Railway station roof gutter drainage state intelligent monitoring system and method

Abstract

The present application relates to the technical field of roof gutter monitoring of railway station buildings, and specifically discloses a kind of roof gutter drainage state intelligent monitoring system and method of railway station building, the method comprises: S1, in the state of no rainfall, continuously collect gutter internal image data and gutter structure displacement data;S2, with preset frequency to gutter internal image data and gutter structure displacement data are comprehensively analyzed, obtain daily risk assessment value, when daily risk assessment value exceeds preset daily risk early warning threshold, generate daily maintenance early warning signal;The present application continuously collects structure and image data in the rainless period, collects flow and water accumulation data in real time in the rainfall period, and carries out multi-dimensional data fusion analysis after the rain, constructs a grading early warning mechanism covering three levels of daily, emergency and prevention, effectively solves the problem of single monitoring means, data isolation, lack of dynamic evaluation and early warning capability in the prior art.

Description

Technical Field

[0001] This invention relates to the field of monitoring technology for roof gutters on railway stations, specifically to an intelligent monitoring system and method for monitoring the drainage status of roof gutters on railway stations. Background Technology

[0002] As a vital transportation hub, the durability of railway station buildings and their safety during operation are of paramount importance. The roof gutter drainage system is a key component of the station building's roof, responsible for collecting and draining rainwater. Its drainage status directly affects the structural safety of the station building's roof and the comfort of the internal waiting environment. Over long-term use, the roof gutter system of railway station buildings may become clogged due to the accumulation of debris, or its waterproof performance may decline due to material aging and structural deformation, leading to poor drainage, water accumulation in the gutters, or even leakage. Therefore, effectively monitoring the drainage status of the roof gutter of railway station buildings is an important maintenance task to ensure the safe operation of the station building.

[0003] In existing technologies, the monitoring methods for roof gutters of railway stations are mostly single and isolated, such as relying solely on regular manual inspections or deploying simple liquid level alarm devices. These methods may make it difficult to detect routine structural and progressive defects (such as slow displacement and debris accumulation) in a timely manner, and there is a lack of effective real-time assessment and early warning for emergency situations during rainfall. Furthermore, existing methods lack the ability to intelligently integrate and comprehensively analyze multi-source data, and fail to conduct correlation analysis between routine structural health status and dynamic drainage performance during rainfall. This results in delayed and one-sided operation and maintenance decisions, and the inability to issue accurate preventive maintenance signals before potential hazards develop into serious failures. Summary of the Invention

[0004] The purpose of this invention is to provide an intelligent monitoring system and method for the drainage status of roof gutters in railway station buildings, solving the following technical problems:

[0005] How to overcome the problems of limited monitoring methods and lack of early warning mechanisms for railway station roof gutters in existing technologies.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A method for intelligent monitoring of drainage status of roof gutters in railway station buildings, the method comprising:

[0008] S1. Under conditions of no rainfall, continuously collect image data of the inside of the gutter and displacement data of the gutter structure;

[0009] S2. Perform comprehensive analysis on the internal image data and structural displacement data of the gutter at a preset frequency to obtain the daily risk assessment value. When the daily risk assessment value exceeds the preset daily risk warning threshold, generate a daily maintenance warning signal.

[0010] S3. When rainfall is detected, rainwater flow data and gutter water accumulation data are collected in real time;

[0011] S4. Analyze rainwater flow data and gutter water accumulation data to obtain drainage risk assessment value. When the drainage risk assessment value exceeds the preset emergency risk warning threshold, generate an emergency response warning signal.

[0012] S5. After the rainfall ends, a comprehensive risk assessment value is obtained by combining the time-series dataset of drainage risk assessment values ​​throughout the rainfall process with the latest daily risk assessment values. When the comprehensive risk assessment value exceeds the preset comprehensive risk warning threshold, a preventive maintenance warning signal is generated.

