Subway line safety management and control system based on intelligent maintenance mode

Abstract

The invention discloses a metro line safety management and control system based on an intelligent maintenance mode, and belongs to the field of metro safety management and control, and the system comprises a parameter collection module which starts a timer when metro line equipment is started, and obtains operation control parameters and operation state monitoring data when a preset duration is satisfied; the operation prediction module is used for obtaining operation state prediction data by taking the operation control parameters as constraints; the disturbance analysis module is used for performing deviation analysis on the running state prediction data and the monitoring data to obtain a disturbance coefficient; the early warning processing module is used for generating an operation and maintenance identifier when the disturbance coefficient is greater than or equal to a threshold value; and the cycle control module is used for resetting the timer to zero when the disturbance coefficient is smaller than the threshold value. According to the invention, the technical problem that the subway line equipment maintenance depends on a regular maintenance mode and intelligent maintenance cannot be carried out according to the actual operation state of the equipment in the prior art is solved, and the technical effects of timely discovering the abnormal operation of the equipment through real-time monitoring and predictive analysis and realizing intelligent on-demand maintenance are achieved.

Description

Technical Field

[0001] The present invention relates to the field of subway safety management and control, and in particular to a subway line safety management and control system based on a smart maintenance mode. Background Art

[0002] The safe and stable operation of subway line equipment is crucial to the urban rail transit system. At present, the maintenance of subway line equipment mainly adopts the regular maintenance mode, that is, routine inspection and maintenance of equipment at preset time intervals. However, the regular maintenance mode is to perform maintenance according to a fixed cycle, and it is impossible to perform targeted maintenance according to the actual operating status of the equipment, which may cause a waste of maintenance resources. Some equipment is also inspected when it does not actually need maintenance, and some equipment cannot be handled in time when it fails outside the maintenance cycle. At the same time, the traditional regular maintenance mode lacks intelligent features and cannot realize real-time monitoring and early warning of equipment status. Abnormal status during equipment operation can often only be discovered after the failure occurs, which is not conducive to the prevention and timely handling of failures, resulting in potential safety hazards in subway rail transit. Summary of the invention

[0003] This application provides a subway line safety management and control system based on a smart maintenance mode, aiming to solve the technical problem in the prior art that subway line equipment maintenance relies on a periodic maintenance mode and cannot perform intelligent maintenance according to the actual operating status of the equipment.

[0004] The present application discloses a subway line safety management and control system based on a smart maintenance mode, comprising: a parameter acquisition module, which is used to start a timer when a subway line device is started, and when a preset time is met, interact with the subway line device to obtain subway line device operation control parameters and subway line device operation status monitoring data; an operation prediction module, which is used to collect fault-free sample operation status record data of subway line device models with the subway line device operation control parameters as constraints, perform frequency aggregation, and obtain subway line device operation status prediction data; a disturbance analysis module, which is used to perform deviation analysis on subway line device operation status prediction data and subway line device operation status monitoring data to obtain an operation status disturbance coefficient; an early warning processing module, which is used to generate an operation and maintenance identification for the subway line device when the operation status disturbance coefficient is greater than or equal to a disturbance coefficient threshold, and send it to an operation and maintenance management and control terminal; a loop control module, which is used to reset the timer to zero and start timing when the operation status disturbance coefficient is less than the disturbance coefficient threshold, and to execute the process in a loop.

[0005] One or more technical solutions provided in this application have at least the following technical effects or advantages: When the subway line equipment is started, the timer is started. When the preset time is met, the subway line equipment is interacted with to obtain the subway line equipment operation control parameters and subway line equipment operation status monitoring data, so as to realize the timed collection of equipment operation data and provide a data basis for subsequent analysis. With the subway line equipment operation control parameters as constraints, the fault-free sample operation status record data of the subway line equipment model is collected for frequency aggregation to obtain the subway line equipment operation status prediction data and establish a reference benchmark for the normal operation status of the equipment. The subway line equipment operation status prediction data and the subway line equipment operation status monitoring data are analyzed for deviations to obtain the operation status disturbance coefficient. Through comparative analysis, the actual operation status of the equipment is quantified. The degree of deviation from the expected state; when the operating state disturbance coefficient is greater than or equal to the disturbance coefficient threshold, an operation and maintenance mark is generated for the subway line equipment and sent to the operation and maintenance control end. When the equipment state is abnormal, an early warning signal is issued in time to facilitate timely processing by maintenance personnel; when the operating state disturbance coefficient is less than the disturbance coefficient threshold, the timer is reset to zero and starts timing, and the process is executed in a loop to achieve continuous monitoring of the equipment state and ensure stable operation of the system. The technical solution solves the technical problem that the maintenance of subway line equipment in the prior art relies on the regular maintenance mode and cannot perform intelligent maintenance according to the actual operating status of the equipment. It achieves the technical effect of timely discovering equipment operation abnormalities and realizing intelligent on-demand maintenance through real-time monitoring and predictive analysis.

[0006] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 A structural schematic diagram of a subway line safety management and control system based on a smart maintenance mode is provided for an embodiment of the present application; Figure 2 A flow chart of obtaining subway line equipment operation status prediction data in a subway line safety management and control system based on a smart maintenance mode is provided for an embodiment of the present application.

