Intelligent power management and control system for urban rail video monitoring system

Abstract

The invention discloses an intelligent power management and control system for an urban rail video monitoring system, and relates to the technical field of urban rail transit operation and maintenance. The system comprises a data acquisition unit, a strategy construction unit, an abnormity identification unit, a feature extraction unit, a demand determination unit and a power supply regulation and control unit. The strategy construction unit is used for constructing a dynamic power supply strategy model based on the collected data and simulating power supply demand changes of the monitoring equipment in different scenes; and the abnormity identification unit is used for matching the real-time acquired data with the dynamic power supply strategy model and identifying an abnormal behavior deviating from the expected power supply mode. According to the invention, by means of the multi-system intelligent linkage capability, third-party subsystems such as fire alarm and access control are deeply integrated, the power supply priority is dynamically optimized according to the event type, position and severity, it is ensured that the monitoring equipment can be rapidly and accurately activated in an emergency scene, and the timeliness and pertinence of overall safety response are enhanced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of urban rail transit operation and maintenance technology, and particularly relates to an intelligent power management and control system for a city rail video monitoring system. BACKGROUND

[0002] With the rapid expansion of urban rail transit networks, as a key infrastructure to ensure operational safety, the deployment scale and complexity of video monitoring systems continue to increase. Front-end monitoring devices are usually installed in outdoor equipment boxes and rely on traditional power management systems for unified power supply. However, the existing power supply mode generally adopts a 7x24-hour uninterrupted operation strategy, lacking dynamic sensing capabilities for operating periods, passenger flow density, and regional importance, resulting in a large amount of energy being wasted during unnecessary periods, significantly increasing the overall operating cost of the system. Especially in the night shutdown or low passenger flow section, the monitoring devices still maintain full load working state, causing serious energy waste, which is contrary to the current green and low-carbon smart city development concept.

[0003] Currently, intelligent power management technology has become a core direction to improve the energy efficiency and response capability of city rail video monitoring systems. This technology aims to achieve fine regulation and control of front-end device power supply behavior through state sensing, strategy scheduling, and remote control means. Its basic goal is to dynamically adjust device operating modes according to actual business needs while ensuring safety monitoring coverage, thereby achieving intelligent upgrading of the system in multiple dimensions such as energy saving, emergency response, and fault self-healing.

[0004] However, the existing power management system has multiple structural defects in terms of intelligence level. First, its power supply strategy is rigid and cannot adaptively switch device operating states based on time, train operation diagrams, or regional risk levels, making it difficult to transition from "continuous power supply" to "on-demand power supply". Second, in emergency response scenarios, the system lacks deep linkage capabilities with third-party subsystems such as fire alarms and access control, and can only perform coarse-grained power-on or power-off operations, making it impossible to accurately activate specific cameras based on event type, location, and severity level, severely restricting the timeliness and specificity of emergency response. In addition, the discovery of device faults (such as freezing or image lag) relies on manual inspection or passive reporting, and maintenance personnel need to restart the device on site, which not only is inefficient but also creates a monitoring blind spot during the fault period, posing potential safety risks. Therefore, there is an urgent need for a city rail video monitoring intelligent power management and control method and system that integrates dynamic energy saving, intelligent linkage, and automatic maintenance to overcome the comprehensive bottlenecks in energy efficiency, response, and reliability of existing technologies. SUMMARY

[0005] In view of the deficiencies of the prior art, the application provides an intelligent power management and control system for a city rail video monitoring system, which optimizes a power supply strategy through dynamic modeling and multi-dimensional data analysis, improves the power supply reliability and intelligent level of the city rail video monitoring system, and reduces energy consumption and fault risk.

[0006] In a first aspect, the application provides an intelligent power management and control method for a city rail video monitoring system, comprising: S100, collecting running state data of a front-end monitoring device, train operation diagram information, and regional risk level data; S200, constructing a dynamic power supply strategy model based on the running state data, the train operation diagram information, and the regional risk level data, and simulating power supply demand changes of the monitoring device in different scenarios; S300, matching the real-time collected running state data, train operation diagram information, and regional risk level data with the dynamic power supply strategy model, and identifying abnormal behaviors deviating from an expected power supply mode; S400, for the abnormal behaviors, extracting power spectral density characteristic quantities representing device energy consumption fluctuation characteristics from the running state data, and extracting time window priority characteristic quantities representing emergency degrees of events from the regional risk level data; S500, calculating a weighted difference value of the power spectral density characteristic quantities and the time window priority characteristic quantities, and determining a potential fault or an emergency demand if the weighted difference value exceeds a preset range; S600, when determining the potential fault or the emergency demand, starting a hierarchical power supply mechanism and implementing precise power supply regulation based on a device identification code, user operation records, and environmental parameters.

