Method, device and equipment for determining suspension state of train and medium

Abstract

The invention discloses a train suspension state determination method, device and equipment and a medium, and relates to the technical field of maglev trains. According to the scheme, the preset judgment standard of the suspension state is obtained by collecting the suspension data of the current train, and the historical suspension data of the train in the preset period is obtained; according to the historical suspension data and a preset judgment standard, determining a historical suspension state of the train in a preset period, a corresponding historical feature matrix and a feature matrix of the current train; and determining the suspension state of the current train according to the historical feature matrix and the feature matrix. Therefore, according to the scheme, the historical suspension data of the train is obtained, the historical suspension data is applied, real-time data is analyzed online, the historical suspension data of the train is subjected to feature extraction to determine the corresponding historical suspension state, and the suspension resonance condition is judged in combination with the suspension data collected in real time in the train running process. The method has high real-time performance, and the suspension control level of the train can be effectively improved.

Description

Technical Field

[0001] This application relates to the technical field of maglev trains, and particularly to a method, device, equipment and medium for determining the suspension state of a train. Background Art

[0002] During the running of a maglev train, problems such as unstable suspension may occur. For example, the suspension control response delay caused by track unevenness may lead to varying degrees of rail hitting phenomena of the vehicle, and further trigger various faults. Therefore, it is crucial to determine the suspension state of the train in real time.

[0003] Currently, the train has not established a comprehensive error reporting mechanism for such situations, and can only judge the suspension state by setting certain calculation criteria through historical data. However, this method lacks real-time judgment and cannot effectively improve the level of train suspension control.

[0004] In view of the above, how to solve the problem of unstable suspension faced by maglev trains, where the existing suspension state determination mechanism relies on historical data and lacks real-time performance, affecting the improvement of the suspension control level, is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of this application is to provide a method, device, equipment and medium for determining the suspension state of a train, so as to solve the problems of unstable suspension faced by maglev trains, where the existing suspension state determination mechanism relies on historical data and lacks real-time performance, affecting the improvement of the suspension control level.

[0006] To solve the above technical problems, this application provides a method for determining the suspension state of a train, including:

[0007] Collect the suspension data of the current train; wherein, the suspension data at least includes the suspension gap, suspension acceleration and train speed;

[0008] Obtain the preset determination criteria for the suspension state, and obtain the historical suspension data of the train within a preset period;

[0009] According to the historical suspension data and the preset determination criteria, determine the historical suspension state of the train within the preset period, and determine the historical feature matrix corresponding to the historical suspension state;

[0010] Determine the feature matrix of the current train according to the suspension data;

[0011] Determine the suspension state of the current train according to the historical feature matrix and the feature matrix.

[0012] On the one hand, collecting the suspension data of the current train includes:

[0013] Set the preset data sampling frequency;

[0014] Collect the multi-channel suspension data of the current train according to the preset data sampling frequency;

[0015] Correspondingly, obtain the historical suspension data of the train within a preset period, including:

[0016] Divide the preset period into multiple equal time windows;

[0017] According to the preset data sampling frequency and each time window, collect the multi-channel historical suspension data to obtain the historical suspension data of the train within the preset period.

[0018] On the other hand, according to the historical suspension data and the preset determination criteria, determine the historical suspension state of the train within the preset period, including:

[0019] When the number of times that the suspension gap of the train within the preset period is greater than the first threshold is greater than the preset number of times, and the suspension gap is less than twice the rated gap within the preset period always holds, it is determined that the train has a first suspension state within the preset period;

[0020] When the train has a suspension gap equal to twice the rated gap within the preset period, and the corresponding duration is less than the second threshold, it is determined that the train has a second suspension state within the preset period;

[0021] When the train has a suspension gap equal to twice the rated gap within the preset period, and the corresponding duration is greater than the second threshold, it is determined that the train has a third suspension state within the preset period.

[0022] On the other hand, determine the historical feature matrix corresponding to the historical suspension state, including:

[0023] Determine the starting time point of the historical suspension state;

[0024] According to the starting time point and the historical suspension data, determine the historical feature data corresponding to the historical suspension state;

[0025] Determine the historical feature matrix according to the historical feature data.