[0013] Furthermore, in step S2, the process of generating the routine maintenance early warning signal includes:

[0014] ;

[0015] The daily risk assessment value is obtained by analyzing and calculating using formula (1). ;

[0016] in, To block the risk index, This is a structural anomaly index. , The first weighting coefficient;

[0017] Daily risk assessment values With preset daily risk warning threshold Perform a comparison;

[0018] like Then a routine maintenance early warning signal will be generated;

[0019] Conversely, continue with the routine monitoring process.

[0020] Furthermore, the process of obtaining the congestion risk index includes:

[0021] ;

[0022] ;

[0023] ;

[0024] The congestion risk index is obtained by analyzing and calculating using formulas (2)-(4). ;

[0025] wherein, is the total number of data points within the preset sliding time window, , is the debris coverage rate corresponding to the Nth monitoring point within the preset sliding time window, is the change value of the debris coverage rate within adjacent monitoring points, is the change speed of the debris coverage rate within the preset sliding time window, 、 、 is a second weight coefficient, is the debris coverage rate corresponding to the N-1th monitoring point within the preset sliding time window, is the debris coverage rate corresponding to the ith monitoring point within the preset sliding time window, is the timestamp corresponding to the ith monitoring point within the preset sliding time window.

[0026] Further, the process of obtaining the structure anomaly index includes:

[0027] ;

[0028] ;

[0029] ;

[0030] The structure anomaly index is obtained by formula (5)-(7) analysis and calculation ;

[0031] wherein, is the displacement deviation value of the gutter structure within the preset sliding time window, is the displacement change rate of the gutter structure within the preset sliding time window, 、 is a third weight coefficient, is the displacement value of the gutter structure corresponding to the Nth monitoring point within the preset sliding time window, is the reference displacement value set after the gutter installation acceptance or the last overhaul, is the displacement value of the gutter structure corresponding to the ith monitoring point within the preset sliding time window.

[0032] Further, the process of generating the emergency treatment early warning signal includes:

[0033] ;

[0034] ;

[0035] ;

[0036] The drainage risk assessment value is obtained by analyzing and calculating through formulas (8)-(10) ;

[0037] Wherein, is the real-time drainage efficiency index, is the waterlogging risk index, , is the fourth weight coefficient, is the real-time drainage flow, and h is the current gutter water depth, is the current water depth corresponding to the theoretical drainage flow, is the safe water depth of the gutter, is the gutter water depth of the last monitoring period, is the time interval of the adjacent monitoring period in the rainfall state, , is the fifth weight coefficient;

[0038] The drainage risk assessment value is compared with the preset emergency risk warning threshold ;

[0039] If , an emergency disposal warning signal is generated;

[0040] Otherwise, the rainfall monitoring process is continued.

[0041] Further, the process of generating the preventive maintenance warning signal comprises:

[0042] ;

[0043] ;

[0044] ;

[0045] The comprehensive risk assessment value is obtained by analyzing and calculating through formulas (11)-(13) ;

[0046] Wherein, is the latest daily risk assessment value after the rainfall ends, is the average value of the drainage risk assessment values exceeding the peak threshold value during the rainfall process, is the stability coefficient of the drainage risk assessment values during the rainfall process, , , is the sixth weight coefficient, and M is the number of drainage risk assessment values generated during the rainfall process, , is the kth drainage risk assessment value in the rainfall process, is the average value of all drainage risk assessment values in the rainfall process, and m is the number of drainage risk assessment values exceeding the peak threshold value in the rainfall process, , is the jth drainage risk assessment value exceeding the peak threshold value;

[0047] The comprehensive risk assessment value is compared with a preset comprehensive risk warning threshold value .

[0048] If , a preventive maintenance warning signal is generated.

[0049] Otherwise, the daily monitoring process is re-executed.

[0050] Further, the method further comprises:

[0051] S6, adaptively adjusting the preset frequency based on the daily risk assessment value;

[0052] ;

[0053] The preset frequency is obtained by formula (14) analysis and calculation .

[0054] wherein, is the reference monitoring frequency, is the adjustment coefficient.

