction converter and the environment temperature are input as real-time data, the temperature of the traction system is predicted in real time, and then the over-temperature fault risk of the traction system can be predicted and alarmed in real time.
The embodiment of the invention provides a motor train unit fault prediction and health management system to realize the motor train unit traction system over-temperature fault prediction method. The method comprises the following specific steps:
step one, data screening:
extracting MVB vehicle-mounted data of the motor train unit for 52 weeks in one year and three days per week, and screening out stator temperature values T of the traction motorsmotorTraction converter cooling water temperature TconverterTrain speed v, motor current ImotorAmbient temperature TenvironmentThe sampling rate of the type of data is 5 Sample/s;
extracting maintenance cleaning data F of motor train unit traction system heat dissipation device provided by each railway administration application departmentmaintainThe method is simplified into three states, namely 0 represents that the heat dissipation system is not maintained and cleaned in the previous night, 1 represents cleaning or blowing and other common cleaning, and 2 represents disassembly cleaning and other deep cleaning.
Step two, data preprocessing:
the original sampling rate of MVB vehicle-mounted data of the motor train unit is 5Sample/s, resampling is carried out, the sampling rate is 1Sample/s, and the current I of the motor ismotorAfter square treatment to obtain
The ventilation data Q of the heat dissipation system is judged through the real-time temperature of the motor and the converter and the real-time speed of the motor train unit:
the ventilation quantity of the traction motor is determined by adopting the following rule:
if the speed v of the train is more than or equal to 10 and less than 60km/h, TmotorIf the temperature is more than 85 ℃, the ventilation volume of a fan of the traction motor is as follows: qmotor＝2.5m3/s；
If the train speed v is more than or equal to 60km/h, TmotorIf the temperature is more than 140 ℃, the ventilation volume of the fan of the traction motor is as follows: qmotor＝5m3/s；
If the train speed v is less than 10km/h, the ventilation volume of the draught fan of the traction motor is as follows: qmotor＝0m3/s。
The ventilation of the traction converter is determined by the following rule:
if the train speed is more than 1 v and less than 65km/h or 35 and less than or equal to TconverterIf the temperature is less than 45 ℃, the ventilation volume of a fan of the traction converter is as follows: qconverter＝2.5m3/s；
If the train speed v is more than or equal to 65km/h or TconverterIf the temperature is higher than 45 ℃, the ventilation volume of a fan of the traction converter is as follows: qconverter＝5m3/s；
If the train speed v is less than 1km/h, the fan ventilation volume of the traction converter is as follows: qconverter＝0m3/s。
The draft Q sampling rate should be set to also 1 Sample/s.
Fig. 2 is a schematic diagram illustrating data screening and preprocessing performed in this embodiment. And analyzing according to the communication protocol of the MVB of the motor train unit, and screening out target parameters. The 8-group motor train unit has 4 converters, 4 converters with cooling water temperature data, 1 speed signal, 16 motors with current data, and only 1 ambient temperature. The purpose of data resampling is to reduce the amount of calculation and improve the training speed of the deep learning neural network, and the data should be resampled from 5Sample/s to 1 Sample/s. The draught fan ventilation volume of the traction converter is vehicle-mounted inherent logic, the draught fan ventilation volume can be obtained through deduction of speed and water temperature of the converter, and maintenance history data of each motor car can be consulted according to maintenance data of the heat dissipation device of the converter.
Step three: step two, maintaining data F of the heat dissipation system of the convertermaintainSquare value of motor current
Train speed v, fan draft Q of traction converterconvertAmbient temperature TenvironmentFive characteristic quantities are used as input, and the cooling water temperature value Q of the traction converter is usedconvertThe method comprises the following specific steps of constructing a GRU neural network overtemperature early warning model for output (the construction method of the temperature model of the traction motor is the same and is not described in detail):
1. constructing a GRU neural network which takes the characteristic value obtained in the step two as input and the cooling water temperature value of the traction converter as output, wherein 200 hidden nodes are set, the characteristic quantity is 5, the output is 1, the gradient critical value is 1, the initial learning rate is 0.005, the learning rate reduction period is 1.25, and the learning rate reduction factor is 0.2;
2. inputting the training sample into a GRU neural network, and completing training after the iteration times are 250 times at maximum and reach 250 times.
