Fire-fighting equipment power supply monitoring method and system and medium

Abstract

The invention discloses a fire-fighting equipment power supply monitoring method and system and a medium, and relates to the technical field of data processing, the method comprises the following steps: interactively obtaining equipment information of fire-fighting equipment, and establishing a time sequence monitoring data set; acquiring node control signals and time sequence load data in the time sequence monitoring data set, performing dynamic and static mode judgment, and generating a dynamic and static mode judgment result; performing dynamic and static mode division on the data set by utilizing a judgment result, performing dynamic and static anomaly recognition by combining equipment information, and establishing joint recognition anomaly; and fire-fighting equipment power supply monitoring management is carried out based on the joint identification abnormity. According to the method, the technical problem that the accuracy and reliability of equipment monitoring are insufficient due to the fact that an existing method cannot accurately recognize abnormities of the equipment in different working states is solved, and the effects of accurately distinguishing abnormal performance of the equipment in different working states through dynamic and static mode judgment and combined abnormal recognition are achieved. And the accuracy and reliability of equipment monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly relates to a method, a system and a medium for monitoring the power supply of fire-fighting equipment. Background Art

[0002] In modern fire-fighting systems, the power supply monitoring of fire-fighting equipment is a key link to ensure the reliable operation of the equipment. With the increase in the complexity of fire-fighting systems, the networked deployment of equipment and the diversification of operating states have put forward higher requirements for power supply monitoring. However, the existing technologies mainly rely on static voltage and current monitoring, and can only detect obvious power failures, making it difficult to capture the dynamic changes, modal switches of the equipment operating states and the mutual influence between equipment. This limitation results in the monitoring system being unable to detect potential failures in a timely manner, affecting the stability and safety of fire-fighting equipment. Summary of the Invention

[0003] This application provides a method, a system and a medium for monitoring the power supply of fire-fighting equipment, which are used to solve the technical problem that the existing methods cannot accurately identify the anomalies of equipment in different working states, resulting in insufficient accuracy and reliability of equipment monitoring.

[0004] In the first aspect of this application, a method for monitoring the power supply of fire-fighting equipment is provided. The method includes: interactively obtaining the equipment information of the fire-fighting equipment, where the equipment information includes equipment basic attributes and topological structures; after deploying monitoring sensors, establishing a time-series monitoring data set; obtaining the node control signals and time-series load data of the time-series monitoring data set, performing static and dynamic mode discrimination according to the node control signals and the time-series load data, and establishing a static and dynamic mode discrimination result; after using the static and dynamic mode discrimination result to divide the time-series monitoring data set into static and dynamic modes, based on the static and dynamic mode division result and the equipment information, performing anomaly identification for both static and dynamic states, and establishing a combined identification anomaly; and performing equipment power supply monitoring and management of the fire-fighting equipment according to the combined identification anomaly.

[0005] In a second aspect of the present application, a power monitoring system for fire-fighting equipment is provided. The system includes: an equipment information interaction module configured to interactively obtain equipment information of fire-fighting equipment, where the equipment information includes equipment basic attributes and topological structures; a time-series data monitoring module configured to establish a time-series monitoring data set after deploying monitoring sensors; a dynamic and static mode discrimination module configured to obtain node control signals and time-series load data of the time-series monitoring data set, perform dynamic and static mode discrimination based on the node control signals and the time-series load data, and establish a dynamic and static mode discrimination result; a combined anomaly recognition module configured to perform dynamic and static mode partitioning on the time-series monitoring data set by using the dynamic and static mode discrimination result, and perform anomaly recognition in both dynamic and static modes based on the dynamic and static mode partitioning result and the equipment information, and establish a combined recognized anomaly; and a power monitoring management module configured to perform equipment power monitoring management of fire-fighting equipment according to the combined recognized anomaly.

[0006] In a third aspect of the present application, a computer-readable storage medium is provided. A computer program is stored on the storage medium, and when the computer program is executed by a processor, the method of the first aspect is implemented.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages: A method, system, and medium for monitoring the power supply of fire-fighting equipment provided by the present application relate to the technical field of data processing. By obtaining the basic attributes and topological structures of fire-fighting equipment, establishing a time-series monitoring data set after deploying sensors, obtaining node control signals and load data, performing dynamic and static mode discrimination, performing dynamic and static mode partitioning on the data set according to the discrimination result, combining equipment information for anomaly recognition, establishing a combined recognized anomaly, and performing equipment power monitoring management based on this, the technical problem that existing methods cannot accurately identify anomalies of equipment in different working states, resulting in insufficient accuracy and reliability of equipment monitoring is solved. The technical effect of accurately distinguishing anomaly manifestations of equipment in different working states through dynamic and static mode discrimination and combined anomaly recognition, and improving the accuracy and reliability of equipment monitoring is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0009] Figure 1 It is a schematic flowchart of a method for monitoring the power supply of fire-fighting equipment provided by an embodiment of the present application; Figure 2 This is a schematic structural diagram of a power supply monitoring system for fire-fighting equipment provided by an embodiment of the present application.

[0010] Explanation of reference numerals: Equipment information interaction module 11, timing data monitoring module 12, dynamic and static mode discrimination module 13, combined anomaly recognition module 14, power supply monitoring and management module 15. Detailed implementation manners

[0011] The present application provides a method, a system and a medium for monitoring the power supply of fire-fighting equipment, which are used to solve the technical problem that the existing method cannot accurately identify the anomalies of equipment in different working states, resulting in insufficient accuracy and reliability of equipment monitoring.

[0012] Next, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0013] It should be noted that the terms "first", "second", etc. in the specification and the above-mentioned accompanying drawings of the present application are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices.

