A method, device, system and medium for diagnosing abnormal temperature of an electromagnet of a maglev train

Abstract

The present invention discloses a method, device, system and computer-readable storage medium for diagnosing abnormal temperature of an electromagnet of a maglev train, which is applied to the technical field of maglev trains. The method includes collecting the working condition data of the train; analyzing the working condition data according to a pre-established abnormal temperature diagnosis model of the electromagnet to obtain an output result, wherein the abnormal temperature diagnosis model of the electromagnet is established based on historical working condition data; determining the state of the electromagnet based on the output result. During use, the problem of inaccurate diagnosis results of abnormal temperature of the electromagnet in the prior art can be solved, the diagnosis accuracy is improved, and it is beneficial to improve the operation safety of the maglev train.

Description

Technical Field

[0001] The present invention relates to the technical field of maglev trains, and particularly to a method, device, system and computer-readable storage medium for diagnosing abnormal temperature of an electromagnet of a maglev train. Background Art

[0002] When a maglev train is running in a suspended state, the coils of the suspension electromagnets need to pass a certain amount of current to balance the suspension load and external disturbances, such as pneumatic load disturbances, vehicle dynamics disturbances caused by track unevenness, etc. Since there is resistance in the electromagnet coils, the suspension current will generate joule heat on the resistance of the electromagnet coils. When the maglev train operates for a long time, the accumulation of these heats will cause the temperature of the electromagnet coils to rise, and the increase in temperature will cause the coil resistance to further increase, thereby generating more heat. When the temperature rises to a certain level, the surface insulating material of the winding of the suspension-controlled electromagnet coil will be damaged, resulting in serious faults such as inter-turn short circuit of the electromagnet and even burnout of the electromagnet. Therefore, how to monitor and diagnose the temperature of the electromagnets of maglev trains is of great significance for train operation safety. In the prior art, the status diagnosis is usually carried out according to the monitored temperature threshold of the maglev train electromagnets, resulting in inaccurate diagnosis results.

[0003] In view of this, how to provide a more accurate method, device, system and computer-readable storage medium for diagnosing abnormal temperature of an electromagnet of a maglev train has become a problem to be solved by those skilled in the art. Summary of the Invention

[0004] The purpose of the embodiments of the present invention is to provide a method, device, system and computer-readable storage medium for diagnosing abnormal temperature of an electromagnet of a maglev train, which can improve the diagnosis accuracy during use and is beneficial to improving the operation safety of maglev trains.

[0005] To solve the above technical problems, the embodiments of the present invention provide a method for diagnosing abnormal temperature of an electromagnet of a maglev train, including:

[0006] Collecting the working condition data of the train;

[0007] Analyzing the working condition data according to a pre-established abnormal temperature diagnosis model of the electromagnet to obtain an output result; wherein, the abnormal temperature diagnosis model of the electromagnet is established based on historical working condition data;

[0008] Determining the state of the electromagnet based on the output result.

[0009] Optionally, establishing the abnormal temperature diagnosis model of the electromagnet based on historical working condition data includes:

[0010] Obtaining the data in each levitation-to-dropping process in the historical working condition data as each sample;

[0011] Determine normal operating condition samples and fault condition samples from each of the said samples;

[0012] Train the temperature diagnosis model based on the said normal operating condition samples and fault condition samples to obtain a trained electromagnet temperature anomaly diagnosis model;

[0013] Then, the acquisition of the operating condition data of the train includes:

[0014] Acquire the operating condition data of the train between levitation and lowering of the car body.

[0015] Optionally, the training of the temperature diagnosis model based on the said normal operating condition samples and fault condition samples to obtain a trained electromagnet temperature anomaly diagnosis model includes:

[0016] Establish augmented fault samples based on the said normal operating condition samples and the said fault condition samples;

[0017] Establish a sample library according to the said normal operating condition samples, the said fault condition samples and the said augmented fault samples;

[0018] Use the said sample library to train the temperature diagnosis model to obtain a trained electromagnet temperature anomaly diagnosis model.

[0019] Optionally, the establishment of augmented fault samples based on the said normal operating condition samples and the said fault condition samples includes:

[0020] For each of the said normal operating condition samples, calculate the distances from the said normal operating condition sample to each of the said fault condition samples;

[0021] Obtain the scores of the said normal operating condition samples according to the respective distances;

[0022] Determine target operating condition samples from each of the said normal operating condition samples according to the scores of each of the said normal operating condition samples;

[0023] Use the said target operating condition samples as augmented fault samples.

