Intelligent monitoring and guaranteeing method for fire-fighting water source

Abstract

The invention relates to the technical field of fire-fighting water source intelligent monitoring, in particular to a fire-fighting water source intelligent monitoring and guaranteeing method. The method comprises the following steps: monitoring a fire-fighting water source in real time, obtaining real-time data of water source operation, and further determining an initial state of the fire-fighting water source; on the basis of the initial state data, the coupling conflict condition in fire-fighting water source dispatching is recognized, the sudden stress increase of the fire-fighting pipeline structure is detected in real time in combination with the structure health monitoring technology, and the aging trend of the pipeline structure is further estimated; the pipeline sediment blocking degree and the leakage condition are evaluated according to the aging trend data, and the fire hose linkage abnormity induction condition is recognized; by analyzing fire-fighting water pipe linkage abnormity, the imbalance trend of a scheduling strategy is detected, and multi-water-source path allocation optimization is implemented; through intelligent monitoring of the fire-fighting water source, the fire-fighting water source dispatching is more accurate and efficient.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring of fire water sources, and in particular to an intelligent monitoring and guarantee method for fire water sources. BACKGROUND

[0002] Water source guarantee is a core support means for fire fighting operations, and the continuity, reliability and intelligent response capability of water supply are directly related to the success or failure of fire emergency handling. However, in the traditional fire water source scheduling and monitoring technology, there are generally problems such as insufficient real-time sensing capability, lagging structure aging identification, and fixed water source deployment strategy, especially in the collaborative scheduling process of multiple types of water sources such as fire water pools, water towers, and municipal pipe networks in the multi-source parallel water supply scene. Water pressure impact, water quantity conflict and scheduling out-of-sync problems are prone to occur, which in turn induces serious hidden dangers such as abnormal growth of fire pipe structure stress, material fatigue or pipe burst. In addition, after long-term operation of the fire pipe network, the structure aging trend is difficult to monitor in a timely manner, and problems such as internal corrosion, wall erosion and micro-crack expansion gradually accumulate, which easily forms systemic risks such as water rust deposition, nozzle blockage and local leakage. At the same time, the lack of comprehensive sensing and analysis means for water source path, flow direction, water pressure fluctuation and multi-water source linkage behavior also makes it difficult for the existing system to achieve precise scheduling and linkage optimization. However, the traditional fire water source intelligent monitoring has the problems of inaccurate estimation of the structure aging trend data of the fire pipe and inaccurate monitoring of the imbalance trend of the fire water source scheduling strategy. SUMMARY

[0003] Therefore, it is necessary to provide an intelligent monitoring and guarantee method for fire water sources to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, an intelligent monitoring and guarantee method for fire water sources comprises the following steps: Step S1: Real-time monitoring and processing of the fire water source to obtain fire water source real-time monitoring data; determining fire water source initial state data based on the fire water source real-time monitoring data; Step S2: determining fire water source scheduling coupling conflict based on the fire water source initial state data; performing fire pipe structure stress sudden increase detection based on the fire water source scheduling coupling conflict to obtain pipe structure stress sudden increase data; performing fire pipe structure aging trend estimation based on the pipe structure stress sudden increase data to obtain fire pipe structure aging trend data; Step S3: estimating pipe sediment blockage degree based on the fire pipe structure aging trend data; determining fire pipe leakage condition based on the fire pipe structure aging trend data; determining fire water pipe chain abnormality induction condition based on the fire pipe leakage condition and the pipe sediment blockage degree; Step S4: detecting the imbalance trend of the fire water source scheduling strategy based on the fire water pipe chain abnormality induction condition; based on the imbalance trend of the fire water source scheduling strategy, performing multi-source path deployment optimization processing to obtain fire water source path deployment optimization data.

[0005] The present application can realize comprehensive perception and accurate analysis of the operation state of the fire water supply system by constructing a closed-loop water source guarantee process composed of multiple steps such as real-time monitoring of fire water sources, scheduling coupling conflict identification, structure stress detection, aging trend estimation, chain abnormality analysis and path deployment optimization, which has significant technical advantages and application value. The present application can accurately construct the initial state of the fire water source by real-time acquisition of the operation state of the fire water source, dynamic identification of key data such as fire pool interconnection structure, water level change and pipe inlet pressure fluctuation, and provide a reliable foundation for subsequent scheduling strategy and risk assessment. Secondly, the system analyzes the scheduling coupling conflict in the multi-source water supply scene based on the initial state data, identifies the multi-source linkage conflict behavior caused by structure topology loss, water distribution abnormality or real-time decay, and further detects the water hammer effect and interference growth risk faced by the pipeline by combining the flow of the fire pipeline node, the abnormal superposition behavior of the water source and the frequent trend of water pressure fluctuation. Thirdly, the system identifies the sudden growth of the structure stress of the fire pipeline based on this, accurately estimates the aging trend of the fire pipeline structure by combining multi-dimensional features such as fatigue aggravation, crack propagation, structure displacement and bearing limit change, and further quantifies the reliability decay level of the pipeline. On the basis of the structure aging trend, the system can further identify the material shedding phenomenon caused by wall erosion and estimate the degree of sediment blockage and local leakage risk caused by it, establish a fire water pipe chain abnormality model by combining the two types of hidden dangers, and realize comprehensive early warning of the continuous failure induction chain of the water supply system. In addition, the system can also evaluate the change of the fire water source scheduling difficulty and the imbalance trend of the strategy according to the chain abnormality condition, dynamically optimize the multi-source path deployment strategy, and form an optimal scheduling scheme that accurately matches the water supply capacity and fire extinguishing demand. Through the above method, the present application can not only significantly improve the operation safety and scheduling response speed of the fire water source, but also effectively avoid the problem of large-area water supply failure caused by structure aging, water pressure abnormality or path conflict, and has wide adaptability and practicality in high-risk scenes such as complex buildings, industrial parks and high-rise spaces, and has good popularization and application prospect. Therefore, the present application optimizes the traditional intelligent monitoring of fire water sources, solves the problems of inaccurate estimation of fire pipeline structure aging trend data and inaccurate monitoring of imbalance trend of fire water source scheduling strategy in traditional intelligent monitoring of fire water sources, improves the accuracy of estimation of fire pipeline structure aging trend data and the accuracy of monitoring of imbalance trend of fire water source scheduling strategy. BRIEF DESCRIPTION OF DRAWINGS

[0006] Figure 1It is a kind of fire water source intelligent monitoring and safeguard method step flow schematic diagram; Figure 2 It is Figure 1 Detailed implementation step flow schematic diagram of step S2 in the embodiment; Figure 3 It is Figure 1 Detailed implementation step flow schematic diagram of step S4 in the embodiment; The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0007] The technical method of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are 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.

[0008] In addition, the accompanying drawings are only schematic illustrations of the present application, and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated description thereof will be omitted. Some block diagrams shown in the drawings are functional entities, which do not necessarily have to correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0009] It should be understood that although the terms "first", "second" and the like can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the exemplary embodiments, a first element can be called a second element, and similarly a second element can be called a first element. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0010] To achieve the above-mentioned purpose, please refer to Figures 1 to 3 A fire water source intelligent monitoring and safeguard method, comprising the following steps: Step S1: real-time monitoring and processing of the fire water source to obtain fire water source real-time monitoring data; determining the initial state data of the fire water source based on the fire water source real-time monitoring data; In the embodiment of the application, by deploying liquid level meters, water pressure transmitters, electromagnetic valve state feedback devices, flow meters and other sensor devices on the fire water pool, water tower, high-level water tank and key connecting pipe sections, a real-time sensing system covering the core area of the fire water source is constructed. Various devices operate at a sampling frequency of 2Hz, and transmit data to the local edge processing unit through industrial bus protocols (such as MODBUS-TCP or OPC-UA). The collected data includes water level, water inflow and outflow pressure, valve opening and closing state, flow data, etc. The edge processing unit is configured with a data preprocessing module to perform sliding average filtering on the original monitoring data to eliminate high-frequency interference and abnormal values. At the same time, the sensor data of various types are synchronized through timestamp alignment and spatial position indexing to generate a set of real-time monitoring data of the fire water source on a unified time axis. Based on the data set, combined with the known fire water pool and its pipe network topology drawing, the pool connection structure data is extracted, including whether each water storage unit is physically connected and the direction information of the mutual pipe connection. On this basis, further combined with the valve opening state, it is judged whether each water storage unit has water regulating capacity, the effective water regulating capacity and water regulating flow direction of the fire water pool are calculated, and the connection structure and water regulating capacity data are recorded in matrix form. On this basis, the current effective water storage capacity of each pool or connection structure unit is calculated using the following formula:

[0011] wherein is the current effective water storage capacity, in cubic meters, is the real-time liquid level height (unit: meters) of the th water storage unit, is the effective horizontal area (unit: square meters) of the th water storage unit, is the water storage unit number. In addition, according to the water pressure change value at the inlet and outlet of the pool pipe, the pressure loss of each pipe section is estimated by applying the water transmission equation, so as to obtain the pipe water regulating resistance trend and pressure difference change. All these data together constitute the initial state data of the fire water source, including the connection structure relationship matrix, the effective water regulating capacity value, the current water supply or static state of each water storage unit, the water pressure change trend and the valve control state, etc.

