A large-scale IoT model system and method for emergency monitoring of fire water pressure in smart cities

Abstract

This invention provides a large-scale IoT model system and method for emergency monitoring of fire-fighting water pressure in smart cities, relating to the field of fire-fighting water pressure monitoring. The large-scale IoT model system includes an emergency monitoring management platform configured to execute this method. The method includes: determining the location of water supply anomalies based on sensor data at preset locations within the fire-fighting pipeline network; determining the type of water supply anomaly based on sensor data at the location of the anomaly; determining boosting parameters and / or maintenance parameters based on the location and type of the anomaly; generating boosting instructions including key boosting nodes and preset water pressure based on the boosting parameters; and generating maintenance instructions including maintenance location and maintenance actions based on the maintenance parameters. This invention can improve the accuracy, timeliness, and intelligence level of urban fire-fighting water pressure management.

Description

Technical Field

[0001] This manual relates to the field of fire water pressure monitoring, and in particular to a smart city fire water pressure emergency monitoring IoT large-scale model system and method. Background Technology

[0002] With the development of smart city construction, real-time monitoring and emergency response of fire water pressure are becoming increasingly important for public safety. Currently, some urban fire water pressure monitoring systems have basic data acquisition and remote monitoring capabilities, which can reflect the operational status of fire pipelines to a certain extent. However, facing the complex and ever-changing urban operating environment, such as different building functions, seasonal changes, pedestrian flow fluctuations, and special events, existing systems are not accurate enough in perceiving and judging the operational status, and lack the ability to deeply integrate and dynamically adapt to multi-source environmental factors, resulting in delays in anomaly identification and emergency response.

[0003] Therefore, there is a need to provide a smart city fire water pressure emergency monitoring IoT big data model system and method, which can improve the accuracy, timeliness and intelligence level of urban fire water pressure management. Summary of the Invention

[0004] To address the problem of accurately and promptly identifying the operational status of fire protection pipelines, this invention provides a smart city fire water pressure emergency monitoring IoT large-scale model system and method.

[0005] The invention includes a smart city fire water pressure emergency monitoring IoT large-scale model system, the system including an emergency monitoring management platform configured to execute a smart city fire water pressure emergency monitoring method.

[0006] The invention includes a smart city fire water pressure emergency monitoring method, executed by an emergency monitoring management platform within a smart city fire water pressure emergency monitoring IoT big data model system. The method includes: determining the location of an abnormal water supply based on sensor data at preset locations within the fire pipeline network; determining the type of water supply anomaly at the abnormal location based on the sensor data; determining boosting parameters and / or maintenance parameters based on the abnormal location and the type of anomaly; generating a boosting command including a key boosting node and a preset water pressure based on the boosting parameters, wherein the boosting command is configured to control the corresponding fire pump at the key boosting node to adjust the water pressure to the preset water pressure at the key boosting node; and generating a maintenance command including a maintenance location and a maintenance action based on the maintenance parameters, wherein the maintenance command is configured to control a maintenance robot to move to the maintenance location and perform the maintenance action on the abnormal fire pump.

[0007] The beneficial effects of the above invention include, but are not limited to: (1) By determining the location and type of water supply anomaly, and automatically generating a boosting command containing the key boosting node and preset water pressure, or a maintenance command containing the maintenance location and maintenance action, the full-process automated emergency response from anomaly monitoring, intelligent diagnosis to precise handling is realized, improving the timeliness, accuracy and intelligence level of fire water pressure supervision; (2) By combining the performance characteristics of the corresponding fire pump of the key node and its distance from the key node, the jurisdiction intensity of the fire pump on the key node is determined, and the abnormal interval is determined based on the jurisdiction intensity, scene characteristics and time period characteristics, so that the setting of the abnormal interval not only considers external environmental factors, but also integrates equipment capabilities, improving the accuracy of anomaly judgment; (3) By combining the similarity analysis of the municipal water supply fluctuation curve and the sensor fluctuation curve, the preliminarily determined abnormal key node is verified a second time, which can effectively distinguish between normal data fluctuations caused by external municipal water supply fluctuations and real water supply anomalies, thereby accurately correcting the location of water supply anomalies, improving the accuracy of anomaly identification, and reducing false alarms and missed alarms. Attached Figure Description

[0008] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting; in these embodiments, the same reference numerals denote the same structures, wherein:

[0009] Figure 1 This is a schematic diagram of the platform structure of a smart city fire water pressure emergency monitoring IoT large model system according to some embodiments of this specification; Figure 2 This is an exemplary flowchart of a smart city fire-fighting water pressure emergency monitoring method according to some embodiments of this specification; Figure 3 This is an exemplary schematic diagram illustrating the determination of the abnormal interval corresponding to the key node according to some embodiments of this specification; Figure 4 This is an exemplary flowchart illustrating the re-determination of critical abnormal nodes according to some embodiments of this specification; Figure 5 This is an exemplary flowchart illustrating the determination of boost parameters according to some embodiments of this specification. Detailed Implementation

[0010] The accompanying drawings used in the description of the embodiments will be briefly introduced below. The drawings do not represent all embodiments.

[0011] The terms “system,” “device,” “unit,” and / or “module” as used herein are a method of distinguishing different components, elements, parts, sections, or assemblies at different levels. If other terms can achieve the same purpose, they may be replaced with other expressions.

[0012] Unless the context clearly indicates an exception, words such as "a," "an," "a kind," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0013] In the embodiments described in this specification, the order of the steps is interchangeable unless otherwise specified, and steps may be omitted. Other steps may also be included in the operation process.

[0014] Figure 1 This is a schematic diagram of the platform structure of a smart city fire water pressure emergency monitoring IoT large-scale model system according to some embodiments of this specification.

[0015] In some embodiments, such as Figure 1 As shown, the smart city fire water pressure emergency monitoring IoT large model system 100 may include an emergency monitoring user platform 110, an emergency monitoring service platform 120, an emergency monitoring management platform 130, an emergency monitoring sensor network platform 140, and an emergency monitoring perception and control platform 150.