[0014] Embodiment 1, as Figure 1 shown, the present application provides a method for monitoring the power supply of fire-fighting equipment, and the method includes: P10: Interactively obtain the equipment information of the fire-fighting equipment, where the equipment information includes equipment basic attributes and topological structures.

[0015] Specifically, first, it is necessary to obtain the equipment information of the fire-fighting equipment through an interaction interface. The equipment information can be divided into two categories: equipment basic attributes and topological structures.

[0016] The basic attributes of a device refer to the set of information inherent in a fire protection device that can identify its basic characteristics. These attributes usually include the device model, specifications, rated power, rated voltage, manufacturer, production date, installation location, etc. For example, the device model can clarify the type and function of the device, and the rated power and rated voltage are directly related to the normal operating conditions of the device. This basic attribute information provides the basic operating parameters and performance indicators of the device for the monitoring system, and is an important reference basis for subsequent data collection, analysis, and anomaly judgment.

[0017] The topology structure refers to the connection relationship and layout method of fire protection devices in the system. In a complex fire protection system, there are various connection relationships between devices, such as series connection, parallel connection, or networked connection, etc. The topology structure reflects the hierarchical relationship, communication path, and mutual dependence between devices. For example, in a fire pump system, multiple pumps may be connected in series or in parallel through pipes, and its topology structure determines the water flow distribution and control method. By obtaining the topology structure information of the device, the monitoring system can clearly understand the interaction relationship between devices, so as to accurately locate the fault point, analyze the abnormal propagation path, and take corresponding management measures during the monitoring process.

[0018] In the process of interactively obtaining device information, communication protocols and data interfaces can be used to achieve information exchange between the device and the monitoring system. The monitoring system interacts with the communication module of the fire protection device, sends request instructions according to the preset communication protocol, and the device then feeds back its basic attribute and topology structure information according to the instructions. This information is transmitted to the monitoring system in the form of data and stored in the database, providing basic data support for subsequent monitoring steps. This interactive acquisition method can not only ensure the accuracy and timeliness of information, but also adapt to different types of fire protection devices and complex system architectures, with good compatibility and scalability.

[0019] P20: After deploying the monitoring sensors, establish a time-series monitoring data set.

[0020] Furthermore, step P20 of the embodiment of the present application further includes: P21: Conduct joint verification self-check of the sensors on the monitoring sensors to generate joint verification self-check compensation; P22: After correcting the monitoring results according to the joint verification self-check compensation, establish the time-series monitoring data set.

[0021] Optionally, deploy monitoring sensors at key positions of the fire protection device. The monitoring sensor is the core component for real-time collection of device operation status data, and these data include but are not limited to physical quantities such as voltage, current, load, temperature, vibration, etc. The selection and layout of the sensors need to be determined according to the actual needs and working environment of the device to ensure that the operation status of the device can be comprehensively and accurately reflected.

[0022] After deploying the sensors, in order to ensure the reliability of the sensors and the accuracy of data collection, it is necessary to conduct a joint verification self-check on the sensors. The joint verification self-check refers to verifying the working status and data accuracy of each sensor through data comparison and coordination among multiple sensors. Specifically, a set of known standards or reference signals can be set, and combined with the results collected by different sensors, to determine whether there are faults or deviations. If the data of a certain sensor is abnormal, its error can be identified and corrected by comparing and analyzing it with the data of other sensors. The key purpose of this step is to ensure that the sensors can work properly in actual applications, and to avoid low data accuracy caused by sensor failures, thus affecting the subsequent analysis and monitoring effects.

[0023] After completing the joint verification self-check of the sensors, the monitoring results are corrected according to the generated joint verification self-check compensation. The self-check compensation refers to correcting the output data of the sensors according to the verification self-check results, making the data more accurate and eliminating the influence caused by sensor errors, drifts or environmental changes. The compensation parameters can be automatically calculated by an algorithm and applied to the correction of real-time monitoring data. For example, if there is a systematic deviation in the measured value of a certain current sensor, the deviation can be corrected through the joint verification self-check compensation, making the corrected data closer to the true value. After data correction, the corrected data of each sensor can be summarized and stored in chronological order, and finally a complete chronological monitoring data set is established. This data set not only contains the original data of the equipment operation, but also has been error-corrected, so it has higher accuracy and reliability. The chronological monitoring data set established in this way can provide higher-quality data support for subsequent dynamic and static mode discrimination and anomaly identification, thus improving the performance and reliability of the entire monitoring system.

[0024] P30: Obtain the node control signal and chronological load data of the chronological monitoring data set, and conduct dynamic and static mode discrimination according to the node control signal and the chronological load data, and establish the dynamic and static mode discrimination result.

[0025] Specifically, it is first necessary to extract the node control signal and chronological load data from the chronological monitoring data set. The node control signal can be obtained through the control system of the fire-fighting equipment, and can reflect the operation instructions and status changes of the equipment, such as switch signals, working mode switching signals, etc. These signals can indicate whether the equipment is in the running state, standby state or off state. The chronological load data is the equipment operation data collected by the monitoring sensors in real time, mainly including electrical parameters such as current and voltage, and can reflect the load changes of the equipment.

[0026] Next, based on the obtained node control signals and timing load data, the discrimination of dynamic and static modes is carried out. Specifically, by analyzing the node control signals, it can be preliminarily judged whether the device is in an operating state. If the control signal indicates that the device is under a start or run command, it is preliminarily determined that the device is in a dynamic mode; conversely, if the control signal shows that the device is in a standby or stop state, it is preliminarily determined that the device is in a static mode. However, relying solely on the node control signals for mode discrimination may have errors, so it is necessary to combine the timing load data for further verification. In the dynamic mode, the timing load data of the device usually shows obvious fluctuations or change trends, such as increases or decreases in current and power; while in the static mode, the timing load data is relatively stable with less change. By comprehensively analyzing the node control signals and the timing load data, the true operating mode of the device can be determined more accurately. If the discrimination results of both are consistent, the mode of the device is confirmed; if they are inconsistent, the abnormal conditions of the data need to be further analyzed to ensure the accuracy of mode discrimination.

