Railway freight transport safety evaluation method and system based on data analysis

Abstract

The application discloses a railway freight safety evaluation method and system based on data analysis, and relates to the field of railway freight, and comprises the following steps: an uploading module is used for uploading and storing attribute data of transported goods corresponding to a current railway freight task; a calibration module is used for traversing the attribute data of goods stored in the uploading module, and evaluating and calibrating an upper limit value of a transport speed corresponding to the freight task based on the attribute data of goods; and the application can accurately evaluate the upper limit of the freight speed and the optimal driving speed of each section according to the characteristics of goods, the load distribution of the carriage and the real-time road conditions of the line, smoothly transition when the speed is changed, effectively reduce the risk of goods overturning and deformation, and effectively improve the safety of the whole railway freight.

Description

Technical Field

[0001] This invention relates to the field of railway freight technology, specifically to a railway freight safety assessment method and system based on data analysis. Background Technology

[0002] Railway freight is the core carrier of bulk commodity transportation in my country, and its safe and stable operation is directly related to national economic development and the safety of people's lives and property. Currently, railway freight has gradually introduced intelligent detection systems such as TFDS, combined with manual inspections for safety management, accumulating massive amounts of multi-source data on vehicle inspection, track status, and operational processes. The rapid development and widespread adoption of data analysis technology provides crucial technical support for achieving precise and efficient assessment of railway freight safety.

[0003] Patent application number 201811625878.9 discloses a method and system for assessing the operational safety of railway freight trains. This application aims to address the problem that "traditional freight train operation status monitoring primarily relies on overweight and over-limit monitoring. Typically, a data module transmits received information to a monitoring module, which then sends a signal to an alarm module to trigger an alarm. However, this overweight and over-limit monitoring method is only effective for single-car freight trains. For multi-car high-speed freight trains, this method can easily lead to unreasonable cargo distribution between carriages, potentially causing serious accidents such as derailment due to excessive longitudinal impact."

[0004] However, in the current railway freight scenario, there is no complete technology to assess the upper limit of transportation speed based on the attributes of the transported goods and to evaluate the optimal transportation speed in real time based on the road conditions of the transportation route to support railway freight safety.

[0005] To this end, we propose a data analysis-based method and system for railway freight safety assessment. Summary of the Invention

[0006] In view of the above-mentioned shortcomings of the existing technology, the present invention provides a railway freight safety assessment method and system based on data analysis, which can effectively solve the problems of the existing technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions; This invention discloses a railway freight safety assessment system based on data analysis, comprising: The upload module is used to upload and store the attribute data of the goods transported for the current railway freight task; The calibration module iterates through the cargo attribute data stored in the upload module and evaluates and calibrates the upper limit of transportation speed corresponding to this freight task based on the cargo attribute data. The load acquisition module collects the static load distribution data of each carriage of this freight train and stores the static load distribution data of each carriage with different labels. The road condition acquisition module obtains the real-time road condition data of the entire transportation route of this freight task and simultaneously marks the speed adjustment nodes of the entire route. The speed adjustment module combines the calibrated upper limit of transportation speed, the static load distribution data of each carriage, the real-time road condition data, and the speed adjustment nodes to evaluate the real-time optimal transportation speed of the corresponding route. The output module organizes the calculated real-time optimal transportation speed data into railway freight safety assessment data of the corresponding transportation route and outputs it to the freight train control terminal. The upload module is interconnected with the calibration module via a wireless network. The calibration module is interconnected with the load acquisition module and the road condition acquisition module via a wireless network. The load acquisition module and the road condition acquisition module are interconnected with the pacing module via a wireless network. The output module is interconnected with the upload module, the calibration module, the load acquisition module, the road condition acquisition module, and the pacing module via a wireless network.

[0008] Furthermore, during the operation of the upload module, the uploaded cargo attribute data is simultaneously subjected to compliance verification and standardized preprocessing. The cargo attribute data includes the cargo's equivalent center of gravity height, number of stacking layers, packaging shear strength, fixing method constraint strength, cargo deformation critical acceleration, cargo overturning critical acceleration, and cargo embargo environment threshold. The compliance verification process involves removing abnormal data that exceeds the preset data format range. The standardization preprocessing process involves converting the verified cargo attribute data into a standardized dataset with a unified dimension, and uniquely binding and storing the standardized dataset with the unique identifier and train formation information of this freight mission.

[0009] Furthermore, the calibration module traverses the standardized dataset bound to the storage, extracts the critical acceleration for overturning of the cargo and the equivalent center of gravity height, and combines this with the minimum curve radius of the entire transportation path for this freight mission and the fixed wheelbase of the freight train bogie to calculate the upper limit of the transportation speed corresponding to this freight mission through the critical speed balance model: ; In the formula: This is the maximum transport speed limit for this freight mission; The critical acceleration for cargo to overturn; This refers to the minimum curve radius along the entire transportation route for this freight mission. It is the constant of gravitational acceleration; The fixed wheelbase for freight train bogies; The equivalent center of gravity height of the goods.

[0010] Furthermore, the critical acceleration for the cargo to overturn. Based on the critical acceleration benchmark for cargo overturning in the standardized dataset, and combined with the critical acceleration for cargo deformation, packaging shear strength, restraint strength of fixing method, number of stacking layers, and cargo embargo environment threshold from the standardized dataset, the correction calculation is completed: ; In the formula: The critical acceleration benchmark for cargo overturning in the standardized dataset; To standardize the shear strength of the packaging in the dataset; This is a preset benchmark value for the shear strength of the packaging. To standardize the fixed-method constraint strength in the dataset; The preset fixed constraint strength benchmark value; To standardize the number of stack layers in the dataset; The critical acceleration for cargo deformation in the standardized dataset; These are environmental correction coefficients calibrated based on cargo embargo environment thresholds in a standardized dataset; The equivalent center of gravity height of the cargo is calculated based on the baseline value of the equivalent center of gravity height of the cargo in the standardized dataset, and the correction calculation is completed by combining the stacking layer number and the constraint strength of the fixing method in the standardized dataset. ; In the formula: This is the base value for the equivalent center of gravity height of goods in the standardized dataset; The minimum curve radius of the entire transportation route for this freight mission is extracted and determined from the entire transportation route design parameters corresponding to the unique identifier of this freight mission, which is uniquely bound to the standardized dataset; the fixed wheelbase of the freight train bogie is extracted and determined from the train formation information uniquely bound to the standardized dataset.