[0026] On the other hand, determine the starting time point of the historical suspension state, including:

[0027] Based on each sampling time point within the preset period, calculate the average value of the multi-channel suspension accelerations of its adjacent sampling time points before and after;

[0028] Compare the average value of the multi-channel suspension accelerations of each sampling time point with the average value of the multi-channel suspension accelerations of its adjacent sampling time points before and after respectively;

[0029] Determine the starting time point as the sampling time point at which the average value of the multi-channel levitation acceleration corresponding to the first one is greater than the average values of the multi-channel levitation accelerations at the adjacent sampling time points before and after;

[0030] Correspondingly, according to the starting time point and the historical levitation data, determine the historical feature data corresponding to the historical levitation state, including:

[0031] Determine the historical levitation data corresponding to the time window starting from the starting time point as the historical feature data corresponding to the historical levitation state.

[0032] On the other hand, determine the historical feature matrix according to the historical feature data, including:

[0033] Determine the original data matrix according to the historical feature data;

[0034] Determine the de-centered matrix according to the original data matrix, and calculate the covariance matrix of the de-centered matrix;

[0035] According to the covariance matrix and the preset conditions, determine the eigenvectors corresponding to the covariance matrix to determine the historical feature matrix.

[0036] On the other hand, determine the levitation state of the current train according to the historical feature matrix and the feature matrix, including:

[0037] Determine the Euclidean distance threshold;

[0038] According to the historical feature matrix, the feature matrix and the Euclidean distance threshold, determine the levitation state of the current train.

[0039] To solve the above technical problems, the present application also provides a device for determining the levitation state of a train, including:

[0040] An acquisition module for acquiring the levitation data of the current train; wherein, the levitation data at least includes the levitation gap, the levitation acceleration and the train speed;

[0041] An acquisition module for acquiring the preset determination criteria for the levitation state and acquiring the historical levitation data of the train within a preset period;

[0042] A first determination module for determining the historical levitation state of the train within the preset period according to the historical levitation data and the preset determination criteria, and determining the historical feature matrix corresponding to the historical levitation state;

[0043] A second determination module for determining the feature matrix of the current train according to the levitation data;

[0044] A third determination module, configured to determine the suspension state of the current train according to the historical feature matrix and the feature matrix.

[0045] To solve the above technical problems, the present application further provides a train suspension state determination device, including:

[0046] A memory, configured to store a computer program;

[0047] A processor, configured to implement the steps of the above-mentioned train suspension state determination method when executing the computer program.

[0048] To solve the above technical problems, the present application further 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 above-mentioned train suspension state determination method are implemented.

[0049] A train suspension state determination method provided by the present application includes collecting suspension data of the current train; wherein the suspension data at least includes a suspension gap, a suspension acceleration, and a train speed; obtaining a preset determination criterion for the suspension state, and obtaining historical suspension data of the train within a preset period; determining the historical suspension state of the train within the preset period according to the historical suspension data and the preset determination criterion, and determining a historical feature matrix corresponding to the historical suspension state; determining a feature matrix of the current train according to the suspension data; and determining the suspension state of the current train according to the historical feature matrix and the feature matrix. It can be seen that this solution has high real-time performance by obtaining the historical suspension data of the train, performing the application of the historical suspension data and the online analysis of the real-time data, extracting features from the historical suspension data of the train to determine the corresponding historical suspension state, and judging the suspension resonance situation in combination with the real-time collected suspension data during the train operation, and can effectively improve the train suspension control level.

[0050] In addition, the present application further provides a train suspension state determination device, equipment, and medium with the same effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] To more clearly illustrate the embodiments of the present application, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0052] Figure 1 It is a flowchart of a train suspension state determination method provided by an embodiment of the present application;

[0053] Figure 2 It is a schematic diagram of a train suspension state determination device provided by an embodiment of the present application;

[0054] Figure 3 This is a structural diagram of a train suspension state determination device provided by an embodiment of the present application. Detailed implementation manners

[0055] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present application.

[0056] The core of the present application is to provide a train suspension state determination method, device, equipment and medium to solve the problems that the maglev train faces unstable suspension, the existing suspension state determination mechanism depends on historical data and lacks real-time performance, which affects the improvement of the suspension control level.

[0057] To enable those skilled in the art to better understand the solution of the present application, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0058] During the running of the maglev train, it may encounter the problem of unstable suspension. For example, the suspension control response delay caused by the uneven track may lead to different degrees of rail hitting phenomena of the vehicle, which may further cause various failures. However, the current train has not established a comprehensive error reporting mechanism for such situations, and can only set certain calculation criteria through historical data to judge whether there are these problems, lacking real-time judgment and unable to effectively improve the suspension control level of the train.