[0027] Finally, based on the results of the above comprehensive analysis, the discrimination results of dynamic and static modes are established. This result will serve as an important basis for subsequent steps and be used to guide operations such as anomaly recognition and monitoring management. Through this process, the dynamic and static operating states of the device can be accurately distinguished, providing strong support for realizing efficient power monitoring of fire-fighting equipment.

[0028] P40: After dividing the timing monitoring data set into dynamic and static modes by using the discrimination results of dynamic and static modes, based on the division results of dynamic and static modes and the device information, anomaly recognition of dynamic and static states is carried out to establish a combined recognition anomaly.

[0029] Furthermore, step P40 of the embodiment of the present application further includes: P41: Obtain the static mode division result, perform the associated recognition of mode conversion of the static mode division result, and reconstruct the static mode period according to the associated recognition result; P42: Set a time sliding window in the reconstructed static mode period, perform static feature recognition based on the time sliding window, and establish a static feature perception result; P43: Perform perception fluctuation recognition on the static feature perception result to establish a first recognition anomaly; P44: Perform common cause interference recognition on the static feature perception result according to the topological structure to establish a second recognition anomaly, and the second recognition anomaly is a position association anomaly; P45: Establish a static recognition anomaly according to the first recognition anomaly and the second recognition anomaly; P46: Use the static recognition anomaly to establish a combined recognition anomaly.

[0030] It should be understood that based on the above-mentioned dynamic and static mode discrimination results, the time-series monitoring data set is divided into dynamic and static modes, and the time-series monitoring data is divided into two types: dynamic and static data, so that the data in different modes can be analyzed and processed independently. By dividing the time-series data into dynamic and static modes, the system can more accurately identify the device behavior characteristics in different working states, and provide a clear data distribution and processing basis for subsequent anomaly identification.

[0031] After completing the dynamic and static mode discrimination, first use the discrimination results to divide the time-series monitoring data set into dynamic and static modes. For the static mode division results, further perform modal conversion correlation identification. This is to identify the possible modal conversion situations of the device in the static mode, such as the transition process when the device switches from the dynamic mode to the static mode. Through modal conversion correlation identification, the characteristic changes of the device during the modal switch can be analyzed, and the static mode period can be reconstructed accordingly. The reconstructed static mode period can more accurately reflect the stable operation stage of the device in the static mode, providing a more accurate time range for subsequent anomaly identification.

[0032] Next, within the reconstructed static mode period, set a time sliding window. The time sliding window is a data processing technique that can perform local analysis on the data within the window by sliding a time window of a fixed length in the time-series data. Based on the time sliding window for static feature recognition, the stable features of the power supply parameters of the device in the static mode can be captured, such as the average value and variance of current and voltage. Through this process, the static feature perception results are established, providing basic data for subsequent anomaly identification.

[0033] Immediately afterwards, perform perception fluctuation identification on the static feature perception results to detect whether there are abnormal fluctuations in the power supply parameters of the device in the static mode. For example, if there are unexpected mutations or fluctuations in the current or voltage in the static mode, it may indicate that there is a potential fault in the device. Through perception fluctuation identification, the first identified anomalies are established, which are identified based on the fluctuation conditions of the device's own operation characteristics.

[0034] At the same time, based on the topological structure, perform common cause interference identification on the static feature perception results, focusing on identifying location-related anomalies. Location-related anomalies refer to the abnormal performance of a device being associated with its location due to the interaction between devices or the interference of environmental factors. Since there are connection relationships and hierarchical structures among fire-fighting devices, the anomaly of one device may affect other devices connected to it. Through common cause interference identification, the mutual influence between devices can be analyzed, and location-related anomalies, that is, the second identified anomalies, can be identified.

[0035] Combine the first recognition anomaly and the second recognition anomaly to establish a static recognition anomaly. The static recognition anomaly covers the abnormal fluctuations of the device's own operating characteristics and the comprehensive situation of the associated faults between devices. On this basis, use the static recognition anomaly to establish a combined recognition anomaly, providing comprehensive and accurate anomaly information for subsequent fire equipment power monitoring and management.

[0036] Finally, combine the static recognition anomaly results with the dynamic recognition anomaly to finally form a combined recognition anomaly. This combined recognition anomaly is not just a separate recognition of anomalies in the static and dynamic modes, but by integrating the anomaly recognition results in the static and dynamic modes, it provides an all-round and accurate basis for anomaly judgment, which can provide reliable technical support for the subsequent fault warning and power management of the system, ensuring that the device can respond in a timely manner when anomalies occur and take necessary maintenance measures.

[0037] Furthermore, step P42 of the embodiment of the present application further includes: P42-1: Slide the time window. The time window is a multi-scale time window, and each moment is covered by the multi-scale time window; P42-2: Within each time window, perform voltage stability feature, current residue feature, temperature rise trend feature, resistance calculation feature, and time-frequency domain feature extraction, and establish a static feature perception result according to the feature extraction result.

[0038] Specifically, the process of static feature recognition can be further refined to achieve a refined perception of the device operation state in the static mode.

