Rail transit line monitoring sensor layout optimization method and system for vehicle-rail cooperation

Abstract

The invention provides a rail transit line monitoring sensor layout optimization method and system oriented to vehicle-rail cooperation, and belongs to the technical field of rail transit system monitoring optimization. Based on the sensing accuracy of the monitoring sensor sensing algorithm to the abnormal event, determining the combined sensing accuracy of the monitoring sensor to the abnormal event under the vehicle-track cooperation; according to the combined sensing accuracy of the monitoring sensors on the abnormal events under the vehicle-rail cooperation, the arrangement distance and the arrangement number of the trackside monitoring sensors are calculated; and optimizing trackside monitoring sensors close to the area junction according to the maximum monitoring sensor layout spacing allowed by the sensing accuracy threshold. According to the method, factors such as sensing boundaries, sensing accuracy and layout cost of the monitoring sensors are fully considered, and the layout cost of the monitoring sensors is effectively reduced on the premise of ensuring high sensing accuracy of the monitoring sensors to line abnormal events aiming at the phenomenon of resource waste caused by the fact that the trackside monitoring sensors at the region junction are too close; the economy is higher.

Description

Technical Field

[0001] The present invention relates to the technical field of rail transit system monitoring optimization, and in particular to a rail transit line monitoring sensor layout optimization method and system oriented to vehicle-track collaboration. Background Art

[0002] According to statistics, one of the main reasons for related accidents in rail transit is abnormal external environment, such as natural disasters causing damage to line infrastructure and foreign body intrusion. Therefore, comprehensive monitoring of the train operation environment is of great significance to ensure the safe operation of trains. In the rail transit system, by deploying monitoring sensor equipment at the front of the train and along the track, the environmental status along the line can be monitored, the autonomous perception ability of the rail transit system can be improved, and the safety of the train operation environment can be ensured. Relevant units have issued corresponding standard documents and technical specifications for rail transit video monitoring, indicating the monitoring requirements of each component and key nodes of the system, and standardizing the protection requirements and equipment technical requirements of the video monitoring system. For the monitoring of rail transit lines, the existing video monitoring solution is to deploy long-distance cameras on the towers on both sides of the line to monitor the section lines on both sides of the towers. With the rapid construction of rail transit in recent years, high-speed trains have higher requirements for the safety of the operating environment, and the existing monitoring system along the line is difficult to meet the rail transit safety protection goals. In the "Standards for the Setting of Video Monitoring of Railway Section Lines", for lines with higher design speeds, the types and density of medium and short-distance monitoring sensors are increased to achieve comprehensive and continuous monitoring of the line.

[0003] At present, the cost of monitoring sensors such as cameras and lidar is gradually decreasing, and they can obtain data information with complementary characteristics, ensuring the validity of data under different lighting and weather conditions. The relevant intelligent analysis algorithms are also developing rapidly, and the monitoring and analysis effects are reliable. Monitoring sensors based on this combination can meet the needs of all-weather monitoring and intelligent analysis. However, the rail transit lines are long, and to achieve full coverage of monitoring sensors, the deployment and system maintenance costs are extremely high, and the feasibility is poor. Multimodal sensors and related intelligent analysis algorithms can effectively perceive abnormal events with a small pixel ratio, broaden the perception boundaries of monitoring sensors under existing standards, and reduce the number of deployments. Based on the needs of on-site monitoring, the development trend of monitoring sensors and intelligent algorithms, it is necessary to propose a reasonable monitoring sensor deployment method to achieve efficient monitoring and save sensor deployment costs. Summary of the invention

[0004] The object of the present invention is to provide a method and system for optimizing the deployment of rail transit line monitoring sensors for vehicle-track collaboration, so as to solve at least one technical problem existing in the above-mentioned background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect, the present invention provides a rail transit line monitoring sensor deployment optimization method for vehicle-track collaboration, which is characterized by comprising:

[0007] According to the monitoring performance of the monitoring sensor and the perception algorithm's ability to perceive abnormal events, determine the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm for abnormal events, as well as the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration;

[0008] Calculate the layout spacing of trackside monitoring sensors based on the joint perception accuracy of abnormal events under vehicle-track collaboration; divide the entire line into regions according to the changes in line characteristics, and calculate the number of trackside monitoring sensors required in each region based on the layout spacing;

[0009] For adjacent trackside monitoring sensors at the regional junction, the maximum trackside monitoring sensor layout spacing allowed by the perception accuracy threshold is calculated, the monitoring sensors with closer distances at the regional junction are optimized, and the total number of trackside monitoring sensors required for the entire line is calculated.

