Automatic identification method and system for train pull-in carriage position

Abstract

The invention discloses a method and a system for automatically identifying the position of a train arrival carriage. The method comprises the steps of train arrival data acquisition, data preprocessing, train arrival positioning model construction, train arrival data encryption and practical application. The invention belongs to the technical field of data processing, and particularly relates to a method and a system for automatically identifying the position of a train pull-in carriage. According to the scheme, a determined model architecture is adopted, and the dependency relationship between train pull-in carriage positioning data and influence factors is captured and extracted through preprocessed train pull-in data; performing cross validation to evaluate the positioning accuracy, and performing loop iteration until satisfying performance indexes are achieved; permission setting is carried out, it is ensured that only a user having a specific permission can carry out related operation, random numbers are randomly selected, pseudo-random functions are defined, key components obtained by a data user are calculated, a data sender encrypts a plaintext and calculates a ciphertext, and train arrival data are protected.

Description

Technical Field

[0001] The invention belongs to the technical field of data processing, and in particular relates to a method and a system for automatically identifying the position of a train compartment entering a station. Background Art

[0002] The method of automatically identifying the position of a train entering a station is to install sensors on stations and rails to identify the position, speed and stop status of the train, thereby automatically identifying the position of the train. However, the existing method of automatically identifying the position of a train entering a station has the following technical problems: the data for constructing the train entry positioning model is complex and diverse, and it is difficult to sort out the dependencies between the positioning data and various influencing factors, resulting in inaccurate positioning; there is also the technical problem that the security protection of the train entry data is not in place, resulting in the leakage of the train entry data, affecting the safe operation of the train. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a method and system for automatically identifying the position of a train entering a station carriage. In view of the technical problem that the data of the current train entering a station positioning model are complex and diverse, and it is difficult to sort out the dependency between the positioning data and various influencing factors, resulting in inaccurate positioning, a certain model architecture is adopted, and the dependency between the train entering a station carriage positioning data and the influencing factors is captured and extracted through the pre-processed train entering a station data, and the positioning accuracy is cross-validated and evaluated, and the positioning is iterated repeatedly until satisfactory performance indicators are achieved; in view of the technical problem that the security protection of the train entering a station data is not in place, resulting in the leakage of the train entering a station data and affecting the safe operation of the train, permission setting is adopted to ensure that only users with specific permissions can perform related operations, randomly select random numbers, define pseudo-random functions, and calculate the key components obtained by the data user, and the data sender encrypts the plaintext and calculates the ciphertext to protect the train entering a station data.

[0004] The technical solution adopted by the present invention is as follows: The present invention provides a method for automatically identifying the position of a train carriage entering a station, the method comprising the following steps:

[0005] Step S1: Collect train entry data, set up sensors, and obtain key data of train entry, including the length, spacing and speed of the carriages;

[0006] Step S2: Data preprocessing: clean the train arrival data, remove invalid and erroneous data, classify and summarize according to train number and station, and standardize the time data;

[0007] Step S3: construct a train entry positioning model, determine the model architecture, capture and extract the dependency between the train entry carriage positioning data and influencing factors through the preprocessed train entry data, perform cross-validation to evaluate the positioning accuracy, and iterate repeatedly until satisfactory performance indicators are achieved;

[0008] Step S4: Encrypt the train entry data, set permissions to ensure that only users with specific permissions can perform related operations, randomly select random numbers, define pseudo-random functions, and calculate the key components obtained by the data user. The data sender encrypts the plaintext and calculates the ciphertext;

[0009] Step S5: practical application.

[0010] Furthermore, in step S1, the collecting of train entry data includes the following steps:

[0011] Step S11: Determine the sensor position, install sensors on the top, side and bottom of each carriage, and configure sensor parameters, including detection range, resolution and frame rate, to ensure that the sensors can meet the requirements of data collection;

[0012] Step S12: Connect the data acquisition system, connect the sensor to the data acquisition system, and collect train entry data in real time.

[0013] Furthermore, in step S2, the data is preprocessed, specifically, the train entry data is cleaned, invalid and erroneous data is removed, the data is classified and summarized according to the train number and station, and the time data is standardized.

