Rail transit infrastructure building, management and maintenance integrated data management platform

Abstract

The invention discloses a rail transit infrastructure building, management and maintenance integrated data management platform, which belongs to the technical field of rail transit infrastructure management and comprises a facility parameter input module, a data acquisition module, a damage reporting module, a grouping planning module, a damage analysis module and a facility management and maintenance module. The facility parameter input module is used for inputting basic parameters of rail transit infrastructures, and the basic parameters comprise rail facilities and station facilities. The data acquisition module is used for acquiring influence data of different stations, and the influence data comprises rainfall, pedestrian flow and train number. According to the construction, management and maintenance integrated data management platform for the rail transit infrastructure, parameter input, data acquisition, damage analysis, grouping planning and maintenance management are carried out on the rail transit infrastructure of different stations, real-time interaction and cooperation of multi-module data are achieved, the rail transit management efficiency and decision accuracy are improved, and the system is suitable for popularization and application. And the operation reliability of the rail transit infrastructure is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of rail transit facility management, and in particular is a data management platform integrating construction, management and maintenance of rail transit infrastructure. Background Art

[0002] With the rapid development of urban rail transit, the scale of its infrastructure has continued to expand, covering many rail transit stations and a large number of facilities and equipment of different specifications and models. However, the traditional rail transit infrastructure management model has exposed many problems and is difficult to meet the current needs of efficient and safe operation. In the traditional rail transit facility management and maintenance process, routine inspections of rail transit infrastructure are usually carried out based on fixed inspection cycles, or maintenance of rail transit infrastructure is carried out based on reported information when a fault occurs. There is a lack of comprehensive consideration of the specifications of different rail transit infrastructure combined with the geographical environment information of the stations. It is not possible to conduct a comprehensive analysis of the damage to the infrastructure of each rail transit station in combination with the specifications, models, parameters and geographical environment of the infrastructure, making it difficult to detect potential damage hazards in advance, and there are problems of low practicality and functionality; This case proposes an integrated data management platform for the construction, management and maintenance of rail transit infrastructure to solve the above technical problems. Summary of the invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes an integrated data management platform for the construction, management and maintenance of rail transit infrastructure, which solves the above technical problems by improving the detection method and processing method.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: An integrated data management platform for the construction, management and maintenance of rail transit infrastructure, including a facility parameter entry module, a data acquisition module, a damage reporting module, a group planning module, a damage analysis module, and a facility management and maintenance module; The facility parameter input module is used to input basic parameters of rail transit infrastructure, including rail facilities and station facilities; The data collection module is used to collect the impact data of different sites, including rainfall, passenger flow, and vehicle number, and comprehensively calculate the total value of the impact data for the day, week, month, season, and year; The damage reporting module integrates the parameters of the damaged facilities and the impact data of the reported damage location based on the reported damage to the rail transit infrastructure, and transmits them to the damage analysis module; The damage analysis module, for the reported rail transit infrastructure damage, combines the influencing parameters of the damage location to characterize the damage type, including accidental damage and structural damage, does not record the influencing parameters of the damage location of accidental damage, records the influencing parameters of the damage location of structural damage and analyzes the cause of the damage, screens the influencing parameters associated with the structural damage, and transmits them to subsequent modules; The group planning module divides rail transit stations using the same specification of infrastructure and in the same type of climate zone into the same group according to the basic parameters of the rail transit infrastructure and the geographical location and climate zone; The facility management and maintenance module calculates the abnormal influence parameter range of the associated influence parameters based on the structural damage associated influence parameters, performs influence data analysis on the remaining sites in the same group as the site where the structural damage occurs, determines the similarity of the site influence parameters, marks similar potential danger points, and manages and maintains the rail transit infrastructure.

