Intelligent prediction method for train receiving and dispatching route occupation time of railway technology station

Abstract

The invention discloses an intelligent prediction method for train receiving and departure route occupation time of a railway technology station, and aims at the train receiving and departure operation process of the railway technology station, mass data accumulated in the daily production process is utilized to scientifically and accurately calculate the route occupation time required in different operation links of a train. The driving command personnel can know the future execution progress of each operation in advance, the labor intensity can be reduced, and the operation efficiency can be improved. Meanwhile, more accurate time parameters are provided for station transportation production organization decision making, the station capacity utilization rate is improved, and a foundation is laid for intelligent transformation of a future railway technology station.

Description

Technical Field

[0001] The present invention relates to the field of rail transit technology, and in particular to a method for intelligently predicting the occupancy time of train receiving and dispatching routes at a railway technical station. Background Art

[0002] As a key node in the railway transportation network, the railway technical station is responsible for the arrival and departure, unmarshaling, and locomotive replacement of railway freight trains. The transportation production operations are busy, and the route resources in the station are very tight. In the same throat area of ​​the technical station, the train routes, shunting routes, and service locomotive routes are arranged in an intersecting manner, and there will be conflicts between the routes in time and space, which will affect each other's operating efficiency and driving safety.

[0003] In the actual production process, due to uneven traffic, equipment failure, construction work, weather and human factors, most of the freight trains arriving and departing from the technical station are delayed. At present, we can only rely on experienced train controllers to find opportunities according to the station status, operation conditions, interlocking relationships and other conditions, and complete the route selection through manual intervention to perform operations. Train controllers are highly concentrated for a long time, which is prone to omissions and errors, which can easily lead to safety accidents and restrict the transportation organization and turnover efficiency of the entire railway freight hub.

[0004] The Chinese invention patent application with application number 201911077494.2, "A method for predicting the arrival time of a high-speed railway train based on a dispatching and command system", discloses a method for predicting the arrival time of a high-speed railway train based on a dispatching and command system, including: standardizing the historical data of the dispatching and command system, constructing a spatiotemporal state data processing model based on block partitions and discretized train trajectories, extracting the spatiotemporal data of train operation, and standardizing it; estimating the block partition operation time parameters of various types of trains in the actual operating environment by analyzing the standardized historical driving data; using the estimated block partition operation time parameters, combined with the real-time operating environment status and train status, predicting the signal status in a period of time in the future, and finally realizing the prediction of the train arrival time through the mutual constraints and interaction between the train and signal status.

[0005] However, this patent application provides a method for predicting the arrival time of high-speed railway trains. High-speed railways are characterized by running according to a schedule and stable operation, which is quite different from the flexible operation scenarios of railway technical stations. The operating processes of high-speed railways and railway technical stations are affected by different factors. Therefore, the solution of this patent application cannot be applied to the prediction of the occupancy time of train reception and dispatching routes at railway technical stations.

[0006] In view of this, the present invention is proposed. Summary of the invention

[0007] The purpose of the present invention is to provide an intelligent prediction method for the occupancy time of train receiving and dispatching routes at railway technical stations. According to the train receiving and dispatching operation process at railway technical stations, the occupancy time of trains to be operated can be accurately calculated in combination with massive daily data.

[0008] The objective of the present invention is achieved through the following technical solutions:

[0009] A method for intelligently predicting the occupancy time of train receiving and dispatching routes at a railway technical station, comprising:

[0010] Analyze the train receiving and dispatching process at the railway technical station and determine the factors affecting the time occupied by the receiving and dispatching routes;

[0011] The determined influencing factors are used as characteristic parameters to collect corresponding data, and after processing, a training set and a test set are obtained;

[0012] Using the training set to establish an intelligent prediction model, using the intelligent prediction model to predict the test set, and using the prediction results to optimize the model parameters;

[0013] After the optimization is completed, the characteristic value of the current operation route instruction is extracted in combination with the determined influencing factors, and input into the optimized intelligent prediction model to obtain the predicted value of the occupancy time of each route.