[0008] Explanation of reference numerals: parameter acquisition module 11 , operation prediction module 12 , disturbance analysis module 13 , early warning processing module 14 , circulation control module 15 . DETAILED DESCRIPTION

[0009] The overall idea of ​​the technical solution provided by this application is as follows: The embodiment of the present application provides a subway line safety management and control system based on a smart maintenance mode, which realizes the transformation of subway line equipment from traditional periodic maintenance to intelligent on-demand maintenance by establishing an intelligent equipment status monitoring and analysis system. Specifically, first, the real-time operation data of the equipment is obtained by regularly collecting equipment operation control parameters and operation status monitoring data; then, a prediction model is established based on fault-free sample data to generate prediction data of the equipment operation status; then, by comparing the deviation between the prediction data and the actual monitoring data, the operation status disturbance coefficient is calculated; when the disturbance coefficient exceeds the threshold, an operation and maintenance mark is generated in time and an early warning message is sent; when the disturbance coefficient is within the threshold range, the timing is reset and the monitoring is continued in a cycle. In this way, not only the problem of insufficient intelligence of the traditional periodic maintenance mode is solved, but also real-time monitoring of equipment status and abnormal early warning are realized, providing support for the intelligent operation and maintenance management of subway line equipment.

[0010] After introducing the basic principles of the present application, the non-limiting implementation methods of the present application will be specifically introduced below in conjunction with the drawings in the specification.

[0011] like Figure 1 As shown, the embodiment of the present application provides a subway line safety management and control system based on a smart maintenance mode, the system comprising: The parameter acquisition module 11 is used to start the timer when the subway line equipment is started, and when the preset time is met, interact with the subway line equipment to obtain the subway line equipment operation control parameters and subway line equipment operation status monitoring data.

[0012] Specifically, the parameter acquisition module 11 is used to realize the automatic collection of subway line equipment operation data. The parameter acquisition module 11 starts working by detecting the start signal of the subway line equipment. When the subway line equipment is detected to be started, the parameter acquisition module 11 immediately starts the internal timer to start timing. During the operation of the timer, when the accumulated time reaches the preset duration, the parameter acquisition module 11 immediately establishes data interaction with the subway line equipment. Through data interaction, the parameter acquisition module 11 obtains two types of important data: subway line equipment operation control parameters and subway line equipment operation status monitoring data. Among them, the subway line equipment operation control parameters reflect the control status information of the equipment, and the subway line equipment operation status monitoring data contains the real-time operation status of the equipment.

[0013] The parameter acquisition module 11 adopts a collection mechanism triggered by a preset time length to ensure the time interval and regularity of data collection. Through the timed collection method, the necessary data basis is provided for the subsequent operation prediction module 12.

[0014] The operation prediction module 12 is used to collect the fault-free sample operation status record data of the subway line equipment model and perform frequency aggregation based on the subway line equipment operation control parameters to obtain subway line equipment operation status prediction data.

[0015] Specifically, the operation prediction module 12 is used to make intelligent predictions on the operation status of subway line equipment. First, the operation prediction module 12 uses the operation control parameters of the subway line equipment obtained by the parameter acquisition module 11 as constraints, and extracts the trouble-free sample operation status record data of the same model of subway line equipment from the database. Then, the operation prediction module 12 performs frequency aggregation operations on the extracted trouble-free sample operation status record data. The frequency aggregation process is based on statistical principles, and by analyzing the distribution characteristics of a large amount of trouble-free operation data, a mathematical model of the normal operation status of the equipment is established. Through frequency aggregation operations, the operation prediction module 12 finally obtains the subway line equipment operation status prediction data.

[0016] The operation prediction module 12 ensures that the selected fault-free sample data have similar operating conditions by introducing the subway line equipment operation control parameters as constraints. This constraint-based sample selection method improves the accuracy and reliability of the operation status prediction. At the same time, the frequency aggregation method is used to process the fault-free sample data, making the prediction results more statistically significant and better reflecting the normal operation law of the equipment.

[0017] The disturbance analysis module 13 is used to perform deviation analysis on the subway line equipment operation status prediction data and the subway line equipment operation status monitoring data to obtain an operation status disturbance coefficient.

[0018] Specifically, the disturbance analysis module 13 is used to conduct a comprehensive deviation analysis on the operation status of the subway line equipment. The disturbance analysis module 13 uses the subway line equipment operation status prediction data output by the operation prediction module 12 as a benchmark reference, and conducts a systematic comparative analysis with the subway line equipment operation status monitoring data acquired in real time by the parameter acquisition module 11. Specifically, the disturbance analysis module 13 performs in-depth deviation calculations on the two types of data by setting multi-dimensional evaluation indicators. In the data processing process, not only the instantaneous deviation of the data is paid attention to, but also the characteristics such as the duration of the deviation and the change trend of the deviation amplitude are comprehensively analyzed. Through a multi-dimensional analysis method, the disturbance analysis module 13 obtains a comprehensive indicator, namely the operation status disturbance coefficient, which can comprehensively reflect the degree of deviation of the current operation status of the subway line equipment relative to the expected state.