[0005] Furthermore, the facility parameter collection module can Establish a rail transit infrastructure management database, and establish city archives according to the cities where the rail transit is located. Within the city archives, establish sub-archives according to the names of the rail transit stations under the jurisdiction of the city, and enter the basic parameters of the rail transit infrastructure of each station, including rail facility parameters and station facility parameters; The data acquisition module includes a passenger flow sensor, which collects meteorological data of different station areas, obtains passenger flow, train number, rainfall, temperature, and humidity data of different stations according to the train operation schedule of the station, and performs daily, weekly, monthly, seasonal, and annual statistics on the collected rainfall, temperature, humidity, passenger flow, and train number data, calculates the total value, average value, maximum value, minimum value, and peak value per unit time of each data, and records them in the corresponding station sub-file respectively; The grouping planning module obtains the climate zone information of each rail transit station through geographic information system technology, and performs infrastructure matching grouping on the sub-files based on the basic parameter information of facilities in different sub-files in the rail transit infrastructure management database. The specific steps are as follows: For category parameters, the site sub-files that use the same model and material infrastructure are classified into the same category file. By performing error matching on the numerical parameters in the site sub-files in the same category file, the category files are further grouped. The steps are as follows: Extract the numerical parameters of each site sub-file in the same category file, define one of the site sub-files as the target sub-file, and calculate the parameter matching degree between the target sub-file and other sub-files respectively: ; in, They represent the same numerical parameter values ​​of the target site sub-file and other site sub-files in the same category file. represents the error range, Represents the degree of matching; Based on the parameter matching of each parameter, the overall parameter matching is calculated: ; In the above formula, Represents the number of facility parameters, Representative The matching degree of parameters, represents the corresponding weight, and , Represents the overall parameter matching degree, when ≥ When , it means that the matching degree of the numerical parameters in the two site sub-files meets the requirements, and the files that meet the matching degree requirements with the target sub-file are recorded in the target sub-file. < When , it means that the matching degree of the numerical parameters in the two site sub-files does not meet the requirements and will not be recorded; For the remaining sub-files recorded in each target sub-file, based on the climate zone information of the current target sub-file, the remaining sub-files consistent with the climate zone of the target sub-file are retained to obtain the associated sub-files of the current target sub-file.

[0006] Furthermore, the damage reporting module receives the damage information of the rail transit infrastructure reported from manual and automatic channels, the damage information including the damage site information, the type of damaged infrastructure, the time of damage, whether it involves human damage, and the damage location image, retrieves the impact data of the damage location through the rail transit infrastructure management database, combines the damage information and summarizes it into a damage report, which is transmitted to the damage analysis module; The damage analysis module, based on the damage report transmitted by the damage reporting module, characterizes the damage type in the current damage report according to the damage characteristics and related information, and determines whether the damage is accidental damage or structural damage; For qualitative structural damage, record the influencing parameters of the damage location and analyze the cause of the damage, filter the structural damage-related influencing parameters in the current damage report, and transmit them to subsequent modules.

[0007] Further, the damage report transmitted by the damage reporting module is used to characterize the damage type in the current damage report according to the damage characteristics and related information, and to determine whether the damage is accidental damage or structural damage, including the following steps: When the damage report involves man-made damage, the damage type in the current damage report shall be classified as accidental damage; When the damage report does not involve man-made damage, the damage type in the current damage report is qualitatively classified based on the type of damaged infrastructure. The specific steps are as follows: Collect historical damage image data of different rail transit infrastructure, and annotate the image data as structural damage or accidental damage. Adjust the images to the same size, normalize the pixel values ​​to the range of [0, 1]. Divide the processed historical damage image data of different rail transit infrastructure into training set, validation set and test set according to the infrastructure type, with data accounting for 70%, 15% and 15% respectively. Build a convolutional neural network model through the training set, adjust the model hyperparameters through the validation set, and evaluate the final performance of the model through the test set. According to the type of damaged infrastructure in the damage report, the damage location image data will be input into the CNN judgment model under the corresponding infrastructure type, and the judgment result will be output to determine whether the damage type in the current damage report is accidental damage or structural damage.

[0008] Furthermore, for the qualitative structural damage, the damage location influencing parameters of the structural damage are recorded and the damage causes are analyzed, and the structural damage related influencing parameters in the current damage report are screened and transmitted to the subsequent modules, including the following steps: For structural damage, the damage report is used to obtain the impact data of the damage site during the damage period, including the passenger flow, vehicle number, rainfall, temperature, and humidity data at the damage site on the day the damage occurred, as well as the passenger flow, vehicle number, rainfall, temperature, and humidity data at the current site on historical normal dates. The number of samples of historical damage status records of the same infrastructure at the current site is also obtained, where the passenger flow, vehicle number, rainfall, temperature, and humidity data are , the number of historical damage status record samples is ; The Z score was used to standardize the data of passenger flow, vehicle number, rainfall, temperature, and humidity. The Pearson correlation coefficient and Spearman rank correlation coefficient were used to screen the injury-related parameters, and multivariate feature selection was performed: ; In the above formula, Representative The damage status of the samples, is the intercept term, Representative The regression coefficients of the parameters, is the regularization parameter, keeping Parameters ≠ 0 are used as structural damage correlation influencing parameters. Representative The sample parameter values.