[0010] Furthermore, the accuracy of the perception algorithm based on the monitoring sensor is correlated with the distance from the abnormal event to the monitoring sensor. The perception accuracy of the monitoring sensor decreases with increasing distance. This method assumes that within the range of distance a, the perception accuracy of the monitoring sensor is p. Beyond the range, the perception accuracy decreases with increasing distance. Within the range of distance a to b, the relationship between the perception accuracy and distance is: When the distance exceeds b, the monitoring sensor cannot sense anything.

[0011] Furthermore, the monitoring sensor perception accuracy distribution function is as follows:

[0012]

[0013] Where x is the distance from the abnormal event to the monitoring sensor, and p(x) is the monitoring sensor’s perception accuracy of the abnormal event at distance x.

[0014] Furthermore, the perception accuracy of the trackside monitoring sensor for abnormal events at a distance x from it is p(x), and the perception accuracy of the onboard monitoring sensor for abnormal events at a distance y from the front of the train is p(y); the working state of the monitoring sensor system for vehicle-track collaboration is divided into two cases depending on whether there is a train passing by; the formula for the joint perception accuracy of the vehicle-track collaborative monitoring sensor system for abnormal events is expressed as follows:

[0015]

[0016] Among them, s represents the working status of the collaborative system, s=0 means that there is no train passing, and only the trackside monitoring sensors are working in the system; s=1 means that there is a train passing, and both the trackside monitoring sensors and the on-board monitoring sensors are involved in the work; f(p(x), p(y)) is the accuracy of the vehicle-track collaborative perception algorithm.

[0017] Furthermore, assuming that the average perception accuracy of the trackside monitoring sensors within the layout interval D is The calculation formula for the layout spacing D between adjacent trackside monitoring sensors is as follows:

[0018]

[0019] In order to ensure the effectiveness of sensing abnormal events in different situations, the trackside monitoring sensors are arranged at equal intervals. Therefore, in an area with a length of S, the number of trackside monitoring sensors N that need to be deployed is calculated as follows:

[0020] The entire line is divided into areas according to the changes in the line's characteristics, and the number of trackside monitoring sensors required for each area is calculated based on the layout spacing.

[0021] Furthermore, under the condition of full coverage, a perception accuracy threshold is set for the junction area, and the maximum spacing allowed for the deployment of adjacent monitoring sensors under the threshold condition is calculated, so as to determine the selection of terminal monitoring sensors in each area; the number of monitoring sensors finally deployed in each area is calculated as follows:

[0022]

[0023] Among them, C i is the number of trackside monitoring sensors finally deployed in area i, n is the number of trackside monitoring sensors deployed in area i, is the position of the second to last trackside monitoring sensor at the end of the ith zone, is the position of the trackside monitoring sensor at the beginning of the i+1th zone, D max It is the maximum spacing allowed under the perception accuracy threshold.

[0024] In a second aspect, the present invention provides a rail transit line monitoring sensor deployment optimization system for vehicle-track collaboration, comprising:

[0025] Establishing a module, for determining the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm for abnormal events, and the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration, according to the monitoring performance of the monitoring sensor and the perception ability of the perception algorithm for abnormal events;

[0026] The division module is used to calculate the layout spacing of the trackside monitoring sensors according to the joint perception accuracy of abnormal events by the monitoring sensors under the coordination of the train and track; divide the entire line into regions according to the characteristic changes of the line, and calculate the number of trackside monitoring sensors required in each region according to the layout spacing;

[0027] The calculation module is used to calculate the maximum trackside monitoring sensor layout spacing allowed by the perception accuracy threshold for adjacent trackside monitoring sensors at the regional junction, optimize the monitoring sensors that are closer at the regional junction, and calculate the total number of trackside monitoring sensors required for the entire line.

[0028] In a third aspect, the present invention provides a non-transitory computer-readable storage medium, which is used to store computer instructions. When the computer instructions are executed by a processor, the rail transit line monitoring sensor deployment optimization method for vehicle-track collaboration as described in the first aspect is implemented.

[0029] In a fourth aspect, the present invention provides a computer device comprising a memory and a processor, wherein the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the rail transit line monitoring sensor layout optimization method for vehicle-track collaboration as described in the first aspect.

[0030] In a fifth aspect, the present invention provides an electronic device, comprising: a processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the method for optimizing the layout of rail transit line monitoring sensors for vehicle-track collaboration as described in the first aspect.