[0039] When performing static feature recognition, first perform a sliding window operation on the time window to cover the time series data through a multi-scale time window. This time window is a multi-scale time window, that is, it contains sliding windows of different time lengths. For example, short time windows are used to capture rapidly changing features, and long time windows are used to analyze long-term trends. By setting a multi-scale time window and ensuring that each moment is covered by the multi-scale time window, the operating characteristics of the device at different time scales in the static mode can be comprehensively captured. The core advantage of this method is that it can simultaneously analyze the small changes and large fluctuations in the time series, helping to more accurately identify abnormal behaviors in the static operation process of the device. It can effectively handle various abnormal situations that may occur during the device operation. Whether it is instantaneous fluctuations or long-term trend changes, they can be accurately detected. Specifically, the movement process of the time window is continuous, and each time point will be covered by at least one time window, thus ensuring the integrity and continuity of the data.

[0040] Next, within each time window, further perform a variety of feature extraction operations to obtain the detailed operating characteristics of the device in the static mode. The specific feature extraction operations include the following aspects: Voltage stability feature extraction: By analyzing the voltage data within a time sliding window, statistical parameters such as the fluctuation range, mean, and variance of the voltage are calculated to evaluate the voltage stability. Voltage stability is an important indicator for judging whether the power supply state of the device is normal. A stable voltage indicates that the device is in a good operating state. If the voltage fluctuation exceeds the preset threshold range, it may indicate that there is a problem with the power supply instability of the device and further attention is required.

[0041] Current residue feature extraction: Calculate the residue value of the current within a time sliding window, that is, the difference between the actual measured value and the theoretical value of the current. The current residue feature can reflect whether there are abnormal load conditions in the device, such as whether there is leakage or short circuit. By comparing the difference between the actual current and the theoretical current, potential electrical faults in the device under the static mode can be identified.

[0042] Temperature rise trend feature extraction: Analyze the change trend of the device temperature within a time sliding window. By calculating parameters such as the temperature rise rate and the maximum temperature rise, it is judged whether the device has an overheating risk. The temperature rise trend feature is of great significance for early detection of potential faults in the device because overheating is often a precursor to device faults. By monitoring the change trend of the temperature, it can be timely found whether there is an overheating problem in the device under the static mode, and corresponding measures can be taken.

[0043] Resistance calculation feature extraction: Based on Ohm's law, the resistance value of the device is calculated by measuring voltage and current data, and the change trend of the resistance is analyzed. The resistance calculation feature can help identify whether there are problems such as poor contact or material aging inside the device. By calculating the resistance value and monitoring its change, it can be judged whether the electrical connection of the device is normal and whether there is an increase in resistance caused by aging.

[0044] Time-frequency domain feature extraction: Convert the data within a time sliding window into the time-frequency domain, for example, through Fourier transform or wavelet transform, to extract the frequency components and time-frequency features of the device operation signal. Time-frequency domain feature extraction can reveal hidden periodic or non-periodic changes during the device operation, providing richer information for anomaly identification. By analyzing the frequency components of the signal, it can be identified whether there are abnormal frequency fluctuations or noise interferences in the device under the static mode.

[0045] Through the above feature extraction process, the system can comprehensively capture the performance of the device in the static working state from different dimensions. Based on the extraction results of these static features, a static feature perception result is finally established. Through this refined feature extraction method, this application can more sensitively capture the abnormal conditions of the device in the static mode, thereby improving the accuracy and reliability of anomaly identification and further ensuring the stable operation of fire-fighting equipment.

[0046] Furthermore, step P46 of the embodiment of this application further includes: P46-1: Establish a standard dynamic response behavior chain for fire-fighting equipment based on the device information; P46-2: Extract key feature indicators from the standard dynamic response behavior chain to establish a key feature indicator family; P46-3: After performing feature extraction on the results of dynamic mode division based on the key feature indicator family, execute dynamic anomaly annotation to establish dynamic recognition anomalies; P46-4: Establish the combined recognition anomalies based on the static recognition anomalies and the dynamic recognition anomalies.

[0047] Optionally, the process of establishing combined recognition anomalies can be further improved to form comprehensive combined recognition anomalies.

[0048] During the process of establishing combined recognition anomalies, first establish a standard dynamic response behavior chain for fire-fighting equipment according to the device information. The device information includes the basic attributes of the device, the topological structure, and historical operation data, etc. These information provide a basis for defining the dynamic behavior pattern of the device in the normal operation state. The standard dynamic response behavior chain refers to the typical change sequence of power supply parameters (such as current, voltage, power, etc.) during the entire process from startup to stable operation after the device receives a control signal. For example, when a fire pump starts, the current will increase instantaneously and then gradually stabilize. The parameter change sequence of this process is the standard dynamic response behavior chain. By analyzing the historical operation data and design parameters of the device, the standard dynamic response behavior chain of each device can be constructed.

[0049] Next, extract key feature indicators from the standard dynamic response behavior chain to establish a key feature indicator family. The key feature indicators refer to the parameters that can significantly reflect the dynamic behavior characteristics of the device, such as startup time, current peak value, voltage stabilization time, etc. By analyzing the standard dynamic response behavior chain, these key feature indicators are extracted and combined into a key feature indicator family. For example, for a fire pump, its key feature indicator family may include the startup current peak value, current stabilization time, voltage fluctuation range, etc. These key feature indicator families can provide clear guidance for feature extraction of the dynamic mode division results, ensuring the accuracy and consistency of feature extraction.