[0012] Step S2: determining the fire water source scheduling coupling conflict based on the initial state data of the fire water source; detecting the sudden growth of the fire pipe structure based on the fire water source scheduling coupling conflict; obtaining pipe structure sudden growth data; estimating the aging trend of the fire pipe structure based on the pipe structure sudden growth data; obtaining fire pipe structure aging trend data; In the embodiment of the present application, based on the initial state data of the fire water source obtained in step S1, the data is structured and analyzed, and the data is divided into multiple parameter sets such as the water level height of the fire pool, the pipeline inlet pressure, the interconnection structure topological relationship, and the pressure gradient between the pools. The dynamic cooperative flow relationship graph between the fire pools in the region is constructed by using parameter matching. Based on the relationship graph, combined with the flow direction time sequence of each water dispatching path in the fire dispatching plan, the shortest hydraulic path length and flow rate difference in each dispatching path are calculated by using the Dijkstra algorithm, and the abnormal pressure growth area of the dispatching intersection point caused by the flow difference is further identified, and the fire water source dispatching coupling conflict graph is constructed. In the conflict graph, the dispatching intensity (water quantity change rate per unit time) and the connection weight (hydraulic conflict degree) of different intersection points are marked to quantify the fire water source dispatching coupling conflict. Based on the above conflict, the stress response data of the same type of pipe network structure under the condition of sudden dispatching in the historical operation is collected, and the key node components (such as the turning pipe section and the interface weld) are selected for stress monitoring. The real-time strain data is collected by arranging the fiber bragg grating (FBG) stress sensor, and the stress change of the key point is calculated according to the formula:

[0013] wherein is the stress value (unit: MPa), is the elastic modulus of the pipe material (unit: GPa), is the real-time strain value (dimensionless), and the stress change of the key point is calculated. If the stress change rate in unit time exceeds the stress increase threshold value of the pipe material Δσ / Δt, it is judged that the stress has a sudden increase, and the data is recorded as the pipe structure stress sudden increase data. Then, based on the historical aging data, the aging trend index curve is established, the current stress increase data is fitted with the curve, the trend extension value is calculated by using the least square method, and the fire pipe structure aging trend data is output.

[0014] Step S3: estimating the pipe sediment blockage degree based on the fire pipe structure aging trend data; determining the fire pipe leakage condition based on the fire pipe structure aging trend data; determining the fire water pipe chain abnormal induction condition based on the fire pipe leakage condition and the pipe sediment blockage degree; In the embodiment of the present application, the structural aging trend data obtained in step S2 is taken as input, the aging grade interval is established according to the relationship between the structural fatigue index and the service life, and the fire pipe is divided into paragraphs in combination with the aging grade. The historical inner wall wear data, scour mark image and water quality impurity content of each paragraph are collected to construct a sediment generation risk factor model. The particle image velocimetry (PIV) technology is used for water flow visualization collection in the inner wall area, the local flow velocity change graph of the scour point is extracted, the time cumulative wear area data is superimposed, and the material peeling probability of each paragraph is estimated. Then, through the fluid particle concentration analysis method, the volume distribution density of particles in the pipeline is collected, the sediment accumulation amount per unit length is output in combination with the flow velocity prediction model, and the pipeline sediment blockage degree data is formed. Then, according to the aforementioned aging trend data, in combination with the crack growth rate curve, the crack length change in the structure weak point area is obtained by ultrasonic reflection detection method, and the leakage risk evaluation index is established by using the relationship between the crack propagation rate da / dN and the cyclic stress Δσ. If the crack length growth rate in a certain period is greater than the set threshold value, it is determined that the pipe segment has a leakage risk, and the fire pipe leakage condition data is output. The leakage condition data and the sediment blockage degree data are mapped in space coordinates, and if both of them exist at the same time, a chain fault induction path is established. In combination with the dispatching time sequence data, the time delay from the upstream pool dispatching start to the occurrence of the abnormality at this point is analyzed to form the fire water pipe chain abnormality induction condition data.

[0015] Step S4: detecting the imbalance trend of the fire water source scheduling strategy based on the fire water pipe chain abnormality induction condition; performing multi-water source path deployment optimization processing based on the imbalance trend of the fire water source scheduling strategy to obtain fire water source path deployment optimization data.

[0016] In the embodiment of the present application, based on the fire water pipe chain abnormality inducing condition data obtained in step S3, various abnormality inducing events are classified, and an inducing type label library is established, including: dispatch response delay triggering type, water pressure imbalance impact type, pipe closed blocking type, etc. For different types, by constructing a dispatch difficulty coefficient evaluation model, influence factors such as abnormal duration, spatial range, number of dispatch paths, etc. are introduced, and the dispatch difficulty growth score is calculated by using the weighted method. The path node whose score exceeds the set threshold will be marked as a key dispatch pressure point, which is used as the basis for dispatch strategy optimization. Subsequently, the calling frequency and response time of each water source node in the current dispatch strategy are collected, the water source dispatch curve is constructed and fitted with the dispatch difficulty growth score, if the curve fluctuation amplitude is greater than the set value, it is determined that there is a dispatch strategy imbalance trend, and the data is recorded. Next, according to the dispatch strategy imbalance trend data and the path crossing relationship between the identified abnormality inducing areas, the dispatch coverage rate decline is calculated, and the dispatch path defect type is evaluated, including path conflict type, path single type and path non-closed loop type. The above defect classification results are input into the multi-source path deployment module, the water source path feasible graph (including the calling water source node and the path accessibility) is constructed, the heuristic A* algorithm is used to find the redundant path and the alternative node in the graph, and the fire water source path deployment optimization data is output under the condition of meeting the water pressure continuity and water transfer ability constraint. The optimization data includes dispatch path ID, path length, node order, water pressure maintenance scheme and other information, which is directly input into the subsequent dispatch system.

[0017] Preferably, step S1 comprises the following steps: Step S1 comprises the following steps: Step S11: Real-time monitoring and processing of the fire water source to obtain fire water source real-time monitoring data; In the embodiment of the present application, by arranging sensor terminal nodes with IP communication function at key positions of the fire water source system, multiple indicators including fire pool water level, water quality parameters (such as turbidity, conductivity, residual chlorine concentration), water temperature, water inflow and outflow velocity, pipeline pressure, etc. are collected, and data is uniformly uploaded using RS485 bus communication protocol. The above sensors all use high-frequency sampling mechanism, collect once per minute and pack in JSON format, and are synchronously transmitted to the fire monitoring data center through the edge data collection gateway. During the collection process, the instantaneous flow rate value is obtained by using an electromagnetic flowmeter for flow rate, and the water surface to pool bottom distance is measured by using an ultrasonic water level meter, and the current water depth is obtained by presetting the pool depth conversion; the water quality parameters are collected by using a multi-parameter water quality monitor. All collected data is checked by CRC16 checking mechanism before transmission to ensure integrity. After being analyzed by the data center, the real-time monitoring data is stored in the database in the form of time stamp as input data for subsequent analysis and initial state determination. The real-time monitoring data of the fire water source obtained by the subsequent structure relationship construction and capacity analysis is a set of multi-dimensional structures, including collection time, collection location, collection index type and value, which is used to support the subsequent steps.

[0018] Step S12: determining fire pool connection structure data based on fire water source real-time monitoring data; In the embodiment of the present application, after obtaining the fire water source real-time monitoring data, the physical connection relationship between the fire pools is analyzed based on the information about flow rate, water level, water pressure, etc. in the data. By using GIS spatial coordinate information and pipeline number in CAD drawings, combined with pipeline network topology database, all pairs of pools with direct connection relationship are identified by using graph traversal algorithm. For any pool node, if there is flow rate correlation between its water outlet pipe and the water inlet pipe of another node, and the pressure difference is not zero, it is determined that the two nodes have actual hydraulic connectivity. Further, the connection structure is standardized by establishing a three-element relationship table (starting pool, ending pool, connection pipeline number). In this process, if there is a one-way valve in a connection section, the connection direction is recorded in the topology graph in the form of a directed edge to ensure the accuracy of the subsequent water transfer direction calculation. The fire pool connection structure data output by the subsequent water transfer capacity estimation and water source initial state determination is stored in the form of a two-dimensional matrix, and the matrix element (i, j) represents the connection state between the i th pool and the j th pool and the connection pipe section number, which is used to support the subsequent water transfer capacity estimation and water source initial state determination.