[0014] It can be seen from the technical solution provided by the present invention that by using the massive data accumulated in the daily production process, the time required for the route in different operation links of the train can be scientifically and accurately calculated, and the driving commander can know the future execution progress of each operation in advance, which can reduce their labor intensity and improve work efficiency. At the same time, it also provides more accurate time parameters for station transportation production organization decision-making, realizes the improvement of station capacity utilization, and lays the foundation for the intelligent transformation of future railway technical stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0016] Figure 1 A flow chart of a method for intelligently predicting the occupancy time of train receiving and dispatching routes at a railway technical station provided by an embodiment of the present invention;

[0017] Figure 2 An analysis diagram of the operation process of a passing train and a terminating train of a technical station provided in an embodiment of the present invention;

[0018] Figure 3An analysis diagram of the operation process of a train originating from a technical station provided in an embodiment of the present invention;

[0019] Figure 4 A flow chart of a random forest regression prediction model provided by an embodiment of the present invention;

[0020] Figure 5 A schematic diagram of an application scheme of a route occupancy time prediction model provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] The following is a clear and complete description of the technical solutions in the embodiments of the present invention 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, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of the present invention.

[0022] First, the terms that may be used in this article are explained as follows:

[0023] The terms "include", "comprises", "contains", "has" or other descriptions with similar semantics should be interpreted as non-exclusive inclusion. For example, including certain technical feature elements (such as raw materials, components, ingredients, carriers, dosage forms, materials, dimensions, parts, components, mechanisms, devices, steps, procedures, methods, reaction conditions, processing conditions, parameters, algorithms, signals, data, products or products, etc.) should be interpreted as including not only certain technical feature elements explicitly listed, but also other technical feature elements known in the art that are not explicitly listed.

[0024] The term "consisting of..." means excluding any technical feature elements not explicitly listed. If this term is used in a claim, it will make the claim closed, so that it does not contain technical feature elements other than the technical feature elements explicitly listed, except for the conventional impurities related to them. If this term only appears in a clause of a claim, it only limits the elements explicitly listed in the clause, and the elements recorded in other clauses are not excluded from the overall claim.

[0025] The following is a detailed description of a method for intelligently predicting the occupancy time of a train receiving and dispatching route at a railway technical station provided by the present invention. The contents not described in detail in the embodiments of the present invention belong to the prior art known to professional and technical personnel in the field. If no specific conditions are specified in the embodiments of the present invention, the conventional conditions in the field or the conditions recommended by the manufacturer shall be followed.

[0026] like Figure 1As shown, it is a flowchart of a method for intelligently predicting the occupancy time of a railway technical station train receiving and dispatching route provided by an embodiment of the present invention. The method for intelligently predicting the occupancy time of a railway technical station train receiving and dispatching route can be abstracted as follows: for the same route, the route occupancy time is predicted according to the known influencing factors of different operation processes. The input is a series of numerical feature data or classification feature data, and the output is the occupancy time interval range of the entire route. The overall step flow is as follows:

[0027] (1) Analyze the train reception and dispatching process at the railway technical station and determine the factors that affect the time occupied by the reception and dispatching routes.

[0028] (2) The corresponding data is collected using the determined influencing factors as characteristic parameters, and after processing, the training set and the test set are obtained.

[0029] (3) using the training set to establish an intelligent prediction model, using the intelligent prediction model to predict the test set, and using the prediction results to optimize the model parameters;

[0030] (4) After the optimization is completed, the characteristic value of the current operation route instruction (on-site real-time data) is extracted in combination with the determined influencing factors and input into the optimized intelligent prediction model to obtain the predicted value of the occupancy time of each route.

[0031] In order to more clearly demonstrate the technical solution and technical effects provided by the present invention, the method provided by the embodiment of the present invention is described in detail with reference to specific embodiments below.

[0032] 1. Analyze the operation process and determine the influencing factors.

[0033] In actual production, the train controllers shall promptly handle the procedures for receiving and dispatching trains and open the routes for receiving and dispatching trains according to the stage plan requirements issued by the train dispatcher of the dispatching office to ensure the safety and punctuality of the trains. Trains in technical stations can be divided into three types according to the types of receiving and dispatching trains: final arrival trains, departure trains, and passing trains. The factors affecting the route occupancy time of different types of receiving and dispatching trains are different. Therefore, for different types, the receiving and dispatching train operation processes are analyzed separately to determine the factors affecting the route occupancy time of receiving and dispatching trains.

[0034] 1. The final train arrival.

