Intelligent fire-extinguishing water intake hydrant anomaly detection system and method based on networking

Abstract

The invention relates to the technical field of intelligent fire fighting equipment, and discloses a networking-based intelligent fire-extinguishing water-taking hydrant abnormity detection system and a networking-based intelligent fire-extinguishing water-taking hydrant abnormity detection method. The system comprises a multi-source sensing module used for collecting water pressure, flow and environment state data; the abnormal feature analysis module is used for generating an abnormal feature vector based on an improved support vector machine; the dynamic state compensation module is used for outputting state compensation parameters by using a wavelet transform algorithm; and the networking collaborative decision module is used for constructing a multi-node optimization model to generate a global collaborative control instruction. The multi-source sensing module fuses various sensor data, and outputs comprehensive detection features through feature fusion and a graph convolutional network. An improved support vector machine is integrated with a particle swarm optimization algorithm to improve the detection precision, and a wavelet transform algorithm is combined with a Bayesian network to realize dynamic modeling compensation. And the multi-node optimization model adopts a distributed collaborative architecture to realize collaborative control. The system and the method can accurately detect abnormity, improve the efficiency of a fire-fighting water supply system and guarantee fire-fighting safety.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent fire fighting equipment, and in particular to an intelligent fire fighting water hydrant abnormality detection system and method based on networking. Background Art

[0002] In the field of firefighting infrastructure, fire hydrants are key fire water supply equipment, and the reliability of their operating status plays a vital role in fire safety. However, traditional fire hydrants have many problems, which seriously affect their effectiveness and reliability in firefighting work.

[0003] From the perspective of detection methods, early fire-fighting water hydrants lacked an effective real-time monitoring mechanism. In the past, they relied more on regular manual inspections, which was not only inefficient, but also difficult to detect and handle abnormal situations in a timely manner. Manual inspections often have time intervals. Once an abnormality occurs during the interval, such as abnormal water pressure caused by a ruptured pipeline or flow changes caused by a damaged valve, it is difficult to detect it in time, which can easily delay the best time to fight the fire. Even during the inspection process, manual judgment is subjective and limited, and some subtle abnormal signs may not be accurately identified, thus posing a safety hazard.

[0004] With the development of technology, although some simple monitoring equipment has emerged, their functions are single and they can only monitor a single parameter of water pressure or flow, and they cannot comprehensively consider the impact of multiple factors on the operating status of fire hydrants. For example, if only the water pressure is monitored, an alarm cannot be issued in time when the flow changes abnormally, resulting in an inability to fully and accurately evaluate the actual operating status of the fire hydrant. Moreover, these simple devices are independent of each other and have no networking function, so data sharing and collaborative processing cannot be achieved, making it difficult to meet the needs of unified management of large-scale firefighting facilities.

[0005] In terms of anomaly detection technology, traditional detection algorithms lack accuracy. Early algorithms were mostly based on simple threshold judgments. When environmental factors interfered or complex equipment failures occurred, false alarms and missed alarms occurred frequently. For example, when environmental factors such as temperature and humidity change greatly, water pressure and flow data will be affected to a certain extent. Simple threshold judgments may misjudge normal fluctuations as abnormalities, causing unnecessary troubles to fire management; and for some gradually developing hidden faults, they may be missed because they do not reach the set threshold, and potential dangers cannot be discovered in time.

[0006] In addition, in large-scale fire protection systems, there is a lack of an effective coordination mechanism among fire hydrants. When a fire breaks out and a large amount of water is needed, it is impossible to rationally allocate water according to the status of surrounding fire hydrants, resulting in insufficient water supply at some fire hydrants while some are idle, causing waste of resources and low utilization efficiency. Moreover, due to the lack of global coordinated control, when dealing with multiple fire points or complex fire scenarios, the entire fire water supply system is difficult to respond effectively and quickly, seriously affecting the fire extinguishing effect. Summary of the Invention

[0007] The purpose of the present invention is to provide an intelligent abnormal detection system and method for fire hydrants based on networking to solve the problems raised in the above-mentioned background technology.

[0008] To achieve the above purpose, the present invention provides the following technical solutions: An intelligent abnormal detection system for fire hydrants based on networking, the system includes: Multi-source perception module: used to collect water pressure data, flow data and environmental status data of fire hydrants through a variety of sensors; Abnormal feature analysis module: based on an improved support vector machine, perform pattern recognition on the water pressure data and flow data to generate abnormal feature vectors; Dynamic state compensation module: adopt wavelet transform algorithm to perform real-time modeling on the mechanical vibration and temperature drift of fire hydrants, and output state compensation parameters; Networked collaborative decision-making module: according to the abnormal feature vectors and state compensation parameters, construct a multi-node optimization model and generate global collaborative control instructions.