[0031] Beneficial effects of the present invention: Based on the joint perception accuracy of abnormal events by the vehicle-track collaborative monitoring sensor perception algorithm, a method for calculating the spacing and number of trackside monitoring sensors is proposed. At the same time, the rail transit line is divided into regions, and the number of trackside monitoring sensors required for each region is calculated separately. Compared with the existing layout standards, this optimized layout method reduces the number of monitoring sensors on the basis of ensuring a high perception accuracy of abnormal events, reduces the layout cost, and is more economical and reasonable.

[0032] Additional advantages of the present invention will be more clearly given in the following description or learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0034] Figure 1 This is an overall flow chart of the rail transit line monitoring sensor deployment optimization method for vehicle-track collaboration according to an embodiment of the present invention.

[0035] Figure 2 This is a framework diagram of the rail transit line monitoring sensor deployment optimization method for vehicle-track collaboration according to an embodiment of the present invention.

[0036] Figure 3 This is a schematic diagram of the deployment of rail transit line monitoring sensors for vehicle-track collaboration according to an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below by the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be interpreted as limiting the present invention.

[0038] It should be understood by those skilled in the art that unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those skilled in the art to which this invention belongs.

[0039] It should also be understood that terms, such as those defined in commonly used dictionaries, should be understood to have a meaning consistent with that in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless as defined herein.

[0040] Those skilled in the art will appreciate that, unless otherwise stated, the singular forms "a", "an", "said" and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present invention refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements and / or groups thereof.

[0041] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. Different embodiments or examples described in this specification and features of different embodiments or examples may be combined and combined by those skilled in the art without contradiction.

[0042] To facilitate understanding of the present invention, the present invention is further explained below with reference to specific embodiments in conjunction with the accompanying drawings, and the specific embodiments do not constitute a limitation on the embodiments of the present invention.

[0043] Those skilled in the art should understand that the drawings are merely schematic diagrams of embodiments, and the components in the drawings are not necessarily necessary for implementing the present invention.

[0044] Example 1

[0045] In this embodiment 1, a rail transit line monitoring sensor layout optimization system for vehicle-track collaboration is first provided, including: an establishment module, which is used to determine the perception accuracy distribution function of the monitoring sensor-based perception algorithm for abnormal events, and the joint perception accuracy of the monitoring sensors for abnormal events under vehicle-track collaboration according to the monitoring performance of the monitoring sensors and the perception ability of the perception algorithm for abnormal events; a division module, which is used to calculate the layout spacing of the trackside monitoring sensors according to the joint perception accuracy of the monitoring sensors for abnormal events under vehicle-track collaboration; according to the characteristic changes of the line, the entire line is divided into regions, and the number of trackside monitoring sensors required for each region is calculated according to the layout spacing; a calculation module, which is used to calculate the maximum trackside monitoring sensor layout spacing allowed by the perception accuracy threshold for adjacent trackside monitoring sensors at the junction of the regions, optimize the monitoring sensors that are close at the junction of the regions, and calculate the total number of trackside monitoring sensors required for the entire line.

[0046] In this embodiment 1, the above-mentioned system is used to implement a rail transit line monitoring sensor deployment optimization method for vehicle-track collaboration, including the following steps:

[0047] According to the monitoring performance of the monitoring sensor and the perception algorithm's ability to perceive abnormal events, determine the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm for abnormal events, as well as the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration;

[0048] According to the joint perception accuracy of abnormal events by monitoring sensors under vehicle-track coordination, the layout spacing of trackside monitoring sensors is calculated. According to the characteristic changes of the line, the entire line is divided into regions, and the number of trackside monitoring sensors required in each region is calculated according to the layout spacing.

[0049] In order to address the waste of resources caused by the close distance between adjacent trackside monitoring sensors at the junction of tunnels, bridges and other areas, the maximum trackside monitoring sensor layout spacing allowed by the perception accuracy threshold is calculated, and the monitoring sensors with closer distances at the junction of areas are optimized. The total number of trackside monitoring sensors required for the entire line is calculated.

[0050] The accuracy of the perception algorithm based on the monitoring sensor is correlated with the distance from the abnormal event to the monitoring sensor. The perception accuracy of the monitoring sensor decreases as the distance increases. This method assumes that within the range of distance a, the perception accuracy of the monitoring sensor is p. Beyond the range, the perception accuracy decreases as the distance increases. Within the distance from a to b, the relationship between the perception accuracy and the distance is: When the distance exceeds b, the monitoring sensor cannot sense anything. Therefore, the monitoring sensor perception accuracy distribution function is as follows:

[0051]

[0052] Where x is the distance from the abnormal event to the monitoring sensor, and p(x) is the monitoring sensor’s perception accuracy of the abnormal event at distance x.