[0007] Preferably, the S100 comprises: collecting device power supply data through a high-precision sensor; analyzing train arrival time sequences and section operation plans in the train operation diagram; simultaneously capturing safety event type distributions and risk weight coefficients in the regional risk level data through a regional risk assessment module.

[0008] Preferably, the S200 comprises: based on device working current, voltage fluctuation data, and power consumption curves in the running state data, generating a device energy consumption prediction model through a load characteristic equation to simulate power supply demands of the monitoring device under different load conditions; based on train arrival time sequences and section operation plans in the train operation diagram information, generating time axis power supply scheduling rules to simulate power supply switching logic of the monitoring device in a train operation cycle; A risk response matrix is established based on the safety event type distribution and risk weight coefficient in the regional risk level data, to simulate the power supply priority allocation of the monitoring device under different risk levels. The device energy consumption prediction model, the time axis power supply scheduling rule and the risk response matrix are cooperatively integrated to generate a dynamic power supply strategy model.

[0009] Preferably, the S300 comprises: The device working current, voltage fluctuation data and power consumption curve in the real-time collected operation state data are input into the device energy consumption prediction model to calculate a first deviation value between the actual energy consumption and the predicted energy consumption; The train arrival time sequence in the real-time collected train working diagram and the interval operation plan are input into the time axis power supply scheduling rule to detect a second deviation value between the actual power supply switching logic and the expected switching logic; The safety event type distribution and risk weight coefficient in the real-time collected regional risk level data are input into the risk response matrix to evaluate a third deviation value between the actual power supply priority allocation and the expected priority allocation; When the first deviation value exceeds the energy consumption tolerance range, or the second deviation value exceeds the switching logic tolerance range, or the third deviation value exceeds the priority allocation tolerance range, the corresponding behavior is marked as an abnormal behavior deviating from the expected power supply mode.

[0010] Preferably, the S400 comprises: For the operation state data in the abnormal behavior deviating from the expected power supply mode, the frequency domain characteristics of the device working current and voltage fluctuation data are analyzed, and the maximum peak value of the power spectral density is calculated as a power spectral density characteristic quantity; For the regional risk level data in the abnormal behavior deviating from the expected power supply mode, the cumulative integral value of the risk weight coefficient is calculated on the time axis of the safety event type distribution to obtain a time window priority characteristic quantity.

[0011] Preferably, the S500 comprises: The maximum peak value in the power spectral density characteristic quantity and the cumulative integral value in the time window priority characteristic quantity are normalized; The difference scalar of the normalized maximum peak value and the cumulative integral value is calculated by a weighting operator as a weighted difference value; When the weighted difference value exceeds a pre-set numerical range, it is determined as a potential fault or an emergency demand.

[0012] Preferably, the S600 comprises: When it is determined as a potential fault or an emergency demand, a start process of a hierarchical power supply mechanism is triggered; A device identification code is generated based on the device working current in the operation state data; Extract operation behavior sequence based on user operation record in abnormal behavior deviating from expected power supply mode; Construct environment parameter distribution map based on maximum peak value in power spectrum density feature quantity; Formulate precise power supply regulation rule according to device identification code, operation behavior sequence and environment parameter distribution map; Adjust power supply state of monitoring device by executing precise power supply regulation rule through hierarchical power supply mechanism.

[0013] In the second aspect, the application further provides an intelligent power management and control system for a city rail video monitoring system, which applies the intelligent power management and control method for the city rail video monitoring system as described above, and the system comprises a data acquisition unit, a strategy construction unit, an abnormality identification unit, a feature extraction unit, a demand determination unit and a power supply regulation unit. The data acquisition unit is used to acquire running state data of front-end monitoring devices, train working diagrams and regional risk level data. The strategy construction unit is used to construct a dynamic power supply strategy model based on the running state data, the train working diagrams and the regional risk level data, and simulate power supply demand changes of the monitoring devices under different scenarios. The abnormality identification unit is used to match the real-time acquired running state data, train working diagrams and regional risk level data with the dynamic power supply strategy model, and identify abnormal behaviors deviating from expected power supply mode. The feature extraction unit is used to extract power spectrum density feature quantities representing device energy consumption fluctuation characteristics from the running state data, and extract time window priority feature quantities representing emergency degree of events from the regional risk level data, for the abnormal behaviors. The demand determination unit is used to calculate weighted difference values of the power spectrum density feature quantities and the time window priority feature quantities, and determine as potential faults or emergency demands if the weighted difference values exceed a preset range. The power supply regulation unit is used to start a hierarchical power supply mechanism and implement precise power supply regulation based on device identification codes, user operation records and environment parameters when determining as potential faults or emergency demands.