[0019] Furthermore, when calculating the operating state disturbance coefficient, the disturbance analysis module 13 adopts a weight distribution mechanism to perform differentiated processing on different types of deviations. This processing method ensures that the disturbance coefficient can more accurately reflect the actual abnormal degree of the equipment operating state. At the same time, the disturbance analysis module 13 can establish a dynamic data analysis mechanism to continuously track the changing trend of the equipment operating state and capture potential abnormal states in a timely manner.

[0020] The disturbance analysis module 13 quantifies the abnormal degree of the subway line equipment operation status into specific numerical indicators through deviation analysis, providing a reliable decision-making basis for subsequent early warning processing. The accuracy and reliability of abnormal state identification are improved through a method based on multi-dimensional analysis.

[0021] The early warning processing module 14 is used to generate an operation and maintenance mark for the subway line equipment and send it to the operation and maintenance control terminal when the operation status disturbance coefficient is greater than or equal to the disturbance coefficient threshold.

[0022] Specifically, the early warning processing module 14 is used to realize intelligent early warning of the operation status of the subway line equipment. The early warning processing module 14 receives the operation status disturbance coefficient calculated by the disturbance analysis module 13, and compares it with a preset disturbance coefficient threshold in real time.

[0023] When the early warning processing module 14 detects that the operating status disturbance coefficient is greater than or equal to the disturbance coefficient threshold, it is determined that the current operating status of the subway line equipment is abnormal. At this time, the early warning processing module 14 immediately generates an operation and maintenance identification for the subway line equipment. The operation and maintenance identification contains the abnormal status information of the equipment and is used to mark the equipment that needs maintenance and repair. After generating the operation and maintenance identification, the early warning processing module 14 sends the identification information to the operation and maintenance control end in a timely manner so that the operation and maintenance personnel can promptly know the equipment status and take corresponding maintenance measures. Furthermore, when generating the operation and maintenance identification, the early warning processing module 14 packages the specific data of the disturbance analysis together, including but not limited to the specific value of the disturbance coefficient, the time point when the abnormality occurs, the duration of the abnormality and other key information. The provision of these detailed information helps the operation and maintenance personnel to accurately judge the degree of abnormality of the equipment and formulate corresponding maintenance plans.

[0024] The early warning processing module 14 realizes the timely discovery and rapid response of abnormal status of subway line equipment by establishing an intelligent early warning mechanism based on thresholds. Compared with the traditional regular maintenance mode, this early warning method is more targeted and timely, which can effectively reduce the risk of equipment failure and improve operation and maintenance efficiency.

[0025] The loop control module 15 is used to reset the timer to zero and start timing when the operating state disturbance coefficient is less than the disturbance coefficient threshold, and to execute the process in a loop.

[0026] Specifically, the cyclic control module 15 is used to realize continuous control of the operation status monitoring of the subway line equipment. The cyclic control module 15 performs intelligent control on the entire subway line operation and maintenance management process according to the operation status disturbance coefficient output by the disturbance analysis module 13.

[0027] The loop control module 15 first determines whether the operating status disturbance coefficient is less than the preset disturbance coefficient threshold. When the judgment result is yes, it indicates that the subway line equipment is in normal operation. At this time, the loop control module 15 resets the timer in the parameter acquisition module 11 to zero, so that it restarts timing. Through the reset operation, a new round of monitoring cycle is started, and a series of processes such as parameter acquisition, operation prediction, and disturbance analysis are re-executed. The loop control module 15 realizes the periodic operation control of the entire subway line operation and maintenance management by controlling the reset of the timer. This loop mechanism ensures that the operating status of the subway line equipment can be continuously monitored and analyzed to form a complete closed-loop control process.

[0028] The cycle control module 15 adopts a cycle control method based on the disturbance coefficient judgment, which not only ensures the continuity of the monitoring process, but also avoids the ineffective occupation of resources. This intelligent cycle control mechanism provides a reliable technical guarantee for the continuous monitoring of subway line equipment.

[0029] Further, such as Figure 2 As shown, with the subway line equipment operation control parameters as constraints, the fault-free sample operation status record data of the subway line equipment model is collected for frequency aggregation to obtain the subway line equipment operation status prediction data, including: Taking the subway line equipment operation control parameters as constraints, collecting the first-level fault-free sample operation status record data of the subway line equipment model, wherein the first-level fault-free sample operation status record data has the first-level sample subway line equipment operation control record parameters; taking the first-level sample subway line equipment operation control record parameters as constraints, collecting the second-level fault-free sample operation status record data of the subway line equipment model, wherein the second-level fault-free sample operation status record data has the second-level sample subway line equipment operation control record parameters; taking the second-level sample subway line equipment operation control record parameters as constraints, collecting the third-level fault-free sample operation status record data of the subway line equipment model; performing frequency aggregation on the first-level fault-free sample operation status record data, the second-level fault-free sample operation status record data and the third-level fault-free sample operation status record data to obtain the subway line equipment operation status prediction data.

[0030] In a feasible implementation, a multi-level data collection and frequency aggregation method is provided, which achieves accurate prediction of the operating status of subway line equipment by gradually expanding the sample data set and performing frequency analysis.