[0009] Furthermore, the facility management and maintenance module calculates the abnormal influence parameter range of the associated influence parameter according to the structural damage associated influence parameter, performs influence data analysis on the remaining sites in the same group as the site where the structural damage occurs, determines the similarity of the site influence parameters, marks similar potential danger points, and manages and maintains the rail transit infrastructure. The specific steps are as follows: For the obtained structural damage correlation influencing parameters, the correlation influencing parameter range of the current structural damage is obtained through single variable anomaly detection and multivariate anomaly detection; According to the current damage report, the associated sub-file information in the current damage site sub-file in the rail transit infrastructure management database is determined, the structural damage associated influencing parameters in the associated sub-file are extracted, the similarity of the associated influencing parameters in the associated sub-file is determined, and similar potential danger points are marked in the rail transit infrastructure management database to manage and maintain the rail transit infrastructure.

[0010] Furthermore, for the obtained structural damage associated influencing parameters, the associated influencing parameter range of the current structural damage is obtained through single variable anomaly detection and multivariate anomaly detection, and the specific steps are: When the structural damage correlation influencing parameter is a single variable, based on The principle determines the range of parameters affecting the structural damage association; When the structural damage association influencing parameters are multivariable, the range of the structural damage association influencing parameters is determined by the Mahalanobis distance. The specific steps are as follows: ; in, Represents a vector of multiple structural damage-related impact parameters, Represents the mean vector of multiple parameters, that is, the average value of each parameter under normal conditions, Represents the inverse matrix of the covariance matrix, when > When , it is judged as multi-parameter abnormality, among which represents the critical value of the chi-square distribution, is the number of parameters and 0.95 is the confidence level.

[0011] Furthermore, according to the current damage report, the associated sub-file information in the current damage site sub-file in the rail transit infrastructure management database is determined, the structural damage associated impact parameters in the associated sub-file are extracted, the similarity of the associated impact parameters in the associated sub-file is determined, and similar potential danger points are marked in the rail transit infrastructure management database, and the rail transit infrastructure is managed and maintained. The specific steps are: According to the type of associated impact parameter of the current site sub-file structural damage, the corresponding associated impact parameter data record is extracted from the associated sub-file, and the potential danger points of the site in the associated sub-file are determined: When the structural damage correlation influencing parameter is a single variable, the structural damage correlation influencing parameter data in the associated sub-files are counted. If the structural damage correlation influencing parameter data in the associated sub-files on any day is not present If it is within the range, it means that there is a potential infrastructure anomaly in the current associated sub-file, and the relevant infrastructure in the associated sub-file is marked in red, and the status is marked as pending maintenance in the rail transit infrastructure management database; When the structural damage correlation influencing parameters are multivariable, the corresponding correlation influencing parameter data records are extracted from the correlation sub-file and calculated. , when any date exists in the historical date > , it means that there is a potential infrastructure anomaly in the current associated sub-file, and the relevant infrastructure in the associated sub-file is marked in red, and the status is marked as pending maintenance in the rail transit infrastructure management database.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. In the present invention, based on the geographical environment information of different rail transit stations, combined with the specifications, models and parameters of rail transit infrastructure, damage maintenance and divergence analysis of rail transit infrastructure are carried out to achieve potential damage management and maintenance of rail transit infrastructure, discover potential damage in advance, reduce the operational safety risks of rail transit infrastructure, and enhance practicality; 2. In the present invention, by determining the damage type of rail transit infrastructure, different management and maintenance measures are taken for different types of damage, the structural damage of the infrastructure is discovered in time and the remaining rail transit stations in similar environments are maintained, potential danger points are warned in advance, the risk of sudden accidents is reduced, and the functionality of the system is enhanced; 3. In the present invention, the infrastructure information of rail transit stations is combined with climate zone data, and the facility parameter matching algorithm is used to intelligently divide homogeneous station groups to achieve "centralized control of similar risk sites", improve the pertinence and efficiency of maintenance resource allocation, realize real-time interaction and coordination of multi-module data, and improve the management efficiency of rail transit infrastructure; 4. In the present invention, by predicting the potential damage location of rail transit infrastructure and conducting targeted inspection and maintenance, the service life of the infrastructure is extended through damage management and maintenance, thereby reducing the economic damage caused by damage to the rail transit infrastructure, realizing integrated management and maintenance of the rail transit infrastructure, and reducing the difficulty of rail transit maintenance management; The integrated data management platform for the construction, management and maintenance of the entire rail transit infrastructure realizes real-time interaction and coordination of multi-module data through parameter entry, data collection, damage analysis, group planning and maintenance management of rail transit infrastructure at different stations, thereby improving rail transit management efficiency and decision-making accuracy, and improving the operational reliability of rail transit infrastructure. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 This is a block diagram of an integrated data management platform for construction, management and maintenance of rail transit infrastructure of the present invention. DETAILED DESCRIPTION

[0014] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0015] Example 1: Figure 1 As shown, a data management platform for the integrated construction, management and maintenance of rail transit infrastructure includes.