[0011] Furthermore, the load acquisition module collects static load distribution data of each car of this freight train through distributed load sensing units deployed on the floor of each car. The static load distribution data includes the longitudinal load distribution sequence of the car, the transverse load distribution sequence of the car, the maximum load value at a single point in the car, the average load value of the car, and the eccentric load coefficient of the car. The load acquisition module assigns a unique storage index to the static load distribution data of each carriage, which is bound to the carriage number and the unique identifier of the freight task. At the same time, it classifies and marks the load data of the corresponding carriages based on the off-center load coefficient. The classification and marking results are synchronously transmitted to the speed adjustment module along with the storage index for speed calculation of the corresponding road segments of the speed adjustment nodes, including the speed adjustment nodes added in real time.

[0012] Furthermore, the road condition acquisition module uses a preset mileage interval as a benchmark, and combines the line boundary points, station boundary points, curve and straight section boundary points, and slope and flat section boundary points of the entire transportation route of this freight task to divide the entire transportation route into several continuous independent road segments with non-overlapping mileage. Each independent road segment is assigned a unique mileage interval identifier, and all independent road segments are arranged sequentially and continuously according to the train travel direction of the transportation route. The road condition acquisition module divides the pace adjustment nodes into basic pace adjustment nodes and newly added pace adjustment nodes. The independent road segment between two adjacent pace adjustment nodes is the pace execution segment. The basic pace adjustment node involves calculating a basic pace trigger value for each independent road segment. When the basic pace trigger value exceeds a preset basic trigger threshold range, the independent road segment is determined to be a basic pace execution segment. The starting point of the basic pace execution segment is marked as entering the pace adjustment node, and the ending point is marked as exiting the pace adjustment node. ; In the formula: The base pace trigger value for the target independent road segment; The absolute value of the track gradient for the target independent section; This is the maximum allowable slope threshold determined based on the attributes of the cargo in this shipment. This is the minimum curve radius for the entire transportation route of this freight mission; The radius of the track curve for the target independent road segment; The maximum amplitude of track elevation unevenness for the target independent track section; This is the maximum permissible roughness threshold determined based on the attributes of the cargo in this shipment; Adding a new pace adjustment node: During the operation of this freight train, the road condition acquisition module acquires dynamic incremental road condition data in real time from continuous independent road segments arranged according to the direction of travel ahead of the train's current operating position at a preset acquisition frequency. For each independent road segment ahead, a new pace trigger value is calculated sequentially according to the train's direction of travel. When the new pace trigger value exceeds a preset new trigger threshold range, the road segment is determined to be a new pace adjustment execution segment. The starting point of this new pace adjustment execution segment is marked as a new entry pace adjustment node, and the ending point is marked as a new exit pace adjustment node. The entire path pace adjustment node set is updated synchronously. ; In the formula: Add a new pace trigger value for the independent road segment ahead of the target; The absolute value of the difference between the measured slope of the independent road segment ahead of the target and the initial reference slope of the corresponding road segment; This is the maximum allowable slope threshold determined based on the attributes of the cargo in this shipment. The initial reference curve radius for the independent road segment ahead of the target; The measured radius of the track curve for the independent road segment ahead of the target; The maximum difference between the measured roughness amplitude of the independent road segment ahead of the target and the initial baseline roughness amplitude of the corresponding road segment; This is the maximum permissible roughness threshold determined based on the attributes of the cargo in this shipment; All newly added speed adjustment nodes belong to the corresponding independent road segment mileage intervals pre-divided for the entire route. The mileage positions of newly added speed adjustment nodes and newly added speed adjustment nodes are all taken from the mileage interval range of the corresponding independent road segment. The triggering and execution of all speed adjustment nodes are based on the real-time mileage position of the freight train head.

[0013] Furthermore, the pacing module, combining the upper limit of transport speed, the carriage load classification mark, the environmental correction coefficient, the basic pacing trigger value, and the new pacing trigger value, calculates the real-time optimal transport speed for the basic pacing execution segment corresponding to the basic pacing adjustment node and the new pacing execution segment corresponding to the new pacing adjustment node, respectively, according to the following formula: The base pace adjustment node corresponds to the real-time optimal transport pace for the road segment: ; The newly added speed adjustment node corresponds to the real-time optimal transport speed for the road segment: ; In the formula: The real-time optimal transport speed for the road segment based on the base speed; To provide the real-time optimal transport speed for newly added speed-controlled road segments; This is the maximum transport speed limit for this freight mission; This is the load correction factor; This is an environmental correction factor; Base pace trigger value; Add a new pace trigger value.

[0014] Furthermore, when the speed of adjacent segments in the entire transportation route of a freight task changes, the change is completed through a smooth transition and by setting an allowable transition time. The allowable time range for the transition process is set to 5s to 30s. The greater the change in pace, the longer the allowable time range for the transition process, and vice versa.

[0015] On the other hand, a data analysis-based method for railway freight safety assessment includes: The system uploads and stores cargo attribute data for this railway freight mission, performs compliance verification and standardization preprocessing on the cargo attribute data, and binds and stores the standardized dataset with the unique identifier of the freight mission and train formation information. It then traverses the standardized dataset to extract the critical acceleration for cargo overturning and the equivalent center of gravity height. Combining this with the minimum curve radius of the transport path and the fixed wheelbase of the train bogie, it calibrates the upper limit of the transport speed for this freight mission using a critical speed balance model. The system collects static load distribution data for each carriage of the freight train, classifies and labels the load data according to the off-center load factor, and binds and stores the classification and labeling results with the carriage number and the unique identifier of the freight mission. The system divides the transport path into several independent segments according to preset rules, collects real-time road condition data for each independent segment, calculates the basic and new speed adjustment trigger values, and marks the corresponding speed adjustment nodes. Finally, it calculates the real-time optimal transport speed for each speed-executed segment by combining the upper limit of the transport speed, load classification labels, environmental correction coefficients, and speed adjustment trigger values. The real-time optimal transport speed data is organized into railway freight safety assessment data and output to the freight train control terminal.