[0031] First, the first-level sampling is performed using the subway line equipment operation control parameters as the initial constraint conditions. Specifically, according to the currently running subway line equipment model, the first-level fault-free sample operation status record data that matches the constraint conditions is retrieved from the historical database. These first-level fault-free sample data contain the first-level sample subway line equipment operation control record parameters, which will serve as the constraint benchmark for the second-level sampling. In the second-level sampling, the first-level sample subway line equipment operation control record parameters are used as new constraints. Based on this constraint condition, the second-level fault-free sample operation status record data of the same model equipment is continuously retrieved from the historical database. The second-level fault-free sample data obtained in this way contains the second-level sample subway line equipment operation control record parameters, which will be used for the third-level sampling. During the third-level sampling process, the second-level sample subway line equipment operation control record parameters are used as the final constraint conditions to collect the corresponding third-level fault-free sample operation status record data. Through this three-level progressive sampling process, a rich sample set is obtained. After completing the third-level data sampling, all collected fault-free sample operation status record data are subjected to frequency aggregation analysis. Specifically, statistical analysis is performed on various parameters of the first-level fault-free sample operation status record data, the second-level fault-free sample operation status record data, and the third-level fault-free sample operation status record data, and parameter features and parameter combinations with higher frequencies are extracted to form subway line equipment operation status prediction data.

[0032] Through multi-level sampling and frequency aggregation methods, the scale of sample data is expanded, the data coverage is improved, and the most representative operating status characteristics are extracted, which enhances the reliability of prediction results and provides effective support for the accurate prediction of the operating status of subway line equipment.

[0033] Furthermore, taking the first-level sample subway line equipment operation control record parameters as constraints, collecting the second-level fault-free sample operation status record data of the subway line equipment model, including: According to the first-level sample subway line equipment operation control record parameters, the first sample subway line equipment operation control record parameters are obtained until the N-th sample subway line equipment operation control record parameters; with the first sample subway line equipment operation control record parameters as constraints, the first sample second-level fault-free sample operation status record data of the subway line equipment model is collected; until the N-th sample second-level fault-free sample operation status record data of the subway line equipment model is collected with the N-th sample subway line equipment operation control record parameters as constraints; the first sample second-level fault-free sample operation status record data until the N-th sample second-level fault-free sample operation status record data are added into the second-level fault-free sample operation status record data.

[0034] In a preferred embodiment, the collection and integration of the second-level fault-free sample operation status record data is achieved through detailed division and one-by-one constrained sampling of the first-level sample subway line equipment operation control record parameters.

[0035] Specifically, first, the obtained first-level sample subway line equipment operation control record parameters are systematically divided, and they are divided into the first sample subway line equipment operation control record parameters, the second sample subway line equipment operation control record parameters, and the Nth sample subway line equipment operation control record parameters. These N sample parameters each represent the equipment operation characteristics under different working conditions. After completing the parameter division, the first sample subway line equipment operation control record parameters are used as constraints to retrieve and collect the first sample second-level fault-free sample operation status record data of the corresponding subway line equipment model in the historical database. Subsequently, the second sample subway line equipment operation control record parameters, the third sample subway line equipment operation control record parameters and other operation control record parameters are used as constraints in turn to collect the corresponding second-level fault-free sample operation status record data. This process continues until the collection of the Nth sample second-level fault-free sample operation status record data with the Nth sample subway line equipment operation control record parameters as constraints is completed. After completing the data collection of all N sample subway line equipment operation control record parameters, the collected data, i.e., from the first sample second-level fault-free sample operation status record data to the Nth sample second-level fault-free sample operation status record data, are uniformly integrated and added to the second-level fault-free sample operation status record data.

[0036] A meticulous sub-sampling collection method is adopted, and the comprehensiveness of the secondary sampling is ensured by finely dividing the first-level sample subway line equipment operation control record parameters. At the same time, a one-by-one constrained sampling method is adopted to ensure the close correlation between each group of second-level fault-free sample operation status record data and the corresponding first-level sample subway line equipment operation control record parameters, providing a reliable data basis for subsequent analysis.

[0037] Furthermore, taking the first sample subway line equipment operation control record parameter as a constraint, collecting the first sample secondary fault-free sample operation status record data of the subway line equipment model, including: Construct a sample constraint function: , , in, Characterize the first constraint factor, Characterize the second constraint factor, Characterize the first sample subway line equipment operation control record parameters, Characterize the operation control record parameters of the subway line equipment of the fault-free sample to be sorted, The i-th attribute operation control record parameter representing the first sample subway line equipment operation control record parameter, The i-th attribute operation control record parameter representing the operation control record parameter of the subway line equipment of the fault-free sample to be sorted, represents the deviation threshold of the parameter of the operation control record of the i-th attribute, N represents the number of the control record parameter attributes, A characterization counting function; according to the sample constraint function, the operation control record parameters of the sample subway line equipment to be sorted and the first sample subway line equipment operation control record parameters of the subway line equipment model are processed to obtain a first constraint factor and a second constraint factor; when the first constraint factor is less than or equal to a first constraint factor threshold, and the second constraint factor is less than or equal to a second constraint factor threshold, the operation status record data of the sample subway line equipment to be sorted corresponding to the operation control record parameters of the sample subway line equipment to be sorted is added to the first sample secondary fault-free sample operation status record data.