[0024] Optionally, the obtaining of the scores of the said normal operating condition samples according to the respective distances includes:

[0025] Take the average distance of the respective distances as the score of the said normal operating condition sample.

[0026] Optionally, the calculation of the distances from the said normal operating condition sample to each of the said fault condition samples includes:

[0027] Calculate the Euclidean distances from the said normal operating condition sample to each of the said fault condition samples.

[0028] Optionally, determining the target operating condition samples from each of the normal operating condition samples according to the scores of each of the normal operating condition samples includes:

[0029] Sorting the scores of each of the normal operating condition samples in descending order;

[0030] Taking the preset number of normal operating condition samples with the smallest average distance as the target operating condition samples.

[0031] Optionally, establishing a sample library according to the normal operating condition samples, the fault operating condition samples, and the extended fault samples includes:

[0032] Taking the fault operating condition samples and the extended fault samples as the fault operating condition sample library;

[0033] Taking each of the normal operating condition samples other than the target operating condition samples among each of the normal operating condition samples as the normal operating condition sample base library;

[0034] Extracting normal operating condition samples in a preset proportion to the number of fault operating condition samples from the normal operating condition sample base library as the normal operating condition sample library;

[0035] Establishing a final sample library based on the normal operating condition sample library and the fault operating condition sample library.

[0036] Optionally, both the normal operating condition samples and the fault operating condition samples include various types of parameters;

[0037] Then, calculating the distances from the normal operating condition samples to each of the fault operating condition samples includes:

[0038] For each of the fault operating condition samples, calculating the sub-distances between each type of parameter in the normal operating condition samples and the corresponding type of parameter in the fault operating condition samples;

[0039] Calculating the distances between the normal operating condition samples and the fault operating condition samples according to the respective sub-distances and the weights corresponding to each type of parameter.

[0040] Optionally, the various types of parameters include any combination of any of the surface temperature of the electromagnet, the internal temperature of the electromagnet, the ambient temperature, the difference between the surface temperature of the electromagnet and the ambient temperature, and the difference between the internal temperature of the electromagnet and the ambient temperature.

[0041] An embodiment of the present invention further provides a magnetic levitation train electromagnet temperature anomaly diagnosis device, including:

[0042] An acquisition module for acquiring the operating condition data of the train;

[0043] An analysis module for analyzing the working condition data according to a pre - established abnormal electromagnet temperature diagnosis model to obtain an output result, wherein the abnormal electromagnet temperature diagnosis model is established based on historical working condition data;

[0044] A determination module for determining the temperature state of the electromagnet based on the output result.

[0045] An embodiment of the present invention also provides a method for diagnosing abnormal temperature of an electromagnet of a maglev train, including:

[0046] A memory for storing a computer program;

[0047] A processor for implementing the steps of the method for diagnosing abnormal temperature of an electromagnet of a maglev train as described above when executing the computer program.

[0048] An embodiment of the present invention also provides a computer - readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for diagnosing abnormal temperature of an electromagnet of a maglev train as described above are implemented.

[0049] An embodiment of the present invention provides a method, device, system and computer - readable storage medium for diagnosing abnormal temperature of an electromagnet of a maglev train. The method includes: collecting the working condition data of the train; analyzing the working condition data according to a pre - established abnormal electromagnet temperature diagnosis model to obtain an output result, wherein the abnormal electromagnet temperature diagnosis model is established based on historical working condition data; determining the electromagnet state based on the output result.

[0050] It can be seen that in the embodiment of the present invention, an abnormal electromagnet temperature diagnosis model is pre - established based on historical working condition data, then the working condition data of the train is collected during the operation of the maglev train, and then the abnormal electromagnet temperature diagnosis model is used to analyze the working condition data to obtain an output result, and the electromagnet state is determined based on the output result, which can improve the diagnosis accuracy and is beneficial to improving the operation safety of the maglev train. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the prior art and the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a schematic flowchart of a method for diagnosing abnormal temperature of an electromagnet of a maglev train provided by an embodiment of the present invention;

[0053] Figure 2The structural schematic diagram of a temperature anomaly diagnosis device for an electromagnet of a maglev train provided by an embodiment of the present invention. Specific embodiments

[0054] An embodiment of the present invention provides a temperature anomaly diagnosis method, device, system and computer-readable storage medium for an electromagnet of a maglev train, which can improve the diagnosis accuracy during use and is beneficial to improving the operation safety of the maglev train.