[0059] It should be noted that when the above situation occurs, data such as the suspension gap of the train will present specific characteristics. By extracting the data characteristics related to the gap and performing linkage analysis, corresponding design improvement measures can be taken to enhance the suspension stability of the train. Based on this principle, to solve the above problems, the present application provides a train suspension state determination method.

[0060] Figure 1 This is a flowchart of a train suspension state determination method provided by an embodiment of the present application. As Figure 1 shown, the method includes:

[0061] S10: Collect the suspension data of the current train.

[0062] Among them, the suspension data at least includes the suspension gap, suspension acceleration and train speed.

[0063] Specifically, first, the suspension data of the current train is collected in real time. It should be noted that the suspension data at least includes the suspension gap, suspension acceleration, and train speed, which are three key parameters indispensable in the train suspension system. By monitoring and precisely controlling these parameters in real time, the smooth operation of the train, the comfort of passengers, and overall safety can be ensured. Specifically, the suspension gap refers to the vertical distance between the train's suspension system (such as the electromagnet of a maglev train) and the track; by maintaining an appropriate gap, the train can be suspended above the track using the principle of magnetic force or air flotation, thus eliminating direct contact with the track and reducing friction and wear. The suspension acceleration is the rate of change of the train's acceleration in the vertical direction, that is, how fast the speed of the train's suspension system changes in the vertical direction; by controlling the suspension acceleration, the vertical vibrations generated when the train accelerates, decelerates, or passes through uneven sections can be reduced, improving the riding comfort of passengers. The train speed refers to the speed at which the train travels on the track, usually measured in kilometers per hour (km / h) or meters per second (m / s); the train speed directly affects the transportation efficiency and travel time, and by reasonably controlling the speed, efficient transportation services can be achieved. Generally, the suspension gap, suspension acceleration, and train speed can be collected by a ranging sensor, an accelerometer, and a wheel speed sensor respectively, or can be collected by other sensors, which is not limited in this embodiment. In addition, the specific method of collecting the suspension data in this embodiment is not limited either.

[0064] S11: Obtain the preset determination criteria for the suspension state and obtain the historical suspension data of the train within a preset period.

[0065] Furthermore, obtain the preset determination criteria for the train suspension state (N is a positive integer). It should be noted that the preset determination criteria are a series of indicators and conditions used to determine whether the train is in a certain suspension state, and these criteria are constructed based on key parameters such as the suspension gap, suspension acceleration, and train speed. The specific content of the preset determination criteria in this embodiment is not limited and depends on the specific implementation situation.

[0066] At the same time, obtain the historical suspension data of the train within a preset period. It should be noted that the preset period is a certain time period before the current moment, and the historical suspension data is the suspension data of the train collected within the preset period, which also at least includes the historical suspension gap, suspension acceleration, and train speed. The specific process of obtaining the historical suspension data of the train within the preset period in this embodiment is not limited and depends on the specific implementation situation.

[0067] It should be noted that the purpose of obtaining the historical levitation data of the train within the preset period in this embodiment is to determine the corresponding relationship between the levitation data and the levitation state of the train according to the preset determination criteria. In specific implementation, the determination criteria may not be given, but instead, the historical levitation data corresponding to different levitation states confirmed by the expert system may be directly input to determine the levitation state.

[0068] S12: According to the historical levitation data and the preset determination criteria, determine the historical levitation state of the train within the preset period, and determine the historical feature matrix corresponding to the historical levitation state.

[0069] Subsequently, according to the historical levitation data and the preset determination criteria, determine the historical levitation state of the train within the preset period, and determine the historical feature matrix corresponding to the historical levitation state. It should be noted that the historical feature matrix is used to represent the set of features of the historical levitation state. Specifically, the historical feature matrix comprehensively describes and quantifies the historical levitation state of the sample by organizing different features of each sample into a matrix structure in numerical form. In this embodiment, there are no restrictions on the determination processes of the historical levitation state and the corresponding historical feature matrix, which depend on the specific implementation situation.

[0070] S13: Determine the feature matrix of the current train according to the levitation data.

[0071] S14: Determine the levitation state of the current train according to the historical feature matrix and the feature matrix.

[0072] Finally, determine the feature matrix of the current train according to the train levitation data collected in real time. In this embodiment, there are no restrictions on the specific determination process of the feature matrix of the current train.