[0053] The perception accuracy of the trackside monitoring sensor for abnormal events at a distance x from it is p(x), and the perception accuracy of the onboard monitoring sensor for abnormal events at a distance y from the front of the train is p(y). The working state of the monitoring sensor system for vehicle-track collaboration is divided into two cases depending on whether there is a train passing by. The formula for the joint perception accuracy of the vehicle-track collaborative monitoring sensor system for abnormal events is expressed as follows:

[0054]

[0055] Among them, s represents the working state of the collaborative system. s = 0 means that there is no train passing by and only the trackside monitoring sensors in the system are working; s = 1 means that there is a train passing by and both the trackside monitoring sensors and the on-board monitoring sensors are working. f(p(x),p(y)) is the accuracy of the vehicle-track collaborative perception algorithm.

[0056] Assume that the average perception accuracy within the layout interval D of the trackside monitoring sensors is The calculation formula for the layout spacing D between adjacent trackside monitoring sensors is as follows:

[0057]

[0058] In order to ensure the effectiveness of sensing abnormal events in different situations, the trackside monitoring sensors are arranged at equal intervals. Therefore, in an area with a length of S, the number of trackside monitoring sensors that need to be arranged is calculated as follows:

[0059]

[0060] The entire line is divided into areas according to the changes in the line's characteristics, and the number of trackside monitoring sensors required for each area is calculated based on the layout spacing.

[0061] Under full coverage conditions, such as at the junction of tunnels, bridges and other areas, there will be a phenomenon of waste of resources due to the proximity of adjacent trackside sensors. To address this problem, a perception accuracy threshold is set, and the maximum spacing allowed for adjacent monitoring sensors under this threshold condition is calculated according to formulas (1), (2), and (3), so as to determine the selection of monitoring sensors at the end of each area. The number of monitoring sensors finally deployed in each area is calculated as follows:

[0062]

[0063] Among them, C i is the number of trackside monitoring sensors finally deployed in area i, n is the number of trackside monitoring sensors deployed in area i calculated by formula (4), is the position of the second to last trackside monitoring sensor at the end of the ith zone, is the position of the trackside monitoring sensor at the beginning of the i+1th zone, D max It is the maximum spacing allowed under the perception accuracy threshold.

[0064] Example 2

[0065] like Figures 1 to 3 As shown, in this embodiment 2, a method for optimizing the deployment of monitoring sensors for rail transit lines oriented to vehicle-track collaboration is provided to reduce the deployment cost of monitoring sensors while ensuring that the monitoring sensors have a high perception accuracy rate for abnormal events. The method mainly includes the following steps:

[0066] Step S1: According to the monitoring performance of the monitoring sensor and the perception ability of the perception algorithm to abnormal events, determine the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm to abnormal events as the distance changes, and further determine the joint perception accuracy of the monitoring sensor to abnormal events under vehicle-track collaboration.

[0067] Step S2: Calculate the layout spacing of the trackside monitoring sensors based on the joint perception accuracy of abnormal events under the vehicle-track collaboration. Divide the entire line into regions according to the characteristic changes of the line, and calculate the number of trackside monitoring sensors required in each region based on the layout spacing.

[0068] Step S3: In view of the situation where the distance between trackside monitoring sensors at the junction of areas is too close, causing waste of resources, an acceptable minimum perception accuracy threshold is set for the junction area while ensuring the perception accuracy, and the spacing between trackside monitoring sensors in the junction area is compared with the spacing threshold, so as to flexibly adjust the trackside monitoring sensors at the end of each area.

[0069] Furthermore, step S1 specifically includes the following steps:

[0070] Step 1.1, determine the distribution function of the perception accuracy of the algorithm based on monitoring sensors for abnormal events. The accuracy of the perception algorithm based on monitoring sensors is correlated with the distance from the abnormal event to the monitoring sensor. The perception accuracy of the monitoring sensor will decrease with increasing distance. Assume that within the range of distance a, the perception accuracy of the monitoring sensor is p. Beyond the range, the perception accuracy will decrease with increasing distance. Within the range of distance a to b, the relationship between perception accuracy and distance is: When the distance exceeds b, the monitoring sensor cannot sense anything. Therefore, the monitoring sensor perception accuracy distribution function is as follows:

[0071]

[0072] Where x is the distance from the abnormal event to the monitoring sensor, and p(x) is the monitoring sensor’s perception accuracy of the abnormal event at distance x.