[0016] The present invention provides an integrated data management platform for construction, management and maintenance of rail transit infrastructure, which, when in use, includes a facility parameter input module, a data acquisition module, a damage reporting module, a group planning module, a damage analysis module, and a facility management and maintenance module; Facility parameter collection module, through Establish a rail transit infrastructure management database, and establish city archives according to the cities where the rail transit is located. Within the city archives, establish sub-files according to the names of the rail transit stations under the jurisdiction of the city, and enter the basic parameters of the rail transit infrastructure of each station, including rail facility parameters and station facility parameters; It should be noted that the track facility parameters include track model, track material, contact grid model, track gauge, building area, etc.; the station facility parameters include the model, quantity, running speed of elevators and escalators, the type and quantity of lamps in the lighting system, the cooling capacity and power of the air-conditioning system, the model of gates, etc. The track facility parameters and station facility parameters are collected according to the construction design drawings of the rail transit station and recorded in the relevant sub-files.

[0017] The data collection module includes a passenger flow sensor, which collects meteorological data of different station areas, obtains passenger flow, train number, rainfall, temperature, and humidity data of different stations according to the train operation schedule of the station, and performs daily, weekly, monthly, seasonal, and annual statistics on the collected rainfall, temperature, humidity, passenger flow, and train number data, calculates the total value, average value, maximum value, minimum value, and peak value per unit time of each data, and records them in the corresponding station sub-file respectively; It should be noted that the unit time is 1 hour or half an hour, and the peak value within the unit time is the maximum value of the data statistics in all 1-hour or half-hour time periods in that day, so as to reflect the extreme situations of different collected data within the unit time scale, so as to analyze the maximum load or intensity of the passenger flow, vehicle number or rainfall in the station area within a specific short time.

[0018] The group planning module uses geographic information system technology to obtain the climate zone information of each rail transit station. Based on the basic parameter information of facilities in different sub-files in the rail transit infrastructure management database, the sub-files are grouped for infrastructure matching. The specific steps are as follows: For category parameters, the site sub-files that use the same model and material infrastructure are classified into the same category file. By performing error matching on the numerical parameters in the site sub-files in the same category file, the category files are further grouped. The steps are as follows: Extract the numerical parameters of each site sub-file in the same category file, define one of the site sub-files as the target sub-file, and calculate the parameter matching degree between the target sub-file and other sub-files respectively: ; in, They represent the same numerical parameter values ​​of the target site sub-file and other site sub-files in the same category file. represents the error range, Represents the degree of matching; It should be noted that by defining each site sub-file in the same category file as a target sub-file, the relationship between each site sub-file and other site sub-files in the same category file can be obtained, which is convenient for subsequent facility management and maintenance. The numerical parameters include track gauge, building area, platform length, platform height, axle weight, voltage and current of power supply equipment, etc. Different numerical parameters have different error ranges. For each numerical parameter, calculate its fluctuation range in historical data. That is, the maximum and minimum values ​​of the parameter under normal use, get the fluctuation range of the parameter, and take 20% of the fluctuation range as the error range.

[0019] Based on the parameter matching of each parameter, the overall parameter matching is calculated: ; In the above formula, Represents the number of facility parameters, Representative The matching degree of parameters, represents the corresponding weight, and , Represents the overall parameter matching degree, when ≥ When , it means that the matching degree of the numerical parameters in the two site sub-files meets the requirements, and the files that meet the matching degree requirements with the target sub-file are recorded in the target sub-file. < When , it means that the matching degree of the numerical parameters in the two site sub-files does not meet the requirements and will not be recorded; It should be noted that The value of is set to 0.9, which means that the two are 90% similar in numerical parameters. To ensure that all parameters have the same weight, adjust The value can further refine or fuzzify the filter conditions.

[0020] For the remaining sub-files recorded in each target sub-file, based on the climate zone information of the current target sub-file, the remaining sub-files consistent with the climate zone of the target sub-file are retained to obtain the associated sub-files of the current target sub-file.