[0009] Preferably, the multi-source perception module includes: A variety of sensors include pressure transmitters, electromagnetic flow meters, temperature and humidity sensors, and vibration accelerometers; Perform time-domain synchronization processing on the data of pressure transmitters and electromagnetic flow meters to construct a working condition state model of fire hydrants; perform wavelet packet decomposition on the data of temperature and humidity sensors and vibration accelerometers to extract environmental interference characteristics and mechanical vibration spectra; Construct a two-channel feature fusion network. The first channel uses a one-dimensional convolutional neural network to extract the time-domain fluctuation characteristics of the working condition state model, and the second channel uses a frequency-domain attention mechanism to extract the frequency-domain energy distribution characteristics of the mechanical vibration spectrum; Fuse the time-domain fluctuation characteristics and frequency-domain energy distribution characteristics through a cross-domain feature alignment strategy to generate a joint feature matrix; perform node association modeling on the joint feature matrix based on a graph convolutional network, and output comprehensive detection features including water pressure anomalies, flow rate mutations, and mechanical wear states.

[0010] Preferably, the improved support vector machine integrates a particle swarm optimization algorithm, including: Model anomaly detection as a multi-classification problem, where the decision variables include the kernel function type, penalty coefficient, and relaxation factor; Initialize the support vector machine parameters and calculate the classification hyperplane. The objective function includes maximizing the classification margin, the weights of misclassified samples, and the separability index of the feature space; In the parameter optimization stage, dynamically adjust the particle swarm search step size according to the environmental interference characteristics; in the model training stage, adopt the cross-validation strategy to screen the optimal kernel function combination; Introduce the Pareto optimal solution set to iteratively screen the multi-objective optimization results, and finally output the anomaly feature vector.

[0011] Preferably, the wavelet transform algorithm combined with the Bayesian network includes: Construct a vibration-temperature coupling state equation, and use the mechanical vibration amplitude, temperature change gradient, and water pressure fluctuation as observation variables; Design a wavelet basis function library to map the observation variables into multi-scale wavelet coefficients; Dynamically update the state transition probability through online Bayesian inference, and use the maximum a posteriori estimation to optimize the wavelet decomposition layer number; Output the state compensation parameters including the vibration suppression coefficient and the temperature compensation amount.

[0012] Preferably, the multi-node optimization model adopts a distributed collaborative architecture, including: Construct a node communication topology graph, where the nodes represent each fire hydrant control unit, and the edges represent the data transmission delay constraints between the nodes; Use the alternating direction multiplier method to decompose the global optimization problem into local sub-problems. Each sub-problem includes the node response time limit, the energy consumption balance term, and the data consistency penalty term; Introduce virtual coordination variables at the decision layer to balance the conflicts of each node's control instructions, and achieve collaborative iterative solution through the distributed consensus algorithm; Finally, generate the global collaborative control instructions.

[0013] Preferably, the one-dimensional convolutional neural network adopts a multi-scale residual structure, including: Divide the working condition state model into multi-time window sequences, and each time window includes statistical quantities such as mean, variance, and range; In the convolution stage, use a dilated convolutional kernel with a dilation rate of 2 to capture long-time sequence dependence features, and in the residual connection stage, fuse short-time sequence details and long-time sequence trend features; Introduce a temporal attention module to adaptively weight the feature channels; The timing attention module adopts a frequency-domain and time-domain joint focusing mechanism, including: calculating the energy density weight of the feature map in the frequency domain dimension to screen the dominant frequency components, constructing a sliding window model in the time domain dimension to locate the abnormal event occurrence period, and fusing the frequency-domain weight and the time-domain weight through tensor product operation.

[0014] Preferably, the particle swarm optimization algorithm is implemented based on a dynamic inertia weight mechanism, including: collecting the classification accuracy and calculation time consumption in the historical detection process as optimization factors; constructing a radial basis function network to fit the non-linear relationship between the inertia weight and the optimization factors.

[0015] Preferably, the Bayesian network adopts a two-stage inference structure, including: The forward inference stage estimates the state transition probability based on Markov chain Monte Carlo sampling; The backward correction stage updates the wavelet basis function parameters through the expectation maximization algorithm; Define a hybrid inference strategy, and fuse the forward probability distribution and the backward parameter correction result through weighting to output the final state compensation parameter.