3. Using three days of feature values which do not participate in training as prediction samples to be input into the GRU neural network which is trained to obtain an output value TpredictWill TpredictAnd actual TrealAnd comparing and calculating the root mean square RMSE error, wherein the RMSE calculation formula is as follows:
4. when RMSE is less than or equal to 1.5 ℃, the GRU neural network model training is completed, when RMSE is more than 1.5 ℃, 50 hidden nodes are added, the training is continued according to 1-3, the training is stopped until RMSE is less than or equal to 1.5 ℃, and the GRU neural network model is taken for the last time.
Fig. 3 is a schematic diagram of neural network training performed in this embodiment. In the model of this embodiment, 5 inputs and 1 output are established, the number of nodes is 200 GRU neural networks, 200 hidden nodes are set, the feature quantity is 5, the output is 1, the gradient critical value is 1, the initial learning rate is 0.005, the learning rate reduction period is 1.25, the learning rate reduction factor is 0.2, the iteration frequency is 250 times at most, the training is completed after 250 times, the RMSE value is calculated, the training is completed if the RMSE value is less than 1.5 ℃, and 50 nodes are increased each time if the RMSE value is greater than 1.5 ℃ until the training is completed if the RMSE value is less than 1.5 ℃.
Step four: the trained GRU neural network model is deployed in a motor train unit fault prediction and health management system, after the motor train unit is put in storage, operating line data and weather forecast data of the next day are input, and the motor current, the motor train unit speed, the fan ventilation volume of a traction converter, the ambient temperature and the like are respectively predicted through simulation.
In this embodiment, maintenance data F of the converter cooling system at nightmaintainSet to 0, 1 and 2, respectively.
Step five: fmaintainRespectively setting the parameters to be 0, 1 and 2, inputting the other 4 simulation prediction characteristic quantities into a GRU neural network model to respectively obtain Tpredict0，Tpredict1，Tpredict2。
When T ispredict0，Tpredict1，Tpredict2The current transformer heat dissipation device is smaller than the vehicle-mounted alarm value of the vehicle-mounted current transformer, namely the current transformer heat dissipation device is not cleaned at night;
when T ispredict0，Tpredict1，Tpredict21 value is larger than the vehicle-mounted alarm value of the vehicle-mounted converter, and the converter heat dissipation device is normally cleaned at night;
when T ispredict0，Tpredict1，Tpredict22 or 3 values are larger than the vehicle-mounted alarm value of the vehicle-mounted converter, and the converter heat dissipation device is deeply cleaned at night.
Fig. 4 is a schematic diagram of prediction by using a trained audit network model in this embodiment. The well-trained GRU nerveThe network model is deployed in a motor train unit fault prediction and health management system, after the motor train unit is put in storage, operating line data and weather forecast data of the next day are input, the motor current, the speed of the motor train unit, the ventilation volume of a draught fan of a traction converter, the ventilation volume of the environment temperature and the like are respectively predicted, and the maintenance data F of the heat dissipation system of the current transformer at nightmaintainAnd respectively setting the characteristic values as 0, 1 and 2, inputting the characteristic values into a GRU neural network, comparing the obtained water temperature value of the converter with a vehicle-mounted alarm value, and taking corresponding preventive maintenance measures for the heat dissipation device of the traction system according to the comparison result.
The invention utilizes the conditions of maintenance procedures such as traction system temperature value, train speed, motor current, environment temperature, ventilation volume data of a heat dissipation system, heat dissipation device cleaning, filter screen blowing cleaning, filter screen cleaning and the like carried out on a motor train unit every day, training a deep learning GRU neural network, then deploying the deep learning GRU neural network into a large data system of the motor train unit, after the motor train unit finishes the operation task on the current day and returns to the motor train station, importing the line data, the target speed and the weather forecast temperature to be operated on the next day, obtaining the predicted train speed, the motor current, the ambient temperature and the ventilation volume of the heat dissipation system, inputting the predicted train speed, the predicted motor current, the predicted ambient temperature and the predicted ventilation volume of the heat dissipation system into the deep learning GRU neural network, evaluating the over-temperature fault risk of the traction system on the second day, if the risk is identified, preventive maintenance measures such as cleaning of a heat dissipation device of the traction system and the like are started at night, and the over-temperature fault of the traction system on the next day is avoided.