[0050] Based on the key feature index family, feature extraction is performed on the dynamic mode division results. In the dynamic mode, the operating state of the device is dynamically changing, so it is necessary to extract features related to dynamic behavior. By analyzing the time-series monitoring data in the dynamic mode division results, the actual operating parameters corresponding to the key feature indicators are extracted. For example, parameters such as the actual current peak value and the current stabilization time during the startup process of the device are extracted and compared with the key feature indicators in the standard dynamic response behavior chain. If there are significant deviations between the actual operating parameters and the key feature indicators in the standard dynamic response behavior chain, dynamic anomaly annotation is performed to establish dynamic recognition anomalies. Dynamic anomaly annotation refers to marking the operating state that does not conform to the standard behavior chain as an abnormal state and recording the specific features and occurrence time of the anomaly. For example, if the startup current peak value of the device exceeds the standard range or the current stabilization time is too long, these situations are marked as dynamic anomalies, and the relevant parameters and time information are recorded to form dynamic recognition anomalies.

[0051] Finally, based on the static recognition anomalies and the dynamic recognition anomalies, a combined recognition anomaly is established. The combined recognition anomaly is the result of comprehensively analyzing and integrating the abnormal situations in the static mode and the dynamic mode. By comparing the static recognition anomalies and the dynamic recognition anomalies, the abnormal situations of the device in different operating modes can be comprehensively understood, so as to provide more comprehensive and accurate abnormal information for the power supply monitoring and management of fire-fighting equipment. For example, if there is a voltage fluctuation anomaly in the static mode and a startup current anomaly in the dynamic mode for the device, the combined recognition anomaly will include both of these abnormal situations and provide detailed abnormal features and time information, so that the monitoring system can take corresponding measures for processing.

[0052] Furthermore, step P46-4 of the embodiment of the present application further includes: P46-41: Perform abnormal time positioning on the static recognition anomaly and the dynamic recognition anomaly; P46-42: Perform static and dynamic anomaly correlation analysis according to the abnormal time positioning result, and generate the combined recognition anomaly according to the static and dynamic anomaly correlation analysis result.

[0053] Specifically, in order to further improve the accuracy and practicality of the combined recognition anomaly, first perform abnormal time positioning on the static recognition anomaly and the dynamic recognition anomaly. Abnormal time positioning refers to accurately locating the time point when the anomaly occurs by analyzing the abnormal data identified in the static and dynamic modes. The core task of this step is to determine the specific positions of these anomalies on the time axis according to the timestamp information in the monitoring data and in combination with the characteristics of the static and dynamic anomalies. For example, the device may exhibit abnormal voltage fluctuations or load changes within a specific time period, and abnormal time positioning helps to determine the occurrence time of these behaviors. Through accurate time positioning, a clear time reference can be provided for tracking the anomaly source and subsequent processing, avoiding time ambiguity in the anomaly recognition results.

[0054] Next, perform dynamic and static anomaly correlation analysis based on the anomaly time localization result. Dynamic and static anomaly correlation analysis refers to analyzing the temporal correlation between static anomalies and dynamic anomalies to determine whether there is a causal relationship or mutual influence between them. For example, if an abnormal current is detected during the device startup process (dynamic mode), and an abnormal voltage fluctuation is detected after the device enters the stable operation stage (static mode), through correlation analysis, it can be determined whether these two anomalies are caused by the same fault source. If there is an obvious sequence or overlapping time period between the two anomalies in terms of time, and their correlation can be inferred from the device operation logic, they can be regarded as correlated anomalies. For example, the abnormal current during device startup may cause voltage fluctuations during the subsequent operation of the device. In this case, there is a causal relationship between the dynamic anomaly and the static anomaly.

[0055] Finally, generate a combined recognized anomaly based on the results of the dynamic and static anomaly correlation analysis. The combined recognized anomaly is the final anomaly result formed by comprehensively considering the correlation between static and dynamic anomalies. If there is a correlation between the static anomaly and the dynamic anomaly, they are merged into a combined recognized anomaly, and detailed information such as the type of anomaly, occurrence time, affected range, and possible fault causes is recorded. For example, if the correlation analysis shows that the abnormal current during device startup leads to subsequent voltage fluctuations, the combined recognized anomaly will include detailed information about the startup current anomaly and the voltage fluctuation anomaly, and indicate the causal relationship between them. If there is no obvious correlation between the static anomaly and the dynamic anomaly, they are recorded as independent anomaly events and listed separately in the combined recognized anomaly. In this way, the combined recognized anomaly can comprehensively and accurately reflect the abnormal conditions of the device in different operation modes, provide more detailed and targeted anomaly information for the power supply monitoring and management of fire-fighting equipment, and thus help the monitoring system take effective measures in a timely manner for fault troubleshooting and handling to ensure the safe operation of fire-fighting equipment.

[0056] Furthermore, using the static recognized anomaly to establish the combined recognized anomaly, the embodiment of the present application further includes step P46a, and step P46a further includes: P46-1a: Create a transition mode period according to the correlation recognition result; P46-2a: Analyze the mode conversion transition behavior of the fire-fighting equipment for the transition mode period to establish an auxiliary recognized anomaly; P46-3a: Compensate the combined recognized anomaly using the auxiliary recognized anomaly.

[0057] In a possible embodiment of the present application, by creating a transition mode period, analyzing the mode conversion transition behavior, and compensating the combined recognized anomaly, the accuracy and integrity of anomaly recognition can be further improved.

[0058] First, create a transition mode period based on the associated recognition result. The transition mode period refers to the dynamic characteristics exhibited by a device during the conversion of its state from one working mode to another. Exemplarily, it is the characteristic information of the device during the mode conversion obtained through the associated recognition of the static mode division result. These characteristic information reflect the behavioral changes of the device when switching from one operating mode (such as the dynamic mode) to another mode (such as the static mode). Based on these associated recognition results, the time range of the device during the mode conversion can be determined, thereby creating a transition mode period. Creating a transition mode period can help the system model and analyze these changes, so as to better understand the behavioral performance of the device during the transition period and provide a reference basis for subsequent anomaly recognition.