[0073] It should be noted that there is a corresponding relationship between the historical feature matrix and the historical levitation state. Since there can be multiple historical levitation states, there are correspondingly multiple historical feature matrices. By comparing the feature matrix with multiple historical feature matrices, the historical feature matrix closest to the feature matrix can be determined, thereby determining the levitation state of the current train. In this embodiment, there are no restrictions on the specific process of determining the levitation state of the current train according to the historical feature matrix and the feature matrix.

[0074] In this embodiment, the suspension data of the current train is collected, where the suspension data at least includes the suspension gap, suspension acceleration, and train speed. The preset determination criteria for the suspension state are obtained, and the historical suspension data of the train within the preset period is obtained. According to the historical suspension data and the preset determination criteria, the historical suspension state of the train within the preset period is determined, and the historical feature matrix corresponding to the historical suspension state is determined. The feature matrix of the current train is determined according to the suspension data. According to the historical feature matrix and the feature matrix, the suspension state of the current train is determined. It can be seen that in this solution, by obtaining the historical suspension data of the train, using the historical suspension data and performing online analysis of real-time data, feature extraction is performed on the historical suspension data of the train to determine the corresponding historical suspension state, and during the train operation, the suspension resonance situation is judged by combining the real-time collected suspension data, which has high real-time performance and can effectively improve the train suspension control level.

[0075] Based on the above embodiment, in some embodiments, collecting the suspension data of the current train includes:

[0076] S101: Set the preset data sampling frequency.

[0077] S102: Collect the suspension data of multiple channels of the current train according to the preset data sampling frequency.

[0078] To better collect the suspension data of the current train, in specific implementation, it is first necessary to set the preset data sampling frequency . That is, there are data sampling points per second. In this embodiment, the specific value of the preset data sampling frequency is not limited and is determined according to the specific implementation situation.

[0079] Subsequently, collect the suspension data of multiple channels of the current train according to the preset data sampling frequency. It should be noted that in order to achieve redundant statistics and prevent statistical errors, it is necessary to perform data collection and transmission simultaneously for multiple channels. For example, in the data at a certain moment t, it includes channels of suspension gap , channels of suspension acceleration and channels of train speed . In this embodiment, the specific number of channels is not limited and is determined according to the specific implementation situation.

[0080] Correspondingly, obtaining the historical suspension data of the train within the preset period includes:

[0081] S111: Divide the preset period into multiple equal time windows.

[0082] S112: According to the preset data sampling frequency and each time window, collect multiplexed historical levitation data to obtain the historical levitation data of the train within a preset period.

[0083] To make the collection of historical levitation data correspond to that of real-time levitation data, when collecting historical levitation data, specifically divide the preset period into multiple equal time windows ; According to the preset data sampling frequency Collect multiplexed historical levitation data, and pack the data according to the length of the time window to obtain the historical levitation data of the train within a preset period.

[0084] For example, in a data packet, the data at a certain moment t contains levitation gaps of , levitation accelerations of and train speeds of . Further, make arranged in sequence to form a vector , corresponding to the vector of sampling points formed into .

[0085] In this way, the collection of real-time levitation data and historical levitation data is respectively realized.

[0086] Based on the above embodiments, in some embodiments, according to the historical levitation data and the preset determination criteria, determine the historical levitation state of the train within a preset period, including:

[0087] S121: When the number of times that the levitation gap of the train within a preset period is greater than the first threshold is greater than the preset number of times, and it is always true within the preset period that the levitation gap is less than twice the rated gap, determine that the train has a first levitation state within the preset period.

[0088] S122: When there is a levitation gap equal to twice the rated gap within the preset period of the train, and the corresponding duration is less than the second threshold, determine that the train has a second levitation state within the preset period.

[0089] S123: When there is a levitation gap equal to twice the rated gap within the preset period of the train, and the corresponding duration is greater than the second threshold, determine that the train has a third levitation state within the preset period.

[0090] To determine the historical levitation state of the train within a preset period, specific levitation state determination criteria are given in this embodiment , specifically as follows:

[0091] 1) The number of times the train is within the preset period is greater than times, and is always true within the preset period , then it is considered that the train has entered the first floating state within the preset period . .

[0092] 2) There exists a moment within the preset period of the train, and the duration is less than , then it is considered that the train has entered the second floating state within the preset period .

[0093] 3) There exists a moment within the preset period of the train, and the duration is greater than , then it is considered that the train has entered the third floating state within the preset period .