[0055] An intelligent monitoring system for the drainage state of a roof gutter of a railway station building, the system being used to implement an intelligent monitoring method for the drainage state of a roof gutter of a railway station building, the system comprising:

[0056] a collection module comprising a waterproof camera unit, a displacement sensing unit, a flow sensing unit, a water depth detection unit, and a rainfall detection unit, for collecting internal images of the gutter, structural displacement, rainwater flow, water depth, and rainfall event raw data under various environmental conditions;

[0057] a data processing and analysis module comprising a blockage analysis unit, a structure analysis unit, a drainage efficiency analysis unit, and a water accumulation analysis unit, for processing and calculating the raw data transmitted by the collection module to obtain a blockage risk index, a structural anomaly index, a drainage efficiency index, and a water accumulation risk index, respectively;

[0058] a risk assessment and warning module comprising a daily risk assessment unit, a drainage risk assessment unit, and a comprehensive risk assessment unit, for generating three types of warning signals, i.e., daily maintenance, emergency disposal, and preventive maintenance, based on the output results of the data processing and analysis module; ​

[0059] a mode control module for controlling switching of the monitoring mode according to a rainfall event.

[0060] Advantages of the present application:

[0061] (1) The present application continuously collects structural and image data during the rain-free period, real-time collects flow and water accumulation data during the rainfall period, and performs multi-dimensional data fusion analysis after the rain, thereby constructing a hierarchical early warning mechanism covering three levels of daily, emergency and prevention, effectively solving the problems of single monitoring means, isolated data, lack of dynamic evaluation and early warning capability in the prior art, and timely discovering structural gradual diseases and drainage abnormalities during rainfall, realizing the change from passive repair to active early warning, from post-disposal to pre-prevention, and significantly improving the operation and maintenance efficiency and structural safety level of the roof gutter drainage system of the railway station building.

[0062] (2) The present application creatively constructs a comprehensive index for comprehensively evaluating the long-term health of the gutter by integrating three core elements of the daily structural state, the peak pressure during rainfall and the stability of the drainage process after the rain, and performs correlation quantitative analysis on the dynamic performance during rainfall and the daily structural state, thereby accurately identifying the gutter system that has not yet occurred an emergency danger but has shown a significant performance degradation trend, realizing the fundamental change from post-maintenance to pre-prevention, and effectively solving the core defects of early warning lag and one-sided decision-making in the prior art. BRIEF DESCRIPTION OF DRAWINGS

[0063] The present application will be further described below with reference to the accompanying drawings.

[0064] Figure 1 is a step flow chart of a railway station building roof gutter drainage state intelligent monitoring method proposed by the present application;

[0065] Figure 2 is a schematic block diagram of a railway station building roof gutter drainage state intelligent monitoring system proposed by the present application. DETAILED DESCRIPTION

[0066] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0067] Please refer to Figure 1 shown, in one embodiment, a railway station building roof gutter drainage state intelligent monitoring method is provided, the method comprising:

[0068] S1, continuously collecting gutter interior image data and gutter structure displacement data under no rainfall conditions to reflect the daily structural state and debris accumulation of the gutter;

[0069] S2, comprehensively analyzing the gutter interior image data and gutter structure displacement data at a preset frequency to obtain a daily risk assessment value, and when the daily risk assessment value exceeds a preset daily risk warning threshold, prompting that there may be potential risks such as structural deformation or debris accumulation, and generating a daily maintenance warning signal;

[0070] S3, when rainfall is detected, real-time collection of rainwater flow data and gutter water accumulation data for evaluating the actual drainage state;

[0071] S4, analyzing the rainwater flow data and gutter water accumulation data to obtain a drainage risk assessment value, and when the drainage risk assessment value exceeds a preset emergency risk warning threshold, prompting that the current drainage system may be blocked or have insufficient drainage capacity, and generating an emergency disposal warning signal;

[0072] S5, after detecting the end of rainfall, based on the time series data set of the drainage risk assessment value during the entire rainfall process, and combining the latest daily risk assessment value for comprehensive analysis, a comprehensive risk assessment value is obtained, and when the comprehensive risk assessment value exceeds a preset comprehensive risk warning threshold, it is prompted that the gutter system may have the possibility of structural performance degradation or functional degradation due to long-term cumulative effect, and a preventive maintenance warning signal is generated.