Meanwhile, the invention also provides a device for predicting the overtemperature fault of the traction system of the motor train unit, as shown in fig. 5, comprising:
the data acquisition module 501 is used for acquiring vehicle-mounted data and weather temperature data of the motor train unit;
the neural network processing module 502 is used for determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and a pre-trained neural network overtemperature early warning model; the neural network overtemperature early warning model is obtained by carrying out neural network training in advance according to historical vehicle-mounted data and historical weather temperature data;
and the early warning processing module 503 is configured to perform over-temperature fault prediction according to the determined traction system temperature and the alarm value of the traction system temperature under different maintenance conditions.
As shown in fig. 6, in the embodiment of the present invention, the apparatus further includes: and the model training module 504 is used for performing neural network training according to the historical vehicle-mounted data and the historical weather temperature data to determine a neural network overtemperature early warning model.
Further, as shown in fig. 7, the model training module 504 includes:
the sampling unit 5041 is used for sampling the historical vehicle-mounted data and the historical weather temperature data according to a preset sampling rate to determine training sample data of motor current square, train speed, ambient temperature, traction system temperature and maintenance coefficient;
the ventilation sample data determining unit 5042 is used for determining the training sample data of the ventilation of the traction system according to the train speed and the temperature data of the traction system;
and the training unit 5043 is used for training the GRU neural network model by taking the square of the motor current, the train speed, the environment temperature, the maintenance coefficient and the traction system ventilation volume as input training sample data of the neural network model, and taking the traction system temperature as output training sample data of the neural network model, so as to determine the neural network overtemperature early warning model.
As shown in fig. 8, in the embodiment of the present invention, the neural network processing module 502 includes:
the data processing unit 5021 is used for determining a maintenance coefficient, a square value of motor current, ventilation of a traction system and train speed according to the vehicle-mounted data;
and the model processing unit 5022 is used for taking the maintenance coefficient, the square value of the motor current, the ventilation volume of the traction system, the train speed and the weather temperature data as the input of the neural network overtemperature early warning model and determining the temperature of the traction system under different maintenance conditions.
As shown in fig. 9, in the embodiment of the present invention, the early warning processing module 503 includes:
the real-time early warning unit 5031 is used for carrying out real-time early warning according to the determined temperature of the traction system and the alarm value of the temperature of the traction system;
the cleaning operation early warning unit 5032 is used for determining the cleaning operation on the cooling device of the converter of the motor train unit according to the determined temperature of the traction system and the temperature alarm value of the traction system under different maintenance conditions.
Meanwhile, the embodiment also provides an electronic device, which may be a desktop computer, a tablet computer, a mobile terminal, and the like, but the embodiment is not limited thereto. In this embodiment, the electronic device may refer to the embodiments of the method and the apparatus, and the contents thereof are incorporated herein, and repeated descriptions are omitted.
Fig. 10 is a schematic block diagram of a system configuration of an electronic apparatus 600 according to an embodiment of the present invention. As shown in fig. 10, the electronic device 600 may include a central processor 100 and a memory 140; the memory 140 is coupled to the central processor 100. Notably, this diagram is exemplary; other types of structures may also be used in addition to or in place of the structure to implement telecommunications or other functions.
In one embodiment, the over-temperature fault prediction function of the traction system of the motor train unit can be integrated into the central processor 100. The central processor 100 may be configured to control as follows:
acquiring vehicle-mounted data and weather temperature data of a motor train unit;
determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and a pre-trained neural network overtemperature early warning model; the neural network overtemperature early warning model is obtained by carrying out neural network training in advance according to historical vehicle-mounted data and historical weather temperature data;
and predicting the overtemperature fault according to the determined traction system temperature and the traction system temperature alarm value under different maintenance conditions.