[0016] The Emergency Supervision User Platform 110 refers to a platform that interacts with users (such as supervisors and citizens), including terminal devices. These include devices with input and / or output functions, such as mobile devices, tablets, and consoles. The Emergency Supervision User Platform 110 can interact bidirectionally with the Emergency Supervision Service Platform 120.

[0017] The emergency monitoring service platform 120 refers to an interactive service platform for receiving and transmitting data, including servers, gateways, and routers. The emergency monitoring service platform 120 can interact bidirectionally with the emergency monitoring management platform 130.

[0018] The emergency monitoring and management platform 130 refers to a comprehensive platform for processing and managing emergency monitoring data, which may include processors and / or servers, storage devices, etc.

[0019] In some embodiments, the emergency monitoring and management platform 130 can be configured to execute a smart city fire water pressure emergency monitoring method. More information about this method can be found in [link to relevant documentation]. Figure 2 Related descriptions.

[0020] The emergency monitoring sensor network platform 140 refers to a platform used for the comprehensive management of sensor information, and can be configured as a communication network and / or gateway, etc. The emergency monitoring sensor network platform 140 can interact bidirectionally with the emergency monitoring management platform 130 and the emergency monitoring perception and control platform 150.

[0021] The emergency monitoring and control platform 150 refers to a platform for emergency monitoring data acquisition, monitoring information generation, and control information execution. In some embodiments, the emergency monitoring and control platform 150 may include various devices, such as fire pumps, sensors, and maintenance robots. More information about fire pumps, sensors, and maintenance robots can be found in Figure 2 and its related description.

[0022] For more information about the above platforms, please see the following: Figures 2 to 5 And its related descriptions.

[0023] In some embodiments, the smart city fire water pressure emergency monitoring IoT big data system 100 may further include a processor, which can process data and / or information related to the smart city fire water pressure emergency monitoring IoT big data system 100. In some embodiments, the processor may include one or more sub-processing devices. By way of example only, the processor may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or any combination thereof.

[0024] In some embodiments, the processor can interact with multiple platforms included in the smart city fire water pressure emergency monitoring IoT big data model system 100, or can be configured on multiple platforms.

[0025] In some embodiments of this specification, the Smart City Fire Water Pressure Emergency Monitoring IoT Big Data Model System 100 can form a closed-loop information operation among various functional platforms, coordinating and operating systematically. It can automatically and intelligently realize emergency monitoring of urban fire water pressure, effectively improving emergency response speed and the reliability of urban fire water supply by real-time monitoring of urban fire water pressure and automatically generating emergency measures. Simultaneously, the use of the IoT big data model makes data fusion, analysis, and decision-making more efficient and comprehensive.

[0026] Figure 2 This is an exemplary flowchart illustrating a smart city fire-fighting water pressure emergency monitoring method according to some embodiments of this specification. Figure 2 As shown, process 200 includes the following steps. In some embodiments, process 200 may be executed by an emergency monitoring and management platform in a smart city fire water pressure emergency monitoring IoT big data model system, for example, by a processor.

[0027] Step S210: Determine the location of water supply anomalies based on sensor data at preset locations within the fire protection pipeline network.

[0028] Preset locations refer to the locations within the fire protection piping network that need to be monitored. In some embodiments, preset locations include critical nodes and fire pumps.

[0029] Critical nodes refer to key locations in the fire protection pipeline network used for monitoring water supply safety. For example, critical nodes may include the inlet of the main water inlet pipe connecting the municipal water supply to the fire protection pipeline network, the liquid level monitoring location and pressure monitoring location of the fire water tank or water tank, the inlet of the fire water supply branch pipe in each fire compartment, and the outlet of the fire hydrant or the end of the sprinkler head that is farthest from the fire pump, highest in location, or has the greatest resistance in multiple fire compartments.

[0030] Sensor data refers to monitoring data that characterizes the status of fire protection piping networks. In some embodiments, sensor data at preset locations may include hydraulic data of key nodes and operating data of fire pumps.

[0031] Hydraulic data for critical nodes can include water pressure and flow rate data.

[0032] Operating data for fire pumps can include pump body current, pump vibration data, bearing temperature, pump outlet pressure, pump outlet flow rate, and pump speed.

[0033] In some embodiments, sensing data at a preset location can be obtained using sensors deployed at the preset location. These sensors may include pressure sensors, flow sensors, temperature sensors, current sensors, vibration sensors, speed sensors, etc.

[0034] An abnormal water supply location refers to a location in the fire protection network where sensor data is abnormal. In some embodiments, abnormal water supply locations include abnormal critical nodes and abnormal fire pumps.

[0035] Anomaly-critical nodes refer to critical nodes where hydraulic data is abnormal. Anomaly-critical fire pumps refer to fire pumps with abnormal operating data.

[0036] In some embodiments, the processor can determine the location of water supply anomalies in various ways based on sensor data at preset locations within the fire protection pipe network. For example, sensor data anomaly can refer to the sensor data being within an abnormal range; that is, when one or more sensor data at a preset location are within the corresponding abnormal range, then that preset location is a water supply anomaly location.

[0037] An abnormal range refers to the numerical range used to determine abnormal sensor data. In some embodiments, the abnormal range may include abnormal water pressure range, abnormal flow rate range, abnormal pump body current range, abnormal pump vibration data range, abnormal bearing temperature range, abnormal pump outlet pressure range, abnormal pump outlet flow rate range, abnormal pump speed range, etc.

[0038] For example, critical nodes where water pressure data is in the abnormal water pressure range and / or flow rate data is in the abnormal flow rate range are considered abnormal critical nodes. Fire pumps that meet one or more of the following conditions are considered abnormal fire pumps: bearing temperature is in the bearing temperature range, pump body current is in the abnormal pump body current range, pump vibration data is in the abnormal pump vibration data range, pump outlet flow rate is in the abnormal pump outlet flow rate range, pump speed is in the abnormal pump speed range, and pump outlet pressure is in the abnormal pump outlet pressure range.