[0073] Through the above technical solution, the embodiment provides an intelligent monitoring method for the drainage state of a roof gutter of a railway station building. The method continuously collects structure and image data during the dry season, real-time collects flow and water accumulation data during the rainfall period, and performs multi-dimensional data fusion analysis after the rain, thereby constructing a hierarchical warning mechanism covering three levels of daily, emergency and preventive, effectively solving the problems of single monitoring means, isolated data, lack of dynamic evaluation and warning capability in the prior art, and timely discovering structural gradual diseases and drainage abnormalities during rainfall, realizing the transformation from passive repair to active warning, from post-disposal to pre-prevention, and significantly improving the operation and maintenance efficiency and structural safety level of the roof gutter drainage system of the railway station building.

[0074] In an embodiment, in step S2, the process of generating the daily maintenance warning signal includes:

[0075] ;

[0076] The daily risk assessment value is obtained by formula (1) ;

[0077] wherein, The clog risk index is used to quantify the degree of risk that the drainage capacity of gutters will decrease due to the accumulation of debris. This is a structural anomaly index used to quantify the degree of structural risk caused by deformation, settlement, or displacement in a gutter structure. , As the first weighting coefficient, these represent the relative importance of congestion and structural risk in the overall assessment. Their values ​​are determined based on historical maintenance data and expert knowledge. For example, for station buildings with abundant vegetation and fallen leaves, A higher value (e.g., 0.6-0.7) can be used to more sensitively reflect blockages; for stations with old structures or located in geologically unstable areas, A higher value (such as 0.6-0.7) can be chosen to place greater emphasis on structural safety;

[0078] Daily risk assessment values With preset daily risk warning threshold The preset daily risk warning threshold was compared. It is determined based on historical monitoring data, structural safety specifications and practical engineering experience, and is mainly based on the allowable deformation range and common siltation degree of the gutter structure design.

[0079] like Then a routine maintenance early warning signal will be generated;

[0080] Conversely, continue with the routine monitoring process.

[0081] High-definition cameras deployed at key locations in the gutter continuously collect images of the bottom of the gutter. Based on computer vision technology, a semantic segmentation model is used to analyze the images, classifying pixels into "debris" (such as leaves, mud, and plastic) and "gutter base". The debris coverage rate of each frame is then calculated, which is the proportion of debris pixels to the total area pixels.

[0082] The process of obtaining the congestion risk index includes:

[0083] ;

[0084] ;

[0085] ;

[0086] The congestion risk index is obtained by analyzing and calculating using formulas (2)-(4). ;

[0087] in, This is the total number of data points within the preset sliding time window. For example, if an image is captured every 10 minutes and the window length is set to 24 hours, then N=144. , is the debris coverage rate of the latest (Nth) monitoring point in the preset sliding time window, is the change value of debris coverage rate between adjacent monitoring points, used to capture the sudden increase of debris (such as a large amount of fallen leaves instantaneously flowing in after a strong wind), is the change speed of debris coverage rate in the preset sliding time window, used to judge the accumulation speed, , , is the second weight coefficient, which is obtained by regression analysis on a large number of historical image data sequences, is the debris coverage rate of the N-1th monitoring point in the preset sliding time window, is the debris coverage rate of the ith monitoring point in the preset sliding time window, is the time stamp corresponding to the ith monitoring point in the preset sliding time window.

[0088] The displacement sensor installed on the gutter support structure continuously collects the displacement data of the gutter in the vertical and horizontal directions. After pre-processing by algorithms such as Kalman filtering, the noise interference such as temperature change and instantaneous vibration is eliminated, and the displacement value sequence used for analysis is obtained;

[0089] The process of obtaining the structure anomaly index includes:

[0090] ;

[0091] ;

[0092] ;

[0093] The structure anomaly index is obtained by analyzing and calculating by formulas (5)-(7) ;

[0094] Among them, is the displacement deviation value of the gutter structure in the preset sliding time window, is the displacement change rate of the gutter structure in the preset sliding time window, , is the third weight coefficient, which is obtained according to the relative importance of the two in the structure failure path, is the displacement value of the latest (Nth) monitoring point corresponding to the gutter structure in the preset sliding time window, is the reference displacement value set after the gutter installation acceptance or the last overhaul, is the displacement value of the ith monitoring point corresponding to the gutter structure in the preset sliding time window.