Wherein, the vehicle-mounted data comprises: motor current, train speed, traction system temperature data and preset maintenance coefficients.
Wherein, the method comprises the following steps: performing neural network training according to historical vehicle-mounted data and historical weather temperature data to determine a neural network overtemperature early warning model; wherein, include:
sampling the historical vehicle-mounted data and the historical weather temperature data according to a preset sampling rate to determine training sample data of motor current square, train speed, environment temperature, traction system temperature and maintenance coefficient;
determining ventilation training sample data of a traction system according to the speed of the train and the temperature data of the traction system;
the method comprises the steps of taking the square of motor current, train speed, environment temperature, maintenance coefficient and traction system ventilation volume as input training sample data of a neural network model, taking the traction system temperature as output training sample data of the neural network model, training the GRU neural network model, and determining the neural network overtemperature early warning model.
Wherein, the step of determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and the pre-trained neural network overtemperature early warning model comprises the following steps:
determining a maintenance coefficient, a square value of motor current, ventilation of a traction system and train speed according to the vehicle-mounted data;
and determining the temperature of the traction system under different maintenance conditions by taking the maintenance coefficient, the square value of the motor current, the ventilation quantity of the traction system, the train speed and the weather temperature data as the input of a neural network overtemperature early warning model.
The overtemperature fault prediction method based on the determined traction system temperature and the traction system temperature alarm value under different maintenance conditions comprises the following steps:
carrying out real-time early warning according to the determined temperature of the traction system and the temperature warning value of the traction system; and/or
And determining the cleaning operation of the cooling device of the converter of the motor train unit according to the determined temperature of the traction system and the temperature alarm value of the traction system under different maintenance conditions.
In another embodiment, the motor train unit traction system over-temperature fault prediction device may be configured separately from the central processing unit 100, for example, the motor train unit traction system over-temperature fault prediction device may be configured as a chip connected to the central processing unit 100, and the motor train unit traction system over-temperature fault prediction function is realized through the control of the central processing unit.
As shown in fig. 10, the electronic device 600 may further include: communication module 110, input unit 120, audio processing unit 130, display 160, power supply 170. It is noted that the electronic device 600 does not necessarily include all of the components shown in FIG. 10; furthermore, the electronic device 600 may also comprise components not shown in fig. 10, which may be referred to in the prior art.
As shown in fig. 10, the central processor 100, sometimes referred to as a controller or operational control, may include a microprocessor or other processor device and/or logic device, the central processor 100 receiving input and controlling the operation of the various components of the electronic device 600.
The memory 140 may be, for example, one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. The information relating to the failure may be stored, and a program for executing the information may be stored. And the central processing unit 100 may execute the program stored in the memory 140 to realize information storage or processing, etc.
The input unit 120 provides input to the cpu 100. The input unit 120 is, for example, a key or a touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display an object to be displayed, such as an image or a character. The display may be, for example, an LCD display, but is not limited thereto.
The memory 140 may be a solid state memory such as Read Only Memory (ROM), Random Access Memory (RAM), a SIM card, or the like. There may also be a memory that holds information even when power is off, can be selectively erased, and is provided with more data, an example of which is sometimes called an EPROM or the like. The memory 140 may also be some other type of device. Memory 140 includes buffer memory 141 (sometimes referred to as a buffer). The memory 140 may include an application/function storage section 142, and the application/function storage section 142 is used to store application programs and function programs or a flow for executing the operation of the electronic device 600 by the central processing unit 100.
The memory 140 may also include a data store 143, the data store 143 for storing data, such as contacts, digital data, pictures, sounds, and/or any other data used by the electronic device. The driver storage portion 144 of the memory 140 may include various drivers of the electronic device for communication functions and/or for performing other functions of the electronic device (e.g., messaging application, address book application, etc.).
The communication module 110 is a transmitter/receiver 110 that transmits and receives signals via an antenna 111. The communication module (transmitter/receiver) 110 is coupled to the central processor 100 to provide an input signal and receive an output signal, which may be the same as in the case of a conventional mobile communication terminal.