[0019] Step S13: determining fire pool water transfer capacity data based on fire pool connection structure data; In the embodiment of the present application, according to the fire pool connection structure data determined in step S12, the hydraulic calculation is performed on the connection pipeline between each pair of pools to evaluate the water transfer capacity. A simplified pipeline hydraulics model is used to quantitatively analyze each connection pipeline, and the formula is introduced as follows: ; Q is the adjustable water quantity per unit time (unit m³ / s), C is the flow coefficient (determined by pipe roughness and pipe length), A is the pipe cross-sectional area (unit m²), g is the acceleration of gravity (9.81 m / s²), h is the water level difference between the two pools (unit m). In actual operation, the water level difference value obtained by the foregoing monitoring data and the preset pipe section size are combined with the pipe material grade table to obtain the C value, so as to calculate the maximum water transfer capacity of each connection path one by one. The above data is stored in a three-dimensional tensor manner, with dimensions of (starting pool ID, target pool ID, water transfer capacity), and each element represents the water exchange capacity of a connected path under certain conditions. The obtained fire pool water transfer capacity data will directly participate in the subsequent hydraulic coordination analysis and initial state construction.

[0020] Step S14: determining the initial state data of the fire water source based on the fire pool connection structure data and the fire pool water transfer capacity data.

[0021] In the embodiment of the application, based on the foregoing obtained fire pool connection structure data and fire pool water transfer capacity data, the initial state of the current system of the fire water source needs to be comprehensively determined, and a fire pool network structure diagram is constructed, each fire pool is taken as a node, each connected pipeline is taken as an edge, and the weight of the edge is defined as the water transfer capacity per unit time. The network is calculated for connectivity by a network analysis algorithm (such as the Floyd-Warshall all-source shortest path algorithm), and the reachable paths of each node and the water transfer path reachability are identified. Combined with the current water level monitoring data, the distribution of water sufficient area and water deficient area is determined, and whether the water transfer capacity matches the actual demand is compared, if there is obvious imbalance (i.e. the adjustable water capacity is less than the water demand), the path is marked as a potential water supply bottleneck. Further, the node water transfer pressure index is constructed by calculating the difference between the inflow capacity and the outflow capacity of each node, the greater the index value, the more responsibility the node bears for water transfer, and the negative index indicates that it is in the water receiving state. The water transfer pressure index, connection path reachability, water level height, water quality parameter and historical water transfer success rate of all nodes are weighted and summarized to form the initial state data of the fire water source. The data is presented in a structured table form, including the current state of each pool (such as water level height, water transfer capacity level), connection path state (whether congested, water transfer direction, on-off state) and node scheduling feasibility label, as the input basic data for step S2 scheduling conflict identification and structure stress monitoring.

[0022] Preferably, step S14 comprises the following steps: Step S141: based on the fire pool interconnection structure data and the fire pool water regulating capacity data, the water level height of the fire pool is measured to obtain the fire pool water level height data; In the embodiment of the application, on the basis of obtaining the fire pool interconnection structure data and the fire pool water regulating capacity data, a high-precision ultrasonic water level measuring instrument is used to continuously monitor the internal water level of each fire pool. The ultrasonic water level meter is installed on the top of the fire pool, and the distance between the water surface and the sensor is measured by emitting sound waves and receiving reflected waves. Combined with the geometric size of the fire pool structure, the water level height in the pool is calculated. The measurement process is collected at a high frequency, at least once a minute, to reflect the dynamic changes of the water level. The measured water level height data includes time stamp, specific pool number and water level height value, and the data is transmitted to the centralized monitoring system through wired or wireless communication network. The system stores and organizes the data in real time to ensure the integrity and timeliness of the data. The fire pool water level height data obtained through this step provides key basic data support for subsequent pressure change measurement and scheduling decision, and realizes accurate grasp of the water resource status in the fire pool.

[0023] Step S142: according to the fire pool water level height data, the fire pool interconnection structure data is measured to measure the pressure change of the fire pool pipeline inlet; In the embodiment of the application, based on the fire pool water level height data obtained in step S141, the pressure change at the inlet of each pool connecting pipeline is measured and analyzed in combination with the fire pool interconnection structure data. Specifically, a pressure sensor installed at the inlet of the connecting pipeline is used to collect pressure values in real time, and the data frequency is synchronized with the water level measurement to ensure time consistency. By comparing the pressure data changes at different time points, combined with the change of the water level of the pool, the flow state and pressure fluctuation characteristics are analyzed by using the principle of fluid mechanics. The pressure sensor uses a piezoelectric element, which can accurately reflect the instantaneous change of the water pressure in the pipeline. The sensor data is transmitted to the monitoring center after analog-digital conversion. The pressure change data and the water level data are used in combination to calculate the pressure gradient and flow rate variation at the inlet of the pipeline through a pressure-water level coupling model, including indicators such as the amplitude, frequency and duration of pressure increase and decrease. This step accurately describes the pressure change at the inlet of the pipeline through dynamic pressure monitoring, and lays a foundation for further pressure fluctuation analysis.

[0024] Step S143: according to the fire pool pipeline inlet pressure change, the fire pool inlet pressure fluctuation is determined; In the embodiment of the present application, on the basis of obtaining the fire pool pipeline inlet pressure change data in step S142, the pressure fluctuation condition is determined, the pressure time sequence data is processed, the frequency component and amplitude characteristic of the pressure fluctuation are extracted by using the fast Fourier transform (FFT) technology. By analyzing the periodicity and amplitude of the pressure fluctuation, the high-frequency and low-frequency fluctuation phenomena are identified, and the strength and fluctuation range of the pressure fluctuation are quantified by combining the statistical distribution of the pressure peak value and the valley value. The pressure fluctuation condition is expressed in the form of fluctuation index and fluctuation frequency index, the fluctuation index reflects the amplitude of the pressure change, and the fluctuation frequency reflects the number of times of the pressure change. The statistical analysis result is used to determine the stability and abnormal characteristics of the pressure fluctuation, and the data structure includes time stamp, fluctuation amplitude, fluctuation frequency and fluctuation duration. The determination of the pressure fluctuation condition provides a basis for evaluating the pool cooperative working state and potential risks.

[0025] Step S144: determining the cooperative relationship data between fire pools based on the fire pool water regulating capacity data; In the embodiment of the present application, based on the fire pool water regulating capacity data, the cooperative relationship between each fire pool is determined. The operation establishes a multi-node hydraulic cooperation model, regards the fire pool as a network node, and regards the water regulating capacity as the weight of the edge between the nodes. Combined with the water regulating capacity of each connected pipeline, the water transmission capacity and scheduling response rate between nodes are calculated. By constructing a node cooperation matrix, the matrix elements reflect the direct capacity and influence range of water allocation between two pools. The node cooperative relationship is quantitatively analyzed to identify the core water regulating node and its range of action. The cooperative relationship data structure includes node pair identification, water regulating capacity value and response time parameter. This step realizes the characterization of the cooperative network characteristics between fire pools, and provides input for subsequent water pressure gradient evaluation.

[0026] Step S145: evaluating the fire pool water pressure gradient condition based on the fire pool inlet pressure fluctuation condition and the cooperative relationship data between fire pools; In the embodiment of the present application, the fire pool inlet pressure fluctuation condition obtained in step S143 and the cooperative relationship data between fire pools in step S144 are used to evaluate the fire pool water pressure gradient condition. The specific operation includes calculating the pressure difference between each pair of connected pools and its change rate with time, combining the pressure fluctuation amplitude with the cooperative water regulating capacity, and quantifying the dynamic change characteristics of the water pressure gradient. The pressure gradient index reflects the difference and change trend of the water pressure in the spatial distribution, and the pressure gradient strength is described by using a mathematical function, which can reflect the uniformity of the system pressure distribution and the water regulating cooperation effect. By dynamically monitoring the pressure gradient change, it is judged whether the system has a pressure imbalance risk. The evaluation result provides an important reference for comprehensively judging the initial state of the fire water source.

[0027] Step S146: determining the initial state data of the fire water source based on the fire pool water pressure gradient condition and the inter-fire pool coordination relationship data.

[0028] In the embodiment of the present application, the fire pool water level height data, the pipe inlet pressure fluctuation condition, the inter-fire pool coordination relationship data and the water pressure gradient condition obtained in steps S141 to S145 are integrated to construct the initial state data of the fire water source. The data integration includes normalization processing and weighted aggregation of the pool water level, water pressure fluctuation and hydraulic coordination indicators to form a multi-dimensional state vector. Through a multi-index fusion algorithm, an initial state data set describing the overall running state of the system is generated, covering the water level stability, pressure fluctuation intensity, coordination water transfer efficiency and pressure distribution balance. The output data format of the table is structured, listing the current water level, pressure fluctuation indicator, coordination relationship strength and local pressure gradient of each fire pool. Each parameter in the table has a time stamp to ensure dynamic time sequence traceability. The initial state data of the fire water source provides direct input for subsequent fire water source scheduling coupling conflict detection and pipe structure stress analysis, ensuring the continuity and accuracy of the entire monitoring and protection method.