[0016] Preferably, the virtual coordination variable adopts a lag compensation mechanism, including: Measuring the execution delay of each node's control instruction and constructing a time-varying lag coefficient matrix; Introduce a lag compensation term in the consensus algorithm and determine the compensation gain coefficient through stability analysis.

[0017] Preferably, the present invention further includes an abnormal detection method for an intelligent fire-extinguishing water intake hydrant based on networking, including the following steps: S1. Collect the water pressure data, flow data and environmental state data of the fire-extinguishing water intake hydrant through a multi-source sensor network; S2. Perform pattern recognition on the water pressure data and flow data based on an improved support vector machine to generate an abnormal feature vector containing abnormal fluctuation features and data correlation; S3. Adopt a wavelet transform algorithm to dynamically model the mechanical vibration signal and temperature drift parameter of the fire-extinguishing water intake hydrant to generate real-time state compensation parameters; S4. According to the abnormal feature vector and the state compensation parameter, construct a multi-node optimization decision model to generate a global collaborative control instruction and a dynamic collaborative resource matching network.

[0018] Compared with the prior art, the beneficial effects of the present invention are: In terms of data acquisition and analysis, the multi-source perception module plays a key role. By working together with various sensors such as pressure transmitters, electromagnetic flowmeters, temperature and humidity sensors, and vibration accelerometers, it can not only collect water pressure and flow data in real time but also obtain environmental status data. This makes the condition monitoring of fire hydrants more comprehensive and detailed, avoiding the limitations of single-parameter monitoring. For example, in a humid environment, the data from the temperature and humidity sensors can assist in judging whether there is a risk of equipment corrosion caused by humidity, and combined with the data from the vibration accelerometers, it can further analyze the wear of the mechanical components of the equipment. Through time-domain synchronization processing, wavelet packet decomposition of the collected data, and the use of dual-channel feature fusion networks and graph convolutional networks, the generated comprehensive detection features can accurately reflect water pressure anomalies, flow rate mutations, and mechanical wear states, greatly improving the accuracy and reliability of detection and effectively reducing false alarms and missed detections.

[0019] The abnormal feature analysis module integrates an improved support vector machine with a particle swarm optimization algorithm, models anomaly detection as a multi-classification problem, and through dynamically adjusting the particle swarm search step size, cross-validation to screen the optimal kernel function combination, and iterative screening of the Pareto optimal solution set, it can more accurately identify abnormal patterns in water pressure and flow data. The generated abnormal feature vectors contain rich abnormal information, providing a reliable basis for subsequent decision-making. This multi-objective optimization method can better adapt to complex actual application scenarios compared with traditional single-objective detection algorithms and can stably and accurately detect anomalies under different environmental interferences.

[0020] The dynamic state compensation module combines a wavelet transform algorithm with a Bayesian network to perform real-time modeling for the mechanical vibration and temperature drift of fire hydrants. By constructing a vibration-temperature coupling state equation, designing a wavelet basis function library, and using online Bayesian inference and maximum a posteriori estimation to optimize the number of wavelet decomposition layers, the output state compensation parameters can effectively suppress mechanical vibration and compensate for the influence of temperature drift on the equipment operation state, ensure the accuracy of equipment operation data, extend the service life of the equipment, and improve the stability of equipment operation.

[0021] The networked collaborative decision-making module adopts a multi-node optimization model with a distributed collaborative architecture, constructs a node communication topology map and considers data transmission delay constraints, decomposes the optimization problem through the alternating direction method of multipliers, introduces virtual coordination variables to balance control instruction conflicts, and uses a distributed consensus algorithm for collaborative iterative solution to achieve efficient collaboration among the control units of each fire hydrant. This enables the system to quickly generate global collaborative control instructions according to the actual states and requirements of each hydrant in the face of emergencies such as fires, rationally allocate water resources, avoid situations where some hydrants have insufficient water supply while some are idle, greatly improve the response speed and water supply efficiency of the fire water supply system, effectively enhance the fire extinguishing effect, and ensure the safety of people's lives and property.