[0035] In the embodiment of the present invention, for the type of train arriving at the terminal, the influencing factors of the time of occupying the receiving route are determined in combination with the receiving operation process; specifically: for the type of train arriving at the terminal, starting from the time when the station agrees that the neighboring station A has completed the departure procedures until the train completely enters the track and stops, it is the entire receiving operation process of the train arriving at the terminal, including: the departure procedures at station A, the opening of the departure route at station A, the train pressing the exit signal of station A, the train pressing the red departure section of station A, the train pressing the red approach section of this station, the opening of the receiving route at this station, and the complete entry of the train into the track; taking the departure procedures at station A as the starting point for calculation, and other operation processes as key adjustment points, the operation time between all two adjacent key adjustment points constitutes the occupation time of the receiving route of the terminal train at this station (from the opening of the route at this station to the complete entry of the train into the track); the operation time between each two adjacent key adjustment points is analyzed separately to obtain the corresponding influencing factors.

[0036] like Figure 2 As shown in the figure, it is an analysis diagram of the operation process of the technical station passing train and the terminal train; for the terminal train, the seven operation processes involved, the operation time between two adjacent key adjustment points corresponds to Figure 2 t1, t2, T2, T3, t3, t5 in.

[0037] By sorting out the factors that affect the time required for each operation process, the main ones are as follows:

[0038] t1 influencing factors: operating habits of the duty officer.

[0039] Factors affecting t2: types of trains arriving and departing from adjacent stations, train type, total train weight, number of vehicles, weather conditions, and speed limit conditions.

[0040] T2 influencing factors: route, speed limit conditions, train type, total train weight, and number of vehicles on the train.

[0041] T3 influencing factors: train type, total train weight, number of vehicles in the train, and speed limit conditions.

[0042] t3 influencing factors: timing of route opening.

[0043] Factors affecting t5: route, speed limit conditions, train type, train arrival and departure types, total train weight, and number of vehicles on the train.

[0044] 2. Departure train.

[0045] In the embodiment of the present invention, for the type of originating train, the influencing factors of the departure route occupancy time are determined in combination with the departure operation process; specifically: for the type of originating train, from the time when this station applies for the departure notice procedure to the time when the train completely enters the departure section, it is the entire departure operation process of the originating train, including: the departure procedures at this station, the opening of the departure route at this station, the train pressing the station exit signal off, and the train pressing the red departure section of this station; taking the departure procedures at this station as the starting point for calculation, and other operation processes as key adjustment points, the operation time between all two adjacent key adjustment points constitutes the occupation time of the departure route of the originating train at this station (from the opening of the departure route at this station to the complete entry of the train into the departure section); the operation time between each two adjacent key adjustment points is analyzed separately to obtain the corresponding influencing factors.

[0046] like Figure 3 As shown in the figure, it is an analysis diagram of the operation process of the departure train of the technical station. For the four operation processes involved in the departure train, the operation time between two adjacent key adjustment points corresponds to Figure 3 Among them are t6, t7, and T9.

[0047] By sorting out the factors that affect the time required for each operation process, the main ones are as follows:

[0048] t6 Influencing factors: operating habits of the duty officer.

[0049] t7 influencing factors: train type, total train weight, number of vehicles, weather conditions, and speed limit conditions.

[0050] T9 influencing factors: route, speed limit conditions, train type, total train weight, and number of vehicles on the train.

[0051] 3. Passing train.

[0052] In an embodiment of the present invention, for the passing train type, combined with the receiving and dispatching operation process, the influencing factors of the receiving and dispatching route occupancy time are determined; specifically: for the passing train type, from the time when the station agrees that the neighboring station A has completed the departure procedures to the time when the train completely enters the departure section of the station, it is the entire receiving and dispatching operation process of the passing train, including: station A handles the departure procedures, station A’s departure route is open, the train presses the exit signal of station A, the train presses the red departure section of station A, the train presses the red approach section of the station, the receiving route of the station is open, the departure procedures of the station are handled, the departure route of the station is open, the train completely enters the track, the train presses the exit signal of the station and the train presses the red departure section of the station; taking station A handling the departure procedures as the starting point for calculation, and other operation processes as key adjustment points, the operation time between all two adjacent key adjustment points constitutes the occupation time of the passing train receiving route and the dispatching route at the station; the operation time between each two adjacent key adjustment points is analyzed separately to obtain the corresponding influencing factors.

[0053] like Figure 2 As shown, for the eleven operation processes involved in the originating train, the operation time between any two adjacent key adjustment points is t1, t2, T2, T3, t3, t4, t6, t7, T6, and T7 respectively.

[0054] By sorting out the factors affecting the time required for each operation process, in addition to the time required for the operation process mentioned by the terminal train and the originating train, the factors affecting the operation time that are not mentioned are mainly as follows:

[0055] Factors affecting t4: route, speed limit conditions, train type, train arrival and departure types, total train weight, and number of vehicles on the train.