[0021] It should be noted that the climates of sites in the same climate zone will be similar, that is, the environmental influencing factors are the same. Since my country has a vast territory covering multiple climate zones, sites in the same climate zone will be classified to provide data support for subsequent facility management and maintenance. The climate zones include cold temperate zone, mid-temperate zone, warm temperate zone, northern subtropical zone, mid-subtropical zone, southern subtropical zone, marginal tropical zone, mid-tropical zone, equatorial tropical zone, etc.

[0022] Embodiment 2: A damage reporting module receives damage information of rail transit infrastructure reported from manual and automatic channels, the damage information including damage site information, damaged infrastructure type, damage time, whether human damage is involved, and damage location image, retrieves impact data of the damage location from the rail transit infrastructure management database, combines the damage information and summarizes it into a damage report, which is then transmitted to the damage analysis module; It should be noted that manual channels include daily inspection reports from inspectors, feedback from maintenance personnel, passenger feedback, etc., and automatic channels include abnormal sensor monitoring data, etc. By receiving damage report information from manual channels and automatic channels, the staff will accurately enter the information into the system and record whether the damage involves human damage. The damage report includes the location of the damage, an image of the damage location, the sites involved, the time of occurrence, the type of damaged infrastructure, whether it involves human damage, and the impact data of the damage location and the period of damage.

[0023] The damage analysis module, based on the damage report transmitted by the damage reporting module, characterizes the damage type in the current damage report according to the damage characteristics and related information, and determines whether the damage is accidental damage or structural damage, including the following steps: When the damage report involves man-made damage, the damage type in the current damage report shall be classified as accidental damage; When the damage report does not involve man-made damage, the damage type in the current damage report is qualitatively classified based on the type of damaged infrastructure. The specific steps are as follows: Collect historical damage image data of different rail transit infrastructure, and annotate the image data as structural damage or accidental damage. Adjust the images to the same size, normalize the pixel values ​​to the range of [0, 1]. Divide the processed historical damage image data of different rail transit infrastructure into training set, validation set and test set according to the infrastructure type, with data accounting for 70%, 15% and 15% respectively. Build a convolutional neural network model through the training set, adjust the model hyperparameters through the validation set, and evaluate the final performance of the model through the test set. According to the type of damaged infrastructure in the damage report, the damage location image data will be input into the CNN judgment model under the corresponding infrastructure type, and the judgment result will be output to determine whether the damage type in the current damage report is accidental damage or structural damage.

[0024] It should be noted that in the process of building the convolutional neural network model, the dimensions of the image data input layer are the height, width and number of channels of the image, and the number of neurons in the output layer is set to 2, corresponding to the two categories of accidental damage and structural damage. The activation function outputs the probability of each category, and the difference between the model prediction result and the true label is measured by using the cross entropy loss function. The optimizer updates the parameters of the model. When a new damage report is received, the data in the damage report is input into the model of the corresponding infrastructure type and the qualitative results of the damage type are output. For qualitative structural damage, record the influencing parameters of the damage location of the structural damage and analyze the damage causes, filter the structural damage related influencing parameters in the current damage report, and transmit them to the subsequent modules, including the following steps: For structural damage, the damage report is used to obtain the impact data of the damage site during the damage period, including the passenger flow, vehicle number, rainfall, temperature, and humidity data at the damage site on the day the damage occurred, as well as the passenger flow, vehicle number, rainfall, temperature, and humidity data at the current site on historical normal dates. The number of samples of historical damage status records of the same infrastructure at the current site is also obtained, where the passenger flow, vehicle number, rainfall, temperature, and humidity data are , the number of historical damage status record samples is ; It should be noted that It is a binary variable, indicating whether the current site has structural damage at a certain moment. If there is structural damage, it is 1, and if there is no structural damage, it is 0.

[0025] The Z score was used to standardize the data of passenger flow, vehicle number, rainfall, temperature, and humidity. The Pearson correlation coefficient and Spearman rank correlation coefficient were used to screen the injury-related parameters, and multivariate feature selection was performed: ; In the above formula, Representative The damage status of the samples, is the intercept term, Representative The regression coefficients of the parameters, is the regularization parameter, keeping Parameters ≠ 0 are used as structural damage correlation influencing parameters. Representative The sample parameter values.