[0055] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0056] Please refer to Figure 1 , Figure 1 The flowchart of a temperature anomaly diagnosis method for an electromagnet of a maglev train provided by an embodiment of the present invention. The method includes:

[0057] S110: Collect the operating condition data of the train;

[0058] It should be noted that since the temperature of the electromagnet of the maglev train is closely related to the specific operating conditions, and the change trend of the electromagnet temperature is different under different operating conditions, the operating condition data of the train can be collected during the operation of the train.

[0059] S120: Analyze the operating condition data according to a pre-established temperature anomaly diagnosis model for the electromagnet to obtain an output result; wherein, the temperature anomaly diagnosis model for the electromagnet is established based on historical operating condition data;

[0060] It should be noted that in practical applications, the historical operating condition data of the maglev train can be obtained in advance, and then a temperature anomaly diagnosis model for the electromagnet is established based on the historical operating condition data, and during the operation of the train, the collected operating condition data is analyzed through the temperature anomaly diagnosis model for the electromagnet to obtain the corresponding output result.

[0061] S130: Determine the electromagnet state based on the output result.

[0062] Specifically, after obtaining the output result, the electromagnet state of the maglev train can be further determined according to the output result. Among them, the output result can be a failure probability value. When the failure probability value is greater than 0.5, it can be determined that the electromagnet is abnormal.

[0063] Among them, the process of establishing a temperature anomaly diagnosis model for the electromagnet based on historical operating condition data in the embodiment of the present invention can specifically include:

[0064] Obtain the data during each levitation to lowering process in the historical operating conditions data as each sample;

[0065] Determine normal operating condition samples and fault operating condition samples from each of the said samples;

[0066] Based on the normal operating condition samples and fault operating condition samples, train the temperature diagnosis model to obtain a trained abnormal electromagnet temperature diagnosis model;

[0067] Then, collect the operating condition data of the train, including:

[0068] Collect the operating condition data of the train between levitation and lowering.

[0069] It should be noted that as the maglev train levitates, is towed, brakes, and lowers, the working state of the electromagnet is constantly changing, and the temperature value is updated at all times with the change of the working state. Therefore, to comprehensively evaluate the working state of the electromagnet and further improve the accuracy of the established abnormal electromagnet temperature diagnosis model, normal operating condition samples and fault operating condition samples between levitation and lowering in the historical operating conditions data can be obtained, a sample set can be established based on these normal operating condition samples and fault operating condition samples, and the temperature diagnosis model can be trained through this sample set to obtain an abnormal electromagnet temperature diagnosis module, thereby improving the diagnosis accuracy of the abnormal electromagnet temperature diagnosis model.

[0070] Specifically, in actual application, collect the operating condition data of the train from levitation to lowering during operation, and then use the established abnormal electromagnet temperature diagnosis model to analyze this operating condition data to obtain an output result.

[0071] In actual application, the collected operating condition data can specifically include various types of parameters, such as the surface temperature of the electromagnet, the resistance of the electromagnet, the ambient temperature, the suspension state, the suspension speed, time and other information. Among them, the surface temperature of the electromagnet is realized by laying a grating temperature sensor on the surface of the electromagnet to monitor the surface temperature in real time, and the internal temperature of the electromagnet can be calculated based on the resistance. Specifically, in actual application, the maximum value, minimum value, mean value, mode, median, 75% quantile, 50% quantile, rising rate, falling rate, variance of the surface temperature and internal temperature of the electromagnet can be extracted, and the mean value of the outdoor ambient temperature, and the mean value, maximum value and variance of the difference between the surface temperature and internal temperature of the electromagnet and the ambient temperature can be extracted.

[0072] Furthermore, the above-mentioned training of the temperature diagnosis model based on the normal operating condition samples and fault operating condition samples to obtain a trained abnormal electromagnet temperature diagnosis model includes:

[0073] Establish an extended fault sample based on normal working condition samples and fault working condition samples;

[0074] Establish a sample library based on normal working condition samples, fault working condition samples and extended fault samples;

[0075] Use the sample library to train the temperature diagnosis model to obtain a trained electromagnet temperature anomaly diagnosis model.

[0076] It should be noted that since there are few fault working condition samples in the historical working condition data, the fault working condition samples can be extended so that the total number of fault working condition samples is balanced with the total number of normal working condition samples, improving the accuracy of the established electromagnet temperature anomaly diagnosis model. Therefore, in the embodiments of the present invention, an extended fault sample can be established based on normal working condition samples and fault working condition samples, and then a sample library can be established based on normal working condition samples, fault working condition samples and extended fault samples, and an electromagnet temperature anomaly diagnosis model can be established based on this sample library.