[0014] Compared with the prior art, the application has the following advantages and beneficial effects: The application adaptively adjusts power supply strategies of front-end monitoring devices based on train working plans, passenger flow changes, regional risk levels and other multi-dimensional information, realizes a change from continuous power supply to on-demand power supply, thereby greatly reduces invalid energy consumption in off-peak periods or low-risk areas, effectively improves system energy efficiency, and meets the development needs of green and low-carbon smart cities.

[0015] The application ensures that key monitoring equipment can be quickly and accurately activated in an emergency scenario, and enhances the timeliness and pertinence of the overall safety response, by means of multi-system intelligent linkage capability, deep integration of third-party subsystems such as fire alarm and access control, dynamic optimization of power supply priority according to event type, location and severity.

[0016] The application reduces the dependence on manual inspection, significantly shortens the fault handling time, and avoids the formation of monitoring blind spots, by introducing a fault self-healing mechanism, real-time monitoring of device operating status, automatic identification of abnormal behavior and triggering of hierarchical power supply regulation, thereby improving the automation level and reliability of system operation and maintenance.

[0017] Overall, the application realizes collaborative optimization in terms of energy saving, emergency linkage and operation and maintenance efficiency, and provides a solid support for the intelligent upgrading of urban rail video monitoring systems. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a flowchart of an intelligent power management and control method for an urban rail video monitoring system.

[0019] Figure 2 is a block diagram of an intelligent power management and control system for an urban rail video monitoring system. DETAILED DESCRIPTION

[0020] The technical solutions of the application will be described below in conjunction with embodiments, obviously, the described embodiments are only some of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the application. It should be noted that the relationship 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 sequence between the entities or operations.

[0021] Embodiment 1 Please refer to Figure 1 The application provides an intelligent power management and control method for an urban rail video monitoring system, which will be further described in detail in conjunction with specific embodiments.

[0022] Currently, under the background of continuous expansion of urban rail transit network, as the core infrastructure to ensure the safety of operation, the front-end camera devices of the video monitoring system are generally deployed in outdoor equipment boxes and rely on centralized power management systems for unified power supply. The traditional power supply architecture adopts an all-weather uninterrupted operation mode, lacks dynamic perception and response capability to the operation period, passenger flow changes and regional risk level, and leads to a large amount of power being wasted during non-peak or shutdown periods. At the same time, the existing power management scheme lacks deep protocol interworking and rule-driven mechanism with third-party systems such as fire alarm and access control in emergency linkage, can only perform coarse-grained line power-on and power-off operations, and cannot wake up specific cameras according to event type and location. In addition, device failures rely on manual inspection or passive alarm to be discovered, and the operation and maintenance response is lagging and prone to form a monitoring blind area. In view of the above technical problems, the present application proposes an intelligent power management and control method integrating dynamic energy-saving regulation, multi-system intelligent linkage and fault self-healing capability.

[0023] In practical applications, first, the running state data of the front-end monitoring device, the train operation diagram and the regional risk level data are collected; wherein, the device power supply data (voltage fluctuation data, working current and power consumption curve) is collected through high-precision sensors, and the train arrival time sequence and interval operation plan in the train operation diagram are analyzed, and at the same time, the safety event type distribution and risk weight coefficient in the regional risk level data are captured through the regional risk assessment module. The collection process of these data needs to ensure high precision and real-time performance to ensure the accuracy of subsequent analysis. For example, in the monitoring scene of the urban rail station, the working current of each monitoring camera is periodically sampled, and the voltage fluctuation is recorded, and at the same time, the corresponding time axis data is generated combining the train arrival time sequence of the train operation diagram. In addition, the regional risk assessment module dynamically updates the safety event type distribution of different regions in the station, thereby providing basic data support for the subsequent risk response matrix.