[0059] Next, conduct an analysis of the transition behavior of the fire-fighting equipment during the transition mode period to establish auxiliary anomaly recognition. The analysis of the transition behavior during the mode conversion refers to a detailed analysis of the change characteristics of the power supply parameters of the device during the mode conversion process. For example, when the device switches from the dynamic mode to the static mode, the current and voltage may undergo a rapid change process, and the parameter changes during this process may contain abnormal information. By analyzing the change trends, change rates, and fluctuation conditions of parameters such as current, voltage, and power within the transition mode period, abnormal behaviors that may occur during the mode conversion of the device can be identified, including sudden current changes, abnormal voltage fluctuations, abnormal power drops, etc. These abnormal behaviors are recorded as auxiliary anomaly recognition, which serves as a supplementary recognition of the abnormal conditions of the device during the mode conversion process and can provide potential problems that may occur during the switching process between the dynamic and static modes of the device.

[0060] Finally, use the established auxiliary anomaly recognition to compensate for the combined anomaly recognition. The combined anomaly recognition is the comprehensive result of anomaly recognition in the static, dynamic, and transition modes. However, anomalies during the transition period may be overlooked during the static and dynamic recognition processes. Therefore, by combining and compensating the auxiliary anomaly recognition with the combined anomaly recognition, the latent problems that may occur during the mode conversion of the device can be further accurately identified. For example, if an abnormal behavior of sudden current change is detected during the mode conversion process, and this abnormal behavior is not fully considered in the static anomaly recognition and dynamic anomaly recognition, then this auxiliary anomaly recognition can be added to the combined anomaly recognition to improve the content of the combined anomaly recognition. In this way, the combined anomaly recognition can more comprehensively reflect the abnormal conditions of the device in different operating modes and during the mode conversion process, provide more accurate and complete abnormal information for the power supply monitoring and management of fire-fighting equipment, and further improve the reliability and safety of the system.

[0061] P50: Conduct device power supply monitoring and management of fire-fighting equipment according to the combined anomaly recognition.

[0062] Furthermore, step P50 of the embodiment of the present application further includes: P51: Establish a three - level early warning discrimination index; P52: Use the three - level early warning discrimination index to perform early warning level discrimination on the combined identification of anomalies, and establish an early warning level discrimination result; P53: Establish an early warning anomaly according to the early warning level discrimination result.

[0063] Specifically, according to the combined identification of anomalies, power monitoring and management of fire - fighting equipment are carried out. That is, according to the abnormal identification result of the equipment state, corresponding management measures are taken to ensure the stable operation of the equipment and timely prevent potential failure risks.

[0064] Specifically, in the process of implementing power monitoring and management of fire - fighting equipment, a three - level early warning discrimination index is first established. The three - level early warning discrimination index divides anomalies into three different early warning levels according to factors such as the severity of the anomaly, the scope of influence, and potential risks, usually the low, medium, and high levels. Each level corresponds to different discrimination criteria, which are formulated based on factors such as the abnormal characteristics, occurrence frequency, duration, and impact on equipment operation in the combined identification of anomalies. For example, a low - level early warning may correspond to occasional minor voltage fluctuations, which have little impact on the normal operation of the equipment; a medium - level early warning may correspond to frequent current anomalies or local overheating of temperature rise, etc., which may have a certain impact on the long - term stability of the equipment; a high - level early warning corresponds to serious power failures, equipment overheating, or critical parameters seriously deviating from the normal range, etc., which may cause the equipment to stop running immediately or lead to more serious safety problems.

[0065] Next, use the established three - level early warning discrimination index to perform early warning level discrimination on the combined identification of anomalies, that is, analyze the abnormal characteristics in the combined identification of anomalies, compare them with the three - level early warning discrimination index, so as to determine the early warning level of each abnormal event. For example, if the combined identification of anomalies includes an abnormal starting current of the equipment, and the frequency of this anomaly is high and the duration is long, according to the three - level early warning discrimination index, it may be discriminated as a medium - level early warning; if the combined identification of anomalies includes a sudden large - scale voltage drop during the operation of the equipment, accompanied by the equipment stopping running, according to the discrimination index, it may be discriminated as a high - level early warning. Through this systematic discrimination method, it can ensure that the division of early warning levels has a clear basis and consistency, providing accurate guidance for subsequent monitoring and management.

[0066] Finally, based on the discrimination results of the warning levels, warning anomalies are established. This is the result of classifying and recording the combined recognition anomalies according to the warning levels, providing clear priorities and response strategies for monitoring and management. For example, for high-level warning anomalies, the monitoring system can immediately trigger an emergency alarm, notify relevant personnel to conduct on-site inspections and handling, and may also take automatic protection measures, such as cutting off the power supply to prevent equipment damage or safety accidents; for medium-level warning anomalies, the monitoring system can issue a warning prompt, suggesting that relevant personnel conduct regular inspections and maintenance to avoid the further deterioration of abnormal situations; for low-level warning anomalies, the monitoring system can record the abnormal situations for subsequent analysis and reference, but usually no immediate measures are required. By establishing warning anomalies, the monitoring system can take corresponding management measures according to the severity of the anomalies, ensuring that the power supply monitoring and management of fire-fighting equipment are both targeted and can effectively guarantee the safe operation of the equipment.

[0067] In summary, through these steps, comprehensive power supply monitoring and management of fire-fighting equipment can be achieved. It can not only accurately identify equipment anomalies, but also classify and warn according to the severity of the anomalies, and timely respond to potential risks through effective warning measures, ensuring the continuous and stable operation of the equipment.