[0029] Preferably, step S2 comprises the following steps: Step S21: determining the fire water source scheduling coupling conflict situation based on the initial state data of the fire water source; In the embodiment of the present application, based on the initial state data of the fire water source obtained in step S146, the fire water source scheduling coupling conflict situation is determined. The water level height, inlet pressure fluctuation indicator, water pressure gradient and inter-pool coordination relationship data of each fire pool in the initial state data of the fire water source are collected. By analyzing the water level difference between the pools, the pressure fluctuation synchronization and the coordination water transfer capacity, the scheduling nodes with potential conflicts are identified. Specifically, the pressure coupling principle in fluid dynamics is used in combination with the topological structure of the water pipe network to calculate the water transfer influence coefficient between the pools, and then the pressure conflict caused by the scheduling action is inferred. The pressure conflict determination criteria include pressure fluctuation amplitude exceeding a threshold value, abnormal phase difference of pressure fluctuation between adjacent pools and rapid change of water pressure gradient. In the data processing process, the time series comparison analysis method is used to compare the current monitoring data with the historical stable operation data to reveal the scheduling response delay or abnormality. The fire water source scheduling coupling conflict situation data is output through this step, including the conflict node list, conflict intensity indicator and conflict occurrence time window, providing a basis for the next step of estimating the fire water source flow burst growth.

[0030] Step S22: estimating the fire water source flow burst growth condition according to the fire water source scheduling coupling conflict situation; In the embodiment of the present application, based on the fire water source scheduling coupling conflict situation obtained in step S21, the fire water source flow burst growth condition is estimated. The specific implementation includes real-time collection of the flow sensor data of the conflict node and its surrounding pipe network, and the instantaneous gradient of the flow change is monitored. Through flow time series curve fitting, the flow mutation rate is calculated, and the flow burst growth threshold is defined as the condition that the flow growth exceeds a certain rate in a continuous time period. The derivative of the flow data is obtained by using the difference method, and the instantaneous flow change rate is obtained, and the flow burst growth index is constructed in combination with the scheduling coupling conflict intensity. The index expresses the burst degree and duration of the flow change in numerical form. Through this step, the fire water source flow burst growth condition data is obtained, which provides a key input for pipe structure stress analysis. The data format includes the flow mutation time point, burst amplitude and affected pipe number.

[0031] Step S23: fire pipe structure stress burst growth detection based on the fire water source scheduling coupling conflict situation and the fire water source flow burst growth condition, to obtain pipe structure stress burst growth data; In the embodiment of the present application, based on the fire water source scheduling coupling conflict situation of step S21 and the fire water source flow burst growth condition of step S22, the fire pipe structure stress burst growth detection is carried out. The specific operation is to install a high-sensitivity stress sensor at the key pipe node, and the sensor continuously collects the pipe stress condition, and the data includes the stress size, change rate and peak frequency. By time aligning the pipe stress data with the flow burst period, the stress burst growth event is identified. The signal filtering technology is used to eliminate environmental interference signals, so as to ensure the true reflection of the stress fluctuation. The definition of stress burst is that the pipe stress exceeds a certain proportion of the baseline stress level in a short time and lasts for more than a preset time length. The pipe structure stress burst growth data output by this step includes the stress peak value, duration, occurrence time and corresponding pipe segment information, which provides an accurate basis for subsequent pipe aging trend estimation.

[0032] Step S24: fire pipe structure aging trend estimation based on the pipe structure stress burst growth data, to obtain fire pipe structure aging trend data.

[0033] In the embodiment of the present application, based on the pipe structure stress burst growth data obtained in step S23, the fire pipe structure aging trend estimation is carried out, the cumulative damage analysis of the stress peak value and frequency is carried out in combination with the material fatigue theory, and the pipe fatigue damage index is calculated. The Miner rule is used to accumulate the damage degree caused by multiple stress cycles, and the formula is wherein is the cumulative damage value, is the actual stress cycle number, The number of cycles corresponding to the stress level of the material fatigue life. By monitoring the stress fluctuation mode and the cumulative damage history, the aging progress rate of the pipeline structure is inferred. The fatigue analysis result is verified by using the pipeline structure deformation monitoring data to ensure the accuracy of the estimation. The step outputs the fire pipeline structure aging trend data, including the fatigue damage index, the crack development probability, the structure deformation index and the predicted remaining service life, which provides a scientific basis for subsequent pipeline maintenance and scheduling optimization.

[0034] Preferably, step S21 comprises the following steps: Step S211: collecting the flow direction data of the fire water according to the initial state data of the fire water source; In the embodiment of the present application, based on the initial state data of the fire water source, the flow direction collection operation of the fire water is carried out. Specifically, high-precision flow direction sensors are installed at key nodes of the fire pipeline network to collect the direction data of the water flow in the pipeline in real time. The flow direction sensor determines the main flow direction of the pipeline by measuring the direction of the fluid flow velocity vector and combining the positional relationship of the multi-point installation using the vector synthesis method. The collected data is filtered to eliminate abnormal jump signals, ensuring the continuity and accuracy of the flow direction data. The collected data format includes time stamp, flow direction angle and sensor position identifier. By comparing the flow direction data at different time points, the flow direction change rule is analyzed to form complete fire water flow direction data, which provides basic input for subsequent analysis of the complexity of the pipe network connection relationship. After the implementation of this step, the output fire water flow direction data will be directly used as the input data of step S212, ensuring the integrity of the step connection.

[0035] Step S212: determining the complexity of the fire water pipe connection relationship based on the fire water flow direction data; In the embodiment of the present application, based on the fire water flow direction data obtained in step S211, the complexity of the fire water pipe connection relationship is determined. The flow direction data is mapped to the topology graph of the fire pipeline network, and the flow path network of the pipeline nodes and pipeline connection edges is constructed to calculate the node degree, loop number and cross connection point number in the network. The complexity of the connection relationship is quantified by using the complex network indicators in graph theory, such as node degree distribution, clustering coefficient and path redundancy. The complexity calculation process includes counting the number of changes in the inflow and outflow directions of each node and the number of loop interactions, reflecting the flow diversity of the water flow in the pipe network. This process uses the flow vector analysis algorithm to interpret the flow direction data, realizing the structured quantitative description of the connection relationship. The analysis result is the complexity data of the fire water pipe connection relationship, including the number of connection nodes, the flow direction change area and the key cross point information. This data is an important basis for step S213 to evaluate the missing topology relationship.

[0036] Step S213: evaluate the missing condition of the water pipe structure topology relationship according to the complexity degree of the fire water pipe connection relationship; In the embodiment of the application, the missing condition of the water pipe structure topology relationship is evaluated according to the complexity degree data of the fire water pipe connection relationship in step S212. Specifically, by comparing the known fire pipe network design topology structure with the measured flow direction network structure, the difference analysis method is used to identify the missing or abnormal part in the connection relationship. The identification of the missing condition relies on the graph structure comparison technology, which matches the nodes and edges in the design graph with the topology graph formed by the measured flow direction, and locates the missing nodes, edge breaks or connection abnormal areas. In the evaluation process, the network connectivity analysis index is applied to detect potential chain breaks or blind area phenomena, and reflect the structural integrity. The evaluation result generates the water pipe structure topology relationship missing condition data, including the missing node list, missing edge segment position and influence range information. This data provides key parameters for the judgment of the fire water source scheduling coupling conflict, and ensures the comprehensive grasp of the pipe network structure state.

[0037] Step S214: determine the delay degree of the fire water source scheduling strategy according to the fire water source initial state data; In the embodiment of the application, the delay degree of the fire water source scheduling strategy is determined based on the fire water source initial state data. The specific operation involves time synchronization collection and analysis of the scheduling instruction sending time and the actual scheduling response time. By comparing the scheduling instruction time stamp issued by the fire water source monitoring system with the flow and pressure change time monitored in the pipe network system, the time delay of the scheduling response is calculated. Using time series data analysis method, each scheduling command and the corresponding water flow change event are paired, the response delay time is measured, and the scheduling time delay database is established. The delay degree of the scheduling strategy is expressed in the form of average delay time and delay distribution characteristics, describing the response efficiency of the scheduling system. This data is used for real-time decay evaluation in step S215, to ensure the time accuracy in the scheduling execution process is quantified.

[0038] Step S215: evaluate the real-time decay of the fire water source scheduling based on the delay degree of the fire water source scheduling strategy, and obtain the real-time decay of the fire water source scheduling; In the embodiment of the present application, based on the scheduling strategy delay degree determined in step S214, the real-time attenuation evaluation of fire water source scheduling is carried out, and the real-time attenuation situation of fire water source scheduling is obtained. The evaluation process adopts time delay cumulative analysis to quantify the response time cumulative effect of each link in the scheduling system. By constructing a scheduling execution time link model, the transmission and execution time delay of each node scheduling command is analyzed, and the scheduling real-time index of the overall system is calculated. The index takes the standard deviation and maximum delay of time delay as the quantitative parameters, reflecting the stability and consistency of the scheduling process. Through long-term monitoring data analysis, the decline trend of the real-time of the scheduling system is revealed, and the scheduling real-time attenuation situation data is formed. The data reflects the response lag situation of the system in actual operation, and provides dynamic time performance basis for scheduling coupling conflict judgment.

[0039] Step S216: determining the fire water source scheduling coupling conflict situation according to the fire water source scheduling real-time attenuation situation and the water pipe structure topological relationship missing situation.