[0024] Then, a dynamic power supply strategy model is constructed based on the collected operation state data, train operation diagram and regional risk level data; the dynamic power supply strategy model includes a device energy consumption prediction model, a time axis power supply scheduling rule and a risk response matrix; wherein the device energy consumption prediction model is generated by a load characteristic equation, and the device working current, voltage fluctuation data and power consumption curve in the operation state data are used to simulate the power supply demand of the monitoring device under different load conditions. For example, for a monitoring camera with a power of 50W, the expected energy consumption value under different load conditions can be calculated according to its historical power consumption curve, and the corresponding energy consumption prediction model is generated. The time axis power supply scheduling rule is generated based on the train arrival time sequence in the train operation diagram and the interval operation plan, which is used to simulate the power supply switching logic of the monitoring device in the train operation cycle. For example, when the train is about to arrive at the station, the power supply priority of the monitoring device can be adjusted according to the train operation diagram to ensure that the monitoring device in the key area can obtain stable power supply. The risk response matrix is established based on the safety event type distribution and risk weight coefficient in the regional risk level data, which is used to simulate the power supply priority allocation of the monitoring device under different risk levels. For example, when an emergency event occurs at the station, the risk response matrix will dynamically adjust the power supply priority of the monitoring device according to the risk weight coefficient of the event, to ensure that the devices in the high-risk area are given priority to power support. Finally, the device energy consumption prediction model, the time axis power supply scheduling rule and the risk response matrix are integrated to generate a complete dynamic power supply strategy model.

[0025] After the dynamic power supply strategy model is generated, the real-time collected operation state data, train operation diagram information and regional risk level data are matched with the dynamic power supply strategy model to identify abnormal behaviors deviating from the expected power supply mode. Specifically, the device working current, voltage fluctuation data and power consumption curve in the real-time collected operation state data are input into the device energy consumption prediction model to calculate the first deviation value between the actual energy consumption and the predicted energy consumption; at the same time, the train arrival time sequence in the real-time collected train operation diagram and the interval operation plan are input into the time axis power supply scheduling rule to detect the second deviation value between the actual power supply switching logic and the expected switching logic; then, the safety event type distribution and risk weight coefficient in the real-time collected regional risk level data are input into the risk response matrix to evaluate the third deviation value between the actual power supply priority allocation and the expected priority allocation. When the first deviation value exceeds the energy consumption tolerance range, or the second deviation value exceeds the switching logic tolerance range, or the third deviation value exceeds the priority allocation tolerance range, the corresponding behavior is marked as an abnormal behavior deviating from the expected power supply mode. For example, when the actual power consumption of a certain monitoring camera exceeds the predicted value by more than 10%, it is marked as an abnormal behavior, and the subsequent processing process is triggered.

[0026] For abnormal behavior, power spectral density features representing energy consumption fluctuation characteristics of devices can be extracted from operational state data, and time window priority features representing emergency degree of events can be extracted from regional risk level data. Specifically, for operational state data in abnormal behavior deviating from expected power supply mode, frequency domain characteristics of device working current and voltage fluctuation data are analyzed, and the maximum peak value of power spectral density is calculated as a power spectral density feature. For example, for current fluctuation data of a certain monitoring camera, its power spectral density is calculated by fast Fourier transform algorithm, and the maximum peak value is extracted as a feature. For regional risk level data in abnormal behavior deviating from expected power supply mode, the cumulative integral value of risk weight coefficient is calculated on the time axis of security event type distribution, and the time window priority feature is obtained. For example, when an emergency event occurs in a certain area, the cumulative integral value is calculated according to the distribution of the risk weight coefficient of the event on the time axis, and it is taken as the time window priority feature.

[0027] Subsequently, the weighted difference value of the power spectral density feature and the time window priority feature is calculated, and it is determined whether it exceeds the preset range. Specifically, the maximum peak value in the power spectral density feature and the cumulative integral value in the time window priority feature are normalized, and the difference scalar of the normalized maximum peak value and the cumulative integral value is calculated by a weighting operator as a weighted difference value. For example, for a certain monitoring camera, the maximum peak value of its power spectral density is 0.8, and the cumulative integral value of the time window priority feature is 0.6. The difference scalar of the two is calculated by a weighting operator, and it is determined whether it exceeds the preset numerical range. When the weighted difference value exceeds the preset range, it is determined as potential failure or emergency demand.