[0073] Step 1.2, determine the joint perception accuracy of abnormal events by the monitoring sensors under vehicle-track collaboration. The perception accuracy of the trackside monitoring sensor for abnormal events at a distance x from it is p(x), and the perception accuracy of the onboard monitoring sensor for abnormal events at a distance y from the front of the train is p(y). The working state of the monitoring sensor system for vehicle-track collaboration is divided into two cases depending on whether there is a train passing by. The formula for the joint perception accuracy of abnormal events by the vehicle-track collaborative monitoring sensor system is expressed as follows:

[0074]

[0075] Among them, s represents the working state of the collaborative system. s = 0 means that there is no train passing by and only the trackside monitoring sensors in the system are working; s = 1 means that there is a train passing by and both the trackside monitoring sensors and the on-board monitoring sensors are working. f(p(x),p(y)) is the accuracy of the vehicle-track collaborative perception algorithm.

[0076] Step S2 specifically includes the following steps:

[0077] Step 2.1, calculate the spacing between adjacent trackside monitoring sensors under high perception accuracy. Assume that the average perception accuracy within the spacing D of trackside monitoring sensors is The calculation formula for the layout spacing D between adjacent trackside monitoring sensors is as follows:

[0078]

[0079] Step 2.2, calculate the number of trackside monitoring sensors deployed within a certain area length. Since the trackside monitoring sensors are deployed at equal intervals, the calculation formula for the number of trackside monitoring sensors that need to be deployed in an area of ​​length S is as follows:

[0080]

[0081] Step 2.3: Divide the entire line into regions according to the changes in the characteristics of the line, and calculate the number of trackside monitoring sensors required for each region based on the layout spacing.

[0082] The method for deploying monitoring sensors in the boundary area described in step S3 takes into account the requirements for on-site perception accuracy and deployment costs. Under full coverage conditions, such as at the junction of tunnels, bridges and other areas, there will be a problem of waste of resources due to the proximity of adjacent trackside sensors. Set a perception accuracy threshold, and calculate the maximum spacing allowed for adjacent trackside monitoring sensors under the threshold condition according to formulas (1), (2), and (3), so as to determine the selection of trackside monitoring sensors at the end of each area. The calculation formula for the spacing between monitoring sensors is the same as (4). Here, it is assumed that the maximum spacing allowed under the perception accuracy threshold is D max The number of trackside monitoring sensors ultimately deployed in each area is calculated as follows:

[0083]

[0084] Among them, C i is the number of trackside monitoring sensors finally deployed in area i, n is the number of trackside monitoring sensors deployed in area i calculated by formula (4), is the position of the second to last trackside monitoring sensor at the end of the ith zone, is the position of the trackside sensor at the beginning of the i+1th zone, D max It is the maximum spacing allowed under the perception accuracy threshold.

[0085] Example 3

[0086] In this embodiment 3, a rail transit line monitoring sensor deployment optimization method for vehicle-track collaboration is provided. This method can effectively reduce the deployment cost of monitoring sensors while ensuring high perception accuracy of abnormal events. Compared with existing deployment standards, this method is more economical and reasonable.

[0087] The specific implementation process of the rail transit line monitoring sensor deployment optimization method for vehicle-track collaboration provided in this embodiment includes the following steps:

[0088] Step S1, according to the monitoring performance of the monitoring sensor and the perception ability of the perception algorithm to abnormal events, determine the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm to abnormal events as the distance changes, and the joint perception accuracy of the monitoring sensor to abnormal events under vehicle-track collaboration.

[0089] The step S1 specifically includes the following steps:

[0090] Step 1.1, determine the distribution function of the perception accuracy of the algorithm based on monitoring sensors for abnormal events. The accuracy of the perception algorithm based on monitoring sensors is correlated with the distance from the abnormal event to the monitoring sensor. The perception accuracy of the monitoring sensor will decrease with increasing distance. Assume that within the range of distance a, the perception accuracy of the monitoring sensor is p. Beyond the range, the perception accuracy will decrease with increasing distance. Within the range of distance a to b, the relationship between perception accuracy and distance is: When the distance exceeds b, the monitoring sensor cannot sense anything. Therefore, the monitoring sensor perception accuracy distribution function is as follows:

[0091]

[0092] Where x is the distance from the abnormal event to the monitoring sensor, and p(x) is the monitoring sensor’s perception accuracy of the abnormal event at distance x.