[0077] Further, the process of establishing an extended fault sample based on normal working condition samples and fault working condition samples may specifically include:

[0078] For each normal working condition sample, calculate the distances from the normal working condition sample to each fault working condition sample respectively;

[0079] Obtain the scores of the normal working condition samples according to the respective distances;

[0080] Determine the target working condition samples from each normal working condition sample according to the scores of each normal working condition sample;

[0081] Use the target working condition samples as the extended fault samples.

[0082] It should be noted that in the embodiments of the present invention, for each normal working condition sample, the distance between the normal working condition sample and each fault working condition sample is calculated. For example, if there are n normal working condition samples and m fault working condition samples, then for one normal working condition sample, m distances are obtained, and then the average calculation of these m distances is performed, and the obtained average distance is used as the score of the normal working condition sample, so as to obtain the scores corresponding to each normal working condition sample respectively, that is, n scores are obtained.

[0083] Specifically, the scores of each normal working condition sample can be sorted according to their magnitudes, and the preset number of normal working condition samples with the smallest scores can be used as the target working condition samples. For example, after sorting the n scores according to their magnitudes, the preset number (such as 20) of normal working condition samples with the smallest scores can be selected as the target working condition samples, and then these target working condition samples are used as the extended fault samples.

[0084] Furthermore, in the embodiments of the present invention, both the normal condition samples and the fault condition samples include various types of parameters; specifically, the surface temperature of the electromagnet, the internal temperature of the electromagnet, the ambient temperature, the difference between the surface temperature of the electromagnet and the ambient temperature, the difference between the internal temperature of the electromagnet and the ambient temperature, etc. can be determined according to various types of parameters, so as to calculate the distance for each type of parameter subsequently.

[0085] Then, calculate the distances from the normal condition samples to each fault condition sample, including:

[0086] For each fault condition sample, calculate the sub-distances between each type of parameter in the normal condition samples and the corresponding type of parameter in the fault condition sample;

[0087] According to each sub-distance and the weights corresponding to each type of parameter respectively, calculate the distance between the normal condition sample and the fault condition sample.

[0088] It can be understood that the corresponding weights can be preset for each type of parameter. For example, the weights corresponding to the surface temperature of the electromagnet, the internal temperature of the electromagnet, the ambient temperature, the difference between the surface temperature of the electromagnet and the ambient temperature, and the difference between the internal temperature of the electromagnet and the ambient temperature can all be 0.2. Of course, in practical applications, it is not limited to 0.2, and the specific values of each weight can be determined according to the actual situation. The embodiments of the present invention do not make special limitations on this.

[0089] Further, the process of establishing a sample library according to the normal condition samples, the fault condition samples, and the extended fault samples may specifically include:

[0090] Take the fault condition samples and the extended fault samples as the fault condition sample library;

[0091] Take each of the other normal condition samples in each normal condition sample except the target condition sample as the normal condition sample base library;

[0092] Extract a preset proportion of normal condition samples from the normal condition sample base library, which is the same as the number of fault condition samples, as the normal condition sample library;

[0093] Establish a final sample library based on the normal condition sample library and the fault condition sample library.

[0094] Specifically, the labels of the target working condition samples in all normal working condition samples can be changed to augmented fault samples, so as to reduce the number of normal working condition samples and increase the number of fault samples. Then, a normal working condition sample base library is established according to each of the other normal working condition samples except the target working condition samples in each normal working condition sample. A fault working condition sample library is established according to each augmented fault sample and fault working condition sample. Then, normal working condition samples that account for a preset ratio of the number of fault working condition samples in the fault working condition sample library are extracted from the normal working condition sample base library to form a normal sample library. The preset ratio can be the ratio of normal working condition samples to fault working condition samples, such as 1:1 or 7:3, etc. Of course, the specific value of the preset ratio can be determined according to actual needs, and the embodiments of the present invention do not make special limitations. After determining the normal working condition sample library and the fault working condition sample library, then a final sample library is established based on the normal working condition sample library and the fault working condition sample library, so that the number of normal working condition samples and the number of fault working condition samples in the final sample library reach a balance. For example, since the number of samples in the fault working condition sample library is less than the number of samples in the normal working condition sample library, the number of samples in the fault working condition sample library can be determined first, and then normal working condition samples that account for a preset ratio of this number are selected from the normal sample library based on this number. The selected normal working condition samples are used as the normal working condition sample library, and each sample in the normal working condition sample library and each sample in the fault working condition sample library are used to form the final sample library, thereby achieving a balance between the number of normal working condition samples and the number of fault working condition samples in the final sample library, which is beneficial to improving the accuracy of the established diagnostic model.