[0056] T6 influencing factors: train type, total train weight, number of vehicles, weather conditions, and speed limit conditions.

[0057] T7 influencing factors: route, speed limit conditions, train type, total train weight, and number of vehicles on the train.

[0058] It should be noted that the foregoing provides examples of influencing factors corresponding to various operation times. In actual applications, users can also adjust the influencing factors according to actual conditions or experience.

[0059] 2. Massive data collection, processing and feature variable selection.

[0060] In an embodiment of the present invention, by collecting station representation information, the operation route is searched in combination with the train number window information, the occupancy and clearance information of the sections within the route are collected, and the tracking result information including the route is formed, and the tracking result information is saved in a database; at the same time, the tracking result information and the executed operation plan are associated to obtain relevant information of the train; the above information all belongs to historical data; using the determined influencing factors as characteristic parameters, the corresponding data is collected from the above historical data; for the influencing factors not included in the historical data, the corresponding influencing factors are used as the primary key for data collection; finally, the data corresponding to all the determined influencing factors are obtained.

[0061] In the embodiment of the present invention, the data is standardized and normalized according to the characteristics of different influencing factors, and the influencing factors are divided into numerical feature influencing factors and classification feature influencing factors. The collected data belonging to the numerical feature influencing factors are normalized. Specifically, the numerical feature is a type of feature whose feature value is a number. In order to eliminate the influence of the unit and scale differences between the features and treat each dimension of the feature equally, the features need to be normalized. The standard deviation is used for normalization, that is, the feature value is scaled to a state with a mean of 0 and a variance of 1, which can reduce the influence of the feature with too large value on the accuracy of the training model. One-hot feature encoding is performed on the collected data belonging to the classification feature influencing factors; specifically, the classification feature is a type of feature whose feature value is different categories. Different classification features usually have values ​​of characters with different meanings. In order to enable the training model to recognize its meaning and perform processing operations, one-hot feature encoding is required.

[0062] Afterwards, the processed data is divided into a training set and a test set according to a set ratio. For example, the Bootstrap sampling method can be used to divide the processed data into a training set and a test set according to a ratio of 2 to 1.

[0063] Taking the prediction of the route occupancy time of the terminal train as an example, assuming that time t is the time when the departure procedures of station A are handled at the adjacent station, then the route occupancy time range is set as a=t1+t2+T2+T3+t3, that is, the prediction target is the time range of [t+a,t+a+t5]. The influencing factors are summarized in Table 1.

[0064] Table 1: Summary of influencing factors

[0065]

[0066] The relevant functions of the predictive variables were screened, and Spearman correlation analysis was performed on the 9 characteristic variables and the predicted target values. The characteristic variables with significant correlation with the predicted target values ​​were selected as the input variables of the prediction model, and the available data sets of multiple characteristic variables and predicted target values ​​were obtained, as shown in Table 2.

[0067] Table 2: Available datasets

[0068]

[0069] 3. Construction and training of intelligent prediction models.

[0070] In the embodiment of the present invention, the model type can be selected according to actual needs, for example, it can be a random forest model, a recurrent neural network model, a convolutional neural network model, a support vector machine model, etc. The random forest model is taken as an example for introduction.

[0071] The training set obtained through the above scheme is used to train and build the model, and the test set is used to measure the prediction performance of the model. Using the idea of ​​random forest regression, an intelligent prediction model based on random forest is constructed to obtain the final prediction value, such as Figure 4 As shown, the main steps are:

[0072] (1) Load the training set for model training.

[0073] (2) Random sampling. Randomly extracting a number of samples from the training set to form a sample set, the size of the sample set is the same as the training set, this sampling method is called random sampling. Usually, data preprocessing has been completed before forming the training set, and sampling with replacement can make the number of sample sets the same as the training set.

[0074] (3) Construct a decision tree. For each sample set, a decision tree is constructed using the random feature selection method, and multiple decision trees are finally obtained. When constructing a decision tree, the Gini index is used for feature selection and node partitioning.

[0075] (4) Ensemble decision trees. For the multiple decision trees that have been constructed, they are combined into a random forest model; for example, classification can be performed by calculating the average or vote of the classification results of each sample in each decision tree.

[0076] (5) Result prediction. Use the constructed random forest model to perform classification or regression prediction on the test set, obtain the result of each decision tree, take the average value as the model output result, and finally complete the training.