[0093] Step 1.2, determine the joint perception accuracy of abnormal events by the monitoring sensors under vehicle-track collaboration. The perception accuracy of the trackside monitoring sensor for abnormal events at a distance x from it is p(x), and the perception accuracy of the onboard monitoring sensor for abnormal events at a distance y from the front of the train is p(y). The working state of the monitoring sensor system for vehicle-track collaboration is divided into two cases depending on whether there is a train passing by. The formula for the joint perception accuracy of abnormal events by the vehicle-track collaborative monitoring sensor system is expressed as follows:

[0094]

[0095] Among them, s represents the working state of the collaborative system. s = 0 means that there is no train passing by and only the trackside monitoring sensors in the system are working; s = 1 means that there is a train passing by and both the trackside monitoring sensors and the on-board monitoring sensors are working.f(p(x),p(y)) is the accuracy of the vehicle-track collaborative perception algorithm.

[0096] Step S2: Calculate the layout spacing of the trackside monitoring sensors based on the joint perception accuracy of abnormal events under the vehicle-track collaboration. Divide the entire line into regions according to the characteristic changes of the line, and calculate the number of trackside monitoring sensors required in each region based on the layout spacing.

[0097] The step S2 specifically includes the following steps:

[0098] Step 2.1, calculate the spacing of adjacent trackside monitoring sensors under high perception accuracy. Assume that the average perception accuracy within the spacing D of the monitoring sensors is The calculation formula for the layout spacing D between adjacent trackside monitoring sensors is as follows:

[0099]

[0100] Step 2.2, calculate the number of trackside monitoring sensors to be deployed within a certain interval length. To ensure that the trackside monitoring sensors are deployed at equal intervals in each case. Therefore, on a line with a length of S, the calculation formula for the number of trackside monitoring sensors that need to be deployed is as follows:

[0101]

[0102] Step 2.3: Divide the entire line into regions according to the changes in the characteristics of the rail transit line, and calculate the number of trackside monitoring sensors required for each region based on the layout spacing.

[0103] The step S3 specifically adjusts the monitoring sensor layout at the end of each area by comparing the distance between adjacent monitoring sensors at the junction of tunnels, bridges and other areas with the spacing under the minimum accuracy threshold. Specifically, the monitoring sensor layout spacing calculation formula is the same as (4), where it is assumed that the maximum layout spacing allowed under the perception accuracy threshold is D max .

[0104] The number of trackside monitoring sensors ultimately deployed in each area is calculated as follows:

[0105]

[0106] Among them, C i is the number of trackside monitoring sensors finally deployed in area i, n is the number of trackside monitoring sensors deployed in area i calculated by formula (4), is the position of the second to last trackside monitoring sensor at the end of the ith zone, is the position of the trackside sensor at the beginning of the i+1th zone, D maxIt is the maximum spacing allowed under the perception accuracy threshold.

[0107] In summary, the method provided in this embodiment innovatively proposes an optimization method for the deployment of rail transit line monitoring sensors for vehicle-track collaboration, in response to the huge cost problem of full coverage of rail transit line monitoring sensors. This method takes the joint perception accuracy of abnormal events by the vehicle-track collaborative monitoring sensor perception algorithm as a benchmark, and proposes a method for calculating the deployment spacing and number of trackside monitoring sensors. At the same time, the rail transit line is divided into regions, and the number of trackside monitoring sensors required for each region is calculated separately. Compared with the existing deployment standards, this optimized deployment method reduces the number of monitoring sensors deployed and reduces the deployment cost on the basis of ensuring a high perception accuracy of abnormal events, making it more economical and reasonable.

[0108] Example 4

[0109] This embodiment 4 provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the above-mentioned rail transit line monitoring sensor layout optimization method for vehicle-track collaboration is implemented. The method includes:

[0110] According to the monitoring performance of the monitoring sensor and the perception algorithm's ability to perceive abnormal events, determine the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm for abnormal events, as well as the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration;

[0111] Calculate the layout spacing of trackside monitoring sensors based on the joint perception accuracy of abnormal events under vehicle-track collaboration; divide the entire line into regions according to the changes in line characteristics, and calculate the number of trackside monitoring sensors required in each region based on the layout spacing;

[0112] For adjacent trackside monitoring sensors at the regional junction, the maximum trackside monitoring sensor layout spacing allowed by the perception accuracy threshold is calculated, the monitoring sensors with closer distances at the regional junction are optimized, and the total number of trackside monitoring sensors required for the entire line is calculated.