[0022] From the perspective of the overall system architecture, each module collaborates and complements each other, forming an organic whole. The multi-source perception module provides an accurate data basis for the subsequent modules. The abnormal feature analysis module and the dynamic state compensation module conduct in-depth analysis and processing of the data, while the networked collaborative decision-making module realizes global optimization control based on the results of the previous modules. This highly integrated and collaborative design not only improves the performance of abnormal detection of fire hydrants but also provides strong support for the intelligent management of fire-fighting facilities, with significant economic and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 FIG. is the working principle diagram of the network-based intelligent fire hydrant abnormal detection system of the present invention; Figure 2 FIG. is the working principle diagram of the multi-source perception module; Figure 3 FIG. is the working principle diagram of the one-dimensional convolutional neural network; Figure 4 FIG. is the working principle diagram of the particle swarm optimization algorithm. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0025] Please refer to Figures 1 - 4 , the present invention provides a technical solution: a network-based intelligent fire hydrant abnormal detection system, the system includes: a multi-source perception module, an abnormal feature analysis module, a dynamic state compensation module, and a networked collaborative decision-making module.

[0026] During the operation of the system, the multi-source perception module uses a variety of sensors, such as pressure transmitters, electromagnetic flowmeters, temperature and humidity sensors, and vibration accelerometers, to collect the water pressure data, flow data, and environmental state data of the fire hydrant. These sensors obtain information from different dimensions, providing a rich data basis for subsequent abnormal detection.

[0027] After the data is collected, the abnormal feature analysis module performs pattern recognition on the water pressure data and flow rate data based on the improved support vector machine. The improved support vector machine integrates the particle swarm optimization algorithm. Through a series of operations, such as modeling the anomaly detection as a multi-classification problem, reasonably setting decision variables, initializing the parameters of the support vector machine and calculating the classification hyperplane, and performing parameter optimization and model training at different stages, an abnormal feature vector is finally generated. This vector contains important information such as the hidden abnormal fluctuation features in the water pressure and flow rate data and the correlation degree between the data.

[0028] The dynamic state compensation module uses the wavelet transform algorithm to perform real-time modeling on the mechanical vibration and temperature drift of the fire hydrant. This algorithm combines the Bayesian network. By constructing a vibration-temperature coupling state equation, designing a wavelet basis function library, and performing online Bayesian inference and other steps, state compensation parameters including vibration suppression coefficients and temperature compensation amounts are output. These parameters can effectively compensate for the errors that may be caused by the mechanical vibration and temperature drift of the fire hydrant, improving the accuracy of detection.

[0029] The networked collaborative decision-making module constructs a multi-node optimization model based on the abnormal feature vector and state compensation parameters. This model adopts a distributed collaborative architecture. By constructing a node communication topology graph, decomposing the global optimization problem into local sub-problems, and introducing virtual coordination variables at the decision-making layer and other operations, global collaborative control instructions are generated. These instructions can achieve the collaborative control of multiple fire hydrants, ensuring that the entire system can respond quickly in case of abnormal situations and guaranteeing the normal supply of fire-fighting water.

[0030] The present invention will be further described below in conjunction with Embodiments 1 to 5: Embodiment 1: This embodiment mainly focuses on the multi-source perception module. In the actual application scenario, various sensors of the multi-source perception module are installed at appropriate positions on and around the fire hydrant. The pressure transmitter is used to accurately measure the water pressure data inside the fire hydrant, the electromagnetic flowmeter is responsible for collecting the flow rate data, the temperature and humidity sensor monitors the temperature and humidity of the surrounding environment, and the vibration accelerometer obtains the mechanical vibration information of the fire hydrant.

[0031] After the data of the pressure transmitter and the electromagnetic flowmeter are collected, time-domain synchronization processing is required. This is because the time when different sensors collect data may vary. If synchronization is not performed, the subsequent constructed working condition state model will be inaccurate. Through a specific time-domain synchronization algorithm, these two types of data are made consistent in time, and then the working condition state model of the fire hydrant is constructed. This model comprehensively reflects the changes in water pressure and flow rate over time and is an important basis for subsequent analysis.

[0032] For the temperature and humidity sensor data and vibration accelerometer data, a wavelet packet decomposition method is used for processing. Wavelet packet decomposition can finely decompose the signal in different frequency bands, so as to extract the environmental interference characteristics and mechanical vibration spectrum. The environmental interference characteristics can reflect the influence of surrounding environmental factors on the fire hydrant, while the mechanical vibration spectrum contains information on the operating state of the mechanical components of the fire hydrant itself.