[0016] Compared with the known prior art, the technical solution provided by this invention has the following beneficial effects: This invention adjusts the speed of freight trains in real time by combining cargo characteristics, carriage load, and track conditions, making the railway freight operation parameters more aligned with actual transportation needs. It corrects critical speeds based on cargo overturning and deformation characteristics, as well as key parameters such as track curves and gradients, accurately determining the upper limit of transportation speed suitable for the current task. Speed ​​weights are adjusted in stages according to carriage load status, and speed adjustment sections are dynamically divided based on track condition nodes. The optimal transportation speed for each section is generated in real time, and speed changes between adjacent sections are smoothly transitioned to avoid transportation shocks caused by sudden speed changes. This effectively reduces the risks of cargo overturning, uneven loading, and deformation, thereby improving the reliability of freight management and ensuring the stability of railway freight throughout the entire process. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0018] Figure 1This is a schematic diagram of a data analysis-based railway freight safety assessment system. Figure 2 This is a flowchart illustrating a data analysis-based method for assessing railway freight safety. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0020] The present invention will be further described below with reference to embodiments.

[0021] Example 1: This embodiment presents a railway freight safety assessment system based on data analysis, such as... Figure 1 As shown, it includes: The upload module is used to upload and store the attribute data of the goods transported for the current railway freight task; During the upload module's operation phase, the uploaded cargo attribute data is simultaneously subjected to compliance verification and standardized preprocessing. The cargo attribute data includes the cargo's equivalent center of gravity height, number of stacking layers, packaging shear strength, fixing method constraint strength, cargo deformation critical acceleration, cargo overturning critical acceleration, and cargo embargo environment threshold. Among them, compliance verification is to remove abnormal data that exceeds the preset data format range, and standardization preprocessing is to convert the verified cargo attribute data into a standardized dataset with a unified dimension, and to uniquely bind and store the standardized dataset with the unique identifier of this freight mission and the train formation information. The calibration module uses the standardized dataset bound to the storage as the sole calculation benchmark to complete the evaluation and calibration of the upper limit of transportation speed; The calibration module is used to traverse the cargo attribute data stored in the upload module and evaluate and calibrate the upper limit of transportation speed corresponding to this freight task based on the cargo attribute data. The calibration module traverses the standardized dataset bound to the storage, extracts the critical acceleration for cargo overturning and the equivalent center of gravity height, and combines this with the minimum curve radius of the entire transportation route for this freight mission and the fixed wheelbase of the freight train bogie to calculate the upper limit of the transportation speed corresponding to this freight mission through the critical speed balance model: ; In the formula: This is the maximum transport speed for this freight mission, expressed in m / s. The critical acceleration for cargo to overturn, measured in m / s². 2 ; This refers to the minimum curve radius along the entire transportation route for this freight mission. The acceleration due to gravity is constant, with a value of 9.8 m / s². 2 ; The fixed wheelbase for freight train bogies; The equivalent center of gravity height of the goods; The above formula is based on the critical acceleration of cargo overturning, the minimum curve radius of the path, the fixed wheelbase of the train bogie, the equivalent center of gravity height of the cargo and the gravity constant to build a balance model, accurately calculate the speed limit adapted to this freight, say goodbye to the uniform speed limit, and realize personalized speed limit calibration that matches the characteristics of cargo and line; Critical acceleration for cargo to overturn Based on the critical acceleration benchmark for cargo overturning in the standardized dataset, and combined with the critical acceleration for cargo deformation, packaging shear strength, restraint strength of fixing method, number of stacking layers, and cargo embargo environment threshold from the standardized dataset, the correction calculation is completed: ; In the formula: The critical acceleration benchmark for cargo overturning in the standardized dataset; To standardize the shear strength of the packaging in the dataset; This is a preset benchmark value for the shear strength of the packaging. To standardize the fixed-method constraint strength in the dataset; The preset fixed constraint strength benchmark value; To standardize the number of stack layers in the dataset; The critical acceleration for cargo deformation in the standardized dataset; These are environmental correction coefficients calibrated based on cargo embargo environment thresholds in a standardized dataset; The above formula is based on the critical overturning acceleration benchmark value, combined with the shear strength of packaging, the strength of fixed constraints, the number of stacking layers, and the critical deformation acceleration for constraint correction. Then, by adjusting the environmental coefficient, the accurate critical overturning acceleration is calculated to fit the loading and transportation environment, thereby improving the accuracy of parameter adaptation. The equivalent center of gravity height of the cargo is calculated based on the baseline value of the equivalent center of gravity height of the cargo in the standardized dataset, and the correction calculation is completed by combining the stacking layer number and the constraint strength of the fixing method in the standardized dataset: ; In the formula: This is the base value for the equivalent center of gravity height of goods in the standardized dataset; The minimum curve radius of the entire transportation route for this freight mission is extracted and determined from the entire transportation route design parameters corresponding to the unique identifier of this freight mission, which is uniquely bound to the standardized dataset; the fixed wheelbase of the freight train bogie is extracted and determined from the train formation information uniquely bound to the standardized dataset. The above formula is based on the equivalent center of gravity height, and dynamically corrected by the number of stacking layers and the strength of fixed constraints, so as to truly reflect the actual center of gravity height of the cargo after loading. in, The dimensionless coefficient is calibrated based on the deviation between the real-time environmental parameters of the transportation route and the cargo embargo threshold. Its value ranges from 0 to 1. When the real-time environmental parameters of the transportation route do not exceed the cargo embargo threshold, the coefficient is 1. The higher the degree to which the real-time environmental parameters exceed the threshold, the closer the coefficient is to 0. The load acquisition module is used to collect static load distribution data of each car in this freight train, and to store the static load distribution data of each car with different labels. The load acquisition module collects static load distribution data of each car of this freight train through distributed load sensing units deployed on the floor of each car. The static load distribution data includes the longitudinal load distribution sequence of the car, the transverse load distribution sequence of the car, the maximum load value at a single point in the car, the average load value of the car, and the eccentric load coefficient of the car. Among them, the distributed load sensing unit uses a resistance strain gauge pressure sensor with a range of 0~50t and an accuracy class of 0.1. Fifteen sensor units are set on the floor of each car in five equal parts longitudinally and three equal parts laterally, evenly covering the load-bearing surface of the car. The acquisition frequency is set to 10Hz to collect and upload the car load data in real time. The load acquisition module assigns a unique storage index to the static load distribution data of each car, which is bound to the car number and the unique identifier of the freight task. At the same time, it classifies and marks the load data of the corresponding car based on the off-center load coefficient. The classification and marking results are synchronously transmitted to the speed adjustment module along with the storage index for speed calculation of the corresponding road segments of the speed adjustment nodes, including the newly added speed adjustment nodes in real time. The road condition acquisition module is used to obtain real-time road condition data for the entire transportation route of this freight mission and simultaneously mark the speed adjustment nodes along the entire route. The road condition acquisition module uses a preset mileage interval as a benchmark and combines the line boundary points, station boundary points, curve and straight section boundary points, and slope and flat section boundary points of the entire transportation route of this freight task to divide the entire transportation route into several continuous independent road segments with non-overlapping mileage. Each independent road segment is assigned a unique mileage interval identifier, and all independent road segments are arranged sequentially and continuously according to the train travel direction of the transportation route. The road condition acquisition module is equipped with a track geometry parameter detection sensor, a meteorological sensor, and a GPS positioning module, with the acquisition frequency set to 1Hz. Basic road condition data is retrieved from the railway line design database, while dynamic incremental road condition data is obtained in real time through the train onboard detection unit and the railway maintenance dispatching system, covering real-time changes in track gradient, curve radius, and unevenness amplitude. The real-time road condition data for the entire transportation route of this freight mission includes the following: track curve radius, track gradient, track elevation irregularity amplitude, track directional