[0014] Further, in step S3, the construction of the train entry carriage positioning model includes the following steps:

[0015] Step S31: Determine the positioning model architecture, including a forget gate, an input gate, an output gate, and a unit state;

[0016] Step S32: training the model, inputting the preprocessed train entry data into the model for training, effectively capturing and extracting the dependency between the train entry carriage positioning data and the influencing factors, the formula used is as follows:

[0017] ;

[0018] ;

[0019] In the formula, and are the outputs of the forward LSTM and backward LSTM at time t, and is the output of the forward LSTM and backward LSTM at time t-1, is the predicted output, is the forward factor, v is the backward factor, and T is the length of the time series;

[0020] Step S33: Perform cross validation and calculate the root mean square error index of the data to reflect the degree of deviation of the data error and determine whether the model accurately locates the train. The formula used is as follows:

[0021] ;

[0022] In the formula, represents the root mean square error index, n is the total data, is the predicted value of the i-th data, The actual value of the i-th data;

[0023] Step S34: Iterate the loop and further optimize the model parameters according to the results of cross-validation, including adjusting the learning rate, improving the number of neurons in the hidden layer, training and validating again, and repeating this process until satisfactory performance indicators are achieved.

[0024] Furthermore, in step S4, the train entry data is encrypted, including the following steps:

[0025] Step S41: Calculate the setting value corresponding to the train entry data protection authority to ensure that only users with specific train entry data protection authority can perform related operations. The formula used is as follows:

[0026] ;

[0027] Where k represents the first index of the train entry data protection authority, B k Indicates the setting value corresponding to the data protection authority for train entry, B indicates the setting value, e indicates the encryption function, g is the basic element, b k These are parameters related to data protection rights for train entry;

[0028] Step S42: Randomly select a random number and define a pseudo-random function, which increases the unpredictability and security of the train entry data, and calculates the output of the pseudo-random function. The formula used is as follows:

[0029] ;

[0030] In the formula, represents the output of the pseudo-random function, a k and a j is a randomly selected random number used for the calculation of pseudo-random functions, s k，j is a specific parameter value, u represents the user's input, j represents the second index of the train entry data protection authority, and j≠k;

[0031] Step S43: Calculate the key components obtained by the data user to ensure that the data user can only obtain the key components that have been specially processed. The key components include encryption keys and initialization vectors, which are used to decrypt data. Data access is strictly controlled by permissions. The formula used is as follows:

[0032] ;

[0033] Where D k，j represents the key component of train station data user acquisition, R k，j represents a random variable;

[0034] Step S44: Calculate the ciphertext of the train entry data. The data sender encrypts the plaintext m and calculates the ciphertext. The formula used is as follows:

[0035] ;

[0036] In the formula, CT represents the ciphertext of train entry data, i.e. the encrypted train entry data, E 0 Indicates the first part of the ciphertext, E 1 Represents the second part of the ciphertext, and s is the random number used to calculate the ciphertext.

[0037] Furthermore, in step S5, the actual application is to feed back the carriage position information to relevant operators in real time according to the train entry data for management operations.

[0038] The present invention provides a system for automatically identifying the position of a train carriage entering a station, comprising a module for collecting train entry data, a data preprocessing module, a module for building a train entry positioning model, a module for encrypting train entry data, and a practical application module;

[0039] The module for collecting train entry data is specifically to set sensors to obtain key data of train entry, including the length, spacing and speed of the carriages;

[0040] The data preprocessing module specifically cleans the train station entry data, removes invalid and erroneous data, classifies and summarizes them according to train numbers and stations, and standardizes and organizes the time data;

[0041] The train station entry positioning model module is constructed, specifically determining the model architecture, capturing and extracting the dependency between the train station entry carriage positioning data and the influencing factors through the preprocessed train station entry data, performing cross-validation to evaluate the positioning accuracy, and iterating repeatedly until a satisfactory performance indicator is achieved;

[0042] The train station entry data encryption module specifically performs permission settings to ensure that only users with specific permissions can perform related operations, randomly selects random numbers, defines pseudo-random functions, and calculates key components obtained by data users. The data sender encrypts the plaintext and calculates the ciphertext;

[0043] The practical application module specifically feeds back carriage location information to relevant operators in real time based on train entry data for management operations.