[0026] It should be noted that Reflection parameters Damage Status The direction and intensity of the impact, >0 o'clock, The larger the size, the higher the probability of damage. <0: The larger the damage probability, the lower the =0, it means Those that have no significant effect on damage need to be eliminated. For linear relationship data, correlation analysis is performed based on the Pearson correlation coefficient. The algorithm formula is: ; in, represents the correlation coefficient, Representative parameters The mean of The value of is 1 to 5, representing the flow of people, number of vehicles, rainfall, temperature, and humidity data respectively. ; For nonlinear relationship data, correlation analysis is performed using the Spearman rank correlation coefficient: ; in, represents the rank correlation coefficient, Representative parameters and The rank difference of Represents the number of samples, retained Parameters > 0.3 are used for multivariate feature selection.

[0027] Embodiment 3: A facility management and maintenance module calculates the abnormal influence parameter range of the associated influence parameter according to the structural damage associated influence parameter, performs influence data analysis on the remaining sites in the same group as the site where the structural damage occurs, determines the similarity of the site influence parameters, marks similar potential danger points, and manages and maintains the rail transit infrastructure. The specific steps are as follows: For the obtained structural damage associated influencing parameters, the associated influencing parameter range of the current structural damage is obtained through single variable anomaly detection and multivariate anomaly detection. The specific steps are as follows: When the structural damage correlation influencing parameter is a single variable, based on The principle determines the range of parameters affecting the structural damage association; When the structural damage association influencing parameters are multivariable, the range of the structural damage association influencing parameters is determined by the Mahalanobis distance. The specific steps are as follows: ; in, Represents a vector of multiple structural damage-related impact parameters, Represents the mean vector of multiple parameters, that is, the average value of each parameter under normal conditions, Represents the inverse matrix of the covariance matrix, when > When , it is judged as multi-parameter abnormality, among which represents the critical value of the chi-square distribution, is the number of parameters and 0.95 is the confidence level.

[0028] It should be noted that Represents a vector of multiple structural damage-related impact parameters, The maximum case is , The normal range of the structural damage correlation influencing parameters is .

[0029] According to the current damage report, determine the associated sub-file information in the current damage site sub-file in the rail transit infrastructure management database, extract the structural damage associated influencing parameters in the associated sub-file, determine the similarity of the associated influencing parameters in the associated sub-file, and mark similar potential danger points in the rail transit infrastructure management database to manage and maintain the rail transit infrastructure. The specific steps are as follows: According to the type of associated impact parameter of the current site sub-file structural damage, the corresponding associated impact parameter data record is extracted from the associated sub-file, and the potential danger points of the site in the associated sub-file are determined: When the structural damage correlation influencing parameter is a single variable, the structural damage correlation influencing parameter data in the associated sub-files are counted. If the structural damage correlation influencing parameter data in the associated sub-files on any day is not present If it is within the range, it means that there is a potential infrastructure anomaly in the current associated sub-file, and the relevant infrastructure in the associated sub-file is marked in red, and the status is marked as pending maintenance in the rail transit infrastructure management database; When the structural damage correlation influencing parameters are multivariable, the corresponding correlation influencing parameter data records are extracted from the correlation sub-file and calculated. , when any date exists in the historical date > , it means that there is a potential infrastructure anomaly in the current associated sub-file, and the relevant infrastructure in the associated sub-file is marked in red, and the status is marked as pending maintenance in the rail transit infrastructure management database.

[0030] It should be noted that by classifying stations in similar environments and based on the structural damage-related influencing parameters of a station in the category, the potential abnormal conditions of the remaining stations can be determined to achieve preventive maintenance of rail transit infrastructure.

[0031] In the embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules is only a logical function division, and there may be other division methods in actual implementation; the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the method of this embodiment.

[0032] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An integrated data management platform for the construction, management and maintenance of rail transit infrastructure, characterized by: It includes facility parameter input module, data collection module, damage reporting module, group planning module, damage analysis module, and facility management and maintenance module; The damage reporting module integrates the parameters of the damaged facilities and the impact data of the reported damage location based on the reported damage to the rail transit infrastructure, and transmits them to the damage analysis module; The damage analysis module, for the reported rail transit infrastructure damage, combines the influencing parameters of the damage location to characterize the damage type, including accidental damage and structural damage, does not record the influencing parameters of the damage location of accidental damage, records the influencing parameters of the damage location of structural damage and analyzes the cause of the damage, screens the influencing parameters associated with the structural damage, and transmits them to subsequent modules; The group planning module divides rail transit stations using the same specification of infrastructure and in the same type of climate zone into the same group according to the basic parameters of the rail transit infrastructure and the geographical location and climate zone; The facility management and maintenance module calculates the abnormal influence parameter range of the associated influence parameters based on the structural damage associated influence parameters, performs influence data analysis on the remaining sites in the same group as the site where the structural damage occurs, determines the similarity of the site influence parameters, marks similar potential danger points, and manages and maintains the rail transit infrastructure.