[0068] In summary, the embodiments of the present application at least have the following technical effects: Through static and dynamic modal discrimination, the present application can accurately distinguish the abnormal manifestations of fire-fighting equipment in different working states, solving the problem that the prior art cannot accurately identify the equipment state; by combining time-series monitoring data and equipment information, real-time monitoring of the equipment power supply is realized, and potential anomalies can be discovered and identified in a timely manner to ensure the stable operation of the equipment; based on the basic attributes, topological structure and monitoring data of the equipment, the system can perform multi-dimensional anomaly identification, thereby improving the accuracy and comprehensiveness of anomaly detection; by combining static and dynamic modal division and combined recognition anomaly method, comprehensive monitoring of the equipment in static and dynamic states is provided, avoiding the neglect of dynamic anomalies by traditional methods; through the combined recognition anomaly results, intelligent power management can be carried out according to the anomaly level, and corresponding measures can be taken in a timely manner to ensure the stability and safety of the equipment power supply.

[0069] It achieves the technical effect of accurately distinguishing the abnormal manifestations of the equipment in different working states through static and dynamic modal discrimination and combined recognition of anomalies, and improving the accuracy and reliability of equipment monitoring.

[0070] Embodiment 2, based on the same inventive concept as the method for monitoring the power supply of a fire-fighting equipment in the foregoing embodiment, as Figure 2 shown, the present application provides a system for monitoring the power supply of a fire-fighting equipment. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes: Device information interaction module 11, which is used to interactively obtain the device information of fire-fighting equipment, and the device information includes device basic attributes and topological structure.

[0071] Timing data monitoring module 12, which is used to establish a timing monitoring data set after deploying monitoring sensors.

[0072] Dynamic and static mode discrimination module 13, which is used to obtain the node control signal and timing load data of the timing monitoring data set, perform dynamic and static mode discrimination according to the node control signal and the timing load data, and establish a dynamic and static mode discrimination result.

[0073] Joint anomaly recognition module 14, which is used to perform dynamic and static mode division on the timing monitoring data set by using the dynamic and static mode discrimination result, and perform anomaly recognition in both dynamic and static states based on the dynamic and static mode division result and the device information, and establish a joint recognition anomaly.

[0074] Power supply monitoring and management module 15, which is used to perform device power supply monitoring and management of fire-fighting equipment according to the joint recognition anomaly.

[0075] Furthermore, the timing data monitoring module 12 is also used to perform the following steps: Perform joint verification and self-check of the monitoring sensors to generate joint verification and self-check compensation; after correcting the monitoring results according to the joint verification and self-check compensation, establish the timing monitoring data set.

[0076] Furthermore, the joint anomaly recognition module 14 is also used to perform the following steps: Obtain the static mode division result, perform modal conversion correlation recognition of the static mode division result, reconstruct the static mode period according to the correlation recognition result; set a time sliding window in the reconstructed static mode period, perform static feature recognition based on the time sliding window, and establish a static feature perception result; perform perception fluctuation recognition on the static feature perception result to establish a first recognition anomaly; perform common cause interference recognition of the static feature perception result according to the topological structure to establish a second recognition anomaly, and the second recognition anomaly is a position correlation anomaly; establish a static recognition anomaly according to the first recognition anomaly and the second recognition anomaly; establish a joint recognition anomaly by using the static recognition anomaly.

[0077] Furthermore, the joint anomaly recognition module 14 is also used to perform the following steps: Slide the time sliding window, where the time sliding window is a multi-scale time window and each moment is covered by the multi-scale time window; within each time sliding window, perform feature extraction of voltage stability characteristics, current residue characteristics, temperature rise trend characteristics, resistance calculation characteristics, and time-frequency domain characteristics, and establish a static feature perception result according to the feature extraction results.

[0078] Further, the joint anomaly recognition module 14 is further configured to perform the following steps: Establish a standard dynamic response behavior chain of the fire-fighting equipment according to the equipment information; extract key feature indicators from the standard dynamic response behavior chain to establish a key feature indicator family; after performing feature extraction on the dynamic mode division result based on the key feature indicator family, perform dynamic anomaly annotation to establish dynamic recognition anomalies; establish the joint recognition anomalies according to the static recognition anomalies and the dynamic recognition anomalies.

[0079] Further, the joint anomaly recognition module 14 is further configured to perform the following steps: Perform anomaly time positioning on the static recognition anomalies and the dynamic recognition anomalies; perform static-dynamic anomaly correlation analysis according to the anomaly time positioning result, and generate the joint recognition anomalies according to the static-dynamic anomaly correlation analysis result.

[0080] Further, the joint anomaly recognition module 14 is further configured to perform the following steps: Create a transition mode period according to the associated recognition result; perform analysis on the modal conversion transition behavior of the fire-fighting equipment for the transition mode period to establish auxiliary recognition anomalies; use the auxiliary recognition anomalies to compensate the joint recognition anomalies.

[0081] Further, the joint anomaly recognition module 14 is further configured to perform the following steps: Establish a three-level early warning discrimination index; use the three-level early warning discrimination index to perform early warning level discrimination on the joint recognition anomalies to establish an early warning level discrimination result; establish early warning anomalies according to the early warning level discrimination result.

[0082] Further, the power supply monitoring and management module 15 is further configured to perform the following steps: Perform joint verification self-check of the monitoring sensors to generate joint verification self-check compensation; after correcting the monitoring results according to the joint verification self-check compensation, establish the time series monitoring data set.

[0083] Embodiment 3, based on the same inventive concept as a fire-fighting equipment power supply monitoring method in the foregoing embodiments, the present application further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method in Embodiment 1 is implemented.