Based on different communication technologies, a plurality of communication modules 110, such as a cellular network module, a bluetooth module, and/or a wireless local area network module, may be provided in the same electronic device. The communication module (transmitter/receiver) 110 is also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and receive audio input from the microphone 132 to implement general telecommunications functions. Audio processor 130 may include any suitable buffers, decoders, amplifiers and so forth. In addition, an audio processor 130 is also coupled to the central processor 100, so that recording on the local can be enabled through a microphone 132, and so that sound stored on the local can be played through a speaker 131.
The embodiment of the invention also provides a computer readable program, wherein when the program is executed in electronic equipment, the program enables a computer to execute the method for predicting the overtemperature fault of the traction system of the motor train unit in the electronic equipment.
The embodiment of the invention also provides a storage medium stored with a computer readable program, wherein the computer readable program enables a computer to execute the overtemperature fault prediction of the traction system of the motor train unit in the electronic device.
The preferred embodiments of the present invention have been described above with reference to the accompanying drawings. The many features and advantages of the embodiments are apparent from the detailed specification, and thus, it is intended by the appended claims to cover all such features and advantages of the embodiments that fall within the true spirit and scope thereof. Further, since numerous modifications and changes will readily occur to those skilled in the art, it is not desired to limit the embodiments of the invention to the exact construction and operation illustrated and described, and accordingly, all suitable modifications and equivalents may be resorted to, falling within the scope thereof.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (12)
1. The method for predicting the overtemperature fault of the traction system of the motor train unit is characterized by comprising the following steps:
acquiring vehicle-mounted data and weather temperature data of a motor train unit;
determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and a pre-trained neural network overtemperature early warning model; the neural network overtemperature early warning model is obtained by carrying out neural network training in advance according to historical vehicle-mounted data and historical weather temperature data;
and predicting the overtemperature fault according to the determined traction system temperature and the traction system temperature alarm value under different maintenance conditions.
2. The method for predicting the overtemperature fault of the traction system of the motor train unit according to claim 1, wherein the vehicle-mounted data comprises: motor current, train speed, traction system temperature data and preset maintenance coefficients.
3. The method for predicting the overtemperature fault of the traction system of the motor train unit as claimed in claim 2, wherein the method comprises the following steps: performing neural network training according to historical vehicle-mounted data and historical weather temperature data to determine a neural network overtemperature early warning model; wherein, include:
sampling the historical vehicle-mounted data and the historical weather temperature data according to a preset sampling rate to determine training sample data of motor current square, train speed, environment temperature, traction system temperature and maintenance coefficient;
determining ventilation training sample data of a traction system according to the speed of the train and the temperature data of the traction system;
the method comprises the steps of taking the square of motor current, train speed, environment temperature, maintenance coefficient and traction system ventilation volume as input training sample data of a neural network model, taking the traction system temperature as output training sample data of the neural network model, training the GRU neural network model, and determining the neural network overtemperature early warning model.
4. The method for predicting the overtemperature fault of the traction system of the motor train unit according to claim 1, wherein the step of determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and the pre-trained neural network overtemperature early warning model comprises the following steps:
determining a maintenance coefficient, a square value of motor current, ventilation of a traction system and train speed according to the vehicle-mounted data;
and determining the temperature of the traction system under different maintenance conditions by taking the maintenance coefficient, the square value of the motor current, the ventilation quantity of the traction system, the train speed and the weather temperature data as the input of a neural network overtemperature early warning model.
5. The method for predicting the overtemperature fault of the traction system of the motor train unit according to the claim 1, wherein the step of predicting the overtemperature fault according to the determined temperature of the traction system and the temperature alarm value of the traction system under different maintenance conditions comprises the following steps:
carrying out real-time early warning according to the determined temperature of the traction system and the temperature warning value of the traction system; and/or
And determining the cleaning operation of the cooling device of the converter of the motor train unit according to the determined temperature of the traction system and the temperature alarm value of the traction system under different maintenance conditions.