[0039] Each preset location has its own corresponding anomaly range, and each type of sensor data has its own corresponding anomaly range. For example, the water pressure anomaly range for key node A1 is... The abnormal traffic range of critical node A1 is: The abnormal water pressure range at critical node A2 is as follows: The abnormal bearing temperature range of fire pump B1 is as follows: wait.

[0040] In some embodiments, the abnormal range can be preset manually based on experience, and the preset abnormal range can be recorded as the standard abnormal range.

[0041] In some embodiments, the processor can determine the abnormal interval corresponding to the preset location based on scene features and time period features of the preset location.

[0042] Scene features refer to characteristic information related to the environment of a preset location. For example, scene information may include building type, pedestrian density, etc. Building type may include commercial area, factory, residential area, etc.

[0043] Time-period characteristics refer to time-related feature information that affects the operational status of a preset location. For example, time-period characteristics may include the current season, whether it is during a specific event period, and the specific type of event. Being during a specific event period is marked as 1, and not being during a specific event period is marked as 0. Specific event types may include sports meets, concerts, holidays, etc.

[0044] In some embodiments, the processor can determine the abnormal interval based on scene features and time period features of a preset location through various methods. For example, the processor can determine the abnormal interval by querying a scenario configuration library based on scene features and time period features of a preset location.

[0045] In some embodiments, the scenario configuration library can be constructed based on clustering analysis methods. For example, the processor can construct multiple cluster vectors, each cluster vector consisting of historical scene features and historical time period features of a historical water supply anomaly location. The historical water supply anomaly locations include historical critical nodes and historical fire pumps where water supply anomalies have occurred in the fire hydrant network. Multiple cluster vectors are clustered to obtain multiple clusters. For each cluster, based on the anomaly data in the historical sensor data corresponding to all historical water supply anomaly locations within the cluster, the historical anomaly range of each type of sensor data within the cluster is statistically determined. Based on each historical anomaly range, the anomaly interval corresponding to each type of sensor data within the cluster is determined. The anomaly interval determined above is used as the anomaly interval corresponding to all cluster vectors in the cluster. That is, the scenario configuration library can be constructed through the above process.

[0046] In this specification, only two abnormal situations—insufficient water pressure and / or insufficient flow—are considered for critical nodes. Therefore, the historical water supply anomaly locations corresponding to the clustering vectors used for clustering are selected from historical anomaly critical nodes with insufficient water pressure and / or insufficient flow, and abnormal fire pumps with one or more of the above-mentioned abnormal operating data. The specific abnormal data for each historical water supply anomaly location has been pre-labeled.

[0047] For example, a certain cluster contains 500 cluster vectors composed of historical scene features and historical time period features of 500 historically anomalous key nodes. The historical water pressure data of 400 historically anomalous key nodes are considered anomalous data, with the minimum and maximum values ​​being... and Then, the water pressure anomaly intervals corresponding to all cluster vectors in this cluster are: Historical traffic data for 450 historically abnormal key nodes is considered abnormal. The minimum and maximum values ​​among these nodes are as follows: and Then, the traffic anomaly intervals corresponding to all cluster vectors in this cluster are: Similarly, the abnormal intervals corresponding to each type of sensor data are determined, and all clustering vectors in the cluster correspond to the abnormal intervals determined by the above process.

[0048] In some embodiments, the processor can determine the jurisdiction intensity of the corresponding fire pump of a critical node based on the performance characteristics of the corresponding fire pump of the critical node and the distance between the corresponding fire pump and the critical node; and determine the abnormal interval corresponding to the critical node based on the scene characteristics of the critical node, the time period characteristics of the critical node, and the jurisdiction intensity of the corresponding fire pump of the critical node. For more information on this part, please refer to... Figure 3 Related descriptions.

[0049] By combining the scene characteristics and time period characteristics of preset locations, abnormal intervals are determined, making the anomaly judgment more in line with the actual operating environment. This improves the accuracy and adaptability of abnormal interval settings, effectively reduces false alarms and missed alarms, and enhances the intelligent supervision capabilities in complex urban environments.

[0050] Step S220: Based on the sensor data of the abnormal water supply location, determine the type of water supply abnormality at the abnormal water supply location.

[0051] Water supply anomaly type refers to the specific category of water supply anomaly. Water supply anomaly types can include insufficient water pressure, water pump failure to start, blown fuse, loose wiring, impeller jamming, insufficient lubrication, etc.

[0052] In some embodiments, the processor can determine the type of water supply anomaly at the location of the water supply anomaly through various methods based on sensor data at the location of the water supply anomaly.

[0053] For example, if the location of the water supply anomaly is an anomaly critical node, the processor can directly determine the type of water supply anomaly based on the hydraulic data of the anomaly critical node. For instance, if the water pressure data of the anomaly critical node is in the water pressure anomaly range (or below the lower limit of the water pressure anomaly range), or if the water pressure data is in the water pressure anomaly range and the flow rate data is in the flow rate anomaly range (because the flow rate is usually also abnormal when the water pressure is abnormal), then the water supply anomaly type of the anomaly critical node is insufficient water pressure.

[0054] For example, if the abnormal water supply location is an abnormal fire pump, the processor can construct a feature vector based on the hydraulic data within the water supply range of the abnormal fire pump and the operating data of the abnormal fire pump. Based on the feature vector, it can search the vector database to obtain the reference vector with the highest similarity to the feature vector, and determine the label corresponding to the reference vector as the water supply abnormality type corresponding to the abnormal fire pump.

[0055] The vector database comprises multiple reference vectors and corresponding labels. Each reference vector is constructed from historical hydraulic data within the supply range of a historically anomalous fire pump and its historical operational data. The corresponding label represents the actual type of water supply anomaly of that fire pump. The supply range of the fire pump can be pre-defined manually, and the hydraulic data within that range can be the average of the hydraulic data from all key nodes within that range. Similarity can be determined based on vector distance, including Euclidean distance, etc.

[0056] Step S230: Determine booster parameters and / or maintenance parameters based on the location and type of water supply anomaly.