[0033] To make more effective use of these features, a dual-channel feature fusion network is constructed. The first channel uses a one-dimensional convolutional neural network (1D-CNN). The working condition state model is divided into multi-time window sequences, and each time window contains mean, variance, and range statistics. In the convolution stage, dilated convolutional kernels with a dilation rate of 2 are used. Dilated convolutional kernels can expand the receptive field of the convolutional kernel without increasing the number of parameters, capturing long-term sequence dependence features. In the residual connection stage, short-term sequence details and long-term sequence trend features are fused, enabling the network to better learn various features of the data. At the same time, a temporal attention module is introduced to adaptively weight the feature channels. The temporal attention module adopts a frequency-domain and time-domain joint focusing mechanism, calculating the energy density weights of the feature map in the frequency domain , screening the dominant frequency components; constructing a sliding window model in the time domain to locate the time period when abnormal events occur, and fusing the frequency-domain weights and time-domain weights through tensor product operations , obtaining the comprehensive weights . This can highlight the features that are important for anomaly detection and improve the accuracy of detection.

[0034] The second channel uses a frequency-domain attention mechanism to extract the frequency-domain energy distribution characteristics of the mechanical vibration spectrum. The frequency-domain attention mechanism analyzes the energy distribution of different frequency components of the mechanical vibration spectrum, finds the frequency bands that contribute more to anomaly detection, and assigns corresponding weights.

[0035] Finally, through a cross-domain feature alignment strategy, the time-domain fluctuation characteristics and frequency-domain energy distribution characteristics are fused to generate a joint feature matrix. Based on the graph convolutional network, node association modeling is performed on the joint feature matrix, fully considering the mutual relationships between different features, and outputting comprehensive detection features including water pressure anomalies, flow rate mutations, and mechanical wear states. These comprehensive detection features provide comprehensive and valuable information for subsequent anomaly analysis.

[0036] Example 2: This example focuses on the specific implementation of the improved support vector machine integrated particle swarm optimization algorithm in the anomaly feature analysis module.

[0037] Model the anomaly detection as a multi-classification problem, and the decision variables include the kernel function type , the penalty coefficient , and the relaxation factor . The type of kernel function determines the mapping method of data in the feature space, and different kernel functions are suitable for different data distributions; the penalty coefficient is used to balance the maximization of the classification margin and the penalty degree of misclassified samples; the slack factor allows a certain degree of misclassification to adapt to the possible noise and complex distributions in the actual data.

[0038] Initialize the support vector machine parameters, including selecting a suitable initial kernel function type, penalty coefficient, and slack factor, and calculate the classification hyperplane. The objective function is , where represents the weight vector of the two-norm, and its role is to maximize the classification margin; is the penalty coefficient, as mentioned above, used to balance the classification margin and the penalty of misclassified samples; is the sum of the slack factors of all samples, is the number of samples, which reflects the tolerance for misclassified samples. The design of this objective function comprehensively considers the maximization of the classification margin, the weights of misclassified samples, and the separability index of the feature space.

[0039] In the parameter optimization stage, dynamically adjust the particle swarm search step size according to the environmental interference characteristics. Collect the classification accuracy and the calculation time in the historical detection process as optimization factors, and construct a radial basis function network to fit the nonlinear relationship between the inertia weight and the optimization factors. Assume that the output of the radial basis function network is , where is the number of radial basis functions, is the weight of the th radial basis function, is the input vector, which consists of the classification accuracy and the calculation time , is the center of the th radial basis function, is the th width of the radial basis function. In this way, according to different environmental interference situations, dynamically adjust the particle swarm search step size to improve the search efficiency and accuracy of the algorithm.

[0040] In the model training stage, adopt a cross-validation strategy to screen the optimal kernel function combination. Divide the dataset into multiple subsets, train and validate on different subsets, compare the model performance under different kernel function combinations, and select the kernel function combination with the best performance.

[0041] Finally, the Pareto optimal solution set is introduced to iteratively screen the multi-objective optimization results. The Pareto optimal solution set contains a group of solutions that achieve a balance among multiple objectives. Through continuous iterative screening, an abnormal feature vector is finally output. This abnormal feature vector comprehensively considers multiple factors and can more accurately reflect the abnormal conditions in the water pressure data and flow data.

[0042] Embodiment 3: This embodiment elaborates in detail the wavelet transform algorithm combined with a Bayesian network in the dynamic state compensation module.