[0095] Through the technical scheme, the embodiment provides a roof gutter daily risk assessment method for a railway station building, the method constructs a blockage risk index and a structure abnormality index respectively, introduces a sliding time window mechanism to perform dynamic trend analysis on the debris coverage and the structure displacement, and finally realizes quantitative assessment of the daily risk through weighted fusion, so that potential hidden dangers caused by slow accumulation of debris and progressive deformation of the structure can be effectively identified, and the timeliness and continuity of traditional manual inspection can be overcome.

[0096] In an embodiment, the process of generating the emergency treatment early warning signal comprises:

[0097] ;

[0098] ;

[0099] ;

[0100] The drainage risk assessment value is obtained through formula (8)-(10) ;

[0101] wherein, is a real-time drainage efficiency index, representing the instantaneous performance state of the drainage system, is a waterlogging risk index, , is a fourth weight coefficient, used to balance the weight of the drainage efficiency and the waterlogging risk in the overall assessment, is a real-time drainage flow, obtained by directly measuring through a flow meter installed at the gutter downpipe, h is a current gutter waterlogging depth, obtained by real-time measurement through a liquid level sensor installed at the bottom of the gutter, is a current waterlogging depth corresponding to a theoretical drainage flow, according to the design drawings (such as pipe diameter, slope, material) of the gutter and the drainage pipeline, a hydraulic calculation model such as the Manning formula is applied to establish a corresponding relationship database or function of “waterlogging depth-drainage flow”, and in operation, the system can obtain the ideal flow that the drainage system should reach under the depth according to the real-time measured waterlogging depth h by querying the database, is a gutter safety waterlogging depth, a key safety threshold preset according to the design drawings of the gutter structure, is a gutter waterlogging depth of the last monitoring period, directly obtained from historical monitoring data records, is a time interval of adjacent monitoring periods in a rainfall state, in the rainfall state, the system is automatically switched to a high-frequency monitoring mode, and the time interval will be significantly shortened (for example, set to 5 minutes or less) to adapt to the rapid changes during rainfall, , is a fifth weight coefficient, which is obtained according to experience pre-setting, and is used for balancing the relative importance of the absolute value of the waterlogging depth and the waterlogging rising speed;

[0102] The drainage risk assessment value is compared with a preset emergency risk early warning threshold value , the preset emergency risk early warning threshold value is determined through historical waterlogging event data, system hydraulic model simulation, and safety checking under an extreme rainfall scenario, and corresponds to a critical state in which the system drainage function has been close to failure, and has begun to produce substantial harm (such as leakage and structural overload);

[0103] If , an emergency treatment early warning signal is generated;

[0104] Otherwise, the rainfall monitoring process is continued.

[0105] Through the above technical solution, the embodiment provides a roof gutter drainage safety real-time evaluation and early warning method for a railway station building, which fuses real-time measured drainage flow and waterlogging depth data, and combines theoretical drainage capacity based on a hydraulic model and a preset structure safety threshold value, to construct a two-dimensional dynamic evaluation model that covers drainage efficiency and waterlogging risk, can not only early perceive the attenuation of drainage capacity through a drainage efficiency index, but also comprehensively judge the severity and urgency of the danger through a waterlogging risk index, so as to realize precise, timely, and graded early warning of emergency conditions such as gutter blockage and poor drainage during rainfall, effectively overcome the hysteresis of traditional single liquid level alarm, and provide key real-time decision support for ensuring the operation safety of the railway station building under extreme weather.