[0095] It can be seen that in the embodiments of the present invention, an abnormal electromagnet temperature diagnostic model is established in advance based on historical working condition data. Then, during the operation of the maglev train, the working condition data of the train is collected, and then the abnormal electromagnet temperature diagnostic model is used to analyze the working condition data to obtain an output result, and the electromagnet temperature state is determined based on the output result, which can improve the diagnostic accuracy and is beneficial to improving the operation safety of the maglev train.

[0096] Based on the above embodiments, the embodiments of the present invention further provide a maglev train abnormal electromagnet temperature diagnostic device. Specifically, please refer to Figure 2 , and the device includes:

[0097] A collection module 21, configured to collect the working condition data of the train;

[0098] An analysis module 22, configured to analyze the working condition data according to an abnormal electromagnet temperature diagnostic model established in advance to obtain an output result; wherein, the abnormal electromagnet temperature diagnostic model is established based on historical working condition data;

[0099] A determination module 23, configured to determine the electromagnet temperature state based on the output result.

[0100] It should be noted that the magnetic levitation train electromagnet temperature anomaly diagnosis device provided in the embodiments of the present invention has the same beneficial effects as the magnetic levitation train electromagnet temperature anomaly diagnosis method provided in the above embodiments. For the introduction of the magnetic levitation train electromagnet temperature anomaly diagnosis method involved in the embodiments of the present invention, please refer to the above embodiments, and the present invention will not elaborate here.

[0101] Based on the above embodiments, the embodiments of the present invention further provide a magnetic levitation train electromagnet temperature anomaly diagnosis system, which includes:

[0102] A memory for storing a computer program;

[0103] A processor for implementing the steps of the magnetic levitation train electromagnet temperature anomaly diagnosis method as described above when executing the computer program.

[0104] For example, the processor in the embodiments of the present invention is specifically used to implement collecting the working condition data of the train; analyzing the working condition data according to the pre-established electromagnet temperature anomaly diagnosis model to obtain an output result; wherein, the electromagnet temperature anomaly diagnosis model is established based on historical working condition data; and determining the electromagnet temperature state based on the output result.

[0105] Based on the above embodiments, the embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the magnetic levitation train electromagnet temperature anomaly diagnosis method as described above are implemented.

[0106] The computer-readable storage medium may include: various media such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc that can store program codes.

[0107] The various embodiments in this specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0108] It should also be noted that in this specification, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0109] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for diagnosing abnormal temperature of an electromagnet of a maglev train, characterized in that, Including: Collecting the operating condition data of the train; Analyzing the operating condition data according to a pre-established abnormal electromagnet temperature diagnosis model to obtain an output result; wherein, the abnormal electromagnet temperature diagnosis model is established based on historical operating condition data; Determining the electromagnet state based on the output result; wherein: Establishing the abnormal electromagnet temperature diagnosis model based on historical operating condition data includes: obtaining the data of each floating-to-lowering process in the historical operating condition data as each sample; determining normal operating condition samples and faulty operating condition samples from each of the samples; training the temperature diagnosis model according to the normal operating condition samples and the faulty operating condition samples to obtain a trained abnormal electromagnet temperature diagnosis model; Then, collecting the operating condition data of the train includes: collecting the operating condition data of the train between floating and lowering; Training the temperature diagnosis model according to the normal operating condition samples and the faulty operating condition samples to obtain a trained abnormal electromagnet temperature diagnosis model includes: for each normal operating condition sample, calculating the distances from the normal operating condition sample to each of the faulty operating condition samples; obtaining the scores of the normal operating condition samples according to the respective distances; determining target operating condition samples from each of the normal operating condition samples according to the scores of each normal operating condition sample; using the target operating condition samples as extended faulty samples; establishing a sample library according to the normal operating condition samples, the faulty operating condition samples and the extended faulty samples; training the temperature diagnosis model with the sample library to obtain a trained abnormal electromagnet temperature diagnosis model.