[0044] The beneficial results achieved by the present invention using the above scheme are as follows:

[0045] (1) In view of the technical problem that the data of the current train station entry positioning model is complex and diverse, and it is difficult to sort out the dependency relationship between the positioning data and various influencing factors, resulting in inaccurate positioning, a certain model architecture is adopted to capture and extract the dependency relationship between the train station entry carriage positioning data and influencing factors through pre-processed train station entry data, and cross-validation is performed to evaluate the positioning accuracy, and the positioning is iterated repeatedly until satisfactory performance indicators are achieved;

[0046] (2) In order to address the technical problem that the security protection of train entry data is not in place, resulting in the leakage of train entry data and affecting the safe operation of trains, permission settings are adopted to ensure that only users with specific permissions can perform related operations, randomly select random numbers, define pseudo-random functions, and calculate the key components obtained by data users. The data sender encrypts the plaintext and calculates the ciphertext. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic diagram of a flow chart of a method for automatically identifying the position of a train carriage entering a station provided by the present invention;

[0048] Figure 2 A schematic diagram of a system for automatically identifying the position of a train carriage entering a station provided by the present invention;

[0049] Figure 3 is a schematic diagram of the process of step S3;

[0050] Figure 4 It is a schematic diagram of the process of step S4.

[0051] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0052] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0053] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0054] Example 1, see Figure 1 The present invention provides a method for automatically identifying the position of a train carriage entering a station, the method comprising the following steps:

[0055] Step S1: Collect train entry data, set up sensors, and obtain key data of train entry, including the length, spacing and speed of the carriages;

[0056] Step S2: Data preprocessing: clean the train entry data, remove invalid and erroneous data, classify and summarize according to train number and station, and standardize the time data;

[0057] Step S3: construct a train entry positioning model, determine the model architecture, capture and extract the dependency between the train entry carriage positioning data and influencing factors through the preprocessed train entry data, perform cross-validation to evaluate the positioning accuracy, and iterate repeatedly until satisfactory performance indicators are achieved;

[0058] Step S4: Encrypt the train entry data, set permissions to ensure that only users with specific permissions can perform related operations, randomly select random numbers, define pseudo-random functions, and calculate the key components obtained by the data user. The data sender encrypts the plaintext and calculates the ciphertext;

[0059] Step S5: practical application.

[0060] Example 2, see Figure 1 This embodiment is based on the above embodiment. In step S1, the acquisition of train entry data includes the following steps:

[0061] Step S11: Determine the sensor position, install sensors on the top, side and bottom of each carriage, and configure sensor parameters, including detection range, resolution and frame rate, to ensure that the sensors can meet the requirements of data collection;

[0062] Step S12: Connect the data acquisition system, connect the sensor to the data acquisition system, and collect train entry data in real time.

[0063] Example 3, see Figure 1 This embodiment is based on the above embodiment. In step S2, the data preprocessing is specifically to clean the train entry data, remove invalid and erroneous data, classify and summarize according to the train number and station, and standardize the time data.

[0064] Example 4, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. In step S3, the construction of the train carriage positioning model includes the following steps:

[0065] Step S31: Determine the positioning model architecture, including a forget gate, an input gate, an output gate, and a unit state;

[0066] Step S32: training the model, inputting the preprocessed train entry data into the model for training, effectively capturing and extracting the dependency between the train entry carriage positioning data and the influencing factors, the formula used is as follows:

[0067] ;

[0068] ;

[0069] In the formula, and are the outputs of the forward LSTM and backward LSTM at time t, and is the output of the forward LSTM and backward LSTM at time t-1, is the predicted output, is the forward factor, v is the backward factor, and T is the length of the time series;

[0070] Step S33: Perform cross validation and calculate the root mean square error index of the data to reflect the degree of deviation of the data error and determine whether the model accurately locates the train. The formula used is as follows:

[0071] ;

[0072] In the formula, represents the root mean square error index, n is the total data, is the predicted value of the i-th data, The actual value of the i-th data;

[0073] Step S34: Iterate the loop and further optimize the model parameters according to the results of cross-validation, including adjusting the learning rate, improving the number of neurons in the hidden layer, training and validating again, and repeating this process until satisfactory performance indicators are achieved.

[0074] By executing the above operations and adopting a determined model architecture, the pre-processed train entry data is used to capture and extract the dependency between the train entry carriage positioning data and the influencing factors, cross-validation is performed to evaluate the positioning accuracy, and the cycle is iterated until satisfactory performance indicators are achieved. This solves the technical problem that the current data for constructing the train entry positioning model is complex and diverse, and it is difficult to sort out the dependency between the positioning data and various influencing factors, resulting in inaccurate positioning.