[0038] In a preferred embodiment, a sample sorting method based on a dual constraint function is provided, and accurate collection of the running status record data of the first sample and the second level fault-free sample is achieved by constructing two complementary constraint factors.

[0039] First, construct a sample constraint function, which includes two sample constraint functions. The first sample constraint function is , this function generates the first constraint factor by calculating the proportion of parameter attributes that exceed the deviation threshold in the samples to be sorted This constraint factor evaluates the quality level of the sample to be sorted from the perspective of parameter abnormality rate. The second sample constraint function is This function generates the second constraint factor by calculating the overall deviation of the sample to be sorted relative to the reference sample. This constraint factor quantifies the difference between the sample to be sorted and the reference sample from the perspective of cumulative deviation. In the constraint function, Characterizes the first sample subway line equipment operation control record parameters as a benchmark, The operational control record parameters of the subway line equipment of the fault-free sample to be sorted and evaluated are characterized. and Respectively represent the i-th attribute value of these two sets of parameters, represents the parameter deviation threshold allowed for the i-th attribute, N represents the total number of parameter attributes, The function is used to count the number of conditions that meet the condition.

[0040] In practical application, the parameters of the sample to be sorted and the parameters of the first sample are substituted into the two constraint functions for calculation, and the first constraint factor and the second constraint factor are obtained respectively. When the two constraint factors simultaneously meet their respective threshold requirements, that is, the first constraint factor is less than or equal to the first constraint factor threshold, and the second constraint factor is less than or equal to the second constraint factor threshold, the running status record data corresponding to the sample to be sorted is included in the first sample secondary fault-free sample running status record data set.

[0041] By adopting a dual-constraint screening mechanism, we can achieve comprehensive control of sample quality from two dimensions: the abnormal rate of control parameters and the cumulative deviation. The first constraint factor focuses on the quantity control of abnormal parameters, while the second constraint factor focuses on the overall deviation of the parameters. The combination of the two significantly improves the accuracy and reliability of sample screening and provides an evaluation standard for obtaining high-quality secondary fault-free samples.

[0042] Further, frequency aggregation is performed on the first-level fault-free sample operation status record data, the second-level fault-free sample operation status record data, and the third-level fault-free sample operation status record data to obtain the subway line equipment operation status prediction data, including: According to the first-level fault-free sample operation status record data, the second-level fault-free sample operation status record data and the third-level fault-free sample operation status record data, a first state attribute record value set is extracted; a central trend analysis is performed on the first state attribute record value set to obtain a first state attribute set record value; a box plot distribution is performed on the first state attribute set record value to obtain a first state attribute distribution interval, which is added to the subway line equipment operation status prediction data.

[0043] In a preferred embodiment, a data analysis method based on frequency aggregation is provided, which achieves accurate prediction of the operating status of subway line equipment by systematically analyzing and statistically modeling multi-level fault-free sample data.

[0044] First, the collected first-level fault-free sample operation status record data, second-level fault-free sample operation status record data, and third-level fault-free sample operation status record data are uniformly processed. By analyzing the sample data of these three levels, the first-state attribute record value set contained therein is extracted, which reflects the attribute characteristics of the subway line equipment in different operating states. After obtaining the first-state attribute record value set, a central trend analysis is performed on it. The main distribution laws of the data are identified and extracted through statistical methods, and the centralized distribution characteristics of the data in the first-state attribute record value set are analyzed to obtain the first-state attribute set record value that can represent the overall characteristics, reflecting the typical attribute performance of the subway line equipment under normal operating conditions.

[0045] At the same time, the box plot analysis method is further used to conduct an in-depth study on the recorded values ​​of the first state attribute set. Through the box plot distribution analysis, the quartile distribution characteristics, outlier distribution and overall distribution range of the data are clearly identified, so as to obtain the distribution interval of the first state attribute. This distribution interval not only contains the core concentrated area of ​​the data, but also reflects the reasonable fluctuation range, providing a reliable reference standard for subsequent state prediction. Afterwards, this statistically significant distribution interval is added to the subway line equipment operation status prediction data.

[0046] Through multi-level data analysis and processing methods, effective transformation from original sample data to prediction model is achieved. Not only the centralization trend of the data is taken into account, but also the distribution characteristics of the data are retained through box plot analysis, providing more comprehensive and accurate data support for the operation status prediction of subway line equipment.