2. According to claim 1, a data management platform for integrated construction, management and maintenance of rail transit infrastructure is characterized by: The facility parameter collection module Establish a rail transit infrastructure management database, and establish city archives according to the cities where the rail transit is located. Within the city archives, establish sub-files according to the names of the rail transit stations under the jurisdiction of the city, and enter the basic parameters of the rail transit infrastructure of each station, including rail facility parameters and station facility parameters; The data acquisition module includes a passenger flow sensor, which collects meteorological data of different station areas, obtains passenger flow, train number, rainfall, temperature, and humidity data of different stations according to the train operation schedule of the station, and performs daily, weekly, monthly, seasonal, and annual statistics on the collected rainfall, temperature, humidity, passenger flow, and train number data, calculates the total value, average value, maximum value, minimum value, and peak value per unit time of each data, and records them in the corresponding station sub-file respectively; The grouping planning module obtains the climate zone information of each rail transit station through the geographic information system technology, and performs infrastructure matching grouping on the sub-files based on the basic parameter information of the facilities in different sub-files in the rail transit infrastructure management database. The specific steps are as follows: For category parameters, the site sub-files that use the same model and material infrastructure are classified into the same category file. By performing error matching on the numerical parameters in the site sub-files in the same category file, the category files are further grouped. The steps are as follows: Extract the numerical parameters of each site sub-file in the same category file, define one of the site sub-files as the target sub-file, and calculate the parameter matching degree between the target sub-file and other sub-files respectively: ； in, They represent the same numerical parameter values ​​of the target site sub-file and other site sub-files in the same category file. represents the error range, Represents the degree of matching; Based on the parameter matching of each parameter, the overall parameter matching is calculated: ； In the above formula, Represents the number of facility parameters, Representative The matching degree of parameters, represents the corresponding weight, and , Represents the overall parameter matching degree, when ≥ When , it means that the matching degree of the numerical parameters in the two site sub-files meets the requirements, and the files that meet the matching degree requirements with the target sub-file are recorded in the target sub-file. < When , it means that the matching degree of the numerical parameters in the two site sub-files does not meet the requirements and will not be recorded; For the remaining sub-files recorded in each target sub-file, based on the climate zone information of the current target sub-file, the remaining sub-files consistent with the climate zone of the target sub-file are retained to obtain the associated sub-files of the current target sub-file.

3. According to claim 2, a data management platform for integrated construction, management and maintenance of rail transit infrastructure is characterized by: The damage reporting module receives the damage information of the rail transit infrastructure reported from manual and automatic channels, the damage information includes the damage site information, the type of damaged infrastructure, the damage time, whether it involves human damage, and the damage location image, retrieves the impact data of the damage location through the rail transit infrastructure management database, combines the damage information and summarizes it into a damage report, and transmits it to the damage analysis module; The damage analysis module, based on the damage report transmitted by the damage reporting module, characterizes the damage type in the current damage report according to the damage characteristics and related information, and determines whether the damage is accidental damage or structural damage; For qualitative structural damage, record the influencing parameters of the damage location and analyze the cause of the damage, filter the structural damage-related influencing parameters in the current damage report, and transmit them to subsequent modules.

4. According to claim 3, a data management platform for integrated construction, management and maintenance of rail transit infrastructure is characterized by: According to the damage report transmitted by the damage reporting module, the damage type in the current damage report is qualitatively determined according to the damage characteristics and related information to determine whether the damage is accidental damage or structural damage, including the following steps: When the damage report involves man-made damage, the damage type in the current damage report shall be classified as accidental damage; When the damage report does not involve man-made damage, the damage type in the current damage report is qualitatively classified based on the type of damaged infrastructure. The specific steps are as follows: Collect historical damage image data of different rail transit infrastructure, and annotate the image data as structural damage or accidental damage. Adjust the images to the same size, normalize the pixel values ​​to the range of [0, 1]. Divide the processed historical damage image data of different rail transit infrastructure into training set, validation set and test set according to the infrastructure type, with data accounting for 70%, 15% and 15% respectively. Build a convolutional neural network model through the training set, adjust the model hyperparameters through the validation set, and evaluate the final performance of the model through the test set. According to the type of damaged infrastructure in the damage report, the damage location image data will be input into the CNN judgment model under the corresponding infrastructure type, and the judgment result will be output to determine whether the damage type in the current damage report is accidental damage or structural damage.