[0113] Example 5

[0114] This embodiment 5 provides a computer device, including a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions executable by the processor, the processor calls the program instructions to execute the above-mentioned rail transit line monitoring sensor layout optimization method for vehicle-track collaboration, the method comprising:

[0115] According to the monitoring performance of the monitoring sensor and the perception algorithm's ability to perceive abnormal events, determine the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm for abnormal events, as well as the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration;

[0116] Calculate the layout spacing of trackside monitoring sensors based on the joint perception accuracy of abnormal events under vehicle-track collaboration; divide the entire line into regions according to the changes in line characteristics, and calculate the number of trackside monitoring sensors required in each region based on the layout spacing;

[0117] For adjacent trackside monitoring sensors at the regional junction, the maximum trackside monitoring sensor layout spacing allowed by the perception accuracy threshold is calculated, the monitoring sensors with closer distances at the regional junction are optimized, and the total number of trackside monitoring sensors required for the entire line is calculated.

[0118] Example 6

[0119] This embodiment 6 provides an electronic device, including: a processor, a memory, and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory, so that the electronic device executes instructions for implementing the above-mentioned rail transit line monitoring sensor layout optimization method for vehicle-track collaboration, the method comprising:

[0120] According to the monitoring performance of the monitoring sensor and the perception algorithm's ability to perceive abnormal events, determine the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm for abnormal events, as well as the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration;

[0121] Calculate the layout spacing of trackside monitoring sensors based on the joint perception accuracy of abnormal events under vehicle-track collaboration; divide the entire line into regions according to the changes in line characteristics, and calculate the number of trackside monitoring sensors required in each region based on the layout spacing;

[0122] For adjacent trackside monitoring sensors at the regional junction, the maximum trackside monitoring sensor layout spacing allowed by the perception accuracy threshold is calculated, the monitoring sensors with closer distances at the regional junction are optimized, and the total number of trackside monitoring sensors required for the entire line is calculated.

[0123] In summary, the method for optimizing the deployment of monitoring sensors for rail transit lines in vehicle-track collaboration according to the embodiment of the present invention. The method comprises: first, based on the perception accuracy of the monitoring sensor perception algorithm for abnormal events, determining the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration; then, calculating the deployment spacing and deployment quantity of the trackside monitoring sensors according to the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration; finally, optimizing the trackside monitoring sensors at the junction of bridges, tunnels, etc. that are close to other areas according to the maximum monitoring sensor deployment spacing allowed by the perception accuracy threshold. The monitoring sensor optimization deployment method proposed by the method of the present invention fully considers factors such as the monitoring sensor perception boundary, perception accuracy, and deployment cost, and proposes a method for calculating the deployment spacing and specific deployment quantity of the trackside monitoring sensors. And an optimization method is proposed for the waste of resources caused by the trackside monitoring sensors being too close at the junction of the area. The method effectively reduces the deployment cost of the monitoring sensors while ensuring the high perception accuracy of the monitoring sensors for abnormal events on the line, which is more economical.

[0124] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0125] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0126] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0128] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Technical personnel in the relevant field should understand that various modifications or variations that can be made by those skilled in the art without creative work on the basis of the technical solution disclosed in the present invention should be included in the scope of protection of the present invention.

Claims

1. A rail transit line monitoring sensor layout optimization method for vehicle-track collaboration, characterized in that: include: According to the monitoring performance of the monitoring sensor and the perception algorithm's ability to perceive abnormal events, determine the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm for abnormal events, as well as the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration; Calculate the layout spacing of trackside monitoring sensors based on the joint perception accuracy of abnormal events under vehicle-track collaboration; divide the entire line into regions according to the changes in line characteristics, and calculate the number of trackside monitoring sensors required in each region based on the layout spacing; For adjacent trackside monitoring sensors at the regional junction, the maximum trackside monitoring sensor layout spacing allowed by the perception accuracy threshold is calculated, the monitoring sensors with closer distances at the regional junction are optimized, and the total number of trackside monitoring sensors required for the entire line is calculated.

2. The rail transit line monitoring sensor layout optimization method for vehicle-track collaboration according to claim 1 is characterized in that: The accuracy of the perception algorithm based on the monitoring sensor is correlated with the distance from the abnormal event to the monitoring sensor. The perception accuracy of the monitoring sensor decreases as the distance increases. This method assumes that within the range of distance a, the perception accuracy of the monitoring sensor is p. Beyond the range, the perception accuracy decreases as the distance increases. Within the distance from a to b, the relationship between the perception accuracy and the distance is: When the distance exceeds b, the monitoring sensor cannot sense anything.