[0077] (6) Evaluate model performance. Evaluate the performance of the random forest model based on the model output results, and adjust the model parameters based on the evaluation results. For example, a method such as cross-validation can be used to evaluate the performance of the random forest model, and operations such as parameter tuning can be performed.

[0078] 4. Prediction of route occupancy time.

[0079] Based on the above scheme, an intelligent prediction model that can be applied in practice is obtained. The real-time data on site is input into the intelligent prediction model to obtain accurate route occupancy time prediction results, and provided to the station control system for necessary autonomous calculations and safety card control. Preferably, after the train operation is completed, the actual train operation time is recorded and compared with the predicted value of the occupancy time of the corresponding route, the error rate is calculated, and it is determined whether the error rate is within the set range; if not, the data is updated to the data set to retrain the intelligent prediction model.

[0080] like Figure 5 The figure shows the application process of the route occupancy time prediction model, which mainly includes:

[0081] (1) After the operator selects a train operation task on the station control system and starts the operation, the system decomposes the train operation plan and obtains the operation route instruction.

[0082] (2) The characteristic value of the operation is passed to the intelligent prediction model to obtain the predicted value of the occupancy time of each route.

[0083] (3) When the route arrangement is completed, the corresponding operations are carried out. After the train operation is completed, the actual train operation time is recorded, compared with the predicted value, and the error rate is calculated (the acceptable error rate range is set by experts) to determine whether the error is acceptable.

[0084] (4) If the error rate is acceptable, the prediction is terminated; if the error rate requirement is not met, the data involved in the prediction process is updated to the training set to retrain the prediction model to obtain a new optimized prediction model. The data involved in the prediction process described here mainly include: characteristic values ​​(influencing factors), actual train operation time, and may also include the occupancy time prediction value.

[0085] The above-mentioned scheme provided by the embodiment of the present invention is aimed at the operation process of the train commander, and combined with massive daily data, it can accurately calculate the occupancy time of the receiving and dispatching routes of the trains to be operated, and can provide auxiliary decision-making and adjustment for the train commander. It is of great significance to improve the level of railway transportation train command and operation control, strengthen the overall throughput capacity of the station, optimize scheduling, improve transportation efficiency and ensure driving safety.

[0086] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above embodiments can be implemented by software, or by means of software plus necessary general hardware platforms. Based on such understanding, the technical solutions of the above embodiments can be embodied in the form of software products, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0087] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for intelligently predicting the occupancy time of train receiving and dispatching routes at railway technical stations, characterized in that: include: Analyze the train receiving and dispatching process at the railway technical station and determine the factors affecting the time occupied by the receiving and dispatching routes; The determined influencing factors are used as characteristic parameters to collect corresponding data, and after processing, a training set and a test set are obtained; Using the training set to establish an intelligent prediction model, using the intelligent prediction model to predict the test set, and using the prediction results to optimize the model parameters; After the optimization is completed, the characteristic value of the current operation route instruction is extracted in combination with the determined influencing factors, and input into the optimized intelligent prediction model to obtain the predicted value of the occupancy time of each route.

2. According to claim 1, a method for intelligently predicting the occupancy time of train receiving and dispatching routes at railway technical stations is characterized in that: The analysis of the train receiving and dispatching operation process of the railway technical station and the factors affecting the occupancy time of the receiving and dispatching route include: The types of trains received and dispatched at railway technical stations are divided into three types: final arrival trains, originating trains and passing trains. For different types, the receiving and dispatching operation processes are analyzed separately to determine the influencing factors of the receiving and dispatching route occupancy time.

3. According to claim 2, a method for intelligently predicting the occupancy time of train receiving and dispatching routes at railway technical stations is characterized in that: It also includes: for the type of train arriving at the terminal, combined with the train receiving operation process, determining the factors affecting the time of the train receiving route; For the type of train that is arriving at the final station, the entire process of receiving the train for the final train begins when this station agrees with the neighboring station A to complete the departure formalities, and ends when the train completely enters the track and stops. This process includes: the departure formalities at station A, the opening of the departure route at station A, the train turning off the exit signal at station A, the train turning on the red signal in the departure section of station A, the train turning on the red signal in the approach section of this station, the opening of the receiving route at this station, and the train completely entering the track. The departure formalities at station A are taken as the starting point for calculation, and the other operation processes are taken as the key adjustment points. The operation time between all two adjacent key adjustment points constitutes the occupation time of the receiving route for the final train at this station. The operation time between each pair of adjacent key adjustment points is analyzed separately to obtain the corresponding influencing factors.