[0057] Boosting parameters refer to the parameters used to address water supply anomalies during boosting operations. For example, boosting parameters may include key boosting nodes, the corresponding fire pumps for these key nodes, and preset water pressures.

[0058] A pressurization critical node refers to a key node in the fire protection pipe network that requires pressurization. Pressurization critical nodes are classified as abnormally critical nodes.

[0059] The corresponding fire pump for a critical node refers to the fire pump that supplies water to the critical node. Each critical node has one corresponding fire pump. The corresponding fire pump for a critical node can be pre-set manually based on the physical structure of the fire hydrant network and the water supply path relationships.

[0060] The fire pump corresponding to the key pressurization node is the fire pump that supplies water to the key pressurization node.

[0061] The preset water pressure refers to the target water pressure value set to restore the normal water supply capacity of the fire protection pipe network.

[0062] Maintenance parameters refer to the relevant parameters used in maintenance operations to resolve water supply anomalies. For example, maintenance parameters may include maintenance location and maintenance actions.

[0063] The maintenance location refers to the location of the abnormal fire pump that needs maintenance.

[0064] Maintenance actions refer to the repair methods corresponding to the malfunctions of abnormal fire pumps. For example, malfunctions of abnormal fire pumps may include blown fuses, loose motor wiring, insufficient lubrication, impeller jamming, etc. Maintenance actions may include replacing fuses, tightening motor wiring, adding lubricant, and removing foreign objects from the impeller.

[0065] In some embodiments, the processor can determine booster parameters and / or maintenance parameters in various ways based on the location and type of water supply anomaly. For example, the processor can determine the booster parameters and / or maintenance parameters by querying a first preset table based on the location and type of water supply anomaly. The first preset table may include the correspondence between the location and type of water supply anomaly and the booster parameters and / or maintenance parameters. The first preset table may be pre-constructed manually based on historical data and / or historical experience.

[0066] Step S240: Based on the pressurization parameters, generate a pressurization command including key pressurization nodes and preset water pressure.

[0067] In some embodiments, the processor can generate multiple candidate parameters for pressurization; construct a water supply map based on a preset location, sensor data at the preset location, locations of water supply anomalies, and types of water supply anomalies; for each candidate parameter for pressurization, determine its influence characteristics and pressurization effect based on the water supply map and a control model; and determine the pressurization parameter based on the influence characteristics and pressurization effects of multiple candidate parameters. For more information on this part, please refer to [link to relevant documentation]. Figure 5 Related descriptions.

[0068] A boost command is a command used to control boost operation.

[0069] In some embodiments, the boosting command is configured to control the corresponding fire pump at the boosting critical node to adjust the water pressure to a preset water pressure at the boosting critical node.

[0070] In some embodiments, the processor can generate pressurization instructions, including pressurization key nodes and preset water pressure, based on pressurization parameters and according to a preset instruction template.

[0071] Step S250: Based on the maintenance parameters, generate maintenance instructions including maintenance location and maintenance actions.

[0072] A maintenance instruction is a command used to control maintenance operations.

[0073] In some embodiments, the maintenance command is configured to control a maintenance robot to move to a maintenance location and perform maintenance actions on the malfunctioning fire pump.

[0074] A maintenance robot is a robot used to perform maintenance actions. Based on maintenance commands, a maintenance robot can move to a maintenance location and perform maintenance actions on malfunctioning fire pumps to resolve the faults.

[0075] In some embodiments, the processor can generate maintenance instructions, including maintenance location and maintenance actions, based on maintenance parameters and according to a preset instruction template.

[0076] By identifying the location and type of water supply anomalies, and automatically generating boosting commands that include key boosting nodes and preset water pressures, or maintenance commands that include maintenance locations and actions, the system achieves fully automated emergency response from anomaly monitoring and intelligent diagnosis to precise handling, thereby improving the timeliness, accuracy, and intelligence of fire water pressure monitoring.

[0077] Figure 3 This is an exemplary schematic diagram illustrating the determination of the abnormal interval corresponding to the key node according to some embodiments of this specification.

[0078] In some embodiments, the preset locations include critical nodes and fire pumps, such as Figure 3As shown, the processor can also determine the jurisdiction intensity 330 of the corresponding fire pump of the key node based on the performance characteristics 310 of the corresponding fire pump of the key node and the distance 320 between the corresponding fire pump of the key node and the key node; and determine the abnormal interval 360 corresponding to the key node based on the scene characteristics 340 of the key node, the time period characteristics 350 of the key node and the jurisdiction intensity 330 of the corresponding fire pump of the key node.

[0079] For more information on key nodes, fire pumps, corresponding fire pumps for key nodes, scene characteristics, and time-related characteristics, please refer to [link / reference needed]. Figure 2 Related descriptions in Chinese.

[0080] Performance characteristics refer to parameters that measure the long-term reliability of a fire pump. In some embodiments, performance characteristics can be represented by the ratio of the fire pump's historical normal operating time to its historical total operating time. Normal operating time means that the fire pump's operating data is normal (e.g., not within the corresponding abnormal range), and the historical normal operating time and historical total operating time can be obtained based on historical records.

[0081] The distance between the corresponding fire pump and the critical node can refer to the length of the pipeline between the corresponding fire pump and the critical node, which can be obtained based on the engineering structure diagram of the fire pipeline network.

[0082] The jurisdiction intensity of the corresponding fire pump at a critical node is an indicator that measures the water supply capacity of the corresponding fire pump to that critical node. Jurisdiction intensity can be expressed numerically; the higher the value, the greater the jurisdiction intensity, and the stronger the water supply capacity of the corresponding fire pump to the critical node.

[0083] In some embodiments, the processor can determine the jurisdiction intensity of a corresponding fire pump based on its performance characteristics and the distance between the fire pump and the critical node through various methods. For example, the processor can normalize the performance characteristics of the fire pump corresponding to the critical node and the distance between the fire pump and the critical node, and then perform a weighted summation to determine the jurisdiction intensity of the fire pump corresponding to the critical node. The weighting coefficients for the weighted summation can be set manually based on experience, with the weighting coefficient for distance being negative and the weighting coefficient for performance characteristics being positive. The normalization methods can include, but are not limited to, Min-Max normalization, Z-score normalization, etc.