[0028] Finally, when it is determined as potential failure or emergency demand, the hierarchical power supply mechanism is started, and precise power supply regulation is implemented based on device identification code, user operation record and environmental parameters. Specifically, the device identification code is generated based on the device working current in the operational state data, and the operation behavior sequence is extracted based on the user operation record in the abnormal behavior deviating from the expected power supply mode. For example, for a certain monitoring camera, a unique device identification code is generated according to its working current, and the operation behavior sequence of the user is recorded; at the same time, the environmental parameter distribution map is constructed based on the maximum peak value in the power spectral density feature, and the precise power supply regulation rule is formulated according to the device identification code, the operation behavior sequence and the environmental parameter distribution map. For example, when a certain monitoring camera is determined as potential failure, its power supply state is adjusted according to its device identification code and environmental parameter distribution map to ensure that it can maintain basic functions in the minimum power consumption mode; in addition, the precise power supply regulation rule is executed through the hierarchical power supply mechanism to adjust the power supply state of the monitoring device. For example, when an emergency event occurs in a certain area, stable power support is provided to the monitoring devices in high-risk areas, while the power supply priority of the devices in low-risk areas is reduced.

[0029] In practical application scenarios, the specific embodiments of the present application can significantly improve the power management efficiency of the urban rail video monitoring system. For example, in a subway station in a certain city, the monitoring system covers multiple areas such as platforms, waiting areas, entrances and exits. Through the intelligent power management and control method and system provided by the present application, the station management personnel can monitor the running state of each monitoring device in real time, and dynamically adjust the power supply strategy according to the train operation diagram and regional risk level data. During the peak period of train arrival, the system will preferentially provide stable power support for the monitoring devices in the platform area, while in the off-peak period, the power supply priority will be appropriately reduced to save energy. In addition, in the event of an emergency, the system can quickly identify high-risk areas and preferentially provide power support for their monitoring devices, thereby ensuring that the monitoring function of the key area is not affected.

[0030] Embodiment 2 Please refer to Figure 2 The embodiment provides an intelligent power management and control method and system for an urban rail video monitoring system, which applies the intelligent power management and control method for the urban rail video monitoring system as described above, characterized in that: the system comprises a data acquisition unit, a strategy construction unit, an abnormality identification unit, a feature extraction unit, a demand determination unit and a power supply regulation unit. The data acquisition unit is used to acquire running state data of front-end monitoring devices, train operation diagrams and regional risk level data. The strategy construction unit is used to construct a dynamic power supply strategy model based on the running state data, the train operation diagram and the regional risk level data, and simulate the power supply demand changes of the monitoring devices in different scenarios. The abnormality identification unit is used to match the real-time acquired running state data, train operation diagram and regional risk level data with the dynamic power supply strategy model, and identify abnormal behaviors deviating from the expected power supply mode. The feature extraction unit is used to extract, from the running state data, power spectral density feature quantities representing device energy consumption fluctuation characteristics, and from the regional risk level data, time window priority feature quantities representing event emergency degree, for the abnormal behaviors. The demand determination unit is used to calculate the weighted difference value of the power spectral density feature quantities and the time window priority feature quantities, and if the weighted difference value exceeds the preset range, it is determined as a potential fault or emergency demand. The power supply regulation unit is used to start a hierarchical power supply mechanism and implement precise power supply regulation based on device identification codes, user operation records and environmental parameters when a potential fault or emergency demand is determined.

[0031] Embodiment 3 In order to better enable the relevant personnel in the technical field to fully understand and implement the present application, the specific implementation principles of the present application are further supplemented below in conjunction with a specific application scenario.

[0032] In a subway station in a certain city, the monitoring system covers multiple areas such as platforms, waiting areas, entrances and exits. Through the intelligent power management and control method and system provided by the present application, the station management personnel can monitor the running state of each monitoring device in real time, and dynamically adjust the power supply strategy according to the train operation diagram information and regional risk level data. The following will combine the module structure and its connection relationship in the accompanying Figure 1 to the accompanying Figure 2 illustrate the running steps and implementation principles of the system.

[0033] Firstly, the data acquisition unit obtains the working current, voltage fluctuation data and power consumption curve of the front-end monitoring device in real time through the current sensor. For example, in the monitoring camera in the platform area, the data acquisition unit will sample its working current at a fixed period and record the voltage fluctuation. At the same time, the data acquisition unit analyzes the train arrival time sequence and interval operation plan in the train operation diagram to generate corresponding time axis data. In addition, the regional risk assessment module dynamically updates the safety event type distribution of different areas in the station, thereby providing basic data support for the subsequent risk response matrix. The data acquisition process ensures high precision and real-time performance, providing a reliable basis for subsequent analysis.