[0043] First, a vibration-temperature coupling state equation is constructed, taking the mechanical vibration amplitude , the temperature change gradient , and the water pressure fluctuation as the observation variables. These observation variables can comprehensively reflect the changes in the operating state of the fire hydrant. The vibration-temperature coupling state equation can be expressed in the form of a state space model, for example , where is the state vector at time, containing information such as the mechanical vibration amplitude, the temperature change gradient, and the water pressure fluctuation; is the state transition matrix, describing the relationship between the states over time; is the control input matrix (in this scenario, it may be related to factors such as external disturbances); is the control input at time; is the process noise at

[0044] Design a wavelet basis function library to map the observation variables into multi-scale wavelet coefficients. The selection of wavelet basis functions is very crucial, as different wavelet basis functions have different decomposition effects on signals. According to the characteristics of the fire hydrant data, appropriate wavelet basis functions are selected, such as Daubechies wavelets, etc. Through wavelet transform, the observation variables are decomposed at different scales to obtain multi-scale wavelet coefficients, which contain information about the signal at different frequencies and time scales.

[0045] During the processing, the state transition probability is dynamically updated through online Bayesian inference. The Bayesian network adopts a two-stage inference structure. In the forward inference stage, the state transition probability is estimated based on Markov chain Monte Carlo sampling. Assume the state transition probability is , and Markov chain Monte Carlo sampling constructs a Markov chain whose stationary distribution is the target distribution . By sampling on the Markov chain, an estimated value of the state transition probability is obtained.

[0046] In the reverse correction stage, the wavelet basis function parameters are updated by the Expectation-Maximization (EM) algorithm. The EM algorithm is an iterative algorithm that consists of an expectation step and a maximization step. In the expectation step, the expected value of the log-likelihood function under the current parameter estimates is calculated; in the maximization step, the parameter values that maximize the expected value are found, and the iteration continues until the parameters converge.

[0047] Define a hybrid inference strategy to output the final state compensation parameters by weighted fusion of the forward probability distribution and the reverse parameter correction results. Let the forward probability distribution be , and the reverse parameter correction result be , with weights and respectively. Then the final state compensation parameter . In this way, by comprehensively considering the forward and reverse information, the accuracy of the state compensation parameters is improved, and the state compensation parameters including the vibration suppression coefficient and the temperature compensation amount are output, realizing effective compensation for the mechanical vibration and temperature drift of the fire hydrant.

[0048] Example 4: This example focuses on the distributed collaborative architecture adopted by the multi-node optimization model in the networked collaborative decision-making module.

[0049] Construct a node communication topology graph. The nodes represent the control units of each fire hydrant, and each node is responsible for collecting and processing the relevant data of the fire hydrant where it is located. The edges represent the data transmission delay constraints between nodes, and the data transmission delay is an important factor affecting the system's collaborative performance. Assume that the data transmission delay between node and node is , and this delay may be affected by various factors such as network bandwidth and transmission distance.

[0050] Use the Alternating Direction Method of Multipliers (ADMM) to decompose the global optimization problem into local sub-problems. Each sub-problem contains a node response time limit, an energy consumption balance term, and a data consistency penalty term. Taking the sub-problem of node as an example, its objective function can be expressed as , where is the part of the objective function related to node itself, for example, related to the accuracy of anomaly detection of the fire hydrant controlled by this node; is the term related to data consistency, represents the local variable of node ; is the penalty parameter used to adjust the strength of the data consistency penalty; is the set of neighbor nodes of node ; is the decision variable of node . is a node and the node The dual variable between. The node response time limit ensures that each node can respond to abnormal situations within the specified time, the energy consumption balance term ensures that the energy consumption of each node is relatively balanced, avoiding excessive energy consumption of some nodes, and the data consistency penalty term ensures the consistency of data between different nodes.

[0051] Introduce a virtual coordination variable at the decision-making layer to balance the control instruction conflicts of each node. The virtual coordination variable adopts a lag compensation mechanism, measures the execution time delay of each node's control instruction, and constructs a time-varying lag coefficient matrix Suppose is the node to the node The time-varying lag coefficient of, which changes with time and reflects the difference in the execution time delay of control instructions between different nodes. Introduce a lag compensation term in the consensus algorithm, and determine the compensation gain coefficient through stability analysis. Stability analysis is usually based on methods such as Lyapunov stability theory to ensure that the system still operates stably after introducing the lag compensation term. Through the distributed consensus algorithm, collaborative iterative solution is realized. Information is continuously exchanged between each node, and its decision variables are adjusted. Finally, global collaborative control instructions are generated. These instructions can coordinate the work of each fire hydrant and achieve the efficient operation of the entire system.

[0052] Example 5: This example further illustrates the comprehensive application and advantages of the system from multiple aspects. In a large fire water supply network, multiple fire hydrants with the intelligent fire hydrant anomaly detection system of the present invention are deployed.