irregularity amplitude, track maintenance status, temporary speed limit section information, line closure status, and meteorological environmental data along the route for each independent section of the transportation route. The traffic data acquisition module divides the pace adjustment nodes into basic pace adjustment nodes and newly added pace adjustment nodes. The independent road segment between two adjacent pace adjustment nodes is the pace execution segment. The basic pace adjustment node involves calculating a basic pace trigger value for each independent road segment. When the basic pace trigger value exceeds a preset basic trigger threshold range, the independent road segment is determined to be a basic pace execution segment. The starting point of the basic pace execution segment is marked as entering the pace adjustment node, and the ending point is marked as exiting the pace adjustment node. ; In the formula: The base pace trigger value for the target independent road segment; The absolute value of the track gradient for the target independent section; This is the maximum allowable slope threshold determined based on the attributes of the cargo in this shipment. This is the minimum curve radius for the entire transportation route of this freight mission; The radius of the track curve for the target independent road segment; The maximum amplitude of track elevation unevenness for the target independent track section; This is the maximum permissible roughness threshold determined based on the attributes of the cargo in this shipment; The above formula integrates the line gradient, curve radius, and track irregularity amplitude, and calculates the basic speed trigger value by combining the cargo adaptation threshold. It can quickly identify the basic road sections that need speed adjustment, realize the linkage between road conditions and cargo characteristics, and simplify the speed node calibration process. Adding a new pace adjustment node: During the operation of this freight train, the road condition acquisition module acquires dynamic incremental road condition data in real time from continuous independent road segments arranged according to the direction of travel ahead of the train's current operating position at a preset acquisition frequency. It calculates a new pace trigger value for each independent road segment ahead, sequentially according to the train's direction of travel. When the new pace trigger value exceeds a preset new trigger threshold range, the road segment is determined to be a new pace adjustment execution segment. The starting point of this new pace adjustment execution segment is marked as a new entry pace adjustment node, and the ending point is marked as a new exit pace adjustment node. The entire path pace adjustment node set is updated synchronously. ; In the formula: Add a new pace trigger value for the independent road segment ahead of the target; The absolute value of the difference between the measured slope of the independent road segment ahead of the target and the initial reference slope of the corresponding road segment; This is the maximum allowable slope threshold determined based on the attributes of the cargo in this shipment. The initial reference curve radius for the independent road segment ahead of the target; The measured radius of the track curve for the independent road segment ahead of the target; The maximum difference between the measured roughness amplitude of the independent road segment ahead of the target and the initial baseline roughness amplitude of the corresponding road segment; This is the maximum permissible roughness threshold determined based on the attributes of the cargo in this shipment; The above formula calculates the real-time changes in road section slope, curve radius, and unevenness amplitude, and combines them with cargo threshold to calculate the new speed trigger value. It captures dynamic road condition changes in real time and adds speed adjustment nodes to make up for the lag in static road condition calibration. All newly added speed adjustment nodes belong to the corresponding independent road segment mileage intervals pre-divided for the entire route. The mileage positions of newly added speed adjustment nodes and newly added speed adjustment nodes are all taken from the mileage interval range of the corresponding independent road segment. The triggering and execution of all speed adjustment nodes are based on the real-time mileage position of the freight train head. The speed grading module is used to evaluate the optimal real-time transport speed for a given road segment by combining the calibrated upper limit of transport speed, static load distribution data of each car, real-time road condition data, and speed adjustment nodes. The speed grading module combines the upper limit of transport speed, the vehicle load classification marker, the environmental correction factor, the basic speed grading trigger value, and the new speed grading trigger value to calculate the real-time optimal transport speed for the basic speed execution segment corresponding to the basic speed adjustment node and the new speed execution segment corresponding to the new speed adjustment node, respectively, according to the following formula: The base pace adjustment node corresponds to the real-time optimal transport pace for the road segment: ; This formula takes the upper limit of the transportation speed specified for this freight mission as the core benchmark, introduces a load correction coefficient to adapt to the off-center load distribution of the entire train carriage, combines an environmental correction coefficient to match the real-time transportation environment conditions, and then completes the adaptation and adjustment of the basic road conditions by the reciprocal of the basic speed trigger value. The multi-dimensional parameters are collaboratively calculated to obtain the real-time optimal speed of the basic road section, which not only strictly adheres to the safety critical conditions of cargo overturning and deformation, but also fully conforms to the characteristics of the basic road conditions of the line. It is different from the fixed speed mode and realizes the precise, safe and adaptive control of the speed of the basic road section. The newly added speed adjustment node corresponds to the real-time optimal transport speed for the road segment: ; This formula continues the core safety benchmark of the upper limit of transportation speed, retains the safety constraint role of load correction coefficient and environmental correction coefficient, and responds to real-time dynamic changes in road conditions by adding a reciprocal response to the speed trigger value. It accurately calculates the optimal speed for incremental road sections and can quickly adapt to sudden changes in line gradient, curve radius and unevenness amplitude. It can still ensure the safety and optimality of speed in dynamic road condition change scenarios, and solve the problem that traditional speed cannot keep up with real-time road condition changes. In the formula: The real-time optimal transport speed for the road segment based on the base speed; To provide the real-time optimal transport speed for newly added speed-controlled road segments; This is the maximum transport speed limit for this freight mission; This is the load correction factor; This is an environmental correction factor; Base pace trigger value; Add a new pace trigger value; in, The value range is preset to (0,1], and is determined comprehensively based on the graded marking of the off-center load coefficient of all cars in the entire freight train. The higher the degree of off-center load of the entire train and the more off-center load cars there are, the smaller the value will be. Environmental correction factor A segmented calibration formula is adopted: when the transportation environment parameters do not exceed the cargo embargo threshold. =1; when the temperature exceeds the threshold ±10℃ and the wind speed exceeds the threshold ±2m / s =0.8; exceeding ±20℃ and ±4m / s =0.5; exceeding ±30℃, ±6m / s and above =0.2; The preset basic trigger threshold range is set to 0.2~1.8, and the preset new trigger threshold range is set to 0.1~1.5. The off-center load coefficient classification standard is as follows: off-center load coefficient ≤ 0.1 is marked as Grade A (normal), 0.1 < off-center load coefficient ≤ 0.3 is marked as Grade B (slight off-center load), 0.3 < off-center load coefficient ≤ 0.5 is marked as Grade C (moderate off-center load), and off-center load coefficient > 0.5 is marked as Grade D (severe off-center load). Maximum allowable slope threshold Maximum permissible unevenness threshold All are based on the critical acceleration benchmark value for cargo overturning. Calibration, ≥5m / s 2 hour Take 8‰ Take 8mm, <5m / s 2 hour Take 5‰ Take 5mm; Load correction factor Determined by the proportion of unevenly loaded carriages in the entire train: When Class A carriages account for 100% =1.0, when the proportion of Class B carriages is ≤30% =0.92~0.98, when the proportion of Class C carriages is ≤20% =0.80~0.90, when the proportion of D-class carriages is >0 =0.60~0.75; When the speed of adjacent segments in the entire transportation route of a freight task changes, the change is completed through a smooth transition and by setting an allowable time for the transition process; The allowable time range for the transition process is set to 5s to 30s. The greater the change in pace, the longer the allowable time range for the transition process, and vice versa. The smooth transition of pacing adopts a linear gradual change algorithm, and the formula for speed change during the transition process is as follows: Where V(t) is the real-time velocity of the transient process, The pace for the previous section, The current speed is t, the transition time is T, and the set allowable transition time is T. When the speed change is greater than 10 m / s, T is 25 s to 30 s; when the change is 5 to 10 m / s, T is 15 s to 20 s; and when the change is less than 5 m / s, T is 5 s to 10 s. The output module is used to organize the calculated real-time optimal transport speed data into railway freight safety assessment data for the corresponding transport segment and output it to the freight train control terminal. The upload module is connected to the calibration module via a wireless network. The calibration module is connected to the load acquisition module and the road condition acquisition module via a wireless network. The load acquisition module and the road condition acquisition module are connected to the pacing module via a wireless network. The output module is connected to the upload module, the calibration module, the load acquisition module, the road condition acquisition module, and the pacing module via a wireless network.

[0022] In this embodiment, the upload module uploads and stores the attribute data of the goods transported for the current railway freight task. The calibration module iterates through the cargo attribute data stored in the upload module in real time, and evaluates and calibrates the upper limit of the transport speed corresponding to this freight task based on the cargo attribute data. The load acquisition module simultaneously acquires the static load distribution data of each carriage of the freight train, and stores the static load distribution data of each carriage with different markings. The road condition acquisition module runs in the background to obtain the real-time road condition data of the entire transport route of this freight task, and simultaneously marks the speed adjustment nodes of the entire route. Then, the speed module combines the calibrated upper limit of transport speed, the static load distribution data of each carriage, the real-time road condition data, and the speed adjustment nodes to evaluate the real-time optimal transport speed of the corresponding route. Finally, the output module organizes the calculated real-time optimal transport speed data into railway freight safety assessment data of the corresponding transport route and outputs it to the freight train control terminal.

[0023] In the above embodiments, the system can accurately assess the upper limit of freight speed and the optimal driving speed for each section based on the characteristics of the goods, the load distribution of the carriages, and the real-time road conditions. It ensures the stability of freight transportation through multi-dimensional parameter correction, accurately identifies the speed adjustment nodes of the line and dynamically optimizes the driving speed, and smoothly transitions when the speed changes. This can effectively reduce the risk of cargo overturning and deformation, effectively improve the safety of railway freight throughout the entire process, and at the same time take into account transportation efficiency and reduce the adverse effects of factors such as line conditions and uneven load on freight transportation.

[0024] Based on the system in the above embodiments, an application example of this system is given: A railway freight group was tasked with transporting 50-ton large oil-immersed transformers by freight train from XX North Station to YY North Station.

[0025] Before the commencement of this freight mission, freight dispatchers first entered and uploaded all cargo attribute data for the transportation mission through the system's upload module. This included the transformer's equivalent center of gravity height (basic value), stacking layers, packaging shear strength, fixing method constraint strength, cargo deformation critical acceleration, cargo overturning critical acceleration (benchmark value), and cargo embargo environmental thresholds (temperature range -20℃ to 60℃, wind speed limit ≤12m / s). After receiving the data, the system automatically performed compliance checks on the uploaded data, eliminating a set of abnormal data with non-compliant formats. The remaining valid data underwent standardized preprocessing, converting all data into a standardized dataset with unified dimensions. This dataset was then uniquely bound and stored to the unique identifier of this freight mission (number: XX-YY-20240318-001) and train formation information (6 flatcars were used, with a fixed wheelbase of 2.4m for the train bogies), providing a unified data benchmark for subsequent calculations.

[0026] Subsequently, the system calibration module automatically traversed the bound and stored standardized dataset, extracting two core parameters: the corrected critical acceleration for cargo overturning and the equivalent center of gravity height. Simultaneously, it retrieved the minimum curve radius parameter (300m) from the entire transportation route and, combined with the train bogie fixed wheelbase parameter, completed the calculation using a critical speed balance model. The final calculated maximum transportation speed for this freight mission was 22.5 m / s (equivalent to 81 km / h). The calibration module simultaneously incorporated the critical acceleration for cargo deformation, packaging shear strength, fixing method constraint strength, stacking layers, and cargo embargo threshold values ​​to complete parameter correction calculations. Combined with the initial environmental parameters of the transportation route, the initial environmental correction coefficient for this mission was determined to be 1.

[0027] Before and during mission execution, the system's load acquisition module continuously collects static load distribution data for each of the six carriages using distributed load sensing units deployed on the floor. This data covers five categories: longitudinal load distribution sequence, lateral load distribution sequence, maximum single-point load value, average load value, and eccentricity coefficient. The system assigns a unique storage index to the load data of each carriage, binding it to the carriage number and the unique identifier of the freight mission. Simultaneously, it categorizes the load data of each carriage based on the eccentricity coefficient: carriages 1, 3, 5, and 6 have eccentricity coefficients within the normal range and are categorized as Grade A; carriages 2 and 4 exhibit slight eccentricity and are categorized as Grade B. The system synchronously transmits the categorization results and storage indexes to the speed control module for subsequent speed adjustment node calculations.

[0028] The system's road condition data collection module uses a preset mileage interval of 1 kilometer. Combining this with the route's boundary points, station boundary points, curve / straight section boundary points, and gradient / flat section boundary points, it divides the entire transportation route from Hefei North Station to Xuzhou North Station into 128 continuous and non-overlapping independent segments. Each segment is assigned a unique mileage interval identifier and ordered sequentially according to the train's direction of travel. The module collects real-time road condition data for each independent segment, including track curve radius, track gradient, track elevation and directional irregularities, track maintenance status, temporary speed limit information, track closure status, and meteorological data along the route. During this transportation trip, the temperature was 18℃ and the wind speed was 8 m / s, both within the thresholds for prohibited cargo transport environments. The road condition acquisition module first calculates the basic pace trigger value for each independent road segment, filters out road segments that exceed the threshold, and marks 23 basic pace adjustment nodes. During train operation, the module collects dynamic incremental road condition data of continuous road segments ahead of the train in real time at a fixed frequency, calculates new pace trigger values, adds 3 pace adjustment nodes triggered by excessive amplitude of local track irregularities, and updates the entire path pace adjustment node set simultaneously. All pace adjustment nodes are triggered based on the real-time mileage position of the freight train locomotive.

[0029] The system's speed control module integrates the upper limit of transport speed, carriage load classification markers, environmental correction coefficients, basic speed control trigger values, and newly added speed control trigger values ​​to calculate the real-time optimal transport speed for two types of speed control sections. Based on the overall train load distribution, a load correction coefficient of 0.92 is determined. The real-time optimal transport speed for sections using the basic speed control is 18.2 m / s to 21.3 m / s. For sections using newly added speed control, due to local road condition deviations, the real-time optimal transport speed is 12.5 m / s to 15.6 m / s. For speed changes between adjacent sections, the system uses a smooth transition method. For sections with large speed changes, the allowable transition time is set to 25 seconds; for sections with small speed changes, the allowable transition time is set to 8 seconds, ensuring a smooth and shock-free transition throughout.

[0030] Finally, the system output module organizes the real-time optimal transport speed data calculated for each section into railway freight safety assessment data, which includes the entry speed, exit speed, transition time, load safety warnings, and track condition risk warnings for each speed adjustment node. This data is then output to the freight train driving control terminal in real time. Based on the safety assessment data output by the system, the train driver precisely controls the train speed. Throughout the entire transport process, there were no risks of cargo imbalance, displacement, or overturning. The train and track were well-matched, and the railway freight task for this large transformer was successfully completed.

[0031] Example 2: A data analysis-based method for railway freight safety assessment includes: Upload and store the cargo attribute data for this railway freight mission, perform compliance verification and standardization preprocessing on the cargo attribute data, and bind and store the standardized dataset with the unique identifier of the freight mission and train formation information; By traversing the standardized dataset, the critical acceleration for cargo overturning and the equivalent center of gravity height are extracted. Combined with the minimum curve radius of the transportation path and the fixed wheelbase of the train bogie, the upper limit of the transportation speed for this freight is determined through the critical speed balance model. Collect static load distribution data for each car of a freight train, classify and label the load data according to the off-center load factor, and bind and store the classification and labeling results with the car number and the unique identifier of the freight task. The transportation route is divided into several independent road segments according to preset rules. Real-time road condition data of each independent road segment is collected, the basic and new pace trigger values ​​are calculated, and the corresponding pace adjustment nodes are marked. By combining the upper limit of transport speed, load classification marker, environmental correction factor, and speed trigger value, the real-time optimal transport speed for each speed execution segment is calculated; The real-time optimal transport speed data is organized into railway freight safety assessment data and output to the freight train control terminal.

[0032] In summary, the system in the above embodiments adjusts the speed of freight trains in real time by combining cargo characteristics, carriage load, and track conditions, making the railway freight driving parameters more in line with actual transportation needs. Based on cargo overturning and deformation characteristics, as well as key parameters such as track curves and gradients, the critical speed is corrected to accurately determine the upper limit of transportation speed suitable for this task. The speed distribution weight is adjusted in stages according to the carriage load status, and the speed adjustment sections are dynamically divided in combination with track condition nodes. The optimal transportation speed suitable for each section is generated in real time. The speed change between adjacent sections adopts a smooth transition method to avoid the transportation impact caused by sudden speed changes, effectively reducing the risks of cargo overturning, uneven loading, and deformation, thereby improving the reliability of freight management and ensuring the stability of railway freight throughout the entire process.

[0033] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A railway freight safety assessment system based on data analysis, characterized in that, include: The upload module is used to upload and store the attribute data of the goods transported for the current railway freight task; The calibration module is used to traverse the cargo attribute data stored in the upload module and evaluate and calibrate the upper limit of transportation speed corresponding to this freight task based on the cargo attribute data. The load acquisition module is used to collect static load distribution data of each car in this freight train, and to store the static load distribution data of each car with different labels. The road condition acquisition module is used to obtain real-time road condition data for the entire transportation route of this freight mission and simultaneously mark the speed adjustment nodes along the entire route. The speed grading module is used to evaluate the optimal real-time transport speed for a given road segment by combining the calibrated upper limit of transport speed, static load distribution data of each car, real-time road condition data, and speed adjustment nodes. The output module is used to organize the calculated real-time optimal transport speed data into railway freight safety assessment data for the corresponding transport segment and output it to the freight train control terminal.

2. The railway freight safety assessment system based on data analysis according to claim 1, characterized in that, During the operation of the upload module, the uploaded cargo attribute data is simultaneously verified for compliance and preprocessed for standardization. The cargo attribute data includes the cargo's equivalent center of gravity height, number of stacking layers, packaging shear strength, fixing method constraint strength, cargo deformation critical acceleration, cargo overturning critical acceleration, and cargo embargo environment threshold. The compliance verification process involves removing abnormal data that exceeds the preset data format range. The standardization preprocessing process involves converting the verified cargo attribute data into a standardized dataset with a unified dimension, and uniquely binding and storing the standardized dataset with the unique identifier and train formation information of this freight mission.

3. The railway freight safety assessment system based on data analysis according to claim 2, characterized in that, The calibration module traverses the standardized dataset bound to the storage, extracts the critical overturning acceleration and equivalent center of gravity height of the cargo, and combines this with the minimum curve radius of the entire transportation route for this freight mission and the fixed wheelbase of the freight train bogie to calculate the upper limit of the transportation speed corresponding to this freight mission through the critical speed balance model. ； In the formula: This is the maximum transport speed limit for this freight mission; The critical acceleration for cargo to overturn; This refers to the minimum curve radius along the entire transportation route for this freight mission. It is the constant of gravitational acceleration; The fixed wheelbase for freight train bogies; The equivalent center of gravity height of the goods.

4. The railway freight safety assessment system based on data analysis according to claim 3, characterized in that, The critical acceleration for the cargo to overturn Based on the critical acceleration benchmark for cargo overturning in the standardized dataset, and combined with the critical acceleration for cargo deformation, packaging shear strength, restraint strength of fixing method, number of stacking layers, and cargo embargo environment threshold from the standardized dataset, the correction calculation is completed: ； In the formula: The critical acceleration benchmark for cargo overturning in the standardized dataset; To standardize the shear strength of the packaging in the dataset; This is a preset benchmark value for the shear strength of the packaging. To standardize the fixed-method constraint strength in the dataset; The preset fixed constraint strength benchmark value; To standardize the number of stack layers in the dataset; The critical acceleration for cargo deformation in the standardized dataset; These are environmental correction coefficients calibrated based on cargo embargo environment thresholds in a standardized dataset; The equivalent center of gravity height of the cargo is calculated based on the baseline value of the equivalent center of gravity height of the cargo in the standardized dataset, and the correction calculation is completed by combining the stacking layer number and the constraint strength of the fixing method in the standardized dataset. ; In the formula: This is the base value for the equivalent center of gravity height of goods in the standardized dataset; The minimum curve radius of the entire transportation route for this freight mission is extracted and determined from the entire transportation route design parameters corresponding to the unique identifier of this freight mission, which is uniquely bound to the standardized dataset; the fixed wheelbase of the freight train bogie is extracted and determined from the train formation information uniquely bound to the standardized dataset.

5. The railway freight safety assessment system based on data analysis according to claim 1, characterized in that, The load acquisition module collects static load distribution data of each car of this freight train through distributed load sensing units deployed on the floor of each car. The static load distribution data includes the longitudinal load distribution sequence of the car, the transverse load distribution sequence of the car, the maximum load value at a single point in the car, the average load value of the car, and the eccentric load coefficient of the car. The load acquisition module assigns a unique storage index to the static load distribution data of each carriage, which is bound to the carriage number and the unique identifier of the freight task. At the same time, it classifies and marks the load data of the corresponding carriages based on the off-center load coefficient. The classification and marking results are synchronously transmitted to the speed adjustment module along with the storage index for speed calculation of the corresponding road segments of the speed adjustment nodes, including the speed adjustment nodes added in real time.

6. The railway freight safety assessment system based on data analysis according to claim 1, characterized in that, The road condition acquisition module uses a preset mileage interval as a benchmark and combines the line boundary points, station boundary points, curve and straight section boundary points, and slope and flat section boundary points of the entire transportation route of this freight task to divide the entire transportation route into several continuous independent road segments with non-overlapping mileage. Each independent road segment is assigned a unique mileage interval identifier, and all independent road segments are arranged sequentially and continuously according to the train travel direction of the transportation route. The road condition acquisition module divides the pace adjustment nodes into basic pace adjustment nodes and newly added pace adjustment nodes. The independent road segment between two adjacent pace adjustment nodes is the pace execution segment. The basic pace adjustment node involves calculating a basic pace trigger value for each independent road segment. When the basic pace trigger value exceeds a preset basic trigger threshold range, the independent road segment is determined to be a basic pace execution segment. The starting point of the basic pace execution segment is marked as entering the pace adjustment node, and the ending point is marked as exiting the pace adjustment node. ； In the formula: The base pace trigger value for the target independent road segment; The absolute value of the track gradient for the target independent section; This is the maximum allowable slope threshold determined based on the attributes of the cargo in this shipment. This is the minimum curve radius for the entire transportation route of this freight mission; The radius of the track curve for the target independent road segment; The maximum amplitude of track elevation unevenness for the target independent track section; This is the maximum permissible roughness threshold determined based on the attributes of the cargo in this shipment; Adding a new pace adjustment node: During the operation of this freight train, the road condition acquisition module acquires dynamic incremental road condition data in real time from continuous independent road segments arranged according to the direction of travel ahead of the train's current operating position at a preset acquisition frequency. For each independent road segment ahead, a new pace trigger value is calculated sequentially according to the train's direction of travel. When the new pace trigger value exceeds a preset new trigger threshold range, the road segment is determined to be a new pace adjustment execution segment. The starting point of this new pace adjustment execution segment is marked as a new entry pace adjustment node, and the ending point is marked as a new exit pace adjustment node. The entire path pace adjustment node set is updated synchronously. ； In the formula: Add a new pace trigger value for the independent road segment ahead of the target; The absolute value of the difference between the measured slope of the independent road segment ahead of the target and the initial reference slope of the corresponding road segment; This is the maximum allowable slope threshold determined based on the attributes of the cargo in this shipment. The initial reference curve radius for the independent road segment ahead of the target; The measured radius of the track curve for the independent road segment ahead of the target; The maximum difference between the measured roughness amplitude of the independent road segment ahead of the target and the initial baseline roughness amplitude of the corresponding road segment; This is the maximum permissible roughness threshold determined based on the attributes of the cargo in this shipment; All newly added speed adjustment nodes belong to the corresponding independent road segment mileage intervals pre-divided for the entire route. The mileage positions of newly added speed adjustment nodes and newly added speed adjustment nodes are all taken from the mileage interval range of the corresponding independent road segment. The triggering and execution of all speed adjustment nodes are based on the real-time mileage position of the freight train head.

7. A railway freight safety assessment system based on data analysis according to any one of claims 3, 5, and 6, characterized in that, The speed grading module combines the upper limit of transport speed, the carriage load classification mark, the environmental correction factor, the basic speed grading trigger value, and the new speed grading trigger value to calculate the real-time optimal transport speed for the basic speed execution segment corresponding to the basic speed adjustment node and the new speed execution segment corresponding to the new speed adjustment node, respectively, according to the following formula: The base pace adjustment node corresponds to the real-time optimal transport pace for the road segment: ； The newly added speed adjustment node corresponds to the real-time optimal transport speed for the road segment: ； In the formula: The real-time optimal transport speed for the road segment based on the base speed; To provide the real-time optimal transport speed for newly added speed-controlled road segments; This is the maximum transport speed limit for this freight mission; This is the load correction factor; This is an environmental correction factor; Base pace trigger value; Add a new pace trigger value.

8. The railway freight safety assessment system based on data analysis according to claim 1, characterized in that, When the speed of adjacent segments in the entire transportation route of a freight task changes, the change is completed through a smooth transition and by setting an allowable time for the transition process; The allowable time range for the transition process is set to 5s to 30s. The greater the change in pace, the longer the allowable time range for the transition process, and vice versa.

9. A railway freight safety assessment system based on data analysis according to claim 1, characterized in that, The upload module is interconnected with the calibration module via a wireless network. The calibration module is interconnected with the load acquisition module and the road condition acquisition module via a wireless network. The load acquisition module and the road condition acquisition module are interconnected with the pacing module via a wireless network. The output module is interconnected with the upload module, the calibration module, the load acquisition module, the road condition acquisition module, and the pacing module via a wireless network.

10. A method for railway freight safety assessment based on data analysis, wherein the method is an implementation method of the railway freight safety assessment system based on data analysis as described in any one of claims 1-9, characterized in that, include: Upload and store the cargo attribute data for this railway freight mission, perform compliance verification and standardization preprocessing on the cargo attribute data, and bind and store the standardized dataset with the unique identifier of the freight mission and train formation information; By traversing the standardized dataset, the critical acceleration for cargo overturning and the equivalent center of gravity height are extracted. Combined with the minimum curve radius of the transportation path and the fixed wheelbase of the train bogie, the upper limit of the transportation speed for this freight is determined through the critical speed balance model. Collect static load distribution data for each car of a freight train, classify and label the load data according to the off-center load factor, and bind and store the classification and labeling results with the car number and the unique identifier of the freight task. The transportation route is divided into several independent road segments according to preset rules. Real-time road condition data of each independent road segment is collected, the basic and new pace trigger values ​​are calculated, and the corresponding pace adjustment nodes are marked. By combining the upper limit of transport speed, load classification marker, environmental correction factor, and speed trigger value, the real-time optimal transport speed for each speed execution segment is calculated; The real-time optimal transport speed data is organized into railway freight safety assessment data and output to the freight train control terminal.

Images