[0106] In an embodiment, the process of generating the preventive maintenance early warning signal includes:

[0107] After detecting the end of the rainfall, the system calls the time series data of the drainage risk assessment value recorded in the whole process of this rainfall, and combines the latest daily risk assessment value after the end of the rainfall to calculate and obtain a comprehensive risk assessment value;

[0108] ;

[0109] ;

[0110] ;

[0111] The comprehensive risk assessment value is obtained through formula (11)-(13) ;

[0112] , wherein For the latest daily risk assessment value after rainfall, the system immediately performs the daily risk assessment procedure in step S2 once again at the first rain-free monitoring period after rainfall, the calculated latest value is meaningful to assess the residual impact of rainfall on the gutter, such as new debris accumulation caused by rain flushing, or aggravated structural displacement due to soil erosion and water flow flushing, For the average value of the drainage risk assessment values exceeding the peak threshold value during rainfall, the higher the average value, the closer the system is to its carrying limit during rainfall, the peak threshold value is usually set slightly lower than the preset emergency risk warning threshold One value, For the stability coefficient of the drainage risk assessment value during rainfall, The higher the value, the more the drainage state fluctuates (e.g. sometimes unobstructed and sometimes obstructed), which is a typical manifestation of unstable system operation, indicating that there may be intermittent blockage or drainage capacity is in a critical state, , , For the sixth weight coefficient, which is obtained by experience setting, M is the number of drainage risk assessment values generated during rainfall, , For the kth drainage risk assessment value during rainfall, For the average value of all drainage risk assessment values during rainfall, m is the number of all drainage risk assessment values exceeding the peak threshold value during rainfall, , For the jth drainage risk assessment value exceeding the peak threshold value;

[0113] The comprehensive risk assessment value Is compared with the preset comprehensive risk warning threshold The preset comprehensive risk warning threshold Is determined according to the backtracking analysis of those events in historical data that indeed appeared functional degradation or required maintenance within a subsequent maintenance period (before the next rainy season), which corresponds to the critical point that the system is about to enter the accelerated performance degradation period;

[0114] If A preventive maintenance warning signal is generated;

[0115] Otherwise, the daily monitoring procedure is re-executed.

[0116] Through the technical scheme, the embodiment provides a long-term risk assessment method for roof gutters of railway stations, which creatively constructs a comprehensive index for comprehensively assessing long-term health of the gutters by integrating three core elements of a daily structural state, a peak pressure borne during rainfall, and stability of a drainage process after rain, and which correlates and quantitatively analyzes dynamic performance during rainfall and a daily structural state, so as to accurately identify the gutter systems that have not yet occurred emergency danger but have shown obvious performance degradation trend, and realizes a fundamental change from post-maintenance to pre-prevention, and effectively solves the core defects of early warning lag and one-sided decision-making in the prior art.

[0117] In an embodiment, the method further comprises:

[0118] S6, adaptively adjusting the preset frequency based on the daily risk assessment value;

[0119] ;

[0120] The preset frequency is obtained by formula (14) analysis and calculation ;

[0121] wherein, is a reference monitoring frequency, which is determined according to structural importance of the monitored gutter, environment, and historical data characteristics, and is a basic monitoring frequency adopted by the system at the lowest risk level or normal state, and is a basic balance point between resource consumption and monitoring demand, for example, for a key station house in a region with a lot of fallen leaves or a structure that is aging, the reference frequency can be set to a higher level, such as once every 30 minutes, and for a general station house with a clean environment and a good structure, the reference frequency can be set to a lower level, such as once every 2 hours, is an adjustment coefficient.

[0122] Through the technical scheme, the embodiment provides an intelligent monitoring method of resource adaptive optimization, which creatively realizes intelligent matching of monitoring resource input and system risk level by establishing a nonlinear dynamic correlation between the monitoring frequency and the quantitative risk assessment value, can automatically reduce the monitoring frequency when the gutter state is good, save operation and maintenance resources, and prolong the service life of equipment, and automatically increase the monitoring frequency when the risk increases, realize intensive tracking and early warning of the evolution process of hidden dangers, so as to significantly improve the intelligent level and economy of the monitoring action under the premise of ensuring system safety, and solve the problems of rigid resource allocation and low efficiency in the fixed frequency monitoring mode.

[0123] Please refer to Figure 2As shown, in one embodiment, a railway station roof gutter drainage state intelligent monitoring system is provided, characterized in that the system is used to realize a railway station roof gutter drainage state intelligent monitoring method, and the system comprises:

[0124] The acquisition module comprises a waterproof camera unit, a displacement sensing unit, a flow sensing unit, a water depth detection unit, and a rainfall detection unit, and is used to acquire internal images of the gutter, structural displacement, rainwater flow, water depth, and rainfall event raw data under various environmental conditions.

[0125] The data processing and analysis module comprises a blockage analysis unit, a structure analysis unit, a drainage efficiency analysis unit, and a waterlogging analysis unit, and is used to process and calculate the raw data transmitted by the acquisition module to obtain a blockage risk index, a structural anomaly index, a drainage efficiency index, and a waterlogging risk index, respectively.

[0126] The risk assessment and early warning module comprises a daily risk assessment unit, a drainage risk assessment unit, and a comprehensive risk assessment unit, and is used to generate three types of early warning signals, namely daily maintenance, emergency disposal, and preventive maintenance, based on the output results of the data processing and analysis module.

[0127] The mode control module is used to control the switching of the monitoring mode according to the rainfall event.

[0128] Through the above technical solution, the present embodiment provides a railway station roof gutter drainage state intelligent monitoring system, which realizes closed-loop management from data acquisition to risk decision-making by constructing a complete technical architecture comprising multi-source data acquisition, professional analysis units, and hierarchical evaluation and early warning. The system combines image recognition, structure monitoring, and hydraulic analysis to realize adaptive monitoring under different environmental conditions through the mode control module, effectively solving the problems of single traditional monitoring means and isolated data, and significantly improving the comprehensiveness, accuracy, and timeliness of gutter drainage state monitoring.

[0129] The above describes one embodiment of the present application in detail, but the content is only a preferred embodiment of the present application and cannot be considered as limiting the scope of the present application. Any equivalent changes and improvements made within the scope of the present application should still be included in the patent coverage of the present application.

Claims

1. A railway station house roof gutter drainage state intelligent monitoring method, characterized in that, The method comprises: S1, continuously collecting gutter internal image data and gutter structure displacement data under a rainfall-free state; S2, comprehensively analyzing the gutter internal image data and the gutter structure displacement data at a preset frequency to obtain a daily risk assessment value, and generating a daily maintenance warning signal when the daily risk assessment value exceeds a preset daily risk warning threshold; S3, when rainfall is detected, real-time collection of rainwater flow data and gutter water accumulation data; S4, analyzing the rainwater flow data and gutter water accumulation data to obtain a drainage risk assessment value, and generating an emergency disposal warning signal when the drainage risk assessment value exceeds a preset emergency risk warning threshold; S5, after detecting the end of rainfall, based on the time series data set of the drainage risk assessment value during the entire rainfall process, and combining the latest daily risk assessment value for comprehensive analysis, a comprehensive risk assessment value is obtained, and a preventive maintenance warning signal is generated when the comprehensive risk assessment value exceeds a preset comprehensive risk warning threshold; The process of generating the emergency disposal warning signal comprises: The drainage risk assessment value is obtained by analyzing and calculating by formulas (8)-(10) ; wherein, is a real-time drainage efficiency index, is a waterlogging risk index, , is a fourth weight coefficient, is a real-time drainage flow, h is a current gutter waterlogging depth, is a current waterlogging depth is a corresponding theoretical drainage flow, is a gutter safety waterlogging depth, is a gutter waterlogging depth of a previous monitoring period, is a time interval of adjacent monitoring periods in a rainfall state, , is a fifth weight coefficient; assessing the risk of waterlogging with a preset emergency risk warning threshold comparison; If then an emergency treatment warning signal is generated; Otherwise, continue to execute the rainfall monitoring process.

2. The intelligent monitoring method for the drainage state of a roof gutter of a railway station building according to claim 1, characterized in that, In step S2, the process of generating the daily maintenance warning signal comprises: The daily risk assessment value is obtained by formula (1) analysis calculation ; wherein, is a plugging risk index, is a structure anomaly index, , is a first weight coefficient; comparing the daily risk assessment value with a preset daily risk alert threshold are compared; If a daily maintenance warning signal is generated; Otherwise, continue to execute the daily monitoring process.

3. The intelligent monitoring method for the drainage state of a roof gutter of a railway station building according to claim 2, characterized in that, The process of obtaining the blockage risk index comprises: The plugging risk index is obtained by analyzing and calculating by formulas (2)-(4) ; wherein, is the total number of data points within the preset sliding time window, , is the debris coverage rate corresponding to the Nth monitoring point within the preset sliding time window, is the change value of the debris coverage rate within adjacent monitoring points, is the change speed of the debris coverage rate within the preset sliding time window, , , is the second weight coefficient, is the debris coverage rate corresponding to the N-1th monitoring point within the preset sliding time window, is the debris coverage rate corresponding to the ith monitoring point within the preset sliding time window, is the timestamp corresponding to the ith monitoring point within the preset sliding time window.

4. The intelligent monitoring method for the drainage state of a roof gutter of a railway station building according to claim 3, characterized in that, The process of obtaining the structure anomaly index comprises: The structural abnormality index is obtained by analyzing and calculating by formulas (5)-(7) ; wherein, is a displacement deviation value of the gutter structure within a preset sliding time window, is a displacement change rate of the gutter structure within a preset sliding time window, 、 is a third weight coefficient, is a displacement value of the gutter structure corresponding to the Nth monitoring point within a preset sliding time window, is a reference displacement value set after installation and acceptance of the gutter or after the last overhaul, is a displacement value of the gutter structure corresponding to the ith monitoring point within a preset sliding time window.

5. The intelligent monitoring method for the drainage state of a roof gutter of a railway station building according to claim 4, characterized in that, The process of generating the preventive maintenance warning signal comprises: The comprehensive risk assessment value is obtained by analyzing and calculating by formulas (11)-(13) ; wherein, is the latest daily risk assessment value after the end of the rainfall, is the average of the drainage risk assessment values that exceed the peak threshold value during the rainfall, is the stability coefficient of the drainage risk assessment values during the rainfall, , , is the sixth weight coefficient, M is the number of drainage risk assessment values generated during the rainfall, , is the kth drainage risk assessment value during the rainfall, is the average of all drainage risk assessment values during the rainfall, m is the number of all drainage risk assessment values that exceed the peak threshold value during the rainfall, , is the jth drainage risk assessment value that exceeds the peak threshold value; comprehensive risk assessment value with a preset comprehensive risk warning threshold comparison; If a preventive maintenance warning signal is generated; Otherwise, re-execute the daily monitoring process.

6. The intelligent monitoring method for the drainage state of a roof gutter of a railway station building according to claim 5, characterized in that, The method further comprises: S6, adaptively adjusting the preset frequency based on the daily risk assessment value; The preset frequency is obtained by analyzing and calculating by formula (14) ; wherein is the reference monitoring frequency, is the adjustment coefficient.

7. A railway station building roof gutter drainage state intelligent monitoring system, characterized in that, The system is used to implement the railway station roof gutter drainage state intelligent monitoring method according to any one of claims 1-6, and the system comprises: A collection module comprising a waterproof camera unit, a displacement sensing unit, a flow sensing unit, a water depth detection unit, and a rainfall detection unit, for collecting internal images, structure displacement, rainwater flow, water depth, and rainfall event original data of the gutter under various environmental conditions; A data processing and analysis module comprising a blockage analysis unit, a structure analysis unit, a drainage efficiency analysis unit, and a water accumulation analysis unit, for processing and calculating the original data transmitted by the collection module to obtain a blockage risk index, a structure anomaly index, a drainage efficiency index, and a water accumulation risk index; A risk assessment and warning module comprising a daily risk assessment unit, a drainage risk assessment unit, and a comprehensive risk assessment unit, for generating three types of warning signals of daily maintenance, emergency disposal, and preventive maintenance based on the output results of the data processing and analysis module; A mode control module for controlling the switching of the monitoring mode according to the rainfall event.

Images