[0094] Among them, is the floating gap of the train, is the rated gap of the train, is the first threshold, is the second threshold, is the preset number of times. In this embodiment, the magnitudes of the first threshold, the second threshold, and the preset number of times are not limited and are determined according to specific implementation situations.

[0095] Based on the above embodiments, in some embodiments, determining the historical feature matrix corresponding to the historical floating state includes:

[0096] S124: Determine the starting time point of the historical floating state.

[0097] S125: Determine the historical feature data corresponding to the historical floating state according to the starting time point and the historical floating data.

[0098] S126: Determine the historical feature matrix according to the historical feature data.

[0099] After collecting the historical floating data and determining the corresponding historical floating state, it is necessary to determine the starting time point of the historical floating state within the preset period, and take this starting time point as the starting point to determine the historical floating data within a certain period of time after it as the historical feature data corresponding to the historical floating state. Finally, determine the historical feature matrix according to the historical feature data to facilitate comparing with the feature matrix to determine the floating state of the current train.

[0100] It should be noted that in this embodiment, there is no limitation on the determination method of the starting time point, nor on the determination process of the historical feature data, which depends on the specific implementation situation. The specific determination process is given below in combination with specific embodiments.

[0101] In some embodiments, determining the starting time point of the historical levitation state includes:

[0102] S127: Based on each sampling time point within a preset period, calculate the average value of the multi-channel levitation accelerations of its adjacent sampling time points before and after.

[0103] S128: Compare the average value of the multi-channel levitation accelerations of each sampling time point with the average values of the multi-channel levitation accelerations of its adjacent sampling time points before and after respectively.

[0104] S129: Determine the sampling time point at which the average value of the first corresponding multi-channel levitation acceleration is simultaneously greater than the average values of the multi-channel levitation accelerations of its adjacent sampling time points before and after as the starting time point.

[0105] To determine the starting time point of the historical levitation state, in this embodiment, specifically based on each sampling time point within a preset period, calculate the average value of the multi-channel levitation accelerations of its adjacent sampling time points before and after. It can be understood that the sampling time point is the time point for collecting historical levitation data based on the preset data sampling frequency within the preset period.

[0106] Further, compare the average value of the multi-channel levitation accelerations of each sampling time point with the average values of the multi-channel levitation accelerations of its adjacent sampling time points before and after respectively. Finally, determine the sampling time point at which the average value of the first corresponding multi-channel levitation acceleration is simultaneously greater than the average values of the multi-channel levitation accelerations of its adjacent sampling time points before and after as the starting time point. Generally speaking, it is to determine the time point when the average values of the multi-channel levitation accelerations of the adjacent time points before and after are both less than the average value of the corresponding multi-channel levitation acceleration as the starting time point.

[0107] Correspondingly, according to the starting time point and the historical levitation data, determining the historical feature data corresponding to the historical levitation state includes:

[0108] S130: Determine the historical levitation data corresponding to the time window starting from the starting time point as the historical feature data corresponding to the historical levitation state.

[0109] To determine the historical feature data corresponding to the historical levitation state, in this embodiment, specifically determine the historical levitation data corresponding to the time window starting from the starting time point as the historical feature data corresponding to the historical levitation state, that is, the time point After The historical floating data corresponding to the time interval of seconds is used as the characteristic data when the historical floating state appears once.

[0110] Based on the above embodiments, in some embodiments, determining the historical feature matrix according to the historical feature data includes:

[0111] S131: Determine the original data matrix according to the historical feature data.

[0112] S132: Determine the decentralized matrix according to the original data matrix, and calculate the covariance matrix of the decentralized matrix.

[0113] S133: Determine the eigenvector corresponding to the covariance matrix according to the covariance matrix and the preset conditions to determine the historical feature matrix.

[0114] In order to determine the historical feature matrix, in this embodiment, the original data matrix is specifically determined according to the historical feature data. It should be noted that in the specific implementation, when the historical floating state appears for the third time At this time, starting from the time when it is received, each time the state appears The corresponding is obtained. This is because matrix calculation can be performed through historical floating data only after at least three times. It should also be noted that represents the floating state The th time when it occurs. When the floating state Occurs times, the original data matrix can be obtained;

[0115]

[0116] Among them, is the original data matrix, , and are all positive integers.