[0084] In some embodiments, the sensing data at the preset location includes the operating data of the fire pump, and the jurisdiction intensity of the corresponding fire pump at the critical node is related to the operating data of the corresponding fire pump at the critical node.

[0085] More information on fire pump operating data can be found at [link to relevant documentation]. Figure 2Related descriptions. For more information on jurisdictional strength, please refer to the preceding text and its related descriptions.

[0086] In some embodiments, when the pump outlet pressure or pump outlet flow rate is lower in the operating data, the operating status of the fire pump is worse, and the long-distance water supply capability of the fire pump is weaker. Therefore, the absolute weight of the distance between the corresponding fire pump and the critical node should be increased so that the jurisdiction intensity of the corresponding fire pump of the critical node is smaller, that is, the lower the pump outlet pressure or pump outlet flow rate, the smaller the jurisdiction intensity.

[0087] By linking the jurisdiction intensity of the corresponding fire pumps at key nodes with their operating data, the jurisdiction intensity can be dynamically reduced when the operating status of the fire pumps is abnormal, even if the fire pumps have been performing well for a long time. This allows for reasonable adjustment of the abnormal range and avoids underestimating the risk of remote water supply due to reliance on fire pumps in poor condition.

[0088] In some embodiments, the processor can determine the abnormal interval corresponding to a key node by querying a scenario configuration library based on the scene characteristics, time period characteristics, and jurisdiction intensity of the corresponding fire pump of the key node. The scenario configuration library may include the scene characteristics, time period characteristics, and the correspondence between the jurisdiction intensity and abnormal interval of the key node's corresponding fire pump. For the construction of the scenario configuration library, please refer to step S210 and its related description; jurisdiction intensity only needs to be added when constructing the clustering vector.

[0089] By combining the performance characteristics of the corresponding fire pumps at key nodes and their distance from the key nodes, the jurisdiction intensity of the fire pumps over the key nodes is determined. Based on the jurisdiction intensity, scene characteristics, and time period characteristics, abnormal intervals are determined. This ensures that the setting of abnormal intervals not only considers external environmental factors but also integrates equipment capabilities, thereby improving the accuracy of anomaly judgment.

[0090] Figure 4 This is an exemplary flowchart illustrating the re-determination of critical abnormal nodes according to some embodiments of this specification. Figure 4 As shown, process 400 includes the following steps. In some embodiments, process 400 may be executed by an emergency monitoring and management platform in a smart city fire water pressure emergency monitoring IoT big data model system, for example, by a processor.

[0091] In some embodiments, the sensor data at the preset location includes hydraulic data of key nodes, and the abnormal water supply location includes abnormal key nodes and abnormal fire pumps.

[0092] For more information on hydraulic data, critical abnormal nodes, and abnormal fire pumps, please refer to [link / reference needed]. Figure 2 Related descriptions.

[0093] Step S410: Based on municipal water supply parameters, determine the water supply fluctuation curve of abnormal critical nodes.

[0094] Municipal water supply parameters refer to relevant parameters of the current water supply provided by the municipal authorities. For example, municipal water supply parameters may include the most recently updated water pressure and flow rate. These parameters can be entered manually or obtained through a processor connected to the relevant municipal platform.

[0095] The water supply fluctuation curve refers to the curve showing the expected changes in hydraulic data at key points within a preset time period. Expected hydraulic data refers to hydraulic data under normal conditions (no abnormalities in water supply), including expected water pressure data and expected flow rate data.

[0096] A preset time period refers to a period between the time when the municipal water supply parameters were last updated by the municipal department and the current time. In some embodiments, the preset time period can be set manually based on experience. For example, the preset time period could be 3 minutes after the time when the municipal department last updated the municipal water supply parameters.

[0097] In some embodiments, each key node has a corresponding water supply fluctuation curve. The horizontal axis of the water supply fluctuation curve represents time, and the vertical axis represents the expected hydraulic data of the key node. The water supply fluctuation curve can be fitted by multiple coordinate points, where each coordinate point represents the expected water pressure or expected flow rate data of the key node at a predetermined time point within a preset time period. The fitting algorithm may include, but is not limited to, least squares method, polynomial regression, etc.

[0098] In some embodiments, for each critical abnormal node, the processor can determine the corresponding water supply fluctuation curve based on municipal water supply parameters through various methods.

[0099] For example, for a critical node, the processor can construct multiple clustering vectors based on various historical municipal water supply parameters under normal water supply conditions. Each clustering vector is associated with the historical water supply fluctuation curve of the critical node within a historical time period. The historical time period is the same as a preset time period, such as 3 minutes after the update time of the corresponding historical municipal water supply parameters. The historical water supply fluctuation curve can be fitted by multiple historical coordinate points, where each historical coordinate point represents the actual water pressure or actual flow data of the critical node at a historical time point within the historical time period.

[0100] For an abnormal critical node, the processor constructs multiple clustering vectors using the above method and constructs a target vector based on the current municipal water supply parameters. It performs clustering analysis on all clustering vectors and the target vector to generate multiple clusters. The cluster to which the target vector belongs is determined as the target cluster. The average curve of the historical water supply fluctuation curves associated with all clustering vectors in the target cluster is used as the water supply fluctuation curve of the abnormal critical node.

[0101] The average curve can be obtained by aligning multiple historical water supply fluctuation curves over time and averaging them point by point. Clustering methods include, but are not limited to, mean clustering and drift clustering.

[0102] Step S420: Based on the hydraulic data of the abnormal critical node, determine the sensing fluctuation curve of the abnormal critical node.

[0103] For an explanation of the hydraulic data for abnormal critical nodes, please refer to [link / reference needed]. Figure 2 Related content.

[0104] The sensor fluctuation curve refers to the curve showing the change of actual hydraulic data at key nodes within a preset time period.