[0047] Furthermore, a deviation analysis is performed on the subway line equipment operation status prediction data and the subway line equipment operation status monitoring data to obtain an operation status disturbance coefficient, including: The time proportion of each state attribute in the subway line equipment operation state monitoring data that does not belong to the subway line equipment operation state prediction data is counted to obtain the time domain disturbance degree of the first state attribute until the time domain disturbance degree of the Mth state attribute; the deviation mean of each state attribute in the subway line equipment operation state monitoring data that does not belong to the subway line equipment operation state prediction data is traversed to obtain the disturbance step length of the first state attribute until the disturbance step length of the Mth state attribute; when the time domain disturbance degree of the first state attribute is greater than or equal to the disturbance degree threshold, and the disturbance step length of the first state attribute is greater than or equal to the disturbance step length threshold, the first state attribute is marked as disturbance, otherwise the first state attribute is marked as non-disturbance; until the time domain disturbance degree of the Mth state attribute is greater than or equal to the disturbance degree threshold, and the disturbance step length of the Mth state attribute is greater than or equal to the disturbance step length threshold, the Mth state attribute is marked as disturbance, otherwise the Mth state attribute is marked as non-disturbance; the proportion of the number of attributes with disturbance marks is counted and set as the operation state disturbance coefficient.

[0048] In a preferred embodiment, a method for analyzing operating status disturbance is provided, which realizes accurate quantification of the abnormal degree of operating status of subway line equipment by establishing a two-dimensional disturbance evaluation mechanism.

[0049] First, the time domain analysis of the subway line equipment operation status monitoring data is carried out. Specifically, the time proportion of the monitoring value of each state attribute that does not belong to the predicted data range is counted, and the time domain disturbance degree from the first state attribute to the Mth state attribute is obtained respectively. This time domain disturbance degree reflects the abnormal degree of each state attribute in the time dimension, which provides an important basis for the subsequent disturbance judgment. Subsequently, the state attribute values ​​that deviate from the prediction range in the monitoring data are traversed and analyzed. By calculating the mean of these deviation values, the disturbance step length from the first state attribute to the Mth state attribute is obtained respectively. The disturbance step length quantifies the degree to which each state attribute deviates from the prediction range and reflects the intensity characteristics of the disturbance. After obtaining the time domain disturbance degree and disturbance step length, a dual threshold judgment mechanism is established. For the first state attribute, when its time domain disturbance degree is greater than or equal to the preset disturbance degree threshold, and the disturbance step length is greater than or equal to the preset disturbance step length threshold, the attribute is marked with a disturbance mark; otherwise, it is marked as a non-disturbance mark. The same judgment process is performed on all state attributes in turn until the disturbance judgment of the Mth state attribute is completed. After that, the number of all attributes that have obtained disturbance marks is counted, and their proportion in the total number of attributes is calculated, and the proportion value is set as the operation status disturbance coefficient. The operation status disturbance coefficient comprehensively reflects the overall abnormality of the current operation status of the subway line equipment.

[0050] Through the multi-dimensional disturbance analysis method, not only the time characteristics of the disturbance are taken into account, but also the intensity characteristics of the disturbance are quantified, so as to achieve a comprehensive assessment of the abnormal operation status. It can not only detect the operation abnormality in time, but also accurately judge the severity of the abnormality, providing a reliable decision-making basis for the intelligent operation and maintenance of subway line equipment.

[0051] Furthermore, the proportion of the number of attributes with disturbance flags is counted and set as the running state disturbance coefficient, and further includes: Configure sensitive state attributes; when the state attribute with a disturbance mark belongs to the sensitive state attribute, set the operating state disturbance coefficient to be greater than or equal to the disturbance coefficient threshold; when the state attribute with a disturbance mark does not belong to the sensitive state attribute, set the proportion of the number of attributes with a disturbance mark to the operating state disturbance coefficient.

[0052] In a preferred embodiment, an improved operation status disturbance coefficient calculation method is provided, which realizes focused monitoring and differentiated processing of key operation parameters by introducing a sensitive state attribute mechanism.

[0053] First, configure sensitive state attributes. Sensitive state attributes refer to key parameters that have an important impact on the operation safety and performance of subway line equipment and require special monitoring and processing. By pre-configuring sensitive state attributes, a basic framework for hierarchical monitoring is established. When calculating the operating state disturbance coefficient, first determine whether the state attribute with a disturbance mark belongs to a sensitive state attribute. When it is detected that the state attribute with a disturbance mark contains a sensitive state attribute, the operating state disturbance coefficient is directly set to be greater than or equal to the disturbance coefficient threshold. This processing mechanism reflects the high attention paid to sensitive parameter anomalies and ensures timely response to important parameter disturbances. In contrast, when none of the state attributes with a disturbance mark belong to sensitive state attributes, the conventional calculation method is used to take the ratio of the number of attributes with a disturbance mark to the total number of attributes as the operating state disturbance coefficient. This differentiated processing strategy not only ensures the accurate evaluation of common parameter disturbances, but also highlights the warning effect of sensitive parameter anomalies.

[0054] Through this disturbance coefficient calculation method based on sensitive state attributes, a more reasonable state assessment mechanism has been established, which not only takes into account the overall situation of parameter disturbance, but also strengthens the monitoring of key parameters, providing more reliable guarantee for the safe operation of subway line equipment.

[0055] Furthermore, the embodiment of the present application also includes: Obtain the fault sample operation status record data of the subway line equipment model, wherein any one of the fault sample operation status record data includes a deviation state attribute; based on the fault sample operation status record data, count the abnormal trigger frequency ratio of the deviation state attribute, and set it as the state attribute sensitivity; extract the state attribute whose state attribute sensitivity is greater than or equal to the sensitivity threshold, and set it as the sensitive state attribute.