2. The method for diagnosing abnormal temperature of the electromagnetic iron of a maglev train according to claim 1, wherein The obtaining the scores of the normal operating condition samples according to the respective distances includes: Taking the average distance of the respective distances as the score of the normal operating condition sample.

3. The method for diagnosing abnormal temperature of the electromagnetic rail suspension train electromagnet according to claim 2, wherein The determining target operating condition samples from each of the normal operating condition samples according to the scores of each normal operating condition sample includes: Sorting the scores of each normal operating condition sample in descending order; Taking a preset number of normal operating condition samples with the smallest average distance as target operating condition samples.

4. The method for diagnosing abnormal temperature of the electromagnetic iron of a maglev train according to claim 1, wherein The establishing a sample library according to the normal operating condition samples, the faulty operating condition samples and the extended faulty samples includes: Taking the faulty operating condition samples and the extended faulty samples as a faulty operating condition sample library; Taking each of the normal operating condition samples other than the target operating condition samples in each of the normal operating condition samples as a normal operating condition sample base library; Extracting a preset proportion of normal operating condition samples from the normal operating condition sample base library according to the number of faulty operating condition samples as a normal operating condition sample library; Establishing a final sample library based on the normal operating condition sample library and the faulty operating condition sample library.

5. The method for diagnosing abnormal temperature of the electromagnetic iron of a maglev train according to claim 1, characterized in that Both the normal operating condition samples and the faulty operating condition samples include various types of parameters; Then, the calculating the distances from the normal operating condition sample to each of the faulty operating condition samples includes: For each faulty operating condition sample, calculating the sub-distances between each type of parameter in the normal operating condition sample and the corresponding type of parameter in the faulty operating condition sample; Calculate the distance between the normal operating condition sample and the faulty operating condition sample according to each sub-distance and the weight corresponding to each type of parameter respectively.

6. The method for diagnosing abnormal temperature of the electromagnetic iron of the maglev train according to claim 5, characterized in that The calculation of the sub-distance between each type of parameter in the normal operating condition sample and the corresponding type of parameter in the faulty operating condition sample includes: Calculate the Euclidean distance between each type of parameter in the normal operating condition sample and the corresponding type of parameter in the faulty operating condition sample.

7. The method for diagnosing abnormal temperature of the electromagnetic magnet of a maglev train according to claim 5, characterized in that, The multiple types of parameters include any combination of the surface temperature of the electromagnet, the internal temperature of the electromagnet, the ambient temperature, the difference between the surface temperature of the electromagnet and the ambient temperature, and the difference between the internal temperature of the electromagnet and the ambient temperature.

8. A temperature anomaly diagnosis device for an electromagnet of a maglev train, characterized in that, It includes: An acquisition module for acquiring the operating condition data of the train; An analysis module for analyzing the operating condition data according to a pre-established abnormal diagnosis model of the electromagnet temperature to obtain an output result; wherein, the abnormal diagnosis model of the electromagnet temperature is established based on historical operating condition data; A determination module for determining the temperature state of the electromagnet based on the output result; wherein: The establishment of the abnormal diagnosis model of the electromagnet temperature based on historical operating condition data includes: obtaining the data of each levitation-to-lowering process in the historical operating condition data as each sample; determining the normal operating condition sample and the faulty operating condition sample from each of the samples; training the temperature diagnosis model according to the normal operating condition sample and the faulty operating condition sample to obtain the trained abnormal diagnosis model of the electromagnet temperature. Then, the acquisition module is specifically used for acquiring the operating condition data of the train between levitation and lowering. The training of the temperature diagnosis model according to the normal operating condition sample and the faulty operating condition sample to obtain the trained abnormal diagnosis model of the electromagnet temperature includes: For each normal operating condition sample, calculate the distance from the normal operating condition sample to each faulty operating condition sample respectively; obtain the score of the normal operating condition sample according to each of the distances; determine the target operating condition sample from each of the normal operating condition samples according to the score of each normal operating condition sample; use the target operating condition sample as an extended faulty sample; establish a sample library according to the normal operating condition sample, the faulty operating condition sample and the extended faulty sample; train the temperature diagnosis model with the sample library to obtain the trained abnormal diagnosis model of the electromagnet temperature.

9. A temperature anomaly diagnosis system for the electromagnet of a maglev train, characterized in that, It includes: A memory for storing a computer program; A processor for implementing the steps of the abnormal diagnosis method of the maglev train electromagnet temperature as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the steps of the abnormal diagnosis method of the maglev train electromagnet temperature as described in any one of claims 1 to 7 are implemented.

Images