[0040] In the embodiment of the present application, based on the fire water source scheduling real-time attenuation situation obtained in step S215 and the water pipe structure topological relationship missing situation in step S213, the fire water source scheduling coupling conflict situation is determined. The specific operation is to construct a multi-dimensional coupling analysis model, combine the scheduling real-time parameters with the pipe network topological integrity index, and identify the conflict. The correlation between scheduling command delay and pipe network structure missing is identified by using multivariate statistical analysis method, and the abnormal water flow and pressure fluctuation phenomenon caused by the failure of scheduling command to accurately conduct is revealed. Through threshold judgment strategy, the time window and influence range of coupling conflict occurrence are determined. The fire water source scheduling coupling conflict situation data including conflict node, conflict intensity and conflict duration is output. The data is directly fed back to the subsequent flow abnormality estimation and pipe stress detection steps, ensuring that the links of the whole monitoring and guarantee method are closely connected, and the continuity and accuracy of data transmission are guaranteed.

[0041] Preferably, step S217 includes the following steps: identifying the fire water pipe blind area according to the water pipe structure topological relationship missing situation, so as to obtain fire water pipe blind area data; In the embodiment of the present application, according to the water pipe structure topological relationship missing situation data, the fire water pipe blind area identification is carried out. Specifically, by comparing the designed pipe network topological structure with the actual operation monitoring data, the existing water supply breakpoints or connection missing areas in the network are identified. The real-time flow and pressure data collected by the flow sensor and pressure sensor installed at the key nodes of the pipe network are used in combination with the topological missing information to identify the areas with extremely low water supply flow or abnormal pressure through breakpoint detection algorithm, and the areas are determined as water supply blind areas. The obtained fire water pipe blind area data includes the geographic location, area range, node and pipe segment information in the blind area, which serves as the basic input for subsequent water distribution abnormality detection.

[0042] Fire water pipe water distribution anomaly detection is performed based on the fire water pipe water supply blind area data, so as to obtain fire water pipe water distribution anomaly data; In the embodiment of the application, based on the above-mentioned fire water pipe water supply blind area data, fire water pipe water distribution anomaly detection is performed. By comparing the normal water demand of each partition of the pipe network with the actual monitored water supply, a water distribution deviation index is calculated. This process involves statistical analysis of the flow data of each node in the pipe, and uses a difference analysis method to identify abnormal water distribution phenomena, such as local water supply shortage or excessive water supply. Combined with pressure data, the severity of the abnormal position is further confirmed, and fire water pipe water distribution anomaly data is obtained, including abnormal nodes, abnormal amplitude and abnormal time period, which provides a quantitative basis for multi-source linkage out-of-step estimation.

[0043] According to the real-time attenuation of fire water source scheduling and the fire water pipe water distribution anomaly data, the multi-source linkage out-of-step condition of the fire water source is estimated; In the embodiment of the application, according to the real-time attenuation of fire water source scheduling data and the fire water pipe water distribution anomaly data, the multi-source linkage out-of-step condition of the fire water source is estimated. The specific method is to establish a time sequence correlation model between scheduling response time delay and water supply anomaly, analyze the water fluctuation and pressure instability phenomenon caused by the inconsistency of each source response in multi-source linkage, and reflect the failure degree of the collaborative work between multiple water sources through the calculation of linkage out-of-step index. The calculation of this index is based on the synchronous analysis of the flow and pressure monitoring data of multiple water sources, and the deviation of different water sources in scheduling response time and supply effect is determined, forming fire water source multi-source linkage out-of-step condition data.

[0044] Based on the multi-source linkage out-of-step condition of the fire water source, the frequent occurrence condition of the fire water source scheduling conflict is determined; In the embodiment of the application, based on the above-mentioned multi-source linkage out-of-step condition, the frequent occurrence condition of the fire water source scheduling conflict is determined. This step identifies the time period and region of the frequent occurrence of scheduling conflicts by statistically analyzing the occurrence frequency and duration of multi-source linkage out-of-step events, combining historical scheduling conflict records, and using frequency analysis method. The output data includes conflict nodes, conflict times and time distribution, which provides a basis for comprehensive judgment of the coupling conflict of fire water source scheduling.

[0045] According to the fire water source scheduling conflict frequent occurrence condition and the fire water source multi-source linkage out-of-step condition, the coupling conflict condition of the fire water source scheduling is determined.

[0046] In the embodiment of the present application, according to the frequent occurrence of fire water source scheduling conflict and the out-of-step situation of fire water source multi-source linkage, the fire water source scheduling coupling conflict situation is comprehensively determined. The comprehensive determination confirms the coupling conflict problems existing in the scheduling process by correlating and analyzing the frequent conflict events and the linkage out-of-step index. The output fire water source scheduling coupling conflict situation data lists the position, intensity and duration of the conflict in detail, and provides input data for the subsequent pipeline stress detection and aging trend estimation steps. The data of each step is related to each other, ensuring the continuity and data integrity of the monitoring and protection method.

[0047] Preferably, step S23 comprises the following steps: Step S231: Estimate the fire pipeline node water source against situation according to the fire water source scheduling coupling conflict situation; In the embodiment of the present application, based on the fire water source scheduling coupling conflict situation, the real-time flow and pressure data of each key node in the fire pipeline network are collected, and the fire pipeline node water source against situation is estimated by analyzing the water flow direction, flow size and pressure change characteristics at the node. The specific operation includes that the multi-point flow meter and pressure sensor are arranged at the key nodes of the pipeline network, the fluid dynamic data are continuously collected, the pipeline topological structure is combined, and the vector flow analysis method is used to identify the mutual conflict situation of water flow at the node. The analysis judges whether there is water flow reversal or pressure mutual offset phenomenon by comparing the time sequence of the node flow direction and pressure mutation, and then locates the against node and evaluates the against intensity, outputs the fire pipeline node water source against situation data as the input basis for the subsequent abnormal superposition detection.

[0048] Step S232: Detect the fire pipeline water source abnormal superposition situation according to the fire pipeline node water source against situation and the fire water source scheduling coupling conflict situation; In the embodiment of the present application, according to the fire pipeline node water source against situation data obtained in step S231 and the fire water source scheduling coupling conflict situation, the fire pipeline water source abnormal superposition situation is detected. This step uses time series statistical method to accumulate the superposition influence of abnormal flow and pressure events by comprehensively analyzing the against intensity of each node and the scheduling conflict frequency. A multi-dimensional abnormal scoring system is adopted to compare the node abnormal data with the scheduling conflict time points, calculate the abnormal superposition index, and clearly reflect the fire pipeline water source abnormal superposition situation data of the concentrated area of water source abnormality in space and time, which provides a basis for water pressure fluctuation trend monitoring.

[0049] Step S233: Detect the frequent trend of fire pipeline water pressure fluctuation based on the fire pipeline water source abnormal superposition situation; In the embodiment of the present application, based on the abnormal superposition condition data of the fire pipeline water source, the frequent trend of water pressure fluctuation in the pipeline is monitored. By installing high-precision pressure sensors at multiple positions of the pipeline, time series data of pressure fluctuation is collected, combined with abnormal superposition condition, frequency, amplitude and duration characteristics of water pressure fluctuation are identified by using signal processing techniques such as spectrum analysis and wavelet transform. By comparing the pressure fluctuation characteristics of the abnormal event period, the fluctuation frequent area and trend are determined. The data is used to indicate the pressure stability condition in the pipeline system, and provides support for subsequent water hammer effect analysis.

[0050] Step S234: estimating the growth condition of fire water pipe water hammer effect based on the frequent trend of fire pipeline water pressure fluctuation and the abnormal superposition condition of fire pipeline water source; In the embodiment of the present application, the growth condition of water hammer effect in the fire pipeline is estimated in combination with the frequent trend of water pressure fluctuation detected in step S233 and the abnormal superposition condition of the fire pipeline water source. A water hammer pressure estimation method based on the principle of fluid mechanics is used to quantitatively analyze the internal pressure change of the pipeline. The specific operation includes collecting physical parameters of the pipeline, such as pipe diameter, pipe material characteristics, pipeline length and internal flow rate, which directly affect the pressure wave propagation speed and amplitude. The pressure fluctuation data collected by the pressure sensor installed at the key node of the pipeline is used, and the amplitude and frequency change of the pressure pulse are particularly focused on. The increment of water hammer pressure is estimated by numerical calculation. The dynamic pressure change in the pipe network is captured in real time by using the pressure fluctuation monitoring equipment, and the time sequence distribution of the pressure peak value and its repetition frequency are analyzed, so as to reveal the growth trend of the water hammer effect. The calculation process is based on the water hammer pressure formula, combined with the pipeline parameters, which can accurately reflect the pressure impact change caused by the sudden stop, start or flow direction mutation of fluid flow. Through continuous monitoring and trend analysis of the characteristics of the pressure pulse, the increment and development rate of the water hammer pressure are quantified, and the severity and frequency change of the pipeline impacted by the water hammer are judged. The quantitative analysis result directly reflects the aggravation of the pressure impact in the pipeline, and provides a scientific basis for subsequent evaluation of the growth of the fire pipeline disturbance and the change of the structural stress, ensuring the accuracy and timeliness of the pipeline operation state monitoring.