3. The rail transit line monitoring sensor layout optimization method for vehicle-track collaboration according to claim 2 is characterized in that: Therefore, the monitoring sensor perception accuracy distribution function is as follows: Where x is the distance from the abnormal event to the monitoring sensor, and p(x) is the monitoring sensor’s perception accuracy of the abnormal event at distance x.

4. The rail transit line monitoring sensor layout optimization method for vehicle-track collaboration according to claim 3 is characterized in that: The perception accuracy of the trackside monitoring sensor for abnormal events at a distance x from it is p(x), and the perception accuracy of the onboard monitoring sensor for abnormal events at a distance y from the front of the train is p(y). The working state of the monitoring sensor system for vehicle-track collaboration is divided into two cases depending on whether there is a train passing by. The formula for the joint perception accuracy of the vehicle-track collaborative monitoring sensor system for abnormal events is expressed as follows: Among them, s represents the working status of the collaborative system, s=0 means that there is no train passing, and only the trackside monitoring sensors are working in the system; s=1 means that there is a train passing, and both the trackside monitoring sensors and the on-board monitoring sensors are involved in the work; f(p(x), p(y)) is the accuracy of the vehicle-track collaborative perception algorithm.

5. The rail transit line monitoring sensor layout optimization method for vehicle-track collaboration according to claim 1 is characterized in that: Assume that the average perception accuracy within the layout interval D of the trackside monitoring sensors is The calculation formula for the layout spacing D between adjacent trackside monitoring sensors is as follows: In order to ensure the effectiveness of sensing abnormal events in different situations, the trackside monitoring sensors are arranged at equal intervals. Therefore, in an area with a length of S, the number of trackside monitoring sensors N that need to be deployed is calculated as follows: The entire line is divided into areas according to the changes in the line's characteristics, and the number of trackside monitoring sensors required for each area is calculated based on the layout spacing.

6. The rail transit line monitoring sensor layout optimization method for vehicle-track collaboration according to claim 1 is characterized in that: Under full coverage conditions, for the junction area, a perception accuracy threshold is set, and the maximum spacing allowed for adjacent monitoring sensors under the threshold condition is calculated, so as to determine the selection of terminal monitoring sensors in each area; the number of monitoring sensors finally deployed in each area is calculated as follows: Among them, C i is the number of trackside monitoring sensors finally deployed in area i, n is the number of trackside monitoring sensors deployed in area i, is the position of the second to last trackside monitoring sensor at the end of the ith zone, is the position of the trackside monitoring sensor at the beginning of the i+1th zone, D max It is the maximum spacing allowed under the perception accuracy threshold.

7. A rail transit line monitoring sensor layout optimization system for vehicle-track collaboration, characterized in that: include: Establishing a module, for determining the distribution function of the perception accuracy of the monitoring sensor-based perception algorithm for abnormal events, and the joint perception accuracy of the monitoring sensor for abnormal events under vehicle-track collaboration, according to the monitoring performance of the monitoring sensor and the perception ability of the perception algorithm for abnormal events; The division module is used to calculate the layout spacing of the trackside monitoring sensors according to the joint perception accuracy of abnormal events by the monitoring sensors under the coordination of the train and track; divide the entire line into regions according to the characteristic changes of the line, and calculate the number of trackside monitoring sensors required in each region according to the layout spacing; The calculation module is used to calculate the maximum trackside monitoring sensor layout spacing allowed by the perception accuracy threshold for adjacent trackside monitoring sensors at the regional junction, optimize the monitoring sensors that are closer at the regional junction, and calculate the total number of trackside monitoring sensors required for the entire line.

8. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by the processor, the rail transit line monitoring sensor deployment optimization method for vehicle-track collaboration as described in any one of claims 1-6 is implemented.

9. A computer device, characterized in that: It includes a memory and a processor, the processor and the memory communicate with each other, the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the rail transit line monitoring sensor layout optimization method for vehicle-track collaboration as described in any one of claims 1-6.

10. An electronic device, characterized in that: include: A processor, a memory and a computer program; wherein the processor is connected to the memory, the computer program is stored in the memory, and when the electronic device is running, the processor executes the computer program stored in the memory so that the electronic device executes instructions for implementing the method for optimizing the layout of rail transit line monitoring sensors for vehicle-track collaboration as described in any one of claims 1-6.

Images