[0105] In some embodiments, each key node has a corresponding sensing fluctuation curve, with the horizontal axis of the sensing fluctuation curve representing time and the vertical axis representing the (actual) hydraulic data of the key node.

[0106] In some embodiments, the processor can determine the sensing fluctuation curve of an abnormal critical node based on the hydraulic data of the abnormal critical node in various ways. For example, the sensing fluctuation curve of an abnormal critical node can be fitted by multiple coordinate points, where each coordinate point represents the water pressure or flow data of the abnormal critical node at a time point within a preset time period.

[0107] Step S430: Based on the curve similarity and similarity threshold between the water supply fluctuation curve and the sensing fluctuation curve, the critical nodes in the abnormal water supply location are re-determined.

[0108] Curve similarity refers to the degree of similarity between the water supply fluctuation curve and the sensor fluctuation curve.

[0109] In some embodiments, curve similarity may be represented by the Pearson correlation coefficient or other methods.

[0110] The similarity threshold is a numerical value used to determine whether a water supply anomaly has occurred at a critical node. In some embodiments, the similarity threshold can be preset manually based on experience.

[0111] In some embodiments, the similarity threshold may also be related to the abnormal interval corresponding to the abnormal key node.

[0112] In some embodiments, the processor can determine a similarity threshold based on the degree of difference between the abnormal interval determined by querying the scenario configuration library and the standard abnormal interval (represented by the difference in width between the abnormal interval and the standard abnormal interval). The width of the interval is represented by the difference between its upper and lower limits.

[0113] When the width of the abnormal interval is greater than the width of the standard abnormal interval, it indicates that the current critical node's scenario or time period has higher requirements for water supply stability. Therefore, the similarity threshold should be set larger, and the greater the width difference, the higher the similarity threshold can be. Conversely, when the width of the abnormal interval is less than the width of the standard abnormal interval, it indicates that the current critical node's scenario or time period has lower requirements for water supply stability. Therefore, the similarity threshold can be appropriately lowered. For an explanation of the abnormal intervals and standard abnormal intervals determined by the scenario configuration library, please refer to [link to relevant documentation]. Figure 2 and Figure 3 Related descriptions.

[0114] By associating the similarity threshold with the abnormal interval corresponding to the critical node, the similarity judgment standard is dynamically adjusted according to the control requirements of the scenario where the critical node is located, which improves the adaptability and accuracy of water supply anomaly identification and avoids missed reports due to lenient judgment in sensitive scenarios.

[0115] In some embodiments, when the similarity between the water supply fluctuation curve and the sensing fluctuation curve is greater than or equal to a similarity threshold, the abnormal critical node is determined to be in a normal fluctuation state, that is, the abnormal critical node is a false abnormal critical node that has been misjudged; when the curve similarity is less than the similarity threshold, the abnormal critical node is determined to be a real water supply abnormality, that is, the abnormal critical node is a real abnormal critical node that has not been misjudged.

[0116] Normal fluctuation state means that the actual hydraulic data fluctuation of abnormal critical nodes is basically consistent with the expected hydraulic data fluctuation, that is, the hydraulic data fluctuation of abnormal critical nodes is caused by normal physical laws, not by abnormal water supply.

[0117] By combining the similarity analysis of municipal water supply fluctuation curves and sensor fluctuation curves, a secondary verification is performed on the initially identified key abnormal nodes. This can effectively distinguish between normal data fluctuations caused by external municipal water supply fluctuations and genuine water supply anomalies, thereby accurately correcting the location of water supply anomalies, improving the accuracy of anomaly identification, and reducing false alarms and missed alarms.

[0118] Figure 5 This is an exemplary flowchart illustrating the determination of boost parameters according to some embodiments of this specification. Figure 5 As shown, process 500 includes the following steps. In some embodiments, process 500 may be executed by an emergency monitoring and management platform in a smart city fire water pressure emergency monitoring IoT big data model system, for example, by a processor.

[0119] Step S510: Generate multiple candidate parameters for boosting.

[0120] Candidate pressure boosting parameters refer to candidate pressure boosting parameters used to regulate the water pressure in fire protection pipe networks. For example, each candidate pressure boosting parameter may include one or more candidate pressure boosting key nodes and their corresponding candidate preset water pressures.

[0121] In some embodiments, the processor can generate multiple candidate pressurization parameters in various ways. For example, the processor randomly combines multiple candidate pressurization key nodes with multiple candidate preset water pressures to generate multiple sets of parameter combinations containing candidate pressurization key nodes and their corresponding candidate preset water pressures, each set constituting a candidate pressurization parameter. The candidate pressurization key nodes can be historical pressurization key nodes, and the candidate preset water pressures can be obtained by making minor adjustments to the historical preset water pressures of the candidate pressurization key nodes.

[0122] Step S520: Construct a water supply map based on the preset location, the sensor data of the preset location, the location of water supply anomalies, and the type of water supply anomalies.

[0123] A water supply map is a map used to represent the topological connections and operational status of a predetermined location. A water supply map can consist of at least two nodes and at least one edge.

[0124] The nodes in the water supply map are preset locations in the fire protection network, including normal nodes and abnormal nodes. Normal nodes include normal critical nodes and normal fire pumps, while abnormal nodes are locations with abnormal water supply, including abnormal critical nodes and abnormal fire pumps.

[0125] The node characteristics of normal critical nodes include the hydraulic data of the normal critical nodes. The node characteristics of normal fire pumps include the operating parameters and operational data of the normal fire pumps. Operating parameters refer to the inherent design parameters of the fire pump. For example, operating parameters include rated power, rated flow rate, rated head, rated speed, rated motor voltage, and pump efficiency. The node characteristics of abnormal critical nodes can include the sensor data of the abnormal critical nodes and the corresponding water supply anomaly type. The node characteristics of abnormal fire pumps include the operational data of the abnormal fire pumps and the corresponding water supply anomaly type. More information on water supply anomaly types can be found in step S220 and its related explanations.

[0126] The edges in the water supply map are directed edges representing the water supply pipes that exist between two nodes. The direction of the edges points from upstream to downstream. Edge features can include dimensional parameters of the water supply pipes, such as pipe length, inner diameter, height difference, and pipe arm thickness.