[0051] Step S235: determining the disturbance growth condition of the fire pipeline based on the growth condition of the fire water pipe water hammer effect and the frequent trend of the fire pipeline water pressure fluctuation; In the embodiment of the present application, based on the growth condition of water hammer effect and the frequent trend of water pressure fluctuation, the interference growth of the fire pipeline is determined, and the water hammer pressure peak and its distribution characteristics in time and space in the pipe network need to be analyzed in detail. Through the pressure sensor arranged at the key nodes of the pipeline, real-time water pressure data is collected, and high sampling frequency is used to ensure the capture of the instantaneous peak of water hammer effect and its fluctuation frequency. Combined with the pipe network structure information, including the specific position of pipe diameter change, pipeline joint and valve, the amplification or buffering effect of these structure nodes on pressure fluctuation is comprehensively considered, and the dynamic change of the stress of the pipeline at each position is evaluated. Through time domain and frequency domain analysis of the pressure signal, the water hammer pressure peak, pressure fluctuation frequency and pressure wave propagation path and other key parameters are extracted, so as to reflect the intensity of water hammer impact and its influence range on the pipeline system. At the same time, the structural health monitoring sensors such as accelerometers and vibration sensors installed on the surface of the pipeline are used to monitor the vibration response of the pipeline under the action of water hammer pressure in real time. Through the frequency spectrum analysis of the collected vibration signal, the vibration frequency component and its change trend with time are identified, and the mutation and duration of vibration amplitude are determined by combining the time domain signal analysis, so as to accurately reveal the dynamic interference enhancement phenomenon caused by water hammer effect. The water hammer pressure analysis result and the vibration response data are associated and analyzed, and the interference growth of the fire pipeline is comprehensively evaluated, which is specifically manifested as the dynamic stress increase of the pipeline structure and the interference growth data of the fire pipeline generated by the strengthening of vibration energy, which reflects in detail the influence of water hammer effect on the structural performance of the pipeline system. It is an important basic data for subsequent pipeline structure stress burst growth detection and aging trend estimation, and guarantees the safe and stable operation of the fire pipeline network.

[0052] Step S236: detecting the burst growth of the fire pipeline structure stress based on the interference growth of the fire pipeline, to obtain the burst growth data of the pipeline structure stress.

[0053] In the embodiment of the present application, the fire pipeline interference growth data obtained in step S235 is used to detect the sudden increase of the fire pipeline structure stress. A plurality of structure health monitoring devices, mainly including high-sensitivity strain gauges and vibration sensors, need to be arranged at the key nodes of the pipeline. The installation positions of these sensors need to be reasonably selected according to the pipeline structure characteristics and stress analysis results to ensure that the areas prone to interference and stress concentration in the pipeline can be covered. Through the real-time data acquisition system of the sensors, the stress changes and vibration responses of the pipeline during operation are continuously monitored. The data acquisition frequency should be high enough to capture the instantaneous and rapidly changing stress peaks and vibration signals. The collected stress and vibration data are fused and analyzed with the fire pipeline interference growth data obtained in step S235. A threshold alarm mechanism is used to identify and locate the stress mutation that exceeds the predetermined safety threshold. The abnormal detection algorithm uses time series data anomaly identification technology, including sliding window analysis, peak detection and frequency domain analysis methods, to determine the occurrence time and specific location of the sudden increase of the structure stress. Specifically, by comparing the real-time stress signal with the historical normal operation data, the abnormal sudden increase of the stress fluctuation is identified. The interference source and influence range are confirmed by the spectrum change in the vibration signal. The detection result forms the structure stress sudden increase data, which specifically represents the stress peaks and their change trends at different time points and spatial positions, accurately reflecting the dynamic load impact on the pipeline structure. This stress sudden increase data is not only used for real-time monitoring of the structural safety state of the fire pipeline, but also serves as a key input parameter for the estimation of the fire water pipe structure aging trend, supporting the subsequent maintenance and repair decisions, and ensuring the stable operation and safety of the fire water supply system.

[0054] Preferably, step S24 comprises the following steps: Step S241: determining the fire water pipe structure fatigue aggravation condition according to the pipeline structure stress sudden increase data; In the embodiment of the present application, the pipeline structure stress data collected is analyzed in detail to determine the fire water pipe structure fatigue aggravation condition. The stress data is obtained by strain gauges and stress sensors installed at key nodes, which reflect the internal and external force changes of the pipeline in real time. By comparing the stress peaks and their cumulative times at different time periods, the fatigue damage accumulation theory is used to calculate the fatigue cumulative damage degree of the pipeline material, thereby determining the degree of fatigue aggravation. The fatigue aggravation condition is specifically manifested as the increase of stress cycle times and the change of peak stress amplitude. Combined with the fatigue limit parameters of the material, the fatigue aggravation index is output, providing basic data for subsequent crack growth trend detection.

[0055] Step S242: detecting the fire water pipe structure crack growth trend based on the fire water pipe structure fatigue aggravation condition; In the embodiment of the present application, based on the aforementioned fatigue aggravation, the crack growth trend of the fire water pipe structure is further detected. By arranging ultrasonic detection instruments and crack sensors, periodic detection is implemented at positions prone to fatigue cracks such as the pipe surface and key welding points, and parameters such as crack length, width and expansion speed are captured. By using the fatigue crack expansion theory and combining the fatigue aggravation data of step S241, the growth rate and expansion trend of the crack are evaluated. During the detection process, the crack morphology is scanned in three dimensions by a multi-point sensor array, time series data of crack growth are formed, a detailed crack expansion curve is formed, crack growth trend data are obtained, and early warning of potential pipe damage is ensured.

[0056] Step S243: detecting the displacement growth condition of the fire pipe according to the pipe structure stress burst growth data; In the embodiment of the present application, the displacement growth condition of the fire pipe is detected according to the pipe structure stress burst growth data. By installing high-precision displacement sensors and laser ranging equipment at key nodes of the pipe structure, the micro-deformation and overall displacement of the pipe are monitored in real time. The data acquisition device captures the time sequence of displacement, combines the time and amplitude of stress burst growth, and analyzes the synchronous response of displacement. By using data fusion technology to correlate stress and displacement data, the trend of plastic deformation or structural loosening of the pipe is identified. This step obtains quantitative data of pipe displacement growth, revealing the deformation condition of the pipe caused by stress changes.

[0057] Step S244: fire pipe structure deformation monitoring is performed according to the displacement growth condition of the fire pipe and the crack growth trend of the fire water pipe structure, and fire pipe structure deformation data are obtained; In the embodiment of the present application, based on the pipe displacement growth condition of step S243 and the crack growth trend of step S242, fire pipe structure deformation monitoring is performed. By comprehensively analyzing the spatial distribution of crack expansion and displacement change, a pipe structure deformation monitoring network is formed using a multi-sensor integrated system. This system includes stress sensors, crack sensors and displacement sensors, and the collected data is processed by time synchronization to build a three-dimensional dynamic model of pipe deformation. By focusing on analyzing the strain concentration area and crack expansion area in the model, complete fire pipe structure deformation data are output, the range, trend and severity of structural deformation are clarified, and data basis is provided for subsequent bearing limit detection.

[0058] Step S245: pipe bearing limit detection is performed on the fire pipe structure deformation data according to the pipe structure stress burst growth data, and fire pipe bearing limit data are obtained; In the embodiment of the present application, based on the sudden increase in stress of the pipeline structure and the structural deformation data obtained in step S244, the pipeline carrying limit detection is carried out. By using the theories of material mechanics and structural mechanics, combined with the actual measured stress and deformation data, the carrying capacity of the pipeline structure is calculated. By using the nonlinear finite element analysis method, the limit carrying state of the pipeline under the current stress and deformation conditions is simulated, and the probability of the pipeline reaching or exceeding the design carrying limit is evaluated. The carrying limit data reflects the maximum safe load that the pipeline structure can bear, and combined with the fatigue and crack conditions, the safety margin of the pipeline is judged.

[0059] Step S246: estimating the aging trend of the fire pipeline structure according to the fire pipeline carrying limit data to obtain the fire pipeline structure aging trend data.

[0060] In the embodiment of the present application, the aging trend of the fire pipeline structure is estimated according to the fire pipeline carrying limit data of step S245. By analyzing the change trend of the carrying limit, combined with the structural fatigue accumulation and crack propagation data, a structural aging evolution model is established. Based on the historical monitoring data and the current carrying capacity, the model predicts the structural performance degradation in a certain period in the future. The aging trend data provides a quantitative evaluation of the remaining life of the structure by quantifying the performance degradation rate of the pipeline, and provides a scientific basis for the pipeline maintenance and replacement plan. After this step is completed, the complete fire pipeline structure aging trend data is formed, which provides key technical support for the entire fire water source intelligent monitoring and protection system.

[0061] Preferably, step S3 comprises the following steps: Step S31: determining the intensified erosion condition of the inner wall of the fire pipeline according to the sudden increase in flow of the fire water source; In the embodiment of the present application, in the specific implementation of determining the intensified erosion condition of the inner wall of the fire pipeline according to the sudden increase in flow of the fire water source, based on the monitored flow sudden increase data in the fire water source dispatching system, the amplitude, duration and frequency of the flow change are identified. By using the flow sensor and pressure sensor data, the instantaneous change of the fluid velocity inside the pipeline is calculated, and then the shear force change of the pipeline wall surface is calculated. The intensified erosion of the inner wall of the pipeline is mainly manifested as the accelerated wear of the wall surface caused by the violent fluctuation of the fluid velocity. Combined with the wear resistance performance parameters and the duration wear curve of the pipeline material, the wear rate under the current flow rate and shear force condition is quantitatively calculated, and the intensified erosion index is obtained. By comparing the historical wear data, the specific time period and position of the intensified erosion are confirmed, and the intensified erosion condition of the inner wall of the fire pipeline is output, which provides basic data for the next step of structural aging estimation.

[0062] Step S32: estimating the material shedding condition of the fire pipeline structure according to the intensified erosion condition of the inner wall of the fire pipeline to obtain the fire pipeline structure aging trend data; In the embodiment of the present application, according to the erosion intensification condition of the inner wall of the fire pipeline obtained in step S31, the structure material shedding condition of the fire pipeline is estimated based on the structure aging trend data. In this step, surface detection technology such as acoustic wave detection and infrared thermal imaging is used in combination with microwave or ultrasonic reflection technology to scan the inner wall of the pipeline and the surface of the pipeline to detect material layer peeling, cracking and corrosion phenomena. The range and severity of material shedding are quantitatively evaluated by using the erosion intensification index and the detected material damage position and area information. The shedding information is fused and analyzed with the structure aging trend data to form a complete material shedding state description, and fire pipeline structure material shedding data is generated to provide a basis for subsequent sediment blockage and material strength analysis.

[0063] Step S33: estimating the pipeline sediment blockage degree according to the structure material shedding condition of the fire pipeline; In the embodiment of the present application, the pipeline sediment blockage degree is analyzed based on the structure material shedding condition of the fire pipeline estimated in step S32. The thickness, distribution range and density of the sediment and other parameters are collected in real time by optical scanners and ultrasonic detection devices installed inside the pipeline. The sediment blockage degree is calculated from the ratio of the sediment volume to the effective flow area of the pipeline. In combination with the material shedding data, the sediment accumulation area caused by the shedding material is identified, and the influence of the sediment on the pipeline flow and pressure is analyzed. The continuous monitoring data is used to dynamically track the change trend of the blockage degree, and pipeline sediment blockage degree data is formed to provide input for pipeline leakage risk assessment.

[0064] Step S34: estimating the material strength attenuation trend of the fire pipeline based on the structure material shedding condition of the fire pipeline; In the embodiment of the present application, the material strength attenuation trend of the fire pipeline is estimated based on the structure material shedding condition of the fire pipeline. The material fatigue and corrosion performance indicators are used in combination with the material performance monitoring results on site to establish a material strength degradation model by combining the shedding position and area information. The weakening rate of the material strength is calculated by using the long-term monitored material mechanical property data, especially the changes of the elastic modulus, yield strength and fracture toughness. The material strength attenuation trend is output by combining the temperature, humidity and chemical corrosion factors in the pipeline working environment to comprehensively evaluate the material strength attenuation trend, thereby providing a quantitative basis for rupture estimation.

[0065] Step S35: fire pipeline rupture estimation according to the material strength attenuation trend of the fire pipeline, to obtain fire pipeline rupture data; In the embodiment of the present application, according to the material strength attenuation trend evaluated in step S34, fire pipeline rupture estimation is implemented to obtain fire pipeline rupture data. The rupture estimation is simulated by finite element analysis technology on the current structure state of the pipeline, and the material strength parameters, wall thickness changes and internal and external pressure data are input. According to the stress concentration area and strength degradation, the position and time window of the pipeline rupture are predicted. Combined with historical failure data and field monitoring data, the pipeline rupture risk level and critical rupture point are confirmed. The rupture estimation result takes the rupture probability, rupture position and rupture time as the core data to form the fire pipeline rupture data to support the subsequent leakage condition determination.

[0066] Step S36: determining the fire pipeline leakage condition according to the fire pipeline rupture data; In the embodiment of the present application, the fire pipeline leakage condition is determined according to the fire pipeline rupture data obtained in step S35. By arranging pressure sensors and flow meters in the key rupture risk area, abnormal pressure drop and abnormal flow change are monitored. The sound wave detection technology is used to detect the leakage sound wave signal, and the leakage position, leakage rate and leakage area are determined combined with the field sensor data. The rupture estimation data and real-time sensor data are combined to identify and locate the pipeline leakage event to form the fire pipeline leakage condition data to ensure timely monitoring and evaluation of the leakage event.

[0067] Step S37: determining the fire water pipe chain abnormality induction condition based on the fire pipeline leakage condition and the pipeline sediment blockage degree.

[0068] In the embodiment of the present application, based on the fire pipeline leakage condition of step S36 and the pipeline sediment blockage degree of step S33, the fire water pipe chain abnormality induction condition is determined. By establishing a pipe network chain response model, the linkage influence of leakage and blockage on the water pressure, water flow velocity and water quality of adjacent pipe sections is analyzed. The propagation path and potential induction mechanism of abnormal events in the pipe network are identified by using historical failure linkage data combined with current monitoring data. Through dynamic simulation, the diffusion trend of abnormal events and the secondary failures caused are evaluated, and the fire water pipe chain abnormality induction data is output to form a whole monitoring and early warning system of pipe network abnormal events, ensuring the integrity and reliability of intelligent monitoring and protection of fire water sources.

[0069] Preferably, step S4 comprises the following steps: Step S41: detecting the growth of fire water source scheduling difficulty based on the fire water pipe chain abnormality induction condition; In the embodiment of the present application, based on the abnormal induction of fire water pipe interlocking, the related data of abnormal induction of fire water pipe interlocking are collected in specific implementation, including the frequency of abnormal events, the influence range and the duration. The real-time pressure and flow change data of key nodes in the pipe network are obtained by using pressure sensors and flow sensors, and the influence degree of abnormal events on the fire water source scheduling system is evaluated by combining the time and space distribution of interlocking abnormal events through time series analysis method. Further, the complexity index of scheduling operation is calculated by combining the structure topology of the pipe network and the historical scheduling record, reflecting the difficulties and challenges in the current scheduling process. Through the above analysis, the growth data of fire water source scheduling difficulty is obtained, which reflects the increase of scheduling control complexity caused by pipe network abnormal events, and provides a basis for subsequent scheduling strategy adjustment.

[0070] Step S42: detecting the imbalance trend of fire water source scheduling strategy according to the growth of fire water source scheduling difficulty; In the embodiment of the present application, the imbalance trend of fire water source scheduling strategy is detected by dynamically monitoring the key parameters in the scheduling process according to the growth of fire water source scheduling difficulty obtained in step S41. Specifically, it includes real-time analysis of response delay of scheduling instruction execution, imbalance degree of flow distribution and abnormal fluctuation of pressure regulation. The deviation and abnormality in the execution process of scheduling strategy are identified by comparing the historical normal scheduling state with the current data by using statistical analysis method. The difference between scheduling command and actual pipe network feedback is analyzed by combining the scheduling log data collected by the automatic monitoring system, the amplitude and development trend of strategy imbalance are quantified, and the imbalance trend data of fire water source scheduling strategy is formed, which provides accurate monitoring basis for strategy optimization.

[0071] Step S43: fire water source scheduling defect evaluation is performed according to the growth of fire water source scheduling difficulty and the imbalance trend of fire water source scheduling strategy, and fire water source scheduling defect data is obtained; In the embodiment of the present application, the comprehensive evaluation of fire water source scheduling defect is performed based on the growth of fire water source scheduling difficulty and the imbalance trend of scheduling strategy obtained in steps S41 and S42. The current scheduling system is comprehensively diagnosed by constructing a scheduling performance evaluation index system, covering scheduling response time, pressure stability, flow distribution efficiency and abnormal event recovery ability. The scheduling difficulty growth and strategy imbalance trend data are input into the evaluation model by using multi-dimensional data fusion technology, and the severity of scheduling defect and potential risk area are quantified. The pipe network operation risk and system stability problem caused by scheduling defect are analyzed, and the fire water source scheduling defect data is output, which provides a scientific basis for optimizing scheduling scheme and improving system robustness.

[0072] Step S44: multi-source path deployment optimization processing is performed based on the fire water source scheduling defect data, and fire water source path deployment optimization data is obtained.

[0073] In the embodiments of the present application, the scheduling defect data of the fire water source obtained by step S43 is used to carry out optimization processing of multi-source path allocation. According to the analysis result of the defect data, the regions with scheduling bottlenecks and unreasonable path configuration are identified, and the multi-source linkage allocation scheme is formulated in combination with the pipe network topology structure and the water source supply capacity. The water supply path and flow distribution scheme of different water sources are calculated by an optimization algorithm to ensure the pressure balance and reasonable flow distribution in the scheduling process. The scheme is dynamically adjusted in combination with the real-time monitoring data in the optimization process to ensure the flexibility and emergency response capability of the water source allocation path. The fire water source path allocation optimization data is generated to support the intelligent management and efficient operation of the pipe network scheduling and ensure the reliable guarantee of the fire water source system.

[0074] The above description is merely a specific implementation of the present application, which enables those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. The present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A fire water source intelligent monitoring and protection method, characterized in that: The following steps are involved: Step S1: Perform real-time monitoring and processing on the fire water source to obtain real-time monitoring data of the fire water source; Determine the initial state data of the fire water source based on the real-time monitoring data of the fire water source; Step S2: determining the fire water source scheduling coupling conflict situation based on the fire water source initial state data; Based on the coupling conflict of fire water source scheduling, the sudden growth of fire pipe structure stress is detected to obtain the sudden growth data of pipeline structure stress; The fire protection pipeline structure aging trend is estimated based on the sudden growth data of pipeline structure stress, and the fire protection pipeline structure aging trend data is obtained; Step S3: estimating the degree of pipe sediment blockage based on the fire pipe structure aging trend data; determining the fire pipe leakage status based on the fire pipe structure aging trend data; and determining the fire water pipe chain abnormality induction based on the fire pipe leakage status and the degree of pipe sediment blockage; Step S4: detecting the imbalance trend of the fire water source dispatching strategy based on the fire water pipe interlocking abnormality induction situation; Based on the imbalance trend of fire water source scheduling strategy, multi-water source path allocation optimization processing is carried out to obtain fire water source path allocation optimization data.

2. The fire water source intelligent monitoring and protection method according to claim 1 is characterized in that: Step S1 includes the following steps: Step S11: performing real-time monitoring processing on the fire water source to obtain real-time monitoring data of the fire water source; Step S12: determining the fire water pool interconnection structure data based on the real-time monitoring data of the fire water source; Step S13: determining the water transfer capacity data of the fire water pool based on the fire water pool interconnection structure data; Step S14: Determine the fire water source initial state data based on the fire water pool interconnection structure data and the fire water pool water transfer capacity data.

3. The fire water source intelligent monitoring and protection method according to claim 2 is characterized in that: Step S14 includes the following steps: Step S141: measuring the water level of the fire water pool based on the fire water pool interconnection structure data and the fire water pool water transfer capacity data to obtain the water level data of the fire water pool; Step S142: measuring the pressure change of the fire water pool pipe inlet according to the fire water pool water level data and the fire water pool connection structure data; Step S143: determining the pressure fluctuation at the fire water pool inlet according to the pressure change at the fire water pool pipeline inlet; Step S144: determining the coordination relationship data between fire water tanks based on the water transfer capacity data of the fire water tanks; Step S145: evaluating the water pressure gradient of the fire water pool based on the synergy relationship data between the fire water pools based on the pressure fluctuation of the fire water pool inlet; Step S146: Determine the initial state data of the fire water source based on the water pressure gradient status of the fire water pool and the collaborative relationship data between the fire water pools.

4. The fire water source intelligent monitoring and protection method according to claim 1 is characterized in that: Step S2 includes the following steps: Step S21: determining the fire water source scheduling coupling conflict situation based on the fire water source initial state data; Step S22: estimating the sudden growth of fire water source flow according to the fire water source scheduling coupling conflict situation; Step S23: performing a sudden increase detection of fire pipe structure stress based on the fire water source scheduling coupling conflict situation and the fire water source flow sudden increase situation, and obtaining pipeline structure stress sudden increase data; Step S24: estimating the fire protection pipeline structure aging trend based on the pipeline structure stress burst growth data to obtain fire protection pipeline structure aging trend data.

5. The fire water source intelligent monitoring and protection method according to claim 4 is characterized in that: Step S21 includes the following steps: Step S211: collecting the fire water flow direction data based on the fire water source initial state data to obtain the fire water flow direction data; Step S212: determining the complexity of the fire water pipe connection relationship based on the fire water flow direction data; Step S213: evaluating the topological relationship missing status of the fire water pipe structure according to the complexity of the fire water pipe connection relationship; Step S214: determining the degree of delay of the fire water source dispatching strategy based on the fire water source initial state data; Step S215: performing a fire water source scheduling real-time attenuation assessment based on the fire water source scheduling strategy delay degree to obtain the fire water source scheduling real-time attenuation situation; Step S216: Determine the fire water source scheduling coupling conflict situation based on the fire water source scheduling real-time attenuation situation and the water pipe structure topology relationship missing situation.

6. The fire water source intelligent monitoring and protection method according to claim 5 is characterized in that: Step S217 includes the following steps: According to the missing topological relationship of the water pipe structure, the blind area of ​​the fire water pipe supply is identified to obtain the blind area data of the fire water pipe supply; Fire water pipe water distribution anomaly detection is performed based on the fire water pipe water supply blind area data, thereby obtaining fire water pipe water distribution anomaly data; Estimate the out-of-sync status of multi-source linkage of fire water sources based on the real-time attenuation of fire water source dispatch and abnormal data on water volume distribution of fire water pipes; Determine the frequent occurrence of fire water source scheduling conflicts based on the out-of-sync situation of multiple fire water source linkage; The fire water source scheduling coupling conflict situation is determined based on the frequent occurrence of fire water source scheduling conflicts and the loss of synchronization of multiple fire water source linkages.

7. The fire water source intelligent monitoring and protection method according to claim 4 is characterized in that: Step S23 includes the following steps: Step S231: estimating the water source hedging status of the fire pipeline node according to the fire water source scheduling coupling conflict situation; Step S232: detecting the abnormal superposition of fire pipeline water sources based on the water source counterbalancing status of fire pipeline nodes and the fire water source scheduling coupling conflict status; Step S233: detecting a frequent fluctuation trend of water pressure in the fire protection pipeline based on the superposition of abnormal water source conditions in the fire protection pipeline; Step S234: estimating the growth of the water hammer effect in the fire pipe according to the frequent fluctuation trend of the water pressure in the fire pipe and the superposition of abnormal water sources in the fire pipe; Step S235: determining the growth of fire pipe interference based on the growth of the water hammer effect of the fire pipe and the frequent fluctuation trend of the water pressure in the fire pipe; Step S236: Performing a sudden growth detection of the fire pipeline structure stress based on the fire pipeline interference growth condition to obtain pipeline structure stress sudden growth data.

8. The fire water source intelligent monitoring and protection method according to claim 4 is characterized in that: Step S24 includes the following steps: Step S241: determining the aggravation of fatigue of the fire water pipe structure according to the sudden increase data of the pipeline structure stress; Step S242: detecting a crack growth trend of the fire water pipe structure based on the aggravated fatigue of the fire water pipe structure; Step S243: detecting the displacement growth status of the fire protection pipeline based on the pipeline structure stress sudden growth data; Step S244: monitoring the deformation of the fire pipe structure according to the displacement growth status of the fire pipe and the growth trend of the cracks in the fire water pipe structure to obtain the deformation data of the fire pipe structure; Step S245: performing pipeline bearing limit detection on the fire protection pipeline structure deformation data according to the pipeline structure stress sudden growth data to obtain the fire protection pipeline bearing limit data; Step S246: Estimating the fire pipeline structure aging trend based on the fire pipeline bearing limit data to obtain fire pipeline structure aging trend data.

9. The fire water source intelligent monitoring and protection method according to claim 1 is characterized in that: Step S3 includes the following steps: Step S31: determining the intensified scouring condition of the inner wall of the fire protection pipe according to the sudden increase in the flow rate of the fire protection water source; Step S32: estimating the material shedding condition of the fire protection pipe structure based on the fire protection pipe structure aging trend data according to the intensified scouring condition of the fire protection pipe inner wall; Step S33: estimating the degree of pipe sediment blockage based on the shedding of fire pipe structural material; Step S34: evaluating the fire protection pipeline material strength attenuation trend based on the fire protection pipeline structural material shedding condition; Step S35: estimating fire pipe rupture based on the fire pipe material strength attenuation trend to obtain fire pipe rupture data; Step S36: determining the fire protection pipeline leakage status based on the fire protection pipeline rupture data; Step S37: Determine the fire water pipe chain abnormality induction situation based on the fire pipe leakage situation and the pipe sediment blockage degree.

10. The fire water source intelligent monitoring and protection method according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: estimating the increasing difficulty of fire water source dispatching based on the fire water pipe interlocking abnormality induction situation detection; Step S42: detecting the imbalance trend of the fire water source dispatching strategy according to the increase in the difficulty of fire water source dispatching; Step S43: performing a fire water source scheduling defect assessment based on the fire water source scheduling difficulty increase and the fire water source scheduling strategy imbalance trend to obtain fire water source scheduling defect data; Step S44: Perform multi-water source path allocation optimization processing based on the fire water source scheduling defect data to obtain fire water source path allocation optimization data.

Images