6. The overtemperature fault prediction device for the traction system of the motor train unit is characterized by comprising the following steps of:
the data acquisition module is used for acquiring vehicle-mounted data and weather temperature data of the motor train unit;
the neural network processing module is used for determining the temperature of the traction system under different maintenance conditions according to the vehicle-mounted data, the weather temperature data and a pre-trained neural network overtemperature early warning model; the neural network overtemperature early warning model is obtained by carrying out neural network training in advance according to historical vehicle-mounted data and historical weather temperature data;
and the early warning processing module is used for predicting the overtemperature fault according to the determined traction system temperature and the alarm value of the traction system temperature under different maintenance conditions.
7. The device for predicting the overtemperature fault of the traction system of the motor train unit according to claim 6, wherein the vehicle-mounted data comprises: motor current, train speed, traction system temperature data and preset maintenance coefficients.
8. The device for predicting the overtemperature fault of the traction system of the motor train unit according to claim 7, further comprising: the model training module is used for carrying out neural network training according to the historical vehicle-mounted data and the historical weather temperature data to determine a neural network overtemperature early warning model; it includes:
the sampling unit is used for sampling the historical vehicle-mounted data and the historical weather temperature data according to a preset sampling rate to determine training sample data of motor current square, train speed, environment temperature, traction system temperature and maintenance coefficient;
the ventilation sample data determining unit is used for determining ventilation training sample data of the traction system according to the train speed and the temperature data of the traction system;
and the training unit is used for training the GRU neural network model by taking the square of the motor current, the train speed, the environment temperature, the maintenance coefficient and the ventilation volume of the traction system as input training sample data of the neural network model, and taking the temperature of the traction system as output training sample data of the neural network model, so as to determine the neural network overtemperature early warning model.
9. The device for predicting the overtemperature fault of the traction system of the motor train unit according to claim 6, wherein the neural network processing module comprises:
the data processing unit is used for determining a maintenance coefficient, a square value of motor current, ventilation of a traction system and train speed according to the vehicle-mounted data;
and the model processing unit is used for taking the maintenance coefficient, the square value of the motor current, the ventilation quantity of the traction system, the train speed and the weather temperature data as the input of the neural network overtemperature early warning model and determining the temperature of the traction system under different maintenance conditions.
10. The motor train unit traction system overtemperature fault prediction device of claim 6, wherein the early warning processing module comprises:
the real-time early warning unit is used for carrying out real-time early warning according to the determined temperature of the traction system and the alarm value of the temperature of the traction system; and/or
And the cleaning operation early warning unit is used for determining cleaning operation on the cooling device of the converter of the motor train unit according to the determined temperature of the traction system and the temperature alarm value of the traction system under different maintenance conditions.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the method of any of claims 1 to 5 when executing the computer program.
12. A computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program for executing the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111075173.6A CN113792487B (en) | 2021-09-14 | 2021-09-14 | Method and device for predicting overtemperature fault of traction system of motor train unit |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111075173.6A CN113792487B (en) | 2021-09-14 | 2021-09-14 | Method and device for predicting overtemperature fault of traction system of motor train unit |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113792487A true CN113792487A (en) | 2021-12-14 |
| CN113792487B CN113792487B (en) | 2024-02-02 |
Family