[0053] The multi-source perception module continuously collects the water pressure data, flow data, temperature and humidity data, and vibration data of each fire hydrant. These data are transmitted to the subsequent processing module in real time through the network. For example, within a certain period of time, the environmental temperature near one of the fire hydrants changes greatly, and the temperature and humidity sensor captures this information in time and transmits it together with other data.

[0054] The abnormal feature analysis module deeply analyzes the collected water pressure and flow data. By improving the support vector machine integrated particle swarm optimization algorithm, accurately identify the abnormal fluctuation features in the data. Suppose at a certain moment, the water pressure of this fire hydrant drops abnormally and the flow rate also changes suddenly. The abnormal feature analysis module quickly generates an abnormal feature vector containing this abnormal information.

[0055] The dynamic state compensation module performs real-time modeling for mechanical vibration and temperature drift. Since temperature changes may affect the performance of the internal components of the fire hydrant, the wavelet transform algorithm combined with the Bayesian network comes into play. It processes the observed variables such as the amplitude of mechanical vibration, the temperature change gradient, and the water pressure fluctuation collected according to the vibration-temperature coupling state equation. For example, through online Bayesian inference, it adjusts the state transition probability in a timely manner and accurately outputs the state compensation parameters such as the vibration suppression coefficient and the temperature compensation amount to compensate for the errors that may be caused by temperature and vibration.

[0056] The networked collaborative decision-making module constructs a multi-node optimization model based on the abnormal feature vector and the state compensation parameters. In this large-scale fire water supply network, each fire hydrant control unit serves as a node and is interconnected through the node communication topology diagram. When an abnormality occurs in a certain fire hydrant, the multi-node optimization model uses a distributed collaborative architecture for processing. By decomposing the global optimization problem through the alternating direction multiplier method, each node calculates according to its own sub-problem. At the same time, a virtual coordination variable is introduced to balance the control instruction conflicts of each node. Suppose there may be conflicts in the control instructions of different nodes during the process of adjusting the water pressure. The virtual coordination variable is adjusted according to the time-varying lag coefficient matrix and the compensation gain coefficient through the lag compensation mechanism, and finally, the distributed consensus algorithm is used to achieve collaborative iterative solution to generate the global collaborative control instructions. These instructions can coordinate the work of each fire hydrant to ensure that the entire fire water supply network can still operate stably and efficiently in the event of an abnormality and guarantee the normal supply of fire water. It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0057] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principle and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent fire hydrant abnormality detection system based on networking, characterized in that: include: Multi-source sensing module: used to collect water pressure data, flow data and environmental status data of fire hydrants through multiple sensors; Abnormal feature analysis module: performs pattern recognition on the water pressure data and flow data based on an improved support vector machine to generate an abnormal feature vector; Dynamic state compensation module: uses wavelet transform algorithm to model the mechanical vibration and temperature drift of fire hydrants in real time and output state compensation parameters; Networked collaborative decision-making module: Based on the abnormal feature vector and state compensation parameters, a multi-node optimization model is constructed to generate global collaborative control instructions.

2. According to claim 1, a network-based intelligent fire hydrant abnormality detection system is characterized in that: The multi-source perception module comprises: A variety of sensors including pressure transmitters, electromagnetic flow meters, temperature and humidity sensors, and vibration accelerometers; The pressure transmitter data and the electromagnetic flowmeter data are synchronously processed in the time domain to build a working condition model of the fire hydrant; the temperature and humidity sensor data and the vibration accelerometer data are decomposed by wavelet packets to extract environmental interference characteristics and mechanical vibration spectra; A dual-channel feature fusion network is constructed. The first channel uses a one-dimensional convolutional neural network to extract the time domain fluctuation characteristics of the working condition model, and the second channel uses a frequency domain attention mechanism to extract the frequency domain energy distribution characteristics of the mechanical vibration spectrum. The time domain fluctuation features and frequency domain energy distribution features are fused through a cross-domain feature alignment strategy to generate a joint feature matrix. The joint feature matrix is ​​modeled based on node associations in a graph convolutional network to output comprehensive detection features including water pressure anomalies, flow rate mutations, and mechanical wear status.