[0034] Next, the strategy construction unit constructs a dynamic power supply strategy model based on the above collected data. The strategy construction unit first generates a device energy consumption prediction model using the load characteristic equation. For example, for a monitoring camera with a power of 50W, the strategy construction unit calculates the expected energy consumption value under different load conditions according to its historical power consumption curve, and generates a corresponding energy consumption prediction model. Subsequently, the strategy construction unit generates time axis power supply scheduling rules based on the train arrival time sequence and interval operation plan in the train operation diagram information. For example, when the train is about to arrive, the strategy construction unit will adjust the power supply priority of the monitoring device according to the train operation diagram information to ensure that the monitoring device in the key area can obtain stable power supply. In addition, the strategy construction unit also establishes a risk response matrix based on the safety event type distribution and risk weight coefficient in the regional risk level data. For example, when an emergency occurs in the station, the risk response matrix will dynamically adjust the power supply priority of the monitoring device according to the risk weight coefficient of the event to ensure that the device in the high-risk area is given priority to power support. Finally, the strategy construction unit integrates the device energy consumption prediction model, time axis power supply scheduling rules and risk response matrix to generate a complete dynamic power supply strategy model.

[0035] After the dynamic power supply strategy model is generated, the anomaly identification unit is responsible for matching the real-time collected operation state data, train operation diagram and regional risk level data with the dynamic power supply strategy model to identify abnormal behaviors deviating from the expected power supply mode. Specifically, the anomaly identification unit inputs the device working current, voltage fluctuation data and power consumption curve in the real-time collected operation state data into the device energy consumption prediction model, calculates the first deviation value between the actual energy consumption and the predicted energy consumption; at the same time, the train arrival time sequence in the real-time collected train operation diagram information and the interval operation plan are input into the time axis power supply scheduling rule to detect the second deviation value between the actual power supply switching logic and the expected switching logic; in addition, the safety event type distribution and risk weight coefficient in the real-time collected regional risk level data are input into the risk response matrix to evaluate the third deviation value between the actual power supply priority allocation and the expected priority allocation. When the first deviation value exceeds the energy consumption tolerance range, or the second deviation value exceeds the switching logic tolerance range, or the third deviation value exceeds the priority allocation tolerance range, the anomaly identification unit will mark the corresponding behavior as an abnormal behavior deviating from the expected power supply mode. For example, when the actual power consumption of a certain monitoring camera exceeds the predicted value by more than 10%, the anomaly identification unit will mark it as an abnormal behavior and trigger the subsequent processing process.

[0036] For abnormal behaviors, the feature extraction unit extracts power spectrum density feature quantities representing device energy consumption fluctuation characteristics from operation state data, and extracts time window priority feature quantities representing event emergency degree from regional risk level data. Specifically, for the operation state data in the abnormal behavior deviating from the expected power supply mode, the feature extraction unit analyzes the frequency domain characteristics of the device working current and voltage fluctuation data, and calculates the maximum peak value of the power spectrum density as the power spectrum density feature quantity. For example, for the current fluctuation data of a certain monitoring camera, the feature extraction unit will calculate its power spectrum density through the fast Fourier transform algorithm, and extract the maximum peak value as the feature quantity. For the regional risk level data in the abnormal behavior deviating from the expected power supply mode, the feature extraction unit calculates the cumulative integral value of the risk weight coefficient on the time axis of the safety event type distribution to obtain the time window priority feature quantity. For example, when an emergency event occurs in a certain region, the feature extraction unit will calculate the cumulative integral value according to the distribution of the risk weight coefficient of the event on the time axis, and take it as the time window priority feature quantity.

[0037] Subsequently, the demand determination unit calculates a weighted difference value of the power spectral density feature quantity and the time window priority feature quantity, and determines whether it exceeds a preset range. Specifically, the demand determination unit normalizes the maximum peak value in the power spectral density feature quantity and the cumulative integral value in the time window priority feature quantity, and calculates the difference scalar of the normalized maximum peak value and the cumulative integral value as the weighted difference value through a weighting operator. For example, for a certain monitoring camera, the maximum peak value of the power spectral density is 0.8, and the cumulative integral value of the time window priority feature quantity is 0.6. The demand determination unit calculates the difference scalar of the two through a weighting operator, and determines whether it exceeds a preset numerical range. When the weighted difference value exceeds the preset range, the demand determination unit determines that there is a potential fault or an emergency demand, and triggers the subsequent hierarchical power supply mechanism.