ID=78880188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111075173.6A Active CN113792487B (en) | 2021-09-14 | 2021-09-14 | Method and device for predicting overtemperature fault of traction system of motor train unit |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113792487B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019017991A1 (en) * | 2017-07-21 | 2019-01-24 | Quantumscape Corporation | Predictive model for estimating battery states |
| CN109752651A (en) * | 2017-11-03 | 2019-05-14 | 株洲中车时代电气股份有限公司 | A kind of method and system of traction electric machine overtemperature failure predication |
| CN111204363A (en) * | 2020-04-23 | 2020-05-29 | 湖南中车时代通信信号有限公司 | Fault diagnosis early warning and state evaluation method, device and system for traction system |
| WO2021097604A1 (en) * | 2019-11-18 | 2021-05-27 | 株洲中车时代电气股份有限公司 | Multi-information fusion-based fault early warning method and device for converter |
-
2021
- 2021-09-14 CN CN202111075173.6A patent/CN113792487B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019017991A1 (en) * | 2017-07-21 | 2019-01-24 | Quantumscape Corporation | Predictive model for estimating battery states |
| CN109752651A (en) * | 2017-11-03 | 2019-05-14 | 株洲中车时代电气股份有限公司 | A kind of method and system of traction electric machine overtemperature failure predication |
| WO2021097604A1 (en) * | 2019-11-18 | 2021-05-27 | 株洲中车时代电气股份有限公司 | Multi-information fusion-based fault early warning method and device for converter |
| CN111204363A (en) * | 2020-04-23 | 2020-05-29 | 湖南中车时代通信信号有限公司 | Fault diagnosis early warning and state evaluation method, device and system for traction system |
Non-Patent Citations (2)
| Title |
|---|
| 刘峰;刘海生;: "基于改进小波神经网络的动车组牵引电机故障趋势预测", 制造业自动化, no. 07 * |
| 顾佳;黄明;关岳;: "高速列车牵引变流器故障诊断研究", 振动.测试与诊断, no. 05 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113792487B (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9953517B2 (en) | Risk early warning method and apparatus | |
| US20160370333A1 (en) | Generating fine resolution air pollution estimates | |
| CN106934107A (en) | Traffic trip scenario building method, device, equipment and storage medium | |
| CA3028216A1 (en) | Method and system for monitoring and assessing road conditions | |
| CN112434260A (en) | Road traffic state detection method and device, storage medium and terminal | |
| CN115100848A (en) | Travel tracing method and system for ground traffic congestion | |
| CN112799950A (en) | Background service load capacity test system and method, storage medium and electronic device | |
| US11816543B2 (en) | System and method for using knowledge gathered by a vehicle | |
| CN113159408B (en) | Rail transit station passenger flow prediction method and device | |
| CN113792487B (en) | Method and device for predicting overtemperature fault of traction system of motor train unit | |
| CN111105070B (en) | Passenger flow early warning method and system | |
| CN117169744A (en) | Method, system, equipment and medium for estimating residual electric quantity of electric automobile | |
| CN116795720A (en) | Unmanned driving system credibility evaluation method and device based on scene | |
| US20180089909A1 (en) | Smart odometer | |
| CN110363320B (en) | Method and device for predicting estimated arrival time and computing equipment | |
| CN116453541A (en) | Sound source intensity prediction method and device, electronic equipment and storage medium | |
| JP2020021305A (en) | Information processing method, server and program | |
| CN114757418A (en) | Training method, system and equipment for sharing bicycle demand prediction model | |
| CN115222265A (en) | Method and device for determining railway full-line track state | |
| CN115202691A (en) | Remote upgrading method and system based on vehicle end FOTA | |
| CN114331206A (en) | Point location addressing method and device, electronic equipment and readable storage medium | |
| CN111327449A (en) | Method, device, equipment and medium for determining network abnormity | |
| Portilla et al. | Decentralized model-based predictive control for urban traffic control | |
| CN112381560B (en) | Shared equipment product market prediction system and method | |
| CN115729812B (en) | Test method, electronic device and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20231007 Address after: 100038 No. 10 Fuxing Road, Haidian District, Beijing Applicant after: China National Railway Group Co.,Ltd. Applicant after: CHINA ACADEMY OF RAILWAY SCIENCES Corp.,Ltd. Applicant after: LOCOMOTIVE & CAR RESEARCH INSTITUTE OF CHINA ACADEMY OF RAILWAY SCIENCES Corp.,Ltd. Applicant after: BEIJING ZONGHENG ELECTRO-MECHANICAL TECHNOLOGY Co.,Ltd. Address before: 100081 Beijing city Haidian District Daliushu Road No. 2 Applicant before: CHINA ACADEMY OF RAILWAY SCIENCES Corp.,Ltd. Applicant before: LOCOMOTIVE & CAR RESEARCH INSTITUTE OF CHINA ACADEMY OF RAILWAY SCIENCES Corp.,Ltd. Applicant before: BEIJING ZONGHENG ELECTRO-MECHANICAL TECHNOLOGY Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |