Railway freight transportation status early warning method and system

Abstract

The invention discloses a railway freight transportation status early warning method and system, and specifically relates to the technical field of railway transportation; real-time monitoring is achieved by installing sensors on the freight, data encryption is used to ensure information security, and a wireless transmission network is used to ensure instant data transmission; a control center optimizes the train running speed and stop position through real-time data analysis, generates signal instructions and evaluates transmission real-time performance, promptly corrects low real-time performance instructions and warns of the risk of medium real-time transmission failure, thereby improving the accuracy and timeliness of freight monitoring, reducing abnormal response time, optimizing transportation plans, reducing transportation risks, ensuring freight safety, improving transportation efficiency and significantly reducing operating costs and complexity.

Description

Technical Field

[0001] The present invention relates to the technical field of railway transportation, and in particular to a railway freight transportation status early warning method and system. Background Art

[0002] Railway freight transportation status early warning refers to the real-time tracking and evaluation of the transportation status of goods during railway freight transportation through advanced monitoring technology and data analysis methods. Once an abnormal situation is detected, such as cargo delays, temperature changes, abnormal vibrations, etc., the system will immediately issue an early warning notification to prompt relevant personnel to take corresponding measures. However, in modern railway freight transportation systems, traditional cargo monitoring and management methods usually rely on regular inspections and manual records, lacking real-time monitoring and rapid response capabilities for cargo status. This makes it difficult to timely discover and deal with abnormal cargo status, transportation delays and potential risks during transportation, and it is impossible to effectively optimize train speeds and stop locations, which increases the complexity and uncertainty of transportation. Summary of the invention

[0003] The purpose of the present invention is to provide a railway freight transportation status early warning method and system to solve the shortcomings of the background technology.

[0004] In order to achieve the above object, the present invention provides the following technical solution: a railway freight transportation status early warning method, comprising the following steps:

[0005] S1: Install several sensors on the cargo for real-time monitoring, obtain the real-time status data of the cargo, encrypt the real-time status data, and transmit the encrypted data to the control center and the locomotive driver's equipment in real time through the wireless transmission network;

[0006] S2: The computing system of the control center analyzes the transmitted data in real time and calculates the optimal travel speed and stop position according to the train operation plan and the current cargo status;

[0007] S3: Generate corresponding signal instructions based on the analysis results and send them to the locomotive driver through signal lights, signs and communication equipment. Comprehensively analyze the abnormal conditions in signal transmission and execution and the accuracy of train response instructions, and evaluate the real-time transmission of signal instructions;

[0008] S4: classifying the real-time performance of the signal instruction transmission according to the evaluation result into high real-time performance transmission, medium real-time performance transmission and low real-time performance transmission, and automatically correcting the low real-time performance transmission instruction;

[0009] S5: When the transmission process of the signal instruction is medium real-time transmission, the risk of signal instruction transmission failure in the medium real-time transmission process is predicted and warned, and the signal instruction transmission path is adjusted according to the prediction result to improve the accuracy of the transmission of the cargo status information.

[0010] In a preferred embodiment, in S2, the current position x(t) and time t of the train are obtained in real time by the sensor, and the calculation expression of the real-time speed v(t) of the train is: v(t) = ;

[0011] In order to avoid collision between trains, the safe distance dsafe of the trains is calculated, the maximum braking distance of the trains is obtained as dbrake, and the safety margin Δd is set: dsafe=dbrake+Δd; according to the current cargo status and the train operation plan, the optimal travel speed vopt(t) is calculated, the real-time target speed of the train is obtained as vtarget and the current speed is v(t), and the optimal travel speed vopt(t) is calculated according to the cargo status speed limit information vlimitv and the acceleration capacity a of the train. The specific calculation expression is: Where Δt is the time interval;

[0012] When the train stops at position xstop, the optimal braking time tbrake and position xbrake are calculated based on the current train position x(t), speed v(t) and braking acceleration abrake. The calculation expression is: tbrake= ; The train starts braking at xbrake to ensure it stops at xstop;

[0013] According to the calculation results, the corresponding signal instruction S(t) is generated, including the driving speed and the parking position: S(t)={vopt(t),xbrake}.

[0014] In a preferred embodiment, the abnormal conditions in signal transmission and execution are analyzed to generate a redundant path switching abnormality index, and the method for obtaining the redundant path switching abnormality index is:

[0015] Establish the system state set S={S0,S1,S2,…,St,…,Sn}, t=1,2,…,n, n is a positive integer greater than 0; and establish the system action set A={A0,A1,…,At,…,Am}, t=1,2,…,m, m is a positive integer greater than 0; calculate the transition probability P(s'|s,a), that is, the probability of taking action a in state s to transition to state s', P(s'|s, a) =Pr(St+1=s'|St=s,At=a); and calculate the reward function R(s,a), that is, the immediate reward for taking action a in state s;

[0016] Get the value function V(s) of state s, that is, the long-term expected reward starting in state s, V(s) = [R(s,a)+γ ]; where γ is the discount factor, For the action a that maximizes, is the value function of the subsequent state s', which represents the long-term expected reward in state s'; the redundant path switching anomaly index is calculated, and the specific calculation expression is: P ; In the formula, is the redundant path switching anomaly index, Indicates the normal state after switching.

[0017] In a preferred embodiment, the abnormal conditions in signal transmission and execution are analyzed to generate a redundant path switching abnormality index, and the method for obtaining the redundant path switching abnormality index is:

[0018] Collect the time series data of train response instructions to show the train response efficiency to the instructions. ; Define weights for each data point, the weight sequence is ,and =1, calculate the weighted moving average of each time point, mark the weighted moving average as WMAt, the specific calculation expression is: WMAt= ; For the The weight of the data point, For time point The response frequency, n is the window size, which indicates the number of time points used to calculate the moving average;

[0019] Calculate the difference between the actual response data and the weighted moving average, that is, calculate the response efficiency fluctuation index. The specific calculation expression is: ; In the formula, To respond to the efficiency fluctuation index, is the actual response frequency at time point t.

[0020] In a preferred embodiment, the redundant path switching abnormality index and the response efficiency fluctuation index are normalized, and the real-time coefficient of the signal instruction transmission is calculated based on the normalized redundant path switching abnormality index and the response efficiency fluctuation index.

[0021] In a preferred embodiment, the real-time performance of signal instruction transmission is graded according to the evaluation results, specifically:

[0022] The real-time coefficient of the acquired signal instruction transmission is compared with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the real-time coefficient of the signal instruction transmission is compared with the first standard threshold and the second standard threshold respectively;

[0023] If the real-time coefficient of the signal instruction transmission is greater than the second standard threshold, the real-time of the signal instruction transmission is classified as high real-time transmission;

[0024] If the real-time coefficient of the signal instruction transmission is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time of the signal instruction transmission is classified as medium real-time transmission;

[0025] If the real-time coefficient of the signal instruction transmission is less than the first standard threshold, the real-time of the signal instruction transmission is classified as low real-time transmission, and the low real-time transmission instruction is automatically corrected.

[0026] In a preferred embodiment, in S5, when the transmission process of the signal instruction is medium real-time transmission, that is, the real-time coefficient of the signal instruction transmission generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time coefficient of the signal instruction transmission generated within the subsequent fixed time period is collected, and a corresponding data set D is established, D= ;in, , ,..., is a time point within a fixed time period, and n is a positive integer greater than 0;

[0027] Extract the features of the real-time coefficient within a fixed time period, and the feature vector X contains the extracted features: X={x1,x2,…,xm};

[0028] Use historical data to train the machine learning model, input the feature vector X, and output the predicted risk probability Prisk;

[0029] Extract features from new data sets, input them into the trained model, and predict the risk probability Prisk of signal instruction transmission failure in the real-time transmission process;

[0030] The prediction formula is: Prisk=f(X); where f is the trained risk prediction model;

[0031] Make decisions based on the predicted risk probability Prisk.

[0032] In a preferred embodiment, in S6, the acquired risk probability is compared with the risk probability reference threshold. If the risk probability is greater than or equal to the risk probability reference threshold, a warning signal is generated and the signal instruction transmission path is adjusted; if the risk probability is less than the risk probability reference threshold, no warning signal is generated and no adjustment is required.

[0033] The present invention also provides a railway freight transportation status early warning system, comprising a data acquisition module, a data processing module, a real-time evaluation module, a real-time division module and a path adjustment module;

[0034] Data acquisition module: several sensors are installed on the cargo for real-time monitoring, obtaining the real-time status data of the train and cargo, encrypting the real-time status data, and transmitting the encrypted data to the control center and the locomotive driver's equipment in real time through the wireless transmission network;

[0035] Data processing module: The computing system of the control center analyzes the transmitted data in real time and calculates the optimal travel speed and stop position according to the train operation plan and the current cargo status;

[0036] Real-time evaluation module: Generates corresponding signal instructions based on the analysis results and sends them to the locomotive driver through signal lights, signs and communication equipment. It conducts a comprehensive analysis of abnormal conditions in signal transmission and execution and the accuracy of train response instructions, and evaluates the real-time transmission of signal instructions;

[0037] Real-time classification module: the real-time of signal instruction transmission is classified into high real-time transmission, medium real-time transmission and low real-time transmission according to the evaluation results, and the low real-time transmission instructions are automatically corrected;

[0038] Path adjustment module: When the transmission process of the signal instruction is medium real-time transmission, the risk of signal instruction transmission failure in the medium real-time transmission process is predicted and warned, and the signal instruction transmission path is adjusted according to the prediction results to improve the accuracy of the transmission of cargo status information.

[0039] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0040] 1. The present invention can obtain the status data of the goods in real time through the sensors installed on the goods, and transmit the encrypted data to the control center and the locomotive driver's equipment through the wireless network. The control center uses real-time data analysis to calculate the optimal driving speed and parking position, and generates corresponding signal instructions to ensure safety and efficiency during transportation. In addition, by evaluating the real-time transmission of signal instructions, automatically correcting low-real-time instructions, and conducting risk prediction and early warning for medium-real-time transmission processes, the reliability of the system is further improved.

[0041] 2. Through real-time monitoring and data analysis, the present invention can timely discover and handle problems such as abnormal cargo status and transportation delays, optimize transportation plans, reduce transportation risks, ensure cargo safety and improve transportation efficiency. It not only improves the response speed and accuracy of the railway freight transportation system, but also reduces operating costs through intelligent management and improves overall transportation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0043] Figure 1 The present invention is a flow chart of the method.

[0044] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0045] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are 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 scope of protection of the present invention.

[0046] Example 1, please refer to Figure 1 As shown, the railway freight transportation status early warning method described in this embodiment includes the following steps:

[0047] S1: Install several sensors on the cargo for real-time monitoring, obtain the real-time status data of the cargo, encrypt the real-time status data, and transmit the encrypted data to the control center and the locomotive driver's equipment in real time through the wireless transmission network;

[0048] S2: The computing system of the control center analyzes the transmitted data in real time and calculates the optimal travel speed and stop position according to the train operation plan and the current cargo status;

[0049] S3: Generate corresponding signal instructions based on the analysis results and send them to the locomotive driver through signal lights, signs and communication equipment. Comprehensively analyze the abnormal conditions in signal transmission and execution and the accuracy of train response instructions, and evaluate the real-time transmission of signal instructions;

[0050] S4: classifying the real-time performance of the signal instruction transmission according to the evaluation result into high real-time performance transmission, medium real-time performance transmission and low real-time performance transmission, and automatically correcting the low real-time performance transmission instruction;

[0051] S5: When the transmission process of the signal instruction is medium real-time transmission, the risk of signal instruction transmission failure in the medium real-time transmission process is predicted and warned, and the signal instruction transmission path is adjusted according to the prediction result to improve the accuracy of the transmission of the cargo status information.

[0052] Among them, in S1, several sensors are installed on the cargo for real-time monitoring, obtaining the real-time status data of the cargo, encrypting the real-time status data, and transmitting the encrypted data to the control center and the locomotive driver's equipment in real time through the wireless transmission network, specifically:

[0053] Determine the cargo parameters that need to be monitored (such as temperature, humidity, vibration, location, etc.) Install appropriate sensors at key locations of the cargo to ensure that the sensors can collect data stably and accurately.

[0054] Calibrate the installed sensors to ensure that the data they read is accurate. Perform preliminary tests to verify that the sensors are working properly. Start the sensors to start real-time monitoring of the status data of the goods. The sensors send the collected data to the data processing unit at predetermined time intervals.

[0055] Use data encryption algorithms to encrypt the real-time status data collected by sensors to ensure the security of data during transmission. You can choose a suitable encryption algorithm, such as AES (Advanced Encryption Standard) or RSA (asymmetric encryption algorithm).

[0056] The encrypted data is transmitted to the control center and the locomotive driver's equipment in real time through the wireless transmission network. The wireless transmission network can choose LoRa, ZigBee, NB-IoT and other technologies suitable for long-distance and low-power transmission.

[0057] S2: The computing system of the control center analyzes the transmitted data in real time and calculates the optimal travel speed and stop location based on the train operation plan and the current cargo status.

[0058] The current position x(t) and time t of the train are obtained in real time through the sensor, and the calculation expression of the real-time speed v(t) of the train is: v(t) = ;

[0059] In order to avoid collision between trains, the safe distance dsafe of the trains is calculated, the maximum braking distance of the trains is obtained as dbrake, and the safety margin Δd is set: dsafe=dbrake+Δd; according to the current cargo status and the train operation plan, the optimal travel speed vopt(t) is calculated, the real-time target speed of the train is obtained as vtarget and the current speed is v(t), and the optimal travel speed vopt(t) is calculated according to the cargo status speed limit information vlimitv and the acceleration capacity a of the train. The specific calculation expression is: Where Δt is the time interval.

[0060] When the train stops at a certain position xstop, the optimal braking time tbrake and position xbrake are calculated according to the current train position x(t), speed v(t) and braking acceleration abrake. The calculation expression is: tbrake= ; The train should start braking at xbrake to ensure it stops at xstop.

[0061] Based on the calculation results, the corresponding signal instruction S(t) is generated, including the driving speed and the stopping position: S(t)={vopt(t),xbrake}; the control center analyzes the data transmitted by the sensors in real time and uses the formula to calculate the optimal driving speed and stopping position of the train to ensure the safety and efficiency of the train operation.

[0062] S3: Generate corresponding signal instructions based on the analysis results and send them to the locomotive driver through signal lights, signs and communication equipment. Comprehensively analyze the abnormal conditions in signal transmission and execution and the accuracy of train response instructions, and evaluate the real-time performance of signal instruction transmission.

[0063] The corresponding signal instructions are generated based on the analysis results and sent to the locomotive driver through signal lights, signs and communication equipment. Specifically:

[0064] Signal command generation: Generate control command S(t), including optimal driving speed vopt(t) and optimal braking position xbrake.

[0065] Signal transmission: Send instructions S(t) to the locomotive driver through signal lights, signs and communication equipment. Ensure the timeliness and accuracy of signal transmission to avoid delays and miscommunication.

[0066] The abnormal conditions in signal transmission and execution are analyzed to generate a redundant path switching abnormality index. The method for obtaining the redundant path switching abnormality index is as follows:

[0067] A system state set S={S0,S1,S2,…,St,…,Sn} is established, where t=1,2,…,n, and n is a positive integer greater than 0. The system states include: primary path normal, primary path faulty, redundant path normal, redundant path faulty, etc. A system action set A={A0,A1,…,At,…,Am} is established, where t=1,2,…,m, and m is a positive integer greater than 0. The system actions include: maintaining the current path and switching to the redundant path.

[0068] Calculate the transition probability P(s'|s,a), that is, the probability of taking action a in state s to transfer to state s', P(s'|s,a) =Pr(St+1=s'|St=s,At=a); and calculate the reward function R(s,a), that is, the immediate reward or cost of taking action a in state s, for example: the reward for keeping the path running normally, the cost of switching the path.

[0069] Get the value function V(s) of state s, that is, the long-term expected reward starting in state s, V(s) = [R(s,a)+γ ]; where γ is the discount factor, For the action a that maximizes, is the value function of the subsequent state s', which represents the long-term expected reward in state s'; the redundant path switching anomaly index is calculated, and the specific calculation expression is: P ; In the formula, is the redundant path switching anomaly index, Indicates the normal state after switching.

[0070] The redundant path switching anomaly index is an indicator used to quantify the probability of anomalies when path switching occurs. When the index is high, it indicates that there is a high probability of anomalies (such as signal loss, transmission delay, etc.) occurring during the switch from the primary path to the redundant path. Such anomalies will cause the signal instructions to fail to be transmitted in time, thus affecting the real-time operation and control of the train.

[0071] The real-time transmission of signal instructions is a key factor in ensuring safe and efficient train operation. High real-time performance means that signal instructions can be transmitted and executed in the shortest time, ensuring that the train can respond quickly to various situations, such as emergency braking, speed adjustment, etc. When the redundant path switching abnormality index is high, the transmission of signal instructions may be significantly delayed or interfered, and may not reach the locomotive driver or control system in time, thereby increasing the risk of train operation.

[0072] The accuracy of the train response command is analyzed to generate the response efficiency fluctuation index. The method for obtaining the response efficiency fluctuation index is:

[0073] Collect the time series data of train response instructions to show the train response efficiency to the instructions. ;

[0074] Define weights for each data point. New data points have higher weights. The weight sequence is ,and =1, calculate the weighted moving average of each time point, mark the weighted moving average as WMAt, the specific calculation expression is: WMAt= ; For the The weight of the data point, For time point The response frequency, n is the window size, which indicates the number of time points used to calculate the moving average;

[0075] Calculate the difference between the actual response data and the weighted moving average, that is, calculate the response efficiency fluctuation index. The specific calculation expression is: ; In the formula, To respond to the efficiency fluctuation index, is the actual response frequency at time point t.

[0076] The larger the response efficiency fluctuation index is, the greater the fluctuation is in the train's response to the signal command, reflecting the existence of unstable factors in the signal transmission process. These unstable factors may lead to delays in command transmission, data loss, or inaccurate command execution, thus affecting the normal operation of the train.

[0077] The larger the response efficiency fluctuation index is, the worse the real-time transmission of signal instructions is. Poor real-time performance means that signal instructions cannot be transmitted and executed within the expected time, resulting in the train's inability to respond in time. This may cause a series of problems, such as untimely adjustment of train speed, inability to brake or accelerate in time, etc., which in turn affects the overall operating efficiency and safety of the railway system.

[0078] A high response efficiency fluctuation index indicates that there is significant delay and instability in signal instruction transmission, which may cause the train to fail to accurately receive and execute instructions at critical moments, increasing operational risks. In order to ensure the safety and efficiency of train operation, it is necessary to minimize the response efficiency fluctuation index to ensure that signal instructions can be quickly and accurately transmitted to the train and executed in a timely manner. By improving signal transmission technology and optimizing system parameters, the real-time performance of signal instruction transmission can be effectively improved and the fluctuation index can be reduced.

[0079] The redundant path switching abnormality index and the response efficiency fluctuation index are normalized, and the real-time coefficient of signal instruction transmission is calculated through the normalized redundant path switching abnormality index and the response efficiency fluctuation index.

[0080] For example, the present invention may use the following formula to calculate the real-time coefficient of signal instruction transmission, and the calculation expression is: = ; In the formula, is the real-time coefficient of signal instruction transmission, is the redundant path switching anomaly index, To respond to the efficiency fluctuation index, are the proportional coefficients of redundant path switching anomaly index and response efficiency fluctuation index, respectively, and 0.

[0081] S4: The real-time performance of the signal instruction transmission is graded according to the evaluation result, and the real-time performance of the signal instruction transmission is divided into high real-time transmission, medium real-time transmission and low real-time transmission, and the low real-time transmission instruction is automatically corrected.

[0082] The real-time coefficient of the acquired signal instruction transmission is compared with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the real-time coefficient of the signal instruction transmission is compared with the first standard threshold and the second standard threshold respectively;

[0083] If the real-time coefficient of the signal instruction transmission is greater than the second standard threshold, the real-time of the signal instruction transmission is classified as high real-time transmission, and the signal transmission is confirmed to be stable and no further processing is required;

[0084] If the real-time coefficient of the signal instruction transmission is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time of the signal instruction transmission is classified as medium real-time transmission, the signal transmission is monitored to ensure that the real-time meets the requirements, and if possible, the network conditions are optimized or the system parameters are adjusted to improve to high real-time;

[0085] If the real-time coefficient of the signal instruction transmission is less than the first standard threshold, the real-time of the signal instruction transmission is classified as low real-time transmission, and the low real-time transmission instruction is automatically corrected, including: retransmitting lost or erroneous data packets; switching to a redundant path to avoid bottlenecks or failures in the main path; increasing the power of the signal transmission or using a signal amplifier to enhance the signal strength; adjusting the network configuration to reduce delays and interference and increase the transmission rate.

[0086] In this embodiment, a number of sensors are installed on the cargo for real-time monitoring, real-time status data of the train and the cargo are obtained, the real-time status data is encrypted, and the encrypted data is transmitted to the control center and the locomotive driver's equipment in real time through the wireless transmission network; the computing system of the control center analyzes the transmitted data in real time, and calculates the optimal travel speed and stop position according to the train operation plan and the current cargo status; the corresponding signal instructions are generated according to the analysis results, and sent to the locomotive driver through signal lights, signs and communication equipment, and the abnormal conditions in signal transmission and execution and the accuracy of the train response instructions are comprehensively analyzed to evaluate the real-time transmission of the signal instructions; the real-time transmission of the signal instructions is graded according to the evaluation results, and the real-time transmission of the signal instructions is divided into high real-time transmission, medium real-time transmission and low real-time transmission, and the low real-time transmission instructions are automatically corrected; the train operation can be efficiently managed and optimized, and the real-time and accuracy of the signal instruction transmission can be ensured, thereby improving the safety and reliability of the train operation.

[0087] Embodiment 2, S5: When the transmission process of the signal instruction is medium real-time transmission, the risk of signal instruction transmission failure in the medium real-time transmission process is predicted and warned, and the signal instruction transmission path is adjusted according to the prediction result to improve the accuracy of the transmission of the cargo status information.

[0088] When the transmission process of the signal instruction is medium real-time transmission, that is, the real-time coefficient of the signal instruction transmission generated in a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time coefficient of the signal instruction transmission generated in the subsequent fixed time period is collected and the corresponding data set D is established, D= ;in, , ,..., is a time point within a fixed time period, and n is a positive integer greater than 0;

[0089] Extract the features of the real-time coefficient within a fixed time period, such as mean, variance, maximum, minimum, etc. The feature vector X contains the extracted features: X={x1,x2,…,xm};

[0090] Risk prediction model training: Use historical data to train the machine learning model, input the feature vector X, and output the predicted risk probability Prisk.

[0091] Extract features from new data sets, input them into the trained model, and predict the risk probability Prisk of signal instruction transmission failure in the real-time transmission process;

[0092] The prediction formula is: Prisk=f(X); where f is the trained risk prediction model; decisions are made based on the predicted risk probability Prisk.

[0093] The acquired risk probability is compared with the risk probability reference threshold. If the risk probability is greater than or equal to the risk probability reference threshold, a warning signal is generated. The signal instruction transmission path is adjusted, the data transmission of the main path is stopped, the redundant path is enabled, the data transmission is started, and the transmission performance of the redundant path is monitored to ensure that it can operate stably to improve the accuracy of the transmission of cargo status information. If the risk probability is less than the risk probability reference threshold, no warning signal is generated and no adjustment is required.

[0094] In this embodiment, when the transmission process of the signal instruction is medium real-time transmission, that is, when the real-time coefficient of the signal instruction transmission generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time coefficient of the signal instruction transmission generated within the subsequent fixed time period is collected to establish a corresponding data set. The machine learning model is trained using historical data to predict the risk probability of signal instruction transmission failure in the medium real-time transmission process, and the acquired risk probability is compared with the risk probability reference threshold. If the risk probability is greater than or equal to the risk probability reference threshold, the signal instruction transmission path is adjusted, the data transmission of the main path is stopped, the redundant path is enabled, the data transmission starts, and the transmission performance of the redundant path is monitored to ensure that it can operate stably.

[0095] Example 3, please refer to Figure 2 As shown, a railway freight transportation status early warning system described in this embodiment includes a data acquisition module, a data processing module, a real-time evaluation module, a real-time division module and a path adjustment module;

[0096] Data acquisition module: install several sensors on the cargo for real-time monitoring, obtain the real-time status data of the cargo, encrypt the real-time status data, and transmit the encrypted data to the control center and the locomotive driver's equipment in real time through the wireless transmission network;

[0097] Data processing module: The computing system of the control center analyzes the transmitted data in real time and calculates the optimal travel speed and stop position according to the train operation plan and the current cargo status;

[0098] Real-time evaluation module: Generates corresponding signal instructions based on the analysis results and sends them to the locomotive driver through signal lights, signs and communication equipment. It conducts a comprehensive analysis of abnormal conditions in signal transmission and execution and the accuracy of train response instructions, and evaluates the real-time transmission of signal instructions;

[0099] Real-time classification module: the real-time of signal instruction transmission is classified into high real-time transmission, medium real-time transmission and low real-time transmission according to the evaluation results, and the low real-time transmission instructions are automatically corrected;

[0100] Path adjustment module: When the transmission process of the signal instruction is medium real-time transmission, the risk of signal instruction transmission failure in the medium real-time transmission process is predicted and warned, and the signal instruction transmission path is adjusted according to the prediction results to improve the accuracy of the transmission of cargo status information.

[0101] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0102] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0103] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0104] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0105] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0106] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A railway freight transportation status early warning method, characterized by: The steps include: S1: Install several sensors on the cargo for real-time monitoring, obtain the real-time status data of the cargo, encrypt the real-time status data, and transmit the encrypted data to the control center and the locomotive driver's equipment in real time through the wireless transmission network; S2: The computing system of the control center analyzes the transmitted data in real time and calculates the optimal travel speed and stop position according to the train operation plan and the current cargo status; The step S2 specifically includes: obtaining the current position x(t) and time t of the train in real time through the sensor, and the calculation expression of the real-time speed v(t) of the train is: In order to avoid collision between trains, the safe distance dsafe of the trains is calculated, the maximum braking distance of the train is obtained as dbrake, and the safety margin Δd is set: dsafe=dbrake+Δd; according to the current cargo status and the train operation plan, the optimal travel speed vopt(t) is calculated, the real-time target speed of the train is obtained as vtarget and the current speed is v(t), and the optimal travel speed vopt(t) is calculated according to the cargo status speed limit information vlimitv and the acceleration capacity a of the train. The calculation expression is: vopt(t)=min(vtarget, vlimit, v(t)+a×Δt); where Δt is the time interval; When the train stops at position xstop, the optimal braking time tbrake and position xbrake are calculated based on the current train position x(t), speed v(t) and braking acceleration abrake. The specific calculation expression is: The train starts braking at xbrake to ensure that it stops at xstop. According to the calculation results, the corresponding signal instruction S(t) is generated, including the travel speed and the stop position: S(t) = {vopt(t), xbrake}; S3: Generate corresponding signal instructions based on the analysis results and send them to the locomotive driver through signal lights, signs and communication equipment. Comprehensively analyze the abnormal conditions in signal transmission and execution and the accuracy of train response instructions, and evaluate the real-time transmission of signal instructions; The step S3 specifically includes: analyzing the abnormal conditions in signal transmission and execution to generate a redundant path switching abnormality index, and the method for obtaining the redundant path switching abnormality index is: Establish the system state set S = {S0, S1, S2, ..., St, ..., Sn}, t = 1, 2, ..., n, n is a positive integer greater than 0; and establish the system action set A = {A0, A1, ..., At, ..., Am}, t = 1, 2, ..., m, m is a positive integer greater than 0; calculate the transition probability P(s'|s, a), that is, the probability of taking action a in state s to transition to state s', P(s'|s, a) = Pr(St+1 = s'|St = s, At = a); and calculate the reward function R(s, a), that is, the immediate reward for taking action a in state s; Get the value function V(s) of state s, that is, the long-term expected reward starting in state s, V(s) = max a [R(s,a)+γ∑ s′ P(s'|s,aV(s'))]; where γ is the discount factor, max a is the maximizing action a, V(s') is the value function of the subsequent state s', which represents the long-term expected reward in state s'; the redundant path switching anomaly index is calculated, and the specific calculation expression is: QD = P(s' norroal |V(s),a); where QD is the redundant path switching anomaly index, s′ norroal Indicates the normal state after switching; The abnormal conditions in signal transmission and execution are analyzed to generate a redundant path switching abnormality index. The method for obtaining the redundant path switching abnormality index is as follows: Collect the time series data of train response instructions to represent the train's response efficiency to the instructions, and transform the time series data [y1, y2, ..., yn]; define weights for each data point, and the weight sequence is [w1, w2, ..., wn], and Calculate the weighted moving average at each time point and mark the weighted moving average as WMAt. The specific calculation expression is: w i+1 is the weight of the i+1th data point, y t-i is the response frequency at time point ti, n is the window size, which indicates the number of time points used to calculate the moving average; Calculate the difference between the actual response data and the weighted moving average, that is, calculate the response efficiency fluctuation index. The specific calculation expression is: EK = |y t -WMAt|; where EK is the response efficiency fluctuation index, y t is the actual response frequency at time point t; The redundant path switching abnormality index and the response efficiency fluctuation index are normalized, and the real-time coefficient of signal instruction transmission is calculated by the normalized redundant path switching abnormality index and the response efficiency fluctuation index. The calculation expression is: Wherein, AX is the real-time coefficient of signal instruction transmission, QD is the redundant path switching abnormality index, EK is the response efficiency fluctuation index, a1 and a2 are the proportional coefficients of the redundant path switching abnormality index and the response efficiency fluctuation index, respectively, and a2>a1>0; S4: classifying the real-time performance of the signal instruction transmission according to the evaluation result into high real-time performance transmission, medium real-time performance transmission and low real-time performance transmission, and automatically correcting the low real-time performance transmission instruction; S5: When the transmission process of the signal instruction is medium real-time transmission, the risk of signal instruction transmission failure in the medium real-time transmission process is predicted and warned, and the signal instruction transmission path is adjusted according to the prediction result to improve the accuracy of the transmission of the cargo status information.

2. A railway freight transportation status early warning method according to claim 1, characterized in that: According to the evaluation results, the real-time performance of signal instruction transmission is divided into levels, specifically: The real-time coefficient of the acquired signal instruction transmission is compared with a gradient standard threshold, the gradient standard threshold includes a first standard threshold and a second standard threshold, and the first standard threshold is less than the second standard threshold, and the real-time coefficient of the signal instruction transmission is compared with the first standard threshold and the second standard threshold respectively; If the real-time coefficient of the signal instruction transmission is greater than the second standard threshold, the real-time of the signal instruction transmission is classified as high real-time transmission; If the real-time coefficient of the signal instruction transmission is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time of the signal instruction transmission is classified as medium real-time transmission; If the real-time coefficient of the signal instruction transmission is less than the first standard threshold, the real-time of the signal instruction transmission is classified as low real-time transmission, and the low real-time transmission instruction is automatically corrected.

3. A railway freight transportation status early warning method according to claim 2, characterized in that: In S5, when the transmission process of the signal instruction is medium real-time transmission, that is, the real-time coefficient of the signal instruction transmission generated within a fixed time period is greater than or equal to the first standard threshold and less than or equal to the second standard threshold, the real-time coefficient of the signal instruction transmission generated within the subsequent fixed time period is collected and a corresponding data set D is established, D = [AX t1 , AX t2 , ..., AX tn ]; where t1, t2, ..., tn are time points within a fixed time period, and n is a positive integer greater than 0; Extract the features of the real-time coefficient within a fixed time period, and the feature vector X contains the extracted features: X = {x1, x2, ..., xm}; Use historical data to train the machine learning model, input the feature vector X, and output the predicted risk probability Prisk; Extract features from new data sets, input them into the trained model, and predict the risk probability Prisk of signal instruction transmission failure in the real-time transmission process; The prediction formula is: Prisk = f(X); where f is the trained risk prediction model; Make decisions based on the predicted risk probability Prisk.

4. A railway freight transportation status early warning method according to claim 3, characterized in that: In S6, the acquired risk probability is compared with the risk probability reference threshold. If the risk probability is greater than or equal to the risk probability reference threshold, a warning signal is generated and the signal instruction transmission path is adjusted. If the risk probability is less than the risk probability reference threshold, no warning signal is generated and no adjustment is required.

5. A railway freight transportation status early warning system, used to implement a railway freight transportation status early warning method according to any one of claims 1 to 4, characterized in that: It includes a data acquisition module, a data processing module, a real-time evaluation module, a real-time division module and a path adjustment module; Data acquisition module: several sensors are installed on the cargo for real-time monitoring, obtaining the real-time status data of the train and cargo, encrypting the real-time status data, and transmitting the encrypted data to the control center and the locomotive driver's equipment in real time through the wireless transmission network; Data processing module: The computing system of the control center analyzes the transmitted data in real time and calculates the optimal travel speed and stop position according to the train operation plan and the current cargo status; Real-time evaluation module: Generates corresponding signal instructions based on the analysis results and sends them to the locomotive driver through signal lights, signs and communication equipment. It conducts a comprehensive analysis of abnormal conditions in signal transmission and execution and the accuracy of train response instructions, and evaluates the real-time transmission of signal instructions; Real-time classification module: the real-time of signal instruction transmission is classified into high real-time transmission, medium real-time transmission and low real-time transmission according to the evaluation results, and the low real-time transmission instructions are automatically corrected; Path adjustment module: When the transmission process of the signal instruction is medium real-time transmission, the risk of signal instruction transmission failure in the medium real-time transmission process is predicted and warned, and the signal instruction transmission path is adjusted according to the prediction results to improve the accuracy of the transmission of cargo status information.

Images