[0117] Furthermore, to determine the decentralized matrix according to the original data matrix, specifically, the average value of all rows of the original data matrix is calculated to obtain an average column vector:

[0118] , ;

[0119] At this time, the decentralized matrix is obtained:

[0120] ;

[0121] Subsequently, calculate the covariance matrix of the decentralized matrix, and the formula is as follows:

[0122] ;

[0123] Among them, is the covariance matrix.

[0124] Finally, according to the covariance matrix and the preset conditions, the eigenvectors corresponding to the covariance matrix are determined to determine the historical feature matrix. Specifically, all eigenvalues satisfying are arranged from largest to smallest to form , and then the eigenvectors corresponding to the covariance matrix can be obtained. These eigenvectors form the historical feature matrix .

[0125] It should also be noted that whenever suspended data is collected and the corresponding suspended state is determined to be , the historical feature matrix will be updated according to the suspended state data in the corresponding data interval at this time. . In addition, the process of determining the feature matrix of the current train based on the real-time collected suspended data is the same as the specific process of determining the historical feature matrix described above.

[0126] Based on the above embodiments, in some embodiments, determining the suspended state of the current train according to the historical feature matrix and the feature matrix includes:

[0127] S141: Determine the Euclidean distance threshold.

[0128] S142: Determine the suspended state of the current train according to the historical feature matrix, the feature matrix, and the Euclidean distance threshold.

[0129] After obtaining the current feature matrix and the historical feature matrix, in order to determine the current suspended state of the train, the Euclidean distance threshold is specifically determined, and the suspended state of the current train is determined according to the historical feature matrix, the feature matrix, and the Euclidean distance threshold, as follows:

[0130] ;

[0131] Among them, is the Euclidean distance calculation result, is the Euclidean distance threshold. In this embodiment, the size of the Euclidean distance threshold is not limited.

[0132] Based on the above formula, the qualified is output, and then the corresponding suspended state can be determined.

[0133] On this basis, after determining the current levitation state of the train, by collecting the time and location information when the levitation state appears, a comprehensive understanding of the train's performance under different operating conditions can be obtained. For example, if an abnormal levitation state frequently occurs in a specific section, it may indicate a problem with the track in that section and maintenance is required. These data not only help to detect and solve potential faults in a timely manner, but also provide an important basis for vehicle health management. By analyzing historical data, the equipment life and maintenance requirements can be predicted, so as to optimize the maintenance plan and reduce the operating cost. In addition, these information are also crucial for the train automation design. They can be used to optimize the algorithms of the control system, improve the train's adaptive ability and intelligent level, ensure that the train can maintain the best performance under different environments and operating conditions, and provide a safer and more comfortable travel experience for passengers.

[0134] In the above embodiments, the method for determining the train levitation state is described in detail. The present application also provides corresponding embodiments of the train levitation state determination device.

[0135] Figure 2 The following is a schematic diagram of a train levitation state determination device provided by an embodiment of the present application. As Figure 2 shown, the device includes:

[0136] An acquisition module 10, configured to acquire the levitation data of the current train; wherein, the levitation data at least includes the levitation gap, levitation acceleration and train speed.

[0137] An acquisition module 11, configured to obtain a preset determination criterion for the levitation state and obtain the historical levitation data of the train within a preset period.

[0138] A first determination module 12, configured to determine the historical levitation state of the train within a preset period according to the historical levitation data and the preset determination criterion, and determine the historical feature matrix corresponding to the historical levitation state.

[0139] A second determination module 13, configured to determine the feature matrix of the current train according to the levitation data.

[0140] A third determination module 14, configured to determine the levitation state of the current train according to the historical feature matrix and the feature matrix.

[0141] In some embodiments, the acquisition module 10 includes:

[0142] A setting sub-module, configured to set a preset data sampling frequency;

[0143] A first acquisition sub-module, configured to acquire the multi-channel levitation data of the current train according to the preset data sampling frequency;

[0144] Correspondingly, the acquisition module 11 includes:

[0145] A division sub-module, configured to divide a preset period into multiple equal time windows;

[0146] A second acquisition sub-module, configured to acquire multi-channel historical suspension data according to a preset data sampling frequency and each time window, so as to obtain the historical suspension data of the train within a preset period.