[0056] In a preferred embodiment, a sensitive state attribute configuration method based on historical fault data is provided, and a state attribute sensitivity evaluation system is established by analyzing parameter characteristics in fault samples.

[0057] First, the fault sample operation status record data corresponding to the subway line equipment model is obtained. These fault sample data record the operation status of the equipment when the fault occurs, which contains various deviation state attributes. Each fault sample operation status record data contains the parameter deviation information when the fault occurs, providing an important data basis for the identification of sensitive attributes. After obtaining the fault sample data, the deviation state attributes therein are statistically analyzed. By calculating the frequency ratio of each deviation state attribute in all fault samples, the abnormal trigger frequency of each state attribute is obtained. This frequency ratio is defined as the state attribute sensitivity, which reflects the degree of correlation between the attribute and the equipment fault. After that, a sensitivity threshold is set, and the attributes whose state attribute sensitivity exceeds the threshold are extracted and determined as sensitive state attributes. Through the screening method based on statistical analysis, it is ensured that the selected sensitive state attributes have strong fault indication capabilities.

[0058] Through the data-driven sensitive attribute configuration method, scientific identification of key monitoring parameters is achieved. It is not only based on the objective analysis of historical fault data, but also realizes flexible adjustment of configuration through the setting of sensitivity thresholds, providing a more accurate parameter selection basis for the status monitoring of subway line equipment.

[0059] In summary, the subway line safety management and control system based on the intelligent maintenance mode provided in the embodiment of the present application has the following technical effects: The parameter collection module is used to start the timer when the subway line equipment is started. When the preset time is met, it interacts with the subway line equipment to obtain the subway line equipment operation control parameters and subway line equipment operation status monitoring data. By setting the preset time to collect data, the regularity and continuity of data collection are ensured, providing basic data support for subsequent analysis and prediction. The operation prediction module is used to collect the fault-free sample operation status record data of the subway line equipment model with the subway line equipment operation control parameters as constraints, and obtain the subway line equipment operation status prediction data. The prediction is made with the operation control parameters as constraints, and a prediction model for the normal operation status of the equipment is established to ensure the accuracy and reference value of the prediction results. The disturbance analysis module is used to perform deviation analysis on the subway line equipment operation status prediction data and the subway line equipment operation status monitoring data, and obtain the operation status disturbance coefficient, which reflects the degree of deviation between the actual operation status of the equipment and the expected status, and is an important basis for judging whether the equipment needs maintenance. The early warning processing module is used to generate an operation and maintenance mark for the subway line equipment when the operating state disturbance coefficient is greater than or equal to the disturbance coefficient threshold, and send it to the operation and maintenance control end, so as to realize timely early warning of abnormal equipment status, so that maintenance personnel can intervene and handle it in time. The loop control module is used to reset the timer to zero and start timing when the operating state disturbance coefficient is less than the disturbance coefficient threshold, and the loop execution process realizes continuous monitoring of the equipment status, ensures the continuous operation of the entire subway line operation and maintenance management system, and realizes intelligent on-demand maintenance.

[0060] Any steps of the system described above may be stored as computer instructions or programs in an unlimited computer memory, and may be called and recognized by an unlimited computer processor to implement any system in the embodiments of the present application, without any unnecessary restrictions.

[0061] Furthermore, the first or second mentioned above may not only represent an order relationship, but may also represent a specific concept, and / or refer to multiple elements that can be selected individually or in full. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these changes and variations.

Claims

1. A subway line safety management and control system based on intelligent maintenance mode, characterized in that: include: A parameter acquisition module, which is used to start a timer when the subway line equipment is started, and when a preset time is met, interact with the subway line equipment to obtain subway line equipment operation control parameters and subway line equipment operation status monitoring data; An operation prediction module, wherein the operation prediction module is used to collect the fault-free sample operation status record data of the subway line equipment model and perform frequency aggregation based on the subway line equipment operation control parameters as constraints to obtain subway line equipment operation status prediction data; A disturbance analysis module, the disturbance analysis module is used to perform deviation analysis on the subway line equipment operation status prediction data and the subway line equipment operation status monitoring data to obtain an operation status disturbance coefficient; An early warning processing module, wherein when the operating state disturbance coefficient is greater than or equal to a disturbance coefficient threshold, the early warning processing module generates an operation and maintenance mark for the subway line equipment and sends the mark to the operation and maintenance control terminal; A loop control module is used for resetting the timer to zero and starting timing when the operating state disturbance coefficient is less than the disturbance coefficient threshold, and cyclically executing the process.

2. A subway line safety management and control system based on intelligent maintenance mode as claimed in claim 1, characterized in that: The operation prediction module includes the following execution steps: Taking the subway line equipment operation control parameters as constraints, collecting the first-level fault-free sample operation status record data of the subway line equipment model, wherein the first-level fault-free sample operation status record data has the first-level sample subway line equipment operation control record parameters; Taking the first-level sample subway line equipment operation control record parameters as constraints, collecting the second-level fault-free sample operation status record data of the subway line equipment model, wherein the second-level fault-free sample operation status record data has the second-level sample subway line equipment operation control record parameters; Taking the second-level sample subway line equipment operation control record parameters as constraints, collecting the third-level fault-free sample operation status record data of the subway line equipment model; Frequency aggregation is performed on the first-level fault-free sample operation status record data, the second-level fault-free sample operation status record data, and the third-level fault-free sample operation status record data to obtain the subway line equipment operation status prediction data.