[0084] Through the foregoing detailed description of a method for monitoring the power supply of fire-fighting equipment, those skilled in the art can clearly know a method, a system and a medium for monitoring the power supply of fire-fighting equipment in this embodiment. Therefore, for the sake of brevity of the specification, it will not be described in detail here. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0085] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0086] It should be noted that the above sequence of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the specific embodiments of this specification have been described. Further, the processes depicted in the accompanying drawings do not necessarily require the particular order or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0087] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0088] This specification and the drawings are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for monitoring the power supply of fire-fighting equipment, characterized in that, The method includes: Interactively obtaining the device information of fire-fighting equipment, where the device information includes device basic attributes and topological structure; After deploying monitoring sensors, establishing a time-series monitoring data set; Obtaining the node control signal and time-series load data of the time-series monitoring data set, performing dynamic and static modal discrimination based on the node control signal and the time-series load data, and establishing a dynamic and static modal discrimination result; After performing dynamic and static modal partitioning on the time-series monitoring data set using the dynamic and static modal discrimination result, performing abnormal identification of dynamic and static states based on the dynamic and static modal partitioning result and the device information, and establishing a combined identification of abnormality; Performing device power monitoring and management of fire-fighting equipment according to the combined identification of abnormality.

2. The method for monitoring the power supply of a fire-fighting device according to claim 1, characterized in that, The performing abnormal identification of dynamic and static states based on the dynamic and static modal partitioning result and the device information, and establishing a combined identification of abnormality includes: Obtaining the static modal partitioning result, performing modal conversion correlation identification of the static modal partitioning result, and reconstructing the static modal period according to the correlation identification result; Setting a time sliding window in the reconstructed static modal period, performing static feature identification based on the time sliding window, and establishing a static feature perception result; Performing perception fluctuation identification on the static feature perception result, and establishing a first identification of abnormality; Performing common cause interference identification of the static feature perception result according to the topological structure, and establishing a second identification of abnormality, where the second identification of abnormality is a location correlation abnormality; Establishing a static identification of abnormality according to the first identification of abnormality and the second identification of abnormality; Establishing a combined identification of abnormality using the static identification of abnormality.

3. A method for monitoring the power supply of a fire-fighting device according to claim 2, characterized in that, The performing static feature identification based on the time sliding window, and establishing a static feature perception result includes: Moving the time sliding window, where the time sliding window is a multi-scale time window, and each moment is covered by the multi-scale time window; Within each time sliding window, performing extraction of voltage stability feature, current residue feature, temperature rise trend feature, resistance calculation feature, and time-frequency domain feature, and establishing a static feature perception result according to the feature extraction result.

4. The method for monitoring the power supply of a fire-fighting device according to claim 2, characterized in that, The establishing a combined identification of abnormality using the static identification of abnormality includes: Establishing a standard dynamic response behavior chain of fire-fighting equipment according to the device information; Extracting key feature indicators from the standard dynamic response behavior chain, and establishing a key feature indicator family; After performing feature extraction on the dynamic modal partitioning result based on the key feature indicator family, performing dynamic abnormality annotation, and establishing a dynamic identification of abnormality; Establishing the combined identification of abnormality according to the static identification of abnormality and the dynamic identification of abnormality.

5. The method for monitoring the power supply of a fire-fighting equipment according to claim 4, wherein, The establishing the combined identification of abnormality according to the static identification of abnormality and the dynamic identification of abnormality includes: Performing abnormal time positioning on the static identification of abnormality and the dynamic identification of abnormality; Performing dynamic and static abnormality correlation analysis according to the abnormal time positioning result, and generating the combined identification of abnormality according to the dynamic and static abnormality correlation analysis result.

6. The method for monitoring the power supply of fire-fighting equipment according to claim 2, characterized in that, The establishing a combined identification of abnormality using the static identification of abnormality further includes: Creating a transition modal period according to the correlation identification result; Performing modal conversion transition behavior analysis of fire-fighting equipment on the transition modal period, and establishing an auxiliary identification of abnormality; Compensating the combined identification of abnormality using the auxiliary identification of abnormality.

7. A method for monitoring the power supply of a fire-fighting equipment according to claim 1, characterized in that, Performing device power monitoring and management of fire-fighting equipment according to the combined anomaly recognition, including: Establishing a three-level early warning discrimination index; Using the three-level early warning discrimination index to perform early warning level discrimination on the combined anomaly recognition and establishing an early warning level discrimination result; Establishing an early warning anomaly according to the early warning level discrimination result.

8. A method for monitoring the power supply of a fire-fighting device according to claim 1, characterized in that, After deploying the monitoring sensors, establishing a time-series monitoring data set, including: Performing combined verification and self-check on the monitoring sensors to generate combined verification and self-check compensation; After correcting the monitoring results according to the combined verification and self-check compensation, establishing the time-series monitoring data set.

9. A power monitoring system for fire-fighting equipment, characterized in that, The system includes: An equipment information interaction module, which is used to interactively obtain the equipment information of fire-fighting equipment, and the equipment information includes equipment basic attributes and topological structures; A time-series data monitoring module, which is used to establish a time-series monitoring data set after deploying the monitoring sensors; A static and dynamic mode discrimination module, which is used to obtain the node control signal and time-series load data of the time-series monitoring data set, perform static and dynamic mode discrimination according to the node control signal and the time-series load data, and establish a static and dynamic mode discrimination result; A combined anomaly recognition module, which is used to perform static and dynamic mode division on the time-series monitoring data set by using the static and dynamic mode discrimination result, and perform static and dynamic dual-mode anomaly recognition based on the static and dynamic mode division result and the equipment information to establish a combined recognition anomaly; A power monitoring and management module, which is used to perform device power monitoring and management of fire-fighting equipment according to the combined recognition anomaly.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the storage medium, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images