[0147] In some embodiments, the first determination module 12 includes:

[0148] A first determination sub-module, configured to determine that the train has a first suspension state within a preset period when the number of times that the suspension gap of the train is greater than a first threshold within a preset period is greater than a preset number, and the suspension gap is less than twice the rated gap within the preset period;

[0149] A second determination sub-module, configured to determine that the train has a second suspension state within a preset period when the suspension gap of the train is equal to twice the rated gap within a preset period and the corresponding duration is less than a second threshold;

[0150] A third determination sub-module, configured to determine that the train has a third suspension state within a preset period when the suspension gap of the train is equal to twice the rated gap within a preset period and the corresponding duration is greater than a second threshold.

[0151] In some embodiments, the first determination module 12 includes:

[0152] A fourth determination sub-module, configured to determine the starting time point of the historical suspension state;

[0153] A fifth determination sub-module, configured to determine the historical feature data corresponding to the historical suspension state according to the starting time point and the historical suspension data;

[0154] A sixth determination sub-module, configured to determine a historical feature matrix according to the historical feature data.

[0155] In some embodiments, the fourth determination sub-module includes:

[0156] A calculation sub-module, configured to calculate the average value of multi-channel suspension accelerations at adjacent sampling time points before and after based on each sampling time point within a preset period;

[0157] A comparison sub-module, configured to compare the average value of multi-channel suspension accelerations at each sampling time point with the average value of multi-channel suspension accelerations at adjacent sampling time points before and after;

[0158] A seventh determination sub-module, configured to determine the sampling time point at which the average value of the first corresponding multi-channel suspension accelerations is simultaneously greater than the average value of the multi-channel suspension accelerations at adjacent sampling time points before and after as the starting time point;

[0159] Correspondingly, the fifth determination sub-module includes:

[0160] The eighth determination sub-module is configured to determine the historical feature data corresponding to the historical suspension state from the historical suspension data corresponding within the time window starting from the starting time point.

[0161] In some embodiments, the sixth determination sub-module includes:

[0162] The ninth determination sub-module is configured to determine the original data matrix according to the historical feature data;

[0163] The tenth determination sub-module is configured to determine the decentralized matrix according to the original data matrix and calculate the covariance matrix of the decentralized matrix;

[0164] The eleventh determination sub-module is configured to determine the eigenvectors corresponding to the covariance matrix according to the covariance matrix and the preset conditions to determine the historical feature matrix.

[0165] In some embodiments, the third determination module 14 includes:

[0166] The twelfth determination sub-module is configured to determine the Euclidean distance threshold;

[0167] The thirteenth determination sub-module is configured to determine the suspension state of the current train according to the historical feature matrix, the feature matrix, and the Euclidean distance threshold.

[0168] Since the embodiments of the device part correspond to the embodiments of the method part, for the embodiments of the device part, please refer to the description of the embodiments of the method part, which will not be elaborated here.

[0169] Figure 3 This is a structural diagram of a train suspension state determination device provided by an embodiment of the present application. As Figure 3 shown, the train suspension state determination device includes:

[0170] A memory 20 for storing a computer program;

[0171] A processor 21 for implementing the steps of the train suspension state determination method as mentioned in the above embodiments when executing the computer program.

[0172] The train suspension state determination device provided by this embodiment may include, but is not limited to, a smart phone, a tablet computer, a notebook computer, or a desktop computer, etc.

[0173] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 may be implemented in at least one hardware form of a Digital Signal Processor (DSP), a Field-Programmable Gate Array (FPGA), and a Programmable Logic Array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the wake state, also known as the Central Processing Unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a Graphics Processing Unit (GPU), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may further include an Artificial Intelligence (AI) processor, and the AI processor is used to process computational operations related to machine learning.

[0174] The memory 20 may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory 20 may further include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201. After the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the train suspension state determination method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 20 may further include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. The data 203 may include, but is not limited to, the data involved in the train suspension state determination method.

[0175] In some embodiments, the train suspension state determination device may further include a display screen 22, an input / output interface 23, a communication interface 24, a power supply 25, and a communication bus 26.

[0176] Those skilled in the art can understand that Figure 3 the structure shown in

[0177] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps recorded in the above method embodiments are implemented.

[0178] It can be understood that if the method in the above embodiments is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage media include: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0179] The above provides a detailed introduction to a method, device, equipment, and medium for determining the suspension state of a train provided by the present application. The various embodiments in the specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple. For the relevant parts, reference can be made to the description of the method part. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the protection scope of the present application.