5. According to claim 3, a data management platform for integrated construction, management and maintenance of rail transit infrastructure is characterized by: The qualitative structural damage, recording the influencing parameters of the damage location of the structural damage and analyzing the damage causes, screening the structural damage related influencing parameters in the current damage report, and transmitting them to the subsequent modules, includes the following steps: For structural damage, the damage report is used to obtain the impact data of the damage site during the damage period, including the passenger flow, vehicle number, rainfall, temperature, and humidity data at the damage site on the day the damage occurred, as well as the passenger flow, vehicle number, rainfall, temperature, and humidity data at the current site on historical normal dates. The number of samples of historical damage status records of the same infrastructure at the current site is also obtained, where the passenger flow, vehicle number, rainfall, temperature, and humidity data are , the number of historical damage status record samples is ; The Z score was used to standardize the data of passenger flow, vehicle number, rainfall, temperature, and humidity. The Pearson correlation coefficient and Spearman rank correlation coefficient were used to screen the injury-related parameters, and multivariate feature selection was performed: ； In the above formula, Representative The damage status of the samples, is the intercept term, Representative The regression coefficients of the parameters, is the regularization parameter, keeping Parameters ≠ 0 are used as structural damage correlation influencing parameters. Representative The sample parameter values.

6. The integrated data management platform for construction, management and maintenance of rail transit infrastructure according to claim 5, characterized in that: The facility management and maintenance module calculates the abnormal influence parameter range of the associated influence parameter according to the structural damage associated influence parameter, performs influence data analysis on the remaining sites in the same group as the site where the structural damage occurs, determines the similarity of the site influence parameters, marks similar potential danger points, and manages and maintains the rail transit infrastructure. The specific steps are as follows: For the obtained structural damage correlation influencing parameters, the correlation influencing parameter range of the current structural damage is obtained through single variable anomaly detection and multivariate anomaly detection; According to the current damage report, the associated sub-file information in the current damage site sub-file in the rail transit infrastructure management database is determined, the structural damage associated influencing parameters in the associated sub-file are extracted, the similarity of the associated influencing parameters in the associated sub-file is determined, and similar potential danger points are marked in the rail transit infrastructure management database to manage and maintain the rail transit infrastructure.

7. The integrated data management platform for construction, management and maintenance of rail transit infrastructure according to claim 6 is characterized by: The specific steps of obtaining the associated influencing parameters of the structural damage by using single variable anomaly detection and multivariate anomaly detection to obtain the associated influencing parameter range of the current structural damage are as follows: When the structural damage correlation influencing parameter is a single variable, based on The principle determines the range of parameters affecting the structural damage association; When the structural damage association influencing parameters are multivariable, the range of the structural damage association influencing parameters is determined by the Mahalanobis distance. The specific steps are as follows: ； in, Represents a vector of multiple structural damage-related impact parameters, Represents the mean vector of multiple parameters, that is, the average value of each parameter under normal conditions, Represents the inverse matrix of the covariance matrix, when > When , it is judged as multi-parameter abnormality, among which represents the critical value of the chi-square distribution, is the number of parameters and 0.95 is the confidence level.

8. The integrated data management platform for construction, management and maintenance of rail transit infrastructure according to claim 7 is characterized by: The method comprises the following steps: determining the associated sub-file information in the current damage report site sub-file in the rail transit infrastructure management database according to the current damage report, extracting the structural damage associated influencing parameters in the associated sub-file, determining the similarity of the associated influencing parameters in the associated sub-file, marking similar potential danger points in the rail transit infrastructure management database, and managing and maintaining the rail transit infrastructure. According to the type of associated impact parameter of the current site sub-file structural damage, the corresponding associated impact parameter data record is extracted from the associated sub-file, and the potential danger points of the site in the associated sub-file are determined: When the structural damage correlation influencing parameter is a single variable, the structural damage correlation influencing parameter data in the associated sub-files are counted. If the structural damage correlation influencing parameter data in the associated sub-files on any day is not present If it is within the range, it means that there is a potential infrastructure anomaly in the current associated sub-file, and the relevant infrastructure in the associated sub-file is marked in red, and the status is marked as pending maintenance in the rail transit infrastructure management database; When the structural damage correlation influencing parameters are multivariable, the corresponding correlation influencing parameter data records are extracted from the correlation sub-file and calculated. , when any date exists in the historical date > , it means that there is a potential infrastructure anomaly in the current associated sub-file, and the relevant infrastructure in the associated sub-file is marked in red, and the status is marked as pending maintenance in the rail transit infrastructure management database.

Images