4. According to claim 2, a method for intelligently predicting the occupancy time of train receiving and dispatching routes at railway technical stations is characterized in that: Also includes: For the type of the departure train, determine the factors affecting the departure route occupancy time in combination with the departure operation process; For the type of originating train, the entire departure operation process of the originating train starts from the application of departure notice procedures at this station to the complete entry of the train into the departure section, including: the departure procedures at this station, the opening of the departure route at this station, the turning off of the exit signal at this station, and the turning on of the train to leave the departure section at this station; the departure procedures at this station are taken as the starting point for calculation, and other operation processes are taken as key adjustment points. The operation time between all two adjacent key adjustment points constitutes the occupation time of the departure route of the originating train at this station; The operation time between each pair of adjacent key adjustment points is analyzed separately to obtain the corresponding influencing factors.

5. According to claim 2, a method for intelligently predicting the occupancy time of train receiving and dispatching routes at railway technical stations is characterized in that: It also includes: for the type of passing trains, combined with the receiving and dispatching operation process, determining the factors affecting the occupancy time of the receiving and dispatching route; For the passing train type, the entire receiving and dispatching operation process of the passing train starts from the time when this station agrees with the neighboring station A to complete the departure formalities until the train completely enters the departure section of this station, including: the departure formalities at station A, the opening of the departure route at station A, the train turns off the departure signal at station A, the train turns on the red departure section of station A, the train turns on the red approach section of this station, the receiving route at this station is open, the departure formalities at this station, the departure route at this station is open, the train completely enters the track, the train turns off the departure signal at this station, and the train turns on the red departure section of this station; Taking the departure formalities at Station A as the starting point for calculation, and other operation processes as key adjustment points, the operation time between all two adjacent key adjustment points constitutes the occupancy time of the train receiving route and the departure route at this station; The operation time between each pair of adjacent key adjustment points is analyzed separately to obtain the corresponding influencing factors.

6. According to claim 1, a method for intelligently predicting the occupancy time of train receiving and dispatching routes at railway technical stations is characterized in that: The method of collecting corresponding data by using the determined influencing factors as characteristic parameters includes: By collecting station information, combined with the train number window information, the operation route is searched, the occupation and clearance information of the sections within the route is collected, and the tracking result information including the route is formed, and the tracking result information is saved in the database; at the same time, the tracking result information and the executed operation plan are associated to obtain the relevant information of the train; the above information belongs to historical data; the determined influencing factors are used as characteristic parameters, and the corresponding data is collected from the above historical data; For influencing factors not included in historical data, data collection is performed using the corresponding influencing factors as the primary key; Finally, the data corresponding to all determined influencing factors are obtained.

7. The method for intelligently predicting the occupancy time of train receiving and dispatching routes at railway technical stations according to claim 1 or 6, characterized in that: After the processing, the training set and the test set are obtained, including: The influencing factors are divided into numerical feature influencing factors and categorical feature influencing factors; the collected data belonging to the numerical feature influencing factors are normalized; the collected data belonging to the categorical feature influencing factors are subjected to one-hot feature encoding; The processed data is divided into training set and test set according to the set ratio.

8. The method for intelligently predicting the occupancy time of train receiving and dispatching routes at railway technical stations according to claim 1 is characterized in that: The using the training set to establish an intelligent prediction model, predicting the test set by the intelligent prediction model, and optimizing the model parameters by using the prediction results include: Loading the training set; Randomly select a sample set from the training set; For each sample set, a decision tree is constructed using the random feature selection method, and multiple decision trees are finally obtained; For the multiple decision trees that have been constructed, they are combined into a random forest model as an intelligent prediction model; Use the constructed random forest model to perform classification or regression prediction on the test set to obtain the model output results; The model output results are used to evaluate the performance of the random forest model, and the model parameters are adjusted according to the evaluation results.

9. The method for intelligently predicting the occupancy time of train receiving and dispatching routes at railway technical stations according to claim 1 is characterized in that: After obtaining the predicted occupancy time of each route, it also includes: After the train operation is completed, the actual train operation time is recorded and compared with the predicted value of the occupancy time of the corresponding route, the error rate is calculated, and it is determined whether the error rate is within the set range; If not, the data involved in the prediction process is updated to the training set to retrain the intelligent prediction model.

Images