[0075] Example 5, see Figure 1 and Figure 4 This embodiment is based on the above embodiment. In step S4, the train entry data is encrypted, including the following steps:

[0076] Step S41: Calculate the setting value corresponding to the train entry data protection authority to ensure that only users with specific train entry data protection authority can perform related operations. The formula used is as follows:

[0077] ;

[0078] Where k represents the first index of the train entry data protection authority, B k Indicates the setting value corresponding to the data protection authority for train entry, B indicates the setting value, e indicates the encryption function, g is the basic element, b k These are parameters related to data protection rights for train entry;

[0079] Step S42: Randomly select a random number and define a pseudo-random function, which increases the unpredictability and security of the train entry data, and calculates the output of the pseudo-random function. The formula used is as follows:

[0080] ;

[0081] In the formula, represents the output of the pseudo-random function, a k and a j is a randomly selected random number used for the calculation of pseudo-random functions, s k，j is a specific parameter value, u represents the user's input, j represents the second index of the train entry data protection authority, and j≠k;

[0082] Step S43: Calculate the key components obtained by the data user to ensure that the data user can only obtain the key components that have been specially processed. The key components include encryption keys and initialization vectors, which are used to decrypt data. Data access is strictly controlled by permissions. The formula used is as follows:

[0083] ;

[0084] Where D k，j represents the key component of train station data user acquisition, R k，j represents a random variable;

[0085] Step S44: Calculate the ciphertext of the train entry data. The data sender encrypts the plaintext m and calculates the ciphertext. The formula used is as follows:

[0086] ;

[0087] In the formula, CT represents the ciphertext of train entry data, i.e. the encrypted train entry data, E 0 Indicates the first part of the ciphertext, E 1 Represents the second part of the ciphertext, and s is the random number used to calculate the ciphertext.

[0088] By performing the above operations, permission settings are adopted to ensure that only users with specific permissions can perform related operations, random numbers are randomly selected, pseudo-random functions are defined, and key components obtained by data users are calculated. The data sender encrypts the plaintext and calculates the ciphertext, which solves the technical problem of inadequate security protection of train entry data, resulting in leakage of train entry data and affecting the safe operation of trains.

[0089] Example 6, see Figure 1 This embodiment is based on the above embodiment. In step S5, the actual application is to feed back the carriage position information to relevant operators in real time according to the train entry data for management operations.

[0090] Embodiment 7, see Figure 2 , this embodiment is based on the above embodiment, and the present invention provides a system for automatically identifying the position of a train entering a station carriage, including a module for collecting train entering a station data, a data preprocessing module, a module for building a train entering a station positioning model, a module for encrypting train entering a station data, and a practical application module;

[0091] The module for collecting train entry data is specifically to set sensors to obtain key data of train entry, including the length, spacing and speed of the carriages;

[0092] The data preprocessing module specifically cleans the train station entry data, removes invalid and erroneous data, classifies and summarizes them according to train numbers and stations, and standardizes and organizes the time data;

[0093] The train station entry positioning model module is constructed, specifically determining the model architecture, capturing and extracting the dependency between the train station entry carriage positioning data and the influencing factors through the preprocessed train station entry data, performing cross-validation to evaluate the positioning accuracy, and iterating repeatedly until a satisfactory performance indicator is achieved;

[0094] The train station entry data encryption module specifically performs permission settings to ensure that only users with specific permissions can perform related operations, randomly selects random numbers, defines pseudo-random functions, and calculates key components obtained by data users. The data sender encrypts the plaintext and calculates the ciphertext;

[0095] The practical application module specifically feeds back carriage location information to relevant operators in real time based on train entry data for management operations.

[0096] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0097] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0098] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A method for automatically identifying the position of a train carriage entering a station, characterized in that: The method comprises the following steps: Step S1: Collect train entry data; Step S2: data preprocessing; Step S3: construct a train entry positioning model, adopt a certain model architecture, capture and extract the dependency between the train entry carriage positioning data and influencing factors through the pre-processed train entry data, perform cross-validation to evaluate the positioning accuracy, and iterate repeatedly until satisfactory performance indicators are achieved; Step S4: Encrypt the train entry data, set permissions to ensure that only users with specific permissions can perform related operations, randomly select random numbers, define pseudo-random functions, and calculate the key components obtained by the data user. The data sender encrypts the plaintext and calculates the ciphertext; Step S5: practical application.