[0180] 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 a 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 a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

Claims

1. A method for determining the suspension state of a train, characterized in that Including: Collecting the suspension data of the current train; wherein, the suspension data at least includes a suspension gap, a suspension acceleration, and a train speed; Obtaining a preset determination criterion for the suspension state, and obtaining the historical suspension data of the train within a preset period; Determining the historical suspension state of the train within the preset period according to the historical suspension data and the preset determination criterion, and determining a historical feature matrix corresponding to the historical suspension state; Determining a feature matrix of the current train according to the suspension data; Determining the suspension state of the current train according to the historical feature matrix and the feature matrix.

2. The method for determining the train suspension state according to claim 1, wherein Collecting the suspension data of the current train, including: Setting a preset data sampling frequency; Collecting the multi-channel suspension data of the current train according to the preset data sampling frequency; Correspondingly, obtaining the historical suspension data of the train within a preset period, including: Dividing the preset period into a plurality of equal time windows; Collecting multi-channel historical suspension data according to the preset data sampling frequency and each time window to obtain the historical suspension data of the train within the preset period.

3. The method for determining the train suspension state according to claim 1, characterized in that, Determining the historical suspension state of the train within the preset period according to the historical suspension data and the preset determination criterion, including: When the number of times that the suspension gap of the train within the preset period is greater than a first threshold is greater than a preset number, and it is always true within the preset period that the suspension gap is less than twice the rated gap, determining that the train has a first suspension state within the preset period; When the train has a suspension gap equal to twice the rated gap within the preset period and the corresponding duration is less than a second threshold, determining that the train has a second suspension state within the preset period; When the train has a suspension gap equal to twice the rated gap within the preset period and the corresponding duration is greater than a second threshold, determining that the train has a third suspension state within the preset period.

4. The method for determining the train suspension state according to claim 2, wherein Determining a historical feature matrix corresponding to the historical suspension state, including: Determining the starting time point of the historical suspension state; Determining historical feature data corresponding to the historical suspension state according to the starting time point and the historical suspension data; Determining the historical feature matrix according to the historical feature data.

5. The method for determining the train suspension state according to claim 4, wherein Determining the starting time point of the historical suspension state, including: Calculating the average value of the multi-channel suspension accelerations of the adjacent sampling time points before and after each sampling time point within the preset period; Comparing the average value of the multi-channel suspension accelerations of each sampling time point with the average value of the multi-channel suspension accelerations of the adjacent sampling time points before and after it; Determining the sampling time point at which the first corresponding average value of the multi-channel suspension accelerations is simultaneously greater than the average values of the multi-channel suspension accelerations of the adjacent sampling time points before and after it as the starting time point; Correspondingly, determining historical feature data corresponding to the historical suspension state according to the starting time point and the historical suspension data, including: Determining the historical suspension data corresponding to the time window starting from the starting time point as the historical feature data corresponding to the historical suspension state.

6. The method for determining the train suspension state according to claim 4, characterized in that, Determining the historical feature matrix according to the historical feature data, including: Determine the original data matrix according to the historical feature data; Determine the decentralized matrix according to the original data matrix, and calculate the covariance matrix of the decentralized matrix; Determine the eigenvectors corresponding to the covariance matrix according to the covariance matrix and preset conditions, so as to determine the historical feature matrix.

7. The method for determining the train suspension state according to any one of claims 1 to 6, characterized in that Determine the levitation state of the current train according to the historical feature matrix and the feature matrix, including: Determine the Euclidean distance threshold; Determine the levitation state of the current train according to the historical feature matrix, the feature matrix and the Euclidean distance threshold.

8. A device for determining the suspension state of a train, characterized in that Including: An acquisition module, configured to acquire the levitation data of the current train; wherein, the levitation data at least includes the levitation gap, the levitation acceleration and the train speed; An acquisition module, configured to acquire the preset determination criteria for the levitation state and acquire the historical levitation data of the train within a preset period; A first determination module, configured to determine the historical levitation state of the train within the preset period according to the historical levitation data and the preset determination criteria, and determine the historical feature matrix corresponding to the historical levitation state; A second determination module, configured to determine the feature matrix of the current train according to the levitation data; A third determination module, configured to determine the levitation state of the current train according to the historical feature matrix and the feature matrix.

9. A train suspension state determination device, characterized in that Including: A memory, configured to store a computer program; A processor, configured to implement the steps of the train levitation state determination method according to 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 a processor, the steps of the train levitation state determination method according to any one of claims 1 to 7 are implemented.

Images