3. According to the network-based intelligent fire hydrant abnormality detection system of claim 1, it is characterized in that: The improved support vector machine integrated particle swarm optimization algorithm comprises: Anomaly detection is modeled as a multi-classification problem, and the decision variables include kernel function type, penalty coefficient, and relaxation factor; Initialize the support vector machine parameters and calculate the classification hyperplane. The objective function includes maximizing the classification interval, the weight of misclassified samples, and the feature space separability index. In the parameter optimization stage, the particle swarm search step size is dynamically adjusted according to the environmental interference characteristics; in the model training stage, the cross-validation strategy is used to select the optimal kernel function combination; The Pareto optimal solution set is introduced to iteratively screen the multi-objective optimization results, and finally the abnormal feature vector is output.

4. According to the network-based intelligent fire hydrant abnormality detection system of claim 1, it is characterized in that: The wavelet transform algorithm is combined with a Bayesian network, including: The vibration-temperature coupling state equation is constructed, and the mechanical vibration amplitude, temperature change gradient and water pressure fluctuation are used as observation variables; Design a wavelet basis function library to map observed variables into multi-scale wavelet coefficients; The state transition probability is dynamically updated through online Bayesian reasoning, and the maximum a posteriori estimation is used to optimize the number of wavelet decomposition layers; The output includes the state compensation parameters of the vibration suppression coefficient and the temperature compensation amount.

5. According to the network-based intelligent fire hydrant abnormality detection system of claim 1, it is characterized in that: The multi-node optimization model adopts a distributed collaborative architecture, including: Construct a node communication topology graph, where nodes represent the control units of each fire hydrant and edges represent the data transmission delay constraints between nodes; The alternating direction multiplier method is used to decompose the global optimization problem into local sub-problems. Each sub-problem contains node response time limit, energy consumption balance term and data consistency penalty term. Introduce virtual coordination variables at the decision-making layer to balance the control instruction conflicts of each node, and achieve collaborative iterative solution through distributed consensus algorithm; Finally, global collaborative control instructions are generated.

6. The network-based intelligent fire hydrant abnormality detection system according to claim 2 is characterized in that: The one-dimensional convolutional neural network adopts a multi-scale residual structure, including: The operating state model is divided into multiple time window sequences, each of which contains mean, variance and range statistics; In the convolution stage, a dilated convolution kernel with a dilation rate of 2 is used to capture long-term temporal dependency features, and in the residual connection stage, short-term details and long-term trend features are integrated; Introduce the temporal attention module to adaptively weight feature channels; The temporal attention module adopts a frequency domain-time domain joint focusing mechanism, including: calculating the energy density weight of the feature map in the frequency domain dimension, screening the dominant frequency components, building a sliding window model in the time domain dimension, locating the time period when abnormal events occur, and fusing the frequency domain weight and the time domain weight through tensor product operations.

7. The network-based intelligent fire hydrant abnormality detection system according to claim 3 is characterized in that: The particle swarm optimization algorithm is implemented based on a dynamic inertia weight mechanism, including: collecting classification accuracy and calculation time in the historical detection process as optimization factors; constructing a radial basis function network to fit the nonlinear relationship between the inertia weight and the optimization factor.

8. The network-based intelligent fire hydrant abnormality detection system according to claim 4 is characterized in that: The Bayesian network adopts a two-stage reasoning structure, including: The forward reasoning stage estimates the state transition probability based on Markov chain Monte Carlo sampling; In the reverse correction stage, the wavelet basis function parameters are updated through the expectation maximization algorithm; A hybrid inference strategy is defined to weight the forward probability distribution and the reverse parameter correction result to output the final state compensation parameters.

9. The network-based intelligent fire hydrant abnormality detection system according to claim 5 is characterized in that: The virtual coordination variable adopts a hysteresis compensation mechanism, including: Measure the execution delay of control instructions of each node and construct a time-varying lag coefficient matrix; A hysteresis compensation term is introduced into the consensus algorithm, and the compensation gain coefficient is determined through stability analysis.

10. A network-based intelligent fire hydrant abnormality detection method, characterized in that: The following steps are involved: S1, collect water pressure data, flow data and environmental status data of fire hydrants through a multi-source sensor network; S2. Performing pattern recognition on the water pressure data and flow rate data based on an improved support vector machine to generate an abnormal feature vector including abnormal fluctuation characteristics and data correlation; S3, using wavelet transform algorithm to dynamically model the mechanical vibration signal and temperature drift parameters of the fire hydrant to generate real-time state compensation parameters; S4. According to the abnormal feature vector and state compensation parameters, a multi-node optimization decision model is constructed to generate global collaborative control instructions and a dynamic collaborative resource matching network.

Images