2. The method for automatically identifying the position of a train carriage entering a station according to claim 1, characterized in that: In step S3, the construction of the train entry positioning model includes the following steps: Step S31: Determine the positioning model architecture; Step S32: training the model, inputting the preprocessed train entry data into the model for training, effectively capturing and extracting the dependency between the train entry carriage positioning data and the influencing factors, the formula used is as follows: ； ； In the formula, and are the outputs of the forward LSTM and backward LSTM at time t, and is the output of the forward LSTM and backward LSTM at time t-1, is the predicted output, is the forward factor, v is the backward factor, and T is the length of the time series; Step S33: Perform cross validation and calculate the root mean square error index of the data to reflect the degree of deviation of the data error and determine whether the model accurately locates the train. The formula used is as follows: ； In the formula, represents the root mean square error index, n is the total data, is the predicted value of the i-th data, The actual value of the i-th data; Step S34: Iterate the loop and further optimize the model parameters according to the cross-validation results. Repeat this process until satisfactory performance indicators are achieved.

3. The method for automatically identifying the position of a train carriage entering a station according to claim 1, characterized in that: In step S4, the train entry data is encrypted, including the following steps: Step S41: Calculate the setting value corresponding to the train entry data protection authority to ensure that only users with specific train entry data protection authority can perform related operations. The formula used is as follows: ； Where k represents the first index of the train entry data protection authority, B k Indicates the setting value corresponding to the data protection authority for train entry, B indicates the setting value, e indicates the encryption function, g is the basic element, b k These are parameters related to data protection rights for train entry; Step S42: Randomly select a random number, define a pseudo-random function, increase the unpredictability and security of the train entry data, and calculate the output of the pseudo-random function. The formula used is as follows: ； In the formula, represents the output of the pseudo-random function, a k and a j is a randomly selected random number used for the calculation of pseudo-random functions, s k，j is a specific parameter value, u represents the user's input, j represents the second index of the train entry data protection authority, and j≠k; Step S43: Calculate the key components obtained by the data user to ensure that the data user can only obtain the key components that have been specially processed. The key components include encryption keys and initialization vectors, which are used to decrypt data. Data access is strictly controlled by permissions. The formula used is as follows: ； Where D k，j represents the key component of train station data user acquisition, R k，j represents a random variable; Step S44: Calculate the ciphertext of the train entry data. The data sender encrypts the plaintext m and calculates the ciphertext. The formula used is as follows: ； In the formula, CT represents the ciphertext of train entry data, that is, the encrypted train entry data, E0 represents the first part of the ciphertext, E1 represents the second part of the ciphertext, and s is the random number used to calculate the ciphertext.

4. The method for automatically identifying the position of a train carriage entering a station according to claim 1, characterized in that: In step S1, the acquisition of train entry data includes the following steps: Step S11: determine the sensor positions, install sensors on the top, sides and bottom of each carriage, and configure sensor parameters; Step S12: Connect the data acquisition system, connect the sensor to the data acquisition system, and collect train entry data in real time.

5. The method for automatically identifying the position of a train carriage entering a station according to claim 1, characterized in that: In step S2, the data is preprocessed, specifically, the train entry data is cleaned, invalid and erroneous data is removed, the data is classified and summarized according to the train number and station, and the time data is standardized.

6. The method for automatically identifying the position of a train carriage entering a station according to claim 1, characterized in that: In step S5, the actual application is to feed back the carriage position information to relevant operators in real time according to the train entry data for management operations.

7. A system for automatically identifying the position of a train carriage entering a station, used to implement a method for automatically identifying the position of a train carriage entering a station as claimed in any one of claims 1 to 6, characterized in that: It includes a module for collecting train entry data, a data preprocessing module, a module for building a train entry positioning model, a module for encrypting train entry data and a practical application module.

8. The automatic identification system for train carriage position entering a station according to claim 7, characterized in that: The module for collecting train entry data is specifically configured to set sensors to obtain key data of train entry; The data preprocessing module specifically cleans the train station entry data, removes invalid and erroneous data, classifies and summarizes them according to train numbers and stations, and standardizes and organizes the time data; The train station entry positioning model module is constructed, specifically determining the model architecture, capturing and extracting the dependency between the train station entry carriage positioning data and the influencing factors through the preprocessed train station entry data, performing cross-validation to evaluate the positioning accuracy, and iterating repeatedly until a satisfactory performance indicator is achieved; The train station entry data encryption module specifically performs permission settings to ensure that only users with specific permissions can perform related operations, randomly selects random numbers, defines pseudo-random functions, and calculates key components obtained by data users. The data sender encrypts the plaintext and calculates the ciphertext; The practical application module specifically feeds back carriage location information to relevant operators in real time based on train entry data for management operations.

Images