3. A subway line safety management and control system based on intelligent maintenance mode as claimed in claim 2, characterized in that: The operation prediction module also includes the following execution steps: According to the first-level sample subway line equipment operation control record parameters, obtaining the first sample subway line equipment operation control record parameters until the Nth sample subway line equipment operation control record parameters; Taking the first sample subway line equipment operation control record parameters as constraints, collecting the first sample secondary fault-free sample operation status record data of the subway line equipment model; Until the Nth sample secondary fault-free sample operation status record data of the subway line equipment model is collected with the Nth sample subway line equipment operation control record parameter as a constraint; The first sample secondary fault-free sample operation status record data to the Nth sample secondary fault-free sample operation status record data are added into the secondary fault-free sample operation status record data.

4. A subway line safety management and control system based on intelligent maintenance mode as claimed in claim 3, characterized in that: The operation prediction module also includes the following execution steps: Construct a sample constraint function: ， ， in, Characterize the first constraint factor, Characterize the second constraint factor, Characterize the first sample subway line equipment operation control record parameters, Characterize the operation control record parameters of the subway line equipment of the fault-free sample to be sorted, The i-th attribute operation control record parameter representing the first sample subway line equipment operation control record parameter, The i-th attribute operation control record parameter representing the operation control record parameter of the subway line equipment of the fault-free sample to be sorted, represents the deviation threshold of the parameter of the operation control record of the i-th attribute, N represents the number of the control record parameter attributes, Characterize counting functions; According to the sample constraint function, the sample subway line equipment operation control record parameters to be sorted and the first sample subway line equipment operation control record parameters of the subway line equipment model are processed to obtain a first constraint factor and a second constraint factor; When the first constraint factor is less than or equal to the first constraint factor threshold, and the second constraint factor is less than or equal to the second constraint factor threshold, the operation status record data of the sample subway line equipment to be sorted corresponding to the operation control record parameters of the sample subway line equipment to be sorted is added to the first sample secondary fault-free sample operation status record data.

5. A subway line safety management and control system based on intelligent maintenance mode as claimed in claim 2, characterized in that: The operation prediction module also includes the following execution steps: Extracting a first state attribute record value set according to the first-level fault-free sample operation state record data, the second-level fault-free sample operation state record data, and the third-level fault-free sample operation state record data; Performing a central tendency analysis on the first state attribute record value set to obtain a first state attribute set record value; Perform box plot distribution on the first state attribute set record values ​​to obtain a first state attribute distribution interval, and add it into the subway line equipment operation state prediction data.

6. A subway line safety management and control system based on intelligent maintenance mode as claimed in claim 1, characterized in that: The disturbance analysis module includes the following execution steps: Counting the time proportion of each state attribute in the subway line equipment operation state monitoring data that does not belong to the subway line equipment operation state prediction data, and obtaining the first state attribute time domain disturbance degree until the Mth state attribute time domain disturbance degree; Traversing each state attribute deviation mean value in the subway line equipment operation state monitoring data that does not belong to the subway line equipment operation state prediction data, and obtaining a first state attribute disturbance step length until an Mth state attribute disturbance step length; When the time domain disturbance degree of the first state attribute is greater than or equal to the disturbance degree threshold, and the disturbance step length of the first state attribute is greater than or equal to the disturbance step length threshold, the first state attribute is marked as disturbed, otherwise the first state attribute is marked as non-disturbed; Until the time domain disturbance degree of the Mth state attribute is greater than or equal to the disturbance degree threshold, and the disturbance step length of the Mth state attribute is greater than or equal to the disturbance step length threshold, the Mth state attribute is marked as disturbed, otherwise the Mth state attribute is marked as non-disturbed; The proportion of the number of attributes with disturbance flags is counted and set as the running state disturbance coefficient.

7. A subway line safety management and control system based on intelligent maintenance mode as claimed in claim 6, characterized in that: The disturbance analysis module also includes the following execution steps: Configure sensitive state attributes; When the state attribute with a disturbance flag belongs to the sensitive state attribute, setting the running state disturbance coefficient to be greater than or equal to the disturbance coefficient threshold; When the state attribute with the disturbance mark does not belong to the sensitive state attribute, the proportion of the number of attributes with the disturbance mark is set as the operating state disturbance coefficient.

8. A subway line safety management and control system based on intelligent maintenance mode as claimed in claim 7, characterized in that: The disturbance analysis module also includes the following execution steps: Obtaining fault sample operation status record data of the subway line equipment model, wherein any one of the fault sample operation status record data includes a deviation state attribute; According to the running status record data of the fault sample, the abnormal trigger frequency ratio of the deviation state attribute is counted and set as the state attribute sensitivity; The state attribute whose state attribute sensitivity is greater than or equal to the sensitivity threshold is extracted and set as the sensitive state attribute.

Images