[0127] In some embodiments, the processor can generate a water supply map by establishing directed edges from upstream to downstream between nodes based on the engineering structure diagram of the fire protection pipe network and the pipe connection relationship.

[0128] Step S530: For each candidate parameter for boosting pressure, based on the water supply map, the influence characteristics and boosting effect of the candidate parameter for boosting pressure are determined through the control model.

[0129] The control model can be any one or a combination of machine learning models, such as neural networks (NNs) or other custom model structures.

[0130] In some embodiments, the input to the control model may include a water supply map and candidate parameters for boosting pressure, and the output may include the influence characteristics of the candidate parameters for boosting pressure and the boosting effect.

[0131] The impact characteristic refers to the effect of pressurization at abnormal nodes on normal nodes. The impact characteristic of pressurization candidate parameters can be represented by the average value of the water pressure fluctuation amplitude of all normal nodes when pressurizing abnormal nodes according to the pressurization candidate parameters. The water pressure fluctuation amplitude can be represented by the change (absolute value) of water pressure data before and after pressurization.

[0132] The pressurization effect refers to the effect after pressurizing an abnormal node. The pressurization effect of the pressurization candidate parameter can be represented by the time required for the water pressure at the abnormal node to recover to the preset water pressure from the start of pressurization.

[0133] In some embodiments, the regulation model can be trained based on a large number of first training samples with first labels. The processor can input multiple first training samples with first labels into the initial regulation model, construct a loss function using the first labels and the results of the initial regulation model, and iteratively update the parameters of the initial regulation model based on the loss function using methods such as gradient descent. When the loss function meets preset conditions, the trained regulation model is obtained. These preset conditions may include loss function convergence, the number of iterations reaching a threshold, etc.

[0134] The first training sample and the first label can be obtained based on historical data. Each first training sample may include a historical water supply map and a historical pressure boosting parameter. The first label corresponding to the first training sample may include the actual impact characteristics of historically normal nodes and the actual pressure boosting effect of historically abnormal nodes in the historical water supply map after pressure boosting according to the historical pressure boosting parameter. The actual impact characteristics are represented by the average value of the actual water pressure fluctuation amplitude of all historically normal nodes when pressure boosting is performed on historically abnormal nodes according to the historical pressure boosting parameter. The actual pressure boosting effect is represented by the time required from the start of pressure boosting to the water pressure of historically abnormal nodes recovering to the historical preset water pressure.

[0135] In some embodiments, in a water supply map, the edge characteristics of the edges between normal nodes and abnormal nodes of the same type include the degree of influence of the abnormal nodes on the normal nodes.

[0136] The degree of impact refers to the extent of disturbance caused by the data fluctuations of abnormal nodes to normal nodes of the same type, including the degree of impact of hydraulic data fluctuations of abnormal critical nodes on the hydraulic data of normal critical nodes, and the degree of impact of abnormal fire pump operation data fluctuations on the operation data of normal fire pumps.

[0137] In some embodiments, the degree of influence can be obtained based on historical data. During a historical period, when the hydraulic data of an anomalous critical node changes, the fluctuation amplitude of its hydraulic data during that historical period is calculated, and the fluctuation amplitude of the hydraulic data of a normal critical node of the same type connected to it via an edge is also calculated during that historical period. The ratio of the fluctuation amplitude corresponding to the anomalous critical node to the fluctuation amplitude corresponding to the normal critical node is calculated. Multiple ratios are determined based on historical data from multiple historical periods, and the average of these ratios is taken as the degree of influence of the anomalous critical node on the normal critical node of the same type. The historical periods are selected manually, and the fluctuation amplitude can be represented by the amount of data change (absolute value).

[0138] In some embodiments, the processor can reconstruct the water supply map based on the influence of abnormal nodes on normal nodes introduced into the edge features of the water supply map. The construction process of the water supply map can be found in step S520 and its related description. The processor can input the reconstructed water supply map into the regulation model to re-output the influence features of the pressure boosting candidate parameters and the pressure boosting effect. The historical water supply map in the first training sample used to train the regulation model can also be a historical water supply map including the edge features of the influence of abnormal nodes on normal nodes.

[0139] By incorporating the influence of abnormal nodes on normal nodes into the edge features of the water supply map, the control model can more accurately characterize the transmission relationship of hydraulic disturbances in the fire protection network, thereby improving the prediction accuracy of the chain fluctuations that may be caused by boosting operations and helping to select the control scheme that minimizes the disturbance to normal nodes.

[0140] Step S540: Determine the boosting parameters based on the influence characteristics and boosting effect of multiple boosting candidate parameters.

[0141] In some embodiments, for each boost candidate parameter, the processor can normalize its corresponding influence characteristics and boost effect, and then perform a weighted summation. The weighted sum is determined as the regulation effect corresponding to the boost candidate parameter. The processor determines the boost candidate parameter with the smallest regulation effect as the boost parameter.

[0142] The weighting coefficients for the weighted sum can be set manually based on experience.

[0143] By constructing a water supply map and combining it with a control model to evaluate and select multiple pressure boosting candidate schemes, and determining the pressure boosting parameters, it is possible to achieve precise and efficient control of water supply anomalies. While ensuring the rapid restoration of water pressure at the location of the water supply anomaly, it can effectively suppress disturbances to normal nodes and improve the stability and intelligence level of the fire protection pipeline network operation.

[0144] The basic concepts have been described above. It is clear that the detailed disclosure above is merely illustrative and does not constitute a limitation of the present invention. Although not explicitly stated herein, various modifications, improvements, and corrections may be made to the present invention by those skilled in the art. Such modifications, improvements, and corrections are suggested in this invention and therefore remain within the spirit and scope of the exemplary embodiments of the present invention.

[0145] This invention uses specific terms to describe embodiments of the invention. For example, "some embodiments" refers to a particular feature, structure, or characteristic associated with at least one embodiment of the invention. Furthermore, certain features, structures, or characteristics in one or more embodiments of the invention can be appropriately combined.