[0038] Finally, the power supply regulation unit starts the hierarchical power supply mechanism when it determines that there is a potential fault or an emergency demand, and implements precise power supply regulation based on the device identification code, user operation record and environmental parameter. Specifically, the power supply regulation unit generates a device identification code based on the device operating current in the operating state data, and extracts an operation behavior sequence based on the user operation record in the abnormal behavior deviating from the expected power supply mode. For example, for a certain monitoring camera, the power supply regulation unit generates a unique device identification code according to its operating current, and records the operation behavior sequence of the user. At the same time, the power supply regulation unit constructs an environmental parameter distribution map based on the maximum peak value in the power spectral density feature quantity, and formulates precise power supply regulation rules according to the device identification code, operation behavior sequence and environmental parameter distribution map. For example, when a certain monitoring camera is determined to have a potential fault, the power supply regulation unit adjusts its power supply state according to its device identification code and environmental parameter distribution map to ensure that it can maintain basic functions in the lowest power consumption mode. In addition, the power supply regulation unit also executes the precise power supply regulation rules through the hierarchical power supply mechanism to adjust the power supply state of the monitoring device. For example, when an emergency occurs in a certain area, the power supply regulation unit will prioritize providing stable power support to the monitoring devices in high-risk areas, while reducing the power supply priority of the devices in low-risk areas.

[0039] In this embodiment, the data acquisition unit, the policy construction unit, the anomaly identification unit, the feature extraction unit, the demand determination unit and the power supply regulation unit are tightly connected through data flow and control flow. The data acquisition unit transmits the collected data to the policy construction unit, the dynamic power supply strategy model generated by the policy construction unit is called by the anomaly identification unit, the identification result of the anomaly identification unit is transmitted to the feature extraction unit, the feature quantity extracted by the feature extraction unit is used for weighted difference value calculation by the demand determination unit, and the determination result of the demand determination unit triggers the hierarchical power supply mechanism of the power supply regulation unit. This modular structure design makes the whole system have high flexibility and scalability, which can adapt to the changes of power supply demand in different scenarios.

[0040] Through the above steps, the present application achieves significant technical effects in practical application. For example, during the peak period of train arrival at the station, the system will prioritize providing stable power support for monitoring devices in the platform area, while appropriately reducing the power supply priority during off-peak hours to save energy. In addition, in the event of an emergency, the system can quickly identify high-risk areas and prioritize power support for their monitoring devices, ensuring that the monitoring function of critical areas is not affected. This process is achieved through the precise simulation of the dynamic power supply strategy model, real-time identification of abnormal behavior, and precise regulation of the hierarchical power supply mechanism, effectively improving the power management efficiency of the urban rail video monitoring system.

[0041] The contents not described in detail in the specification are all existing technologies known to those skilled in the art, and the model parameters of each electric appliance are not specifically limited and can be used with conventional equipment. In the present technical solution, the electric appliance control elements not mentioned belong to existing technologies and are not shown in the drawings, and will not be described here.

[0042] The above only describes the preferred embodiments of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A method for intelligent power management and control in urban rail video surveillance systems, characterized in that, include: S100: Collect operational status data from front-end monitoring equipment, train schedules, and regional risk level data; S200: Based on operational status data, train operation diagram information, and regional risk level data, a dynamic power supply strategy model is constructed to simulate the changes in power supply demand of monitoring equipment under different scenarios. S300 matches real-time collected operational status data, train operation diagram information, and regional risk level data with the dynamic power supply strategy model to identify abnormal behaviors that deviate from the expected power supply mode. S400. For abnormal behavior, extract the power spectral density feature quantity that characterizes the energy consumption fluctuation characteristics of the equipment from the operating status data, and extract the time window priority feature quantity that characterizes the urgency of the event from the regional risk level data. S500: Calculate the weighted difference between the power spectral density characteristic and the time window priority characteristic. If the weighted difference exceeds the preset range, it is determined to be a potential fault or emergency requirement. When S600 determines a potential fault or emergency need, it activates a tiered power supply mechanism and implements precise power supply control based on equipment identification codes, user operation records, and environmental parameters.

2. The intelligent power management and control method for urban rail video surveillance system according to claim 1, characterized in that: The S100 includes: The device power supply data is collected using high-precision sensors; Analyze the train arrival time sequence and section operation plan in the train timetable; At the same time, the regional risk assessment module captures the distribution of security event types and risk weight coefficients in the regional risk level data.

3. The intelligent power management and control method for urban rail video surveillance system according to claim 2, characterized in that: The S200 includes: Based on the equipment's operating current, voltage fluctuation data, and power consumption curves in the operating status data, an equipment energy consumption prediction model is generated through load characteristic equations to simulate the power supply requirements of the monitoring equipment under different load conditions. Based on the train arrival time sequence and section operation plan in the train timetable information, a time axis power supply scheduling rule is generated to simulate the power supply switching logic of the monitoring equipment during the train operation cycle. Based on the distribution of security event types and risk weight coefficients in regional risk level data, a risk response matrix is ​​established to simulate the power supply priority allocation of monitoring equipment under different risk levels. By integrating the equipment energy consumption prediction model, time-axis power supply scheduling rules, and risk response matrix, a dynamic power supply strategy model is generated.

4. The intelligent power management and control method for urban rail video surveillance system according to claim 3, characterized in that: The S300 includes: Input the equipment operating current, voltage fluctuation data and power consumption curve from the real-time collected operating status data into the equipment energy consumption prediction model to calculate the first deviation value between the actual energy consumption and the predicted energy consumption. The train arrival time series and section operation plan from the real-time collected train time map are input into the time axis power supply scheduling rules to detect the second deviation value between the actual power supply switching logic and the expected switching logic. The distribution of safety event types and risk weight coefficients in the real-time collected regional risk level data are input into the risk response matrix to evaluate the third deviation value between the actual power supply priority allocation and the expected priority allocation. When the first deviation value exceeds the energy consumption tolerance range, or the second deviation value exceeds the switching logic tolerance range, or the third deviation value exceeds the priority allocation tolerance range, the corresponding behavior is marked as an abnormal behavior that deviates from the expected power supply mode.

5. The intelligent power management and control method for an urban rail video surveillance system according to claim 4, characterized in that: The S400 includes: For the operating status data of abnormal behavior that deviates from the expected power supply mode, analyze the frequency domain characteristics of the equipment operating current and voltage fluctuation data, and calculate the maximum peak value of the power spectral density as the power spectral density characteristic quantity. For regional risk level data in abnormal behaviors that deviate from the expected power supply mode, the cumulative integral value of the risk weight coefficient is calculated on the time axis of the safety event type distribution to obtain the time window priority feature.

6. The intelligent power management and control method for an urban rail video surveillance system according to claim 5, characterized in that: The S500 includes: The maximum peak value in the power spectral density characteristic and the cumulative integral value in the time window priority characteristic are normalized. The difference scalar between the normalized maximum peak value and the cumulative integral value is calculated using a weighted operator and used as the weighted difference value. When the weighted difference value exceeds the preset numerical range, it is determined to be a potential fault or emergency requirement.

7. The intelligent power management and control method for an urban rail video surveillance system according to claim 6, characterized in that: The S600 includes: When a potential fault or emergency demand is identified, the tiered power supply mechanism is activated. Generate device identification code based on device operating current in operating status data; Extracting operation behavior sequences from user operation records based on abnormal behavior that deviates from the expected power supply mode; Construct an environmental parameter distribution map based on the maximum peak value in the power spectral density characteristic quantity; Develop precise power supply control rules based on equipment identification codes, operating behavior sequences, and environmental parameter distribution maps; A tiered power supply mechanism is used to implement precise power supply control rules and adjust the power supply status of monitoring equipment.

8. An intelligent power management and control system for urban rail video surveillance systems, employing the intelligent power management and control method for urban rail video surveillance systems as described in claims 1-7, characterized in that: The system includes a data acquisition unit, a strategy construction unit, an anomaly identification unit, a feature extraction unit, a demand determination unit, and a power supply control unit. The data acquisition unit is used to collect operating status data of the front-end monitoring equipment, train operation diagrams, and regional risk level data; The strategy construction unit is used to build a dynamic power supply strategy model based on operational status data, train operation diagrams and regional risk level data, and to simulate the changes in power supply demand of monitoring equipment under different scenarios. The anomaly identification unit is used to match the real-time collected operating status data, train operation diagram and regional risk level data with the dynamic power supply strategy model to identify abnormal behaviors that deviate from the expected power supply mode. The feature extraction unit is used to extract power spectral density features that characterize the energy consumption fluctuation characteristics of equipment from the operating status data for abnormal behavior, and to extract time window priority features that characterize the urgency of events from the regional risk level data. The demand determination unit is used to calculate the weighted difference value between the power spectral density feature and the time window priority feature. If the weighted difference value exceeds the preset range, it is determined to be a potential fault or emergency demand. When a potential fault or emergency demand is detected, the power supply control unit is used to activate a tiered power supply mechanism and implement precise power supply control based on the equipment identification code, user operation records, and environmental parameters.

Images