[0146] Finally, it should be understood that the embodiments described in this invention are merely illustrative of the principles of the invention. Other modifications may also fall within the scope of this invention. Therefore, alternative configurations of the embodiments of this invention are considered as examples and not limitations, and are regarded as consistent with the teachings of this invention. Accordingly, the embodiments of this invention are not limited to those explicitly described and illustrated herein.

Claims

1. A smart city fire water pressure emergency monitoring IoT large-scale model system, characterized in that, Including an emergency monitoring and management platform; The emergency monitoring and management platform is configured as follows: Based on sensor data at preset locations within the fire protection pipeline network, the location of water supply anomalies is determined; Based on the sensor data of the abnormal water supply location, determine the type of water supply abnormality at the abnormal water supply location; Based on the location and type of the water supply anomaly, determine the booster parameters and / or maintenance parameters; Based on the pressurization parameters, a pressurization command is generated, including a pressurization key node and a preset water pressure. The pressurization command is configured to control the corresponding fire pump of the pressurization key node to adjust the water pressure to the preset water pressure at the pressurization key node. Based on the maintenance parameters, a maintenance instruction is generated, which includes the maintenance location and maintenance action. The maintenance instruction is configured to control the maintenance robot to move to the maintenance location and perform the maintenance action on the abnormal fire pump.

2. The system as described in claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Based on the scene characteristics and time period characteristics of the preset location, the abnormal interval corresponding to the preset location is determined.

3. The system as described in claim 2, characterized in that, The preset locations include key nodes and fire pumps, and the emergency monitoring and management platform is further configured as follows: Based on the performance characteristics of the corresponding fire pumps of the key nodes and the distance between the corresponding fire pumps of the key nodes and the key nodes, the jurisdiction intensity of the corresponding fire pumps of the key nodes is determined. Based on the scene characteristics of the key node, the time period characteristics of the key node, and the jurisdiction intensity of the corresponding fire pump of the key node, the abnormal interval corresponding to the key node is determined.

4. The system as described in claim 1, characterized in that, The sensor data at the preset location includes hydraulic data of key nodes, the abnormal water supply location includes the abnormal key node and the abnormal fire pump, and the emergency monitoring and management platform is further configured as follows: Based on municipal water supply parameters, the water supply fluctuation curve of the aforementioned abnormal critical node is determined; Based on the hydraulic data of the abnormal critical node, the sensing fluctuation curve of the abnormal critical node is determined. Based on the curve similarity and similarity threshold between the water supply fluctuation curve and the sensing fluctuation curve, the critical nodes of the abnormal water supply location are re-determined.

5. The system as described in claim 1, characterized in that, The emergency monitoring and management platform is further configured as follows: Generate multiple candidate boost parameters; Based on the preset location, the sensor data of the preset location, the location of the water supply anomaly, and the type of water supply anomaly, a water supply map is constructed; For each candidate parameter for boosting pressure, based on the water supply map, the influence characteristics and boosting effect of the candidate parameter for boosting pressure are determined by a control model, wherein the control model is a machine learning model. The boosting parameters are determined based on the influence characteristics and boosting effects of the multiple boosting candidate parameters.

6. A smart city fire water pressure emergency monitoring method, characterized in that, The method is executed by the emergency monitoring and management platform in the smart city fire water pressure emergency monitoring IoT big data model system as described in claim 1, and the method includes: Based on sensor data at preset locations within the fire protection pipeline network, the location of water supply anomalies is determined; Based on the sensor data of the abnormal water supply location, determine the type of water supply abnormality at the abnormal water supply location; Based on the location and type of the water supply anomaly, determine the booster parameters and / or maintenance parameters; Based on the pressurization parameters, a pressurization command is generated, including a pressurization key node and a preset water pressure. The pressurization command is configured to control the corresponding fire pump of the pressurization key node to adjust the water pressure to the preset water pressure at the pressurization key node. Based on the maintenance parameters, a maintenance instruction is generated, which includes the maintenance location and maintenance action. The maintenance instruction is configured to control the maintenance robot to move to the maintenance location and perform the maintenance action on the abnormal fire pump.

7. The method as described in claim 6, characterized in that, The method further includes: Based on the scene characteristics and time period characteristics of the preset location, the abnormal interval corresponding to the preset location is determined.

8. The method as described in claim 7, characterized in that, The preset locations include key nodes and fire pumps. The step of determining the abnormal interval corresponding to the preset location based on scene and time period characteristics of the preset location also includes: Based on the performance characteristics of the corresponding fire pumps of the key nodes and the distance between the corresponding fire pumps of the key nodes and the key nodes, the jurisdiction intensity of the corresponding fire pumps of the key nodes is determined. Based on the scene characteristics of the key node, the time period characteristics of the key node, and the jurisdiction intensity of the corresponding fire pump of the key node, the abnormal interval corresponding to the key node is determined.

9. The method as described in claim 6, characterized in that, The sensing data at the preset location includes hydraulic data of key nodes, and the abnormal water supply location includes the abnormal key node and the abnormal fire pump. The method further includes: Based on municipal water supply parameters, the water supply fluctuation curve of the aforementioned abnormal critical node is determined; Based on the hydraulic data of the abnormal critical node, the sensing fluctuation curve of the abnormal critical node is determined. Based on the curve similarity and similarity threshold between the water supply fluctuation curve and the sensing fluctuation curve, the critical nodes of the abnormal water supply location are re-determined.

10. The method as described in claim 6, characterized in that, The step of determining the booster parameters based on the location and type of water supply anomaly includes: Generate multiple candidate boost parameters; Based on the preset location, the sensor data of the preset location, the location of the water supply anomaly, and the type of water supply anomaly, a water supply map is constructed; For each candidate parameter for boosting pressure, based on the water supply map, the influence characteristics and boosting effect of the candidate parameter for boosting pressure are determined by a control model, wherein the control model is a machine learning model. The boosting parameters are determined based on the influence characteristics and boosting effects of the multiple boosting candidate parameters.

Images